diff options
Diffstat (limited to 'arch/x86')
618 files changed, 24289 insertions, 21943 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 222855cc0158..beea77046f9b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -24,7 +24,7 @@ config X86_64 depends on 64BIT # Options that are inherently 64-bit kernel only: select ARCH_HAS_GIGANTIC_PAGE - select ARCH_SUPPORTS_INT128 + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 select ARCH_USE_CMPXCHG_LOCKREF select HAVE_ARCH_SOFT_DIRTY select MODULES_USE_ELF_RELA @@ -68,11 +68,11 @@ config X86 select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 + select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL - select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE select ARCH_HAS_SET_MEMORY @@ -93,10 +93,11 @@ config X86 select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH + select ARCH_WANT_DEFAULT_BPF_JIT if X86_64 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_HUGE_PMD_SHARE select ARCH_WANTS_THP_SWAP if X86_64 - select BUILDTIME_EXTABLE_SORT + select BUILDTIME_TABLE_SORT select CLKEVT_I8253 select CLOCKSOURCE_VALIDATE_LAST_CYCLE select CLOCKSOURCE_WATCHDOG @@ -119,11 +120,13 @@ config X86 select GENERIC_IRQ_RESERVATION_MODE select GENERIC_IRQ_SHOW select GENERIC_PENDING_IRQ if SMP + select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY + select GENERIC_VDSO_TIME_NS select GUP_GET_PTE_LOW_HIGH if X86_PAE select HARDLOCKUP_CHECK_TIMESTAMP if X86_64 select HAVE_ACPI_APEI if ACPI @@ -134,6 +137,7 @@ config X86 select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if X86_64 + select HAVE_ARCH_KASAN_VMALLOC if X86_64 select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT @@ -147,6 +151,7 @@ config X86 select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64 select HAVE_ARCH_VMAP_STACK if X86_64 select HAVE_ARCH_WITHIN_STACK_FRAMES + select HAVE_ASM_MODVERSIONS select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL select HAVE_CONTEXT_TRACKING if X86_64 @@ -156,6 +161,7 @@ config X86 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EISA @@ -197,7 +203,7 @@ config X86 select HAVE_PCI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_RCU_TABLE_FREE if PARAVIRT + select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_FUNCTION_ARG_ACCESS_API @@ -436,8 +442,8 @@ config X86_MPPARSE (esp with 64bit cpus) with acpi support, MADT and DSDT will override it config GOLDFISH - def_bool y - depends on X86_GOLDFISH + def_bool y + depends on X86_GOLDFISH config RETPOLINE bool "Avoid speculative indirect branches in kernel" @@ -453,6 +459,7 @@ config X86_CPU_RESCTRL bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) select KERNFS + select PROC_CPU_RESCTRL if PROC_FS help Enable x86 CPU resource control support. @@ -474,7 +481,7 @@ config X86_BIGSMP bool "Support for big SMP systems with more than 8 CPUs" depends on SMP ---help--- - This option is needed for the systems that have more than 8 CPUs + This option is needed for the systems that have more than 8 CPUs. config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" @@ -558,9 +565,9 @@ config X86_UV # Please maintain the alphabetic order if and when there are additions config X86_GOLDFISH - bool "Goldfish (Virtual Platform)" - depends on X86_EXTENDED_PLATFORM - ---help--- + bool "Goldfish (Virtual Platform)" + depends on X86_EXTENDED_PLATFORM + ---help--- Enable support for the Goldfish virtual platform used primarily for Android development. Unless you are building for the Android Goldfish emulator say N here. @@ -706,7 +713,6 @@ config X86_SUPPORTS_MEMORY_FAILURE config STA2X11 bool "STA2X11 Companion Chip Support" depends on X86_32_NON_STANDARD && PCI - select ARCH_HAS_PHYS_TO_DMA select SWIOTLB select MFD_STA2X11 select GPIOLIB @@ -794,6 +800,7 @@ config KVM_GUEST bool "KVM Guest support (including kvmclock)" depends on PARAVIRT select PARAVIRT_CLOCK + select ARCH_CPUIDLE_HALTPOLL default y ---help--- This option enables various optimizations for running under the KVM @@ -802,6 +809,12 @@ config KVM_GUEST underlying device model, the host provides the guest with timing infrastructure such as time of day, and system time +config ARCH_CPUIDLE_HALTPOLL + def_bool n + prompt "Disable host haltpoll when loading haltpoll driver" + help + If virtualized under KVM, disable host haltpoll. + config PVH bool "Support for running PVH guests" ---help--- @@ -878,16 +891,16 @@ config HPET_EMULATE_RTC depends on HPET_TIMER && (RTC=y || RTC=m || RTC_DRV_CMOS=m || RTC_DRV_CMOS=y) config APB_TIMER - def_bool y if X86_INTEL_MID - prompt "Intel MID APB Timer Support" if X86_INTEL_MID - select DW_APB_TIMER - depends on X86_INTEL_MID && SFI - help - APB timer is the replacement for 8254, HPET on X86 MID platforms. - The APBT provides a stable time base on SMP - systems, unlike the TSC, but it is more expensive to access, - as it is off-chip. APB timers are always running regardless of CPU - C states, they are used as per CPU clockevent device when possible. + def_bool y if X86_INTEL_MID + prompt "Intel MID APB Timer Support" if X86_INTEL_MID + select DW_APB_TIMER + depends on X86_INTEL_MID && SFI + help + APB timer is the replacement for 8254, HPET on X86 MID platforms. + The APBT provides a stable time base on SMP + systems, unlike the TSC, but it is more expensive to access, + as it is off-chip. APB timers are always running regardless of CPU + C states, they are used as per CPU clockevent device when possible. # Mark as expert because too many people got it wrong. # The code disables itself when not needed. @@ -923,36 +936,6 @@ config GART_IOMMU If unsure, say Y. -config CALGARY_IOMMU - bool "IBM Calgary IOMMU support" - select IOMMU_HELPER - select SWIOTLB - depends on X86_64 && PCI - ---help--- - Support for hardware IOMMUs in IBM's xSeries x366 and x460 - systems. Needed to run systems with more than 3GB of memory - properly with 32-bit PCI devices that do not support DAC - (Double Address Cycle). Calgary also supports bus level - isolation, where all DMAs pass through the IOMMU. This - prevents them from going anywhere except their intended - destination. This catches hard-to-find kernel bugs and - mis-behaving drivers and devices that do not use the DMA-API - properly to set up their DMA buffers. The IOMMU can be - turned off at boot time with the iommu=off parameter. - Normally the kernel will make the right choice by itself. - If unsure, say Y. - -config CALGARY_IOMMU_ENABLED_BY_DEFAULT - def_bool y - prompt "Should Calgary be enabled by default?" - depends on CALGARY_IOMMU - ---help--- - Should Calgary be enabled by default? if you choose 'y', Calgary - will be used (if it exists). If you choose 'n', Calgary will not be - used even if it exists. If you choose 'n' and would like to use - Calgary anyway, pass 'iommu=calgary' on the kernel command line. - If unsure, say Y. - config MAXSMP bool "Enable Maximum number of SMP Processors and NUMA Nodes" depends on X86_64 && SMP && DEBUG_KERNEL @@ -991,8 +974,8 @@ config NR_CPUS_RANGE_END config NR_CPUS_RANGE_END int depends on X86_64 - default 8192 if SMP && ( MAXSMP || CPUMASK_OFFSTACK) - default 512 if SMP && (!MAXSMP && !CPUMASK_OFFSTACK) + default 8192 if SMP && CPUMASK_OFFSTACK + default 512 if SMP && !CPUMASK_OFFSTACK default 1 if !SMP config NR_CPUS_DEFAULT @@ -1056,8 +1039,8 @@ config SCHED_MC_PRIO If unsure say Y here. config UP_LATE_INIT - def_bool y - depends on !SMP && X86_LOCAL_APIC + def_bool y + depends on !SMP && X86_LOCAL_APIC config X86_UP_APIC bool "Local APIC support on uniprocessors" if !PCI_MSI @@ -1206,8 +1189,8 @@ config X86_LEGACY_VM86 If unsure, say N here. config VM86 - bool - default X86_LEGACY_VM86 + bool + default X86_LEGACY_VM86 config X86_16BIT bool "Enable support for 16-bit segments" if EXPERT @@ -1228,10 +1211,10 @@ config X86_ESPFIX64 depends on X86_16BIT && X86_64 config X86_VSYSCALL_EMULATION - bool "Enable vsyscall emulation" if EXPERT - default y - depends on X86_64 - ---help--- + bool "Enable vsyscall emulation" if EXPERT + default y + depends on X86_64 + ---help--- This enables emulation of the legacy vsyscall page. Disabling it is roughly equivalent to booting with vsyscall=none, except that it will also disable the helpful warning if a program @@ -1245,6 +1228,24 @@ config X86_VSYSCALL_EMULATION Disabling this option saves about 7K of kernel size and possibly 4K of additional runtime pagetable memory. +config X86_IOPL_IOPERM + bool "IOPERM and IOPL Emulation" + default y + ---help--- + This enables the ioperm() and iopl() syscalls which are necessary + for legacy applications. + + Legacy IOPL support is an overbroad mechanism which allows user + space aside of accessing all 65536 I/O ports also to disable + interrupts. To gain this access the caller needs CAP_SYS_RAWIO + capabilities and permission from potentially active security + modules. + + The emulation restricts the functionality of the syscall to + only allowing the full range I/O port access, but prevents the + ability to disable interrupts from user space which would be + granted if the hardware IOPL mechanism would be used. + config TOSHIBA tristate "Toshiba Laptop support" depends on X86_32 @@ -1483,6 +1484,7 @@ config X86_PAE config X86_5LEVEL bool "Enable 5-level page tables support" + default y select DYNAMIC_MEMORY_LAYOUT select SPARSEMEM_VMEMMAP depends on X86_64 @@ -1503,7 +1505,7 @@ config X86_5LEVEL config X86_DIRECT_GBPAGES def_bool y - depends on X86_64 && !DEBUG_PAGEALLOC + depends on X86_64 ---help--- Certain kernel features effectively disable kernel linear 1 GB mappings (even if the CPU otherwise @@ -1514,13 +1516,10 @@ config X86_CPA_STATISTICS bool "Enable statistic for Change Page Attribute" depends on DEBUG_FS ---help--- - Expose statistics about the Change Page Attribute mechanims, which + Expose statistics about the Change Page Attribute mechanism, which helps to determine the effectiveness of preserving large and huge page mappings when mapping protections are changed. -config ARCH_HAS_MEM_ENCRYPT - def_bool y - config AMD_MEM_ENCRYPT bool "AMD Secure Memory Encryption (SME) support" depends on X86_64 && CPU_SUP_AMD @@ -1548,12 +1547,12 @@ config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT # Common NUMA Features config NUMA - bool "Numa Memory Allocation and Scheduler Support" + bool "NUMA Memory Allocation and Scheduler Support" depends on SMP depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP) default y if X86_BIGSMP ---help--- - Enable NUMA (Non Uniform Memory Access) support. + Enable NUMA (Non-Uniform Memory Access) support. The kernel will try to allocate memory used by a CPU on the local memory controller of the CPU and add some more @@ -1653,9 +1652,9 @@ config ARCH_PROC_KCORE_TEXT depends on X86_64 && PROC_KCORE config ILLEGAL_POINTER_VALUE - hex - default 0 if X86_32 - default 0xdead000000000000 if X86_64 + hex + default 0 if X86_32 + default 0xdead000000000000 if X86_64 config X86_PMEM_LEGACY_DEVICE bool @@ -1745,7 +1744,7 @@ config X86_RESERVE_LOW config MATH_EMULATION bool depends on MODIFY_LDT_SYSCALL - prompt "Math emulation" if X86_32 + prompt "Math emulation" if X86_32 && (M486SX || MELAN) ---help--- Linux can emulate a math coprocessor (used for floating point operations) if you don't have one. 486DX and Pentium processors have @@ -1874,50 +1873,22 @@ config X86_SMAP If unsure, say Y. -config X86_INTEL_UMIP +config X86_UMIP def_bool y - depends on CPU_SUP_INTEL - prompt "Intel User Mode Instruction Prevention" if EXPERT + depends on CPU_SUP_INTEL || CPU_SUP_AMD + prompt "User Mode Instruction Prevention" if EXPERT ---help--- - The User Mode Instruction Prevention (UMIP) is a security - feature in newer Intel processors. If enabled, a general - protection fault is issued if the SGDT, SLDT, SIDT, SMSW - or STR instructions are executed in user mode. These instructions - unnecessarily expose information about the hardware state. + User Mode Instruction Prevention (UMIP) is a security feature in + some x86 processors. If enabled, a general protection fault is + issued if the SGDT, SLDT, SIDT, SMSW or STR instructions are + executed in user mode. These instructions unnecessarily expose + information about the hardware state. The vast majority of applications do not use these instructions. For the very few that do, software emulation is provided in specific cases in protected and virtual-8086 modes. Emulated results are dummy. -config X86_INTEL_MPX - prompt "Intel MPX (Memory Protection Extensions)" - def_bool n - # Note: only available in 64-bit mode due to VMA flags shortage - depends on CPU_SUP_INTEL && X86_64 - select ARCH_USES_HIGH_VMA_FLAGS - ---help--- - MPX provides hardware features that can be used in - conjunction with compiler-instrumented code to check - memory references. It is designed to detect buffer - overflow or underflow bugs. - - This option enables running applications which are - instrumented or otherwise use MPX. It does not use MPX - itself inside the kernel or to protect the kernel - against bad memory references. - - Enabling this option will make the kernel larger: - ~8k of kernel text and 36 bytes of data on a 64-bit - defconfig. It adds a long to the 'mm_struct' which - will increase the kernel memory overhead of each - process and adds some branches to paths used during - exec() and munmap(). - - For details, see Documentation/x86/intel_mpx.rst - - If unsure, say N. - config X86_INTEL_MEMORY_PROTECTION_KEYS prompt "Intel Memory Protection Keys" def_bool y @@ -1934,6 +1905,51 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS If unsure, say y. +choice + prompt "TSX enable mode" + depends on CPU_SUP_INTEL + default X86_INTEL_TSX_MODE_OFF + help + Intel's TSX (Transactional Synchronization Extensions) feature + allows to optimize locking protocols through lock elision which + can lead to a noticeable performance boost. + + On the other hand it has been shown that TSX can be exploited + to form side channel attacks (e.g. TAA) and chances are there + will be more of those attacks discovered in the future. + + Therefore TSX is not enabled by default (aka tsx=off). An admin + might override this decision by tsx=on the command line parameter. + Even with TSX enabled, the kernel will attempt to enable the best + possible TAA mitigation setting depending on the microcode available + for the particular machine. + + This option allows to set the default tsx mode between tsx=on, =off + and =auto. See Documentation/admin-guide/kernel-parameters.txt for more + details. + + Say off if not sure, auto if TSX is in use but it should be used on safe + platforms or on if TSX is in use and the security aspect of tsx is not + relevant. + +config X86_INTEL_TSX_MODE_OFF + bool "off" + help + TSX is disabled if possible - equals to tsx=off command line parameter. + +config X86_INTEL_TSX_MODE_ON + bool "on" + help + TSX is always enabled on TSX capable HW - equals the tsx=on command + line parameter. + +config X86_INTEL_TSX_MODE_AUTO + bool "auto" + help + TSX is enabled on TSX capable HW that is believed to be safe against + side channel attacks- equals the tsx=auto command line parameter. +endchoice + config EFI bool "EFI runtime service support" depends on ACPI @@ -1951,11 +1967,12 @@ config EFI platforms. config EFI_STUB - bool "EFI stub support" - depends on EFI && !X86_USE_3DNOW - select RELOCATABLE - ---help--- - This kernel feature allows a bzImage to be loaded directly + bool "EFI stub support" + depends on EFI && !X86_USE_3DNOW + depends on $(cc-option,-mabi=ms) || X86_32 + select RELOCATABLE + ---help--- + This kernel feature allows a bzImage to be loaded directly by EFI firmware without the use of a bootloader. See Documentation/admin-guide/efi-stub.rst for more information. @@ -2025,20 +2042,30 @@ config KEXEC_FILE config ARCH_HAS_KEXEC_PURGATORY def_bool KEXEC_FILE -config KEXEC_VERIFY_SIG +config KEXEC_SIG bool "Verify kernel signature during kexec_file_load() syscall" depends on KEXEC_FILE ---help--- - This option makes kernel signature verification mandatory for - the kexec_file_load() syscall. - In addition to that option, you need to enable signature + This option makes the kexec_file_load() syscall check for a valid + signature of the kernel image. The image can still be loaded without + a valid signature unless you also enable KEXEC_SIG_FORCE, though if + there's a signature that we can check, then it must be valid. + + In addition to this option, you need to enable signature verification for the corresponding kernel image type being loaded in order for this to work. +config KEXEC_SIG_FORCE + bool "Require a valid signature in kexec_file_load() syscall" + depends on KEXEC_SIG + ---help--- + This option makes kernel signature verification mandatory for + the kexec_file_load() syscall. + config KEXEC_BZIMAGE_VERIFY_SIG bool "Enable bzImage signature verification support" - depends on KEXEC_VERIFY_SIG + depends on KEXEC_SIG depends on SIGNED_PE_FILE_VERIFICATION select SYSTEM_TRUSTED_KEYRING ---help--- @@ -2905,9 +2932,6 @@ config HAVE_ATOMIC_IOMAP def_bool y depends on X86_32 -config X86_DEV_DMA_OPS - bool - source "drivers/firmware/Kconfig" source "arch/x86/kvm/Kconfig" diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 8e29c991ba3e..bc3a497c029c 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -50,12 +50,19 @@ choice See each option's help text for additional details. If you don't know what to do, choose "486". +config M486SX + bool "486SX" + depends on X86_32 + ---help--- + Select this for an 486-class CPU without an FPU such as + AMD/Cyrix/IBM/Intel SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5S. + config M486 - bool "486" + bool "486DX" depends on X86_32 ---help--- Select this for an 486-class CPU such as AMD/Cyrix/IBM/Intel - 486DX/DX2/DX4 or SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. + 486DX/DX2/DX4 and UMC U5D. config M586 bool "586/K5/5x86/6x86/6x86MX" @@ -312,20 +319,20 @@ config X86_L1_CACHE_SHIFT int default "7" if MPENTIUM4 || MPSC default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU - default "4" if MELAN || M486 || MGEODEGX1 + default "4" if MELAN || M486SX || M486 || MGEODEGX1 default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX config X86_F00F_BUG def_bool y - depends on M586MMX || M586TSC || M586 || M486 + depends on M586MMX || M586TSC || M586 || M486SX || M486 config X86_INVD_BUG def_bool y - depends on M486 + depends on M486SX || M486 config X86_ALIGNMENT_16 def_bool y - depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1 + depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486SX || M486 || MVIAC3_2 || MGEODEGX1 config X86_INTEL_USERCOPY def_bool y @@ -378,7 +385,15 @@ config X86_MINIMUM_CPU_FAMILY config X86_DEBUGCTLMSR def_bool y - depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486) && !UML + depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486SX || M486) && !UML + +config IA32_FEAT_CTL + def_bool y + depends on CPU_SUP_INTEL || CPU_SUP_CENTAUR || CPU_SUP_ZHAOXIN + +config X86_VMX_FEATURE_NAMES + def_bool y + depends on IA32_FEAT_CTL && X86_FEATURE_NAMES menuconfig PROCESSOR_SELECT bool "Supported processor vendors" if EXPERT @@ -402,7 +417,7 @@ config CPU_SUP_INTEL config CPU_SUP_CYRIX_32 default y bool "Support Cyrix processors" if PROCESSOR_SELECT - depends on M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT) + depends on M486SX || M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT) ---help--- This enables detection, tunings and quirks for Cyrix processors @@ -470,7 +485,7 @@ config CPU_SUP_TRANSMETA_32 config CPU_SUP_UMC_32 default y bool "Support UMC processors" if PROCESSOR_SELECT - depends on M486 || (EXPERT && !64BIT) + depends on M486SX || M486 || (EXPERT && !64BIT) ---help--- This enables detection, tunings and quirks for UMC processors diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 71c92db47c41..2e74690b028a 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -62,26 +62,10 @@ config EARLY_PRINTK_USB_XDBC config MCSAFE_TEST def_bool n -config X86_PTDUMP_CORE - def_bool n - -config X86_PTDUMP - tristate "Export kernel pagetable layout to userspace via debugfs" - depends on DEBUG_KERNEL - select DEBUG_FS - select X86_PTDUMP_CORE - ---help--- - Say Y here if you want to show the kernel pagetable layout in a - debugfs file. This information is only useful for kernel developers - who are working in architecture specific areas of the kernel. - It is probably not a good idea to enable this feature in a production - kernel. - If in doubt, say "N" - config EFI_PGT_DUMP bool "Dump the EFI pagetable" depends on EFI - select X86_PTDUMP_CORE + select PTDUMP_CORE ---help--- Enable this if you want to dump the EFI page table before enabling virtual mode. This can be used to debug miscellaneous @@ -90,7 +74,7 @@ config EFI_PGT_DUMP config DEBUG_WX bool "Warn on W+X mappings at boot" - select X86_PTDUMP_CORE + select PTDUMP_CORE ---help--- Generate a warning if any W+X mappings are found at boot. @@ -117,7 +101,7 @@ config DEBUG_WX config DOUBLEFAULT default y - bool "Enable doublefault exception handler" if EXPERT + bool "Enable doublefault exception handler" if EXPERT && X86_32 ---help--- This option allows trapping of rare doublefault exceptions that would otherwise cause a system to silently reboot. Disabling this @@ -171,7 +155,7 @@ config HAVE_MMIOTRACE_SUPPORT config X86_DECODER_SELFTEST bool "x86 instruction decoder selftest" - depends on DEBUG_KERNEL && KPROBES + depends on DEBUG_KERNEL && INSTRUCTION_DECODER depends on !COMPILE_TEST ---help--- Perform x86 instruction decoder selftests at build time. @@ -316,10 +300,6 @@ config UNWINDER_FRAME_POINTER unwinder, but the kernel text size will grow by ~3% and the kernel's overall performance will degrade by roughly 5-10%. - This option is recommended if you want to use the livepatch - consistency model, as this is currently the only way to get a - reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). - config UNWINDER_GUESS bool "Guess unwinder" depends on EXPERT diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 56e748a7679f..94df0868804b 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -38,6 +38,7 @@ REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -DDISABLE_BRANCH_PROFILING \ REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector) +REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4)) export REALMODE_CFLAGS diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 1f5faf8606b4..cd3056759880 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -10,6 +10,7 @@ else tune = $(call cc-option,-mcpu=$(1),$(2)) endif +cflags-$(CONFIG_M486SX) += -march=i486 cflags-$(CONFIG_M486) += -march=i486 cflags-$(CONFIG_M586) += -march=i586 cflags-$(CONFIG_M586TSC) += -march=i586 diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index e2839b5c246c..012b82fc8617 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -45,8 +45,8 @@ setup-y += video-vesa.o setup-y += video-bios.o targets += $(setup-y) -hostprogs-y := tools/build -hostprogs-$(CONFIG_X86_FEATURE_NAMES) += mkcpustr +hostprogs := tools/build +hostprogs += mkcpustr HOST_EXTRACFLAGS += -I$(srctree)/tools/include \ -include include/generated/autoconf.h \ @@ -67,6 +67,7 @@ clean-files += cpustr.h KBUILD_CFLAGS := $(REALMODE_CFLAGS) -D_SETUP KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ +KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) GCOV_PROFILE := n UBSAN_SANITIZE := n @@ -87,7 +88,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 19eca14b49a0..ca866f1cca2e 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -28,8 +28,6 @@ #include "cpuflags.h" /* Useful macros */ -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) - #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) extern struct setup_header hdr; diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 6b84afdd7538..26050ae0b27e 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -38,6 +38,7 @@ KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) KBUILD_CFLAGS += -Wno-pointer-sign +KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n @@ -57,7 +58,7 @@ KBUILD_LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \ endif LDFLAGS_vmlinux := -T -hostprogs-y := mkpiggy +hostprogs := mkpiggy HOST_EXTRACFLAGS += -I$(srctree)/tools/include sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' @@ -72,8 +73,8 @@ $(obj)/../voffset.h: vmlinux FORCE $(obj)/misc.o: $(obj)/../voffset.h -vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ - $(obj)/string.o $(obj)/cmdline.o $(obj)/error.o \ +vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/kernel_info.o $(obj)/head_$(BITS).o \ + $(obj)/misc.o $(obj)/string.o $(obj)/cmdline.o $(obj)/error.o \ $(obj)/piggy.o $(obj)/cpuflags.o vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o @@ -88,7 +89,7 @@ vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone -vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \ +vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o \ $(objtree)/drivers/firmware/efi/libstub/lib.a vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o @@ -102,7 +103,7 @@ vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o quiet_cmd_check_data_rel = DATAREL $@ define cmd_check_data_rel for obj in $(filter %.o,$^); do \ - ${CROSS_COMPILE}readelf -S $$obj | grep -qF .rel.local && { \ + $(READELF) -S $$obj | grep -qF .rel.local && { \ echo "error: $$obj has data relocations!" >&2; \ exit 1; \ } || true; \ diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 15255f388a85..ef2ad7253cd5 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -21,30 +21,6 @@ struct mem_vector immovable_mem[MAX_NUMNODES*2]; /* - * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex - * digits, and '\0' for termination. - */ -#define MAX_ADDR_LEN 19 - -static acpi_physical_address get_acpi_rsdp(void) -{ - acpi_physical_address addr = 0; - -#ifdef CONFIG_KEXEC - char val[MAX_ADDR_LEN] = { }; - int ret; - - ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN); - if (ret < 0) - return 0; - - if (kstrtoull(val, 16, &addr)) - return 0; -#endif - return addr; -} - -/* * Search EFI system tables for RSDP. If both ACPI_20_TABLE_GUID and * ACPI_TABLE_GUID are found, take the former, which has more features. */ @@ -278,10 +254,7 @@ acpi_physical_address get_rsdp_addr(void) { acpi_physical_address pa; - pa = get_acpi_rsdp(); - - if (!pa) - pa = boot_params->acpi_rsdp_addr; + pa = boot_params->acpi_rsdp_addr; /* * Try to get EFI data from setup_data. This can happen when we're a @@ -301,6 +274,30 @@ acpi_physical_address get_rsdp_addr(void) } #if defined(CONFIG_RANDOMIZE_BASE) && defined(CONFIG_MEMORY_HOTREMOVE) +/* + * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex + * digits, and '\0' for termination. + */ +#define MAX_ADDR_LEN 19 + +static acpi_physical_address get_cmdline_acpi_rsdp(void) +{ + acpi_physical_address addr = 0; + +#ifdef CONFIG_KEXEC + char val[MAX_ADDR_LEN] = { }; + int ret; + + ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN); + if (ret < 0) + return 0; + + if (kstrtoull(val, 16, &addr)) + return 0; +#endif + return addr; +} + /* Compute SRAT address from RSDP. */ static unsigned long get_acpi_srat_table(void) { @@ -311,7 +308,17 @@ static unsigned long get_acpi_srat_table(void) char arg[10]; u8 *entry; - rsdp = (struct acpi_table_rsdp *)(long)boot_params->acpi_rsdp_addr; + /* + * Check whether we were given an RSDP on the command line. We don't + * stash this in boot params because the kernel itself may have + * different ideas about whether to trust a command-line parameter. + */ + rsdp = (struct acpi_table_rsdp *)get_cmdline_acpi_rsdp(); + + if (!rsdp) + rsdp = (struct acpi_table_rsdp *)(long) + boot_params->acpi_rsdp_addr; + if (!rsdp) return 0; @@ -386,7 +393,13 @@ int count_immovable_mem_regions(void) table = table_addr + sizeof(struct acpi_table_srat); while (table + sizeof(struct acpi_subtable_header) < table_end) { + sub_table = (struct acpi_subtable_header *)table; + if (!sub_table->length) { + debug_putstr("Invalid zero length SRAT subtable.\n"); + return 0; + } + if (sub_table->type == ACPI_SRAT_TYPE_MEMORY_AFFINITY) { struct acpi_srat_mem_affinity *ma; diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index d6662fdef300..287393d725f0 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -6,6 +6,8 @@ * * ----------------------------------------------------------------------- */ +#pragma GCC visibility push(hidden) + #include <linux/efi.h> #include <linux/pci.h> @@ -13,37 +15,24 @@ #include <asm/e820/types.h> #include <asm/setup.h> #include <asm/desc.h> +#include <asm/boot.h> #include "../string.h" #include "eboot.h" static efi_system_table_t *sys_table; +extern const bool efi_is64; -static struct efi_config *efi_early; - -__pure const struct efi_config *__efi_early(void) +__pure efi_system_table_t *efi_system_table(void) { - return efi_early; -} - -#define BOOT_SERVICES(bits) \ -static void setup_boot_services##bits(struct efi_config *c) \ -{ \ - efi_system_table_##bits##_t *table; \ - \ - table = (typeof(table))sys_table; \ - \ - c->runtime_services = table->runtime; \ - c->boot_services = table->boottime; \ - c->text_output = table->con_out; \ + return sys_table; } -BOOT_SERVICES(32); -BOOT_SERVICES(64); -void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) +__attribute_const__ bool efi_is_64bit(void) { - efi_call_proto(efi_simple_text_output_protocol, output_string, - efi_early->text_output, str); + if (IS_ENABLED(CONFIG_EFI_MIXED)) + return efi_is64; + return IS_ENABLED(CONFIG_X86_64); } static efi_status_t @@ -62,17 +51,17 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) * large romsize. The UEFI spec limits the size of option ROMs to 16 * MiB so we reject any ROMs over 16 MiB in size to catch this. */ - romimage = (void *)(unsigned long)efi_table_attr(efi_pci_io_protocol, - romimage, pci); - romsize = efi_table_attr(efi_pci_io_protocol, romsize, pci); + romimage = efi_table_attr(pci, romimage); + romsize = efi_table_attr(pci, romsize); if (!romimage || !romsize || romsize > SZ_16M) return EFI_INVALID_PARAMETER; size = romsize + sizeof(*rom); - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, + (void **)&rom); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'rom'\n"); + efi_printk("Failed to allocate memory for 'rom'\n"); return status; } @@ -84,27 +73,24 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) rom->pcilen = pci->romsize; *__rom = rom; - status = efi_call_proto(efi_pci_io_protocol, pci.read, pci, - EfiPciIoWidthUint16, PCI_VENDOR_ID, 1, - &rom->vendor); + status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16, + PCI_VENDOR_ID, 1, &rom->vendor); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to read rom->vendor\n"); + efi_printk("Failed to read rom->vendor\n"); goto free_struct; } - status = efi_call_proto(efi_pci_io_protocol, pci.read, pci, - EfiPciIoWidthUint16, PCI_DEVICE_ID, 1, - &rom->devid); + status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16, + PCI_DEVICE_ID, 1, &rom->devid); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to read rom->devid\n"); + efi_printk("Failed to read rom->devid\n"); goto free_struct; } - status = efi_call_proto(efi_pci_io_protocol, get_location, pci, - &rom->segment, &rom->bus, &rom->device, - &rom->function); + status = efi_call_proto(pci, get_location, &rom->segment, &rom->bus, + &rom->device, &rom->function); if (status != EFI_SUCCESS) goto free_struct; @@ -113,7 +99,7 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) return status; free_struct: - efi_call_early(free_pool, rom); + efi_bs_call(free_pool, rom); return status; } @@ -132,27 +118,24 @@ static void setup_efi_pci(struct boot_params *params) void **pci_handle = NULL; efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; unsigned long size = 0; - unsigned long nr_pci; struct setup_data *data; + efi_handle_t h; int i; - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - &pci_proto, NULL, &size, pci_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + &pci_proto, NULL, &size, pci_handle); if (status == EFI_BUFFER_TOO_SMALL) { - status = efi_call_early(allocate_pool, - EFI_LOADER_DATA, - size, (void **)&pci_handle); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, + (void **)&pci_handle); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'pci_handle'\n"); + efi_printk("Failed to allocate memory for 'pci_handle'\n"); return; } - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, &pci_proto, - NULL, &size, pci_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + &pci_proto, NULL, &size, pci_handle); } if (status != EFI_SUCCESS) @@ -163,15 +146,12 @@ static void setup_efi_pci(struct boot_params *params) while (data && data->next) data = (struct setup_data *)(unsigned long)data->next; - nr_pci = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); - for (i = 0; i < nr_pci; i++) { + for_each_efi_handle(h, pci_handle, size, i) { efi_pci_io_protocol_t *pci = NULL; struct pci_setup_rom *rom; - status = efi_call_early(handle_protocol, - efi_is_64bit() ? ((u64 *)pci_handle)[i] - : ((u32 *)pci_handle)[i], - &pci_proto, (void **)&pci); + status = efi_bs_call(handle_protocol, h, &pci_proto, + (void **)&pci); if (status != EFI_SUCCESS || !pci) continue; @@ -188,7 +168,7 @@ static void setup_efi_pci(struct boot_params *params) } free_handle: - efi_call_early(free_pool, pci_handle); + efi_bs_call(free_pool, pci_handle); } static void retrieve_apple_device_properties(struct boot_params *boot_params) @@ -197,34 +177,34 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) struct setup_data *data, *new; efi_status_t status; u32 size = 0; - void *p; + apple_properties_protocol_t *p; - status = efi_call_early(locate_protocol, &guid, NULL, &p); + status = efi_bs_call(locate_protocol, &guid, NULL, (void **)&p); if (status != EFI_SUCCESS) return; - if (efi_table_attr(apple_properties_protocol, version, p) != 0x10000) { - efi_printk(sys_table, "Unsupported properties proto version\n"); + if (efi_table_attr(p, version) != 0x10000) { + efi_printk("Unsupported properties proto version\n"); return; } - efi_call_proto(apple_properties_protocol, get_all, p, NULL, &size); + efi_call_proto(p, get_all, NULL, &size); if (!size) return; do { - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size + sizeof(struct setup_data), &new); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, + size + sizeof(struct setup_data), + (void **)&new); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'properties'\n"); + efi_printk("Failed to allocate memory for 'properties'\n"); return; } - status = efi_call_proto(apple_properties_protocol, get_all, p, - new->data, &size); + status = efi_call_proto(p, get_all, new->data, &size); if (status == EFI_BUFFER_TOO_SMALL) - efi_call_early(free_pool, new); + efi_bs_call(free_pool, new); } while (status == EFI_BUFFER_TOO_SMALL); new->type = SETUP_APPLE_PROPERTIES; @@ -246,7 +226,7 @@ static const efi_char16_t apple[] = L"Apple"; static void setup_quirks(struct boot_params *boot_params) { efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) - efi_table_attr(efi_system_table, fw_vendor, sys_table); + efi_table_attr(efi_system_table(), fw_vendor); if (!memcmp(fw_vendor, apple, sizeof(apple))) { if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) @@ -264,17 +244,16 @@ setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) u32 width, height; void **uga_handle = NULL; efi_uga_draw_protocol_t *uga = NULL, *first_uga; - unsigned long nr_ugas; + efi_handle_t handle; int i; - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size, (void **)&uga_handle); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, + (void **)&uga_handle); if (status != EFI_SUCCESS) return status; - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - uga_proto, NULL, &size, uga_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + uga_proto, NULL, &size, uga_handle); if (status != EFI_SUCCESS) goto free_handle; @@ -282,24 +261,20 @@ setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) width = 0; first_uga = NULL; - nr_ugas = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); - for (i = 0; i < nr_ugas; i++) { + for_each_efi_handle(handle, uga_handle, size, i) { efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; u32 w, h, depth, refresh; void *pciio; - unsigned long handle = efi_is_64bit() ? ((u64 *)uga_handle)[i] - : ((u32 *)uga_handle)[i]; - status = efi_call_early(handle_protocol, handle, - uga_proto, (void **)&uga); + status = efi_bs_call(handle_protocol, handle, uga_proto, + (void **)&uga); if (status != EFI_SUCCESS) continue; pciio = NULL; - efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); + efi_bs_call(handle_protocol, handle, &pciio_proto, &pciio); - status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga, - &w, &h, &depth, &refresh); + status = efi_call_proto(uga, get_mode, &w, &h, &depth, &refresh); if (status == EFI_SUCCESS && (!first_uga || pciio)) { width = w; height = h; @@ -335,7 +310,7 @@ setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) si->rsvd_pos = 24; free_handle: - efi_call_early(free_pool, uga_handle); + efi_bs_call(free_pool, uga_handle); return status; } @@ -354,37 +329,38 @@ void setup_graphics(struct boot_params *boot_params) memset(si, 0, sizeof(*si)); size = 0; - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - &graphics_proto, NULL, &size, gop_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + &graphics_proto, NULL, &size, gop_handle); if (status == EFI_BUFFER_TOO_SMALL) - status = efi_setup_gop(NULL, si, &graphics_proto, size); + status = efi_setup_gop(si, &graphics_proto, size); if (status != EFI_SUCCESS) { size = 0; - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - &uga_proto, NULL, &size, uga_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + &uga_proto, NULL, &size, uga_handle); if (status == EFI_BUFFER_TOO_SMALL) setup_uga(si, &uga_proto, size); } } +void startup_32(struct boot_params *boot_params); + +void __noreturn efi_stub_entry(efi_handle_t handle, + efi_system_table_t *sys_table_arg, + struct boot_params *boot_params); + /* * Because the x86 boot code expects to be passed a boot_params we * need to create one ourselves (usually the bootloader would create * one for us). - * - * The caller is responsible for filling out ->code32_start in the - * returned boot_params. */ -struct boot_params *make_boot_params(struct efi_config *c) +efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, + efi_system_table_t *sys_table_arg) { struct boot_params *boot_params; struct apm_bios_info *bi; struct setup_header *hdr; efi_loaded_image_t *image; - void *handle; efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; int options_size = 0; efi_status_t status; @@ -392,31 +368,22 @@ struct boot_params *make_boot_params(struct efi_config *c) unsigned long ramdisk_addr; unsigned long ramdisk_size; - efi_early = c; - sys_table = (efi_system_table_t *)(unsigned long)efi_early->table; - handle = (void *)(unsigned long)efi_early->image_handle; + sys_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) - return NULL; - - if (efi_is_64bit()) - setup_boot_services64(efi_early); - else - setup_boot_services32(efi_early); + return EFI_INVALID_PARAMETER; - status = efi_call_early(handle_protocol, handle, - &proto, (void *)&image); + status = efi_bs_call(handle_protocol, handle, &proto, (void *)&image); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n"); - return NULL; + efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n"); + return status; } - status = efi_low_alloc(sys_table, 0x4000, 1, - (unsigned long *)&boot_params); + status = efi_low_alloc(0x4000, 1, (unsigned long *)&boot_params); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate lowmem for boot params\n"); - return NULL; + efi_printk("Failed to allocate lowmem for boot params\n"); + return status; } memset(boot_params, 0x0, 0x4000); @@ -438,7 +405,7 @@ struct boot_params *make_boot_params(struct efi_config *c) hdr->type_of_loader = 0x21; /* Convert unicode cmdline to ascii */ - cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); + cmdline_ptr = efi_convert_cmdline(image, &options_size); if (!cmdline_ptr) goto fail; @@ -456,15 +423,15 @@ struct boot_params *make_boot_params(struct efi_config *c) if (status != EFI_SUCCESS) goto fail2; - status = handle_cmdline_files(sys_table, image, + status = handle_cmdline_files(image, (char *)(unsigned long)hdr->cmd_line_ptr, "initrd=", hdr->initrd_addr_max, &ramdisk_addr, &ramdisk_size); if (status != EFI_SUCCESS && hdr->xloadflags & XLF_CAN_BE_LOADED_ABOVE_4G) { - efi_printk(sys_table, "Trying to load files to higher address\n"); - status = handle_cmdline_files(sys_table, image, + efi_printk("Trying to load files to higher address\n"); + status = handle_cmdline_files(image, (char *)(unsigned long)hdr->cmd_line_ptr, "initrd=", -1UL, &ramdisk_addr, &ramdisk_size); @@ -477,14 +444,17 @@ struct boot_params *make_boot_params(struct efi_config *c) boot_params->ext_ramdisk_image = (u64)ramdisk_addr >> 32; boot_params->ext_ramdisk_size = (u64)ramdisk_size >> 32; - return boot_params; + hdr->code32_start = (u32)(unsigned long)startup_32; + + efi_stub_entry(handle, sys_table, boot_params); + /* not reached */ fail2: - efi_free(sys_table, options_size, hdr->cmd_line_ptr); + efi_free(options_size, hdr->cmd_line_ptr); fail: - efi_free(sys_table, 0x4000, (unsigned long)boot_params); + efi_free(0x4000, (unsigned long)boot_params); - return NULL; + return status; } static void add_e820ext(struct boot_params *params, @@ -553,7 +523,11 @@ setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_s case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: - e820_type = E820_TYPE_RAM; + if (efi_soft_reserve_enabled() && + (d->attribute & EFI_MEMORY_SP)) + e820_type = E820_TYPE_SOFT_RESERVED; + else + e820_type = E820_TYPE_RAM; break; case EFI_ACPI_MEMORY_NVS: @@ -615,13 +589,13 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, sizeof(struct e820_entry) * nr_desc; if (*e820ext) { - efi_call_early(free_pool, *e820ext); + efi_bs_call(free_pool, *e820ext); *e820ext = NULL; *e820ext_size = 0; } - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size, (void **)e820ext); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, + (void **)e820ext); if (status == EFI_SUCCESS) *e820ext_size = size; @@ -645,7 +619,7 @@ static efi_status_t allocate_e820(struct boot_params *params, boot_map.key_ptr = NULL; boot_map.buff_size = &buff_size; - status = efi_get_memory_map(sys_table, &boot_map); + status = efi_get_memory_map(&boot_map); if (status != EFI_SUCCESS) return status; @@ -667,8 +641,7 @@ struct exit_boot_struct { struct efi_info *efi; }; -static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, - struct efi_boot_memmap *map, +static efi_status_t exit_boot_func(struct efi_boot_memmap *map, void *priv) { const char *signature; @@ -678,14 +651,14 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, : EFI32_LOADER_SIGNATURE; memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32)); - p->efi->efi_systab = (unsigned long)sys_table_arg; + p->efi->efi_systab = (unsigned long)efi_system_table(); p->efi->efi_memdesc_size = *map->desc_size; p->efi->efi_memdesc_version = *map->desc_ver; p->efi->efi_memmap = (unsigned long)*map->map; p->efi->efi_memmap_size = *map->map_size; #ifdef CONFIG_X86_64 - p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32; + p->efi->efi_systab_hi = (unsigned long)efi_system_table() >> 32; p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; #endif @@ -717,8 +690,7 @@ static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) return status; /* Might as well exit boot services now */ - status = efi_exit_boot_services(sys_table, handle, &map, &priv, - exit_boot_func); + status = efi_exit_boot_services(handle, &map, &priv, exit_boot_func); if (status != EFI_SUCCESS) return status; @@ -736,33 +708,22 @@ static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) * On success we return a pointer to a boot_params structure, and NULL * on failure. */ -struct boot_params * -efi_main(struct efi_config *c, struct boot_params *boot_params) +struct boot_params *efi_main(efi_handle_t handle, + efi_system_table_t *sys_table_arg, + struct boot_params *boot_params) { struct desc_ptr *gdt = NULL; struct setup_header *hdr = &boot_params->hdr; efi_status_t status; struct desc_struct *desc; - void *handle; - efi_system_table_t *_table; unsigned long cmdline_paddr; - efi_early = c; - - _table = (efi_system_table_t *)(unsigned long)efi_early->table; - handle = (void *)(unsigned long)efi_early->image_handle; - - sys_table = _table; + sys_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) goto fail; - if (efi_is_64bit()) - setup_boot_services64(efi_early); - else - setup_boot_services32(efi_early); - /* * make_boot_params() may have been called before efi_main(), in which * case this is the second time we parse the cmdline. This is ok, @@ -777,11 +738,14 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) * otherwise we ask the BIOS. */ if (boot_params->secure_boot == efi_secureboot_mode_unset) - boot_params->secure_boot = efi_get_secureboot(sys_table); + boot_params->secure_boot = efi_get_secureboot(); /* Ask the firmware to clear memory on unclean shutdown */ - efi_enable_reset_attack_mitigation(sys_table); - efi_retrieve_tpm2_eventlog(sys_table); + efi_enable_reset_attack_mitigation(); + + efi_random_get_seed(); + + efi_retrieve_tpm2_eventlog(); setup_graphics(boot_params); @@ -789,18 +753,17 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) setup_quirks(boot_params); - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - sizeof(*gdt), (void **)&gdt); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, sizeof(*gdt), + (void **)&gdt); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'gdt' structure\n"); + efi_printk("Failed to allocate memory for 'gdt' structure\n"); goto fail; } gdt->size = 0x800; - status = efi_low_alloc(sys_table, gdt->size, 8, - (unsigned long *)&gdt->address); + status = efi_low_alloc(gdt->size, 8, (unsigned long *)&gdt->address); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'gdt'\n"); + efi_printk("Failed to allocate memory for 'gdt'\n"); goto fail; } @@ -810,12 +773,13 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) */ if (hdr->pref_address != hdr->code32_start) { unsigned long bzimage_addr = hdr->code32_start; - status = efi_relocate_kernel(sys_table, &bzimage_addr, + status = efi_relocate_kernel(&bzimage_addr, hdr->init_size, hdr->init_size, hdr->pref_address, - hdr->kernel_alignment); + hdr->kernel_alignment, + LOAD_PHYSICAL_ADDR); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "efi_relocate_kernel() failed!\n"); + efi_printk("efi_relocate_kernel() failed!\n"); goto fail; } @@ -825,7 +789,7 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "exit_boot() failed!\n"); + efi_printk("exit_boot() failed!\n"); goto fail; } @@ -918,7 +882,8 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) return boot_params; fail: - efi_printk(sys_table, "efi_main() failed!\n"); + efi_printk("efi_main() failed!\n"); - return NULL; + for (;;) + asm("hlt"); } diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index 8297387c4676..99f35343d443 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -12,22 +12,20 @@ #define DESC_TYPE_CODE_DATA (1 << 0) -typedef struct { - u32 get_mode; - u32 set_mode; - u32 blt; -} efi_uga_draw_protocol_32_t; +typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t; -typedef struct { - u64 get_mode; - u64 set_mode; - u64 blt; -} efi_uga_draw_protocol_64_t; - -typedef struct { - void *get_mode; - void *set_mode; - void *blt; -} efi_uga_draw_protocol_t; +union efi_uga_draw_protocol { + struct { + efi_status_t (__efiapi *get_mode)(efi_uga_draw_protocol_t *, + u32*, u32*, u32*, u32*); + void *set_mode; + void *blt; + }; + struct { + u32 get_mode; + u32 set_mode; + u32 blt; + } mixed_mode; +}; #endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/efi_stub_32.S b/arch/x86/boot/compressed/efi_stub_32.S deleted file mode 100644 index 257e341fd2c8..000000000000 --- a/arch/x86/boot/compressed/efi_stub_32.S +++ /dev/null @@ -1,87 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * EFI call stub for IA32. - * - * This stub allows us to make EFI calls in physical mode with interrupts - * turned off. Note that this implementation is different from the one in - * arch/x86/platform/efi/efi_stub_32.S because we're _already_ in physical - * mode at this point. - */ - -#include <linux/linkage.h> -#include <asm/page_types.h> - -/* - * efi_call_phys(void *, ...) is a function with variable parameters. - * All the callers of this function assure that all the parameters are 4-bytes. - */ - -/* - * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save. - * So we'd better save all of them at the beginning of this function and restore - * at the end no matter how many we use, because we can not assure EFI runtime - * service functions will comply with gcc calling convention, too. - */ - -.text -ENTRY(efi_call_phys) - /* - * 0. The function can only be called in Linux kernel. So CS has been - * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found - * the values of these registers are the same. And, the corresponding - * GDT entries are identical. So I will do nothing about segment reg - * and GDT, but change GDT base register in prelog and epilog. - */ - - /* - * 1. Because we haven't been relocated by this point we need to - * use relative addressing. - */ - call 1f -1: popl %edx - subl $1b, %edx - - /* - * 2. Now on the top of stack is the return - * address in the caller of efi_call_phys(), then parameter 1, - * parameter 2, ..., param n. To make things easy, we save the return - * address of efi_call_phys in a global variable. - */ - popl %ecx - movl %ecx, saved_return_addr(%edx) - /* get the function pointer into ECX*/ - popl %ecx - movl %ecx, efi_rt_function_ptr(%edx) - - /* - * 3. Call the physical function. - */ - call *%ecx - - /* - * 4. Balance the stack. And because EAX contain the return value, - * we'd better not clobber it. We need to calculate our address - * again because %ecx and %edx are not preserved across EFI function - * calls. - */ - call 1f -1: popl %edx - subl $1b, %edx - - movl efi_rt_function_ptr(%edx), %ecx - pushl %ecx - - /* - * 10. Push the saved return address onto the stack and return. - */ - movl saved_return_addr(%edx), %ecx - pushl %ecx - ret -ENDPROC(efi_call_phys) -.previous - -.data -saved_return_addr: - .long 0 -efi_rt_function_ptr: - .long 0 diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S deleted file mode 100644 index 99494dff2113..000000000000 --- a/arch/x86/boot/compressed/efi_stub_64.S +++ /dev/null @@ -1,5 +0,0 @@ -#include <asm/segment.h> -#include <asm/msr.h> -#include <asm/processor-flags.h> - -#include "../../platform/efi/efi_stub_64.S" diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S index bff9ab7c6317..8fb7f6799c52 100644 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -10,7 +10,7 @@ * needs to be able to service interrupts. * * On the plus side, we don't have to worry about mangling 64-bit - * addresses into 32-bits because we're executing with an identify + * addresses into 32-bits because we're executing with an identity * mapped pagetable and haven't transitioned to 64-bit virtual addresses * yet. */ @@ -23,16 +23,13 @@ .code64 .text -ENTRY(efi64_thunk) +SYM_FUNC_START(__efi64_thunk) push %rbp push %rbx - subq $8, %rsp - leaq efi_exit32(%rip), %rax - movl %eax, 4(%rsp) - leaq efi_gdt64(%rip), %rax - movl %eax, (%rsp) - movl %eax, 2(%rax) /* Fixup the gdt base address */ + leaq 1f(%rip), %rbp + leaq efi_gdt64(%rip), %rbx + movl %ebx, 2(%rbx) /* Fixup the gdt base address */ movl %ds, %eax push %rax @@ -48,15 +45,10 @@ ENTRY(efi64_thunk) movl %esi, 0x0(%rsp) movl %edx, 0x4(%rsp) movl %ecx, 0x8(%rsp) - movq %r8, %rsi - movl %esi, 0xc(%rsp) - movq %r9, %rsi - movl %esi, 0x10(%rsp) + movl %r8d, 0xc(%rsp) + movl %r9d, 0x10(%rsp) - sgdt save_gdt(%rip) - - leaq 1f(%rip), %rbx - movq %rbx, func_rt_ptr(%rip) + sgdt 0x14(%rsp) /* * Switch to gdt with 32-bit segments. This is the firmware GDT @@ -71,9 +63,9 @@ ENTRY(efi64_thunk) pushq %rax lretq -1: addq $32, %rsp - - lgdt save_gdt(%rip) +1: lgdt 0x14(%rsp) + addq $32, %rsp + movq %rdi, %rax pop %rbx movl %ebx, %ss @@ -85,26 +77,13 @@ ENTRY(efi64_thunk) /* * Convert 32-bit status code into 64-bit. */ - test %rax, %rax - jz 1f - movl %eax, %ecx - andl $0x0fffffff, %ecx - andl $0xf0000000, %eax - shl $32, %rax - or %rcx, %rax -1: - addq $8, %rsp + roll $1, %eax + rorq $1, %rax + pop %rbx pop %rbp ret -ENDPROC(efi64_thunk) - -ENTRY(efi_exit32) - movq func_rt_ptr(%rip), %rax - push %rax - mov %rdi, %rax - ret -ENDPROC(efi_exit32) +SYM_FUNC_END(__efi64_thunk) .code32 /* @@ -112,7 +91,7 @@ ENDPROC(efi_exit32) * * The stack should represent the 32-bit calling convention. */ -ENTRY(efi_enter32) +SYM_FUNC_START_LOCAL(efi_enter32) movl $__KERNEL_DS, %eax movl %eax, %ds movl %eax, %es @@ -144,9 +123,7 @@ ENTRY(efi_enter32) */ cli - movl 56(%esp), %eax - movl %eax, 2(%eax) - lgdtl (%eax) + lgdtl (%ebx) movl %cr4, %eax btsl $(X86_CR4_PAE_BIT), %eax @@ -163,29 +140,24 @@ ENTRY(efi_enter32) xorl %eax, %eax lldt %ax - movl 60(%esp), %eax pushl $__KERNEL_CS - pushl %eax + pushl %ebp /* Enable paging */ movl %cr0, %eax btsl $X86_CR0_PG_BIT, %eax movl %eax, %cr0 lret -ENDPROC(efi_enter32) +SYM_FUNC_END(efi_enter32) .data .balign 8 - .global efi32_boot_gdt -efi32_boot_gdt: .word 0 - .quad 0 - -save_gdt: .word 0 - .quad 0 -func_rt_ptr: .quad 0 +SYM_DATA_START(efi32_boot_gdt) + .word 0 + .quad 0 +SYM_DATA_END(efi32_boot_gdt) - .global efi_gdt64 -efi_gdt64: +SYM_DATA_START(efi_gdt64) .word efi_gdt64_end - efi_gdt64 .long 0 /* Filled out by user */ .word 0 @@ -194,4 +166,4 @@ efi_gdt64: .quad 0x00cf92000000ffff /* __KERNEL_DS */ .quad 0x0080890000000000 /* TS descriptor */ .quad 0x0000000000000000 /* TS continued */ -efi_gdt64_end: +SYM_DATA_END_LABEL(efi_gdt64, SYM_L_LOCAL, efi_gdt64_end) diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 37380c0d5999..73f17d0544dd 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -61,7 +61,7 @@ .hidden _egot __HEAD -ENTRY(startup_32) +SYM_FUNC_START(startup_32) cld /* * Test KEEP_SEGMENTS flag to see if the bootloader is asking @@ -140,76 +140,25 @@ ENTRY(startup_32) /* * Jump to the relocated address. */ - leal relocated(%ebx), %eax + leal .Lrelocated(%ebx), %eax jmp *%eax -ENDPROC(startup_32) +SYM_FUNC_END(startup_32) #ifdef CONFIG_EFI_STUB -/* - * We don't need the return address, so set up the stack so efi_main() can find - * its arguments. - */ -ENTRY(efi_pe_entry) - add $0x4, %esp - - call 1f -1: popl %esi - subl $1b, %esi - - popl %ecx - movl %ecx, efi32_config(%esi) /* Handle */ - popl %ecx - movl %ecx, efi32_config+8(%esi) /* EFI System table pointer */ - - /* Relocate efi_config->call() */ - leal efi32_config(%esi), %eax - add %esi, 40(%eax) - pushl %eax - - call make_boot_params - cmpl $0, %eax - je fail - movl %esi, BP_code32_start(%eax) - popl %ecx - pushl %eax - pushl %ecx - jmp 2f /* Skip efi_config initialization */ -ENDPROC(efi_pe_entry) - -ENTRY(efi32_stub_entry) +SYM_FUNC_START(efi32_stub_entry) +SYM_FUNC_START_ALIAS(efi_stub_entry) add $0x4, %esp - popl %ecx - popl %edx - - call 1f -1: popl %esi - subl $1b, %esi - - movl %ecx, efi32_config(%esi) /* Handle */ - movl %edx, efi32_config+8(%esi) /* EFI System table pointer */ - - /* Relocate efi_config->call() */ - leal efi32_config(%esi), %eax - add %esi, 40(%eax) - pushl %eax -2: call efi_main - cmpl $0, %eax movl %eax, %esi - jne 2f -fail: - /* EFI init failed, so hang. */ - hlt - jmp fail -2: movl BP_code32_start(%esi), %eax leal startup_32(%eax), %eax jmp *%eax -ENDPROC(efi32_stub_entry) +SYM_FUNC_END(efi32_stub_entry) +SYM_FUNC_END_ALIAS(efi_stub_entry) #endif .text -relocated: +SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) /* * Clear BSS (stack is currently empty) @@ -240,11 +189,9 @@ relocated: /* push arguments for extract_kernel: */ pushl $z_output_len /* decompressed length, end of relocs */ - movl BP_init_size(%esi), %eax - subl $_end, %eax - movl %ebx, %ebp - subl %eax, %ebp - pushl %ebp /* output address */ + leal _end(%ebx), %eax + subl BP_init_size(%esi), %eax + pushl %eax /* output address */ pushl $z_input_len /* input_len */ leal input_data(%ebx), %eax @@ -260,15 +207,7 @@ relocated: */ xorl %ebx, %ebx jmp *%eax - -#ifdef CONFIG_EFI_STUB - .data -efi32_config: - .fill 5,8,0 - .long efi_call_phys - .long 0 - .byte 0 -#endif +SYM_FUNC_END(.Lrelocated) /* * Stack and heap for uncompression diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 6233ae35d0d9..1f1f6c8139b3 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -45,7 +45,7 @@ __HEAD .code32 -ENTRY(startup_32) +SYM_FUNC_START(startup_32) /* * 32bit entry is 0 and it is ABI so immutable! * If we come here directly from a bootloader, @@ -87,7 +87,7 @@ ENTRY(startup_32) call verify_cpu testl %eax, %eax - jnz no_longmode + jnz .Lno_longmode /* * Compute the delta between where we were compiled to run at @@ -208,10 +208,12 @@ ENTRY(startup_32) pushl $__KERNEL_CS leal startup_64(%ebp), %eax #ifdef CONFIG_EFI_MIXED - movl efi32_config(%ebp), %ebx - cmp $0, %ebx + movl efi32_boot_args(%ebp), %edi + cmp $0, %edi jz 1f - leal handover_entry(%ebp), %eax + leal efi64_stub_entry(%ebp), %eax + movl %esi, %edx + movl efi32_boot_args+4(%ebp), %esi 1: #endif pushl %eax @@ -222,35 +224,37 @@ ENTRY(startup_32) /* Jump from 32bit compatibility mode into 64bit mode. */ lret -ENDPROC(startup_32) +SYM_FUNC_END(startup_32) #ifdef CONFIG_EFI_MIXED .org 0x190 -ENTRY(efi32_stub_entry) +SYM_FUNC_START(efi32_stub_entry) add $0x4, %esp /* Discard return address */ popl %ecx popl %edx popl %esi - leal (BP_scratch+4)(%esi), %esp call 1f 1: pop %ebp subl $1b, %ebp - movl %ecx, efi32_config(%ebp) - movl %edx, efi32_config+8(%ebp) + movl %ecx, efi32_boot_args(%ebp) + movl %edx, efi32_boot_args+4(%ebp) sgdtl efi32_boot_gdt(%ebp) + movb $0, efi_is64(%ebp) - leal efi32_config(%ebp), %eax - movl %eax, efi_config(%ebp) + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 jmp startup_32 -ENDPROC(efi32_stub_entry) +SYM_FUNC_END(efi32_stub_entry) #endif .code64 .org 0x200 -ENTRY(startup_64) +SYM_CODE_START(startup_64) /* * 64bit entry is 0x200 and it is ABI so immutable! * We come here either from startup_32 or directly from a @@ -322,7 +326,7 @@ ENTRY(startup_64) 1: popq %rdi subq $1b, %rdi - call adjust_got + call .Ladjust_got /* * At this point we are in long mode with 4-level paging enabled, @@ -421,7 +425,7 @@ trampoline_return: /* The new adjustment is the relocation address */ movq %rbx, %rdi - call adjust_got + call .Ladjust_got /* * Copy the compressed kernel to the end of our buffer @@ -440,78 +444,26 @@ trampoline_return: /* * Jump to the relocated address. */ - leaq relocated(%rbx), %rax + leaq .Lrelocated(%rbx), %rax jmp *%rax +SYM_CODE_END(startup_64) #ifdef CONFIG_EFI_STUB - -/* The entry point for the PE/COFF executable is efi_pe_entry. */ -ENTRY(efi_pe_entry) - movq %rcx, efi64_config(%rip) /* Handle */ - movq %rdx, efi64_config+8(%rip) /* EFI System table pointer */ - - leaq efi64_config(%rip), %rax - movq %rax, efi_config(%rip) - - call 1f -1: popq %rbp - subq $1b, %rbp - - /* - * Relocate efi_config->call(). - */ - addq %rbp, efi64_config+40(%rip) - - movq %rax, %rdi - call make_boot_params - cmpq $0,%rax - je fail - mov %rax, %rsi - leaq startup_32(%rip), %rax - movl %eax, BP_code32_start(%rsi) - jmp 2f /* Skip the relocation */ - -handover_entry: - call 1f -1: popq %rbp - subq $1b, %rbp - - /* - * Relocate efi_config->call(). - */ - movq efi_config(%rip), %rax - addq %rbp, 40(%rax) -2: - movq efi_config(%rip), %rdi + .org 0x390 +SYM_FUNC_START(efi64_stub_entry) +SYM_FUNC_START_ALIAS(efi_stub_entry) + and $~0xf, %rsp /* realign the stack */ call efi_main movq %rax,%rsi - cmpq $0,%rax - jne 2f -fail: - /* EFI init failed, so hang. */ - hlt - jmp fail -2: movl BP_code32_start(%esi), %eax leaq startup_64(%rax), %rax jmp *%rax -ENDPROC(efi_pe_entry) - - .org 0x390 -ENTRY(efi64_stub_entry) - movq %rdi, efi64_config(%rip) /* Handle */ - movq %rsi, efi64_config+8(%rip) /* EFI System table pointer */ - - leaq efi64_config(%rip), %rax - movq %rax, efi_config(%rip) - - movq %rdx, %rsi - jmp handover_entry -ENDPROC(efi64_stub_entry) +SYM_FUNC_END(efi64_stub_entry) +SYM_FUNC_END_ALIAS(efi_stub_entry) #endif .text -relocated: +SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) /* * Clear BSS (stack is currently empty) @@ -540,6 +492,7 @@ relocated: * Jump to the decompressed kernel. */ jmp *%rax +SYM_FUNC_END(.Lrelocated) /* * Adjust the global offset table @@ -548,7 +501,7 @@ relocated: * first time we touch GOT). * RDI is the new adjustment to apply. */ -adjust_got: +.Ladjust_got: /* Walk through the GOT adding the address to the entries */ leaq _got(%rip), %rdx leaq _egot(%rip), %rcx @@ -570,7 +523,7 @@ adjust_got: * ECX contains the base address of the trampoline memory. * Non zero RDX means trampoline needs to enable 5-level paging. */ -ENTRY(trampoline_32bit_src) +SYM_CODE_START(trampoline_32bit_src) /* Set up data and stack segments */ movl $__KERNEL_DS, %eax movl %eax, %ds @@ -622,7 +575,7 @@ ENTRY(trampoline_32bit_src) movl %eax, %cr4 /* Calculate address of paging_enabled() once we are executing in the trampoline */ - leal paging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax + leal .Lpaging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax /* Prepare the stack for far return to Long Mode */ pushl $__KERNEL_CS @@ -633,11 +586,13 @@ ENTRY(trampoline_32bit_src) movl %eax, %cr0 lret +SYM_CODE_END(trampoline_32bit_src) .code64 -paging_enabled: +SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled) /* Return from the trampoline */ jmp *%rdi +SYM_FUNC_END(.Lpaging_enabled) /* * The trampoline code has a size limit. @@ -647,20 +602,22 @@ paging_enabled: .org trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE .code32 -no_longmode: +SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode) /* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */ 1: hlt jmp 1b +SYM_FUNC_END(.Lno_longmode) #include "../../kernel/verify_cpu.S" .data -gdt64: +SYM_DATA_START_LOCAL(gdt64) .word gdt_end - gdt .quad 0 +SYM_DATA_END(gdt64) .balign 8 -gdt: +SYM_DATA_START_LOCAL(gdt) .word gdt_end - gdt .long gdt .word 0 @@ -669,49 +626,33 @@ gdt: .quad 0x00cf92000000ffff /* __KERNEL_DS */ .quad 0x0080890000000000 /* TS descriptor */ .quad 0x0000000000000000 /* TS continued */ -gdt_end: - -#ifdef CONFIG_EFI_STUB -efi_config: - .quad 0 +SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) #ifdef CONFIG_EFI_MIXED - .global efi32_config -efi32_config: - .fill 5,8,0 - .quad efi64_thunk - .byte 0 +SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0) +SYM_DATA(efi_is64, .byte 1) #endif - .global efi64_config -efi64_config: - .fill 5,8,0 - .quad efi_call - .byte 1 -#endif /* CONFIG_EFI_STUB */ - /* * Stack and heap for uncompression */ .bss .balign 4 -boot_heap: - .fill BOOT_HEAP_SIZE, 1, 0 -boot_stack: +SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) + +SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 -boot_stack_end: +SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end) /* * Space for page tables (not in .bss so not zeroed) */ .section ".pgtable","a",@nobits .balign 4096 -pgtable: - .fill BOOT_PGT_SIZE, 1, 0 +SYM_DATA_LOCAL(pgtable, .fill BOOT_PGT_SIZE, 1, 0) /* * The page table is going to be used instead of page table in the trampoline * memory. */ -top_pgtable: - .fill PAGE_SIZE, 1, 0 +SYM_DATA_LOCAL(top_pgtable, .fill PAGE_SIZE, 1, 0) diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 2e53c056ba20..d7408af55738 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -132,8 +132,14 @@ char *skip_spaces(const char *str) #include "../../../../lib/ctype.c" #include "../../../../lib/cmdline.c" +enum parse_mode { + PARSE_MEMMAP, + PARSE_EFI, +}; + static int -parse_memmap(char *p, unsigned long long *start, unsigned long long *size) +parse_memmap(char *p, unsigned long long *start, unsigned long long *size, + enum parse_mode mode) { char *oldp; @@ -156,8 +162,29 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size) *start = memparse(p + 1, &p); return 0; case '@': - /* memmap=nn@ss specifies usable region, should be skipped */ - *size = 0; + if (mode == PARSE_MEMMAP) { + /* + * memmap=nn@ss specifies usable region, should + * be skipped + */ + *size = 0; + } else { + unsigned long long flags; + + /* + * efi_fake_mem=nn@ss:attr the attr specifies + * flags that might imply a soft-reservation. + */ + *start = memparse(p + 1, &p); + if (p && *p == ':') { + p++; + if (kstrtoull(p, 0, &flags) < 0) + *size = 0; + else if (flags & EFI_MEMORY_SP) + return 0; + } + *size = 0; + } /* Fall through */ default: /* @@ -172,7 +199,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size) return -EINVAL; } -static void mem_avoid_memmap(char *str) +static void mem_avoid_memmap(enum parse_mode mode, char *str) { static int i; @@ -187,7 +214,7 @@ static void mem_avoid_memmap(char *str) if (k) *k++ = 0; - rc = parse_memmap(str, &start, &size); + rc = parse_memmap(str, &start, &size, mode); if (rc < 0) break; str = k; @@ -238,7 +265,6 @@ static void parse_gb_huge_pages(char *param, char *val) } } - static void handle_mem_options(void) { char *args = (char *)get_cmd_line_ptr(); @@ -271,7 +297,7 @@ static void handle_mem_options(void) } if (!strcmp(param, "memmap")) { - mem_avoid_memmap(val); + mem_avoid_memmap(PARSE_MEMMAP, val); } else if (strstr(param, "hugepages")) { parse_gb_huge_pages(param, val); } else if (!strcmp(param, "mem")) { @@ -284,6 +310,8 @@ static void handle_mem_options(void) goto out; mem_limit = mem_size; + } else if (!strcmp(param, "efi_fake_mem")) { + mem_avoid_memmap(PARSE_EFI, val); } } @@ -459,6 +487,18 @@ static bool mem_avoid_overlap(struct mem_vector *img, is_overlapping = true; } + if (ptr->type == SETUP_INDIRECT && + ((struct setup_indirect *)ptr->data)->type != SETUP_INDIRECT) { + avoid.start = ((struct setup_indirect *)ptr->data)->addr; + avoid.size = ((struct setup_indirect *)ptr->data)->len; + + if (mem_overlaps(img, &avoid) && (avoid.start < earliest)) { + *overlap = avoid; + earliest = overlap->start; + is_overlapping = true; + } + } + ptr = (struct setup_data *)(unsigned long)ptr->next; } @@ -760,6 +800,10 @@ process_efi_entries(unsigned long minimum, unsigned long image_size) if (md->type != EFI_CONVENTIONAL_MEMORY) continue; + if (efi_soft_reserve_enabled() && + (md->attribute & EFI_MEMORY_SP)) + continue; + if (efi_mirror_found && !(md->attribute & EFI_MEMORY_MORE_RELIABLE)) continue; diff --git a/arch/x86/boot/compressed/kernel_info.S b/arch/x86/boot/compressed/kernel_info.S new file mode 100644 index 000000000000..f818ee8fba38 --- /dev/null +++ b/arch/x86/boot/compressed/kernel_info.S @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <asm/bootparam.h> + + .section ".rodata.kernel_info", "a" + + .global kernel_info + +kernel_info: + /* Header, Linux top (structure). */ + .ascii "LToP" + /* Size. */ + .long kernel_info_var_len_data - kernel_info + /* Size total. */ + .long kernel_info_end - kernel_info + + /* Maximal allowed type for setup_data and setup_indirect structs. */ + .long SETUP_TYPE_MAX + +kernel_info_var_len_data: + /* Empty for time being... */ +kernel_info_end: diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index 6afb7130a387..dd07e7b41b11 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -15,7 +15,7 @@ .text .code32 -ENTRY(get_sev_encryption_bit) +SYM_FUNC_START(get_sev_encryption_bit) xor %eax, %eax #ifdef CONFIG_AMD_MEM_ENCRYPT @@ -65,10 +65,10 @@ ENTRY(get_sev_encryption_bit) #endif /* CONFIG_AMD_MEM_ENCRYPT */ ret -ENDPROC(get_sev_encryption_bit) +SYM_FUNC_END(get_sev_encryption_bit) .code64 -ENTRY(set_sev_encryption_mask) +SYM_FUNC_START(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT push %rbp push %rdx @@ -90,12 +90,11 @@ ENTRY(set_sev_encryption_mask) xor %rax, %rax ret -ENDPROC(set_sev_encryption_mask) +SYM_FUNC_END(set_sev_encryption_mask) .data #ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 -GLOBAL(sme_me_mask) - .quad 0 +SYM_DATA(sme_me_mask, .quad 0) #endif diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 53ac0cb2396d..9652d5c2afda 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -345,6 +345,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, { const unsigned long kernel_total_size = VO__end - VO__text; unsigned long virt_addr = LOAD_PHYSICAL_ADDR; + unsigned long needed_size; /* Retain x86 boot parameters pointer passed from startup_32/64. */ boot_params = rmode; @@ -379,26 +380,38 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; + /* + * The memory hole needed for the kernel is the larger of either + * the entire decompressed kernel plus relocation table, or the + * entire decompressed kernel plus .bss and .brk sections. + * + * On X86_64, the memory is mapped with PMD pages. Round the + * size up so that the full extent of PMD pages mapped is + * included in the check against the valid memory table + * entries. This ensures the full mapped area is usable RAM + * and doesn't include any reserved areas. + */ + needed_size = max(output_len, kernel_total_size); +#ifdef CONFIG_X86_64 + needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN); +#endif + /* Report initial kernel position details. */ debug_putaddr(input_data); debug_putaddr(input_len); debug_putaddr(output); debug_putaddr(output_len); debug_putaddr(kernel_total_size); + debug_putaddr(needed_size); #ifdef CONFIG_X86_64 /* Report address of 32-bit trampoline */ debug_putaddr(trampoline_32bit); #endif - /* - * The memory hole needed for the kernel is the larger of either - * the entire decompressed kernel plus relocation table, or the - * entire decompressed kernel plus .bss and .brk sections. - */ choose_random_location((unsigned long)input_data, input_len, (unsigned long *)&output, - max(output_len, kernel_total_size), + needed_size, &virt_addr); /* Validate memory location choices. */ diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 5f2d03067ae5..c8862696a47b 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -72,6 +72,8 @@ static unsigned long find_trampoline_placement(void) /* Find the first usable memory region under bios_start. */ for (i = boot_params->e820_entries - 1; i >= 0; i--) { + unsigned long new = bios_start; + entry = &boot_params->e820_table[i]; /* Skip all entries above bios_start. */ @@ -84,15 +86,20 @@ static unsigned long find_trampoline_placement(void) /* Adjust bios_start to the end of the entry if needed. */ if (bios_start > entry->addr + entry->size) - bios_start = entry->addr + entry->size; + new = entry->addr + entry->size; /* Keep bios_start page-aligned. */ - bios_start = round_down(bios_start, PAGE_SIZE); + new = round_down(new, PAGE_SIZE); /* Skip the entry if it's too small. */ - if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr) + if (new - TRAMPOLINE_32BIT_SIZE < entry->addr) continue; + /* Protect against underflow. */ + if (new - TRAMPOLINE_32BIT_SIZE > bios_start) + break; + + bios_start = new; break; } diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S index 4c5f4f4ad035..6afd05e819d2 100644 --- a/arch/x86/boot/copy.S +++ b/arch/x86/boot/copy.S @@ -15,7 +15,7 @@ .code16 .text -GLOBAL(memcpy) +SYM_FUNC_START_NOALIGN(memcpy) pushw %si pushw %di movw %ax, %di @@ -29,9 +29,9 @@ GLOBAL(memcpy) popw %di popw %si retl -ENDPROC(memcpy) +SYM_FUNC_END(memcpy) -GLOBAL(memset) +SYM_FUNC_START_NOALIGN(memset) pushw %di movw %ax, %di movzbl %dl, %eax @@ -44,22 +44,22 @@ GLOBAL(memset) rep; stosb popw %di retl -ENDPROC(memset) +SYM_FUNC_END(memset) -GLOBAL(copy_from_fs) +SYM_FUNC_START_NOALIGN(copy_from_fs) pushw %ds pushw %fs popw %ds calll memcpy popw %ds retl -ENDPROC(copy_from_fs) +SYM_FUNC_END(copy_from_fs) -GLOBAL(copy_to_fs) +SYM_FUNC_START_NOALIGN(copy_to_fs) pushw %es pushw %fs popw %es calll memcpy popw %es retl -ENDPROC(copy_to_fs) +SYM_FUNC_END(copy_to_fs) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 2c11c0f45d49..97d9b6d6c1af 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -300,7 +300,7 @@ _start: # Part 2 of the header, from the old setup.S .ascii "HdrS" # header signature - .word 0x020d # header version number (>= 0x0105) + .word 0x020f # header version number (>= 0x0105) # or else old loadlin-1.5 will fail) .globl realmode_swtch realmode_swtch: .word 0, 0 # default_switch, SETUPSEG @@ -567,6 +567,7 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr init_size: .long INIT_SIZE # kernel initialization size handover_offset: .long 0 # Filled in by build.c +kernel_info_offset: .long 0 # Filled in by build.c # End of setup header ##################################################### diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index 996df3d586f0..e3add857c2c9 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -10,6 +10,7 @@ /* * Main module for the real-mode kernel code */ +#include <linux/build_bug.h> #include "boot.h" #include "string.h" diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c index 9caa10e82217..da0ccc5de538 100644 --- a/arch/x86/boot/mkcpustr.c +++ b/arch/x86/boot/mkcpustr.c @@ -15,6 +15,7 @@ #include "../include/asm/required-features.h" #include "../include/asm/disabled-features.h" #include "../include/asm/cpufeatures.h" +#include "../include/asm/vmxfeatures.h" #include "../kernel/cpu/capflags.c" int main(void) diff --git a/arch/x86/boot/pmjump.S b/arch/x86/boot/pmjump.S index c22f9a7d1aeb..cbec8bd0841f 100644 --- a/arch/x86/boot/pmjump.S +++ b/arch/x86/boot/pmjump.S @@ -21,7 +21,7 @@ /* * void protected_mode_jump(u32 entrypoint, u32 bootparams); */ -GLOBAL(protected_mode_jump) +SYM_FUNC_START_NOALIGN(protected_mode_jump) movl %edx, %esi # Pointer to boot_params table xorl %ebx, %ebx @@ -40,13 +40,13 @@ GLOBAL(protected_mode_jump) # Transition to 32-bit mode .byte 0x66, 0xea # ljmpl opcode -2: .long in_pm32 # offset +2: .long .Lin_pm32 # offset .word __BOOT_CS # segment -ENDPROC(protected_mode_jump) +SYM_FUNC_END(protected_mode_jump) .code32 .section ".text32","ax" -GLOBAL(in_pm32) +SYM_FUNC_START_LOCAL_NOALIGN(.Lin_pm32) # Set up data segments for flat 32-bit mode movl %ecx, %ds movl %ecx, %es @@ -72,4 +72,4 @@ GLOBAL(in_pm32) lldt %cx jmpl *%eax # Jump to the 32-bit entrypoint -ENDPROC(in_pm32) +SYM_FUNC_END(.Lin_pm32) diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 0149e41d42c2..3da1c37c6dd5 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -51,7 +51,10 @@ SECTIONS . = ALIGN(16); _end = .; - /DISCARD/ : { *(.note*) } + /DISCARD/ : { + *(.eh_frame) + *(.note*) + } /* * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility: diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index a93d44e58f9c..55e669d29e54 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -56,6 +56,7 @@ u8 buf[SETUP_SECT_MAX*512]; unsigned long efi32_stub_entry; unsigned long efi64_stub_entry; unsigned long efi_pe_entry; +unsigned long kernel_info; unsigned long startup_64; /*----------------------------------------------------------------------*/ @@ -321,6 +322,7 @@ static void parse_zoffset(char *fname) PARSE_ZOFS(p, efi32_stub_entry); PARSE_ZOFS(p, efi64_stub_entry); PARSE_ZOFS(p, efi_pe_entry); + PARSE_ZOFS(p, kernel_info); PARSE_ZOFS(p, startup_64); p = strchr(p, '\n'); @@ -410,6 +412,9 @@ int main(int argc, char ** argv) efi_stub_entry_update(); + /* Update kernel_info offset. */ + put_unaligned_le32(kernel_info, &buf[0x268]); + crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, dest) != i) die("Writing setup failed"); diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index d0a5ffeae8df..0b9654c7a05c 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -25,7 +25,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_SMP=y -CONFIG_CALGARY_IOMMU=y CONFIG_NR_CPUS=64 CONFIG_SCHED_SMT=y CONFIG_PREEMPT_VOLUNTARY=y diff --git a/arch/x86/crypto/.gitignore b/arch/x86/crypto/.gitignore new file mode 100644 index 000000000000..30be0400a439 --- /dev/null +++ b/arch/x86/crypto/.gitignore @@ -0,0 +1 @@ +poly1305-x86_64-cryptogams.S diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 45734e1cf967..b69e00bf20b8 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -14,11 +14,9 @@ sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o -obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o -obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o @@ -38,17 +36,10 @@ obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o -obj-$(CONFIG_CRYPTO_AEGIS128L_AESNI_SSE2) += aegis128l-aesni.o -obj-$(CONFIG_CRYPTO_AEGIS256_AESNI_SSE2) += aegis256-aesni.o - -obj-$(CONFIG_CRYPTO_MORUS640_GLUE) += morus640_glue.o -obj-$(CONFIG_CRYPTO_MORUS1280_GLUE) += morus1280_glue.o - -obj-$(CONFIG_CRYPTO_MORUS640_SSE2) += morus640-sse2.o -obj-$(CONFIG_CRYPTO_MORUS1280_SSE2) += morus1280-sse2.o obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o +obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o # These modules require assembler to support AVX. ifeq ($(avx_supported),yes) @@ -58,21 +49,18 @@ ifeq ($(avx_supported),yes) obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o + obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o endif # These modules require assembler to support AVX2. ifeq ($(avx2_supported),yes) obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o - - obj-$(CONFIG_CRYPTO_MORUS1280_AVX2) += morus1280-avx2.o endif -aes-i586-y := aes-i586-asm_32.o aes_glue.o twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o -aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o @@ -82,13 +70,13 @@ chacha-x86_64-y := chacha-ssse3-x86_64.o chacha_glue.o serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o -aegis128l-aesni-y := aegis128l-aesni-asm.o aegis128l-aesni-glue.o -aegis256-aesni-y := aegis256-aesni-asm.o aegis256-aesni-glue.o - -morus640-sse2-y := morus640-sse2-asm.o morus640-sse2-glue.o -morus1280-sse2-y := morus1280-sse2-asm.o morus1280-sse2-glue.o nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o +blake2s-x86_64-y := blake2s-core.o blake2s-glue.o +poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o +ifneq ($(CONFIG_CRYPTO_POLY1305_X86_64),) +targets += poly1305-x86_64-cryptogams.S +endif ifeq ($(avx_supported),yes) camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \ @@ -106,8 +94,6 @@ ifeq ($(avx2_supported),yes) chacha-x86_64-y += chacha-avx2-x86_64.o serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o - morus1280-avx2-y := morus1280-avx2-asm.o morus1280-avx2-glue.o - nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o endif @@ -119,10 +105,8 @@ aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o -poly1305-x86_64-y := poly1305-sse2-x86_64.o poly1305_glue.o ifeq ($(avx2_supported),yes) sha1-ssse3-y += sha1_avx2_x86_64_asm.o -poly1305-x86_64-y += poly1305-avx2-x86_64.o endif ifeq ($(sha1_ni_supported),yes) sha1-ssse3-y += sha1_ni_asm.o @@ -136,3 +120,8 @@ sha256-ssse3-y += sha256_ni_asm.o endif sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o + +quiet_cmd_perlasm = PERLASM $@ + cmd_perlasm = $(PERL) $< > $@ +$(obj)/%.S: $(src)/%.pl FORCE + $(call if_changed,perlasm) diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index 4434607e366d..51d46d93efbc 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -71,7 +71,7 @@ * %r8 * %r9 */ -__load_partial: +SYM_FUNC_START_LOCAL(__load_partial) xor %r9d, %r9d pxor MSG, MSG @@ -123,7 +123,7 @@ __load_partial: .Lld_partial_8: ret -ENDPROC(__load_partial) +SYM_FUNC_END(__load_partial) /* * __store_partial: internal ABI @@ -137,7 +137,7 @@ ENDPROC(__load_partial) * %r9 * %r10 */ -__store_partial: +SYM_FUNC_START_LOCAL(__store_partial) mov LEN, %r8 mov DST, %r9 @@ -181,12 +181,12 @@ __store_partial: .Lst_partial_1: ret -ENDPROC(__store_partial) +SYM_FUNC_END(__store_partial) /* * void crypto_aegis128_aesni_init(void *state, const void *key, const void *iv); */ -ENTRY(crypto_aegis128_aesni_init) +SYM_FUNC_START(crypto_aegis128_aesni_init) FRAME_BEGIN /* load IV: */ @@ -226,13 +226,13 @@ ENTRY(crypto_aegis128_aesni_init) FRAME_END ret -ENDPROC(crypto_aegis128_aesni_init) +SYM_FUNC_END(crypto_aegis128_aesni_init) /* * void crypto_aegis128_aesni_ad(void *state, unsigned int length, * const void *data); */ -ENTRY(crypto_aegis128_aesni_ad) +SYM_FUNC_START(crypto_aegis128_aesni_ad) FRAME_BEGIN cmp $0x10, LEN @@ -378,7 +378,7 @@ ENTRY(crypto_aegis128_aesni_ad) .Lad_out: FRAME_END ret -ENDPROC(crypto_aegis128_aesni_ad) +SYM_FUNC_END(crypto_aegis128_aesni_ad) .macro encrypt_block a s0 s1 s2 s3 s4 i movdq\a (\i * 0x10)(SRC), MSG @@ -402,7 +402,7 @@ ENDPROC(crypto_aegis128_aesni_ad) * void crypto_aegis128_aesni_enc(void *state, unsigned int length, * const void *src, void *dst); */ -ENTRY(crypto_aegis128_aesni_enc) +SYM_FUNC_START(crypto_aegis128_aesni_enc) FRAME_BEGIN cmp $0x10, LEN @@ -493,13 +493,13 @@ ENTRY(crypto_aegis128_aesni_enc) .Lenc_out: FRAME_END ret -ENDPROC(crypto_aegis128_aesni_enc) +SYM_FUNC_END(crypto_aegis128_aesni_enc) /* * void crypto_aegis128_aesni_enc_tail(void *state, unsigned int length, * const void *src, void *dst); */ -ENTRY(crypto_aegis128_aesni_enc_tail) +SYM_FUNC_START(crypto_aegis128_aesni_enc_tail) FRAME_BEGIN /* load the state: */ @@ -533,7 +533,7 @@ ENTRY(crypto_aegis128_aesni_enc_tail) FRAME_END ret -ENDPROC(crypto_aegis128_aesni_enc_tail) +SYM_FUNC_END(crypto_aegis128_aesni_enc_tail) .macro decrypt_block a s0 s1 s2 s3 s4 i movdq\a (\i * 0x10)(SRC), MSG @@ -556,7 +556,7 @@ ENDPROC(crypto_aegis128_aesni_enc_tail) * void crypto_aegis128_aesni_dec(void *state, unsigned int length, * const void *src, void *dst); */ -ENTRY(crypto_aegis128_aesni_dec) +SYM_FUNC_START(crypto_aegis128_aesni_dec) FRAME_BEGIN cmp $0x10, LEN @@ -647,13 +647,13 @@ ENTRY(crypto_aegis128_aesni_dec) .Ldec_out: FRAME_END ret -ENDPROC(crypto_aegis128_aesni_dec) +SYM_FUNC_END(crypto_aegis128_aesni_dec) /* * void crypto_aegis128_aesni_dec_tail(void *state, unsigned int length, * const void *src, void *dst); */ -ENTRY(crypto_aegis128_aesni_dec_tail) +SYM_FUNC_START(crypto_aegis128_aesni_dec_tail) FRAME_BEGIN /* load the state: */ @@ -697,13 +697,13 @@ ENTRY(crypto_aegis128_aesni_dec_tail) FRAME_END ret -ENDPROC(crypto_aegis128_aesni_dec_tail) +SYM_FUNC_END(crypto_aegis128_aesni_dec_tail) /* * void crypto_aegis128_aesni_final(void *state, void *tag_xor, * u64 assoclen, u64 cryptlen); */ -ENTRY(crypto_aegis128_aesni_final) +SYM_FUNC_START(crypto_aegis128_aesni_final) FRAME_BEGIN /* load the state: */ @@ -744,4 +744,4 @@ ENTRY(crypto_aegis128_aesni_final) FRAME_END ret -ENDPROC(crypto_aegis128_aesni_final) +SYM_FUNC_END(crypto_aegis128_aesni_final) diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index 46d227122643..4623189000d8 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -144,10 +144,8 @@ static int crypto_aegis128_aesni_setkey(struct crypto_aead *aead, const u8 *key, { struct aegis_ctx *ctx = crypto_aegis128_aesni_ctx(aead); - if (keylen != AEGIS128_KEY_SIZE) { - crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); + if (keylen != AEGIS128_KEY_SIZE) return -EINVAL; - } memcpy(ctx->key.bytes, key, AEGIS128_KEY_SIZE); diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S deleted file mode 100644 index 1461ef00c0e8..000000000000 --- a/arch/x86/crypto/aegis128l-aesni-asm.S +++ /dev/null @@ -1,823 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * AES-NI + SSE2 implementation of AEGIS-128L - * - * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <linux/linkage.h> -#include <asm/frame.h> - -#define STATE0 %xmm0 -#define STATE1 %xmm1 -#define STATE2 %xmm2 -#define STATE3 %xmm3 -#define STATE4 %xmm4 -#define STATE5 %xmm5 -#define STATE6 %xmm6 -#define STATE7 %xmm7 -#define MSG0 %xmm8 -#define MSG1 %xmm9 -#define T0 %xmm10 -#define T1 %xmm11 -#define T2 %xmm12 -#define T3 %xmm13 - -#define STATEP %rdi -#define LEN %rsi -#define SRC %rdx -#define DST %rcx - -.section .rodata.cst16.aegis128l_const, "aM", @progbits, 32 -.align 16 -.Laegis128l_const_0: - .byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d - .byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62 -.Laegis128l_const_1: - .byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1 - .byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd - -.section .rodata.cst16.aegis128l_counter, "aM", @progbits, 16 -.align 16 -.Laegis128l_counter0: - .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07 - .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f -.Laegis128l_counter1: - .byte 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17 - .byte 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f - -.text - -/* - * __load_partial: internal ABI - * input: - * LEN - bytes - * SRC - src - * output: - * MSG0 - first message block - * MSG1 - second message block - * changed: - * T0 - * %r8 - * %r9 - */ -__load_partial: - xor %r9d, %r9d - pxor MSG0, MSG0 - pxor MSG1, MSG1 - - mov LEN, %r8 - and $0x1, %r8 - jz .Lld_partial_1 - - mov LEN, %r8 - and $0x1E, %r8 - add SRC, %r8 - mov (%r8), %r9b - -.Lld_partial_1: - mov LEN, %r8 - and $0x2, %r8 - jz .Lld_partial_2 - - mov LEN, %r8 - and $0x1C, %r8 - add SRC, %r8 - shl $0x10, %r9 - mov (%r8), %r9w - -.Lld_partial_2: - mov LEN, %r8 - and $0x4, %r8 - jz .Lld_partial_4 - - mov LEN, %r8 - and $0x18, %r8 - add SRC, %r8 - shl $32, %r9 - mov (%r8), %r8d - xor %r8, %r9 - -.Lld_partial_4: - movq %r9, MSG0 - - mov LEN, %r8 - and $0x8, %r8 - jz .Lld_partial_8 - - mov LEN, %r8 - and $0x10, %r8 - add SRC, %r8 - pslldq $8, MSG0 - movq (%r8), T0 - pxor T0, MSG0 - -.Lld_partial_8: - mov LEN, %r8 - and $0x10, %r8 - jz .Lld_partial_16 - - movdqa MSG0, MSG1 - movdqu (SRC), MSG0 - -.Lld_partial_16: - ret -ENDPROC(__load_partial) - -/* - * __store_partial: internal ABI - * input: - * LEN - bytes - * DST - dst - * output: - * T0 - first message block - * T1 - second message block - * changed: - * %r8 - * %r9 - * %r10 - */ -__store_partial: - mov LEN, %r8 - mov DST, %r9 - - cmp $16, %r8 - jl .Lst_partial_16 - - movdqu T0, (%r9) - movdqa T1, T0 - - sub $16, %r8 - add $16, %r9 - -.Lst_partial_16: - movq T0, %r10 - - cmp $8, %r8 - jl .Lst_partial_8 - - mov %r10, (%r9) - psrldq $8, T0 - movq T0, %r10 - - sub $8, %r8 - add $8, %r9 - -.Lst_partial_8: - cmp $4, %r8 - jl .Lst_partial_4 - - mov %r10d, (%r9) - shr $32, %r10 - - sub $4, %r8 - add $4, %r9 - -.Lst_partial_4: - cmp $2, %r8 - jl .Lst_partial_2 - - mov %r10w, (%r9) - shr $0x10, %r10 - - sub $2, %r8 - add $2, %r9 - -.Lst_partial_2: - cmp $1, %r8 - jl .Lst_partial_1 - - mov %r10b, (%r9) - -.Lst_partial_1: - ret -ENDPROC(__store_partial) - -.macro update - movdqa STATE7, T0 - aesenc STATE0, STATE7 - aesenc STATE1, STATE0 - aesenc STATE2, STATE1 - aesenc STATE3, STATE2 - aesenc STATE4, STATE3 - aesenc STATE5, STATE4 - aesenc STATE6, STATE5 - aesenc T0, STATE6 -.endm - -.macro update0 - update - pxor MSG0, STATE7 - pxor MSG1, STATE3 -.endm - -.macro update1 - update - pxor MSG0, STATE6 - pxor MSG1, STATE2 -.endm - -.macro update2 - update - pxor MSG0, STATE5 - pxor MSG1, STATE1 -.endm - -.macro update3 - update - pxor MSG0, STATE4 - pxor MSG1, STATE0 -.endm - -.macro update4 - update - pxor MSG0, STATE3 - pxor MSG1, STATE7 -.endm - -.macro update5 - update - pxor MSG0, STATE2 - pxor MSG1, STATE6 -.endm - -.macro update6 - update - pxor MSG0, STATE1 - pxor MSG1, STATE5 -.endm - -.macro update7 - update - pxor MSG0, STATE0 - pxor MSG1, STATE4 -.endm - -.macro state_load - movdqu 0x00(STATEP), STATE0 - movdqu 0x10(STATEP), STATE1 - movdqu 0x20(STATEP), STATE2 - movdqu 0x30(STATEP), STATE3 - movdqu 0x40(STATEP), STATE4 - movdqu 0x50(STATEP), STATE5 - movdqu 0x60(STATEP), STATE6 - movdqu 0x70(STATEP), STATE7 -.endm - -.macro state_store s0 s1 s2 s3 s4 s5 s6 s7 - movdqu \s7, 0x00(STATEP) - movdqu \s0, 0x10(STATEP) - movdqu \s1, 0x20(STATEP) - movdqu \s2, 0x30(STATEP) - movdqu \s3, 0x40(STATEP) - movdqu \s4, 0x50(STATEP) - movdqu \s5, 0x60(STATEP) - movdqu \s6, 0x70(STATEP) -.endm - -.macro state_store0 - state_store STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 -.endm - -.macro state_store1 - state_store STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 -.endm - -.macro state_store2 - state_store STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 -.endm - -.macro state_store3 - state_store STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 -.endm - -.macro state_store4 - state_store STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 -.endm - -.macro state_store5 - state_store STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 -.endm - -.macro state_store6 - state_store STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 -.endm - -.macro state_store7 - state_store STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 -.endm - -/* - * void crypto_aegis128l_aesni_init(void *state, const void *key, const void *iv); - */ -ENTRY(crypto_aegis128l_aesni_init) - FRAME_BEGIN - - /* load key: */ - movdqa (%rsi), MSG1 - movdqa MSG1, STATE0 - movdqa MSG1, STATE4 - movdqa MSG1, STATE5 - movdqa MSG1, STATE6 - movdqa MSG1, STATE7 - - /* load IV: */ - movdqu (%rdx), MSG0 - pxor MSG0, STATE0 - pxor MSG0, STATE4 - - /* load the constants: */ - movdqa .Laegis128l_const_0, STATE2 - movdqa .Laegis128l_const_1, STATE1 - movdqa STATE1, STATE3 - pxor STATE2, STATE5 - pxor STATE1, STATE6 - pxor STATE2, STATE7 - - /* update 10 times with IV and KEY: */ - update0 - update1 - update2 - update3 - update4 - update5 - update6 - update7 - update0 - update1 - - state_store1 - - FRAME_END - ret -ENDPROC(crypto_aegis128l_aesni_init) - -.macro ad_block a i - movdq\a (\i * 0x20 + 0x00)(SRC), MSG0 - movdq\a (\i * 0x20 + 0x10)(SRC), MSG1 - update\i - sub $0x20, LEN - cmp $0x20, LEN - jl .Lad_out_\i -.endm - -/* - * void crypto_aegis128l_aesni_ad(void *state, unsigned int length, - * const void *data); - */ -ENTRY(crypto_aegis128l_aesni_ad) - FRAME_BEGIN - - cmp $0x20, LEN - jb .Lad_out - - state_load - - mov SRC, %r8 - and $0xf, %r8 - jnz .Lad_u_loop - -.align 8 -.Lad_a_loop: - ad_block a 0 - ad_block a 1 - ad_block a 2 - ad_block a 3 - ad_block a 4 - ad_block a 5 - ad_block a 6 - ad_block a 7 - - add $0x100, SRC - jmp .Lad_a_loop - -.align 8 -.Lad_u_loop: - ad_block u 0 - ad_block u 1 - ad_block u 2 - ad_block u 3 - ad_block u 4 - ad_block u 5 - ad_block u 6 - ad_block u 7 - - add $0x100, SRC - jmp .Lad_u_loop - -.Lad_out_0: - state_store0 - FRAME_END - ret - -.Lad_out_1: - state_store1 - FRAME_END - ret - -.Lad_out_2: - state_store2 - FRAME_END - ret - -.Lad_out_3: - state_store3 - FRAME_END - ret - -.Lad_out_4: - state_store4 - FRAME_END - ret - -.Lad_out_5: - state_store5 - FRAME_END - ret - -.Lad_out_6: - state_store6 - FRAME_END - ret - -.Lad_out_7: - state_store7 - FRAME_END - ret - -.Lad_out: - FRAME_END - ret -ENDPROC(crypto_aegis128l_aesni_ad) - -.macro crypt m0 m1 s0 s1 s2 s3 s4 s5 s6 s7 - pxor \s1, \m0 - pxor \s6, \m0 - movdqa \s2, T3 - pand \s3, T3 - pxor T3, \m0 - - pxor \s2, \m1 - pxor \s5, \m1 - movdqa \s6, T3 - pand \s7, T3 - pxor T3, \m1 -.endm - -.macro crypt0 m0 m1 - crypt \m0 \m1 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 -.endm - -.macro crypt1 m0 m1 - crypt \m0 \m1 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 -.endm - -.macro crypt2 m0 m1 - crypt \m0 \m1 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 -.endm - -.macro crypt3 m0 m1 - crypt \m0 \m1 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 STATE4 -.endm - -.macro crypt4 m0 m1 - crypt \m0 \m1 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 STATE3 -.endm - -.macro crypt5 m0 m1 - crypt \m0 \m1 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 STATE2 -.endm - -.macro crypt6 m0 m1 - crypt \m0 \m1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 STATE1 -.endm - -.macro crypt7 m0 m1 - crypt \m0 \m1 STATE1 STATE2 STATE3 STATE4 STATE5 STATE6 STATE7 STATE0 -.endm - -.macro encrypt_block a i - movdq\a (\i * 0x20 + 0x00)(SRC), MSG0 - movdq\a (\i * 0x20 + 0x10)(SRC), MSG1 - movdqa MSG0, T0 - movdqa MSG1, T1 - crypt\i T0, T1 - movdq\a T0, (\i * 0x20 + 0x00)(DST) - movdq\a T1, (\i * 0x20 + 0x10)(DST) - - update\i - - sub $0x20, LEN - cmp $0x20, LEN - jl .Lenc_out_\i -.endm - -.macro decrypt_block a i - movdq\a (\i * 0x20 + 0x00)(SRC), MSG0 - movdq\a (\i * 0x20 + 0x10)(SRC), MSG1 - crypt\i MSG0, MSG1 - movdq\a MSG0, (\i * 0x20 + 0x00)(DST) - movdq\a MSG1, (\i * 0x20 + 0x10)(DST) - - update\i - - sub $0x20, LEN - cmp $0x20, LEN - jl .Ldec_out_\i -.endm - -/* - * void crypto_aegis128l_aesni_enc(void *state, unsigned int length, - * const void *src, void *dst); - */ -ENTRY(crypto_aegis128l_aesni_enc) - FRAME_BEGIN - - cmp $0x20, LEN - jb .Lenc_out - - state_load - - mov SRC, %r8 - or DST, %r8 - and $0xf, %r8 - jnz .Lenc_u_loop - -.align 8 -.Lenc_a_loop: - encrypt_block a 0 - encrypt_block a 1 - encrypt_block a 2 - encrypt_block a 3 - encrypt_block a 4 - encrypt_block a 5 - encrypt_block a 6 - encrypt_block a 7 - - add $0x100, SRC - add $0x100, DST - jmp .Lenc_a_loop - -.align 8 -.Lenc_u_loop: - encrypt_block u 0 - encrypt_block u 1 - encrypt_block u 2 - encrypt_block u 3 - encrypt_block u 4 - encrypt_block u 5 - encrypt_block u 6 - encrypt_block u 7 - - add $0x100, SRC - add $0x100, DST - jmp .Lenc_u_loop - -.Lenc_out_0: - state_store0 - FRAME_END - ret - -.Lenc_out_1: - state_store1 - FRAME_END - ret - -.Lenc_out_2: - state_store2 - FRAME_END - ret - -.Lenc_out_3: - state_store3 - FRAME_END - ret - -.Lenc_out_4: - state_store4 - FRAME_END - ret - -.Lenc_out_5: - state_store5 - FRAME_END - ret - -.Lenc_out_6: - state_store6 - FRAME_END - ret - -.Lenc_out_7: - state_store7 - FRAME_END - ret - -.Lenc_out: - FRAME_END - ret -ENDPROC(crypto_aegis128l_aesni_enc) - -/* - * void crypto_aegis128l_aesni_enc_tail(void *state, unsigned int length, - * const void *src, void *dst); - */ -ENTRY(crypto_aegis128l_aesni_enc_tail) - FRAME_BEGIN - - state_load - - /* encrypt message: */ - call __load_partial - - movdqa MSG0, T0 - movdqa MSG1, T1 - crypt0 T0, T1 - - call __store_partial - - update0 - - state_store0 - - FRAME_END - ret -ENDPROC(crypto_aegis128l_aesni_enc_tail) - -/* - * void crypto_aegis128l_aesni_dec(void *state, unsigned int length, - * const void *src, void *dst); - */ -ENTRY(crypto_aegis128l_aesni_dec) - FRAME_BEGIN - - cmp $0x20, LEN - jb .Ldec_out - - state_load - - mov SRC, %r8 - or DST, %r8 - and $0xF, %r8 - jnz .Ldec_u_loop - -.align 8 -.Ldec_a_loop: - decrypt_block a 0 - decrypt_block a 1 - decrypt_block a 2 - decrypt_block a 3 - decrypt_block a 4 - decrypt_block a 5 - decrypt_block a 6 - decrypt_block a 7 - - add $0x100, SRC - add $0x100, DST - jmp .Ldec_a_loop - -.align 8 -.Ldec_u_loop: - decrypt_block u 0 - decrypt_block u 1 - decrypt_block u 2 - decrypt_block u 3 - decrypt_block u 4 - decrypt_block u 5 - decrypt_block u 6 - decrypt_block u 7 - - add $0x100, SRC - add $0x100, DST - jmp .Ldec_u_loop - -.Ldec_out_0: - state_store0 - FRAME_END - ret - -.Ldec_out_1: - state_store1 - FRAME_END - ret - -.Ldec_out_2: - state_store2 - FRAME_END - ret - -.Ldec_out_3: - state_store3 - FRAME_END - ret - -.Ldec_out_4: - state_store4 - FRAME_END - ret - -.Ldec_out_5: - state_store5 - FRAME_END - ret - -.Ldec_out_6: - state_store6 - FRAME_END - ret - -.Ldec_out_7: - state_store7 - FRAME_END - ret - -.Ldec_out: - FRAME_END - ret -ENDPROC(crypto_aegis128l_aesni_dec) - -/* - * void crypto_aegis128l_aesni_dec_tail(void *state, unsigned int length, - * const void *src, void *dst); - */ -ENTRY(crypto_aegis128l_aesni_dec_tail) - FRAME_BEGIN - - state_load - - /* decrypt message: */ - call __load_partial - - crypt0 MSG0, MSG1 - - movdqa MSG0, T0 - movdqa MSG1, T1 - call __store_partial - - /* mask with byte count: */ - movq LEN, T0 - punpcklbw T0, T0 - punpcklbw T0, T0 - punpcklbw T0, T0 - punpcklbw T0, T0 - movdqa T0, T1 - movdqa .Laegis128l_counter0, T2 - movdqa .Laegis128l_counter1, T3 - pcmpgtb T2, T0 - pcmpgtb T3, T1 - pand T0, MSG0 - pand T1, MSG1 - - update0 - - state_store0 - - FRAME_END - ret -ENDPROC(crypto_aegis128l_aesni_dec_tail) - -/* - * void crypto_aegis128l_aesni_final(void *state, void *tag_xor, - * u64 assoclen, u64 cryptlen); - */ -ENTRY(crypto_aegis128l_aesni_final) - FRAME_BEGIN - - state_load - - /* prepare length block: */ - movq %rdx, MSG0 - movq %rcx, T0 - pslldq $8, T0 - pxor T0, MSG0 - psllq $3, MSG0 /* multiply by 8 (to get bit count) */ - - pxor STATE2, MSG0 - movdqa MSG0, MSG1 - - /* update state: */ - update0 - update1 - update2 - update3 - update4 - update5 - update6 - - /* xor tag: */ - movdqu (%rsi), T0 - - pxor STATE1, T0 - pxor STATE2, T0 - pxor STATE3, T0 - pxor STATE4, T0 - pxor STATE5, T0 - pxor STATE6, T0 - pxor STATE7, T0 - - movdqu T0, (%rsi) - - FRAME_END - ret -ENDPROC(crypto_aegis128l_aesni_final) diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c deleted file mode 100644 index 19eb28b316f0..000000000000 --- a/arch/x86/crypto/aegis128l-aesni-glue.c +++ /dev/null @@ -1,293 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * The AEGIS-128L Authenticated-Encryption Algorithm - * Glue for AES-NI + SSE2 implementation - * - * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <crypto/internal/aead.h> -#include <crypto/internal/simd.h> -#include <crypto/internal/skcipher.h> -#include <crypto/scatterwalk.h> -#include <linux/module.h> -#include <asm/fpu/api.h> -#include <asm/cpu_device_id.h> - -#define AEGIS128L_BLOCK_ALIGN 16 -#define AEGIS128L_BLOCK_SIZE 32 -#define AEGIS128L_NONCE_SIZE 16 -#define AEGIS128L_STATE_BLOCKS 8 -#define AEGIS128L_KEY_SIZE 16 -#define AEGIS128L_MIN_AUTH_SIZE 8 -#define AEGIS128L_MAX_AUTH_SIZE 16 - -asmlinkage void crypto_aegis128l_aesni_init(void *state, void *key, void *iv); - -asmlinkage void crypto_aegis128l_aesni_ad( - void *state, unsigned int length, const void *data); - -asmlinkage void crypto_aegis128l_aesni_enc( - void *state, unsigned int length, const void *src, void *dst); - -asmlinkage void crypto_aegis128l_aesni_dec( - void *state, unsigned int length, const void *src, void *dst); - -asmlinkage void crypto_aegis128l_aesni_enc_tail( - void *state, unsigned int length, const void *src, void *dst); - -asmlinkage void crypto_aegis128l_aesni_dec_tail( - void *state, unsigned int length, const void *src, void *dst); - -asmlinkage void crypto_aegis128l_aesni_final( - void *state, void *tag_xor, unsigned int cryptlen, - unsigned int assoclen); - -struct aegis_block { - u8 bytes[AEGIS128L_BLOCK_SIZE] __aligned(AEGIS128L_BLOCK_ALIGN); -}; - -struct aegis_state { - struct aegis_block blocks[AEGIS128L_STATE_BLOCKS]; -}; - -struct aegis_ctx { - struct aegis_block key; -}; - -struct aegis_crypt_ops { - int (*skcipher_walk_init)(struct skcipher_walk *walk, - struct aead_request *req, bool atomic); - - void (*crypt_blocks)(void *state, unsigned int length, const void *src, - void *dst); - void (*crypt_tail)(void *state, unsigned int length, const void *src, - void *dst); -}; - -static void crypto_aegis128l_aesni_process_ad( - struct aegis_state *state, struct scatterlist *sg_src, - unsigned int assoclen) -{ - struct scatter_walk walk; - struct aegis_block buf; - unsigned int pos = 0; - - scatterwalk_start(&walk, sg_src); - while (assoclen != 0) { - unsigned int size = scatterwalk_clamp(&walk, assoclen); - unsigned int left = size; - void *mapped = scatterwalk_map(&walk); - const u8 *src = (const u8 *)mapped; - - if (pos + size >= AEGIS128L_BLOCK_SIZE) { - if (pos > 0) { - unsigned int fill = AEGIS128L_BLOCK_SIZE - pos; - memcpy(buf.bytes + pos, src, fill); - crypto_aegis128l_aesni_ad(state, - AEGIS128L_BLOCK_SIZE, - buf.bytes); - pos = 0; - left -= fill; - src += fill; - } - - crypto_aegis128l_aesni_ad(state, left, src); - - src += left & ~(AEGIS128L_BLOCK_SIZE - 1); - left &= AEGIS128L_BLOCK_SIZE - 1; - } - - memcpy(buf.bytes + pos, src, left); - pos += left; - assoclen -= size; - - scatterwalk_unmap(mapped); - scatterwalk_advance(&walk, size); - scatterwalk_done(&walk, 0, assoclen); - } - - if (pos > 0) { - memset(buf.bytes + pos, 0, AEGIS128L_BLOCK_SIZE - pos); - crypto_aegis128l_aesni_ad(state, AEGIS128L_BLOCK_SIZE, buf.bytes); - } -} - -static void crypto_aegis128l_aesni_process_crypt( - struct aegis_state *state, struct skcipher_walk *walk, - const struct aegis_crypt_ops *ops) -{ - while (walk->nbytes >= AEGIS128L_BLOCK_SIZE) { - ops->crypt_blocks(state, round_down(walk->nbytes, - AEGIS128L_BLOCK_SIZE), - walk->src.virt.addr, walk->dst.virt.addr); - skcipher_walk_done(walk, walk->nbytes % AEGIS128L_BLOCK_SIZE); - } - - if (walk->nbytes) { - ops->crypt_tail(state, walk->nbytes, walk->src.virt.addr, - walk->dst.virt.addr); - skcipher_walk_done(walk, 0); - } -} - -static struct aegis_ctx *crypto_aegis128l_aesni_ctx(struct crypto_aead *aead) -{ - u8 *ctx = crypto_aead_ctx(aead); - ctx = PTR_ALIGN(ctx, __alignof__(struct aegis_ctx)); - return (void *)ctx; -} - -static int crypto_aegis128l_aesni_setkey(struct crypto_aead *aead, - const u8 *key, unsigned int keylen) -{ - struct aegis_ctx *ctx = crypto_aegis128l_aesni_ctx(aead); - - if (keylen != AEGIS128L_KEY_SIZE) { - crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); - return -EINVAL; - } - - memcpy(ctx->key.bytes, key, AEGIS128L_KEY_SIZE); - - return 0; -} - -static int crypto_aegis128l_aesni_setauthsize(struct crypto_aead *tfm, - unsigned int authsize) -{ - if (authsize > AEGIS128L_MAX_AUTH_SIZE) - return -EINVAL; - if (authsize < AEGIS128L_MIN_AUTH_SIZE) - return -EINVAL; - return 0; -} - -static void crypto_aegis128l_aesni_crypt(struct aead_request *req, - struct aegis_block *tag_xor, - unsigned int cryptlen, - const struct aegis_crypt_ops *ops) -{ - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aegis_ctx *ctx = crypto_aegis128l_aesni_ctx(tfm); - struct skcipher_walk walk; - struct aegis_state state; - - ops->skcipher_walk_init(&walk, req, true); - - kernel_fpu_begin(); - - crypto_aegis128l_aesni_init(&state, ctx->key.bytes, req->iv); - crypto_aegis128l_aesni_process_ad(&state, req->src, req->assoclen); - crypto_aegis128l_aesni_process_crypt(&state, &walk, ops); - crypto_aegis128l_aesni_final(&state, tag_xor, req->assoclen, cryptlen); - - kernel_fpu_end(); -} - -static int crypto_aegis128l_aesni_encrypt(struct aead_request *req) -{ - static const struct aegis_crypt_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_encrypt, - .crypt_blocks = crypto_aegis128l_aesni_enc, - .crypt_tail = crypto_aegis128l_aesni_enc_tail, - }; - - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aegis_block tag = {}; - unsigned int authsize = crypto_aead_authsize(tfm); - unsigned int cryptlen = req->cryptlen; - - crypto_aegis128l_aesni_crypt(req, &tag, cryptlen, &OPS); - - scatterwalk_map_and_copy(tag.bytes, req->dst, - req->assoclen + cryptlen, authsize, 1); - return 0; -} - -static int crypto_aegis128l_aesni_decrypt(struct aead_request *req) -{ - static const struct aegis_block zeros = {}; - - static const struct aegis_crypt_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_decrypt, - .crypt_blocks = crypto_aegis128l_aesni_dec, - .crypt_tail = crypto_aegis128l_aesni_dec_tail, - }; - - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aegis_block tag; - unsigned int authsize = crypto_aead_authsize(tfm); - unsigned int cryptlen = req->cryptlen - authsize; - - scatterwalk_map_and_copy(tag.bytes, req->src, - req->assoclen + cryptlen, authsize, 0); - - crypto_aegis128l_aesni_crypt(req, &tag, cryptlen, &OPS); - - return crypto_memneq(tag.bytes, zeros.bytes, authsize) ? -EBADMSG : 0; -} - -static int crypto_aegis128l_aesni_init_tfm(struct crypto_aead *aead) -{ - return 0; -} - -static void crypto_aegis128l_aesni_exit_tfm(struct crypto_aead *aead) -{ -} - -static struct aead_alg crypto_aegis128l_aesni_alg = { - .setkey = crypto_aegis128l_aesni_setkey, - .setauthsize = crypto_aegis128l_aesni_setauthsize, - .encrypt = crypto_aegis128l_aesni_encrypt, - .decrypt = crypto_aegis128l_aesni_decrypt, - .init = crypto_aegis128l_aesni_init_tfm, - .exit = crypto_aegis128l_aesni_exit_tfm, - - .ivsize = AEGIS128L_NONCE_SIZE, - .maxauthsize = AEGIS128L_MAX_AUTH_SIZE, - .chunksize = AEGIS128L_BLOCK_SIZE, - - .base = { - .cra_flags = CRYPTO_ALG_INTERNAL, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct aegis_ctx) + - __alignof__(struct aegis_ctx), - .cra_alignmask = 0, - .cra_priority = 400, - - .cra_name = "__aegis128l", - .cra_driver_name = "__aegis128l-aesni", - - .cra_module = THIS_MODULE, - } -}; - -static struct simd_aead_alg *simd_alg; - -static int __init crypto_aegis128l_aesni_module_init(void) -{ - if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_AES) || - !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) - return -ENODEV; - - return simd_register_aeads_compat(&crypto_aegis128l_aesni_alg, 1, - &simd_alg); -} - -static void __exit crypto_aegis128l_aesni_module_exit(void) -{ - simd_unregister_aeads(&crypto_aegis128l_aesni_alg, 1, &simd_alg); -} - -module_init(crypto_aegis128l_aesni_module_init); -module_exit(crypto_aegis128l_aesni_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>"); -MODULE_DESCRIPTION("AEGIS-128L AEAD algorithm -- AESNI+SSE2 implementation"); -MODULE_ALIAS_CRYPTO("aegis128l"); -MODULE_ALIAS_CRYPTO("aegis128l-aesni"); diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S deleted file mode 100644 index 37d9b13dfd85..000000000000 --- a/arch/x86/crypto/aegis256-aesni-asm.S +++ /dev/null @@ -1,700 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * AES-NI + SSE2 implementation of AEGIS-128L - * - * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <linux/linkage.h> -#include <asm/frame.h> - -#define STATE0 %xmm0 -#define STATE1 %xmm1 -#define STATE2 %xmm2 -#define STATE3 %xmm3 -#define STATE4 %xmm4 -#define STATE5 %xmm5 -#define MSG %xmm6 -#define T0 %xmm7 -#define T1 %xmm8 -#define T2 %xmm9 -#define T3 %xmm10 - -#define STATEP %rdi -#define LEN %rsi -#define SRC %rdx -#define DST %rcx - -.section .rodata.cst16.aegis256_const, "aM", @progbits, 32 -.align 16 -.Laegis256_const_0: - .byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d - .byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62 -.Laegis256_const_1: - .byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1 - .byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd - -.section .rodata.cst16.aegis256_counter, "aM", @progbits, 16 -.align 16 -.Laegis256_counter: - .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07 - .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f - -.text - -/* - * __load_partial: internal ABI - * input: - * LEN - bytes - * SRC - src - * output: - * MSG - message block - * changed: - * T0 - * %r8 - * %r9 - */ -__load_partial: - xor %r9d, %r9d - pxor MSG, MSG - - mov LEN, %r8 - and $0x1, %r8 - jz .Lld_partial_1 - - mov LEN, %r8 - and $0x1E, %r8 - add SRC, %r8 - mov (%r8), %r9b - -.Lld_partial_1: - mov LEN, %r8 - and $0x2, %r8 - jz .Lld_partial_2 - - mov LEN, %r8 - and $0x1C, %r8 - add SRC, %r8 - shl $0x10, %r9 - mov (%r8), %r9w - -.Lld_partial_2: - mov LEN, %r8 - and $0x4, %r8 - jz .Lld_partial_4 - - mov LEN, %r8 - and $0x18, %r8 - add SRC, %r8 - shl $32, %r9 - mov (%r8), %r8d - xor %r8, %r9 - -.Lld_partial_4: - movq %r9, MSG - - mov LEN, %r8 - and $0x8, %r8 - jz .Lld_partial_8 - - mov LEN, %r8 - and $0x10, %r8 - add SRC, %r8 - pslldq $8, MSG - movq (%r8), T0 - pxor T0, MSG - -.Lld_partial_8: - ret -ENDPROC(__load_partial) - -/* - * __store_partial: internal ABI - * input: - * LEN - bytes - * DST - dst - * output: - * T0 - message block - * changed: - * %r8 - * %r9 - * %r10 - */ -__store_partial: - mov LEN, %r8 - mov DST, %r9 - - movq T0, %r10 - - cmp $8, %r8 - jl .Lst_partial_8 - - mov %r10, (%r9) - psrldq $8, T0 - movq T0, %r10 - - sub $8, %r8 - add $8, %r9 - -.Lst_partial_8: - cmp $4, %r8 - jl .Lst_partial_4 - - mov %r10d, (%r9) - shr $32, %r10 - - sub $4, %r8 - add $4, %r9 - -.Lst_partial_4: - cmp $2, %r8 - jl .Lst_partial_2 - - mov %r10w, (%r9) - shr $0x10, %r10 - - sub $2, %r8 - add $2, %r9 - -.Lst_partial_2: - cmp $1, %r8 - jl .Lst_partial_1 - - mov %r10b, (%r9) - -.Lst_partial_1: - ret -ENDPROC(__store_partial) - -.macro update - movdqa STATE5, T0 - aesenc STATE0, STATE5 - aesenc STATE1, STATE0 - aesenc STATE2, STATE1 - aesenc STATE3, STATE2 - aesenc STATE4, STATE3 - aesenc T0, STATE4 -.endm - -.macro update0 m - update - pxor \m, STATE5 -.endm - -.macro update1 m - update - pxor \m, STATE4 -.endm - -.macro update2 m - update - pxor \m, STATE3 -.endm - -.macro update3 m - update - pxor \m, STATE2 -.endm - -.macro update4 m - update - pxor \m, STATE1 -.endm - -.macro update5 m - update - pxor \m, STATE0 -.endm - -.macro state_load - movdqu 0x00(STATEP), STATE0 - movdqu 0x10(STATEP), STATE1 - movdqu 0x20(STATEP), STATE2 - movdqu 0x30(STATEP), STATE3 - movdqu 0x40(STATEP), STATE4 - movdqu 0x50(STATEP), STATE5 -.endm - -.macro state_store s0 s1 s2 s3 s4 s5 - movdqu \s5, 0x00(STATEP) - movdqu \s0, 0x10(STATEP) - movdqu \s1, 0x20(STATEP) - movdqu \s2, 0x30(STATEP) - movdqu \s3, 0x40(STATEP) - movdqu \s4, 0x50(STATEP) -.endm - -.macro state_store0 - state_store STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 -.endm - -.macro state_store1 - state_store STATE5 STATE0 STATE1 STATE2 STATE3 STATE4 -.endm - -.macro state_store2 - state_store STATE4 STATE5 STATE0 STATE1 STATE2 STATE3 -.endm - -.macro state_store3 - state_store STATE3 STATE4 STATE5 STATE0 STATE1 STATE2 -.endm - -.macro state_store4 - state_store STATE2 STATE3 STATE4 STATE5 STATE0 STATE1 -.endm - -.macro state_store5 - state_store STATE1 STATE2 STATE3 STATE4 STATE5 STATE0 -.endm - -/* - * void crypto_aegis256_aesni_init(void *state, const void *key, const void *iv); - */ -ENTRY(crypto_aegis256_aesni_init) - FRAME_BEGIN - - /* load key: */ - movdqa 0x00(%rsi), MSG - movdqa 0x10(%rsi), T1 - movdqa MSG, STATE4 - movdqa T1, STATE5 - - /* load IV: */ - movdqu 0x00(%rdx), T2 - movdqu 0x10(%rdx), T3 - pxor MSG, T2 - pxor T1, T3 - movdqa T2, STATE0 - movdqa T3, STATE1 - - /* load the constants: */ - movdqa .Laegis256_const_0, STATE3 - movdqa .Laegis256_const_1, STATE2 - pxor STATE3, STATE4 - pxor STATE2, STATE5 - - /* update 10 times with IV and KEY: */ - update0 MSG - update1 T1 - update2 T2 - update3 T3 - update4 MSG - update5 T1 - update0 T2 - update1 T3 - update2 MSG - update3 T1 - update4 T2 - update5 T3 - update0 MSG - update1 T1 - update2 T2 - update3 T3 - - state_store3 - - FRAME_END - ret -ENDPROC(crypto_aegis256_aesni_init) - -.macro ad_block a i - movdq\a (\i * 0x10)(SRC), MSG - update\i MSG - sub $0x10, LEN - cmp $0x10, LEN - jl .Lad_out_\i -.endm - -/* - * void crypto_aegis256_aesni_ad(void *state, unsigned int length, - * const void *data); - */ -ENTRY(crypto_aegis256_aesni_ad) - FRAME_BEGIN - - cmp $0x10, LEN - jb .Lad_out - - state_load - - mov SRC, %r8 - and $0xf, %r8 - jnz .Lad_u_loop - -.align 8 -.Lad_a_loop: - ad_block a 0 - ad_block a 1 - ad_block a 2 - ad_block a 3 - ad_block a 4 - ad_block a 5 - - add $0x60, SRC - jmp .Lad_a_loop - -.align 8 -.Lad_u_loop: - ad_block u 0 - ad_block u 1 - ad_block u 2 - ad_block u 3 - ad_block u 4 - ad_block u 5 - - add $0x60, SRC - jmp .Lad_u_loop - -.Lad_out_0: - state_store0 - FRAME_END - ret - -.Lad_out_1: - state_store1 - FRAME_END - ret - -.Lad_out_2: - state_store2 - FRAME_END - ret - -.Lad_out_3: - state_store3 - FRAME_END - ret - -.Lad_out_4: - state_store4 - FRAME_END - ret - -.Lad_out_5: - state_store5 - FRAME_END - ret - -.Lad_out: - FRAME_END - ret -ENDPROC(crypto_aegis256_aesni_ad) - -.macro crypt m s0 s1 s2 s3 s4 s5 - pxor \s1, \m - pxor \s4, \m - pxor \s5, \m - movdqa \s2, T3 - pand \s3, T3 - pxor T3, \m -.endm - -.macro crypt0 m - crypt \m STATE0 STATE1 STATE2 STATE3 STATE4 STATE5 -.endm - -.macro crypt1 m - crypt \m STATE5 STATE0 STATE1 STATE2 STATE3 STATE4 -.endm - -.macro crypt2 m - crypt \m STATE4 STATE5 STATE0 STATE1 STATE2 STATE3 -.endm - -.macro crypt3 m - crypt \m STATE3 STATE4 STATE5 STATE0 STATE1 STATE2 -.endm - -.macro crypt4 m - crypt \m STATE2 STATE3 STATE4 STATE5 STATE0 STATE1 -.endm - -.macro crypt5 m - crypt \m STATE1 STATE2 STATE3 STATE4 STATE5 STATE0 -.endm - -.macro encrypt_block a i - movdq\a (\i * 0x10)(SRC), MSG - movdqa MSG, T0 - crypt\i T0 - movdq\a T0, (\i * 0x10)(DST) - - update\i MSG - - sub $0x10, LEN - cmp $0x10, LEN - jl .Lenc_out_\i -.endm - -.macro decrypt_block a i - movdq\a (\i * 0x10)(SRC), MSG - crypt\i MSG - movdq\a MSG, (\i * 0x10)(DST) - - update\i MSG - - sub $0x10, LEN - cmp $0x10, LEN - jl .Ldec_out_\i -.endm - -/* - * void crypto_aegis256_aesni_enc(void *state, unsigned int length, - * const void *src, void *dst); - */ -ENTRY(crypto_aegis256_aesni_enc) - FRAME_BEGIN - - cmp $0x10, LEN - jb .Lenc_out - - state_load - - mov SRC, %r8 - or DST, %r8 - and $0xf, %r8 - jnz .Lenc_u_loop - -.align 8 -.Lenc_a_loop: - encrypt_block a 0 - encrypt_block a 1 - encrypt_block a 2 - encrypt_block a 3 - encrypt_block a 4 - encrypt_block a 5 - - add $0x60, SRC - add $0x60, DST - jmp .Lenc_a_loop - -.align 8 -.Lenc_u_loop: - encrypt_block u 0 - encrypt_block u 1 - encrypt_block u 2 - encrypt_block u 3 - encrypt_block u 4 - encrypt_block u 5 - - add $0x60, SRC - add $0x60, DST - jmp .Lenc_u_loop - -.Lenc_out_0: - state_store0 - FRAME_END - ret - -.Lenc_out_1: - state_store1 - FRAME_END - ret - -.Lenc_out_2: - state_store2 - FRAME_END - ret - -.Lenc_out_3: - state_store3 - FRAME_END - ret - -.Lenc_out_4: - state_store4 - FRAME_END - ret - -.Lenc_out_5: - state_store5 - FRAME_END - ret - -.Lenc_out: - FRAME_END - ret -ENDPROC(crypto_aegis256_aesni_enc) - -/* - * void crypto_aegis256_aesni_enc_tail(void *state, unsigned int length, - * const void *src, void *dst); - */ -ENTRY(crypto_aegis256_aesni_enc_tail) - FRAME_BEGIN - - state_load - - /* encrypt message: */ - call __load_partial - - movdqa MSG, T0 - crypt0 T0 - - call __store_partial - - update0 MSG - - state_store0 - - FRAME_END - ret -ENDPROC(crypto_aegis256_aesni_enc_tail) - -/* - * void crypto_aegis256_aesni_dec(void *state, unsigned int length, - * const void *src, void *dst); - */ -ENTRY(crypto_aegis256_aesni_dec) - FRAME_BEGIN - - cmp $0x10, LEN - jb .Ldec_out - - state_load - - mov SRC, %r8 - or DST, %r8 - and $0xF, %r8 - jnz .Ldec_u_loop - -.align 8 -.Ldec_a_loop: - decrypt_block a 0 - decrypt_block a 1 - decrypt_block a 2 - decrypt_block a 3 - decrypt_block a 4 - decrypt_block a 5 - - add $0x60, SRC - add $0x60, DST - jmp .Ldec_a_loop - -.align 8 -.Ldec_u_loop: - decrypt_block u 0 - decrypt_block u 1 - decrypt_block u 2 - decrypt_block u 3 - decrypt_block u 4 - decrypt_block u 5 - - add $0x60, SRC - add $0x60, DST - jmp .Ldec_u_loop - -.Ldec_out_0: - state_store0 - FRAME_END - ret - -.Ldec_out_1: - state_store1 - FRAME_END - ret - -.Ldec_out_2: - state_store2 - FRAME_END - ret - -.Ldec_out_3: - state_store3 - FRAME_END - ret - -.Ldec_out_4: - state_store4 - FRAME_END - ret - -.Ldec_out_5: - state_store5 - FRAME_END - ret - -.Ldec_out: - FRAME_END - ret -ENDPROC(crypto_aegis256_aesni_dec) - -/* - * void crypto_aegis256_aesni_dec_tail(void *state, unsigned int length, - * const void *src, void *dst); - */ -ENTRY(crypto_aegis256_aesni_dec_tail) - FRAME_BEGIN - - state_load - - /* decrypt message: */ - call __load_partial - - crypt0 MSG - - movdqa MSG, T0 - call __store_partial - - /* mask with byte count: */ - movq LEN, T0 - punpcklbw T0, T0 - punpcklbw T0, T0 - punpcklbw T0, T0 - punpcklbw T0, T0 - movdqa .Laegis256_counter, T1 - pcmpgtb T1, T0 - pand T0, MSG - - update0 MSG - - state_store0 - - FRAME_END - ret -ENDPROC(crypto_aegis256_aesni_dec_tail) - -/* - * void crypto_aegis256_aesni_final(void *state, void *tag_xor, - * u64 assoclen, u64 cryptlen); - */ -ENTRY(crypto_aegis256_aesni_final) - FRAME_BEGIN - - state_load - - /* prepare length block: */ - movq %rdx, MSG - movq %rcx, T0 - pslldq $8, T0 - pxor T0, MSG - psllq $3, MSG /* multiply by 8 (to get bit count) */ - - pxor STATE3, MSG - - /* update state: */ - update0 MSG - update1 MSG - update2 MSG - update3 MSG - update4 MSG - update5 MSG - update0 MSG - - /* xor tag: */ - movdqu (%rsi), MSG - - pxor STATE0, MSG - pxor STATE1, MSG - pxor STATE2, MSG - pxor STATE3, MSG - pxor STATE4, MSG - pxor STATE5, MSG - - movdqu MSG, (%rsi) - - FRAME_END - ret -ENDPROC(crypto_aegis256_aesni_final) diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c deleted file mode 100644 index f84da27171d3..000000000000 --- a/arch/x86/crypto/aegis256-aesni-glue.c +++ /dev/null @@ -1,293 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * The AEGIS-256 Authenticated-Encryption Algorithm - * Glue for AES-NI + SSE2 implementation - * - * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <crypto/internal/aead.h> -#include <crypto/internal/simd.h> -#include <crypto/internal/skcipher.h> -#include <crypto/scatterwalk.h> -#include <linux/module.h> -#include <asm/fpu/api.h> -#include <asm/cpu_device_id.h> - -#define AEGIS256_BLOCK_ALIGN 16 -#define AEGIS256_BLOCK_SIZE 16 -#define AEGIS256_NONCE_SIZE 32 -#define AEGIS256_STATE_BLOCKS 6 -#define AEGIS256_KEY_SIZE 32 -#define AEGIS256_MIN_AUTH_SIZE 8 -#define AEGIS256_MAX_AUTH_SIZE 16 - -asmlinkage void crypto_aegis256_aesni_init(void *state, void *key, void *iv); - -asmlinkage void crypto_aegis256_aesni_ad( - void *state, unsigned int length, const void *data); - -asmlinkage void crypto_aegis256_aesni_enc( - void *state, unsigned int length, const void *src, void *dst); - -asmlinkage void crypto_aegis256_aesni_dec( - void *state, unsigned int length, const void *src, void *dst); - -asmlinkage void crypto_aegis256_aesni_enc_tail( - void *state, unsigned int length, const void *src, void *dst); - -asmlinkage void crypto_aegis256_aesni_dec_tail( - void *state, unsigned int length, const void *src, void *dst); - -asmlinkage void crypto_aegis256_aesni_final( - void *state, void *tag_xor, unsigned int cryptlen, - unsigned int assoclen); - -struct aegis_block { - u8 bytes[AEGIS256_BLOCK_SIZE] __aligned(AEGIS256_BLOCK_ALIGN); -}; - -struct aegis_state { - struct aegis_block blocks[AEGIS256_STATE_BLOCKS]; -}; - -struct aegis_ctx { - struct aegis_block key[AEGIS256_KEY_SIZE / AEGIS256_BLOCK_SIZE]; -}; - -struct aegis_crypt_ops { - int (*skcipher_walk_init)(struct skcipher_walk *walk, - struct aead_request *req, bool atomic); - - void (*crypt_blocks)(void *state, unsigned int length, const void *src, - void *dst); - void (*crypt_tail)(void *state, unsigned int length, const void *src, - void *dst); -}; - -static void crypto_aegis256_aesni_process_ad( - struct aegis_state *state, struct scatterlist *sg_src, - unsigned int assoclen) -{ - struct scatter_walk walk; - struct aegis_block buf; - unsigned int pos = 0; - - scatterwalk_start(&walk, sg_src); - while (assoclen != 0) { - unsigned int size = scatterwalk_clamp(&walk, assoclen); - unsigned int left = size; - void *mapped = scatterwalk_map(&walk); - const u8 *src = (const u8 *)mapped; - - if (pos + size >= AEGIS256_BLOCK_SIZE) { - if (pos > 0) { - unsigned int fill = AEGIS256_BLOCK_SIZE - pos; - memcpy(buf.bytes + pos, src, fill); - crypto_aegis256_aesni_ad(state, - AEGIS256_BLOCK_SIZE, - buf.bytes); - pos = 0; - left -= fill; - src += fill; - } - - crypto_aegis256_aesni_ad(state, left, src); - - src += left & ~(AEGIS256_BLOCK_SIZE - 1); - left &= AEGIS256_BLOCK_SIZE - 1; - } - - memcpy(buf.bytes + pos, src, left); - pos += left; - assoclen -= size; - - scatterwalk_unmap(mapped); - scatterwalk_advance(&walk, size); - scatterwalk_done(&walk, 0, assoclen); - } - - if (pos > 0) { - memset(buf.bytes + pos, 0, AEGIS256_BLOCK_SIZE - pos); - crypto_aegis256_aesni_ad(state, AEGIS256_BLOCK_SIZE, buf.bytes); - } -} - -static void crypto_aegis256_aesni_process_crypt( - struct aegis_state *state, struct skcipher_walk *walk, - const struct aegis_crypt_ops *ops) -{ - while (walk->nbytes >= AEGIS256_BLOCK_SIZE) { - ops->crypt_blocks(state, - round_down(walk->nbytes, AEGIS256_BLOCK_SIZE), - walk->src.virt.addr, walk->dst.virt.addr); - skcipher_walk_done(walk, walk->nbytes % AEGIS256_BLOCK_SIZE); - } - - if (walk->nbytes) { - ops->crypt_tail(state, walk->nbytes, walk->src.virt.addr, - walk->dst.virt.addr); - skcipher_walk_done(walk, 0); - } -} - -static struct aegis_ctx *crypto_aegis256_aesni_ctx(struct crypto_aead *aead) -{ - u8 *ctx = crypto_aead_ctx(aead); - ctx = PTR_ALIGN(ctx, __alignof__(struct aegis_ctx)); - return (void *)ctx; -} - -static int crypto_aegis256_aesni_setkey(struct crypto_aead *aead, const u8 *key, - unsigned int keylen) -{ - struct aegis_ctx *ctx = crypto_aegis256_aesni_ctx(aead); - - if (keylen != AEGIS256_KEY_SIZE) { - crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); - return -EINVAL; - } - - memcpy(ctx->key, key, AEGIS256_KEY_SIZE); - - return 0; -} - -static int crypto_aegis256_aesni_setauthsize(struct crypto_aead *tfm, - unsigned int authsize) -{ - if (authsize > AEGIS256_MAX_AUTH_SIZE) - return -EINVAL; - if (authsize < AEGIS256_MIN_AUTH_SIZE) - return -EINVAL; - return 0; -} - -static void crypto_aegis256_aesni_crypt(struct aead_request *req, - struct aegis_block *tag_xor, - unsigned int cryptlen, - const struct aegis_crypt_ops *ops) -{ - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aegis_ctx *ctx = crypto_aegis256_aesni_ctx(tfm); - struct skcipher_walk walk; - struct aegis_state state; - - ops->skcipher_walk_init(&walk, req, true); - - kernel_fpu_begin(); - - crypto_aegis256_aesni_init(&state, ctx->key, req->iv); - crypto_aegis256_aesni_process_ad(&state, req->src, req->assoclen); - crypto_aegis256_aesni_process_crypt(&state, &walk, ops); - crypto_aegis256_aesni_final(&state, tag_xor, req->assoclen, cryptlen); - - kernel_fpu_end(); -} - -static int crypto_aegis256_aesni_encrypt(struct aead_request *req) -{ - static const struct aegis_crypt_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_encrypt, - .crypt_blocks = crypto_aegis256_aesni_enc, - .crypt_tail = crypto_aegis256_aesni_enc_tail, - }; - - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aegis_block tag = {}; - unsigned int authsize = crypto_aead_authsize(tfm); - unsigned int cryptlen = req->cryptlen; - - crypto_aegis256_aesni_crypt(req, &tag, cryptlen, &OPS); - - scatterwalk_map_and_copy(tag.bytes, req->dst, - req->assoclen + cryptlen, authsize, 1); - return 0; -} - -static int crypto_aegis256_aesni_decrypt(struct aead_request *req) -{ - static const struct aegis_block zeros = {}; - - static const struct aegis_crypt_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_decrypt, - .crypt_blocks = crypto_aegis256_aesni_dec, - .crypt_tail = crypto_aegis256_aesni_dec_tail, - }; - - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aegis_block tag; - unsigned int authsize = crypto_aead_authsize(tfm); - unsigned int cryptlen = req->cryptlen - authsize; - - scatterwalk_map_and_copy(tag.bytes, req->src, - req->assoclen + cryptlen, authsize, 0); - - crypto_aegis256_aesni_crypt(req, &tag, cryptlen, &OPS); - - return crypto_memneq(tag.bytes, zeros.bytes, authsize) ? -EBADMSG : 0; -} - -static int crypto_aegis256_aesni_init_tfm(struct crypto_aead *aead) -{ - return 0; -} - -static void crypto_aegis256_aesni_exit_tfm(struct crypto_aead *aead) -{ -} - -static struct aead_alg crypto_aegis256_aesni_alg = { - .setkey = crypto_aegis256_aesni_setkey, - .setauthsize = crypto_aegis256_aesni_setauthsize, - .encrypt = crypto_aegis256_aesni_encrypt, - .decrypt = crypto_aegis256_aesni_decrypt, - .init = crypto_aegis256_aesni_init_tfm, - .exit = crypto_aegis256_aesni_exit_tfm, - - .ivsize = AEGIS256_NONCE_SIZE, - .maxauthsize = AEGIS256_MAX_AUTH_SIZE, - .chunksize = AEGIS256_BLOCK_SIZE, - - .base = { - .cra_flags = CRYPTO_ALG_INTERNAL, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct aegis_ctx) + - __alignof__(struct aegis_ctx), - .cra_alignmask = 0, - .cra_priority = 400, - - .cra_name = "__aegis256", - .cra_driver_name = "__aegis256-aesni", - - .cra_module = THIS_MODULE, - } -}; - -static struct simd_aead_alg *simd_alg; - -static int __init crypto_aegis256_aesni_module_init(void) -{ - if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_AES) || - !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) - return -ENODEV; - - return simd_register_aeads_compat(&crypto_aegis256_aesni_alg, 1, - &simd_alg); -} - -static void __exit crypto_aegis256_aesni_module_exit(void) -{ - simd_unregister_aeads(&crypto_aegis256_aesni_alg, 1, &simd_alg); -} - -module_init(crypto_aegis256_aesni_module_init); -module_exit(crypto_aegis256_aesni_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>"); -MODULE_DESCRIPTION("AEGIS-256 AEAD algorithm -- AESNI+SSE2 implementation"); -MODULE_ALIAS_CRYPTO("aegis256"); -MODULE_ALIAS_CRYPTO("aegis256-aesni"); diff --git a/arch/x86/crypto/aes-i586-asm_32.S b/arch/x86/crypto/aes-i586-asm_32.S deleted file mode 100644 index 2849dbc59e11..000000000000 --- a/arch/x86/crypto/aes-i586-asm_32.S +++ /dev/null @@ -1,362 +0,0 @@ -// ------------------------------------------------------------------------- -// Copyright (c) 2001, Dr Brian Gladman < >, Worcester, UK. -// All rights reserved. -// -// LICENSE TERMS -// -// The free distribution and use of this software in both source and binary -// form is allowed (with or without changes) provided that: -// -// 1. distributions of this source code include the above copyright -// notice, this list of conditions and the following disclaimer// -// -// 2. distributions in binary form include the above copyright -// notice, this list of conditions and the following disclaimer -// in the documentation and/or other associated materials// -// -// 3. the copyright holder's name is not used to endorse products -// built using this software without specific written permission. -// -// -// ALTERNATIVELY, provided that this notice is retained in full, this product -// may be distributed under the terms of the GNU General Public License (GPL), -// in which case the provisions of the GPL apply INSTEAD OF those given above. -// -// Copyright (c) 2004 Linus Torvalds <torvalds@osdl.org> -// Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> - -// DISCLAIMER -// -// This software is provided 'as is' with no explicit or implied warranties -// in respect of its properties including, but not limited to, correctness -// and fitness for purpose. -// ------------------------------------------------------------------------- -// Issue Date: 29/07/2002 - -.file "aes-i586-asm.S" -.text - -#include <linux/linkage.h> -#include <asm/asm-offsets.h> - -#define tlen 1024 // length of each of 4 'xor' arrays (256 32-bit words) - -/* offsets to parameters with one register pushed onto stack */ -#define ctx 8 -#define out_blk 12 -#define in_blk 16 - -/* offsets in crypto_aes_ctx structure */ -#define klen (480) -#define ekey (0) -#define dkey (240) - -// register mapping for encrypt and decrypt subroutines - -#define r0 eax -#define r1 ebx -#define r2 ecx -#define r3 edx -#define r4 esi -#define r5 edi - -#define eaxl al -#define eaxh ah -#define ebxl bl -#define ebxh bh -#define ecxl cl -#define ecxh ch -#define edxl dl -#define edxh dh - -#define _h(reg) reg##h -#define h(reg) _h(reg) - -#define _l(reg) reg##l -#define l(reg) _l(reg) - -// This macro takes a 32-bit word representing a column and uses -// each of its four bytes to index into four tables of 256 32-bit -// words to obtain values that are then xored into the appropriate -// output registers r0, r1, r4 or r5. - -// Parameters: -// table table base address -// %1 out_state[0] -// %2 out_state[1] -// %3 out_state[2] -// %4 out_state[3] -// idx input register for the round (destroyed) -// tmp scratch register for the round -// sched key schedule - -#define do_col(table, a1,a2,a3,a4, idx, tmp) \ - movzx %l(idx),%tmp; \ - xor table(,%tmp,4),%a1; \ - movzx %h(idx),%tmp; \ - shr $16,%idx; \ - xor table+tlen(,%tmp,4),%a2; \ - movzx %l(idx),%tmp; \ - movzx %h(idx),%idx; \ - xor table+2*tlen(,%tmp,4),%a3; \ - xor table+3*tlen(,%idx,4),%a4; - -// initialise output registers from the key schedule -// NB1: original value of a3 is in idx on exit -// NB2: original values of a1,a2,a4 aren't used -#define do_fcol(table, a1,a2,a3,a4, idx, tmp, sched) \ - mov 0 sched,%a1; \ - movzx %l(idx),%tmp; \ - mov 12 sched,%a2; \ - xor table(,%tmp,4),%a1; \ - mov 4 sched,%a4; \ - movzx %h(idx),%tmp; \ - shr $16,%idx; \ - xor table+tlen(,%tmp,4),%a2; \ - movzx %l(idx),%tmp; \ - movzx %h(idx),%idx; \ - xor table+3*tlen(,%idx,4),%a4; \ - mov %a3,%idx; \ - mov 8 sched,%a3; \ - xor table+2*tlen(,%tmp,4),%a3; - -// initialise output registers from the key schedule -// NB1: original value of a3 is in idx on exit -// NB2: original values of a1,a2,a4 aren't used -#define do_icol(table, a1,a2,a3,a4, idx, tmp, sched) \ - mov 0 sched,%a1; \ - movzx %l(idx),%tmp; \ - mov 4 sched,%a2; \ - xor table(,%tmp,4),%a1; \ - mov 12 sched,%a4; \ - movzx %h(idx),%tmp; \ - shr $16,%idx; \ - xor table+tlen(,%tmp,4),%a2; \ - movzx %l(idx),%tmp; \ - movzx %h(idx),%idx; \ - xor table+3*tlen(,%idx,4),%a4; \ - mov %a3,%idx; \ - mov 8 sched,%a3; \ - xor table+2*tlen(,%tmp,4),%a3; - - -// original Gladman had conditional saves to MMX regs. -#define save(a1, a2) \ - mov %a2,4*a1(%esp) - -#define restore(a1, a2) \ - mov 4*a2(%esp),%a1 - -// These macros perform a forward encryption cycle. They are entered with -// the first previous round column values in r0,r1,r4,r5 and -// exit with the final values in the same registers, using stack -// for temporary storage. - -// round column values -// on entry: r0,r1,r4,r5 -// on exit: r2,r1,r4,r5 -#define fwd_rnd1(arg, table) \ - save (0,r1); \ - save (1,r5); \ - \ - /* compute new column values */ \ - do_fcol(table, r2,r5,r4,r1, r0,r3, arg); /* idx=r0 */ \ - do_col (table, r4,r1,r2,r5, r0,r3); /* idx=r4 */ \ - restore(r0,0); \ - do_col (table, r1,r2,r5,r4, r0,r3); /* idx=r1 */ \ - restore(r0,1); \ - do_col (table, r5,r4,r1,r2, r0,r3); /* idx=r5 */ - -// round column values -// on entry: r2,r1,r4,r5 -// on exit: r0,r1,r4,r5 -#define fwd_rnd2(arg, table) \ - save (0,r1); \ - save (1,r5); \ - \ - /* compute new column values */ \ - do_fcol(table, r0,r5,r4,r1, r2,r3, arg); /* idx=r2 */ \ - do_col (table, r4,r1,r0,r5, r2,r3); /* idx=r4 */ \ - restore(r2,0); \ - do_col (table, r1,r0,r5,r4, r2,r3); /* idx=r1 */ \ - restore(r2,1); \ - do_col (table, r5,r4,r1,r0, r2,r3); /* idx=r5 */ - -// These macros performs an inverse encryption cycle. They are entered with -// the first previous round column values in r0,r1,r4,r5 and -// exit with the final values in the same registers, using stack -// for temporary storage - -// round column values -// on entry: r0,r1,r4,r5 -// on exit: r2,r1,r4,r5 -#define inv_rnd1(arg, table) \ - save (0,r1); \ - save (1,r5); \ - \ - /* compute new column values */ \ - do_icol(table, r2,r1,r4,r5, r0,r3, arg); /* idx=r0 */ \ - do_col (table, r4,r5,r2,r1, r0,r3); /* idx=r4 */ \ - restore(r0,0); \ - do_col (table, r1,r4,r5,r2, r0,r3); /* idx=r1 */ \ - restore(r0,1); \ - do_col (table, r5,r2,r1,r4, r0,r3); /* idx=r5 */ - -// round column values -// on entry: r2,r1,r4,r5 -// on exit: r0,r1,r4,r5 -#define inv_rnd2(arg, table) \ - save (0,r1); \ - save (1,r5); \ - \ - /* compute new column values */ \ - do_icol(table, r0,r1,r4,r5, r2,r3, arg); /* idx=r2 */ \ - do_col (table, r4,r5,r0,r1, r2,r3); /* idx=r4 */ \ - restore(r2,0); \ - do_col (table, r1,r4,r5,r0, r2,r3); /* idx=r1 */ \ - restore(r2,1); \ - do_col (table, r5,r0,r1,r4, r2,r3); /* idx=r5 */ - -// AES (Rijndael) Encryption Subroutine -/* void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */ - -.extern crypto_ft_tab -.extern crypto_fl_tab - -ENTRY(aes_enc_blk) - push %ebp - mov ctx(%esp),%ebp - -// CAUTION: the order and the values used in these assigns -// rely on the register mappings - -1: push %ebx - mov in_blk+4(%esp),%r2 - push %esi - mov klen(%ebp),%r3 // key size - push %edi -#if ekey != 0 - lea ekey(%ebp),%ebp // key pointer -#endif - -// input four columns and xor in first round key - - mov (%r2),%r0 - mov 4(%r2),%r1 - mov 8(%r2),%r4 - mov 12(%r2),%r5 - xor (%ebp),%r0 - xor 4(%ebp),%r1 - xor 8(%ebp),%r4 - xor 12(%ebp),%r5 - - sub $8,%esp // space for register saves on stack - add $16,%ebp // increment to next round key - cmp $24,%r3 - jb 4f // 10 rounds for 128-bit key - lea 32(%ebp),%ebp - je 3f // 12 rounds for 192-bit key - lea 32(%ebp),%ebp - -2: fwd_rnd1( -64(%ebp), crypto_ft_tab) // 14 rounds for 256-bit key - fwd_rnd2( -48(%ebp), crypto_ft_tab) -3: fwd_rnd1( -32(%ebp), crypto_ft_tab) // 12 rounds for 192-bit key - fwd_rnd2( -16(%ebp), crypto_ft_tab) -4: fwd_rnd1( (%ebp), crypto_ft_tab) // 10 rounds for 128-bit key - fwd_rnd2( +16(%ebp), crypto_ft_tab) - fwd_rnd1( +32(%ebp), crypto_ft_tab) - fwd_rnd2( +48(%ebp), crypto_ft_tab) - fwd_rnd1( +64(%ebp), crypto_ft_tab) - fwd_rnd2( +80(%ebp), crypto_ft_tab) - fwd_rnd1( +96(%ebp), crypto_ft_tab) - fwd_rnd2(+112(%ebp), crypto_ft_tab) - fwd_rnd1(+128(%ebp), crypto_ft_tab) - fwd_rnd2(+144(%ebp), crypto_fl_tab) // last round uses a different table - -// move final values to the output array. CAUTION: the -// order of these assigns rely on the register mappings - - add $8,%esp - mov out_blk+12(%esp),%ebp - mov %r5,12(%ebp) - pop %edi - mov %r4,8(%ebp) - pop %esi - mov %r1,4(%ebp) - pop %ebx - mov %r0,(%ebp) - pop %ebp - ret -ENDPROC(aes_enc_blk) - -// AES (Rijndael) Decryption Subroutine -/* void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */ - -.extern crypto_it_tab -.extern crypto_il_tab - -ENTRY(aes_dec_blk) - push %ebp - mov ctx(%esp),%ebp - -// CAUTION: the order and the values used in these assigns -// rely on the register mappings - -1: push %ebx - mov in_blk+4(%esp),%r2 - push %esi - mov klen(%ebp),%r3 // key size - push %edi -#if dkey != 0 - lea dkey(%ebp),%ebp // key pointer -#endif - -// input four columns and xor in first round key - - mov (%r2),%r0 - mov 4(%r2),%r1 - mov 8(%r2),%r4 - mov 12(%r2),%r5 - xor (%ebp),%r0 - xor 4(%ebp),%r1 - xor 8(%ebp),%r4 - xor 12(%ebp),%r5 - - sub $8,%esp // space for register saves on stack - add $16,%ebp // increment to next round key - cmp $24,%r3 - jb 4f // 10 rounds for 128-bit key - lea 32(%ebp),%ebp - je 3f // 12 rounds for 192-bit key - lea 32(%ebp),%ebp - -2: inv_rnd1( -64(%ebp), crypto_it_tab) // 14 rounds for 256-bit key - inv_rnd2( -48(%ebp), crypto_it_tab) -3: inv_rnd1( -32(%ebp), crypto_it_tab) // 12 rounds for 192-bit key - inv_rnd2( -16(%ebp), crypto_it_tab) -4: inv_rnd1( (%ebp), crypto_it_tab) // 10 rounds for 128-bit key - inv_rnd2( +16(%ebp), crypto_it_tab) - inv_rnd1( +32(%ebp), crypto_it_tab) - inv_rnd2( +48(%ebp), crypto_it_tab) - inv_rnd1( +64(%ebp), crypto_it_tab) - inv_rnd2( +80(%ebp), crypto_it_tab) - inv_rnd1( +96(%ebp), crypto_it_tab) - inv_rnd2(+112(%ebp), crypto_it_tab) - inv_rnd1(+128(%ebp), crypto_it_tab) - inv_rnd2(+144(%ebp), crypto_il_tab) // last round uses a different table - -// move final values to the output array. CAUTION: the -// order of these assigns rely on the register mappings - - add $8,%esp - mov out_blk+12(%esp),%ebp - mov %r5,12(%ebp) - pop %edi - mov %r4,8(%ebp) - pop %esi - mov %r1,4(%ebp) - pop %ebx - mov %r0,(%ebp) - pop %ebp - ret -ENDPROC(aes_dec_blk) diff --git a/arch/x86/crypto/aes-x86_64-asm_64.S b/arch/x86/crypto/aes-x86_64-asm_64.S deleted file mode 100644 index 8739cf7795de..000000000000 --- a/arch/x86/crypto/aes-x86_64-asm_64.S +++ /dev/null @@ -1,185 +0,0 @@ -/* AES (Rijndael) implementation (FIPS PUB 197) for x86_64 - * - * Copyright (C) 2005 Andreas Steinmetz, <ast@domdv.de> - * - * License: - * This code can be distributed under the terms of the GNU General Public - * License (GPL) Version 2 provided that the above header down to and - * including this sentence is retained in full. - */ - -.extern crypto_ft_tab -.extern crypto_it_tab -.extern crypto_fl_tab -.extern crypto_il_tab - -.text - -#include <linux/linkage.h> -#include <asm/asm-offsets.h> - -#define R1 %rax -#define R1E %eax -#define R1X %ax -#define R1H %ah -#define R1L %al -#define R2 %rbx -#define R2E %ebx -#define R2X %bx -#define R2H %bh -#define R2L %bl -#define R3 %rcx -#define R3E %ecx -#define R3X %cx -#define R3H %ch -#define R3L %cl -#define R4 %rdx -#define R4E %edx -#define R4X %dx -#define R4H %dh -#define R4L %dl -#define R5 %rsi -#define R5E %esi -#define R6 %rdi -#define R6E %edi -#define R7 %r9 /* don't use %rbp; it breaks stack traces */ -#define R7E %r9d -#define R8 %r8 -#define R10 %r10 -#define R11 %r11 - -#define prologue(FUNC,KEY,B128,B192,r1,r2,r5,r6,r7,r8,r9,r10,r11) \ - ENTRY(FUNC); \ - movq r1,r2; \ - leaq KEY+48(r8),r9; \ - movq r10,r11; \ - movl (r7),r5 ## E; \ - movl 4(r7),r1 ## E; \ - movl 8(r7),r6 ## E; \ - movl 12(r7),r7 ## E; \ - movl 480(r8),r10 ## E; \ - xorl -48(r9),r5 ## E; \ - xorl -44(r9),r1 ## E; \ - xorl -40(r9),r6 ## E; \ - xorl -36(r9),r7 ## E; \ - cmpl $24,r10 ## E; \ - jb B128; \ - leaq 32(r9),r9; \ - je B192; \ - leaq 32(r9),r9; - -#define epilogue(FUNC,r1,r2,r5,r6,r7,r8,r9) \ - movq r1,r2; \ - movl r5 ## E,(r9); \ - movl r6 ## E,4(r9); \ - movl r7 ## E,8(r9); \ - movl r8 ## E,12(r9); \ - ret; \ - ENDPROC(FUNC); - -#define round(TAB,OFFSET,r1,r2,r3,r4,r5,r6,r7,r8,ra,rb,rc,rd) \ - movzbl r2 ## H,r5 ## E; \ - movzbl r2 ## L,r6 ## E; \ - movl TAB+1024(,r5,4),r5 ## E;\ - movw r4 ## X,r2 ## X; \ - movl TAB(,r6,4),r6 ## E; \ - roll $16,r2 ## E; \ - shrl $16,r4 ## E; \ - movzbl r4 ## L,r7 ## E; \ - movzbl r4 ## H,r4 ## E; \ - xorl OFFSET(r8),ra ## E; \ - xorl OFFSET+4(r8),rb ## E; \ - xorl TAB+3072(,r4,4),r5 ## E;\ - xorl TAB+2048(,r7,4),r6 ## E;\ - movzbl r1 ## L,r7 ## E; \ - movzbl r1 ## H,r4 ## E; \ - movl TAB+1024(,r4,4),r4 ## E;\ - movw r3 ## X,r1 ## X; \ - roll $16,r1 ## E; \ - shrl $16,r3 ## E; \ - xorl TAB(,r7,4),r5 ## E; \ - movzbl r3 ## L,r7 ## E; \ - movzbl r3 ## H,r3 ## E; \ - xorl TAB+3072(,r3,4),r4 ## E;\ - xorl TAB+2048(,r7,4),r5 ## E;\ - movzbl r1 ## L,r7 ## E; \ - movzbl r1 ## H,r3 ## E; \ - shrl $16,r1 ## E; \ - xorl TAB+3072(,r3,4),r6 ## E;\ - movl TAB+2048(,r7,4),r3 ## E;\ - movzbl r1 ## L,r7 ## E; \ - movzbl r1 ## H,r1 ## E; \ - xorl TAB+1024(,r1,4),r6 ## E;\ - xorl TAB(,r7,4),r3 ## E; \ - movzbl r2 ## H,r1 ## E; \ - movzbl r2 ## L,r7 ## E; \ - shrl $16,r2 ## E; \ - xorl TAB+3072(,r1,4),r3 ## E;\ - xorl TAB+2048(,r7,4),r4 ## E;\ - movzbl r2 ## H,r1 ## E; \ - movzbl r2 ## L,r2 ## E; \ - xorl OFFSET+8(r8),rc ## E; \ - xorl OFFSET+12(r8),rd ## E; \ - xorl TAB+1024(,r1,4),r3 ## E;\ - xorl TAB(,r2,4),r4 ## E; - -#define move_regs(r1,r2,r3,r4) \ - movl r3 ## E,r1 ## E; \ - movl r4 ## E,r2 ## E; - -#define entry(FUNC,KEY,B128,B192) \ - prologue(FUNC,KEY,B128,B192,R2,R8,R1,R3,R4,R6,R10,R5,R11) - -#define return(FUNC) epilogue(FUNC,R8,R2,R5,R6,R3,R4,R11) - -#define encrypt_round(TAB,OFFSET) \ - round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4) \ - move_regs(R1,R2,R5,R6) - -#define encrypt_final(TAB,OFFSET) \ - round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4) - -#define decrypt_round(TAB,OFFSET) \ - round(TAB,OFFSET,R2,R1,R4,R3,R6,R5,R7,R10,R5,R6,R3,R4) \ - move_regs(R1,R2,R5,R6) - -#define decrypt_final(TAB,OFFSET) \ - round(TAB,OFFSET,R2,R1,R4,R3,R6,R5,R7,R10,R5,R6,R3,R4) - -/* void aes_enc_blk(stuct crypto_tfm *tfm, u8 *out, const u8 *in) */ - - entry(aes_enc_blk,0,.Le128,.Le192) - encrypt_round(crypto_ft_tab,-96) - encrypt_round(crypto_ft_tab,-80) -.Le192: encrypt_round(crypto_ft_tab,-64) - encrypt_round(crypto_ft_tab,-48) -.Le128: encrypt_round(crypto_ft_tab,-32) - encrypt_round(crypto_ft_tab,-16) - encrypt_round(crypto_ft_tab, 0) - encrypt_round(crypto_ft_tab, 16) - encrypt_round(crypto_ft_tab, 32) - encrypt_round(crypto_ft_tab, 48) - encrypt_round(crypto_ft_tab, 64) - encrypt_round(crypto_ft_tab, 80) - encrypt_round(crypto_ft_tab, 96) - encrypt_final(crypto_fl_tab,112) - return(aes_enc_blk) - -/* void aes_dec_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in) */ - - entry(aes_dec_blk,240,.Ld128,.Ld192) - decrypt_round(crypto_it_tab,-96) - decrypt_round(crypto_it_tab,-80) -.Ld192: decrypt_round(crypto_it_tab,-64) - decrypt_round(crypto_it_tab,-48) -.Ld128: decrypt_round(crypto_it_tab,-32) - decrypt_round(crypto_it_tab,-16) - decrypt_round(crypto_it_tab, 0) - decrypt_round(crypto_it_tab, 16) - decrypt_round(crypto_it_tab, 32) - decrypt_round(crypto_it_tab, 48) - decrypt_round(crypto_it_tab, 64) - decrypt_round(crypto_it_tab, 80) - decrypt_round(crypto_it_tab, 96) - decrypt_final(crypto_il_tab,112) - return(aes_dec_blk) diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S index 5f6a5af9c489..ec437db1fa54 100644 --- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S +++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S @@ -544,11 +544,11 @@ ddq_add_8: * aes_ctr_enc_128_avx_by8(void *in, void *iv, void *keys, void *out, * unsigned int num_bytes) */ -ENTRY(aes_ctr_enc_128_avx_by8) +SYM_FUNC_START(aes_ctr_enc_128_avx_by8) /* call the aes main loop */ do_aes_ctrmain KEY_128 -ENDPROC(aes_ctr_enc_128_avx_by8) +SYM_FUNC_END(aes_ctr_enc_128_avx_by8) /* * routine to do AES192 CTR enc/decrypt "by8" @@ -557,11 +557,11 @@ ENDPROC(aes_ctr_enc_128_avx_by8) * aes_ctr_enc_192_avx_by8(void *in, void *iv, void *keys, void *out, * unsigned int num_bytes) */ -ENTRY(aes_ctr_enc_192_avx_by8) +SYM_FUNC_START(aes_ctr_enc_192_avx_by8) /* call the aes main loop */ do_aes_ctrmain KEY_192 -ENDPROC(aes_ctr_enc_192_avx_by8) +SYM_FUNC_END(aes_ctr_enc_192_avx_by8) /* * routine to do AES256 CTR enc/decrypt "by8" @@ -570,8 +570,8 @@ ENDPROC(aes_ctr_enc_192_avx_by8) * aes_ctr_enc_256_avx_by8(void *in, void *iv, void *keys, void *out, * unsigned int num_bytes) */ -ENTRY(aes_ctr_enc_256_avx_by8) +SYM_FUNC_START(aes_ctr_enc_256_avx_by8) /* call the aes main loop */ do_aes_ctrmain KEY_256 -ENDPROC(aes_ctr_enc_256_avx_by8) +SYM_FUNC_END(aes_ctr_enc_256_avx_by8) diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c index 9e9d819e8bc3..7b7dc05fa1a4 100644 --- a/arch/x86/crypto/aes_glue.c +++ b/arch/x86/crypto/aes_glue.c @@ -1,71 +1 @@ // SPDX-License-Identifier: GPL-2.0-only -/* - * Glue Code for the asm optimized version of the AES Cipher Algorithm - * - */ - -#include <linux/module.h> -#include <crypto/aes.h> -#include <asm/crypto/aes.h> - -asmlinkage void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); -asmlinkage void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); - -void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) -{ - aes_enc_blk(ctx, dst, src); -} -EXPORT_SYMBOL_GPL(crypto_aes_encrypt_x86); - -void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) -{ - aes_dec_blk(ctx, dst, src); -} -EXPORT_SYMBOL_GPL(crypto_aes_decrypt_x86); - -static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) -{ - aes_enc_blk(crypto_tfm_ctx(tfm), dst, src); -} - -static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) -{ - aes_dec_blk(crypto_tfm_ctx(tfm), dst, src); -} - -static struct crypto_alg aes_alg = { - .cra_name = "aes", - .cra_driver_name = "aes-asm", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_CIPHER, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct crypto_aes_ctx), - .cra_module = THIS_MODULE, - .cra_u = { - .cipher = { - .cia_min_keysize = AES_MIN_KEY_SIZE, - .cia_max_keysize = AES_MAX_KEY_SIZE, - .cia_setkey = crypto_aes_set_key, - .cia_encrypt = aes_encrypt, - .cia_decrypt = aes_decrypt - } - } -}; - -static int __init aes_init(void) -{ - return crypto_register_alg(&aes_alg); -} - -static void __exit aes_fini(void) -{ - crypto_unregister_alg(&aes_alg); -} - -module_init(aes_init); -module_exit(aes_fini); - -MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_CRYPTO("aes"); -MODULE_ALIAS_CRYPTO("aes-asm"); diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index e40bdf024ba7..cad6e1bfa7d5 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -1592,7 +1592,7 @@ _esb_loop_\@: * poly = x^128 + x^127 + x^126 + x^121 + 1 * *****************************************************************************/ -ENTRY(aesni_gcm_dec) +SYM_FUNC_START(aesni_gcm_dec) FUNC_SAVE GCM_INIT %arg6, arg7, arg8, arg9 @@ -1600,7 +1600,7 @@ ENTRY(aesni_gcm_dec) GCM_COMPLETE arg10, arg11 FUNC_RESTORE ret -ENDPROC(aesni_gcm_dec) +SYM_FUNC_END(aesni_gcm_dec) /***************************************************************************** @@ -1680,7 +1680,7 @@ ENDPROC(aesni_gcm_dec) * * poly = x^128 + x^127 + x^126 + x^121 + 1 ***************************************************************************/ -ENTRY(aesni_gcm_enc) +SYM_FUNC_START(aesni_gcm_enc) FUNC_SAVE GCM_INIT %arg6, arg7, arg8, arg9 @@ -1689,7 +1689,7 @@ ENTRY(aesni_gcm_enc) GCM_COMPLETE arg10, arg11 FUNC_RESTORE ret -ENDPROC(aesni_gcm_enc) +SYM_FUNC_END(aesni_gcm_enc) /***************************************************************************** * void aesni_gcm_init(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. @@ -1702,12 +1702,12 @@ ENDPROC(aesni_gcm_enc) * const u8 *aad, // Additional Authentication Data (AAD) * u64 aad_len) // Length of AAD in bytes. */ -ENTRY(aesni_gcm_init) +SYM_FUNC_START(aesni_gcm_init) FUNC_SAVE GCM_INIT %arg3, %arg4,%arg5, %arg6 FUNC_RESTORE ret -ENDPROC(aesni_gcm_init) +SYM_FUNC_END(aesni_gcm_init) /***************************************************************************** * void aesni_gcm_enc_update(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. @@ -1717,12 +1717,12 @@ ENDPROC(aesni_gcm_init) * const u8 *in, // Plaintext input * u64 plaintext_len, // Length of data in bytes for encryption. */ -ENTRY(aesni_gcm_enc_update) +SYM_FUNC_START(aesni_gcm_enc_update) FUNC_SAVE GCM_ENC_DEC enc FUNC_RESTORE ret -ENDPROC(aesni_gcm_enc_update) +SYM_FUNC_END(aesni_gcm_enc_update) /***************************************************************************** * void aesni_gcm_dec_update(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. @@ -1732,12 +1732,12 @@ ENDPROC(aesni_gcm_enc_update) * const u8 *in, // Plaintext input * u64 plaintext_len, // Length of data in bytes for encryption. */ -ENTRY(aesni_gcm_dec_update) +SYM_FUNC_START(aesni_gcm_dec_update) FUNC_SAVE GCM_ENC_DEC dec FUNC_RESTORE ret -ENDPROC(aesni_gcm_dec_update) +SYM_FUNC_END(aesni_gcm_dec_update) /***************************************************************************** * void aesni_gcm_finalize(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. @@ -1747,19 +1747,18 @@ ENDPROC(aesni_gcm_dec_update) * u64 auth_tag_len); // Authenticated Tag Length in bytes. Valid values are 16 (most likely), * // 12 or 8. */ -ENTRY(aesni_gcm_finalize) +SYM_FUNC_START(aesni_gcm_finalize) FUNC_SAVE GCM_COMPLETE %arg3 %arg4 FUNC_RESTORE ret -ENDPROC(aesni_gcm_finalize) +SYM_FUNC_END(aesni_gcm_finalize) #endif -.align 4 -_key_expansion_128: -_key_expansion_256a: +SYM_FUNC_START_LOCAL_ALIAS(_key_expansion_128) +SYM_FUNC_START_LOCAL(_key_expansion_256a) pshufd $0b11111111, %xmm1, %xmm1 shufps $0b00010000, %xmm0, %xmm4 pxor %xmm4, %xmm0 @@ -1769,11 +1768,10 @@ _key_expansion_256a: movaps %xmm0, (TKEYP) add $0x10, TKEYP ret -ENDPROC(_key_expansion_128) -ENDPROC(_key_expansion_256a) +SYM_FUNC_END(_key_expansion_256a) +SYM_FUNC_END_ALIAS(_key_expansion_128) -.align 4 -_key_expansion_192a: +SYM_FUNC_START_LOCAL(_key_expansion_192a) pshufd $0b01010101, %xmm1, %xmm1 shufps $0b00010000, %xmm0, %xmm4 pxor %xmm4, %xmm0 @@ -1795,10 +1793,9 @@ _key_expansion_192a: movaps %xmm1, 0x10(TKEYP) add $0x20, TKEYP ret -ENDPROC(_key_expansion_192a) +SYM_FUNC_END(_key_expansion_192a) -.align 4 -_key_expansion_192b: +SYM_FUNC_START_LOCAL(_key_expansion_192b) pshufd $0b01010101, %xmm1, %xmm1 shufps $0b00010000, %xmm0, %xmm4 pxor %xmm4, %xmm0 @@ -1815,10 +1812,9 @@ _key_expansion_192b: movaps %xmm0, (TKEYP) add $0x10, TKEYP ret -ENDPROC(_key_expansion_192b) +SYM_FUNC_END(_key_expansion_192b) -.align 4 -_key_expansion_256b: +SYM_FUNC_START_LOCAL(_key_expansion_256b) pshufd $0b10101010, %xmm1, %xmm1 shufps $0b00010000, %xmm2, %xmm4 pxor %xmm4, %xmm2 @@ -1828,13 +1824,13 @@ _key_expansion_256b: movaps %xmm2, (TKEYP) add $0x10, TKEYP ret -ENDPROC(_key_expansion_256b) +SYM_FUNC_END(_key_expansion_256b) /* * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, * unsigned int key_len) */ -ENTRY(aesni_set_key) +SYM_FUNC_START(aesni_set_key) FRAME_BEGIN #ifndef __x86_64__ pushl KEYP @@ -1943,12 +1939,12 @@ ENTRY(aesni_set_key) #endif FRAME_END ret -ENDPROC(aesni_set_key) +SYM_FUNC_END(aesni_set_key) /* - * void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) + * void aesni_enc(const void *ctx, u8 *dst, const u8 *src) */ -ENTRY(aesni_enc) +SYM_FUNC_START(aesni_enc) FRAME_BEGIN #ifndef __x86_64__ pushl KEYP @@ -1967,7 +1963,7 @@ ENTRY(aesni_enc) #endif FRAME_END ret -ENDPROC(aesni_enc) +SYM_FUNC_END(aesni_enc) /* * _aesni_enc1: internal ABI @@ -1981,8 +1977,7 @@ ENDPROC(aesni_enc) * KEY * TKEYP (T1) */ -.align 4 -_aesni_enc1: +SYM_FUNC_START_LOCAL(_aesni_enc1) movaps (KEYP), KEY # key mov KEYP, TKEYP pxor KEY, STATE # round 0 @@ -2025,7 +2020,7 @@ _aesni_enc1: movaps 0x70(TKEYP), KEY AESENCLAST KEY STATE ret -ENDPROC(_aesni_enc1) +SYM_FUNC_END(_aesni_enc1) /* * _aesni_enc4: internal ABI @@ -2045,8 +2040,7 @@ ENDPROC(_aesni_enc1) * KEY * TKEYP (T1) */ -.align 4 -_aesni_enc4: +SYM_FUNC_START_LOCAL(_aesni_enc4) movaps (KEYP), KEY # key mov KEYP, TKEYP pxor KEY, STATE1 # round 0 @@ -2134,12 +2128,12 @@ _aesni_enc4: AESENCLAST KEY STATE3 AESENCLAST KEY STATE4 ret -ENDPROC(_aesni_enc4) +SYM_FUNC_END(_aesni_enc4) /* - * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) + * void aesni_dec (const void *ctx, u8 *dst, const u8 *src) */ -ENTRY(aesni_dec) +SYM_FUNC_START(aesni_dec) FRAME_BEGIN #ifndef __x86_64__ pushl KEYP @@ -2159,7 +2153,7 @@ ENTRY(aesni_dec) #endif FRAME_END ret -ENDPROC(aesni_dec) +SYM_FUNC_END(aesni_dec) /* * _aesni_dec1: internal ABI @@ -2173,8 +2167,7 @@ ENDPROC(aesni_dec) * KEY * TKEYP (T1) */ -.align 4 -_aesni_dec1: +SYM_FUNC_START_LOCAL(_aesni_dec1) movaps (KEYP), KEY # key mov KEYP, TKEYP pxor KEY, STATE # round 0 @@ -2217,7 +2210,7 @@ _aesni_dec1: movaps 0x70(TKEYP), KEY AESDECLAST KEY STATE ret -ENDPROC(_aesni_dec1) +SYM_FUNC_END(_aesni_dec1) /* * _aesni_dec4: internal ABI @@ -2237,8 +2230,7 @@ ENDPROC(_aesni_dec1) * KEY * TKEYP (T1) */ -.align 4 -_aesni_dec4: +SYM_FUNC_START_LOCAL(_aesni_dec4) movaps (KEYP), KEY # key mov KEYP, TKEYP pxor KEY, STATE1 # round 0 @@ -2326,13 +2318,13 @@ _aesni_dec4: AESDECLAST KEY STATE3 AESDECLAST KEY STATE4 ret -ENDPROC(_aesni_dec4) +SYM_FUNC_END(_aesni_dec4) /* * void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len) */ -ENTRY(aesni_ecb_enc) +SYM_FUNC_START(aesni_ecb_enc) FRAME_BEGIN #ifndef __x86_64__ pushl LEN @@ -2386,13 +2378,13 @@ ENTRY(aesni_ecb_enc) #endif FRAME_END ret -ENDPROC(aesni_ecb_enc) +SYM_FUNC_END(aesni_ecb_enc) /* * void aesni_ecb_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len); */ -ENTRY(aesni_ecb_dec) +SYM_FUNC_START(aesni_ecb_dec) FRAME_BEGIN #ifndef __x86_64__ pushl LEN @@ -2447,13 +2439,13 @@ ENTRY(aesni_ecb_dec) #endif FRAME_END ret -ENDPROC(aesni_ecb_dec) +SYM_FUNC_END(aesni_ecb_dec) /* * void aesni_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len, u8 *iv) */ -ENTRY(aesni_cbc_enc) +SYM_FUNC_START(aesni_cbc_enc) FRAME_BEGIN #ifndef __x86_64__ pushl IVP @@ -2491,13 +2483,13 @@ ENTRY(aesni_cbc_enc) #endif FRAME_END ret -ENDPROC(aesni_cbc_enc) +SYM_FUNC_END(aesni_cbc_enc) /* * void aesni_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len, u8 *iv) */ -ENTRY(aesni_cbc_dec) +SYM_FUNC_START(aesni_cbc_dec) FRAME_BEGIN #ifndef __x86_64__ pushl IVP @@ -2584,7 +2576,7 @@ ENTRY(aesni_cbc_dec) #endif FRAME_END ret -ENDPROC(aesni_cbc_dec) +SYM_FUNC_END(aesni_cbc_dec) #ifdef __x86_64__ .pushsection .rodata @@ -2604,8 +2596,7 @@ ENDPROC(aesni_cbc_dec) * INC: == 1, in little endian * BSWAP_MASK == endian swapping mask */ -.align 4 -_aesni_inc_init: +SYM_FUNC_START_LOCAL(_aesni_inc_init) movaps .Lbswap_mask, BSWAP_MASK movaps IV, CTR PSHUFB_XMM BSWAP_MASK CTR @@ -2613,7 +2604,7 @@ _aesni_inc_init: MOVQ_R64_XMM TCTR_LOW INC MOVQ_R64_XMM CTR TCTR_LOW ret -ENDPROC(_aesni_inc_init) +SYM_FUNC_END(_aesni_inc_init) /* * _aesni_inc: internal ABI @@ -2630,8 +2621,7 @@ ENDPROC(_aesni_inc_init) * CTR: == output IV, in little endian * TCTR_LOW: == lower qword of CTR */ -.align 4 -_aesni_inc: +SYM_FUNC_START_LOCAL(_aesni_inc) paddq INC, CTR add $1, TCTR_LOW jnc .Linc_low @@ -2642,13 +2632,13 @@ _aesni_inc: movaps CTR, IV PSHUFB_XMM BSWAP_MASK IV ret -ENDPROC(_aesni_inc) +SYM_FUNC_END(_aesni_inc) /* * void aesni_ctr_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len, u8 *iv) */ -ENTRY(aesni_ctr_enc) +SYM_FUNC_START(aesni_ctr_enc) FRAME_BEGIN cmp $16, LEN jb .Lctr_enc_just_ret @@ -2705,7 +2695,7 @@ ENTRY(aesni_ctr_enc) .Lctr_enc_just_ret: FRAME_END ret -ENDPROC(aesni_ctr_enc) +SYM_FUNC_END(aesni_ctr_enc) /* * _aesni_gf128mul_x_ble: internal ABI @@ -2726,10 +2716,10 @@ ENDPROC(aesni_ctr_enc) pxor CTR, IV; /* - * void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, - * bool enc, u8 *iv) + * void aesni_xts_crypt8(const struct crypto_aes_ctx *ctx, u8 *dst, + * const u8 *src, bool enc, le128 *iv) */ -ENTRY(aesni_xts_crypt8) +SYM_FUNC_START(aesni_xts_crypt8) FRAME_BEGIN cmpb $0, %cl movl $0, %ecx @@ -2833,6 +2823,6 @@ ENTRY(aesni_xts_crypt8) FRAME_END ret -ENDPROC(aesni_xts_crypt8) +SYM_FUNC_END(aesni_xts_crypt8) #endif diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index 91c039ab5699..bfa1c0b3e5b4 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -1775,12 +1775,12 @@ _initial_blocks_done\@: # const u8 *aad, /* Additional Authentication Data (AAD)*/ # u64 aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */ ############################################################# -ENTRY(aesni_gcm_init_avx_gen2) +SYM_FUNC_START(aesni_gcm_init_avx_gen2) FUNC_SAVE INIT GHASH_MUL_AVX, PRECOMPUTE_AVX FUNC_RESTORE ret -ENDPROC(aesni_gcm_init_avx_gen2) +SYM_FUNC_END(aesni_gcm_init_avx_gen2) ############################################################################### #void aesni_gcm_enc_update_avx_gen2( @@ -1790,7 +1790,7 @@ ENDPROC(aesni_gcm_init_avx_gen2) # const u8 *in, /* Plaintext input */ # u64 plaintext_len) /* Length of data in Bytes for encryption. */ ############################################################################### -ENTRY(aesni_gcm_enc_update_avx_gen2) +SYM_FUNC_START(aesni_gcm_enc_update_avx_gen2) FUNC_SAVE mov keysize, %eax cmp $32, %eax @@ -1809,7 +1809,7 @@ key_256_enc_update: GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 13 FUNC_RESTORE ret -ENDPROC(aesni_gcm_enc_update_avx_gen2) +SYM_FUNC_END(aesni_gcm_enc_update_avx_gen2) ############################################################################### #void aesni_gcm_dec_update_avx_gen2( @@ -1819,7 +1819,7 @@ ENDPROC(aesni_gcm_enc_update_avx_gen2) # const u8 *in, /* Ciphertext input */ # u64 plaintext_len) /* Length of data in Bytes for encryption. */ ############################################################################### -ENTRY(aesni_gcm_dec_update_avx_gen2) +SYM_FUNC_START(aesni_gcm_dec_update_avx_gen2) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -1838,7 +1838,7 @@ key_256_dec_update: GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 13 FUNC_RESTORE ret -ENDPROC(aesni_gcm_dec_update_avx_gen2) +SYM_FUNC_END(aesni_gcm_dec_update_avx_gen2) ############################################################################### #void aesni_gcm_finalize_avx_gen2( @@ -1848,7 +1848,7 @@ ENDPROC(aesni_gcm_dec_update_avx_gen2) # u64 auth_tag_len)# /* Authenticated Tag Length in bytes. # Valid values are 16 (most likely), 12 or 8. */ ############################################################################### -ENTRY(aesni_gcm_finalize_avx_gen2) +SYM_FUNC_START(aesni_gcm_finalize_avx_gen2) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -1867,7 +1867,7 @@ key_256_finalize: GCM_COMPLETE GHASH_MUL_AVX, 13, arg3, arg4 FUNC_RESTORE ret -ENDPROC(aesni_gcm_finalize_avx_gen2) +SYM_FUNC_END(aesni_gcm_finalize_avx_gen2) #endif /* CONFIG_AS_AVX */ @@ -2746,12 +2746,12 @@ _initial_blocks_done\@: # const u8 *aad, /* Additional Authentication Data (AAD)*/ # u64 aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */ ############################################################# -ENTRY(aesni_gcm_init_avx_gen4) +SYM_FUNC_START(aesni_gcm_init_avx_gen4) FUNC_SAVE INIT GHASH_MUL_AVX2, PRECOMPUTE_AVX2 FUNC_RESTORE ret -ENDPROC(aesni_gcm_init_avx_gen4) +SYM_FUNC_END(aesni_gcm_init_avx_gen4) ############################################################################### #void aesni_gcm_enc_avx_gen4( @@ -2761,7 +2761,7 @@ ENDPROC(aesni_gcm_init_avx_gen4) # const u8 *in, /* Plaintext input */ # u64 plaintext_len) /* Length of data in Bytes for encryption. */ ############################################################################### -ENTRY(aesni_gcm_enc_update_avx_gen4) +SYM_FUNC_START(aesni_gcm_enc_update_avx_gen4) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -2780,7 +2780,7 @@ key_256_enc_update4: GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 13 FUNC_RESTORE ret -ENDPROC(aesni_gcm_enc_update_avx_gen4) +SYM_FUNC_END(aesni_gcm_enc_update_avx_gen4) ############################################################################### #void aesni_gcm_dec_update_avx_gen4( @@ -2790,7 +2790,7 @@ ENDPROC(aesni_gcm_enc_update_avx_gen4) # const u8 *in, /* Ciphertext input */ # u64 plaintext_len) /* Length of data in Bytes for encryption. */ ############################################################################### -ENTRY(aesni_gcm_dec_update_avx_gen4) +SYM_FUNC_START(aesni_gcm_dec_update_avx_gen4) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -2809,7 +2809,7 @@ key_256_dec_update4: GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 13 FUNC_RESTORE ret -ENDPROC(aesni_gcm_dec_update_avx_gen4) +SYM_FUNC_END(aesni_gcm_dec_update_avx_gen4) ############################################################################### #void aesni_gcm_finalize_avx_gen4( @@ -2819,7 +2819,7 @@ ENDPROC(aesni_gcm_dec_update_avx_gen4) # u64 auth_tag_len)# /* Authenticated Tag Length in bytes. # Valid values are 16 (most likely), 12 or 8. */ ############################################################################### -ENTRY(aesni_gcm_finalize_avx_gen4) +SYM_FUNC_START(aesni_gcm_finalize_avx_gen4) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -2838,6 +2838,6 @@ key_256_finalize4: GCM_COMPLETE GHASH_MUL_AVX2, 13, arg3, arg4 FUNC_RESTORE ret -ENDPROC(aesni_gcm_finalize_avx_gen4) +SYM_FUNC_END(aesni_gcm_finalize_avx_gen4) #endif /* CONFIG_AS_AVX2 */ diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 73c0ccb009a0..bbbebbd35b5d 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -26,7 +26,6 @@ #include <crypto/gcm.h> #include <crypto/xts.h> #include <asm/cpu_device_id.h> -#include <asm/crypto/aes.h> #include <asm/simd.h> #include <crypto/scatterwalk.h> #include <crypto/internal/aead.h> @@ -84,10 +83,8 @@ struct gcm_context_data { asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, unsigned int key_len); -asmlinkage void aesni_enc(struct crypto_aes_ctx *ctx, u8 *out, - const u8 *in); -asmlinkage void aesni_dec(struct crypto_aes_ctx *ctx, u8 *out, - const u8 *in); +asmlinkage void aesni_enc(const void *ctx, u8 *out, const u8 *in); +asmlinkage void aesni_dec(const void *ctx, u8 *out, const u8 *in); asmlinkage void aesni_ecb_enc(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len); asmlinkage void aesni_ecb_dec(struct crypto_aes_ctx *ctx, u8 *out, @@ -107,8 +104,8 @@ static void (*aesni_ctr_enc_tfm)(struct crypto_aes_ctx *ctx, u8 *out, asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len, u8 *iv); -asmlinkage void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, u8 *out, - const u8 *in, bool enc, u8 *iv); +asmlinkage void aesni_xts_crypt8(const struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, bool enc, le128 *iv); /* asmlinkage void aesni_gcm_enc() * void *ctx, AES Key schedule. Starts on a 16 byte boundary. @@ -319,17 +316,14 @@ static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx, const u8 *in_key, unsigned int key_len) { struct crypto_aes_ctx *ctx = aes_ctx(raw_ctx); - u32 *flags = &tfm->crt_flags; int err; if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 && - key_len != AES_KEYSIZE_256) { - *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + key_len != AES_KEYSIZE_256) return -EINVAL; - } if (!crypto_simd_usable()) - err = crypto_aes_expand_key(ctx, in_key, key_len); + err = aes_expandkey(ctx, in_key, key_len); else { kernel_fpu_begin(); err = aesni_set_key(ctx, in_key, key_len); @@ -345,26 +339,26 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, return aes_set_key_common(tfm, crypto_tfm_ctx(tfm), in_key, key_len); } -static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +static void aesni_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); - if (!crypto_simd_usable()) - crypto_aes_encrypt_x86(ctx, dst, src); - else { + if (!crypto_simd_usable()) { + aes_encrypt(ctx, dst, src); + } else { kernel_fpu_begin(); aesni_enc(ctx, dst, src); kernel_fpu_end(); } } -static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +static void aesni_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); - if (!crypto_simd_usable()) - crypto_aes_decrypt_x86(ctx, dst, src); - else { + if (!crypto_simd_usable()) { + aes_decrypt(ctx, dst, src); + } else { kernel_fpu_begin(); aesni_dec(ctx, dst, src); kernel_fpu_end(); @@ -551,29 +545,24 @@ static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key, } -static void aesni_xts_tweak(void *ctx, u8 *out, const u8 *in) +static void aesni_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - aesni_enc(ctx, out, in); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, aesni_enc); } -static void aesni_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv) +static void aesni_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, GLUE_FUNC_CAST(aesni_enc)); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, aesni_dec); } -static void aesni_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv) +static void aesni_xts_enc8(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, GLUE_FUNC_CAST(aesni_dec)); + aesni_xts_crypt8(ctx, dst, src, true, iv); } -static void aesni_xts_enc8(void *ctx, u128 *dst, const u128 *src, le128 *iv) +static void aesni_xts_dec8(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - aesni_xts_crypt8(ctx, (u8 *)dst, (const u8 *)src, true, (u8 *)iv); -} - -static void aesni_xts_dec8(void *ctx, u128 *dst, const u128 *src, le128 *iv) -{ - aesni_xts_crypt8(ctx, (u8 *)dst, (const u8 *)src, false, (u8 *)iv); + aesni_xts_crypt8(ctx, dst, src, false, iv); } static const struct common_glue_ctx aesni_enc_xts = { @@ -582,10 +571,10 @@ static const struct common_glue_ctx aesni_enc_xts = { .funcs = { { .num_blocks = 8, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(aesni_xts_enc8) } + .fn_u = { .xts = aesni_xts_enc8 } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(aesni_xts_enc) } + .fn_u = { .xts = aesni_xts_enc } } } }; @@ -595,10 +584,10 @@ static const struct common_glue_ctx aesni_dec_xts = { .funcs = { { .num_blocks = 8, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(aesni_xts_dec8) } + .fn_u = { .xts = aesni_xts_dec8 } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(aesni_xts_dec) } + .fn_u = { .xts = aesni_xts_dec } } } }; @@ -607,10 +596,10 @@ static int xts_encrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&aesni_enc_xts, req, - XTS_TWEAK_CAST(aesni_xts_tweak), + return glue_xts_req_128bit(&aesni_enc_xts, req, aesni_enc, aes_ctx(ctx->raw_tweak_ctx), - aes_ctx(ctx->raw_crypt_ctx)); + aes_ctx(ctx->raw_crypt_ctx), + false); } static int xts_decrypt(struct skcipher_request *req) @@ -618,35 +607,30 @@ static int xts_decrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&aesni_dec_xts, req, - XTS_TWEAK_CAST(aesni_xts_tweak), + return glue_xts_req_128bit(&aesni_dec_xts, req, aesni_enc, aes_ctx(ctx->raw_tweak_ctx), - aes_ctx(ctx->raw_crypt_ctx)); + aes_ctx(ctx->raw_crypt_ctx), + true); } static int rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len) { - struct crypto_cipher *tfm; + struct crypto_aes_ctx ctx; int ret; - tfm = crypto_alloc_cipher("aes", 0, 0); - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - ret = crypto_cipher_setkey(tfm, key, key_len); + ret = aes_expandkey(&ctx, key, key_len); if (ret) - goto out_free_cipher; + return ret; /* Clear the data in the hash sub key container to zero.*/ /* We want to cipher all zeros to create the hash sub key. */ memset(hash_subkey, 0, RFC4106_HASH_SUBKEY_SIZE); - crypto_cipher_encrypt_one(tfm, hash_subkey, hash_subkey); + aes_encrypt(&ctx, hash_subkey, hash_subkey); -out_free_cipher: - crypto_free_cipher(tfm); - return ret; + memzero_explicit(&ctx, sizeof(ctx)); + return 0; } static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key, @@ -654,10 +638,9 @@ static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key, { struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(aead); - if (key_len < 4) { - crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); + if (key_len < 4) return -EINVAL; - } + /*Account for 4 byte nonce at the end.*/ key_len -= 4; @@ -919,8 +902,8 @@ static struct crypto_alg aesni_cipher_alg = { .cia_min_keysize = AES_MIN_KEY_SIZE, .cia_max_keysize = AES_MAX_KEY_SIZE, .cia_setkey = aes_set_key, - .cia_encrypt = aes_encrypt, - .cia_decrypt = aes_decrypt + .cia_encrypt = aesni_encrypt, + .cia_decrypt = aesni_decrypt } } }; diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S new file mode 100644 index 000000000000..24910b766bdd --- /dev/null +++ b/arch/x86/crypto/blake2s-core.S @@ -0,0 +1,258 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* + * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + * Copyright (C) 2017-2019 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved. + */ + +#include <linux/linkage.h> + +.section .rodata.cst32.BLAKE2S_IV, "aM", @progbits, 32 +.align 32 +IV: .octa 0xA54FF53A3C6EF372BB67AE856A09E667 + .octa 0x5BE0CD191F83D9AB9B05688C510E527F +.section .rodata.cst16.ROT16, "aM", @progbits, 16 +.align 16 +ROT16: .octa 0x0D0C0F0E09080B0A0504070601000302 +.section .rodata.cst16.ROR328, "aM", @progbits, 16 +.align 16 +ROR328: .octa 0x0C0F0E0D080B0A090407060500030201 +.section .rodata.cst64.BLAKE2S_SIGMA, "aM", @progbits, 160 +.align 64 +SIGMA: +.byte 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13 +.byte 14, 4, 9, 13, 10, 8, 15, 6, 5, 1, 0, 11, 3, 12, 2, 7 +.byte 11, 12, 5, 15, 8, 0, 2, 13, 9, 10, 3, 7, 4, 14, 6, 1 +.byte 7, 3, 13, 11, 9, 1, 12, 14, 15, 2, 5, 4, 8, 6, 10, 0 +.byte 9, 5, 2, 10, 0, 7, 4, 15, 3, 14, 11, 6, 13, 1, 12, 8 +.byte 2, 6, 0, 8, 12, 10, 11, 3, 1, 4, 7, 15, 9, 13, 5, 14 +.byte 12, 1, 14, 4, 5, 15, 13, 10, 8, 0, 6, 9, 11, 7, 3, 2 +.byte 13, 7, 12, 3, 11, 14, 1, 9, 2, 5, 15, 8, 10, 0, 4, 6 +.byte 6, 14, 11, 0, 15, 9, 3, 8, 10, 12, 13, 1, 5, 2, 7, 4 +.byte 10, 8, 7, 1, 2, 4, 6, 5, 13, 15, 9, 3, 0, 11, 14, 12 +#ifdef CONFIG_AS_AVX512 +.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 640 +.align 64 +SIGMA2: +.long 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13 +.long 8, 2, 13, 15, 10, 9, 12, 3, 6, 4, 0, 14, 5, 11, 1, 7 +.long 11, 13, 8, 6, 5, 10, 14, 3, 2, 4, 12, 15, 1, 0, 7, 9 +.long 11, 10, 7, 0, 8, 15, 1, 13, 3, 6, 2, 12, 4, 14, 9, 5 +.long 4, 10, 9, 14, 15, 0, 11, 8, 1, 7, 3, 13, 2, 5, 6, 12 +.long 2, 11, 4, 15, 14, 3, 10, 8, 13, 6, 5, 7, 0, 12, 1, 9 +.long 4, 8, 15, 9, 14, 11, 13, 5, 3, 2, 1, 12, 6, 10, 7, 0 +.long 6, 13, 0, 14, 12, 2, 1, 11, 15, 4, 5, 8, 7, 9, 3, 10 +.long 15, 5, 4, 13, 10, 7, 3, 11, 12, 2, 0, 6, 9, 8, 1, 14 +.long 8, 7, 14, 11, 13, 15, 0, 12, 10, 4, 5, 6, 3, 2, 1, 9 +#endif /* CONFIG_AS_AVX512 */ + +.text +#ifdef CONFIG_AS_SSSE3 +SYM_FUNC_START(blake2s_compress_ssse3) + testq %rdx,%rdx + je .Lendofloop + movdqu (%rdi),%xmm0 + movdqu 0x10(%rdi),%xmm1 + movdqa ROT16(%rip),%xmm12 + movdqa ROR328(%rip),%xmm13 + movdqu 0x20(%rdi),%xmm14 + movq %rcx,%xmm15 + leaq SIGMA+0xa0(%rip),%r8 + jmp .Lbeginofloop + .align 32 +.Lbeginofloop: + movdqa %xmm0,%xmm10 + movdqa %xmm1,%xmm11 + paddq %xmm15,%xmm14 + movdqa IV(%rip),%xmm2 + movdqa %xmm14,%xmm3 + pxor IV+0x10(%rip),%xmm3 + leaq SIGMA(%rip),%rcx +.Lroundloop: + movzbl (%rcx),%eax + movd (%rsi,%rax,4),%xmm4 + movzbl 0x1(%rcx),%eax + movd (%rsi,%rax,4),%xmm5 + movzbl 0x2(%rcx),%eax + movd (%rsi,%rax,4),%xmm6 + movzbl 0x3(%rcx),%eax + movd (%rsi,%rax,4),%xmm7 + punpckldq %xmm5,%xmm4 + punpckldq %xmm7,%xmm6 + punpcklqdq %xmm6,%xmm4 + paddd %xmm4,%xmm0 + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm12,%xmm3 + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm8 + psrld $0xc,%xmm1 + pslld $0x14,%xmm8 + por %xmm8,%xmm1 + movzbl 0x4(%rcx),%eax + movd (%rsi,%rax,4),%xmm5 + movzbl 0x5(%rcx),%eax + movd (%rsi,%rax,4),%xmm6 + movzbl 0x6(%rcx),%eax + movd (%rsi,%rax,4),%xmm7 + movzbl 0x7(%rcx),%eax + movd (%rsi,%rax,4),%xmm4 + punpckldq %xmm6,%xmm5 + punpckldq %xmm4,%xmm7 + punpcklqdq %xmm7,%xmm5 + paddd %xmm5,%xmm0 + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm13,%xmm3 + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm8 + psrld $0x7,%xmm1 + pslld $0x19,%xmm8 + por %xmm8,%xmm1 + pshufd $0x93,%xmm0,%xmm0 + pshufd $0x4e,%xmm3,%xmm3 + pshufd $0x39,%xmm2,%xmm2 + movzbl 0x8(%rcx),%eax + movd (%rsi,%rax,4),%xmm6 + movzbl 0x9(%rcx),%eax + movd (%rsi,%rax,4),%xmm7 + movzbl 0xa(%rcx),%eax + movd (%rsi,%rax,4),%xmm4 + movzbl 0xb(%rcx),%eax + movd (%rsi,%rax,4),%xmm5 + punpckldq %xmm7,%xmm6 + punpckldq %xmm5,%xmm4 + punpcklqdq %xmm4,%xmm6 + paddd %xmm6,%xmm0 + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm12,%xmm3 + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm8 + psrld $0xc,%xmm1 + pslld $0x14,%xmm8 + por %xmm8,%xmm1 + movzbl 0xc(%rcx),%eax + movd (%rsi,%rax,4),%xmm7 + movzbl 0xd(%rcx),%eax + movd (%rsi,%rax,4),%xmm4 + movzbl 0xe(%rcx),%eax + movd (%rsi,%rax,4),%xmm5 + movzbl 0xf(%rcx),%eax + movd (%rsi,%rax,4),%xmm6 + punpckldq %xmm4,%xmm7 + punpckldq %xmm6,%xmm5 + punpcklqdq %xmm5,%xmm7 + paddd %xmm7,%xmm0 + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm13,%xmm3 + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm8 + psrld $0x7,%xmm1 + pslld $0x19,%xmm8 + por %xmm8,%xmm1 + pshufd $0x39,%xmm0,%xmm0 + pshufd $0x4e,%xmm3,%xmm3 + pshufd $0x93,%xmm2,%xmm2 + addq $0x10,%rcx + cmpq %r8,%rcx + jnz .Lroundloop + pxor %xmm2,%xmm0 + pxor %xmm3,%xmm1 + pxor %xmm10,%xmm0 + pxor %xmm11,%xmm1 + addq $0x40,%rsi + decq %rdx + jnz .Lbeginofloop + movdqu %xmm0,(%rdi) + movdqu %xmm1,0x10(%rdi) + movdqu %xmm14,0x20(%rdi) +.Lendofloop: + ret +SYM_FUNC_END(blake2s_compress_ssse3) +#endif /* CONFIG_AS_SSSE3 */ + +#ifdef CONFIG_AS_AVX512 +SYM_FUNC_START(blake2s_compress_avx512) + vmovdqu (%rdi),%xmm0 + vmovdqu 0x10(%rdi),%xmm1 + vmovdqu 0x20(%rdi),%xmm4 + vmovq %rcx,%xmm5 + vmovdqa IV(%rip),%xmm14 + vmovdqa IV+16(%rip),%xmm15 + jmp .Lblake2s_compress_avx512_mainloop +.align 32 +.Lblake2s_compress_avx512_mainloop: + vmovdqa %xmm0,%xmm10 + vmovdqa %xmm1,%xmm11 + vpaddq %xmm5,%xmm4,%xmm4 + vmovdqa %xmm14,%xmm2 + vpxor %xmm15,%xmm4,%xmm3 + vmovdqu (%rsi),%ymm6 + vmovdqu 0x20(%rsi),%ymm7 + addq $0x40,%rsi + leaq SIGMA2(%rip),%rax + movb $0xa,%cl +.Lblake2s_compress_avx512_roundloop: + addq $0x40,%rax + vmovdqa -0x40(%rax),%ymm8 + vmovdqa -0x20(%rax),%ymm9 + vpermi2d %ymm7,%ymm6,%ymm8 + vpermi2d %ymm7,%ymm6,%ymm9 + vmovdqa %ymm8,%ymm6 + vmovdqa %ymm9,%ymm7 + vpaddd %xmm8,%xmm0,%xmm0 + vpaddd %xmm1,%xmm0,%xmm0 + vpxor %xmm0,%xmm3,%xmm3 + vprord $0x10,%xmm3,%xmm3 + vpaddd %xmm3,%xmm2,%xmm2 + vpxor %xmm2,%xmm1,%xmm1 + vprord $0xc,%xmm1,%xmm1 + vextracti128 $0x1,%ymm8,%xmm8 + vpaddd %xmm8,%xmm0,%xmm0 + vpaddd %xmm1,%xmm0,%xmm0 + vpxor %xmm0,%xmm3,%xmm3 + vprord $0x8,%xmm3,%xmm3 + vpaddd %xmm3,%xmm2,%xmm2 + vpxor %xmm2,%xmm1,%xmm1 + vprord $0x7,%xmm1,%xmm1 + vpshufd $0x93,%xmm0,%xmm0 + vpshufd $0x4e,%xmm3,%xmm3 + vpshufd $0x39,%xmm2,%xmm2 + vpaddd %xmm9,%xmm0,%xmm0 + vpaddd %xmm1,%xmm0,%xmm0 + vpxor %xmm0,%xmm3,%xmm3 + vprord $0x10,%xmm3,%xmm3 + vpaddd %xmm3,%xmm2,%xmm2 + vpxor %xmm2,%xmm1,%xmm1 + vprord $0xc,%xmm1,%xmm1 + vextracti128 $0x1,%ymm9,%xmm9 + vpaddd %xmm9,%xmm0,%xmm0 + vpaddd %xmm1,%xmm0,%xmm0 + vpxor %xmm0,%xmm3,%xmm3 + vprord $0x8,%xmm3,%xmm3 + vpaddd %xmm3,%xmm2,%xmm2 + vpxor %xmm2,%xmm1,%xmm1 + vprord $0x7,%xmm1,%xmm1 + vpshufd $0x39,%xmm0,%xmm0 + vpshufd $0x4e,%xmm3,%xmm3 + vpshufd $0x93,%xmm2,%xmm2 + decb %cl + jne .Lblake2s_compress_avx512_roundloop + vpxor %xmm10,%xmm0,%xmm0 + vpxor %xmm11,%xmm1,%xmm1 + vpxor %xmm2,%xmm0,%xmm0 + vpxor %xmm3,%xmm1,%xmm1 + decq %rdx + jne .Lblake2s_compress_avx512_mainloop + vmovdqu %xmm0,(%rdi) + vmovdqu %xmm1,0x10(%rdi) + vmovdqu %xmm4,0x20(%rdi) + vzeroupper + retq +SYM_FUNC_END(blake2s_compress_avx512) +#endif /* CONFIG_AS_AVX512 */ diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c new file mode 100644 index 000000000000..06ef2d4a4701 --- /dev/null +++ b/arch/x86/crypto/blake2s-glue.c @@ -0,0 +1,233 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + +#include <crypto/internal/blake2s.h> +#include <crypto/internal/simd.h> +#include <crypto/internal/hash.h> + +#include <linux/types.h> +#include <linux/jump_label.h> +#include <linux/kernel.h> +#include <linux/module.h> + +#include <asm/cpufeature.h> +#include <asm/fpu/api.h> +#include <asm/processor.h> +#include <asm/simd.h> + +asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state, + const u8 *block, const size_t nblocks, + const u32 inc); +asmlinkage void blake2s_compress_avx512(struct blake2s_state *state, + const u8 *block, const size_t nblocks, + const u32 inc); + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3); +static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512); + +void blake2s_compress_arch(struct blake2s_state *state, + const u8 *block, size_t nblocks, + const u32 inc) +{ + /* SIMD disables preemption, so relax after processing each page. */ + BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8); + + if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) { + blake2s_compress_generic(state, block, nblocks, inc); + return; + } + + for (;;) { + const size_t blocks = min_t(size_t, nblocks, + PAGE_SIZE / BLAKE2S_BLOCK_SIZE); + + kernel_fpu_begin(); + if (IS_ENABLED(CONFIG_AS_AVX512) && + static_branch_likely(&blake2s_use_avx512)) + blake2s_compress_avx512(state, block, blocks, inc); + else + blake2s_compress_ssse3(state, block, blocks, inc); + kernel_fpu_end(); + + nblocks -= blocks; + if (!nblocks) + break; + block += blocks * BLAKE2S_BLOCK_SIZE; + } +} +EXPORT_SYMBOL(blake2s_compress_arch); + +static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key, + unsigned int keylen) +{ + struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm); + + if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) + return -EINVAL; + + memcpy(tctx->key, key, keylen); + tctx->keylen = keylen; + + return 0; +} + +static int crypto_blake2s_init(struct shash_desc *desc) +{ + struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + struct blake2s_state *state = shash_desc_ctx(desc); + const int outlen = crypto_shash_digestsize(desc->tfm); + + if (tctx->keylen) + blake2s_init_key(state, outlen, tctx->key, tctx->keylen); + else + blake2s_init(state, outlen); + + return 0; +} + +static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in, + unsigned int inlen) +{ + struct blake2s_state *state = shash_desc_ctx(desc); + const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; + + if (unlikely(!inlen)) + return 0; + if (inlen > fill) { + memcpy(state->buf + state->buflen, in, fill); + blake2s_compress_arch(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); + state->buflen = 0; + in += fill; + inlen -= fill; + } + if (inlen > BLAKE2S_BLOCK_SIZE) { + const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); + /* Hash one less (full) block than strictly possible */ + blake2s_compress_arch(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); + in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); + inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); + } + memcpy(state->buf + state->buflen, in, inlen); + state->buflen += inlen; + + return 0; +} + +static int crypto_blake2s_final(struct shash_desc *desc, u8 *out) +{ + struct blake2s_state *state = shash_desc_ctx(desc); + + blake2s_set_lastblock(state); + memset(state->buf + state->buflen, 0, + BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ + blake2s_compress_arch(state, state->buf, 1, state->buflen); + cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); + memcpy(out, state->h, state->outlen); + memzero_explicit(state, sizeof(*state)); + + return 0; +} + +static struct shash_alg blake2s_algs[] = {{ + .base.cra_name = "blake2s-128", + .base.cra_driver_name = "blake2s-128-x86", + .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, + .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), + .base.cra_priority = 200, + .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, + .base.cra_module = THIS_MODULE, + + .digestsize = BLAKE2S_128_HASH_SIZE, + .setkey = crypto_blake2s_setkey, + .init = crypto_blake2s_init, + .update = crypto_blake2s_update, + .final = crypto_blake2s_final, + .descsize = sizeof(struct blake2s_state), +}, { + .base.cra_name = "blake2s-160", + .base.cra_driver_name = "blake2s-160-x86", + .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, + .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), + .base.cra_priority = 200, + .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, + .base.cra_module = THIS_MODULE, + + .digestsize = BLAKE2S_160_HASH_SIZE, + .setkey = crypto_blake2s_setkey, + .init = crypto_blake2s_init, + .update = crypto_blake2s_update, + .final = crypto_blake2s_final, + .descsize = sizeof(struct blake2s_state), +}, { + .base.cra_name = "blake2s-224", + .base.cra_driver_name = "blake2s-224-x86", + .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, + .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), + .base.cra_priority = 200, + .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, + .base.cra_module = THIS_MODULE, + + .digestsize = BLAKE2S_224_HASH_SIZE, + .setkey = crypto_blake2s_setkey, + .init = crypto_blake2s_init, + .update = crypto_blake2s_update, + .final = crypto_blake2s_final, + .descsize = sizeof(struct blake2s_state), +}, { + .base.cra_name = "blake2s-256", + .base.cra_driver_name = "blake2s-256-x86", + .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, + .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), + .base.cra_priority = 200, + .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, + .base.cra_module = THIS_MODULE, + + .digestsize = BLAKE2S_256_HASH_SIZE, + .setkey = crypto_blake2s_setkey, + .init = crypto_blake2s_init, + .update = crypto_blake2s_update, + .final = crypto_blake2s_final, + .descsize = sizeof(struct blake2s_state), +}}; + +static int __init blake2s_mod_init(void) +{ + if (!boot_cpu_has(X86_FEATURE_SSSE3)) + return 0; + + static_branch_enable(&blake2s_use_ssse3); + + if (IS_ENABLED(CONFIG_AS_AVX512) && + boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && + boot_cpu_has(X86_FEATURE_AVX512F) && + boot_cpu_has(X86_FEATURE_AVX512VL) && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | + XFEATURE_MASK_AVX512, NULL)) + static_branch_enable(&blake2s_use_avx512); + + return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? + crypto_register_shashes(blake2s_algs, + ARRAY_SIZE(blake2s_algs)) : 0; +} + +static void __exit blake2s_mod_exit(void) +{ + if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs)); +} + +module_init(blake2s_mod_init); +module_exit(blake2s_mod_exit); + +MODULE_ALIAS_CRYPTO("blake2s-128"); +MODULE_ALIAS_CRYPTO("blake2s-128-x86"); +MODULE_ALIAS_CRYPTO("blake2s-160"); +MODULE_ALIAS_CRYPTO("blake2s-160-x86"); +MODULE_ALIAS_CRYPTO("blake2s-224"); +MODULE_ALIAS_CRYPTO("blake2s-224-x86"); +MODULE_ALIAS_CRYPTO("blake2s-256"); +MODULE_ALIAS_CRYPTO("blake2s-256-x86"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S index 330db7a48af8..4222ac6d6584 100644 --- a/arch/x86/crypto/blowfish-x86_64-asm_64.S +++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S @@ -103,7 +103,7 @@ bswapq RX0; \ xorq RX0, (RIO); -ENTRY(__blowfish_enc_blk) +SYM_FUNC_START(__blowfish_enc_blk) /* input: * %rdi: ctx * %rsi: dst @@ -139,9 +139,9 @@ ENTRY(__blowfish_enc_blk) .L__enc_xor: xor_block(); ret; -ENDPROC(__blowfish_enc_blk) +SYM_FUNC_END(__blowfish_enc_blk) -ENTRY(blowfish_dec_blk) +SYM_FUNC_START(blowfish_dec_blk) /* input: * %rdi: ctx * %rsi: dst @@ -171,7 +171,7 @@ ENTRY(blowfish_dec_blk) movq %r11, %r12; ret; -ENDPROC(blowfish_dec_blk) +SYM_FUNC_END(blowfish_dec_blk) /********************************************************************** 4-way blowfish, four blocks parallel @@ -283,7 +283,7 @@ ENDPROC(blowfish_dec_blk) bswapq RX3; \ xorq RX3, 24(RIO); -ENTRY(__blowfish_enc_blk_4way) +SYM_FUNC_START(__blowfish_enc_blk_4way) /* input: * %rdi: ctx * %rsi: dst @@ -330,9 +330,9 @@ ENTRY(__blowfish_enc_blk_4way) popq %rbx; popq %r12; ret; -ENDPROC(__blowfish_enc_blk_4way) +SYM_FUNC_END(__blowfish_enc_blk_4way) -ENTRY(blowfish_dec_blk_4way) +SYM_FUNC_START(blowfish_dec_blk_4way) /* input: * %rdi: ctx * %rsi: dst @@ -365,4 +365,4 @@ ENTRY(blowfish_dec_blk_4way) popq %r12; ret; -ENDPROC(blowfish_dec_blk_4way) +SYM_FUNC_END(blowfish_dec_blk_4way) diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index a14af6eb09cb..d01ddd73de65 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -189,20 +189,20 @@ * larger and would only be 0.5% faster (on sandy-bridge). */ .align 8 -roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd: +SYM_FUNC_START_LOCAL(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd) roundsm16(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, %rcx, (%r9)); ret; -ENDPROC(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd) +SYM_FUNC_END(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd) .align 8 -roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab: +SYM_FUNC_START_LOCAL(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) roundsm16(%xmm4, %xmm5, %xmm6, %xmm7, %xmm0, %xmm1, %xmm2, %xmm3, %xmm12, %xmm13, %xmm14, %xmm15, %xmm8, %xmm9, %xmm10, %xmm11, %rax, (%r9)); ret; -ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) +SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) /* * IN/OUT: @@ -722,7 +722,7 @@ ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) .text .align 8 -__camellia_enc_blk16: +SYM_FUNC_START_LOCAL(__camellia_enc_blk16) /* input: * %rdi: ctx, CTX * %rax: temporary storage, 256 bytes @@ -806,10 +806,10 @@ __camellia_enc_blk16: %xmm15, %rax, %rcx, 24); jmp .Lenc_done; -ENDPROC(__camellia_enc_blk16) +SYM_FUNC_END(__camellia_enc_blk16) .align 8 -__camellia_dec_blk16: +SYM_FUNC_START_LOCAL(__camellia_dec_blk16) /* input: * %rdi: ctx, CTX * %rax: temporary storage, 256 bytes @@ -891,9 +891,9 @@ __camellia_dec_blk16: ((key_table + (24) * 8) + 4)(CTX)); jmp .Ldec_max24; -ENDPROC(__camellia_dec_blk16) +SYM_FUNC_END(__camellia_dec_blk16) -ENTRY(camellia_ecb_enc_16way) +SYM_FUNC_START(camellia_ecb_enc_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -916,9 +916,9 @@ ENTRY(camellia_ecb_enc_16way) FRAME_END ret; -ENDPROC(camellia_ecb_enc_16way) +SYM_FUNC_END(camellia_ecb_enc_16way) -ENTRY(camellia_ecb_dec_16way) +SYM_FUNC_START(camellia_ecb_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -946,9 +946,9 @@ ENTRY(camellia_ecb_dec_16way) FRAME_END ret; -ENDPROC(camellia_ecb_dec_16way) +SYM_FUNC_END(camellia_ecb_dec_16way) -ENTRY(camellia_cbc_dec_16way) +SYM_FUNC_START(camellia_cbc_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -997,7 +997,7 @@ ENTRY(camellia_cbc_dec_16way) FRAME_END ret; -ENDPROC(camellia_cbc_dec_16way) +SYM_FUNC_END(camellia_cbc_dec_16way) #define inc_le128(x, minus_one, tmp) \ vpcmpeqq minus_one, x, tmp; \ @@ -1005,7 +1005,7 @@ ENDPROC(camellia_cbc_dec_16way) vpslldq $8, tmp, tmp; \ vpsubq tmp, x, x; -ENTRY(camellia_ctr_16way) +SYM_FUNC_START(camellia_ctr_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -1110,7 +1110,7 @@ ENTRY(camellia_ctr_16way) FRAME_END ret; -ENDPROC(camellia_ctr_16way) +SYM_FUNC_END(camellia_ctr_16way) #define gf128mul_x_ble(iv, mask, tmp) \ vpsrad $31, iv, tmp; \ @@ -1120,7 +1120,7 @@ ENDPROC(camellia_ctr_16way) vpxor tmp, iv, iv; .align 8 -camellia_xts_crypt_16way: +SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -1254,9 +1254,9 @@ camellia_xts_crypt_16way: FRAME_END ret; -ENDPROC(camellia_xts_crypt_16way) +SYM_FUNC_END(camellia_xts_crypt_16way) -ENTRY(camellia_xts_enc_16way) +SYM_FUNC_START(camellia_xts_enc_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -1268,9 +1268,9 @@ ENTRY(camellia_xts_enc_16way) leaq __camellia_enc_blk16, %r9; jmp camellia_xts_crypt_16way; -ENDPROC(camellia_xts_enc_16way) +SYM_FUNC_END(camellia_xts_enc_16way) -ENTRY(camellia_xts_dec_16way) +SYM_FUNC_START(camellia_xts_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -1286,4 +1286,4 @@ ENTRY(camellia_xts_dec_16way) leaq __camellia_dec_blk16, %r9; jmp camellia_xts_crypt_16way; -ENDPROC(camellia_xts_dec_16way) +SYM_FUNC_END(camellia_xts_dec_16way) diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index 4be4c7c3ba27..563ef6e83cdd 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -223,20 +223,20 @@ * larger and would only marginally faster. */ .align 8 -roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd: +SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd) roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rcx, (%r9)); ret; -ENDPROC(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd) +SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd) .align 8 -roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab: +SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3, %ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11, %rax, (%r9)); ret; -ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) +SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) /* * IN/OUT: @@ -760,7 +760,7 @@ ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) .text .align 8 -__camellia_enc_blk32: +SYM_FUNC_START_LOCAL(__camellia_enc_blk32) /* input: * %rdi: ctx, CTX * %rax: temporary storage, 512 bytes @@ -844,10 +844,10 @@ __camellia_enc_blk32: %ymm15, %rax, %rcx, 24); jmp .Lenc_done; -ENDPROC(__camellia_enc_blk32) +SYM_FUNC_END(__camellia_enc_blk32) .align 8 -__camellia_dec_blk32: +SYM_FUNC_START_LOCAL(__camellia_dec_blk32) /* input: * %rdi: ctx, CTX * %rax: temporary storage, 512 bytes @@ -929,9 +929,9 @@ __camellia_dec_blk32: ((key_table + (24) * 8) + 4)(CTX)); jmp .Ldec_max24; -ENDPROC(__camellia_dec_blk32) +SYM_FUNC_END(__camellia_dec_blk32) -ENTRY(camellia_ecb_enc_32way) +SYM_FUNC_START(camellia_ecb_enc_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -958,9 +958,9 @@ ENTRY(camellia_ecb_enc_32way) FRAME_END ret; -ENDPROC(camellia_ecb_enc_32way) +SYM_FUNC_END(camellia_ecb_enc_32way) -ENTRY(camellia_ecb_dec_32way) +SYM_FUNC_START(camellia_ecb_dec_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -992,9 +992,9 @@ ENTRY(camellia_ecb_dec_32way) FRAME_END ret; -ENDPROC(camellia_ecb_dec_32way) +SYM_FUNC_END(camellia_ecb_dec_32way) -ENTRY(camellia_cbc_dec_32way) +SYM_FUNC_START(camellia_cbc_dec_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -1060,7 +1060,7 @@ ENTRY(camellia_cbc_dec_32way) FRAME_END ret; -ENDPROC(camellia_cbc_dec_32way) +SYM_FUNC_END(camellia_cbc_dec_32way) #define inc_le128(x, minus_one, tmp) \ vpcmpeqq minus_one, x, tmp; \ @@ -1076,7 +1076,7 @@ ENDPROC(camellia_cbc_dec_32way) vpslldq $8, tmp1, tmp1; \ vpsubq tmp1, x, x; -ENTRY(camellia_ctr_32way) +SYM_FUNC_START(camellia_ctr_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -1200,7 +1200,7 @@ ENTRY(camellia_ctr_32way) FRAME_END ret; -ENDPROC(camellia_ctr_32way) +SYM_FUNC_END(camellia_ctr_32way) #define gf128mul_x_ble(iv, mask, tmp) \ vpsrad $31, iv, tmp; \ @@ -1222,7 +1222,7 @@ ENDPROC(camellia_ctr_32way) vpxor tmp1, iv, iv; .align 8 -camellia_xts_crypt_32way: +SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -1367,9 +1367,9 @@ camellia_xts_crypt_32way: FRAME_END ret; -ENDPROC(camellia_xts_crypt_32way) +SYM_FUNC_END(camellia_xts_crypt_32way) -ENTRY(camellia_xts_enc_32way) +SYM_FUNC_START(camellia_xts_enc_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -1382,9 +1382,9 @@ ENTRY(camellia_xts_enc_32way) leaq __camellia_enc_blk32, %r9; jmp camellia_xts_crypt_32way; -ENDPROC(camellia_xts_enc_32way) +SYM_FUNC_END(camellia_xts_enc_32way) -ENTRY(camellia_xts_dec_32way) +SYM_FUNC_START(camellia_xts_dec_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -1400,4 +1400,4 @@ ENTRY(camellia_xts_dec_32way) leaq __camellia_dec_blk32, %r9; jmp camellia_xts_crypt_32way; -ENDPROC(camellia_xts_dec_32way) +SYM_FUNC_END(camellia_xts_dec_32way) diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S index 23528bc18fc6..1372e6408850 100644 --- a/arch/x86/crypto/camellia-x86_64-asm_64.S +++ b/arch/x86/crypto/camellia-x86_64-asm_64.S @@ -175,7 +175,7 @@ bswapq RAB0; \ movq RAB0, 4*2(RIO); -ENTRY(__camellia_enc_blk) +SYM_FUNC_START(__camellia_enc_blk) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -220,9 +220,9 @@ ENTRY(__camellia_enc_blk) movq RR12, %r12; ret; -ENDPROC(__camellia_enc_blk) +SYM_FUNC_END(__camellia_enc_blk) -ENTRY(camellia_dec_blk) +SYM_FUNC_START(camellia_dec_blk) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -258,7 +258,7 @@ ENTRY(camellia_dec_blk) movq RR12, %r12; ret; -ENDPROC(camellia_dec_blk) +SYM_FUNC_END(camellia_dec_blk) /********************************************************************** 2-way camellia @@ -409,7 +409,7 @@ ENDPROC(camellia_dec_blk) bswapq RAB1; \ movq RAB1, 12*2(RIO); -ENTRY(__camellia_enc_blk_2way) +SYM_FUNC_START(__camellia_enc_blk_2way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -456,9 +456,9 @@ ENTRY(__camellia_enc_blk_2way) movq RR12, %r12; popq %rbx; ret; -ENDPROC(__camellia_enc_blk_2way) +SYM_FUNC_END(__camellia_enc_blk_2way) -ENTRY(camellia_dec_blk_2way) +SYM_FUNC_START(camellia_dec_blk_2way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -496,4 +496,4 @@ ENTRY(camellia_dec_blk_2way) movq RR12, %r12; movq RXOR, %rbx; ret; -ENDPROC(camellia_dec_blk_2way) +SYM_FUNC_END(camellia_dec_blk_2way) diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index abf298c272dc..ccda647422d6 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -19,20 +19,17 @@ #define CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS 32 /* 32-way AVX2/AES-NI parallel cipher functions */ -asmlinkage void camellia_ecb_enc_32way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void camellia_ecb_dec_32way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void camellia_ecb_enc_32way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void camellia_ecb_dec_32way(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void camellia_cbc_dec_32way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void camellia_ctr_32way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void camellia_cbc_dec_32way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void camellia_ctr_32way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); -asmlinkage void camellia_xts_enc_32way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); -asmlinkage void camellia_xts_dec_32way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void camellia_xts_enc_32way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); +asmlinkage void camellia_xts_dec_32way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); static const struct common_glue_ctx camellia_enc = { .num_funcs = 4, @@ -40,16 +37,16 @@ static const struct common_glue_ctx camellia_enc = { .funcs = { { .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_enc_32way) } + .fn_u = { .ecb = camellia_ecb_enc_32way } }, { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_enc_16way) } + .fn_u = { .ecb = camellia_ecb_enc_16way } }, { .num_blocks = 2, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk_2way) } + .fn_u = { .ecb = camellia_enc_blk_2way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk) } + .fn_u = { .ecb = camellia_enc_blk } } } }; @@ -59,16 +56,16 @@ static const struct common_glue_ctx camellia_ctr = { .funcs = { { .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_ctr_32way) } + .fn_u = { .ctr = camellia_ctr_32way } }, { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_ctr_16way) } + .fn_u = { .ctr = camellia_ctr_16way } }, { .num_blocks = 2, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr_2way) } + .fn_u = { .ctr = camellia_crypt_ctr_2way } }, { .num_blocks = 1, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr) } + .fn_u = { .ctr = camellia_crypt_ctr } } } }; @@ -78,13 +75,13 @@ static const struct common_glue_ctx camellia_enc_xts = { .funcs = { { .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc_32way) } + .fn_u = { .xts = camellia_xts_enc_32way } }, { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc_16way) } + .fn_u = { .xts = camellia_xts_enc_16way } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc) } + .fn_u = { .xts = camellia_xts_enc } } } }; @@ -94,16 +91,16 @@ static const struct common_glue_ctx camellia_dec = { .funcs = { { .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_dec_32way) } + .fn_u = { .ecb = camellia_ecb_dec_32way } }, { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_dec_16way) } + .fn_u = { .ecb = camellia_ecb_dec_16way } }, { .num_blocks = 2, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk_2way) } + .fn_u = { .ecb = camellia_dec_blk_2way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk) } + .fn_u = { .ecb = camellia_dec_blk } } } }; @@ -113,16 +110,16 @@ static const struct common_glue_ctx camellia_dec_cbc = { .funcs = { { .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_cbc_dec_32way) } + .fn_u = { .cbc = camellia_cbc_dec_32way } }, { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_cbc_dec_16way) } + .fn_u = { .cbc = camellia_cbc_dec_16way } }, { .num_blocks = 2, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_decrypt_cbc_2way) } + .fn_u = { .cbc = camellia_decrypt_cbc_2way } }, { .num_blocks = 1, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_dec_blk) } + .fn_u = { .cbc = camellia_dec_blk } } } }; @@ -132,21 +129,20 @@ static const struct common_glue_ctx camellia_dec_xts = { .funcs = { { .num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec_32way) } + .fn_u = { .xts = camellia_xts_dec_32way } }, { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec_16way) } + .fn_u = { .xts = camellia_xts_dec_16way } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec) } + .fn_u = { .xts = camellia_xts_dec } } } }; static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { - return __camellia_setkey(crypto_skcipher_ctx(tfm), key, keylen, - &tfm->base.crt_flags); + return __camellia_setkey(crypto_skcipher_ctx(tfm), key, keylen); } static int ecb_encrypt(struct skcipher_request *req) @@ -161,8 +157,7 @@ static int ecb_decrypt(struct skcipher_request *req) static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(camellia_enc_blk), - req); + return glue_cbc_encrypt_req_128bit(camellia_enc_blk, req); } static int cbc_decrypt(struct skcipher_request *req) @@ -180,9 +175,8 @@ static int xts_encrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&camellia_enc_xts, req, - XTS_TWEAK_CAST(camellia_enc_blk), - &ctx->tweak_ctx, &ctx->crypt_ctx); + return glue_xts_req_128bit(&camellia_enc_xts, req, camellia_enc_blk, + &ctx->tweak_ctx, &ctx->crypt_ctx, false); } static int xts_decrypt(struct skcipher_request *req) @@ -190,9 +184,8 @@ static int xts_decrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&camellia_dec_xts, req, - XTS_TWEAK_CAST(camellia_enc_blk), - &ctx->tweak_ctx, &ctx->crypt_ctx); + return glue_xts_req_128bit(&camellia_dec_xts, req, camellia_enc_blk, + &ctx->tweak_ctx, &ctx->crypt_ctx, true); } static struct skcipher_alg camellia_algs[] = { diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 0c22d84750a3..4e5de6ef206e 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -18,41 +18,36 @@ #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16 /* 16-way parallel cipher functions (avx/aes-ni) */ -asmlinkage void camellia_ecb_enc_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void camellia_ecb_enc_16way(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(camellia_ecb_enc_16way); -asmlinkage void camellia_ecb_dec_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void camellia_ecb_dec_16way(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(camellia_ecb_dec_16way); -asmlinkage void camellia_cbc_dec_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void camellia_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(camellia_cbc_dec_16way); -asmlinkage void camellia_ctr_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void camellia_ctr_16way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); EXPORT_SYMBOL_GPL(camellia_ctr_16way); -asmlinkage void camellia_xts_enc_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void camellia_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); EXPORT_SYMBOL_GPL(camellia_xts_enc_16way); -asmlinkage void camellia_xts_dec_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void camellia_xts_dec_16way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); EXPORT_SYMBOL_GPL(camellia_xts_dec_16way); -void camellia_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv) +void camellia_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, - GLUE_FUNC_CAST(camellia_enc_blk)); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, camellia_enc_blk); } EXPORT_SYMBOL_GPL(camellia_xts_enc); -void camellia_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv) +void camellia_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, - GLUE_FUNC_CAST(camellia_dec_blk)); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, camellia_dec_blk); } EXPORT_SYMBOL_GPL(camellia_xts_dec); @@ -62,13 +57,13 @@ static const struct common_glue_ctx camellia_enc = { .funcs = { { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_enc_16way) } + .fn_u = { .ecb = camellia_ecb_enc_16way } }, { .num_blocks = 2, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk_2way) } + .fn_u = { .ecb = camellia_enc_blk_2way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk) } + .fn_u = { .ecb = camellia_enc_blk } } } }; @@ -78,13 +73,13 @@ static const struct common_glue_ctx camellia_ctr = { .funcs = { { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_ctr_16way) } + .fn_u = { .ctr = camellia_ctr_16way } }, { .num_blocks = 2, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr_2way) } + .fn_u = { .ctr = camellia_crypt_ctr_2way } }, { .num_blocks = 1, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr) } + .fn_u = { .ctr = camellia_crypt_ctr } } } }; @@ -94,10 +89,10 @@ static const struct common_glue_ctx camellia_enc_xts = { .funcs = { { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc_16way) } + .fn_u = { .xts = camellia_xts_enc_16way } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc) } + .fn_u = { .xts = camellia_xts_enc } } } }; @@ -107,13 +102,13 @@ static const struct common_glue_ctx camellia_dec = { .funcs = { { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_dec_16way) } + .fn_u = { .ecb = camellia_ecb_dec_16way } }, { .num_blocks = 2, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk_2way) } + .fn_u = { .ecb = camellia_dec_blk_2way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk) } + .fn_u = { .ecb = camellia_dec_blk } } } }; @@ -123,13 +118,13 @@ static const struct common_glue_ctx camellia_dec_cbc = { .funcs = { { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_cbc_dec_16way) } + .fn_u = { .cbc = camellia_cbc_dec_16way } }, { .num_blocks = 2, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_decrypt_cbc_2way) } + .fn_u = { .cbc = camellia_decrypt_cbc_2way } }, { .num_blocks = 1, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_dec_blk) } + .fn_u = { .cbc = camellia_dec_blk } } } }; @@ -139,18 +134,17 @@ static const struct common_glue_ctx camellia_dec_xts = { .funcs = { { .num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec_16way) } + .fn_u = { .xts = camellia_xts_dec_16way } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec) } + .fn_u = { .xts = camellia_xts_dec } } } }; static int camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { - return __camellia_setkey(crypto_skcipher_ctx(tfm), key, keylen, - &tfm->base.crt_flags); + return __camellia_setkey(crypto_skcipher_ctx(tfm), key, keylen); } static int ecb_encrypt(struct skcipher_request *req) @@ -165,8 +159,7 @@ static int ecb_decrypt(struct skcipher_request *req) static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(camellia_enc_blk), - req); + return glue_cbc_encrypt_req_128bit(camellia_enc_blk, req); } static int cbc_decrypt(struct skcipher_request *req) @@ -183,7 +176,6 @@ int xts_camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - u32 *flags = &tfm->base.crt_flags; int err; err = xts_verify_key(tfm, key, keylen); @@ -191,13 +183,12 @@ int xts_camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, return err; /* first half of xts-key is for crypt */ - err = __camellia_setkey(&ctx->crypt_ctx, key, keylen / 2, flags); + err = __camellia_setkey(&ctx->crypt_ctx, key, keylen / 2); if (err) return err; /* second half of xts-key is for tweak */ - return __camellia_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2, - flags); + return __camellia_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2); } EXPORT_SYMBOL_GPL(xts_camellia_setkey); @@ -206,9 +197,8 @@ static int xts_encrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&camellia_enc_xts, req, - XTS_TWEAK_CAST(camellia_enc_blk), - &ctx->tweak_ctx, &ctx->crypt_ctx); + return glue_xts_req_128bit(&camellia_enc_xts, req, camellia_enc_blk, + &ctx->tweak_ctx, &ctx->crypt_ctx, false); } static int xts_decrypt(struct skcipher_request *req) @@ -216,9 +206,8 @@ static int xts_decrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct camellia_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&camellia_dec_xts, req, - XTS_TWEAK_CAST(camellia_enc_blk), - &ctx->tweak_ctx, &ctx->crypt_ctx); + return glue_xts_req_128bit(&camellia_dec_xts, req, camellia_enc_blk, + &ctx->tweak_ctx, &ctx->crypt_ctx, true); } static struct skcipher_alg camellia_algs[] = { diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c index 7c62db56ffe1..242c056e5fa8 100644 --- a/arch/x86/crypto/camellia_glue.c +++ b/arch/x86/crypto/camellia_glue.c @@ -18,19 +18,17 @@ #include <asm/crypto/glue_helper.h> /* regular block cipher functions */ -asmlinkage void __camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, bool xor); +asmlinkage void __camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src, + bool xor); EXPORT_SYMBOL_GPL(__camellia_enc_blk); -asmlinkage void camellia_dec_blk(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void camellia_dec_blk(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(camellia_dec_blk); /* 2-way parallel cipher functions */ -asmlinkage void __camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, bool xor); +asmlinkage void __camellia_enc_blk_2way(const void *ctx, u8 *dst, const u8 *src, + bool xor); EXPORT_SYMBOL_GPL(__camellia_enc_blk_2way); -asmlinkage void camellia_dec_blk_2way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void camellia_dec_blk_2way(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(camellia_dec_blk_2way); static void camellia_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) @@ -1229,12 +1227,10 @@ static void camellia_setup192(const unsigned char *key, u64 *subkey) } int __camellia_setkey(struct camellia_ctx *cctx, const unsigned char *key, - unsigned int key_len, u32 *flags) + unsigned int key_len) { - if (key_len != 16 && key_len != 24 && key_len != 32) { - *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + if (key_len != 16 && key_len != 24 && key_len != 32) return -EINVAL; - } cctx->key_length = key_len; @@ -1257,8 +1253,7 @@ EXPORT_SYMBOL_GPL(__camellia_setkey); static int camellia_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int key_len) { - return __camellia_setkey(crypto_tfm_ctx(tfm), key, key_len, - &tfm->crt_flags); + return __camellia_setkey(crypto_tfm_ctx(tfm), key, key_len); } static int camellia_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, @@ -1267,8 +1262,10 @@ static int camellia_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, return camellia_setkey(&tfm->base, key, key_len); } -void camellia_decrypt_cbc_2way(void *ctx, u128 *dst, const u128 *src) +void camellia_decrypt_cbc_2way(const void *ctx, u8 *d, const u8 *s) { + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; u128 iv = *src; camellia_dec_blk_2way(ctx, (u8 *)dst, (u8 *)src); @@ -1277,9 +1274,11 @@ void camellia_decrypt_cbc_2way(void *ctx, u128 *dst, const u128 *src) } EXPORT_SYMBOL_GPL(camellia_decrypt_cbc_2way); -void camellia_crypt_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv) +void camellia_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) { be128 ctrblk; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; if (dst != src) *dst = *src; @@ -1291,9 +1290,11 @@ void camellia_crypt_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv) } EXPORT_SYMBOL_GPL(camellia_crypt_ctr); -void camellia_crypt_ctr_2way(void *ctx, u128 *dst, const u128 *src, le128 *iv) +void camellia_crypt_ctr_2way(const void *ctx, u8 *d, const u8 *s, le128 *iv) { be128 ctrblks[2]; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; if (dst != src) { dst[0] = src[0]; @@ -1315,10 +1316,10 @@ static const struct common_glue_ctx camellia_enc = { .funcs = { { .num_blocks = 2, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk_2way) } + .fn_u = { .ecb = camellia_enc_blk_2way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk) } + .fn_u = { .ecb = camellia_enc_blk } } } }; @@ -1328,10 +1329,10 @@ static const struct common_glue_ctx camellia_ctr = { .funcs = { { .num_blocks = 2, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr_2way) } + .fn_u = { .ctr = camellia_crypt_ctr_2way } }, { .num_blocks = 1, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr) } + .fn_u = { .ctr = camellia_crypt_ctr } } } }; @@ -1341,10 +1342,10 @@ static const struct common_glue_ctx camellia_dec = { .funcs = { { .num_blocks = 2, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk_2way) } + .fn_u = { .ecb = camellia_dec_blk_2way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk) } + .fn_u = { .ecb = camellia_dec_blk } } } }; @@ -1354,10 +1355,10 @@ static const struct common_glue_ctx camellia_dec_cbc = { .funcs = { { .num_blocks = 2, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_decrypt_cbc_2way) } + .fn_u = { .cbc = camellia_decrypt_cbc_2way } }, { .num_blocks = 1, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_dec_blk) } + .fn_u = { .cbc = camellia_dec_blk } } } }; @@ -1373,8 +1374,7 @@ static int ecb_decrypt(struct skcipher_request *req) static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(camellia_enc_blk), - req); + return glue_cbc_encrypt_req_128bit(camellia_enc_blk, req); } static int cbc_decrypt(struct skcipher_request *req) diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S index dc55c3332fcc..8a6181b08b59 100644 --- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S @@ -209,7 +209,7 @@ .text .align 16 -__cast5_enc_blk16: +SYM_FUNC_START_LOCAL(__cast5_enc_blk16) /* input: * %rdi: ctx * RL1: blocks 1 and 2 @@ -280,10 +280,10 @@ __cast5_enc_blk16: outunpack_blocks(RR4, RL4, RTMP, RX, RKM); ret; -ENDPROC(__cast5_enc_blk16) +SYM_FUNC_END(__cast5_enc_blk16) .align 16 -__cast5_dec_blk16: +SYM_FUNC_START_LOCAL(__cast5_dec_blk16) /* input: * %rdi: ctx * RL1: encrypted blocks 1 and 2 @@ -357,9 +357,9 @@ __cast5_dec_blk16: .L__skip_dec: vpsrldq $4, RKR, RKR; jmp .L__dec_tail; -ENDPROC(__cast5_dec_blk16) +SYM_FUNC_END(__cast5_dec_blk16) -ENTRY(cast5_ecb_enc_16way) +SYM_FUNC_START(cast5_ecb_enc_16way) /* input: * %rdi: ctx * %rsi: dst @@ -394,9 +394,9 @@ ENTRY(cast5_ecb_enc_16way) popq %r15; FRAME_END ret; -ENDPROC(cast5_ecb_enc_16way) +SYM_FUNC_END(cast5_ecb_enc_16way) -ENTRY(cast5_ecb_dec_16way) +SYM_FUNC_START(cast5_ecb_dec_16way) /* input: * %rdi: ctx * %rsi: dst @@ -432,9 +432,9 @@ ENTRY(cast5_ecb_dec_16way) popq %r15; FRAME_END ret; -ENDPROC(cast5_ecb_dec_16way) +SYM_FUNC_END(cast5_ecb_dec_16way) -ENTRY(cast5_cbc_dec_16way) +SYM_FUNC_START(cast5_cbc_dec_16way) /* input: * %rdi: ctx * %rsi: dst @@ -484,9 +484,9 @@ ENTRY(cast5_cbc_dec_16way) popq %r12; FRAME_END ret; -ENDPROC(cast5_cbc_dec_16way) +SYM_FUNC_END(cast5_cbc_dec_16way) -ENTRY(cast5_ctr_16way) +SYM_FUNC_START(cast5_ctr_16way) /* input: * %rdi: ctx * %rsi: dst @@ -560,4 +560,4 @@ ENTRY(cast5_ctr_16way) popq %r12; FRAME_END ret; -ENDPROC(cast5_ctr_16way) +SYM_FUNC_END(cast5_ctr_16way) diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S index 4f0a7cdb94d9..932a3ce32a88 100644 --- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S @@ -247,7 +247,7 @@ .text .align 8 -__cast6_enc_blk8: +SYM_FUNC_START_LOCAL(__cast6_enc_blk8) /* input: * %rdi: ctx * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks @@ -292,10 +292,10 @@ __cast6_enc_blk8: outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM); ret; -ENDPROC(__cast6_enc_blk8) +SYM_FUNC_END(__cast6_enc_blk8) .align 8 -__cast6_dec_blk8: +SYM_FUNC_START_LOCAL(__cast6_dec_blk8) /* input: * %rdi: ctx * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks @@ -339,9 +339,9 @@ __cast6_dec_blk8: outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM); ret; -ENDPROC(__cast6_dec_blk8) +SYM_FUNC_END(__cast6_dec_blk8) -ENTRY(cast6_ecb_enc_8way) +SYM_FUNC_START(cast6_ecb_enc_8way) /* input: * %rdi: ctx * %rsi: dst @@ -362,9 +362,9 @@ ENTRY(cast6_ecb_enc_8way) popq %r15; FRAME_END ret; -ENDPROC(cast6_ecb_enc_8way) +SYM_FUNC_END(cast6_ecb_enc_8way) -ENTRY(cast6_ecb_dec_8way) +SYM_FUNC_START(cast6_ecb_dec_8way) /* input: * %rdi: ctx * %rsi: dst @@ -385,9 +385,9 @@ ENTRY(cast6_ecb_dec_8way) popq %r15; FRAME_END ret; -ENDPROC(cast6_ecb_dec_8way) +SYM_FUNC_END(cast6_ecb_dec_8way) -ENTRY(cast6_cbc_dec_8way) +SYM_FUNC_START(cast6_cbc_dec_8way) /* input: * %rdi: ctx * %rsi: dst @@ -411,9 +411,9 @@ ENTRY(cast6_cbc_dec_8way) popq %r12; FRAME_END ret; -ENDPROC(cast6_cbc_dec_8way) +SYM_FUNC_END(cast6_cbc_dec_8way) -ENTRY(cast6_ctr_8way) +SYM_FUNC_START(cast6_ctr_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -439,9 +439,9 @@ ENTRY(cast6_ctr_8way) popq %r12; FRAME_END ret; -ENDPROC(cast6_ctr_8way) +SYM_FUNC_END(cast6_ctr_8way) -ENTRY(cast6_xts_enc_8way) +SYM_FUNC_START(cast6_xts_enc_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -466,9 +466,9 @@ ENTRY(cast6_xts_enc_8way) popq %r15; FRAME_END ret; -ENDPROC(cast6_xts_enc_8way) +SYM_FUNC_END(cast6_xts_enc_8way) -ENTRY(cast6_xts_dec_8way) +SYM_FUNC_START(cast6_xts_dec_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -493,4 +493,4 @@ ENTRY(cast6_xts_dec_8way) popq %r15; FRAME_END ret; -ENDPROC(cast6_xts_dec_8way) +SYM_FUNC_END(cast6_xts_dec_8way) diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c index 645f8f16815c..48e0f37796fa 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -20,20 +20,17 @@ #define CAST6_PARALLEL_BLOCKS 8 -asmlinkage void cast6_ecb_enc_8way(struct cast6_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void cast6_ecb_dec_8way(struct cast6_ctx *ctx, u8 *dst, - const u8 *src); - -asmlinkage void cast6_cbc_dec_8way(struct cast6_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void cast6_ctr_8way(struct cast6_ctx *ctx, u8 *dst, const u8 *src, +asmlinkage void cast6_ecb_enc_8way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void cast6_ecb_dec_8way(const void *ctx, u8 *dst, const u8 *src); + +asmlinkage void cast6_cbc_dec_8way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void cast6_ctr_8way(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -asmlinkage void cast6_xts_enc_8way(struct cast6_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); -asmlinkage void cast6_xts_dec_8way(struct cast6_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void cast6_xts_enc_8way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); +asmlinkage void cast6_xts_dec_8way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); static int cast6_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) @@ -41,21 +38,21 @@ static int cast6_setkey_skcipher(struct crypto_skcipher *tfm, return cast6_setkey(&tfm->base, key, keylen); } -static void cast6_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv) +static void cast6_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, - GLUE_FUNC_CAST(__cast6_encrypt)); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, __cast6_encrypt); } -static void cast6_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv) +static void cast6_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, - GLUE_FUNC_CAST(__cast6_decrypt)); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, __cast6_decrypt); } -static void cast6_crypt_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv) +static void cast6_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) { be128 ctrblk; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; le128_to_be128(&ctrblk, iv); le128_inc(iv); @@ -70,10 +67,10 @@ static const struct common_glue_ctx cast6_enc = { .funcs = { { .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(cast6_ecb_enc_8way) } + .fn_u = { .ecb = cast6_ecb_enc_8way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(__cast6_encrypt) } + .fn_u = { .ecb = __cast6_encrypt } } } }; @@ -83,10 +80,10 @@ static const struct common_glue_ctx cast6_ctr = { .funcs = { { .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(cast6_ctr_8way) } + .fn_u = { .ctr = cast6_ctr_8way } }, { .num_blocks = 1, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(cast6_crypt_ctr) } + .fn_u = { .ctr = cast6_crypt_ctr } } } }; @@ -96,10 +93,10 @@ static const struct common_glue_ctx cast6_enc_xts = { .funcs = { { .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(cast6_xts_enc_8way) } + .fn_u = { .xts = cast6_xts_enc_8way } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(cast6_xts_enc) } + .fn_u = { .xts = cast6_xts_enc } } } }; @@ -109,10 +106,10 @@ static const struct common_glue_ctx cast6_dec = { .funcs = { { .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(cast6_ecb_dec_8way) } + .fn_u = { .ecb = cast6_ecb_dec_8way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(__cast6_decrypt) } + .fn_u = { .ecb = __cast6_decrypt } } } }; @@ -122,10 +119,10 @@ static const struct common_glue_ctx cast6_dec_cbc = { .funcs = { { .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(cast6_cbc_dec_8way) } + .fn_u = { .cbc = cast6_cbc_dec_8way } }, { .num_blocks = 1, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(__cast6_decrypt) } + .fn_u = { .cbc = __cast6_decrypt } } } }; @@ -135,10 +132,10 @@ static const struct common_glue_ctx cast6_dec_xts = { .funcs = { { .num_blocks = CAST6_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(cast6_xts_dec_8way) } + .fn_u = { .xts = cast6_xts_dec_8way } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(cast6_xts_dec) } + .fn_u = { .xts = cast6_xts_dec } } } }; @@ -154,8 +151,7 @@ static int ecb_decrypt(struct skcipher_request *req) static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(__cast6_encrypt), - req); + return glue_cbc_encrypt_req_128bit(__cast6_encrypt, req); } static int cbc_decrypt(struct skcipher_request *req) @@ -177,7 +173,6 @@ static int xts_cast6_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - u32 *flags = &tfm->base.crt_flags; int err; err = xts_verify_key(tfm, key, keylen); @@ -185,13 +180,12 @@ static int xts_cast6_setkey(struct crypto_skcipher *tfm, const u8 *key, return err; /* first half of xts-key is for crypt */ - err = __cast6_setkey(&ctx->crypt_ctx, key, keylen / 2, flags); + err = __cast6_setkey(&ctx->crypt_ctx, key, keylen / 2); if (err) return err; /* second half of xts-key is for tweak */ - return __cast6_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2, - flags); + return __cast6_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2); } static int xts_encrypt(struct skcipher_request *req) @@ -199,9 +193,8 @@ static int xts_encrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&cast6_enc_xts, req, - XTS_TWEAK_CAST(__cast6_encrypt), - &ctx->tweak_ctx, &ctx->crypt_ctx); + return glue_xts_req_128bit(&cast6_enc_xts, req, __cast6_encrypt, + &ctx->tweak_ctx, &ctx->crypt_ctx, false); } static int xts_decrypt(struct skcipher_request *req) @@ -209,9 +202,8 @@ static int xts_decrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct cast6_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&cast6_dec_xts, req, - XTS_TWEAK_CAST(__cast6_encrypt), - &ctx->tweak_ctx, &ctx->crypt_ctx); + return glue_xts_req_128bit(&cast6_dec_xts, req, __cast6_encrypt, + &ctx->tweak_ctx, &ctx->crypt_ctx, true); } static struct skcipher_alg cast6_algs[] = { diff --git a/arch/x86/crypto/chacha-avx2-x86_64.S b/arch/x86/crypto/chacha-avx2-x86_64.S index 831e4434fc20..ee9a40ab4109 100644 --- a/arch/x86/crypto/chacha-avx2-x86_64.S +++ b/arch/x86/crypto/chacha-avx2-x86_64.S @@ -34,7 +34,7 @@ CTR4BL: .octa 0x00000000000000000000000000000002 .text -ENTRY(chacha_2block_xor_avx2) +SYM_FUNC_START(chacha_2block_xor_avx2) # %rdi: Input state matrix, s # %rsi: up to 2 data blocks output, o # %rdx: up to 2 data blocks input, i @@ -224,9 +224,9 @@ ENTRY(chacha_2block_xor_avx2) lea -8(%r10),%rsp jmp .Ldone2 -ENDPROC(chacha_2block_xor_avx2) +SYM_FUNC_END(chacha_2block_xor_avx2) -ENTRY(chacha_4block_xor_avx2) +SYM_FUNC_START(chacha_4block_xor_avx2) # %rdi: Input state matrix, s # %rsi: up to 4 data blocks output, o # %rdx: up to 4 data blocks input, i @@ -529,9 +529,9 @@ ENTRY(chacha_4block_xor_avx2) lea -8(%r10),%rsp jmp .Ldone4 -ENDPROC(chacha_4block_xor_avx2) +SYM_FUNC_END(chacha_4block_xor_avx2) -ENTRY(chacha_8block_xor_avx2) +SYM_FUNC_START(chacha_8block_xor_avx2) # %rdi: Input state matrix, s # %rsi: up to 8 data blocks output, o # %rdx: up to 8 data blocks input, i @@ -1018,4 +1018,4 @@ ENTRY(chacha_8block_xor_avx2) jmp .Ldone8 -ENDPROC(chacha_8block_xor_avx2) +SYM_FUNC_END(chacha_8block_xor_avx2) diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S index 848f9c75fd4f..bb193fde123a 100644 --- a/arch/x86/crypto/chacha-avx512vl-x86_64.S +++ b/arch/x86/crypto/chacha-avx512vl-x86_64.S @@ -24,7 +24,7 @@ CTR8BL: .octa 0x00000003000000020000000100000000 .text -ENTRY(chacha_2block_xor_avx512vl) +SYM_FUNC_START(chacha_2block_xor_avx512vl) # %rdi: Input state matrix, s # %rsi: up to 2 data blocks output, o # %rdx: up to 2 data blocks input, i @@ -187,9 +187,9 @@ ENTRY(chacha_2block_xor_avx512vl) jmp .Ldone2 -ENDPROC(chacha_2block_xor_avx512vl) +SYM_FUNC_END(chacha_2block_xor_avx512vl) -ENTRY(chacha_4block_xor_avx512vl) +SYM_FUNC_START(chacha_4block_xor_avx512vl) # %rdi: Input state matrix, s # %rsi: up to 4 data blocks output, o # %rdx: up to 4 data blocks input, i @@ -453,9 +453,9 @@ ENTRY(chacha_4block_xor_avx512vl) jmp .Ldone4 -ENDPROC(chacha_4block_xor_avx512vl) +SYM_FUNC_END(chacha_4block_xor_avx512vl) -ENTRY(chacha_8block_xor_avx512vl) +SYM_FUNC_START(chacha_8block_xor_avx512vl) # %rdi: Input state matrix, s # %rsi: up to 8 data blocks output, o # %rdx: up to 8 data blocks input, i @@ -833,4 +833,4 @@ ENTRY(chacha_8block_xor_avx512vl) jmp .Ldone8 -ENDPROC(chacha_8block_xor_avx512vl) +SYM_FUNC_END(chacha_8block_xor_avx512vl) diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S index 2d86c7d6dc88..a38ab2512a6f 100644 --- a/arch/x86/crypto/chacha-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha-ssse3-x86_64.S @@ -33,7 +33,7 @@ CTRINC: .octa 0x00000003000000020000000100000000 * * Clobbers: %r8d, %xmm4-%xmm7 */ -chacha_permute: +SYM_FUNC_START_LOCAL(chacha_permute) movdqa ROT8(%rip),%xmm4 movdqa ROT16(%rip),%xmm5 @@ -109,9 +109,9 @@ chacha_permute: jnz .Ldoubleround ret -ENDPROC(chacha_permute) +SYM_FUNC_END(chacha_permute) -ENTRY(chacha_block_xor_ssse3) +SYM_FUNC_START(chacha_block_xor_ssse3) # %rdi: Input state matrix, s # %rsi: up to 1 data block output, o # %rdx: up to 1 data block input, i @@ -197,9 +197,9 @@ ENTRY(chacha_block_xor_ssse3) lea -8(%r10),%rsp jmp .Ldone -ENDPROC(chacha_block_xor_ssse3) +SYM_FUNC_END(chacha_block_xor_ssse3) -ENTRY(hchacha_block_ssse3) +SYM_FUNC_START(hchacha_block_ssse3) # %rdi: Input state matrix, s # %rsi: output (8 32-bit words) # %edx: nrounds @@ -218,9 +218,9 @@ ENTRY(hchacha_block_ssse3) FRAME_END ret -ENDPROC(hchacha_block_ssse3) +SYM_FUNC_END(hchacha_block_ssse3) -ENTRY(chacha_4block_xor_ssse3) +SYM_FUNC_START(chacha_4block_xor_ssse3) # %rdi: Input state matrix, s # %rsi: up to 4 data blocks output, o # %rdx: up to 4 data blocks input, i @@ -788,4 +788,4 @@ ENTRY(chacha_4block_xor_ssse3) jmp .Ldone4 -ENDPROC(chacha_4block_xor_ssse3) +SYM_FUNC_END(chacha_4block_xor_ssse3) diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c index 388f95a4ec24..68a74953efaf 100644 --- a/arch/x86/crypto/chacha_glue.c +++ b/arch/x86/crypto/chacha_glue.c @@ -7,7 +7,7 @@ */ #include <crypto/algapi.h> -#include <crypto/chacha.h> +#include <crypto/internal/chacha.h> #include <crypto/internal/simd.h> #include <crypto/internal/skcipher.h> #include <linux/kernel.h> @@ -21,24 +21,24 @@ asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src, asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src, unsigned int len, int nrounds); asmlinkage void hchacha_block_ssse3(const u32 *state, u32 *out, int nrounds); -#ifdef CONFIG_AS_AVX2 + asmlinkage void chacha_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src, unsigned int len, int nrounds); asmlinkage void chacha_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src, unsigned int len, int nrounds); asmlinkage void chacha_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src, unsigned int len, int nrounds); -static bool chacha_use_avx2; -#ifdef CONFIG_AS_AVX512 + asmlinkage void chacha_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src, unsigned int len, int nrounds); asmlinkage void chacha_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src, unsigned int len, int nrounds); asmlinkage void chacha_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src, unsigned int len, int nrounds); -static bool chacha_use_avx512vl; -#endif -#endif + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd); +static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2); +static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl); static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks) { @@ -49,9 +49,8 @@ static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks) static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, int nrounds) { -#ifdef CONFIG_AS_AVX2 -#ifdef CONFIG_AS_AVX512 - if (chacha_use_avx512vl) { + if (IS_ENABLED(CONFIG_AS_AVX512) && + static_branch_likely(&chacha_use_avx512vl)) { while (bytes >= CHACHA_BLOCK_SIZE * 8) { chacha_8block_xor_avx512vl(state, dst, src, bytes, nrounds); @@ -79,8 +78,9 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src, return; } } -#endif - if (chacha_use_avx2) { + + if (IS_ENABLED(CONFIG_AS_AVX2) && + static_branch_likely(&chacha_use_avx2)) { while (bytes >= CHACHA_BLOCK_SIZE * 8) { chacha_8block_xor_avx2(state, dst, src, bytes, nrounds); bytes -= CHACHA_BLOCK_SIZE * 8; @@ -104,7 +104,7 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src, return; } } -#endif + while (bytes >= CHACHA_BLOCK_SIZE * 4) { chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds); bytes -= CHACHA_BLOCK_SIZE * 4; @@ -123,37 +123,76 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src, } } -static int chacha_simd_stream_xor(struct skcipher_walk *walk, +void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds) +{ + state = PTR_ALIGN(state, CHACHA_STATE_ALIGN); + + if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) { + hchacha_block_generic(state, stream, nrounds); + } else { + kernel_fpu_begin(); + hchacha_block_ssse3(state, stream, nrounds); + kernel_fpu_end(); + } +} +EXPORT_SYMBOL(hchacha_block_arch); + +void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv) +{ + state = PTR_ALIGN(state, CHACHA_STATE_ALIGN); + + chacha_init_generic(state, key, iv); +} +EXPORT_SYMBOL(chacha_init_arch); + +void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, + int nrounds) +{ + state = PTR_ALIGN(state, CHACHA_STATE_ALIGN); + + if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() || + bytes <= CHACHA_BLOCK_SIZE) + return chacha_crypt_generic(state, dst, src, bytes, nrounds); + + kernel_fpu_begin(); + chacha_dosimd(state, dst, src, bytes, nrounds); + kernel_fpu_end(); +} +EXPORT_SYMBOL(chacha_crypt_arch); + +static int chacha_simd_stream_xor(struct skcipher_request *req, const struct chacha_ctx *ctx, const u8 *iv) { u32 *state, state_buf[16 + 2] __aligned(8); - int next_yield = 4096; /* bytes until next FPU yield */ - int err = 0; + struct skcipher_walk walk; + int err; + + err = skcipher_walk_virt(&walk, req, false); BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16); state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN); - crypto_chacha_init(state, ctx, iv); - - while (walk->nbytes > 0) { - unsigned int nbytes = walk->nbytes; + chacha_init_generic(state, ctx->key, iv); - if (nbytes < walk->total) { - nbytes = round_down(nbytes, walk->stride); - next_yield -= nbytes; - } + while (walk.nbytes > 0) { + unsigned int nbytes = walk.nbytes; - chacha_dosimd(state, walk->dst.virt.addr, walk->src.virt.addr, - nbytes, ctx->nrounds); + if (nbytes < walk.total) + nbytes = round_down(nbytes, walk.stride); - if (next_yield <= 0) { - /* temporarily allow preemption */ - kernel_fpu_end(); + if (!static_branch_likely(&chacha_use_simd) || + !crypto_simd_usable()) { + chacha_crypt_generic(state, walk.dst.virt.addr, + walk.src.virt.addr, nbytes, + ctx->nrounds); + } else { kernel_fpu_begin(); - next_yield = 4096; + chacha_dosimd(state, walk.dst.virt.addr, + walk.src.virt.addr, nbytes, + ctx->nrounds); + kernel_fpu_end(); } - - err = skcipher_walk_done(walk, walk->nbytes - nbytes); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } return err; @@ -163,55 +202,34 @@ static int chacha_simd(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - int err; - - if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) - return crypto_chacha_crypt(req); - err = skcipher_walk_virt(&walk, req, true); - if (err) - return err; - - kernel_fpu_begin(); - err = chacha_simd_stream_xor(&walk, ctx, req->iv); - kernel_fpu_end(); - return err; + return chacha_simd_stream_xor(req, ctx, req->iv); } static int xchacha_simd(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - struct chacha_ctx subctx; u32 *state, state_buf[16 + 2] __aligned(8); + struct chacha_ctx subctx; u8 real_iv[16]; - int err; - - if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) - return crypto_xchacha_crypt(req); - - err = skcipher_walk_virt(&walk, req, true); - if (err) - return err; BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16); state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN); - crypto_chacha_init(state, ctx, req->iv); - - kernel_fpu_begin(); - - hchacha_block_ssse3(state, subctx.key, ctx->nrounds); + chacha_init_generic(state, ctx->key, req->iv); + + if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) { + kernel_fpu_begin(); + hchacha_block_ssse3(state, subctx.key, ctx->nrounds); + kernel_fpu_end(); + } else { + hchacha_block_generic(state, subctx.key, ctx->nrounds); + } subctx.nrounds = ctx->nrounds; memcpy(&real_iv[0], req->iv + 24, 8); memcpy(&real_iv[8], req->iv + 16, 8); - err = chacha_simd_stream_xor(&walk, &subctx, real_iv); - - kernel_fpu_end(); - - return err; + return chacha_simd_stream_xor(req, &subctx, real_iv); } static struct skcipher_alg algs[] = { @@ -227,7 +245,7 @@ static struct skcipher_alg algs[] = { .max_keysize = CHACHA_KEY_SIZE, .ivsize = CHACHA_IV_SIZE, .chunksize = CHACHA_BLOCK_SIZE, - .setkey = crypto_chacha20_setkey, + .setkey = chacha20_setkey, .encrypt = chacha_simd, .decrypt = chacha_simd, }, { @@ -242,7 +260,7 @@ static struct skcipher_alg algs[] = { .max_keysize = CHACHA_KEY_SIZE, .ivsize = XCHACHA_IV_SIZE, .chunksize = CHACHA_BLOCK_SIZE, - .setkey = crypto_chacha20_setkey, + .setkey = chacha20_setkey, .encrypt = xchacha_simd, .decrypt = xchacha_simd, }, { @@ -257,7 +275,7 @@ static struct skcipher_alg algs[] = { .max_keysize = CHACHA_KEY_SIZE, .ivsize = XCHACHA_IV_SIZE, .chunksize = CHACHA_BLOCK_SIZE, - .setkey = crypto_chacha12_setkey, + .setkey = chacha12_setkey, .encrypt = xchacha_simd, .decrypt = xchacha_simd, }, @@ -266,24 +284,29 @@ static struct skcipher_alg algs[] = { static int __init chacha_simd_mod_init(void) { if (!boot_cpu_has(X86_FEATURE_SSSE3)) - return -ENODEV; - -#ifdef CONFIG_AS_AVX2 - chacha_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) && - boot_cpu_has(X86_FEATURE_AVX2) && - cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); -#ifdef CONFIG_AS_AVX512 - chacha_use_avx512vl = chacha_use_avx2 && - boot_cpu_has(X86_FEATURE_AVX512VL) && - boot_cpu_has(X86_FEATURE_AVX512BW); /* kmovq */ -#endif -#endif - return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); + return 0; + + static_branch_enable(&chacha_use_simd); + + if (IS_ENABLED(CONFIG_AS_AVX2) && + boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { + static_branch_enable(&chacha_use_avx2); + + if (IS_ENABLED(CONFIG_AS_AVX512) && + boot_cpu_has(X86_FEATURE_AVX512VL) && + boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */ + static_branch_enable(&chacha_use_avx512vl); + } + return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ? + crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0; } static void __exit chacha_simd_mod_fini(void) { - crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); + if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) && boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); } module_init(chacha_simd_mod_init); diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S index 1c099dc08cc3..9fd28ff65bc2 100644 --- a/arch/x86/crypto/crc32-pclmul_asm.S +++ b/arch/x86/crypto/crc32-pclmul_asm.S @@ -103,7 +103,7 @@ * size_t len, uint crc32) */ -ENTRY(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */ +SYM_FUNC_START(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */ movdqa (BUF), %xmm1 movdqa 0x10(BUF), %xmm2 movdqa 0x20(BUF), %xmm3 @@ -238,4 +238,4 @@ fold_64: PEXTRD 0x01, %xmm1, %eax ret -ENDPROC(crc32_pclmul_le_16) +SYM_FUNC_END(crc32_pclmul_le_16) diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index cb4ab6645106..418bd88acac8 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -94,10 +94,8 @@ static int crc32_pclmul_setkey(struct crypto_shash *hash, const u8 *key, { u32 *mctx = crypto_shash_ctx(hash); - if (keylen != sizeof(u32)) { - crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN); + if (keylen != sizeof(u32)) return -EINVAL; - } *mctx = le32_to_cpup((__le32 *)key); return 0; } diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index eefa0862f309..c20d1b8a82c3 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -91,10 +91,8 @@ static int crc32c_intel_setkey(struct crypto_shash *hash, const u8 *key, { u32 *mctx = crypto_shash_ctx(hash); - if (keylen != sizeof(u32)) { - crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN); + if (keylen != sizeof(u32)) return -EINVAL; - } *mctx = le32_to_cpup((__le32 *)key); return 0; } diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index d9b734d0c8cc..0e6690e3618c 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -74,7 +74,7 @@ # unsigned int crc_pcl(u8 *buffer, int len, unsigned int crc_init); .text -ENTRY(crc_pcl) +SYM_FUNC_START(crc_pcl) #define bufp %rdi #define bufp_dw %edi #define bufp_w %di @@ -311,7 +311,7 @@ do_return: popq %rdi popq %rbx ret -ENDPROC(crc_pcl) +SYM_FUNC_END(crc_pcl) .section .rodata, "a", @progbits ################################################################ diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S index 3d873e67749d..b2533d63030e 100644 --- a/arch/x86/crypto/crct10dif-pcl-asm_64.S +++ b/arch/x86/crypto/crct10dif-pcl-asm_64.S @@ -95,7 +95,7 @@ # Assumes len >= 16. # .align 16 -ENTRY(crc_t10dif_pcl) +SYM_FUNC_START(crc_t10dif_pcl) movdqa .Lbswap_mask(%rip), BSWAP_MASK @@ -280,7 +280,7 @@ ENTRY(crc_t10dif_pcl) jge .Lfold_16_bytes_loop # 32 <= len <= 255 add $16, len jmp .Lhandle_partial_segment # 17 <= len <= 31 -ENDPROC(crc_t10dif_pcl) +SYM_FUNC_END(crc_t10dif_pcl) .section .rodata, "a", @progbits .align 16 diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c new file mode 100644 index 000000000000..eec7d2d24239 --- /dev/null +++ b/arch/x86/crypto/curve25519-x86_64.c @@ -0,0 +1,2476 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Copyright (c) 2017 Armando Faz <armfazh@ic.unicamp.br>. All Rights Reserved. + * Copyright (C) 2018-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + * Copyright (C) 2018 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved. + */ + +#include <crypto/curve25519.h> +#include <crypto/internal/kpp.h> + +#include <linux/types.h> +#include <linux/jump_label.h> +#include <linux/kernel.h> +#include <linux/module.h> + +#include <asm/cpufeature.h> +#include <asm/processor.h> + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2); +static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_adx); + +enum { NUM_WORDS_ELTFP25519 = 4 }; +typedef __aligned(32) u64 eltfp25519_1w[NUM_WORDS_ELTFP25519]; +typedef __aligned(32) u64 eltfp25519_1w_buffer[2 * NUM_WORDS_ELTFP25519]; + +#define mul_eltfp25519_1w_adx(c, a, b) do { \ + mul_256x256_integer_adx(m.buffer, a, b); \ + red_eltfp25519_1w_adx(c, m.buffer); \ +} while (0) + +#define mul_eltfp25519_1w_bmi2(c, a, b) do { \ + mul_256x256_integer_bmi2(m.buffer, a, b); \ + red_eltfp25519_1w_bmi2(c, m.buffer); \ +} while (0) + +#define sqr_eltfp25519_1w_adx(a) do { \ + sqr_256x256_integer_adx(m.buffer, a); \ + red_eltfp25519_1w_adx(a, m.buffer); \ +} while (0) + +#define sqr_eltfp25519_1w_bmi2(a) do { \ + sqr_256x256_integer_bmi2(m.buffer, a); \ + red_eltfp25519_1w_bmi2(a, m.buffer); \ +} while (0) + +#define mul_eltfp25519_2w_adx(c, a, b) do { \ + mul2_256x256_integer_adx(m.buffer, a, b); \ + red_eltfp25519_2w_adx(c, m.buffer); \ +} while (0) + +#define mul_eltfp25519_2w_bmi2(c, a, b) do { \ + mul2_256x256_integer_bmi2(m.buffer, a, b); \ + red_eltfp25519_2w_bmi2(c, m.buffer); \ +} while (0) + +#define sqr_eltfp25519_2w_adx(a) do { \ + sqr2_256x256_integer_adx(m.buffer, a); \ + red_eltfp25519_2w_adx(a, m.buffer); \ +} while (0) + +#define sqr_eltfp25519_2w_bmi2(a) do { \ + sqr2_256x256_integer_bmi2(m.buffer, a); \ + red_eltfp25519_2w_bmi2(a, m.buffer); \ +} while (0) + +#define sqrn_eltfp25519_1w_adx(a, times) do { \ + int ____counter = (times); \ + while (____counter-- > 0) \ + sqr_eltfp25519_1w_adx(a); \ +} while (0) + +#define sqrn_eltfp25519_1w_bmi2(a, times) do { \ + int ____counter = (times); \ + while (____counter-- > 0) \ + sqr_eltfp25519_1w_bmi2(a); \ +} while (0) + +#define copy_eltfp25519_1w(C, A) do { \ + (C)[0] = (A)[0]; \ + (C)[1] = (A)[1]; \ + (C)[2] = (A)[2]; \ + (C)[3] = (A)[3]; \ +} while (0) + +#define setzero_eltfp25519_1w(C) do { \ + (C)[0] = 0; \ + (C)[1] = 0; \ + (C)[2] = 0; \ + (C)[3] = 0; \ +} while (0) + +__aligned(32) static const u64 table_ladder_8k[252 * NUM_WORDS_ELTFP25519] = { + /* 1 */ 0xfffffffffffffff3UL, 0xffffffffffffffffUL, + 0xffffffffffffffffUL, 0x5fffffffffffffffUL, + /* 2 */ 0x6b8220f416aafe96UL, 0x82ebeb2b4f566a34UL, + 0xd5a9a5b075a5950fUL, 0x5142b2cf4b2488f4UL, + /* 3 */ 0x6aaebc750069680cUL, 0x89cf7820a0f99c41UL, + 0x2a58d9183b56d0f4UL, 0x4b5aca80e36011a4UL, + /* 4 */ 0x329132348c29745dUL, 0xf4a2e616e1642fd7UL, + 0x1e45bb03ff67bc34UL, 0x306912d0f42a9b4aUL, + /* 5 */ 0xff886507e6af7154UL, 0x04f50e13dfeec82fUL, + 0xaa512fe82abab5ceUL, 0x174e251a68d5f222UL, + /* 6 */ 0xcf96700d82028898UL, 0x1743e3370a2c02c5UL, + 0x379eec98b4e86eaaUL, 0x0c59888a51e0482eUL, + /* 7 */ 0xfbcbf1d699b5d189UL, 0xacaef0d58e9fdc84UL, + 0xc1c20d06231f7614UL, 0x2938218da274f972UL, + /* 8 */ 0xf6af49beff1d7f18UL, 0xcc541c22387ac9c2UL, + 0x96fcc9ef4015c56bUL, 0x69c1627c690913a9UL, + /* 9 */ 0x7a86fd2f4733db0eUL, 0xfdb8c4f29e087de9UL, + 0x095e4b1a8ea2a229UL, 0x1ad7a7c829b37a79UL, + /* 10 */ 0x342d89cad17ea0c0UL, 0x67bedda6cced2051UL, + 0x19ca31bf2bb42f74UL, 0x3df7b4c84980acbbUL, + /* 11 */ 0xa8c6444dc80ad883UL, 0xb91e440366e3ab85UL, + 0xc215cda00164f6d8UL, 0x3d867c6ef247e668UL, + /* 12 */ 0xc7dd582bcc3e658cUL, 0xfd2c4748ee0e5528UL, + 0xa0fd9b95cc9f4f71UL, 0x7529d871b0675ddfUL, + /* 13 */ 0xb8f568b42d3cbd78UL, 0x1233011b91f3da82UL, + 0x2dce6ccd4a7c3b62UL, 0x75e7fc8e9e498603UL, + /* 14 */ 0x2f4f13f1fcd0b6ecUL, 0xf1a8ca1f29ff7a45UL, + 0xc249c1a72981e29bUL, 0x6ebe0dbb8c83b56aUL, + /* 15 */ 0x7114fa8d170bb222UL, 0x65a2dcd5bf93935fUL, + 0xbdc41f68b59c979aUL, 0x2f0eef79a2ce9289UL, + /* 16 */ 0x42ecbf0c083c37ceUL, 0x2930bc09ec496322UL, + 0xf294b0c19cfeac0dUL, 0x3780aa4bedfabb80UL, + /* 17 */ 0x56c17d3e7cead929UL, 0xe7cb4beb2e5722c5UL, + 0x0ce931732dbfe15aUL, 0x41b883c7621052f8UL, + /* 18 */ 0xdbf75ca0c3d25350UL, 0x2936be086eb1e351UL, + 0xc936e03cb4a9b212UL, 0x1d45bf82322225aaUL, + /* 19 */ 0xe81ab1036a024cc5UL, 0xe212201c304c9a72UL, + 0xc5d73fba6832b1fcUL, 0x20ffdb5a4d839581UL, + /* 20 */ 0xa283d367be5d0fadUL, 0x6c2b25ca8b164475UL, + 0x9d4935467caaf22eUL, 0x5166408eee85ff49UL, + /* 21 */ 0x3c67baa2fab4e361UL, 0xb3e433c67ef35cefUL, + 0x5259729241159b1cUL, 0x6a621892d5b0ab33UL, + /* 22 */ 0x20b74a387555cdcbUL, 0x532aa10e1208923fUL, + 0xeaa17b7762281dd1UL, 0x61ab3443f05c44bfUL, + /* 23 */ 0x257a6c422324def8UL, 0x131c6c1017e3cf7fUL, + 0x23758739f630a257UL, 0x295a407a01a78580UL, + /* 24 */ 0xf8c443246d5da8d9UL, 0x19d775450c52fa5dUL, + 0x2afcfc92731bf83dUL, 0x7d10c8e81b2b4700UL, + /* 25 */ 0xc8e0271f70baa20bUL, 0x993748867ca63957UL, + 0x5412efb3cb7ed4bbUL, 0x3196d36173e62975UL, + /* 26 */ 0xde5bcad141c7dffcUL, 0x47cc8cd2b395c848UL, + 0xa34cd942e11af3cbUL, 0x0256dbf2d04ecec2UL, + /* 27 */ 0x875ab7e94b0e667fUL, 0xcad4dd83c0850d10UL, + 0x47f12e8f4e72c79fUL, 0x5f1a87bb8c85b19bUL, + /* 28 */ 0x7ae9d0b6437f51b8UL, 0x12c7ce5518879065UL, + 0x2ade09fe5cf77aeeUL, 0x23a05a2f7d2c5627UL, + /* 29 */ 0x5908e128f17c169aUL, 0xf77498dd8ad0852dUL, + 0x74b4c4ceab102f64UL, 0x183abadd10139845UL, + /* 30 */ 0xb165ba8daa92aaacUL, 0xd5c5ef9599386705UL, + 0xbe2f8f0cf8fc40d1UL, 0x2701e635ee204514UL, + /* 31 */ 0x629fa80020156514UL, 0xf223868764a8c1ceUL, + 0x5b894fff0b3f060eUL, 0x60d9944cf708a3faUL, + /* 32 */ 0xaeea001a1c7a201fUL, 0xebf16a633ee2ce63UL, + 0x6f7709594c7a07e1UL, 0x79b958150d0208cbUL, + /* 33 */ 0x24b55e5301d410e7UL, 0xe3a34edff3fdc84dUL, + 0xd88768e4904032d8UL, 0x131384427b3aaeecUL, + /* 34 */ 0x8405e51286234f14UL, 0x14dc4739adb4c529UL, + 0xb8a2b5b250634ffdUL, 0x2fe2a94ad8a7ff93UL, + /* 35 */ 0xec5c57efe843faddUL, 0x2843ce40f0bb9918UL, + 0xa4b561d6cf3d6305UL, 0x743629bde8fb777eUL, + /* 36 */ 0x343edd46bbaf738fUL, 0xed981828b101a651UL, + 0xa401760b882c797aUL, 0x1fc223e28dc88730UL, + /* 37 */ 0x48604e91fc0fba0eUL, 0xb637f78f052c6fa4UL, + 0x91ccac3d09e9239cUL, 0x23f7eed4437a687cUL, + /* 38 */ 0x5173b1118d9bd800UL, 0x29d641b63189d4a7UL, + 0xfdbf177988bbc586UL, 0x2959894fcad81df5UL, + /* 39 */ 0xaebc8ef3b4bbc899UL, 0x4148995ab26992b9UL, + 0x24e20b0134f92cfbUL, 0x40d158894a05dee8UL, + /* 40 */ 0x46b00b1185af76f6UL, 0x26bac77873187a79UL, + 0x3dc0bf95ab8fff5fUL, 0x2a608bd8945524d7UL, + /* 41 */ 0x26449588bd446302UL, 0x7c4bc21c0388439cUL, + 0x8e98a4f383bd11b2UL, 0x26218d7bc9d876b9UL, + /* 42 */ 0xe3081542997c178aUL, 0x3c2d29a86fb6606fUL, + 0x5c217736fa279374UL, 0x7dde05734afeb1faUL, + /* 43 */ 0x3bf10e3906d42babUL, 0xe4f7803e1980649cUL, + 0xe6053bf89595bf7aUL, 0x394faf38da245530UL, + /* 44 */ 0x7a8efb58896928f4UL, 0xfbc778e9cc6a113cUL, + 0x72670ce330af596fUL, 0x48f222a81d3d6cf7UL, + /* 45 */ 0xf01fce410d72caa7UL, 0x5a20ecc7213b5595UL, + 0x7bc21165c1fa1483UL, 0x07f89ae31da8a741UL, + /* 46 */ 0x05d2c2b4c6830ff9UL, 0xd43e330fc6316293UL, + 0xa5a5590a96d3a904UL, 0x705edb91a65333b6UL, + /* 47 */ 0x048ee15e0bb9a5f7UL, 0x3240cfca9e0aaf5dUL, + 0x8f4b71ceedc4a40bUL, 0x621c0da3de544a6dUL, + /* 48 */ 0x92872836a08c4091UL, 0xce8375b010c91445UL, + 0x8a72eb524f276394UL, 0x2667fcfa7ec83635UL, + /* 49 */ 0x7f4c173345e8752aUL, 0x061b47feee7079a5UL, + 0x25dd9afa9f86ff34UL, 0x3780cef5425dc89cUL, + /* 50 */ 0x1a46035a513bb4e9UL, 0x3e1ef379ac575adaUL, + 0xc78c5f1c5fa24b50UL, 0x321a967634fd9f22UL, + /* 51 */ 0x946707b8826e27faUL, 0x3dca84d64c506fd0UL, + 0xc189218075e91436UL, 0x6d9284169b3b8484UL, + /* 52 */ 0x3a67e840383f2ddfUL, 0x33eec9a30c4f9b75UL, + 0x3ec7c86fa783ef47UL, 0x26ec449fbac9fbc4UL, + /* 53 */ 0x5c0f38cba09b9e7dUL, 0x81168cc762a3478cUL, + 0x3e23b0d306fc121cUL, 0x5a238aa0a5efdcddUL, + /* 54 */ 0x1ba26121c4ea43ffUL, 0x36f8c77f7c8832b5UL, + 0x88fbea0b0adcf99aUL, 0x5ca9938ec25bebf9UL, + /* 55 */ 0xd5436a5e51fccda0UL, 0x1dbc4797c2cd893bUL, + 0x19346a65d3224a08UL, 0x0f5034e49b9af466UL, + /* 56 */ 0xf23c3967a1e0b96eUL, 0xe58b08fa867a4d88UL, + 0xfb2fabc6a7341679UL, 0x2a75381eb6026946UL, + /* 57 */ 0xc80a3be4c19420acUL, 0x66b1f6c681f2b6dcUL, + 0x7cf7036761e93388UL, 0x25abbbd8a660a4c4UL, + /* 58 */ 0x91ea12ba14fd5198UL, 0x684950fc4a3cffa9UL, + 0xf826842130f5ad28UL, 0x3ea988f75301a441UL, + /* 59 */ 0xc978109a695f8c6fUL, 0x1746eb4a0530c3f3UL, + 0x444d6d77b4459995UL, 0x75952b8c054e5cc7UL, + /* 60 */ 0xa3703f7915f4d6aaUL, 0x66c346202f2647d8UL, + 0xd01469df811d644bUL, 0x77fea47d81a5d71fUL, + /* 61 */ 0xc5e9529ef57ca381UL, 0x6eeeb4b9ce2f881aUL, + 0xb6e91a28e8009bd6UL, 0x4b80be3e9afc3fecUL, + /* 62 */ 0x7e3773c526aed2c5UL, 0x1b4afcb453c9a49dUL, + 0xa920bdd7baffb24dUL, 0x7c54699f122d400eUL, + /* 63 */ 0xef46c8e14fa94bc8UL, 0xe0b074ce2952ed5eUL, + 0xbea450e1dbd885d5UL, 0x61b68649320f712cUL, + /* 64 */ 0x8a485f7309ccbdd1UL, 0xbd06320d7d4d1a2dUL, + 0x25232973322dbef4UL, 0x445dc4758c17f770UL, + /* 65 */ 0xdb0434177cc8933cUL, 0xed6fe82175ea059fUL, + 0x1efebefdc053db34UL, 0x4adbe867c65daf99UL, + /* 66 */ 0x3acd71a2a90609dfUL, 0xe5e991856dd04050UL, + 0x1ec69b688157c23cUL, 0x697427f6885cfe4dUL, + /* 67 */ 0xd7be7b9b65e1a851UL, 0xa03d28d522c536ddUL, + 0x28399d658fd2b645UL, 0x49e5b7e17c2641e1UL, + /* 68 */ 0x6f8c3a98700457a4UL, 0x5078f0a25ebb6778UL, + 0xd13c3ccbc382960fUL, 0x2e003258a7df84b1UL, + /* 69 */ 0x8ad1f39be6296a1cUL, 0xc1eeaa652a5fbfb2UL, + 0x33ee0673fd26f3cbUL, 0x59256173a69d2cccUL, + /* 70 */ 0x41ea07aa4e18fc41UL, 0xd9fc19527c87a51eUL, + 0xbdaacb805831ca6fUL, 0x445b652dc916694fUL, + /* 71 */ 0xce92a3a7f2172315UL, 0x1edc282de11b9964UL, + 0xa1823aafe04c314aUL, 0x790a2d94437cf586UL, + /* 72 */ 0x71c447fb93f6e009UL, 0x8922a56722845276UL, + 0xbf70903b204f5169UL, 0x2f7a89891ba319feUL, + /* 73 */ 0x02a08eb577e2140cUL, 0xed9a4ed4427bdcf4UL, + 0x5253ec44e4323cd1UL, 0x3e88363c14e9355bUL, + /* 74 */ 0xaa66c14277110b8cUL, 0x1ae0391610a23390UL, + 0x2030bd12c93fc2a2UL, 0x3ee141579555c7abUL, + /* 75 */ 0x9214de3a6d6e7d41UL, 0x3ccdd88607f17efeUL, + 0x674f1288f8e11217UL, 0x5682250f329f93d0UL, + /* 76 */ 0x6cf00b136d2e396eUL, 0x6e4cf86f1014debfUL, + 0x5930b1b5bfcc4e83UL, 0x047069b48aba16b6UL, + /* 77 */ 0x0d4ce4ab69b20793UL, 0xb24db91a97d0fb9eUL, + 0xcdfa50f54e00d01dUL, 0x221b1085368bddb5UL, + /* 78 */ 0xe7e59468b1e3d8d2UL, 0x53c56563bd122f93UL, + 0xeee8a903e0663f09UL, 0x61efa662cbbe3d42UL, + /* 79 */ 0x2cf8ddddde6eab2aUL, 0x9bf80ad51435f231UL, + 0x5deadacec9f04973UL, 0x29275b5d41d29b27UL, + /* 80 */ 0xcfde0f0895ebf14fUL, 0xb9aab96b054905a7UL, + 0xcae80dd9a1c420fdUL, 0x0a63bf2f1673bbc7UL, + /* 81 */ 0x092f6e11958fbc8cUL, 0x672a81e804822fadUL, + 0xcac8351560d52517UL, 0x6f3f7722c8f192f8UL, + /* 82 */ 0xf8ba90ccc2e894b7UL, 0x2c7557a438ff9f0dUL, + 0x894d1d855ae52359UL, 0x68e122157b743d69UL, + /* 83 */ 0xd87e5570cfb919f3UL, 0x3f2cdecd95798db9UL, + 0x2121154710c0a2ceUL, 0x3c66a115246dc5b2UL, + /* 84 */ 0xcbedc562294ecb72UL, 0xba7143c36a280b16UL, + 0x9610c2efd4078b67UL, 0x6144735d946a4b1eUL, + /* 85 */ 0x536f111ed75b3350UL, 0x0211db8c2041d81bUL, + 0xf93cb1000e10413cUL, 0x149dfd3c039e8876UL, + /* 86 */ 0xd479dde46b63155bUL, 0xb66e15e93c837976UL, + 0xdafde43b1f13e038UL, 0x5fafda1a2e4b0b35UL, + /* 87 */ 0x3600bbdf17197581UL, 0x3972050bbe3cd2c2UL, + 0x5938906dbdd5be86UL, 0x34fce5e43f9b860fUL, + /* 88 */ 0x75a8a4cd42d14d02UL, 0x828dabc53441df65UL, + 0x33dcabedd2e131d3UL, 0x3ebad76fb814d25fUL, + /* 89 */ 0xd4906f566f70e10fUL, 0x5d12f7aa51690f5aUL, + 0x45adb16e76cefcf2UL, 0x01f768aead232999UL, + /* 90 */ 0x2b6cc77b6248febdUL, 0x3cd30628ec3aaffdUL, + 0xce1c0b80d4ef486aUL, 0x4c3bff2ea6f66c23UL, + /* 91 */ 0x3f2ec4094aeaeb5fUL, 0x61b19b286e372ca7UL, + 0x5eefa966de2a701dUL, 0x23b20565de55e3efUL, + /* 92 */ 0xe301ca5279d58557UL, 0x07b2d4ce27c2874fUL, + 0xa532cd8a9dcf1d67UL, 0x2a52fee23f2bff56UL, + /* 93 */ 0x8624efb37cd8663dUL, 0xbbc7ac20ffbd7594UL, + 0x57b85e9c82d37445UL, 0x7b3052cb86a6ec66UL, + /* 94 */ 0x3482f0ad2525e91eUL, 0x2cb68043d28edca0UL, + 0xaf4f6d052e1b003aUL, 0x185f8c2529781b0aUL, + /* 95 */ 0xaa41de5bd80ce0d6UL, 0x9407b2416853e9d6UL, + 0x563ec36e357f4c3aUL, 0x4cc4b8dd0e297bceUL, + /* 96 */ 0xa2fc1a52ffb8730eUL, 0x1811f16e67058e37UL, + 0x10f9a366cddf4ee1UL, 0x72f4a0c4a0b9f099UL, + /* 97 */ 0x8c16c06f663f4ea7UL, 0x693b3af74e970fbaUL, + 0x2102e7f1d69ec345UL, 0x0ba53cbc968a8089UL, + /* 98 */ 0xca3d9dc7fea15537UL, 0x4c6824bb51536493UL, + 0xb9886314844006b1UL, 0x40d2a72ab454cc60UL, + /* 99 */ 0x5936a1b712570975UL, 0x91b9d648debda657UL, + 0x3344094bb64330eaUL, 0x006ba10d12ee51d0UL, + /* 100 */ 0x19228468f5de5d58UL, 0x0eb12f4c38cc05b0UL, + 0xa1039f9dd5601990UL, 0x4502d4ce4fff0e0bUL, + /* 101 */ 0xeb2054106837c189UL, 0xd0f6544c6dd3b93cUL, + 0x40727064c416d74fUL, 0x6e15c6114b502ef0UL, + /* 102 */ 0x4df2a398cfb1a76bUL, 0x11256c7419f2f6b1UL, + 0x4a497962066e6043UL, 0x705b3aab41355b44UL, + /* 103 */ 0x365ef536d797b1d8UL, 0x00076bd622ddf0dbUL, + 0x3bbf33b0e0575a88UL, 0x3777aa05c8e4ca4dUL, + /* 104 */ 0x392745c85578db5fUL, 0x6fda4149dbae5ae2UL, + 0xb1f0b00b8adc9867UL, 0x09963437d36f1da3UL, + /* 105 */ 0x7e824e90a5dc3853UL, 0xccb5f6641f135cbdUL, + 0x6736d86c87ce8fccUL, 0x625f3ce26604249fUL, + /* 106 */ 0xaf8ac8059502f63fUL, 0x0c05e70a2e351469UL, + 0x35292e9c764b6305UL, 0x1a394360c7e23ac3UL, + /* 107 */ 0xd5c6d53251183264UL, 0x62065abd43c2b74fUL, + 0xb5fbf5d03b973f9bUL, 0x13a3da3661206e5eUL, + /* 108 */ 0xc6bd5837725d94e5UL, 0x18e30912205016c5UL, + 0x2088ce1570033c68UL, 0x7fba1f495c837987UL, + /* 109 */ 0x5a8c7423f2f9079dUL, 0x1735157b34023fc5UL, + 0xe4f9b49ad2fab351UL, 0x6691ff72c878e33cUL, + /* 110 */ 0x122c2adedc5eff3eUL, 0xf8dd4bf1d8956cf4UL, + 0xeb86205d9e9e5bdaUL, 0x049b92b9d975c743UL, + /* 111 */ 0xa5379730b0f6c05aUL, 0x72a0ffacc6f3a553UL, + 0xb0032c34b20dcd6dUL, 0x470e9dbc88d5164aUL, + /* 112 */ 0xb19cf10ca237c047UL, 0xb65466711f6c81a2UL, + 0xb3321bd16dd80b43UL, 0x48c14f600c5fbe8eUL, + /* 113 */ 0x66451c264aa6c803UL, 0xb66e3904a4fa7da6UL, + 0xd45f19b0b3128395UL, 0x31602627c3c9bc10UL, + /* 114 */ 0x3120dc4832e4e10dUL, 0xeb20c46756c717f7UL, + 0x00f52e3f67280294UL, 0x566d4fc14730c509UL, + /* 115 */ 0x7e3a5d40fd837206UL, 0xc1e926dc7159547aUL, + 0x216730fba68d6095UL, 0x22e8c3843f69cea7UL, + /* 116 */ 0x33d074e8930e4b2bUL, 0xb6e4350e84d15816UL, + 0x5534c26ad6ba2365UL, 0x7773c12f89f1f3f3UL, + /* 117 */ 0x8cba404da57962aaUL, 0x5b9897a81999ce56UL, + 0x508e862f121692fcUL, 0x3a81907fa093c291UL, + /* 118 */ 0x0dded0ff4725a510UL, 0x10d8cc10673fc503UL, + 0x5b9d151c9f1f4e89UL, 0x32a5c1d5cb09a44cUL, + /* 119 */ 0x1e0aa442b90541fbUL, 0x5f85eb7cc1b485dbUL, + 0xbee595ce8a9df2e5UL, 0x25e496c722422236UL, + /* 120 */ 0x5edf3c46cd0fe5b9UL, 0x34e75a7ed2a43388UL, + 0xe488de11d761e352UL, 0x0e878a01a085545cUL, + /* 121 */ 0xba493c77e021bb04UL, 0x2b4d1843c7df899aUL, + 0x9ea37a487ae80d67UL, 0x67a9958011e41794UL, + /* 122 */ 0x4b58051a6697b065UL, 0x47e33f7d8d6ba6d4UL, + 0xbb4da8d483ca46c1UL, 0x68becaa181c2db0dUL, + /* 123 */ 0x8d8980e90b989aa5UL, 0xf95eb14a2c93c99bUL, + 0x51c6c7c4796e73a2UL, 0x6e228363b5efb569UL, + /* 124 */ 0xc6bbc0b02dd624c8UL, 0x777eb47dec8170eeUL, + 0x3cde15a004cfafa9UL, 0x1dc6bc087160bf9bUL, + /* 125 */ 0x2e07e043eec34002UL, 0x18e9fc677a68dc7fUL, + 0xd8da03188bd15b9aUL, 0x48fbc3bb00568253UL, + /* 126 */ 0x57547d4cfb654ce1UL, 0xd3565b82a058e2adUL, + 0xf63eaf0bbf154478UL, 0x47531ef114dfbb18UL, + /* 127 */ 0xe1ec630a4278c587UL, 0x5507d546ca8e83f3UL, + 0x85e135c63adc0c2bUL, 0x0aa7efa85682844eUL, + /* 128 */ 0x72691ba8b3e1f615UL, 0x32b4e9701fbe3ffaUL, + 0x97b6d92e39bb7868UL, 0x2cfe53dea02e39e8UL, + /* 129 */ 0x687392cd85cd52b0UL, 0x27ff66c910e29831UL, + 0x97134556a9832d06UL, 0x269bb0360a84f8a0UL, + /* 130 */ 0x706e55457643f85cUL, 0x3734a48c9b597d1bUL, + 0x7aee91e8c6efa472UL, 0x5cd6abc198a9d9e0UL, + /* 131 */ 0x0e04de06cb3ce41aUL, 0xd8c6eb893402e138UL, + 0x904659bb686e3772UL, 0x7215c371746ba8c8UL, + /* 132 */ 0xfd12a97eeae4a2d9UL, 0x9514b7516394f2c5UL, + 0x266fd5809208f294UL, 0x5c847085619a26b9UL, + /* 133 */ 0x52985410fed694eaUL, 0x3c905b934a2ed254UL, + 0x10bb47692d3be467UL, 0x063b3d2d69e5e9e1UL, + /* 134 */ 0x472726eedda57debUL, 0xefb6c4ae10f41891UL, + 0x2b1641917b307614UL, 0x117c554fc4f45b7cUL, + /* 135 */ 0xc07cf3118f9d8812UL, 0x01dbd82050017939UL, + 0xd7e803f4171b2827UL, 0x1015e87487d225eaUL, + /* 136 */ 0xc58de3fed23acc4dUL, 0x50db91c294a7be2dUL, + 0x0b94d43d1c9cf457UL, 0x6b1640fa6e37524aUL, + /* 137 */ 0x692f346c5fda0d09UL, 0x200b1c59fa4d3151UL, + 0xb8c46f760777a296UL, 0x4b38395f3ffdfbcfUL, + /* 138 */ 0x18d25e00be54d671UL, 0x60d50582bec8aba6UL, + 0x87ad8f263b78b982UL, 0x50fdf64e9cda0432UL, + /* 139 */ 0x90f567aac578dcf0UL, 0xef1e9b0ef2a3133bUL, + 0x0eebba9242d9de71UL, 0x15473c9bf03101c7UL, + /* 140 */ 0x7c77e8ae56b78095UL, 0xb678e7666e6f078eUL, + 0x2da0b9615348ba1fUL, 0x7cf931c1ff733f0bUL, + /* 141 */ 0x26b357f50a0a366cUL, 0xe9708cf42b87d732UL, + 0xc13aeea5f91cb2c0UL, 0x35d90c991143bb4cUL, + /* 142 */ 0x47c1c404a9a0d9dcUL, 0x659e58451972d251UL, + 0x3875a8c473b38c31UL, 0x1fbd9ed379561f24UL, + /* 143 */ 0x11fabc6fd41ec28dUL, 0x7ef8dfe3cd2a2dcaUL, + 0x72e73b5d8c404595UL, 0x6135fa4954b72f27UL, + /* 144 */ 0xccfc32a2de24b69cUL, 0x3f55698c1f095d88UL, + 0xbe3350ed5ac3f929UL, 0x5e9bf806ca477eebUL, + /* 145 */ 0xe9ce8fb63c309f68UL, 0x5376f63565e1f9f4UL, + 0xd1afcfb35a6393f1UL, 0x6632a1ede5623506UL, + /* 146 */ 0x0b7d6c390c2ded4cUL, 0x56cb3281df04cb1fUL, + 0x66305a1249ecc3c7UL, 0x5d588b60a38ca72aUL, + /* 147 */ 0xa6ecbf78e8e5f42dUL, 0x86eeb44b3c8a3eecUL, + 0xec219c48fbd21604UL, 0x1aaf1af517c36731UL, + /* 148 */ 0xc306a2836769bde7UL, 0x208280622b1e2adbUL, + 0x8027f51ffbff94a6UL, 0x76cfa1ce1124f26bUL, + /* 149 */ 0x18eb00562422abb6UL, 0xf377c4d58f8c29c3UL, + 0x4dbbc207f531561aUL, 0x0253b7f082128a27UL, + /* 150 */ 0x3d1f091cb62c17e0UL, 0x4860e1abd64628a9UL, + 0x52d17436309d4253UL, 0x356f97e13efae576UL, + /* 151 */ 0xd351e11aa150535bUL, 0x3e6b45bb1dd878ccUL, + 0x0c776128bed92c98UL, 0x1d34ae93032885b8UL, + /* 152 */ 0x4ba0488ca85ba4c3UL, 0x985348c33c9ce6ceUL, + 0x66124c6f97bda770UL, 0x0f81a0290654124aUL, + /* 153 */ 0x9ed09ca6569b86fdUL, 0x811009fd18af9a2dUL, + 0xff08d03f93d8c20aUL, 0x52a148199faef26bUL, + /* 154 */ 0x3e03f9dc2d8d1b73UL, 0x4205801873961a70UL, + 0xc0d987f041a35970UL, 0x07aa1f15a1c0d549UL, + /* 155 */ 0xdfd46ce08cd27224UL, 0x6d0a024f934e4239UL, + 0x808a7a6399897b59UL, 0x0a4556e9e13d95a2UL, + /* 156 */ 0xd21a991fe9c13045UL, 0x9b0e8548fe7751b8UL, + 0x5da643cb4bf30035UL, 0x77db28d63940f721UL, + /* 157 */ 0xfc5eeb614adc9011UL, 0x5229419ae8c411ebUL, + 0x9ec3e7787d1dcf74UL, 0x340d053e216e4cb5UL, + /* 158 */ 0xcac7af39b48df2b4UL, 0xc0faec2871a10a94UL, + 0x140a69245ca575edUL, 0x0cf1c37134273a4cUL, + /* 159 */ 0xc8ee306ac224b8a5UL, 0x57eaee7ccb4930b0UL, + 0xa1e806bdaacbe74fUL, 0x7d9a62742eeb657dUL, + /* 160 */ 0x9eb6b6ef546c4830UL, 0x885cca1fddb36e2eUL, + 0xe6b9f383ef0d7105UL, 0x58654fef9d2e0412UL, + /* 161 */ 0xa905c4ffbe0e8e26UL, 0x942de5df9b31816eUL, + 0x497d723f802e88e1UL, 0x30684dea602f408dUL, + /* 162 */ 0x21e5a278a3e6cb34UL, 0xaefb6e6f5b151dc4UL, + 0xb30b8e049d77ca15UL, 0x28c3c9cf53b98981UL, + /* 163 */ 0x287fb721556cdd2aUL, 0x0d317ca897022274UL, + 0x7468c7423a543258UL, 0x4a7f11464eb5642fUL, + /* 164 */ 0xa237a4774d193aa6UL, 0xd865986ea92129a1UL, + 0x24c515ecf87c1a88UL, 0x604003575f39f5ebUL, + /* 165 */ 0x47b9f189570a9b27UL, 0x2b98cede465e4b78UL, + 0x026df551dbb85c20UL, 0x74fcd91047e21901UL, + /* 166 */ 0x13e2a90a23c1bfa3UL, 0x0cb0074e478519f6UL, + 0x5ff1cbbe3af6cf44UL, 0x67fe5438be812dbeUL, + /* 167 */ 0xd13cf64fa40f05b0UL, 0x054dfb2f32283787UL, + 0x4173915b7f0d2aeaUL, 0x482f144f1f610d4eUL, + /* 168 */ 0xf6210201b47f8234UL, 0x5d0ae1929e70b990UL, + 0xdcd7f455b049567cUL, 0x7e93d0f1f0916f01UL, + /* 169 */ 0xdd79cbf18a7db4faUL, 0xbe8391bf6f74c62fUL, + 0x027145d14b8291bdUL, 0x585a73ea2cbf1705UL, + /* 170 */ 0x485ca03e928a0db2UL, 0x10fc01a5742857e7UL, + 0x2f482edbd6d551a7UL, 0x0f0433b5048fdb8aUL, + /* 171 */ 0x60da2e8dd7dc6247UL, 0x88b4c9d38cd4819aUL, + 0x13033ac001f66697UL, 0x273b24fe3b367d75UL, + /* 172 */ 0xc6e8f66a31b3b9d4UL, 0x281514a494df49d5UL, + 0xd1726fdfc8b23da7UL, 0x4b3ae7d103dee548UL, + /* 173 */ 0xc6256e19ce4b9d7eUL, 0xff5c5cf186e3c61cUL, + 0xacc63ca34b8ec145UL, 0x74621888fee66574UL, + /* 174 */ 0x956f409645290a1eUL, 0xef0bf8e3263a962eUL, + 0xed6a50eb5ec2647bUL, 0x0694283a9dca7502UL, + /* 175 */ 0x769b963643a2dcd1UL, 0x42b7c8ea09fc5353UL, + 0x4f002aee13397eabUL, 0x63005e2c19b7d63aUL, + /* 176 */ 0xca6736da63023beaUL, 0x966c7f6db12a99b7UL, + 0xace09390c537c5e1UL, 0x0b696063a1aa89eeUL, + /* 177 */ 0xebb03e97288c56e5UL, 0x432a9f9f938c8be8UL, + 0xa6a5a93d5b717f71UL, 0x1a5fb4c3e18f9d97UL, + /* 178 */ 0x1c94e7ad1c60cdceUL, 0xee202a43fc02c4a0UL, + 0x8dafe4d867c46a20UL, 0x0a10263c8ac27b58UL, + /* 179 */ 0xd0dea9dfe4432a4aUL, 0x856af87bbe9277c5UL, + 0xce8472acc212c71aUL, 0x6f151b6d9bbb1e91UL, + /* 180 */ 0x26776c527ceed56aUL, 0x7d211cb7fbf8faecUL, + 0x37ae66a6fd4609ccUL, 0x1f81b702d2770c42UL, + /* 181 */ 0x2fb0b057eac58392UL, 0xe1dd89fe29744e9dUL, + 0xc964f8eb17beb4f8UL, 0x29571073c9a2d41eUL, + /* 182 */ 0xa948a18981c0e254UL, 0x2df6369b65b22830UL, + 0xa33eb2d75fcfd3c6UL, 0x078cd6ec4199a01fUL, + /* 183 */ 0x4a584a41ad900d2fUL, 0x32142b78e2c74c52UL, + 0x68c4e8338431c978UL, 0x7f69ea9008689fc2UL, + /* 184 */ 0x52f2c81e46a38265UL, 0xfd78072d04a832fdUL, + 0x8cd7d5fa25359e94UL, 0x4de71b7454cc29d2UL, + /* 185 */ 0x42eb60ad1eda6ac9UL, 0x0aad37dfdbc09c3aUL, + 0x81004b71e33cc191UL, 0x44e6be345122803cUL, + /* 186 */ 0x03fe8388ba1920dbUL, 0xf5d57c32150db008UL, + 0x49c8c4281af60c29UL, 0x21edb518de701aeeUL, + /* 187 */ 0x7fb63e418f06dc99UL, 0xa4460d99c166d7b8UL, + 0x24dd5248ce520a83UL, 0x5ec3ad712b928358UL, + /* 188 */ 0x15022a5fbd17930fUL, 0xa4f64a77d82570e3UL, + 0x12bc8d6915783712UL, 0x498194c0fc620abbUL, + /* 189 */ 0x38a2d9d255686c82UL, 0x785c6bd9193e21f0UL, + 0xe4d5c81ab24a5484UL, 0x56307860b2e20989UL, + /* 190 */ 0x429d55f78b4d74c4UL, 0x22f1834643350131UL, + 0x1e60c24598c71fffUL, 0x59f2f014979983efUL, + /* 191 */ 0x46a47d56eb494a44UL, 0x3e22a854d636a18eUL, + 0xb346e15274491c3bUL, 0x2ceafd4e5390cde7UL, + /* 192 */ 0xba8a8538be0d6675UL, 0x4b9074bb50818e23UL, + 0xcbdab89085d304c3UL, 0x61a24fe0e56192c4UL, + /* 193 */ 0xcb7615e6db525bcbUL, 0xdd7d8c35a567e4caUL, + 0xe6b4153acafcdd69UL, 0x2d668e097f3c9766UL, + /* 194 */ 0xa57e7e265ce55ef0UL, 0x5d9f4e527cd4b967UL, + 0xfbc83606492fd1e5UL, 0x090d52beb7c3f7aeUL, + /* 195 */ 0x09b9515a1e7b4d7cUL, 0x1f266a2599da44c0UL, + 0xa1c49548e2c55504UL, 0x7ef04287126f15ccUL, + /* 196 */ 0xfed1659dbd30ef15UL, 0x8b4ab9eec4e0277bUL, + 0x884d6236a5df3291UL, 0x1fd96ea6bf5cf788UL, + /* 197 */ 0x42a161981f190d9aUL, 0x61d849507e6052c1UL, + 0x9fe113bf285a2cd5UL, 0x7c22d676dbad85d8UL, + /* 198 */ 0x82e770ed2bfbd27dUL, 0x4c05b2ece996f5a5UL, + 0xcd40a9c2b0900150UL, 0x5895319213d9bf64UL, + /* 199 */ 0xe7cc5d703fea2e08UL, 0xb50c491258e2188cUL, + 0xcce30baa48205bf0UL, 0x537c659ccfa32d62UL, + /* 200 */ 0x37b6623a98cfc088UL, 0xfe9bed1fa4d6aca4UL, + 0x04d29b8e56a8d1b0UL, 0x725f71c40b519575UL, + /* 201 */ 0x28c7f89cd0339ce6UL, 0x8367b14469ddc18bUL, + 0x883ada83a6a1652cUL, 0x585f1974034d6c17UL, + /* 202 */ 0x89cfb266f1b19188UL, 0xe63b4863e7c35217UL, + 0xd88c9da6b4c0526aUL, 0x3e035c9df0954635UL, + /* 203 */ 0xdd9d5412fb45de9dUL, 0xdd684532e4cff40dUL, + 0x4b5c999b151d671cUL, 0x2d8c2cc811e7f690UL, + /* 204 */ 0x7f54be1d90055d40UL, 0xa464c5df464aaf40UL, + 0x33979624f0e917beUL, 0x2c018dc527356b30UL, + /* 205 */ 0xa5415024e330b3d4UL, 0x73ff3d96691652d3UL, + 0x94ec42c4ef9b59f1UL, 0x0747201618d08e5aUL, + /* 206 */ 0x4d6ca48aca411c53UL, 0x66415f2fcfa66119UL, + 0x9c4dd40051e227ffUL, 0x59810bc09a02f7ebUL, + /* 207 */ 0x2a7eb171b3dc101dUL, 0x441c5ab99ffef68eUL, + 0x32025c9b93b359eaUL, 0x5e8ce0a71e9d112fUL, + /* 208 */ 0xbfcccb92429503fdUL, 0xd271ba752f095d55UL, + 0x345ead5e972d091eUL, 0x18c8df11a83103baUL, + /* 209 */ 0x90cd949a9aed0f4cUL, 0xc5d1f4cb6660e37eUL, + 0xb8cac52d56c52e0bUL, 0x6e42e400c5808e0dUL, + /* 210 */ 0xa3b46966eeaefd23UL, 0x0c4f1f0be39ecdcaUL, + 0x189dc8c9d683a51dUL, 0x51f27f054c09351bUL, + /* 211 */ 0x4c487ccd2a320682UL, 0x587ea95bb3df1c96UL, + 0xc8ccf79e555cb8e8UL, 0x547dc829a206d73dUL, + /* 212 */ 0xb822a6cd80c39b06UL, 0xe96d54732000d4c6UL, + 0x28535b6f91463b4dUL, 0x228f4660e2486e1dUL, + /* 213 */ 0x98799538de8d3abfUL, 0x8cd8330045ebca6eUL, + 0x79952a008221e738UL, 0x4322e1a7535cd2bbUL, + /* 214 */ 0xb114c11819d1801cUL, 0x2016e4d84f3f5ec7UL, + 0xdd0e2df409260f4cUL, 0x5ec362c0ae5f7266UL, + /* 215 */ 0xc0462b18b8b2b4eeUL, 0x7cc8d950274d1afbUL, + 0xf25f7105436b02d2UL, 0x43bbf8dcbff9ccd3UL, + /* 216 */ 0xb6ad1767a039e9dfUL, 0xb0714da8f69d3583UL, + 0x5e55fa18b42931f5UL, 0x4ed5558f33c60961UL, + /* 217 */ 0x1fe37901c647a5ddUL, 0x593ddf1f8081d357UL, + 0x0249a4fd813fd7a6UL, 0x69acca274e9caf61UL, + /* 218 */ 0x047ba3ea330721c9UL, 0x83423fc20e7e1ea0UL, + 0x1df4c0af01314a60UL, 0x09a62dab89289527UL, + /* 219 */ 0xa5b325a49cc6cb00UL, 0xe94b5dc654b56cb6UL, + 0x3be28779adc994a0UL, 0x4296e8f8ba3a4aadUL, + /* 220 */ 0x328689761e451eabUL, 0x2e4d598bff59594aUL, + 0x49b96853d7a7084aUL, 0x4980a319601420a8UL, + /* 221 */ 0x9565b9e12f552c42UL, 0x8a5318db7100fe96UL, + 0x05c90b4d43add0d7UL, 0x538b4cd66a5d4edaUL, + /* 222 */ 0xf4e94fc3e89f039fUL, 0x592c9af26f618045UL, + 0x08a36eb5fd4b9550UL, 0x25fffaf6c2ed1419UL, + /* 223 */ 0x34434459cc79d354UL, 0xeeecbfb4b1d5476bUL, + 0xddeb34a061615d99UL, 0x5129cecceb64b773UL, + /* 224 */ 0xee43215894993520UL, 0x772f9c7cf14c0b3bUL, + 0xd2e2fce306bedad5UL, 0x715f42b546f06a97UL, + /* 225 */ 0x434ecdceda5b5f1aUL, 0x0da17115a49741a9UL, + 0x680bd77c73edad2eUL, 0x487c02354edd9041UL, + /* 226 */ 0xb8efeff3a70ed9c4UL, 0x56a32aa3e857e302UL, + 0xdf3a68bd48a2a5a0UL, 0x07f650b73176c444UL, + /* 227 */ 0xe38b9b1626e0ccb1UL, 0x79e053c18b09fb36UL, + 0x56d90319c9f94964UL, 0x1ca941e7ac9ff5c4UL, + /* 228 */ 0x49c4df29162fa0bbUL, 0x8488cf3282b33305UL, + 0x95dfda14cabb437dUL, 0x3391f78264d5ad86UL, + /* 229 */ 0x729ae06ae2b5095dUL, 0xd58a58d73259a946UL, + 0xe9834262d13921edUL, 0x27fedafaa54bb592UL, + /* 230 */ 0xa99dc5b829ad48bbUL, 0x5f025742499ee260UL, + 0x802c8ecd5d7513fdUL, 0x78ceb3ef3f6dd938UL, + /* 231 */ 0xc342f44f8a135d94UL, 0x7b9edb44828cdda3UL, + 0x9436d11a0537cfe7UL, 0x5064b164ec1ab4c8UL, + /* 232 */ 0x7020eccfd37eb2fcUL, 0x1f31ea3ed90d25fcUL, + 0x1b930d7bdfa1bb34UL, 0x5344467a48113044UL, + /* 233 */ 0x70073170f25e6dfbUL, 0xe385dc1a50114cc8UL, + 0x2348698ac8fc4f00UL, 0x2a77a55284dd40d8UL, + /* 234 */ 0xfe06afe0c98c6ce4UL, 0xc235df96dddfd6e4UL, + 0x1428d01e33bf1ed3UL, 0x785768ec9300bdafUL, + /* 235 */ 0x9702e57a91deb63bUL, 0x61bdb8bfe5ce8b80UL, + 0x645b426f3d1d58acUL, 0x4804a82227a557bcUL, + /* 236 */ 0x8e57048ab44d2601UL, 0x68d6501a4b3a6935UL, + 0xc39c9ec3f9e1c293UL, 0x4172f257d4de63e2UL, + /* 237 */ 0xd368b450330c6401UL, 0x040d3017418f2391UL, + 0x2c34bb6090b7d90dUL, 0x16f649228fdfd51fUL, + /* 238 */ 0xbea6818e2b928ef5UL, 0xe28ccf91cdc11e72UL, + 0x594aaa68e77a36cdUL, 0x313034806c7ffd0fUL, + /* 239 */ 0x8a9d27ac2249bd65UL, 0x19a3b464018e9512UL, + 0xc26ccff352b37ec7UL, 0x056f68341d797b21UL, + /* 240 */ 0x5e79d6757efd2327UL, 0xfabdbcb6553afe15UL, + 0xd3e7222c6eaf5a60UL, 0x7046c76d4dae743bUL, + /* 241 */ 0x660be872b18d4a55UL, 0x19992518574e1496UL, + 0xc103053a302bdcbbUL, 0x3ed8e9800b218e8eUL, + /* 242 */ 0x7b0b9239fa75e03eUL, 0xefe9fb684633c083UL, + 0x98a35fbe391a7793UL, 0x6065510fe2d0fe34UL, + /* 243 */ 0x55cb668548abad0cUL, 0xb4584548da87e527UL, + 0x2c43ecea0107c1ddUL, 0x526028809372de35UL, + /* 244 */ 0x3415c56af9213b1fUL, 0x5bee1a4d017e98dbUL, + 0x13f6b105b5cf709bUL, 0x5ff20e3482b29ab6UL, + /* 245 */ 0x0aa29c75cc2e6c90UL, 0xfc7d73ca3a70e206UL, + 0x899fc38fc4b5c515UL, 0x250386b124ffc207UL, + /* 246 */ 0x54ea28d5ae3d2b56UL, 0x9913149dd6de60ceUL, + 0x16694fc58f06d6c1UL, 0x46b23975eb018fc7UL, + /* 247 */ 0x470a6a0fb4b7b4e2UL, 0x5d92475a8f7253deUL, + 0xabeee5b52fbd3adbUL, 0x7fa20801a0806968UL, + /* 248 */ 0x76f3faf19f7714d2UL, 0xb3e840c12f4660c3UL, + 0x0fb4cd8df212744eUL, 0x4b065a251d3a2dd2UL, + /* 249 */ 0x5cebde383d77cd4aUL, 0x6adf39df882c9cb1UL, + 0xa2dd242eb09af759UL, 0x3147c0e50e5f6422UL, + /* 250 */ 0x164ca5101d1350dbUL, 0xf8d13479c33fc962UL, + 0xe640ce4d13e5da08UL, 0x4bdee0c45061f8baUL, + /* 251 */ 0xd7c46dc1a4edb1c9UL, 0x5514d7b6437fd98aUL, + 0x58942f6bb2a1c00bUL, 0x2dffb2ab1d70710eUL, + /* 252 */ 0xccdfcf2fc18b6d68UL, 0xa8ebcba8b7806167UL, + 0x980697f95e2937e3UL, 0x02fbba1cd0126e8cUL +}; + +/* c is two 512-bit products: c0[0:7]=a0[0:3]*b0[0:3] and c1[8:15]=a1[4:7]*b1[4:7] + * a is two 256-bit integers: a0[0:3] and a1[4:7] + * b is two 256-bit integers: b0[0:3] and b1[4:7] + */ +static void mul2_256x256_integer_adx(u64 *const c, const u64 *const a, + const u64 *const b) +{ + asm volatile( + "xorl %%r14d, %%r14d ;" + "movq (%1), %%rdx; " /* A[0] */ + "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ + "xorl %%r10d, %%r10d ;" + "movq %%r8, (%0) ;" + "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ + "adox %%r10, %%r15 ;" + "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ + "adox %%r8, %%rax ;" + "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ + "adox %%r10, %%rbx ;" + /******************************************/ + "adox %%r14, %%rcx ;" + + "movq 8(%1), %%rdx; " /* A[1] */ + "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ + "adox %%r15, %%r8 ;" + "movq %%r8, 8(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ + "adox %%r10, %%r9 ;" + "adcx %%r9, %%rax ;" + "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ + "adox %%r8, %%r11 ;" + "adcx %%r11, %%rbx ;" + "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ + "adox %%r10, %%r13 ;" + "adcx %%r13, %%rcx ;" + /******************************************/ + "adox %%r14, %%r15 ;" + "adcx %%r14, %%r15 ;" + + "movq 16(%1), %%rdx; " /* A[2] */ + "xorl %%r10d, %%r10d ;" + "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ + "adox %%rax, %%r8 ;" + "movq %%r8, 16(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ + "adox %%r10, %%r9 ;" + "adcx %%r9, %%rbx ;" + "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ + "adox %%r8, %%r11 ;" + "adcx %%r11, %%rcx ;" + "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ + "adox %%r10, %%r13 ;" + "adcx %%r13, %%r15 ;" + /******************************************/ + "adox %%r14, %%rax ;" + "adcx %%r14, %%rax ;" + + "movq 24(%1), %%rdx; " /* A[3] */ + "xorl %%r10d, %%r10d ;" + "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ + "adox %%rbx, %%r8 ;" + "movq %%r8, 24(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ + "adox %%r10, %%r9 ;" + "adcx %%r9, %%rcx ;" + "movq %%rcx, 32(%0) ;" + "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ + "adox %%r8, %%r11 ;" + "adcx %%r11, %%r15 ;" + "movq %%r15, 40(%0) ;" + "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ + "adox %%r10, %%r13 ;" + "adcx %%r13, %%rax ;" + "movq %%rax, 48(%0) ;" + /******************************************/ + "adox %%r14, %%rbx ;" + "adcx %%r14, %%rbx ;" + "movq %%rbx, 56(%0) ;" + + "movq 32(%1), %%rdx; " /* C[0] */ + "mulx 32(%2), %%r8, %%r15; " /* C[0]*D[0] */ + "xorl %%r10d, %%r10d ;" + "movq %%r8, 64(%0);" + "mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */ + "adox %%r10, %%r15 ;" + "mulx 48(%2), %%r8, %%rbx; " /* C[0]*D[2] */ + "adox %%r8, %%rax ;" + "mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */ + "adox %%r10, %%rbx ;" + /******************************************/ + "adox %%r14, %%rcx ;" + + "movq 40(%1), %%rdx; " /* C[1] */ + "xorl %%r10d, %%r10d ;" + "mulx 32(%2), %%r8, %%r9; " /* C[1]*D[0] */ + "adox %%r15, %%r8 ;" + "movq %%r8, 72(%0);" + "mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */ + "adox %%r10, %%r9 ;" + "adcx %%r9, %%rax ;" + "mulx 48(%2), %%r8, %%r13; " /* C[1]*D[2] */ + "adox %%r8, %%r11 ;" + "adcx %%r11, %%rbx ;" + "mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */ + "adox %%r10, %%r13 ;" + "adcx %%r13, %%rcx ;" + /******************************************/ + "adox %%r14, %%r15 ;" + "adcx %%r14, %%r15 ;" + + "movq 48(%1), %%rdx; " /* C[2] */ + "xorl %%r10d, %%r10d ;" + "mulx 32(%2), %%r8, %%r9; " /* C[2]*D[0] */ + "adox %%rax, %%r8 ;" + "movq %%r8, 80(%0);" + "mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */ + "adox %%r10, %%r9 ;" + "adcx %%r9, %%rbx ;" + "mulx 48(%2), %%r8, %%r13; " /* C[2]*D[2] */ + "adox %%r8, %%r11 ;" + "adcx %%r11, %%rcx ;" + "mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */ + "adox %%r10, %%r13 ;" + "adcx %%r13, %%r15 ;" + /******************************************/ + "adox %%r14, %%rax ;" + "adcx %%r14, %%rax ;" + + "movq 56(%1), %%rdx; " /* C[3] */ + "xorl %%r10d, %%r10d ;" + "mulx 32(%2), %%r8, %%r9; " /* C[3]*D[0] */ + "adox %%rbx, %%r8 ;" + "movq %%r8, 88(%0);" + "mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */ + "adox %%r10, %%r9 ;" + "adcx %%r9, %%rcx ;" + "movq %%rcx, 96(%0) ;" + "mulx 48(%2), %%r8, %%r13; " /* C[3]*D[2] */ + "adox %%r8, %%r11 ;" + "adcx %%r11, %%r15 ;" + "movq %%r15, 104(%0) ;" + "mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */ + "adox %%r10, %%r13 ;" + "adcx %%r13, %%rax ;" + "movq %%rax, 112(%0) ;" + /******************************************/ + "adox %%r14, %%rbx ;" + "adcx %%r14, %%rbx ;" + "movq %%rbx, 120(%0) ;" + : + : "r"(c), "r"(a), "r"(b) + : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", + "%r10", "%r11", "%r13", "%r14", "%r15"); +} + +static void mul2_256x256_integer_bmi2(u64 *const c, const u64 *const a, + const u64 *const b) +{ + asm volatile( + "movq (%1), %%rdx; " /* A[0] */ + "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ + "movq %%r8, (%0) ;" + "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ + "addq %%r10, %%r15 ;" + "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ + "adcq %%r8, %%rax ;" + "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ + "adcq %%r10, %%rbx ;" + /******************************************/ + "adcq $0, %%rcx ;" + + "movq 8(%1), %%rdx; " /* A[1] */ + "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ + "addq %%r15, %%r8 ;" + "movq %%r8, 8(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ + "adcq %%r10, %%r9 ;" + "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ + "adcq %%r8, %%r11 ;" + "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ + "adcq %%r10, %%r13 ;" + /******************************************/ + "adcq $0, %%r15 ;" + + "addq %%r9, %%rax ;" + "adcq %%r11, %%rbx ;" + "adcq %%r13, %%rcx ;" + "adcq $0, %%r15 ;" + + "movq 16(%1), %%rdx; " /* A[2] */ + "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ + "addq %%rax, %%r8 ;" + "movq %%r8, 16(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ + "adcq %%r10, %%r9 ;" + "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ + "adcq %%r8, %%r11 ;" + "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ + "adcq %%r10, %%r13 ;" + /******************************************/ + "adcq $0, %%rax ;" + + "addq %%r9, %%rbx ;" + "adcq %%r11, %%rcx ;" + "adcq %%r13, %%r15 ;" + "adcq $0, %%rax ;" + + "movq 24(%1), %%rdx; " /* A[3] */ + "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ + "addq %%rbx, %%r8 ;" + "movq %%r8, 24(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ + "adcq %%r10, %%r9 ;" + "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ + "adcq %%r8, %%r11 ;" + "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ + "adcq %%r10, %%r13 ;" + /******************************************/ + "adcq $0, %%rbx ;" + + "addq %%r9, %%rcx ;" + "movq %%rcx, 32(%0) ;" + "adcq %%r11, %%r15 ;" + "movq %%r15, 40(%0) ;" + "adcq %%r13, %%rax ;" + "movq %%rax, 48(%0) ;" + "adcq $0, %%rbx ;" + "movq %%rbx, 56(%0) ;" + + "movq 32(%1), %%rdx; " /* C[0] */ + "mulx 32(%2), %%r8, %%r15; " /* C[0]*D[0] */ + "movq %%r8, 64(%0) ;" + "mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */ + "addq %%r10, %%r15 ;" + "mulx 48(%2), %%r8, %%rbx; " /* C[0]*D[2] */ + "adcq %%r8, %%rax ;" + "mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */ + "adcq %%r10, %%rbx ;" + /******************************************/ + "adcq $0, %%rcx ;" + + "movq 40(%1), %%rdx; " /* C[1] */ + "mulx 32(%2), %%r8, %%r9; " /* C[1]*D[0] */ + "addq %%r15, %%r8 ;" + "movq %%r8, 72(%0) ;" + "mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */ + "adcq %%r10, %%r9 ;" + "mulx 48(%2), %%r8, %%r13; " /* C[1]*D[2] */ + "adcq %%r8, %%r11 ;" + "mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */ + "adcq %%r10, %%r13 ;" + /******************************************/ + "adcq $0, %%r15 ;" + + "addq %%r9, %%rax ;" + "adcq %%r11, %%rbx ;" + "adcq %%r13, %%rcx ;" + "adcq $0, %%r15 ;" + + "movq 48(%1), %%rdx; " /* C[2] */ + "mulx 32(%2), %%r8, %%r9; " /* C[2]*D[0] */ + "addq %%rax, %%r8 ;" + "movq %%r8, 80(%0) ;" + "mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */ + "adcq %%r10, %%r9 ;" + "mulx 48(%2), %%r8, %%r13; " /* C[2]*D[2] */ + "adcq %%r8, %%r11 ;" + "mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */ + "adcq %%r10, %%r13 ;" + /******************************************/ + "adcq $0, %%rax ;" + + "addq %%r9, %%rbx ;" + "adcq %%r11, %%rcx ;" + "adcq %%r13, %%r15 ;" + "adcq $0, %%rax ;" + + "movq 56(%1), %%rdx; " /* C[3] */ + "mulx 32(%2), %%r8, %%r9; " /* C[3]*D[0] */ + "addq %%rbx, %%r8 ;" + "movq %%r8, 88(%0) ;" + "mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */ + "adcq %%r10, %%r9 ;" + "mulx 48(%2), %%r8, %%r13; " /* C[3]*D[2] */ + "adcq %%r8, %%r11 ;" + "mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */ + "adcq %%r10, %%r13 ;" + /******************************************/ + "adcq $0, %%rbx ;" + + "addq %%r9, %%rcx ;" + "movq %%rcx, 96(%0) ;" + "adcq %%r11, %%r15 ;" + "movq %%r15, 104(%0) ;" + "adcq %%r13, %%rax ;" + "movq %%rax, 112(%0) ;" + "adcq $0, %%rbx ;" + "movq %%rbx, 120(%0) ;" + : + : "r"(c), "r"(a), "r"(b) + : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", + "%r10", "%r11", "%r13", "%r15"); +} + +static void sqr2_256x256_integer_adx(u64 *const c, const u64 *const a) +{ + asm volatile( + "movq (%1), %%rdx ;" /* A[0] */ + "mulx 8(%1), %%r8, %%r14 ;" /* A[1]*A[0] */ + "xorl %%r15d, %%r15d;" + "mulx 16(%1), %%r9, %%r10 ;" /* A[2]*A[0] */ + "adcx %%r14, %%r9 ;" + "mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */ + "adcx %%rax, %%r10 ;" + "movq 24(%1), %%rdx ;" /* A[3] */ + "mulx 8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */ + "adcx %%rcx, %%r11 ;" + "mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */ + "adcx %%rax, %%rbx ;" + "movq 8(%1), %%rdx ;" /* A[1] */ + "adcx %%r15, %%r13 ;" + "mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */ + "movq $0, %%r14 ;" + /******************************************/ + "adcx %%r15, %%r14 ;" + + "xorl %%r15d, %%r15d;" + "adox %%rax, %%r10 ;" + "adcx %%r8, %%r8 ;" + "adox %%rcx, %%r11 ;" + "adcx %%r9, %%r9 ;" + "adox %%r15, %%rbx ;" + "adcx %%r10, %%r10 ;" + "adox %%r15, %%r13 ;" + "adcx %%r11, %%r11 ;" + "adox %%r15, %%r14 ;" + "adcx %%rbx, %%rbx ;" + "adcx %%r13, %%r13 ;" + "adcx %%r14, %%r14 ;" + + "movq (%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ + /*******************/ + "movq %%rax, 0(%0) ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, 8(%0) ;" + "movq 8(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ + "adcq %%rax, %%r9 ;" + "movq %%r9, 16(%0) ;" + "adcq %%rcx, %%r10 ;" + "movq %%r10, 24(%0) ;" + "movq 16(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ + "adcq %%rax, %%r11 ;" + "movq %%r11, 32(%0) ;" + "adcq %%rcx, %%rbx ;" + "movq %%rbx, 40(%0) ;" + "movq 24(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ + "adcq %%rax, %%r13 ;" + "movq %%r13, 48(%0) ;" + "adcq %%rcx, %%r14 ;" + "movq %%r14, 56(%0) ;" + + + "movq 32(%1), %%rdx ;" /* B[0] */ + "mulx 40(%1), %%r8, %%r14 ;" /* B[1]*B[0] */ + "xorl %%r15d, %%r15d;" + "mulx 48(%1), %%r9, %%r10 ;" /* B[2]*B[0] */ + "adcx %%r14, %%r9 ;" + "mulx 56(%1), %%rax, %%rcx ;" /* B[3]*B[0] */ + "adcx %%rax, %%r10 ;" + "movq 56(%1), %%rdx ;" /* B[3] */ + "mulx 40(%1), %%r11, %%rbx ;" /* B[1]*B[3] */ + "adcx %%rcx, %%r11 ;" + "mulx 48(%1), %%rax, %%r13 ;" /* B[2]*B[3] */ + "adcx %%rax, %%rbx ;" + "movq 40(%1), %%rdx ;" /* B[1] */ + "adcx %%r15, %%r13 ;" + "mulx 48(%1), %%rax, %%rcx ;" /* B[2]*B[1] */ + "movq $0, %%r14 ;" + /******************************************/ + "adcx %%r15, %%r14 ;" + + "xorl %%r15d, %%r15d;" + "adox %%rax, %%r10 ;" + "adcx %%r8, %%r8 ;" + "adox %%rcx, %%r11 ;" + "adcx %%r9, %%r9 ;" + "adox %%r15, %%rbx ;" + "adcx %%r10, %%r10 ;" + "adox %%r15, %%r13 ;" + "adcx %%r11, %%r11 ;" + "adox %%r15, %%r14 ;" + "adcx %%rbx, %%rbx ;" + "adcx %%r13, %%r13 ;" + "adcx %%r14, %%r14 ;" + + "movq 32(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* B[0]^2 */ + /*******************/ + "movq %%rax, 64(%0) ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, 72(%0) ;" + "movq 40(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* B[1]^2 */ + "adcq %%rax, %%r9 ;" + "movq %%r9, 80(%0) ;" + "adcq %%rcx, %%r10 ;" + "movq %%r10, 88(%0) ;" + "movq 48(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* B[2]^2 */ + "adcq %%rax, %%r11 ;" + "movq %%r11, 96(%0) ;" + "adcq %%rcx, %%rbx ;" + "movq %%rbx, 104(%0) ;" + "movq 56(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* B[3]^2 */ + "adcq %%rax, %%r13 ;" + "movq %%r13, 112(%0) ;" + "adcq %%rcx, %%r14 ;" + "movq %%r14, 120(%0) ;" + : + : "r"(c), "r"(a) + : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", + "%r10", "%r11", "%r13", "%r14", "%r15"); +} + +static void sqr2_256x256_integer_bmi2(u64 *const c, const u64 *const a) +{ + asm volatile( + "movq 8(%1), %%rdx ;" /* A[1] */ + "mulx (%1), %%r8, %%r9 ;" /* A[0]*A[1] */ + "mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */ + "mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */ + + "movq 16(%1), %%rdx ;" /* A[2] */ + "mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */ + "mulx (%1), %%rax, %%rdx ;" /* A[0]*A[2] */ + + "addq %%rax, %%r9 ;" + "adcq %%rdx, %%r10 ;" + "adcq %%rcx, %%r11 ;" + "adcq %%r14, %%r15 ;" + "adcq $0, %%r13 ;" + "movq $0, %%r14 ;" + "adcq $0, %%r14 ;" + + "movq (%1), %%rdx ;" /* A[0] */ + "mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */ + + "addq %%rax, %%r10 ;" + "adcq %%rcx, %%r11 ;" + "adcq $0, %%r15 ;" + "adcq $0, %%r13 ;" + "adcq $0, %%r14 ;" + + "shldq $1, %%r13, %%r14 ;" + "shldq $1, %%r15, %%r13 ;" + "shldq $1, %%r11, %%r15 ;" + "shldq $1, %%r10, %%r11 ;" + "shldq $1, %%r9, %%r10 ;" + "shldq $1, %%r8, %%r9 ;" + "shlq $1, %%r8 ;" + + /*******************/ + "mulx %%rdx, %%rax, %%rcx ; " /* A[0]^2 */ + /*******************/ + "movq %%rax, 0(%0) ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, 8(%0) ;" + "movq 8(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ; " /* A[1]^2 */ + "adcq %%rax, %%r9 ;" + "movq %%r9, 16(%0) ;" + "adcq %%rcx, %%r10 ;" + "movq %%r10, 24(%0) ;" + "movq 16(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ; " /* A[2]^2 */ + "adcq %%rax, %%r11 ;" + "movq %%r11, 32(%0) ;" + "adcq %%rcx, %%r15 ;" + "movq %%r15, 40(%0) ;" + "movq 24(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ; " /* A[3]^2 */ + "adcq %%rax, %%r13 ;" + "movq %%r13, 48(%0) ;" + "adcq %%rcx, %%r14 ;" + "movq %%r14, 56(%0) ;" + + "movq 40(%1), %%rdx ;" /* B[1] */ + "mulx 32(%1), %%r8, %%r9 ;" /* B[0]*B[1] */ + "mulx 48(%1), %%r10, %%r11 ;" /* B[2]*B[1] */ + "mulx 56(%1), %%rcx, %%r14 ;" /* B[3]*B[1] */ + + "movq 48(%1), %%rdx ;" /* B[2] */ + "mulx 56(%1), %%r15, %%r13 ;" /* B[3]*B[2] */ + "mulx 32(%1), %%rax, %%rdx ;" /* B[0]*B[2] */ + + "addq %%rax, %%r9 ;" + "adcq %%rdx, %%r10 ;" + "adcq %%rcx, %%r11 ;" + "adcq %%r14, %%r15 ;" + "adcq $0, %%r13 ;" + "movq $0, %%r14 ;" + "adcq $0, %%r14 ;" + + "movq 32(%1), %%rdx ;" /* B[0] */ + "mulx 56(%1), %%rax, %%rcx ;" /* B[0]*B[3] */ + + "addq %%rax, %%r10 ;" + "adcq %%rcx, %%r11 ;" + "adcq $0, %%r15 ;" + "adcq $0, %%r13 ;" + "adcq $0, %%r14 ;" + + "shldq $1, %%r13, %%r14 ;" + "shldq $1, %%r15, %%r13 ;" + "shldq $1, %%r11, %%r15 ;" + "shldq $1, %%r10, %%r11 ;" + "shldq $1, %%r9, %%r10 ;" + "shldq $1, %%r8, %%r9 ;" + "shlq $1, %%r8 ;" + + /*******************/ + "mulx %%rdx, %%rax, %%rcx ; " /* B[0]^2 */ + /*******************/ + "movq %%rax, 64(%0) ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, 72(%0) ;" + "movq 40(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ; " /* B[1]^2 */ + "adcq %%rax, %%r9 ;" + "movq %%r9, 80(%0) ;" + "adcq %%rcx, %%r10 ;" + "movq %%r10, 88(%0) ;" + "movq 48(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ; " /* B[2]^2 */ + "adcq %%rax, %%r11 ;" + "movq %%r11, 96(%0) ;" + "adcq %%rcx, %%r15 ;" + "movq %%r15, 104(%0) ;" + "movq 56(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ; " /* B[3]^2 */ + "adcq %%rax, %%r13 ;" + "movq %%r13, 112(%0) ;" + "adcq %%rcx, %%r14 ;" + "movq %%r14, 120(%0) ;" + : + : "r"(c), "r"(a) + : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", + "%r11", "%r13", "%r14", "%r15"); +} + +static void red_eltfp25519_2w_adx(u64 *const c, const u64 *const a) +{ + asm volatile( + "movl $38, %%edx; " /* 2*c = 38 = 2^256 */ + "mulx 32(%1), %%r8, %%r10; " /* c*C[4] */ + "xorl %%ebx, %%ebx ;" + "adox (%1), %%r8 ;" + "mulx 40(%1), %%r9, %%r11; " /* c*C[5] */ + "adcx %%r10, %%r9 ;" + "adox 8(%1), %%r9 ;" + "mulx 48(%1), %%r10, %%rax; " /* c*C[6] */ + "adcx %%r11, %%r10 ;" + "adox 16(%1), %%r10 ;" + "mulx 56(%1), %%r11, %%rcx; " /* c*C[7] */ + "adcx %%rax, %%r11 ;" + "adox 24(%1), %%r11 ;" + /***************************************/ + "adcx %%rbx, %%rcx ;" + "adox %%rbx, %%rcx ;" + "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ + "adcx %%rcx, %%r8 ;" + "adcx %%rbx, %%r9 ;" + "movq %%r9, 8(%0) ;" + "adcx %%rbx, %%r10 ;" + "movq %%r10, 16(%0) ;" + "adcx %%rbx, %%r11 ;" + "movq %%r11, 24(%0) ;" + "mov $0, %%ecx ;" + "cmovc %%edx, %%ecx ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, (%0) ;" + + "mulx 96(%1), %%r8, %%r10; " /* c*C[4] */ + "xorl %%ebx, %%ebx ;" + "adox 64(%1), %%r8 ;" + "mulx 104(%1), %%r9, %%r11; " /* c*C[5] */ + "adcx %%r10, %%r9 ;" + "adox 72(%1), %%r9 ;" + "mulx 112(%1), %%r10, %%rax; " /* c*C[6] */ + "adcx %%r11, %%r10 ;" + "adox 80(%1), %%r10 ;" + "mulx 120(%1), %%r11, %%rcx; " /* c*C[7] */ + "adcx %%rax, %%r11 ;" + "adox 88(%1), %%r11 ;" + /****************************************/ + "adcx %%rbx, %%rcx ;" + "adox %%rbx, %%rcx ;" + "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ + "adcx %%rcx, %%r8 ;" + "adcx %%rbx, %%r9 ;" + "movq %%r9, 40(%0) ;" + "adcx %%rbx, %%r10 ;" + "movq %%r10, 48(%0) ;" + "adcx %%rbx, %%r11 ;" + "movq %%r11, 56(%0) ;" + "mov $0, %%ecx ;" + "cmovc %%edx, %%ecx ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, 32(%0) ;" + : + : "r"(c), "r"(a) + : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", + "%r10", "%r11"); +} + +static void red_eltfp25519_2w_bmi2(u64 *const c, const u64 *const a) +{ + asm volatile( + "movl $38, %%edx ; " /* 2*c = 38 = 2^256 */ + "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ + "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ + "addq %%r10, %%r9 ;" + "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ + "adcq %%r11, %%r10 ;" + "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ + "adcq %%rax, %%r11 ;" + /***************************************/ + "adcq $0, %%rcx ;" + "addq (%1), %%r8 ;" + "adcq 8(%1), %%r9 ;" + "adcq 16(%1), %%r10 ;" + "adcq 24(%1), %%r11 ;" + "adcq $0, %%rcx ;" + "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ + "addq %%rcx, %%r8 ;" + "adcq $0, %%r9 ;" + "movq %%r9, 8(%0) ;" + "adcq $0, %%r10 ;" + "movq %%r10, 16(%0) ;" + "adcq $0, %%r11 ;" + "movq %%r11, 24(%0) ;" + "mov $0, %%ecx ;" + "cmovc %%edx, %%ecx ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, (%0) ;" + + "mulx 96(%1), %%r8, %%r10 ;" /* c*C[4] */ + "mulx 104(%1), %%r9, %%r11 ;" /* c*C[5] */ + "addq %%r10, %%r9 ;" + "mulx 112(%1), %%r10, %%rax ;" /* c*C[6] */ + "adcq %%r11, %%r10 ;" + "mulx 120(%1), %%r11, %%rcx ;" /* c*C[7] */ + "adcq %%rax, %%r11 ;" + /****************************************/ + "adcq $0, %%rcx ;" + "addq 64(%1), %%r8 ;" + "adcq 72(%1), %%r9 ;" + "adcq 80(%1), %%r10 ;" + "adcq 88(%1), %%r11 ;" + "adcq $0, %%rcx ;" + "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ + "addq %%rcx, %%r8 ;" + "adcq $0, %%r9 ;" + "movq %%r9, 40(%0) ;" + "adcq $0, %%r10 ;" + "movq %%r10, 48(%0) ;" + "adcq $0, %%r11 ;" + "movq %%r11, 56(%0) ;" + "mov $0, %%ecx ;" + "cmovc %%edx, %%ecx ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, 32(%0) ;" + : + : "r"(c), "r"(a) + : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", + "%r11"); +} + +static void mul_256x256_integer_adx(u64 *const c, const u64 *const a, + const u64 *const b) +{ + asm volatile( + "movq (%1), %%rdx; " /* A[0] */ + "mulx (%2), %%r8, %%r9; " /* A[0]*B[0] */ + "xorl %%r10d, %%r10d ;" + "movq %%r8, (%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[0]*B[1] */ + "adox %%r9, %%r10 ;" + "movq %%r10, 8(%0) ;" + "mulx 16(%2), %%r15, %%r13; " /* A[0]*B[2] */ + "adox %%r11, %%r15 ;" + "mulx 24(%2), %%r14, %%rdx; " /* A[0]*B[3] */ + "adox %%r13, %%r14 ;" + "movq $0, %%rax ;" + /******************************************/ + "adox %%rdx, %%rax ;" + + "movq 8(%1), %%rdx; " /* A[1] */ + "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ + "xorl %%r10d, %%r10d ;" + "adcx 8(%0), %%r8 ;" + "movq %%r8, 8(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ + "adox %%r9, %%r10 ;" + "adcx %%r15, %%r10 ;" + "movq %%r10, 16(%0) ;" + "mulx 16(%2), %%r15, %%r13; " /* A[1]*B[2] */ + "adox %%r11, %%r15 ;" + "adcx %%r14, %%r15 ;" + "movq $0, %%r8 ;" + "mulx 24(%2), %%r14, %%rdx; " /* A[1]*B[3] */ + "adox %%r13, %%r14 ;" + "adcx %%rax, %%r14 ;" + "movq $0, %%rax ;" + /******************************************/ + "adox %%rdx, %%rax ;" + "adcx %%r8, %%rax ;" + + "movq 16(%1), %%rdx; " /* A[2] */ + "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ + "xorl %%r10d, %%r10d ;" + "adcx 16(%0), %%r8 ;" + "movq %%r8, 16(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ + "adox %%r9, %%r10 ;" + "adcx %%r15, %%r10 ;" + "movq %%r10, 24(%0) ;" + "mulx 16(%2), %%r15, %%r13; " /* A[2]*B[2] */ + "adox %%r11, %%r15 ;" + "adcx %%r14, %%r15 ;" + "movq $0, %%r8 ;" + "mulx 24(%2), %%r14, %%rdx; " /* A[2]*B[3] */ + "adox %%r13, %%r14 ;" + "adcx %%rax, %%r14 ;" + "movq $0, %%rax ;" + /******************************************/ + "adox %%rdx, %%rax ;" + "adcx %%r8, %%rax ;" + + "movq 24(%1), %%rdx; " /* A[3] */ + "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ + "xorl %%r10d, %%r10d ;" + "adcx 24(%0), %%r8 ;" + "movq %%r8, 24(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ + "adox %%r9, %%r10 ;" + "adcx %%r15, %%r10 ;" + "movq %%r10, 32(%0) ;" + "mulx 16(%2), %%r15, %%r13; " /* A[3]*B[2] */ + "adox %%r11, %%r15 ;" + "adcx %%r14, %%r15 ;" + "movq %%r15, 40(%0) ;" + "movq $0, %%r8 ;" + "mulx 24(%2), %%r14, %%rdx; " /* A[3]*B[3] */ + "adox %%r13, %%r14 ;" + "adcx %%rax, %%r14 ;" + "movq %%r14, 48(%0) ;" + "movq $0, %%rax ;" + /******************************************/ + "adox %%rdx, %%rax ;" + "adcx %%r8, %%rax ;" + "movq %%rax, 56(%0) ;" + : + : "r"(c), "r"(a), "r"(b) + : "memory", "cc", "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", + "%r13", "%r14", "%r15"); +} + +static void mul_256x256_integer_bmi2(u64 *const c, const u64 *const a, + const u64 *const b) +{ + asm volatile( + "movq (%1), %%rdx; " /* A[0] */ + "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ + "movq %%r8, (%0) ;" + "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ + "addq %%r10, %%r15 ;" + "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ + "adcq %%r8, %%rax ;" + "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ + "adcq %%r10, %%rbx ;" + /******************************************/ + "adcq $0, %%rcx ;" + + "movq 8(%1), %%rdx; " /* A[1] */ + "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ + "addq %%r15, %%r8 ;" + "movq %%r8, 8(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ + "adcq %%r10, %%r9 ;" + "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ + "adcq %%r8, %%r11 ;" + "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ + "adcq %%r10, %%r13 ;" + /******************************************/ + "adcq $0, %%r15 ;" + + "addq %%r9, %%rax ;" + "adcq %%r11, %%rbx ;" + "adcq %%r13, %%rcx ;" + "adcq $0, %%r15 ;" + + "movq 16(%1), %%rdx; " /* A[2] */ + "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ + "addq %%rax, %%r8 ;" + "movq %%r8, 16(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ + "adcq %%r10, %%r9 ;" + "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ + "adcq %%r8, %%r11 ;" + "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ + "adcq %%r10, %%r13 ;" + /******************************************/ + "adcq $0, %%rax ;" + + "addq %%r9, %%rbx ;" + "adcq %%r11, %%rcx ;" + "adcq %%r13, %%r15 ;" + "adcq $0, %%rax ;" + + "movq 24(%1), %%rdx; " /* A[3] */ + "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ + "addq %%rbx, %%r8 ;" + "movq %%r8, 24(%0) ;" + "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ + "adcq %%r10, %%r9 ;" + "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ + "adcq %%r8, %%r11 ;" + "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ + "adcq %%r10, %%r13 ;" + /******************************************/ + "adcq $0, %%rbx ;" + + "addq %%r9, %%rcx ;" + "movq %%rcx, 32(%0) ;" + "adcq %%r11, %%r15 ;" + "movq %%r15, 40(%0) ;" + "adcq %%r13, %%rax ;" + "movq %%rax, 48(%0) ;" + "adcq $0, %%rbx ;" + "movq %%rbx, 56(%0) ;" + : + : "r"(c), "r"(a), "r"(b) + : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", + "%r10", "%r11", "%r13", "%r15"); +} + +static void sqr_256x256_integer_adx(u64 *const c, const u64 *const a) +{ + asm volatile( + "movq (%1), %%rdx ;" /* A[0] */ + "mulx 8(%1), %%r8, %%r14 ;" /* A[1]*A[0] */ + "xorl %%r15d, %%r15d;" + "mulx 16(%1), %%r9, %%r10 ;" /* A[2]*A[0] */ + "adcx %%r14, %%r9 ;" + "mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */ + "adcx %%rax, %%r10 ;" + "movq 24(%1), %%rdx ;" /* A[3] */ + "mulx 8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */ + "adcx %%rcx, %%r11 ;" + "mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */ + "adcx %%rax, %%rbx ;" + "movq 8(%1), %%rdx ;" /* A[1] */ + "adcx %%r15, %%r13 ;" + "mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */ + "movq $0, %%r14 ;" + /******************************************/ + "adcx %%r15, %%r14 ;" + + "xorl %%r15d, %%r15d;" + "adox %%rax, %%r10 ;" + "adcx %%r8, %%r8 ;" + "adox %%rcx, %%r11 ;" + "adcx %%r9, %%r9 ;" + "adox %%r15, %%rbx ;" + "adcx %%r10, %%r10 ;" + "adox %%r15, %%r13 ;" + "adcx %%r11, %%r11 ;" + "adox %%r15, %%r14 ;" + "adcx %%rbx, %%rbx ;" + "adcx %%r13, %%r13 ;" + "adcx %%r14, %%r14 ;" + + "movq (%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ + /*******************/ + "movq %%rax, 0(%0) ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, 8(%0) ;" + "movq 8(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ + "adcq %%rax, %%r9 ;" + "movq %%r9, 16(%0) ;" + "adcq %%rcx, %%r10 ;" + "movq %%r10, 24(%0) ;" + "movq 16(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ + "adcq %%rax, %%r11 ;" + "movq %%r11, 32(%0) ;" + "adcq %%rcx, %%rbx ;" + "movq %%rbx, 40(%0) ;" + "movq 24(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ + "adcq %%rax, %%r13 ;" + "movq %%r13, 48(%0) ;" + "adcq %%rcx, %%r14 ;" + "movq %%r14, 56(%0) ;" + : + : "r"(c), "r"(a) + : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", + "%r10", "%r11", "%r13", "%r14", "%r15"); +} + +static void sqr_256x256_integer_bmi2(u64 *const c, const u64 *const a) +{ + asm volatile( + "movq 8(%1), %%rdx ;" /* A[1] */ + "mulx (%1), %%r8, %%r9 ;" /* A[0]*A[1] */ + "mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */ + "mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */ + + "movq 16(%1), %%rdx ;" /* A[2] */ + "mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */ + "mulx (%1), %%rax, %%rdx ;" /* A[0]*A[2] */ + + "addq %%rax, %%r9 ;" + "adcq %%rdx, %%r10 ;" + "adcq %%rcx, %%r11 ;" + "adcq %%r14, %%r15 ;" + "adcq $0, %%r13 ;" + "movq $0, %%r14 ;" + "adcq $0, %%r14 ;" + + "movq (%1), %%rdx ;" /* A[0] */ + "mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */ + + "addq %%rax, %%r10 ;" + "adcq %%rcx, %%r11 ;" + "adcq $0, %%r15 ;" + "adcq $0, %%r13 ;" + "adcq $0, %%r14 ;" + + "shldq $1, %%r13, %%r14 ;" + "shldq $1, %%r15, %%r13 ;" + "shldq $1, %%r11, %%r15 ;" + "shldq $1, %%r10, %%r11 ;" + "shldq $1, %%r9, %%r10 ;" + "shldq $1, %%r8, %%r9 ;" + "shlq $1, %%r8 ;" + + /*******************/ + "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ + /*******************/ + "movq %%rax, 0(%0) ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, 8(%0) ;" + "movq 8(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ + "adcq %%rax, %%r9 ;" + "movq %%r9, 16(%0) ;" + "adcq %%rcx, %%r10 ;" + "movq %%r10, 24(%0) ;" + "movq 16(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ + "adcq %%rax, %%r11 ;" + "movq %%r11, 32(%0) ;" + "adcq %%rcx, %%r15 ;" + "movq %%r15, 40(%0) ;" + "movq 24(%1), %%rdx ;" + "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ + "adcq %%rax, %%r13 ;" + "movq %%r13, 48(%0) ;" + "adcq %%rcx, %%r14 ;" + "movq %%r14, 56(%0) ;" + : + : "r"(c), "r"(a) + : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", + "%r11", "%r13", "%r14", "%r15"); +} + +static void red_eltfp25519_1w_adx(u64 *const c, const u64 *const a) +{ + asm volatile( + "movl $38, %%edx ;" /* 2*c = 38 = 2^256 */ + "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ + "xorl %%ebx, %%ebx ;" + "adox (%1), %%r8 ;" + "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ + "adcx %%r10, %%r9 ;" + "adox 8(%1), %%r9 ;" + "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ + "adcx %%r11, %%r10 ;" + "adox 16(%1), %%r10 ;" + "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ + "adcx %%rax, %%r11 ;" + "adox 24(%1), %%r11 ;" + /***************************************/ + "adcx %%rbx, %%rcx ;" + "adox %%rbx, %%rcx ;" + "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ + "adcx %%rcx, %%r8 ;" + "adcx %%rbx, %%r9 ;" + "movq %%r9, 8(%0) ;" + "adcx %%rbx, %%r10 ;" + "movq %%r10, 16(%0) ;" + "adcx %%rbx, %%r11 ;" + "movq %%r11, 24(%0) ;" + "mov $0, %%ecx ;" + "cmovc %%edx, %%ecx ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, (%0) ;" + : + : "r"(c), "r"(a) + : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", + "%r10", "%r11"); +} + +static void red_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a) +{ + asm volatile( + "movl $38, %%edx ;" /* 2*c = 38 = 2^256 */ + "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ + "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ + "addq %%r10, %%r9 ;" + "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ + "adcq %%r11, %%r10 ;" + "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ + "adcq %%rax, %%r11 ;" + /***************************************/ + "adcq $0, %%rcx ;" + "addq (%1), %%r8 ;" + "adcq 8(%1), %%r9 ;" + "adcq 16(%1), %%r10 ;" + "adcq 24(%1), %%r11 ;" + "adcq $0, %%rcx ;" + "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ + "addq %%rcx, %%r8 ;" + "adcq $0, %%r9 ;" + "movq %%r9, 8(%0) ;" + "adcq $0, %%r10 ;" + "movq %%r10, 16(%0) ;" + "adcq $0, %%r11 ;" + "movq %%r11, 24(%0) ;" + "mov $0, %%ecx ;" + "cmovc %%edx, %%ecx ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, (%0) ;" + : + : "r"(c), "r"(a) + : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", + "%r11"); +} + +static __always_inline void +add_eltfp25519_1w_adx(u64 *const c, const u64 *const a, const u64 *const b) +{ + asm volatile( + "mov $38, %%eax ;" + "xorl %%ecx, %%ecx ;" + "movq (%2), %%r8 ;" + "adcx (%1), %%r8 ;" + "movq 8(%2), %%r9 ;" + "adcx 8(%1), %%r9 ;" + "movq 16(%2), %%r10 ;" + "adcx 16(%1), %%r10 ;" + "movq 24(%2), %%r11 ;" + "adcx 24(%1), %%r11 ;" + "cmovc %%eax, %%ecx ;" + "xorl %%eax, %%eax ;" + "adcx %%rcx, %%r8 ;" + "adcx %%rax, %%r9 ;" + "movq %%r9, 8(%0) ;" + "adcx %%rax, %%r10 ;" + "movq %%r10, 16(%0) ;" + "adcx %%rax, %%r11 ;" + "movq %%r11, 24(%0) ;" + "mov $38, %%ecx ;" + "cmovc %%ecx, %%eax ;" + "addq %%rax, %%r8 ;" + "movq %%r8, (%0) ;" + : + : "r"(c), "r"(a), "r"(b) + : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); +} + +static __always_inline void +add_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a, const u64 *const b) +{ + asm volatile( + "mov $38, %%eax ;" + "movq (%2), %%r8 ;" + "addq (%1), %%r8 ;" + "movq 8(%2), %%r9 ;" + "adcq 8(%1), %%r9 ;" + "movq 16(%2), %%r10 ;" + "adcq 16(%1), %%r10 ;" + "movq 24(%2), %%r11 ;" + "adcq 24(%1), %%r11 ;" + "mov $0, %%ecx ;" + "cmovc %%eax, %%ecx ;" + "addq %%rcx, %%r8 ;" + "adcq $0, %%r9 ;" + "movq %%r9, 8(%0) ;" + "adcq $0, %%r10 ;" + "movq %%r10, 16(%0) ;" + "adcq $0, %%r11 ;" + "movq %%r11, 24(%0) ;" + "mov $0, %%ecx ;" + "cmovc %%eax, %%ecx ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, (%0) ;" + : + : "r"(c), "r"(a), "r"(b) + : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); +} + +static __always_inline void +sub_eltfp25519_1w(u64 *const c, const u64 *const a, const u64 *const b) +{ + asm volatile( + "mov $38, %%eax ;" + "movq (%1), %%r8 ;" + "subq (%2), %%r8 ;" + "movq 8(%1), %%r9 ;" + "sbbq 8(%2), %%r9 ;" + "movq 16(%1), %%r10 ;" + "sbbq 16(%2), %%r10 ;" + "movq 24(%1), %%r11 ;" + "sbbq 24(%2), %%r11 ;" + "mov $0, %%ecx ;" + "cmovc %%eax, %%ecx ;" + "subq %%rcx, %%r8 ;" + "sbbq $0, %%r9 ;" + "movq %%r9, 8(%0) ;" + "sbbq $0, %%r10 ;" + "movq %%r10, 16(%0) ;" + "sbbq $0, %%r11 ;" + "movq %%r11, 24(%0) ;" + "mov $0, %%ecx ;" + "cmovc %%eax, %%ecx ;" + "subq %%rcx, %%r8 ;" + "movq %%r8, (%0) ;" + : + : "r"(c), "r"(a), "r"(b) + : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); +} + +/* Multiplication by a24 = (A+2)/4 = (486662+2)/4 = 121666 */ +static __always_inline void +mul_a24_eltfp25519_1w(u64 *const c, const u64 *const a) +{ + const u64 a24 = 121666; + asm volatile( + "movq %2, %%rdx ;" + "mulx (%1), %%r8, %%r10 ;" + "mulx 8(%1), %%r9, %%r11 ;" + "addq %%r10, %%r9 ;" + "mulx 16(%1), %%r10, %%rax ;" + "adcq %%r11, %%r10 ;" + "mulx 24(%1), %%r11, %%rcx ;" + "adcq %%rax, %%r11 ;" + /**************************/ + "adcq $0, %%rcx ;" + "movl $38, %%edx ;" /* 2*c = 38 = 2^256 mod 2^255-19*/ + "imul %%rdx, %%rcx ;" + "addq %%rcx, %%r8 ;" + "adcq $0, %%r9 ;" + "movq %%r9, 8(%0) ;" + "adcq $0, %%r10 ;" + "movq %%r10, 16(%0) ;" + "adcq $0, %%r11 ;" + "movq %%r11, 24(%0) ;" + "mov $0, %%ecx ;" + "cmovc %%edx, %%ecx ;" + "addq %%rcx, %%r8 ;" + "movq %%r8, (%0) ;" + : + : "r"(c), "r"(a), "r"(a24) + : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", + "%r11"); +} + +static void inv_eltfp25519_1w_adx(u64 *const c, const u64 *const a) +{ + struct { + eltfp25519_1w_buffer buffer; + eltfp25519_1w x0, x1, x2; + } __aligned(32) m; + u64 *T[4]; + + T[0] = m.x0; + T[1] = c; /* x^(-1) */ + T[2] = m.x1; + T[3] = m.x2; + + copy_eltfp25519_1w(T[1], a); + sqrn_eltfp25519_1w_adx(T[1], 1); + copy_eltfp25519_1w(T[2], T[1]); + sqrn_eltfp25519_1w_adx(T[2], 2); + mul_eltfp25519_1w_adx(T[0], a, T[2]); + mul_eltfp25519_1w_adx(T[1], T[1], T[0]); + copy_eltfp25519_1w(T[2], T[1]); + sqrn_eltfp25519_1w_adx(T[2], 1); + mul_eltfp25519_1w_adx(T[0], T[0], T[2]); + copy_eltfp25519_1w(T[2], T[0]); + sqrn_eltfp25519_1w_adx(T[2], 5); + mul_eltfp25519_1w_adx(T[0], T[0], T[2]); + copy_eltfp25519_1w(T[2], T[0]); + sqrn_eltfp25519_1w_adx(T[2], 10); + mul_eltfp25519_1w_adx(T[2], T[2], T[0]); + copy_eltfp25519_1w(T[3], T[2]); + sqrn_eltfp25519_1w_adx(T[3], 20); + mul_eltfp25519_1w_adx(T[3], T[3], T[2]); + sqrn_eltfp25519_1w_adx(T[3], 10); + mul_eltfp25519_1w_adx(T[3], T[3], T[0]); + copy_eltfp25519_1w(T[0], T[3]); + sqrn_eltfp25519_1w_adx(T[0], 50); + mul_eltfp25519_1w_adx(T[0], T[0], T[3]); + copy_eltfp25519_1w(T[2], T[0]); + sqrn_eltfp25519_1w_adx(T[2], 100); + mul_eltfp25519_1w_adx(T[2], T[2], T[0]); + sqrn_eltfp25519_1w_adx(T[2], 50); + mul_eltfp25519_1w_adx(T[2], T[2], T[3]); + sqrn_eltfp25519_1w_adx(T[2], 5); + mul_eltfp25519_1w_adx(T[1], T[1], T[2]); + + memzero_explicit(&m, sizeof(m)); +} + +static void inv_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a) +{ + struct { + eltfp25519_1w_buffer buffer; + eltfp25519_1w x0, x1, x2; + } __aligned(32) m; + u64 *T[5]; + + T[0] = m.x0; + T[1] = c; /* x^(-1) */ + T[2] = m.x1; + T[3] = m.x2; + + copy_eltfp25519_1w(T[1], a); + sqrn_eltfp25519_1w_bmi2(T[1], 1); + copy_eltfp25519_1w(T[2], T[1]); + sqrn_eltfp25519_1w_bmi2(T[2], 2); + mul_eltfp25519_1w_bmi2(T[0], a, T[2]); + mul_eltfp25519_1w_bmi2(T[1], T[1], T[0]); + copy_eltfp25519_1w(T[2], T[1]); + sqrn_eltfp25519_1w_bmi2(T[2], 1); + mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]); + copy_eltfp25519_1w(T[2], T[0]); + sqrn_eltfp25519_1w_bmi2(T[2], 5); + mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]); + copy_eltfp25519_1w(T[2], T[0]); + sqrn_eltfp25519_1w_bmi2(T[2], 10); + mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]); + copy_eltfp25519_1w(T[3], T[2]); + sqrn_eltfp25519_1w_bmi2(T[3], 20); + mul_eltfp25519_1w_bmi2(T[3], T[3], T[2]); + sqrn_eltfp25519_1w_bmi2(T[3], 10); + mul_eltfp25519_1w_bmi2(T[3], T[3], T[0]); + copy_eltfp25519_1w(T[0], T[3]); + sqrn_eltfp25519_1w_bmi2(T[0], 50); + mul_eltfp25519_1w_bmi2(T[0], T[0], T[3]); + copy_eltfp25519_1w(T[2], T[0]); + sqrn_eltfp25519_1w_bmi2(T[2], 100); + mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]); + sqrn_eltfp25519_1w_bmi2(T[2], 50); + mul_eltfp25519_1w_bmi2(T[2], T[2], T[3]); + sqrn_eltfp25519_1w_bmi2(T[2], 5); + mul_eltfp25519_1w_bmi2(T[1], T[1], T[2]); + + memzero_explicit(&m, sizeof(m)); +} + +/* Given c, a 256-bit number, fred_eltfp25519_1w updates c + * with a number such that 0 <= C < 2**255-19. + */ +static __always_inline void fred_eltfp25519_1w(u64 *const c) +{ + u64 tmp0 = 38, tmp1 = 19; + asm volatile( + "btrq $63, %3 ;" /* Put bit 255 in carry flag and clear */ + "cmovncl %k5, %k4 ;" /* c[255] ? 38 : 19 */ + + /* Add either 19 or 38 to c */ + "addq %4, %0 ;" + "adcq $0, %1 ;" + "adcq $0, %2 ;" + "adcq $0, %3 ;" + + /* Test for bit 255 again; only triggered on overflow modulo 2^255-19 */ + "movl $0, %k4 ;" + "cmovnsl %k5, %k4 ;" /* c[255] ? 0 : 19 */ + "btrq $63, %3 ;" /* Clear bit 255 */ + + /* Subtract 19 if necessary */ + "subq %4, %0 ;" + "sbbq $0, %1 ;" + "sbbq $0, %2 ;" + "sbbq $0, %3 ;" + + : "+r"(c[0]), "+r"(c[1]), "+r"(c[2]), "+r"(c[3]), "+r"(tmp0), + "+r"(tmp1) + : + : "memory", "cc"); +} + +static __always_inline void cswap(u8 bit, u64 *const px, u64 *const py) +{ + u64 temp; + asm volatile( + "test %9, %9 ;" + "movq %0, %8 ;" + "cmovnzq %4, %0 ;" + "cmovnzq %8, %4 ;" + "movq %1, %8 ;" + "cmovnzq %5, %1 ;" + "cmovnzq %8, %5 ;" + "movq %2, %8 ;" + "cmovnzq %6, %2 ;" + "cmovnzq %8, %6 ;" + "movq %3, %8 ;" + "cmovnzq %7, %3 ;" + "cmovnzq %8, %7 ;" + : "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]), + "+r"(py[0]), "+r"(py[1]), "+r"(py[2]), "+r"(py[3]), + "=r"(temp) + : "r"(bit) + : "cc" + ); +} + +static __always_inline void cselect(u8 bit, u64 *const px, const u64 *const py) +{ + asm volatile( + "test %4, %4 ;" + "cmovnzq %5, %0 ;" + "cmovnzq %6, %1 ;" + "cmovnzq %7, %2 ;" + "cmovnzq %8, %3 ;" + : "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]) + : "r"(bit), "rm"(py[0]), "rm"(py[1]), "rm"(py[2]), "rm"(py[3]) + : "cc" + ); +} + +static void curve25519_adx(u8 shared[CURVE25519_KEY_SIZE], + const u8 private_key[CURVE25519_KEY_SIZE], + const u8 session_key[CURVE25519_KEY_SIZE]) +{ + struct { + u64 buffer[4 * NUM_WORDS_ELTFP25519]; + u64 coordinates[4 * NUM_WORDS_ELTFP25519]; + u64 workspace[6 * NUM_WORDS_ELTFP25519]; + u8 session[CURVE25519_KEY_SIZE]; + u8 private[CURVE25519_KEY_SIZE]; + } __aligned(32) m; + + int i = 0, j = 0; + u64 prev = 0; + u64 *const X1 = (u64 *)m.session; + u64 *const key = (u64 *)m.private; + u64 *const Px = m.coordinates + 0; + u64 *const Pz = m.coordinates + 4; + u64 *const Qx = m.coordinates + 8; + u64 *const Qz = m.coordinates + 12; + u64 *const X2 = Qx; + u64 *const Z2 = Qz; + u64 *const X3 = Px; + u64 *const Z3 = Pz; + u64 *const X2Z2 = Qx; + u64 *const X3Z3 = Px; + + u64 *const A = m.workspace + 0; + u64 *const B = m.workspace + 4; + u64 *const D = m.workspace + 8; + u64 *const C = m.workspace + 12; + u64 *const DA = m.workspace + 16; + u64 *const CB = m.workspace + 20; + u64 *const AB = A; + u64 *const DC = D; + u64 *const DACB = DA; + + memcpy(m.private, private_key, sizeof(m.private)); + memcpy(m.session, session_key, sizeof(m.session)); + + curve25519_clamp_secret(m.private); + + /* As in the draft: + * When receiving such an array, implementations of curve25519 + * MUST mask the most-significant bit in the final byte. This + * is done to preserve compatibility with point formats which + * reserve the sign bit for use in other protocols and to + * increase resistance to implementation fingerprinting + */ + m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1; + + copy_eltfp25519_1w(Px, X1); + setzero_eltfp25519_1w(Pz); + setzero_eltfp25519_1w(Qx); + setzero_eltfp25519_1w(Qz); + + Pz[0] = 1; + Qx[0] = 1; + + /* main-loop */ + prev = 0; + j = 62; + for (i = 3; i >= 0; --i) { + while (j >= 0) { + u64 bit = (key[i] >> j) & 0x1; + u64 swap = bit ^ prev; + prev = bit; + + add_eltfp25519_1w_adx(A, X2, Z2); /* A = (X2+Z2) */ + sub_eltfp25519_1w(B, X2, Z2); /* B = (X2-Z2) */ + add_eltfp25519_1w_adx(C, X3, Z3); /* C = (X3+Z3) */ + sub_eltfp25519_1w(D, X3, Z3); /* D = (X3-Z3) */ + mul_eltfp25519_2w_adx(DACB, AB, DC); /* [DA|CB] = [A|B]*[D|C] */ + + cselect(swap, A, C); + cselect(swap, B, D); + + sqr_eltfp25519_2w_adx(AB); /* [AA|BB] = [A^2|B^2] */ + add_eltfp25519_1w_adx(X3, DA, CB); /* X3 = (DA+CB) */ + sub_eltfp25519_1w(Z3, DA, CB); /* Z3 = (DA-CB) */ + sqr_eltfp25519_2w_adx(X3Z3); /* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */ + + copy_eltfp25519_1w(X2, B); /* X2 = B^2 */ + sub_eltfp25519_1w(Z2, A, B); /* Z2 = E = AA-BB */ + + mul_a24_eltfp25519_1w(B, Z2); /* B = a24*E */ + add_eltfp25519_1w_adx(B, B, X2); /* B = a24*E+B */ + mul_eltfp25519_2w_adx(X2Z2, X2Z2, AB); /* [X2|Z2] = [B|E]*[A|a24*E+B] */ + mul_eltfp25519_1w_adx(Z3, Z3, X1); /* Z3 = Z3*X1 */ + --j; + } + j = 63; + } + + inv_eltfp25519_1w_adx(A, Qz); + mul_eltfp25519_1w_adx((u64 *)shared, Qx, A); + fred_eltfp25519_1w((u64 *)shared); + + memzero_explicit(&m, sizeof(m)); +} + +static void curve25519_adx_base(u8 session_key[CURVE25519_KEY_SIZE], + const u8 private_key[CURVE25519_KEY_SIZE]) +{ + struct { + u64 buffer[4 * NUM_WORDS_ELTFP25519]; + u64 coordinates[4 * NUM_WORDS_ELTFP25519]; + u64 workspace[4 * NUM_WORDS_ELTFP25519]; + u8 private[CURVE25519_KEY_SIZE]; + } __aligned(32) m; + + const int ite[4] = { 64, 64, 64, 63 }; + const int q = 3; + u64 swap = 1; + + int i = 0, j = 0, k = 0; + u64 *const key = (u64 *)m.private; + u64 *const Ur1 = m.coordinates + 0; + u64 *const Zr1 = m.coordinates + 4; + u64 *const Ur2 = m.coordinates + 8; + u64 *const Zr2 = m.coordinates + 12; + + u64 *const UZr1 = m.coordinates + 0; + u64 *const ZUr2 = m.coordinates + 8; + + u64 *const A = m.workspace + 0; + u64 *const B = m.workspace + 4; + u64 *const C = m.workspace + 8; + u64 *const D = m.workspace + 12; + + u64 *const AB = m.workspace + 0; + u64 *const CD = m.workspace + 8; + + const u64 *const P = table_ladder_8k; + + memcpy(m.private, private_key, sizeof(m.private)); + + curve25519_clamp_secret(m.private); + + setzero_eltfp25519_1w(Ur1); + setzero_eltfp25519_1w(Zr1); + setzero_eltfp25519_1w(Zr2); + Ur1[0] = 1; + Zr1[0] = 1; + Zr2[0] = 1; + + /* G-S */ + Ur2[3] = 0x1eaecdeee27cab34UL; + Ur2[2] = 0xadc7a0b9235d48e2UL; + Ur2[1] = 0xbbf095ae14b2edf8UL; + Ur2[0] = 0x7e94e1fec82faabdUL; + + /* main-loop */ + j = q; + for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) { + while (j < ite[i]) { + u64 bit = (key[i] >> j) & 0x1; + k = (64 * i + j - q); + swap = swap ^ bit; + cswap(swap, Ur1, Ur2); + cswap(swap, Zr1, Zr2); + swap = bit; + /* Addition */ + sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ + add_eltfp25519_1w_adx(A, Ur1, Zr1); /* A = Ur1+Zr1 */ + mul_eltfp25519_1w_adx(C, &P[4 * k], B); /* C = M0-B */ + sub_eltfp25519_1w(B, A, C); /* B = (Ur1+Zr1) - M*(Ur1-Zr1) */ + add_eltfp25519_1w_adx(A, A, C); /* A = (Ur1+Zr1) + M*(Ur1-Zr1) */ + sqr_eltfp25519_2w_adx(AB); /* A = A^2 | B = B^2 */ + mul_eltfp25519_2w_adx(UZr1, ZUr2, AB); /* Ur1 = Zr2*A | Zr1 = Ur2*B */ + ++j; + } + j = 0; + } + + /* Doubling */ + for (i = 0; i < q; ++i) { + add_eltfp25519_1w_adx(A, Ur1, Zr1); /* A = Ur1+Zr1 */ + sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ + sqr_eltfp25519_2w_adx(AB); /* A = A**2 B = B**2 */ + copy_eltfp25519_1w(C, B); /* C = B */ + sub_eltfp25519_1w(B, A, B); /* B = A-B */ + mul_a24_eltfp25519_1w(D, B); /* D = my_a24*B */ + add_eltfp25519_1w_adx(D, D, C); /* D = D+C */ + mul_eltfp25519_2w_adx(UZr1, AB, CD); /* Ur1 = A*B Zr1 = Zr1*A */ + } + + /* Convert to affine coordinates */ + inv_eltfp25519_1w_adx(A, Zr1); + mul_eltfp25519_1w_adx((u64 *)session_key, Ur1, A); + fred_eltfp25519_1w((u64 *)session_key); + + memzero_explicit(&m, sizeof(m)); +} + +static void curve25519_bmi2(u8 shared[CURVE25519_KEY_SIZE], + const u8 private_key[CURVE25519_KEY_SIZE], + const u8 session_key[CURVE25519_KEY_SIZE]) +{ + struct { + u64 buffer[4 * NUM_WORDS_ELTFP25519]; + u64 coordinates[4 * NUM_WORDS_ELTFP25519]; + u64 workspace[6 * NUM_WORDS_ELTFP25519]; + u8 session[CURVE25519_KEY_SIZE]; + u8 private[CURVE25519_KEY_SIZE]; + } __aligned(32) m; + + int i = 0, j = 0; + u64 prev = 0; + u64 *const X1 = (u64 *)m.session; + u64 *const key = (u64 *)m.private; + u64 *const Px = m.coordinates + 0; + u64 *const Pz = m.coordinates + 4; + u64 *const Qx = m.coordinates + 8; + u64 *const Qz = m.coordinates + 12; + u64 *const X2 = Qx; + u64 *const Z2 = Qz; + u64 *const X3 = Px; + u64 *const Z3 = Pz; + u64 *const X2Z2 = Qx; + u64 *const X3Z3 = Px; + + u64 *const A = m.workspace + 0; + u64 *const B = m.workspace + 4; + u64 *const D = m.workspace + 8; + u64 *const C = m.workspace + 12; + u64 *const DA = m.workspace + 16; + u64 *const CB = m.workspace + 20; + u64 *const AB = A; + u64 *const DC = D; + u64 *const DACB = DA; + + memcpy(m.private, private_key, sizeof(m.private)); + memcpy(m.session, session_key, sizeof(m.session)); + + curve25519_clamp_secret(m.private); + + /* As in the draft: + * When receiving such an array, implementations of curve25519 + * MUST mask the most-significant bit in the final byte. This + * is done to preserve compatibility with point formats which + * reserve the sign bit for use in other protocols and to + * increase resistance to implementation fingerprinting + */ + m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1; + + copy_eltfp25519_1w(Px, X1); + setzero_eltfp25519_1w(Pz); + setzero_eltfp25519_1w(Qx); + setzero_eltfp25519_1w(Qz); + + Pz[0] = 1; + Qx[0] = 1; + + /* main-loop */ + prev = 0; + j = 62; + for (i = 3; i >= 0; --i) { + while (j >= 0) { + u64 bit = (key[i] >> j) & 0x1; + u64 swap = bit ^ prev; + prev = bit; + + add_eltfp25519_1w_bmi2(A, X2, Z2); /* A = (X2+Z2) */ + sub_eltfp25519_1w(B, X2, Z2); /* B = (X2-Z2) */ + add_eltfp25519_1w_bmi2(C, X3, Z3); /* C = (X3+Z3) */ + sub_eltfp25519_1w(D, X3, Z3); /* D = (X3-Z3) */ + mul_eltfp25519_2w_bmi2(DACB, AB, DC); /* [DA|CB] = [A|B]*[D|C] */ + + cselect(swap, A, C); + cselect(swap, B, D); + + sqr_eltfp25519_2w_bmi2(AB); /* [AA|BB] = [A^2|B^2] */ + add_eltfp25519_1w_bmi2(X3, DA, CB); /* X3 = (DA+CB) */ + sub_eltfp25519_1w(Z3, DA, CB); /* Z3 = (DA-CB) */ + sqr_eltfp25519_2w_bmi2(X3Z3); /* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */ + + copy_eltfp25519_1w(X2, B); /* X2 = B^2 */ + sub_eltfp25519_1w(Z2, A, B); /* Z2 = E = AA-BB */ + + mul_a24_eltfp25519_1w(B, Z2); /* B = a24*E */ + add_eltfp25519_1w_bmi2(B, B, X2); /* B = a24*E+B */ + mul_eltfp25519_2w_bmi2(X2Z2, X2Z2, AB); /* [X2|Z2] = [B|E]*[A|a24*E+B] */ + mul_eltfp25519_1w_bmi2(Z3, Z3, X1); /* Z3 = Z3*X1 */ + --j; + } + j = 63; + } + + inv_eltfp25519_1w_bmi2(A, Qz); + mul_eltfp25519_1w_bmi2((u64 *)shared, Qx, A); + fred_eltfp25519_1w((u64 *)shared); + + memzero_explicit(&m, sizeof(m)); +} + +static void curve25519_bmi2_base(u8 session_key[CURVE25519_KEY_SIZE], + const u8 private_key[CURVE25519_KEY_SIZE]) +{ + struct { + u64 buffer[4 * NUM_WORDS_ELTFP25519]; + u64 coordinates[4 * NUM_WORDS_ELTFP25519]; + u64 workspace[4 * NUM_WORDS_ELTFP25519]; + u8 private[CURVE25519_KEY_SIZE]; + } __aligned(32) m; + + const int ite[4] = { 64, 64, 64, 63 }; + const int q = 3; + u64 swap = 1; + + int i = 0, j = 0, k = 0; + u64 *const key = (u64 *)m.private; + u64 *const Ur1 = m.coordinates + 0; + u64 *const Zr1 = m.coordinates + 4; + u64 *const Ur2 = m.coordinates + 8; + u64 *const Zr2 = m.coordinates + 12; + + u64 *const UZr1 = m.coordinates + 0; + u64 *const ZUr2 = m.coordinates + 8; + + u64 *const A = m.workspace + 0; + u64 *const B = m.workspace + 4; + u64 *const C = m.workspace + 8; + u64 *const D = m.workspace + 12; + + u64 *const AB = m.workspace + 0; + u64 *const CD = m.workspace + 8; + + const u64 *const P = table_ladder_8k; + + memcpy(m.private, private_key, sizeof(m.private)); + + curve25519_clamp_secret(m.private); + + setzero_eltfp25519_1w(Ur1); + setzero_eltfp25519_1w(Zr1); + setzero_eltfp25519_1w(Zr2); + Ur1[0] = 1; + Zr1[0] = 1; + Zr2[0] = 1; + + /* G-S */ + Ur2[3] = 0x1eaecdeee27cab34UL; + Ur2[2] = 0xadc7a0b9235d48e2UL; + Ur2[1] = 0xbbf095ae14b2edf8UL; + Ur2[0] = 0x7e94e1fec82faabdUL; + + /* main-loop */ + j = q; + for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) { + while (j < ite[i]) { + u64 bit = (key[i] >> j) & 0x1; + k = (64 * i + j - q); + swap = swap ^ bit; + cswap(swap, Ur1, Ur2); + cswap(swap, Zr1, Zr2); + swap = bit; + /* Addition */ + sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ + add_eltfp25519_1w_bmi2(A, Ur1, Zr1); /* A = Ur1+Zr1 */ + mul_eltfp25519_1w_bmi2(C, &P[4 * k], B);/* C = M0-B */ + sub_eltfp25519_1w(B, A, C); /* B = (Ur1+Zr1) - M*(Ur1-Zr1) */ + add_eltfp25519_1w_bmi2(A, A, C); /* A = (Ur1+Zr1) + M*(Ur1-Zr1) */ + sqr_eltfp25519_2w_bmi2(AB); /* A = A^2 | B = B^2 */ + mul_eltfp25519_2w_bmi2(UZr1, ZUr2, AB); /* Ur1 = Zr2*A | Zr1 = Ur2*B */ + ++j; + } + j = 0; + } + + /* Doubling */ + for (i = 0; i < q; ++i) { + add_eltfp25519_1w_bmi2(A, Ur1, Zr1); /* A = Ur1+Zr1 */ + sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ + sqr_eltfp25519_2w_bmi2(AB); /* A = A**2 B = B**2 */ + copy_eltfp25519_1w(C, B); /* C = B */ + sub_eltfp25519_1w(B, A, B); /* B = A-B */ + mul_a24_eltfp25519_1w(D, B); /* D = my_a24*B */ + add_eltfp25519_1w_bmi2(D, D, C); /* D = D+C */ + mul_eltfp25519_2w_bmi2(UZr1, AB, CD); /* Ur1 = A*B Zr1 = Zr1*A */ + } + + /* Convert to affine coordinates */ + inv_eltfp25519_1w_bmi2(A, Zr1); + mul_eltfp25519_1w_bmi2((u64 *)session_key, Ur1, A); + fred_eltfp25519_1w((u64 *)session_key); + + memzero_explicit(&m, sizeof(m)); +} + +void curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE], + const u8 secret[CURVE25519_KEY_SIZE], + const u8 basepoint[CURVE25519_KEY_SIZE]) +{ + if (static_branch_likely(&curve25519_use_adx)) + curve25519_adx(mypublic, secret, basepoint); + else if (static_branch_likely(&curve25519_use_bmi2)) + curve25519_bmi2(mypublic, secret, basepoint); + else + curve25519_generic(mypublic, secret, basepoint); +} +EXPORT_SYMBOL(curve25519_arch); + +void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE], + const u8 secret[CURVE25519_KEY_SIZE]) +{ + if (static_branch_likely(&curve25519_use_adx)) + curve25519_adx_base(pub, secret); + else if (static_branch_likely(&curve25519_use_bmi2)) + curve25519_bmi2_base(pub, secret); + else + curve25519_generic(pub, secret, curve25519_base_point); +} +EXPORT_SYMBOL(curve25519_base_arch); + +static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf, + unsigned int len) +{ + u8 *secret = kpp_tfm_ctx(tfm); + + if (!len) + curve25519_generate_secret(secret); + else if (len == CURVE25519_KEY_SIZE && + crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE)) + memcpy(secret, buf, CURVE25519_KEY_SIZE); + else + return -EINVAL; + return 0; +} + +static int curve25519_generate_public_key(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + const u8 *secret = kpp_tfm_ctx(tfm); + u8 buf[CURVE25519_KEY_SIZE]; + int copied, nbytes; + + if (req->src) + return -EINVAL; + + curve25519_base_arch(buf, secret); + + /* might want less than we've got */ + nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len); + copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst, + nbytes), + buf, nbytes); + if (copied != nbytes) + return -EINVAL; + return 0; +} + +static int curve25519_compute_shared_secret(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + const u8 *secret = kpp_tfm_ctx(tfm); + u8 public_key[CURVE25519_KEY_SIZE]; + u8 buf[CURVE25519_KEY_SIZE]; + int copied, nbytes; + + if (!req->src) + return -EINVAL; + + copied = sg_copy_to_buffer(req->src, + sg_nents_for_len(req->src, + CURVE25519_KEY_SIZE), + public_key, CURVE25519_KEY_SIZE); + if (copied != CURVE25519_KEY_SIZE) + return -EINVAL; + + curve25519_arch(buf, secret, public_key); + + /* might want less than we've got */ + nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len); + copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst, + nbytes), + buf, nbytes); + if (copied != nbytes) + return -EINVAL; + return 0; +} + +static unsigned int curve25519_max_size(struct crypto_kpp *tfm) +{ + return CURVE25519_KEY_SIZE; +} + +static struct kpp_alg curve25519_alg = { + .base.cra_name = "curve25519", + .base.cra_driver_name = "curve25519-x86", + .base.cra_priority = 200, + .base.cra_module = THIS_MODULE, + .base.cra_ctxsize = CURVE25519_KEY_SIZE, + + .set_secret = curve25519_set_secret, + .generate_public_key = curve25519_generate_public_key, + .compute_shared_secret = curve25519_compute_shared_secret, + .max_size = curve25519_max_size, +}; + +static int __init curve25519_mod_init(void) +{ + if (boot_cpu_has(X86_FEATURE_BMI2)) + static_branch_enable(&curve25519_use_bmi2); + else if (boot_cpu_has(X86_FEATURE_ADX)) + static_branch_enable(&curve25519_use_adx); + else + return 0; + return IS_REACHABLE(CONFIG_CRYPTO_KPP) ? + crypto_register_kpp(&curve25519_alg) : 0; +} + +static void __exit curve25519_mod_exit(void) +{ + if (IS_REACHABLE(CONFIG_CRYPTO_KPP) && + (boot_cpu_has(X86_FEATURE_BMI2) || boot_cpu_has(X86_FEATURE_ADX))) + crypto_unregister_kpp(&curve25519_alg); +} + +module_init(curve25519_mod_init); +module_exit(curve25519_mod_exit); + +MODULE_ALIAS_CRYPTO("curve25519"); +MODULE_ALIAS_CRYPTO("curve25519-x86"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S index 7fca43099a5f..fac0fdc3f25d 100644 --- a/arch/x86/crypto/des3_ede-asm_64.S +++ b/arch/x86/crypto/des3_ede-asm_64.S @@ -162,7 +162,7 @@ movl left##d, (io); \ movl right##d, 4(io); -ENTRY(des3_ede_x86_64_crypt_blk) +SYM_FUNC_START(des3_ede_x86_64_crypt_blk) /* input: * %rdi: round keys, CTX * %rsi: dst @@ -244,7 +244,7 @@ ENTRY(des3_ede_x86_64_crypt_blk) popq %rbx; ret; -ENDPROC(des3_ede_x86_64_crypt_blk) +SYM_FUNC_END(des3_ede_x86_64_crypt_blk) /*********************************************************************** * 3-way 3DES @@ -418,7 +418,7 @@ ENDPROC(des3_ede_x86_64_crypt_blk) #define __movq(src, dst) \ movq src, dst; -ENTRY(des3_ede_x86_64_crypt_blk_3way) +SYM_FUNC_START(des3_ede_x86_64_crypt_blk_3way) /* input: * %rdi: ctx, round keys * %rsi: dst (3 blocks) @@ -529,7 +529,7 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way) popq %rbx; ret; -ENDPROC(des3_ede_x86_64_crypt_blk_3way) +SYM_FUNC_END(des3_ede_x86_64_crypt_blk_3way) .section .rodata, "a", @progbits .align 16 diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c index 968386c21ef4..89830e531350 100644 --- a/arch/x86/crypto/des3_ede_glue.c +++ b/arch/x86/crypto/des3_ede_glue.c @@ -19,8 +19,8 @@ #include <linux/types.h> struct des3_ede_x86_ctx { - u32 enc_expkey[DES3_EDE_EXPKEY_WORDS]; - u32 dec_expkey[DES3_EDE_EXPKEY_WORDS]; + struct des3_ede_ctx enc; + struct des3_ede_ctx dec; }; /* regular block cipher functions */ @@ -34,7 +34,7 @@ asmlinkage void des3_ede_x86_64_crypt_blk_3way(const u32 *expkey, u8 *dst, static inline void des3_ede_enc_blk(struct des3_ede_x86_ctx *ctx, u8 *dst, const u8 *src) { - u32 *enc_ctx = ctx->enc_expkey; + u32 *enc_ctx = ctx->enc.expkey; des3_ede_x86_64_crypt_blk(enc_ctx, dst, src); } @@ -42,7 +42,7 @@ static inline void des3_ede_enc_blk(struct des3_ede_x86_ctx *ctx, u8 *dst, static inline void des3_ede_dec_blk(struct des3_ede_x86_ctx *ctx, u8 *dst, const u8 *src) { - u32 *dec_ctx = ctx->dec_expkey; + u32 *dec_ctx = ctx->dec.expkey; des3_ede_x86_64_crypt_blk(dec_ctx, dst, src); } @@ -50,7 +50,7 @@ static inline void des3_ede_dec_blk(struct des3_ede_x86_ctx *ctx, u8 *dst, static inline void des3_ede_enc_blk_3way(struct des3_ede_x86_ctx *ctx, u8 *dst, const u8 *src) { - u32 *enc_ctx = ctx->enc_expkey; + u32 *enc_ctx = ctx->enc.expkey; des3_ede_x86_64_crypt_blk_3way(enc_ctx, dst, src); } @@ -58,7 +58,7 @@ static inline void des3_ede_enc_blk_3way(struct des3_ede_x86_ctx *ctx, u8 *dst, static inline void des3_ede_dec_blk_3way(struct des3_ede_x86_ctx *ctx, u8 *dst, const u8 *src) { - u32 *dec_ctx = ctx->dec_expkey; + u32 *dec_ctx = ctx->dec.expkey; des3_ede_x86_64_crypt_blk_3way(dec_ctx, dst, src); } @@ -122,7 +122,7 @@ static int ecb_encrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm); - return ecb_crypt(req, ctx->enc_expkey); + return ecb_crypt(req, ctx->enc.expkey); } static int ecb_decrypt(struct skcipher_request *req) @@ -130,7 +130,7 @@ static int ecb_decrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct des3_ede_x86_ctx *ctx = crypto_skcipher_ctx(tfm); - return ecb_crypt(req, ctx->dec_expkey); + return ecb_crypt(req, ctx->dec.expkey); } static unsigned int __cbc_encrypt(struct des3_ede_x86_ctx *ctx, @@ -348,20 +348,28 @@ static int des3_ede_x86_setkey(struct crypto_tfm *tfm, const u8 *key, u32 i, j, tmp; int err; - /* Generate encryption context using generic implementation. */ - err = __des3_ede_setkey(ctx->enc_expkey, &tfm->crt_flags, key, keylen); - if (err < 0) + err = des3_ede_expand_key(&ctx->enc, key, keylen); + if (err == -ENOKEY) { + if (crypto_tfm_get_flags(tfm) & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) + err = -EINVAL; + else + err = 0; + } + + if (err) { + memset(ctx, 0, sizeof(*ctx)); return err; + } /* Fix encryption context for this implementation and form decryption * context. */ j = DES3_EDE_EXPKEY_WORDS - 2; for (i = 0; i < DES3_EDE_EXPKEY_WORDS; i += 2, j -= 2) { - tmp = ror32(ctx->enc_expkey[i + 1], 4); - ctx->enc_expkey[i + 1] = tmp; + tmp = ror32(ctx->enc.expkey[i + 1], 4); + ctx->enc.expkey[i + 1] = tmp; - ctx->dec_expkey[j + 0] = ctx->enc_expkey[i + 0]; - ctx->dec_expkey[j + 1] = tmp; + ctx->dec.expkey[j + 0] = ctx->enc.expkey[i + 0]; + ctx->dec.expkey[j + 1] = tmp; } return 0; diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index 5d53effe8abe..bb9735fbb865 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -44,7 +44,7 @@ * T2 * T3 */ -__clmul_gf128mul_ble: +SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble) movaps DATA, T1 pshufd $0b01001110, DATA, T2 pshufd $0b01001110, SHASH, T3 @@ -87,10 +87,10 @@ __clmul_gf128mul_ble: pxor T2, T1 pxor T1, DATA ret -ENDPROC(__clmul_gf128mul_ble) +SYM_FUNC_END(__clmul_gf128mul_ble) /* void clmul_ghash_mul(char *dst, const u128 *shash) */ -ENTRY(clmul_ghash_mul) +SYM_FUNC_START(clmul_ghash_mul) FRAME_BEGIN movups (%rdi), DATA movups (%rsi), SHASH @@ -101,13 +101,13 @@ ENTRY(clmul_ghash_mul) movups DATA, (%rdi) FRAME_END ret -ENDPROC(clmul_ghash_mul) +SYM_FUNC_END(clmul_ghash_mul) /* * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, * const u128 *shash); */ -ENTRY(clmul_ghash_update) +SYM_FUNC_START(clmul_ghash_update) FRAME_BEGIN cmp $16, %rdx jb .Lupdate_just_ret # check length @@ -130,4 +130,4 @@ ENTRY(clmul_ghash_update) .Lupdate_just_ret: FRAME_END ret -ENDPROC(clmul_ghash_update) +SYM_FUNC_END(clmul_ghash_update) diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index ac76fe88ac4f..a4b728518e28 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -57,10 +57,8 @@ static int ghash_setkey(struct crypto_shash *tfm, be128 *x = (be128 *)key; u64 a, b; - if (keylen != GHASH_BLOCK_SIZE) { - crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + if (keylen != GHASH_BLOCK_SIZE) return -EINVAL; - } /* perform multiplication by 'x' in GF(2^128) */ a = be64_to_cpu(x->a); @@ -257,16 +255,11 @@ static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key, { struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm); struct crypto_ahash *child = &ctx->cryptd_tfm->base; - int err; crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK); crypto_ahash_set_flags(child, crypto_ahash_get_flags(tfm) & CRYPTO_TFM_REQ_MASK); - err = crypto_ahash_setkey(child, key, keylen); - crypto_ahash_set_flags(tfm, crypto_ahash_get_flags(child) - & CRYPTO_TFM_RES_MASK); - - return err; + return crypto_ahash_setkey(child, key, keylen); } static int ghash_async_init_tfm(struct crypto_tfm *tfm) @@ -357,6 +350,5 @@ module_init(ghash_pclmulqdqni_mod_init); module_exit(ghash_pclmulqdqni_mod_exit); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("GHASH Message Digest Algorithm, " - "accelerated by PCLMULQDQ-NI"); +MODULE_DESCRIPTION("GHASH hash function, accelerated by PCLMULQDQ-NI"); MODULE_ALIAS_CRYPTO("ghash"); diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c index 901551445387..d3d91a0abf88 100644 --- a/arch/x86/crypto/glue_helper.c +++ b/arch/x86/crypto/glue_helper.c @@ -14,6 +14,7 @@ #include <crypto/b128ops.h> #include <crypto/gf128mul.h> #include <crypto/internal/skcipher.h> +#include <crypto/scatterwalk.h> #include <crypto/xts.h> #include <asm/crypto/glue_helper.h> @@ -133,7 +134,8 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx, src -= num_blocks - 1; dst -= num_blocks - 1; - gctx->funcs[i].fn_u.cbc(ctx, dst, src); + gctx->funcs[i].fn_u.cbc(ctx, (u8 *)dst, + (const u8 *)src); nbytes -= func_bytes; if (nbytes < bsize) @@ -187,7 +189,9 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, /* Process multi-block batch */ do { - gctx->funcs[i].fn_u.ctr(ctx, dst, src, &ctrblk); + gctx->funcs[i].fn_u.ctr(ctx, (u8 *)dst, + (const u8 *)src, + &ctrblk); src += num_blocks; dst += num_blocks; nbytes -= func_bytes; @@ -209,7 +213,8 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, be128_to_le128(&ctrblk, (be128 *)walk.iv); memcpy(&tmp, walk.src.virt.addr, nbytes); - gctx->funcs[gctx->num_funcs - 1].fn_u.ctr(ctx, &tmp, &tmp, + gctx->funcs[gctx->num_funcs - 1].fn_u.ctr(ctx, (u8 *)&tmp, + (const u8 *)&tmp, &ctrblk); memcpy(walk.dst.virt.addr, &tmp, nbytes); le128_to_be128((be128 *)walk.iv, &ctrblk); @@ -239,7 +244,8 @@ static unsigned int __glue_xts_req_128bit(const struct common_glue_ctx *gctx, if (nbytes >= func_bytes) { do { - gctx->funcs[i].fn_u.xts(ctx, dst, src, + gctx->funcs[i].fn_u.xts(ctx, (u8 *)dst, + (const u8 *)src, walk->iv); src += num_blocks; @@ -259,17 +265,36 @@ done: int glue_xts_req_128bit(const struct common_glue_ctx *gctx, struct skcipher_request *req, common_glue_func_t tweak_fn, void *tweak_ctx, - void *crypt_ctx) + void *crypt_ctx, bool decrypt) { + const bool cts = (req->cryptlen % XTS_BLOCK_SIZE); const unsigned int bsize = 128 / 8; + struct skcipher_request subreq; struct skcipher_walk walk; bool fpu_enabled = false; - unsigned int nbytes; + unsigned int nbytes, tail; int err; + if (req->cryptlen < XTS_BLOCK_SIZE) + return -EINVAL; + + if (unlikely(cts)) { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + + tail = req->cryptlen % XTS_BLOCK_SIZE + XTS_BLOCK_SIZE; + + skcipher_request_set_tfm(&subreq, tfm); + skcipher_request_set_callback(&subreq, + crypto_skcipher_get_flags(tfm), + NULL, NULL); + skcipher_request_set_crypt(&subreq, req->src, req->dst, + req->cryptlen - tail, req->iv); + req = &subreq; + } + err = skcipher_walk_virt(&walk, req, false); nbytes = walk.nbytes; - if (!nbytes) + if (err) return err; /* set minimum length to bsize, for tweak_fn */ @@ -287,14 +312,55 @@ int glue_xts_req_128bit(const struct common_glue_ctx *gctx, nbytes = walk.nbytes; } + if (unlikely(cts)) { + u8 *next_tweak, *final_tweak = req->iv; + struct scatterlist *src, *dst; + struct scatterlist s[2], d[2]; + le128 b[2]; + + dst = src = scatterwalk_ffwd(s, req->src, req->cryptlen); + if (req->dst != req->src) + dst = scatterwalk_ffwd(d, req->dst, req->cryptlen); + + if (decrypt) { + next_tweak = memcpy(b, req->iv, XTS_BLOCK_SIZE); + gf128mul_x_ble(b, b); + } else { + next_tweak = req->iv; + } + + skcipher_request_set_crypt(&subreq, src, dst, XTS_BLOCK_SIZE, + next_tweak); + + err = skcipher_walk_virt(&walk, req, false) ?: + skcipher_walk_done(&walk, + __glue_xts_req_128bit(gctx, crypt_ctx, &walk)); + if (err) + goto out; + + scatterwalk_map_and_copy(b, dst, 0, XTS_BLOCK_SIZE, 0); + memcpy(b + 1, b, tail - XTS_BLOCK_SIZE); + scatterwalk_map_and_copy(b, src, XTS_BLOCK_SIZE, + tail - XTS_BLOCK_SIZE, 0); + scatterwalk_map_and_copy(b, dst, 0, tail, 1); + + skcipher_request_set_crypt(&subreq, dst, dst, XTS_BLOCK_SIZE, + final_tweak); + + err = skcipher_walk_virt(&walk, req, false) ?: + skcipher_walk_done(&walk, + __glue_xts_req_128bit(gctx, crypt_ctx, &walk)); + } + +out: glue_fpu_end(fpu_enabled); return err; } EXPORT_SYMBOL_GPL(glue_xts_req_128bit); -void glue_xts_crypt_128bit_one(void *ctx, u128 *dst, const u128 *src, le128 *iv, - common_glue_func_t fn) +void glue_xts_crypt_128bit_one(const void *ctx, u8 *dst, const u8 *src, + le128 *iv, common_glue_func_t fn) { le128 ivblk = *iv; @@ -302,13 +368,13 @@ void glue_xts_crypt_128bit_one(void *ctx, u128 *dst, const u128 *src, le128 *iv, gf128mul_x_ble(iv, &ivblk); /* CC <- T xor C */ - u128_xor(dst, src, (u128 *)&ivblk); + u128_xor((u128 *)dst, (const u128 *)src, (u128 *)&ivblk); /* PP <- D(Key2,CC) */ - fn(ctx, (u8 *)dst, (u8 *)dst); + fn(ctx, dst, dst); /* P <- T xor PP */ - u128_xor(dst, dst, (u128 *)&ivblk); + u128_xor((u128 *)dst, (u128 *)dst, (u128 *)&ivblk); } EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit_one); diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S deleted file mode 100644 index 5413fee33481..000000000000 --- a/arch/x86/crypto/morus1280-avx2-asm.S +++ /dev/null @@ -1,619 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * AVX2 implementation of MORUS-1280 - * - * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <linux/linkage.h> -#include <asm/frame.h> - -#define SHUFFLE_MASK(i0, i1, i2, i3) \ - (i0 | (i1 << 2) | (i2 << 4) | (i3 << 6)) - -#define MASK1 SHUFFLE_MASK(3, 0, 1, 2) -#define MASK2 SHUFFLE_MASK(2, 3, 0, 1) -#define MASK3 SHUFFLE_MASK(1, 2, 3, 0) - -#define STATE0 %ymm0 -#define STATE0_LOW %xmm0 -#define STATE1 %ymm1 -#define STATE2 %ymm2 -#define STATE3 %ymm3 -#define STATE4 %ymm4 -#define KEY %ymm5 -#define MSG %ymm5 -#define MSG_LOW %xmm5 -#define T0 %ymm6 -#define T0_LOW %xmm6 -#define T1 %ymm7 - -.section .rodata.cst32.morus1280_const, "aM", @progbits, 32 -.align 32 -.Lmorus1280_const: - .byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d - .byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62 - .byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1 - .byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd - -.section .rodata.cst32.morus1280_counter, "aM", @progbits, 32 -.align 32 -.Lmorus1280_counter: - .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07 - .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f - .byte 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17 - .byte 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f - -.text - -.macro morus1280_round s0, s1, s2, s3, s4, b, w - vpand \s1, \s2, T0 - vpxor T0, \s0, \s0 - vpxor \s3, \s0, \s0 - vpsllq $\b, \s0, T0 - vpsrlq $(64 - \b), \s0, \s0 - vpxor T0, \s0, \s0 - vpermq $\w, \s3, \s3 -.endm - -/* - * __morus1280_update: internal ABI - * input: - * STATE[0-4] - input state - * MSG - message block - * output: - * STATE[0-4] - output state - * changed: - * T0 - */ -__morus1280_update: - morus1280_round STATE0, STATE1, STATE2, STATE3, STATE4, 13, MASK1 - vpxor MSG, STATE1, STATE1 - morus1280_round STATE1, STATE2, STATE3, STATE4, STATE0, 46, MASK2 - vpxor MSG, STATE2, STATE2 - morus1280_round STATE2, STATE3, STATE4, STATE0, STATE1, 38, MASK3 - vpxor MSG, STATE3, STATE3 - morus1280_round STATE3, STATE4, STATE0, STATE1, STATE2, 7, MASK2 - vpxor MSG, STATE4, STATE4 - morus1280_round STATE4, STATE0, STATE1, STATE2, STATE3, 4, MASK1 - ret -ENDPROC(__morus1280_update) - -/* - * __morus1280_update_zero: internal ABI - * input: - * STATE[0-4] - input state - * output: - * STATE[0-4] - output state - * changed: - * T0 - */ -__morus1280_update_zero: - morus1280_round STATE0, STATE1, STATE2, STATE3, STATE4, 13, MASK1 - morus1280_round STATE1, STATE2, STATE3, STATE4, STATE0, 46, MASK2 - morus1280_round STATE2, STATE3, STATE4, STATE0, STATE1, 38, MASK3 - morus1280_round STATE3, STATE4, STATE0, STATE1, STATE2, 7, MASK2 - morus1280_round STATE4, STATE0, STATE1, STATE2, STATE3, 4, MASK1 - ret -ENDPROC(__morus1280_update_zero) - -/* - * __load_partial: internal ABI - * input: - * %rsi - src - * %rcx - bytes - * output: - * MSG - message block - * changed: - * %r8 - * %r9 - */ -__load_partial: - xor %r9d, %r9d - vpxor MSG, MSG, MSG - - mov %rcx, %r8 - and $0x1, %r8 - jz .Lld_partial_1 - - mov %rcx, %r8 - and $0x1E, %r8 - add %rsi, %r8 - mov (%r8), %r9b - -.Lld_partial_1: - mov %rcx, %r8 - and $0x2, %r8 - jz .Lld_partial_2 - - mov %rcx, %r8 - and $0x1C, %r8 - add %rsi, %r8 - shl $16, %r9 - mov (%r8), %r9w - -.Lld_partial_2: - mov %rcx, %r8 - and $0x4, %r8 - jz .Lld_partial_4 - - mov %rcx, %r8 - and $0x18, %r8 - add %rsi, %r8 - shl $32, %r9 - mov (%r8), %r8d - xor %r8, %r9 - -.Lld_partial_4: - movq %r9, MSG_LOW - - mov %rcx, %r8 - and $0x8, %r8 - jz .Lld_partial_8 - - mov %rcx, %r8 - and $0x10, %r8 - add %rsi, %r8 - pshufd $MASK2, MSG_LOW, MSG_LOW - pinsrq $0, (%r8), MSG_LOW - -.Lld_partial_8: - mov %rcx, %r8 - and $0x10, %r8 - jz .Lld_partial_16 - - vpermq $MASK2, MSG, MSG - movdqu (%rsi), MSG_LOW - -.Lld_partial_16: - ret -ENDPROC(__load_partial) - -/* - * __store_partial: internal ABI - * input: - * %rdx - dst - * %rcx - bytes - * output: - * T0 - message block - * changed: - * %r8 - * %r9 - * %r10 - */ -__store_partial: - mov %rcx, %r8 - mov %rdx, %r9 - - cmp $16, %r8 - jl .Lst_partial_16 - - movdqu T0_LOW, (%r9) - vpermq $MASK2, T0, T0 - - sub $16, %r8 - add $16, %r9 - -.Lst_partial_16: - movq T0_LOW, %r10 - - cmp $8, %r8 - jl .Lst_partial_8 - - mov %r10, (%r9) - pextrq $1, T0_LOW, %r10 - - sub $8, %r8 - add $8, %r9 - -.Lst_partial_8: - cmp $4, %r8 - jl .Lst_partial_4 - - mov %r10d, (%r9) - shr $32, %r10 - - sub $4, %r8 - add $4, %r9 - -.Lst_partial_4: - cmp $2, %r8 - jl .Lst_partial_2 - - mov %r10w, (%r9) - shr $16, %r10 - - sub $2, %r8 - add $2, %r9 - -.Lst_partial_2: - cmp $1, %r8 - jl .Lst_partial_1 - - mov %r10b, (%r9) - -.Lst_partial_1: - ret -ENDPROC(__store_partial) - -/* - * void crypto_morus1280_avx2_init(void *state, const void *key, - * const void *iv); - */ -ENTRY(crypto_morus1280_avx2_init) - FRAME_BEGIN - - /* load IV: */ - vpxor STATE0, STATE0, STATE0 - movdqu (%rdx), STATE0_LOW - /* load key: */ - vmovdqu (%rsi), KEY - vmovdqa KEY, STATE1 - /* load all ones: */ - vpcmpeqd STATE2, STATE2, STATE2 - /* load all zeros: */ - vpxor STATE3, STATE3, STATE3 - /* load the constant: */ - vmovdqa .Lmorus1280_const, STATE4 - - /* update 16 times with zero: */ - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - - /* xor-in the key again after updates: */ - vpxor KEY, STATE1, STATE1 - - /* store the state: */ - vmovdqu STATE0, (0 * 32)(%rdi) - vmovdqu STATE1, (1 * 32)(%rdi) - vmovdqu STATE2, (2 * 32)(%rdi) - vmovdqu STATE3, (3 * 32)(%rdi) - vmovdqu STATE4, (4 * 32)(%rdi) - - FRAME_END - ret -ENDPROC(crypto_morus1280_avx2_init) - -/* - * void crypto_morus1280_avx2_ad(void *state, const void *data, - * unsigned int length); - */ -ENTRY(crypto_morus1280_avx2_ad) - FRAME_BEGIN - - cmp $32, %rdx - jb .Lad_out - - /* load the state: */ - vmovdqu (0 * 32)(%rdi), STATE0 - vmovdqu (1 * 32)(%rdi), STATE1 - vmovdqu (2 * 32)(%rdi), STATE2 - vmovdqu (3 * 32)(%rdi), STATE3 - vmovdqu (4 * 32)(%rdi), STATE4 - - mov %rsi, %r8 - and $0x1F, %r8 - jnz .Lad_u_loop - -.align 4 -.Lad_a_loop: - vmovdqa (%rsi), MSG - call __morus1280_update - sub $32, %rdx - add $32, %rsi - cmp $32, %rdx - jge .Lad_a_loop - - jmp .Lad_cont -.align 4 -.Lad_u_loop: - vmovdqu (%rsi), MSG - call __morus1280_update - sub $32, %rdx - add $32, %rsi - cmp $32, %rdx - jge .Lad_u_loop - -.Lad_cont: - /* store the state: */ - vmovdqu STATE0, (0 * 32)(%rdi) - vmovdqu STATE1, (1 * 32)(%rdi) - vmovdqu STATE2, (2 * 32)(%rdi) - vmovdqu STATE3, (3 * 32)(%rdi) - vmovdqu STATE4, (4 * 32)(%rdi) - -.Lad_out: - FRAME_END - ret -ENDPROC(crypto_morus1280_avx2_ad) - -/* - * void crypto_morus1280_avx2_enc(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus1280_avx2_enc) - FRAME_BEGIN - - cmp $32, %rcx - jb .Lenc_out - - /* load the state: */ - vmovdqu (0 * 32)(%rdi), STATE0 - vmovdqu (1 * 32)(%rdi), STATE1 - vmovdqu (2 * 32)(%rdi), STATE2 - vmovdqu (3 * 32)(%rdi), STATE3 - vmovdqu (4 * 32)(%rdi), STATE4 - - mov %rsi, %r8 - or %rdx, %r8 - and $0x1F, %r8 - jnz .Lenc_u_loop - -.align 4 -.Lenc_a_loop: - vmovdqa (%rsi), MSG - vmovdqa MSG, T0 - vpxor STATE0, T0, T0 - vpermq $MASK3, STATE1, T1 - vpxor T1, T0, T0 - vpand STATE2, STATE3, T1 - vpxor T1, T0, T0 - vmovdqa T0, (%rdx) - - call __morus1280_update - sub $32, %rcx - add $32, %rsi - add $32, %rdx - cmp $32, %rcx - jge .Lenc_a_loop - - jmp .Lenc_cont -.align 4 -.Lenc_u_loop: - vmovdqu (%rsi), MSG - vmovdqa MSG, T0 - vpxor STATE0, T0, T0 - vpermq $MASK3, STATE1, T1 - vpxor T1, T0, T0 - vpand STATE2, STATE3, T1 - vpxor T1, T0, T0 - vmovdqu T0, (%rdx) - - call __morus1280_update - sub $32, %rcx - add $32, %rsi - add $32, %rdx - cmp $32, %rcx - jge .Lenc_u_loop - -.Lenc_cont: - /* store the state: */ - vmovdqu STATE0, (0 * 32)(%rdi) - vmovdqu STATE1, (1 * 32)(%rdi) - vmovdqu STATE2, (2 * 32)(%rdi) - vmovdqu STATE3, (3 * 32)(%rdi) - vmovdqu STATE4, (4 * 32)(%rdi) - -.Lenc_out: - FRAME_END - ret -ENDPROC(crypto_morus1280_avx2_enc) - -/* - * void crypto_morus1280_avx2_enc_tail(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus1280_avx2_enc_tail) - FRAME_BEGIN - - /* load the state: */ - vmovdqu (0 * 32)(%rdi), STATE0 - vmovdqu (1 * 32)(%rdi), STATE1 - vmovdqu (2 * 32)(%rdi), STATE2 - vmovdqu (3 * 32)(%rdi), STATE3 - vmovdqu (4 * 32)(%rdi), STATE4 - - /* encrypt message: */ - call __load_partial - - vmovdqa MSG, T0 - vpxor STATE0, T0, T0 - vpermq $MASK3, STATE1, T1 - vpxor T1, T0, T0 - vpand STATE2, STATE3, T1 - vpxor T1, T0, T0 - - call __store_partial - - call __morus1280_update - - /* store the state: */ - vmovdqu STATE0, (0 * 32)(%rdi) - vmovdqu STATE1, (1 * 32)(%rdi) - vmovdqu STATE2, (2 * 32)(%rdi) - vmovdqu STATE3, (3 * 32)(%rdi) - vmovdqu STATE4, (4 * 32)(%rdi) - - FRAME_END - ret -ENDPROC(crypto_morus1280_avx2_enc_tail) - -/* - * void crypto_morus1280_avx2_dec(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus1280_avx2_dec) - FRAME_BEGIN - - cmp $32, %rcx - jb .Ldec_out - - /* load the state: */ - vmovdqu (0 * 32)(%rdi), STATE0 - vmovdqu (1 * 32)(%rdi), STATE1 - vmovdqu (2 * 32)(%rdi), STATE2 - vmovdqu (3 * 32)(%rdi), STATE3 - vmovdqu (4 * 32)(%rdi), STATE4 - - mov %rsi, %r8 - or %rdx, %r8 - and $0x1F, %r8 - jnz .Ldec_u_loop - -.align 4 -.Ldec_a_loop: - vmovdqa (%rsi), MSG - vpxor STATE0, MSG, MSG - vpermq $MASK3, STATE1, T0 - vpxor T0, MSG, MSG - vpand STATE2, STATE3, T0 - vpxor T0, MSG, MSG - vmovdqa MSG, (%rdx) - - call __morus1280_update - sub $32, %rcx - add $32, %rsi - add $32, %rdx - cmp $32, %rcx - jge .Ldec_a_loop - - jmp .Ldec_cont -.align 4 -.Ldec_u_loop: - vmovdqu (%rsi), MSG - vpxor STATE0, MSG, MSG - vpermq $MASK3, STATE1, T0 - vpxor T0, MSG, MSG - vpand STATE2, STATE3, T0 - vpxor T0, MSG, MSG - vmovdqu MSG, (%rdx) - - call __morus1280_update - sub $32, %rcx - add $32, %rsi - add $32, %rdx - cmp $32, %rcx - jge .Ldec_u_loop - -.Ldec_cont: - /* store the state: */ - vmovdqu STATE0, (0 * 32)(%rdi) - vmovdqu STATE1, (1 * 32)(%rdi) - vmovdqu STATE2, (2 * 32)(%rdi) - vmovdqu STATE3, (3 * 32)(%rdi) - vmovdqu STATE4, (4 * 32)(%rdi) - -.Ldec_out: - FRAME_END - ret -ENDPROC(crypto_morus1280_avx2_dec) - -/* - * void crypto_morus1280_avx2_dec_tail(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus1280_avx2_dec_tail) - FRAME_BEGIN - - /* load the state: */ - vmovdqu (0 * 32)(%rdi), STATE0 - vmovdqu (1 * 32)(%rdi), STATE1 - vmovdqu (2 * 32)(%rdi), STATE2 - vmovdqu (3 * 32)(%rdi), STATE3 - vmovdqu (4 * 32)(%rdi), STATE4 - - /* decrypt message: */ - call __load_partial - - vpxor STATE0, MSG, MSG - vpermq $MASK3, STATE1, T0 - vpxor T0, MSG, MSG - vpand STATE2, STATE3, T0 - vpxor T0, MSG, MSG - vmovdqa MSG, T0 - - call __store_partial - - /* mask with byte count: */ - movq %rcx, T0_LOW - vpbroadcastb T0_LOW, T0 - vmovdqa .Lmorus1280_counter, T1 - vpcmpgtb T1, T0, T0 - vpand T0, MSG, MSG - - call __morus1280_update - - /* store the state: */ - vmovdqu STATE0, (0 * 32)(%rdi) - vmovdqu STATE1, (1 * 32)(%rdi) - vmovdqu STATE2, (2 * 32)(%rdi) - vmovdqu STATE3, (3 * 32)(%rdi) - vmovdqu STATE4, (4 * 32)(%rdi) - - FRAME_END - ret -ENDPROC(crypto_morus1280_avx2_dec_tail) - -/* - * void crypto_morus1280_avx2_final(void *state, void *tag_xor, - * u64 assoclen, u64 cryptlen); - */ -ENTRY(crypto_morus1280_avx2_final) - FRAME_BEGIN - - /* load the state: */ - vmovdqu (0 * 32)(%rdi), STATE0 - vmovdqu (1 * 32)(%rdi), STATE1 - vmovdqu (2 * 32)(%rdi), STATE2 - vmovdqu (3 * 32)(%rdi), STATE3 - vmovdqu (4 * 32)(%rdi), STATE4 - - /* xor state[0] into state[4]: */ - vpxor STATE0, STATE4, STATE4 - - /* prepare length block: */ - vpxor MSG, MSG, MSG - vpinsrq $0, %rdx, MSG_LOW, MSG_LOW - vpinsrq $1, %rcx, MSG_LOW, MSG_LOW - vpsllq $3, MSG, MSG /* multiply by 8 (to get bit count) */ - - /* update state: */ - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - - /* xor tag: */ - vmovdqu (%rsi), MSG - - vpxor STATE0, MSG, MSG - vpermq $MASK3, STATE1, T0 - vpxor T0, MSG, MSG - vpand STATE2, STATE3, T0 - vpxor T0, MSG, MSG - vmovdqu MSG, (%rsi) - - FRAME_END - ret -ENDPROC(crypto_morus1280_avx2_final) diff --git a/arch/x86/crypto/morus1280-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c deleted file mode 100644 index 2d000d66ba4c..000000000000 --- a/arch/x86/crypto/morus1280-avx2-glue.c +++ /dev/null @@ -1,62 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * The MORUS-1280 Authenticated-Encryption Algorithm - * Glue for AVX2 implementation - * - * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <crypto/internal/aead.h> -#include <crypto/internal/simd.h> -#include <crypto/morus1280_glue.h> -#include <linux/module.h> -#include <asm/fpu/api.h> -#include <asm/cpu_device_id.h> - -asmlinkage void crypto_morus1280_avx2_init(void *state, const void *key, - const void *iv); -asmlinkage void crypto_morus1280_avx2_ad(void *state, const void *data, - unsigned int length); - -asmlinkage void crypto_morus1280_avx2_enc(void *state, const void *src, - void *dst, unsigned int length); -asmlinkage void crypto_morus1280_avx2_dec(void *state, const void *src, - void *dst, unsigned int length); - -asmlinkage void crypto_morus1280_avx2_enc_tail(void *state, const void *src, - void *dst, unsigned int length); -asmlinkage void crypto_morus1280_avx2_dec_tail(void *state, const void *src, - void *dst, unsigned int length); - -asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor, - u64 assoclen, u64 cryptlen); - -MORUS1280_DECLARE_ALG(avx2, "morus1280-avx2", 400); - -static struct simd_aead_alg *simd_alg; - -static int __init crypto_morus1280_avx2_module_init(void) -{ - if (!boot_cpu_has(X86_FEATURE_AVX2) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || - !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) - return -ENODEV; - - return simd_register_aeads_compat(&crypto_morus1280_avx2_alg, 1, - &simd_alg); -} - -static void __exit crypto_morus1280_avx2_module_exit(void) -{ - simd_unregister_aeads(&crypto_morus1280_avx2_alg, 1, &simd_alg); -} - -module_init(crypto_morus1280_avx2_module_init); -module_exit(crypto_morus1280_avx2_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>"); -MODULE_DESCRIPTION("MORUS-1280 AEAD algorithm -- AVX2 implementation"); -MODULE_ALIAS_CRYPTO("morus1280"); -MODULE_ALIAS_CRYPTO("morus1280-avx2"); diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S deleted file mode 100644 index 0eece772866b..000000000000 --- a/arch/x86/crypto/morus1280-sse2-asm.S +++ /dev/null @@ -1,893 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * SSE2 implementation of MORUS-1280 - * - * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <linux/linkage.h> -#include <asm/frame.h> - -#define SHUFFLE_MASK(i0, i1, i2, i3) \ - (i0 | (i1 << 2) | (i2 << 4) | (i3 << 6)) - -#define MASK2 SHUFFLE_MASK(2, 3, 0, 1) - -#define STATE0_LO %xmm0 -#define STATE0_HI %xmm1 -#define STATE1_LO %xmm2 -#define STATE1_HI %xmm3 -#define STATE2_LO %xmm4 -#define STATE2_HI %xmm5 -#define STATE3_LO %xmm6 -#define STATE3_HI %xmm7 -#define STATE4_LO %xmm8 -#define STATE4_HI %xmm9 -#define KEY_LO %xmm10 -#define KEY_HI %xmm11 -#define MSG_LO %xmm10 -#define MSG_HI %xmm11 -#define T0_LO %xmm12 -#define T0_HI %xmm13 -#define T1_LO %xmm14 -#define T1_HI %xmm15 - -.section .rodata.cst16.morus640_const, "aM", @progbits, 16 -.align 16 -.Lmorus640_const_0: - .byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d - .byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62 -.Lmorus640_const_1: - .byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1 - .byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd - -.section .rodata.cst16.morus640_counter, "aM", @progbits, 16 -.align 16 -.Lmorus640_counter_0: - .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07 - .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f -.Lmorus640_counter_1: - .byte 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17 - .byte 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f - -.text - -.macro rol1 hi, lo - /* - * HI_1 | HI_0 || LO_1 | LO_0 - * ==> - * HI_0 | HI_1 || LO_1 | LO_0 - * ==> - * HI_0 | LO_1 || LO_0 | HI_1 - */ - pshufd $MASK2, \hi, \hi - movdqa \hi, T0_LO - punpcklqdq \lo, T0_LO - punpckhqdq \hi, \lo - movdqa \lo, \hi - movdqa T0_LO, \lo -.endm - -.macro rol2 hi, lo - movdqa \lo, T0_LO - movdqa \hi, \lo - movdqa T0_LO, \hi -.endm - -.macro rol3 hi, lo - /* - * HI_1 | HI_0 || LO_1 | LO_0 - * ==> - * HI_0 | HI_1 || LO_1 | LO_0 - * ==> - * LO_0 | HI_1 || HI_0 | LO_1 - */ - pshufd $MASK2, \hi, \hi - movdqa \lo, T0_LO - punpckhqdq \hi, T0_LO - punpcklqdq \lo, \hi - movdqa T0_LO, \lo -.endm - -.macro morus1280_round s0_l, s0_h, s1_l, s1_h, s2_l, s2_h, s3_l, s3_h, s4_l, s4_h, b, w - movdqa \s1_l, T0_LO - pand \s2_l, T0_LO - pxor T0_LO, \s0_l - - movdqa \s1_h, T0_LO - pand \s2_h, T0_LO - pxor T0_LO, \s0_h - - pxor \s3_l, \s0_l - pxor \s3_h, \s0_h - - movdqa \s0_l, T0_LO - psllq $\b, T0_LO - psrlq $(64 - \b), \s0_l - pxor T0_LO, \s0_l - - movdqa \s0_h, T0_LO - psllq $\b, T0_LO - psrlq $(64 - \b), \s0_h - pxor T0_LO, \s0_h - - \w \s3_h, \s3_l -.endm - -/* - * __morus1280_update: internal ABI - * input: - * STATE[0-4] - input state - * MSG - message block - * output: - * STATE[0-4] - output state - * changed: - * T0 - */ -__morus1280_update: - morus1280_round \ - STATE0_LO, STATE0_HI, \ - STATE1_LO, STATE1_HI, \ - STATE2_LO, STATE2_HI, \ - STATE3_LO, STATE3_HI, \ - STATE4_LO, STATE4_HI, \ - 13, rol1 - pxor MSG_LO, STATE1_LO - pxor MSG_HI, STATE1_HI - morus1280_round \ - STATE1_LO, STATE1_HI, \ - STATE2_LO, STATE2_HI, \ - STATE3_LO, STATE3_HI, \ - STATE4_LO, STATE4_HI, \ - STATE0_LO, STATE0_HI, \ - 46, rol2 - pxor MSG_LO, STATE2_LO - pxor MSG_HI, STATE2_HI - morus1280_round \ - STATE2_LO, STATE2_HI, \ - STATE3_LO, STATE3_HI, \ - STATE4_LO, STATE4_HI, \ - STATE0_LO, STATE0_HI, \ - STATE1_LO, STATE1_HI, \ - 38, rol3 - pxor MSG_LO, STATE3_LO - pxor MSG_HI, STATE3_HI - morus1280_round \ - STATE3_LO, STATE3_HI, \ - STATE4_LO, STATE4_HI, \ - STATE0_LO, STATE0_HI, \ - STATE1_LO, STATE1_HI, \ - STATE2_LO, STATE2_HI, \ - 7, rol2 - pxor MSG_LO, STATE4_LO - pxor MSG_HI, STATE4_HI - morus1280_round \ - STATE4_LO, STATE4_HI, \ - STATE0_LO, STATE0_HI, \ - STATE1_LO, STATE1_HI, \ - STATE2_LO, STATE2_HI, \ - STATE3_LO, STATE3_HI, \ - 4, rol1 - ret -ENDPROC(__morus1280_update) - -/* - * __morus1280_update_zero: internal ABI - * input: - * STATE[0-4] - input state - * output: - * STATE[0-4] - output state - * changed: - * T0 - */ -__morus1280_update_zero: - morus1280_round \ - STATE0_LO, STATE0_HI, \ - STATE1_LO, STATE1_HI, \ - STATE2_LO, STATE2_HI, \ - STATE3_LO, STATE3_HI, \ - STATE4_LO, STATE4_HI, \ - 13, rol1 - morus1280_round \ - STATE1_LO, STATE1_HI, \ - STATE2_LO, STATE2_HI, \ - STATE3_LO, STATE3_HI, \ - STATE4_LO, STATE4_HI, \ - STATE0_LO, STATE0_HI, \ - 46, rol2 - morus1280_round \ - STATE2_LO, STATE2_HI, \ - STATE3_LO, STATE3_HI, \ - STATE4_LO, STATE4_HI, \ - STATE0_LO, STATE0_HI, \ - STATE1_LO, STATE1_HI, \ - 38, rol3 - morus1280_round \ - STATE3_LO, STATE3_HI, \ - STATE4_LO, STATE4_HI, \ - STATE0_LO, STATE0_HI, \ - STATE1_LO, STATE1_HI, \ - STATE2_LO, STATE2_HI, \ - 7, rol2 - morus1280_round \ - STATE4_LO, STATE4_HI, \ - STATE0_LO, STATE0_HI, \ - STATE1_LO, STATE1_HI, \ - STATE2_LO, STATE2_HI, \ - STATE3_LO, STATE3_HI, \ - 4, rol1 - ret -ENDPROC(__morus1280_update_zero) - -/* - * __load_partial: internal ABI - * input: - * %rsi - src - * %rcx - bytes - * output: - * MSG - message block - * changed: - * %r8 - * %r9 - */ -__load_partial: - xor %r9d, %r9d - pxor MSG_LO, MSG_LO - pxor MSG_HI, MSG_HI - - mov %rcx, %r8 - and $0x1, %r8 - jz .Lld_partial_1 - - mov %rcx, %r8 - and $0x1E, %r8 - add %rsi, %r8 - mov (%r8), %r9b - -.Lld_partial_1: - mov %rcx, %r8 - and $0x2, %r8 - jz .Lld_partial_2 - - mov %rcx, %r8 - and $0x1C, %r8 - add %rsi, %r8 - shl $16, %r9 - mov (%r8), %r9w - -.Lld_partial_2: - mov %rcx, %r8 - and $0x4, %r8 - jz .Lld_partial_4 - - mov %rcx, %r8 - and $0x18, %r8 - add %rsi, %r8 - shl $32, %r9 - mov (%r8), %r8d - xor %r8, %r9 - -.Lld_partial_4: - movq %r9, MSG_LO - - mov %rcx, %r8 - and $0x8, %r8 - jz .Lld_partial_8 - - mov %rcx, %r8 - and $0x10, %r8 - add %rsi, %r8 - pslldq $8, MSG_LO - movq (%r8), T0_LO - pxor T0_LO, MSG_LO - -.Lld_partial_8: - mov %rcx, %r8 - and $0x10, %r8 - jz .Lld_partial_16 - - movdqa MSG_LO, MSG_HI - movdqu (%rsi), MSG_LO - -.Lld_partial_16: - ret -ENDPROC(__load_partial) - -/* - * __store_partial: internal ABI - * input: - * %rdx - dst - * %rcx - bytes - * output: - * T0 - message block - * changed: - * %r8 - * %r9 - * %r10 - */ -__store_partial: - mov %rcx, %r8 - mov %rdx, %r9 - - cmp $16, %r8 - jl .Lst_partial_16 - - movdqu T0_LO, (%r9) - movdqa T0_HI, T0_LO - - sub $16, %r8 - add $16, %r9 - -.Lst_partial_16: - movq T0_LO, %r10 - - cmp $8, %r8 - jl .Lst_partial_8 - - mov %r10, (%r9) - psrldq $8, T0_LO - movq T0_LO, %r10 - - sub $8, %r8 - add $8, %r9 - -.Lst_partial_8: - cmp $4, %r8 - jl .Lst_partial_4 - - mov %r10d, (%r9) - shr $32, %r10 - - sub $4, %r8 - add $4, %r9 - -.Lst_partial_4: - cmp $2, %r8 - jl .Lst_partial_2 - - mov %r10w, (%r9) - shr $16, %r10 - - sub $2, %r8 - add $2, %r9 - -.Lst_partial_2: - cmp $1, %r8 - jl .Lst_partial_1 - - mov %r10b, (%r9) - -.Lst_partial_1: - ret -ENDPROC(__store_partial) - -/* - * void crypto_morus1280_sse2_init(void *state, const void *key, - * const void *iv); - */ -ENTRY(crypto_morus1280_sse2_init) - FRAME_BEGIN - - /* load IV: */ - pxor STATE0_HI, STATE0_HI - movdqu (%rdx), STATE0_LO - /* load key: */ - movdqu 0(%rsi), KEY_LO - movdqu 16(%rsi), KEY_HI - movdqa KEY_LO, STATE1_LO - movdqa KEY_HI, STATE1_HI - /* load all ones: */ - pcmpeqd STATE2_LO, STATE2_LO - pcmpeqd STATE2_HI, STATE2_HI - /* load all zeros: */ - pxor STATE3_LO, STATE3_LO - pxor STATE3_HI, STATE3_HI - /* load the constant: */ - movdqa .Lmorus640_const_0, STATE4_LO - movdqa .Lmorus640_const_1, STATE4_HI - - /* update 16 times with zero: */ - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - call __morus1280_update_zero - - /* xor-in the key again after updates: */ - pxor KEY_LO, STATE1_LO - pxor KEY_HI, STATE1_HI - - /* store the state: */ - movdqu STATE0_LO, (0 * 16)(%rdi) - movdqu STATE0_HI, (1 * 16)(%rdi) - movdqu STATE1_LO, (2 * 16)(%rdi) - movdqu STATE1_HI, (3 * 16)(%rdi) - movdqu STATE2_LO, (4 * 16)(%rdi) - movdqu STATE2_HI, (5 * 16)(%rdi) - movdqu STATE3_LO, (6 * 16)(%rdi) - movdqu STATE3_HI, (7 * 16)(%rdi) - movdqu STATE4_LO, (8 * 16)(%rdi) - movdqu STATE4_HI, (9 * 16)(%rdi) - - FRAME_END - ret -ENDPROC(crypto_morus1280_sse2_init) - -/* - * void crypto_morus1280_sse2_ad(void *state, const void *data, - * unsigned int length); - */ -ENTRY(crypto_morus1280_sse2_ad) - FRAME_BEGIN - - cmp $32, %rdx - jb .Lad_out - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0_LO - movdqu (1 * 16)(%rdi), STATE0_HI - movdqu (2 * 16)(%rdi), STATE1_LO - movdqu (3 * 16)(%rdi), STATE1_HI - movdqu (4 * 16)(%rdi), STATE2_LO - movdqu (5 * 16)(%rdi), STATE2_HI - movdqu (6 * 16)(%rdi), STATE3_LO - movdqu (7 * 16)(%rdi), STATE3_HI - movdqu (8 * 16)(%rdi), STATE4_LO - movdqu (9 * 16)(%rdi), STATE4_HI - - mov %rsi, %r8 - and $0xF, %r8 - jnz .Lad_u_loop - -.align 4 -.Lad_a_loop: - movdqa 0(%rsi), MSG_LO - movdqa 16(%rsi), MSG_HI - call __morus1280_update - sub $32, %rdx - add $32, %rsi - cmp $32, %rdx - jge .Lad_a_loop - - jmp .Lad_cont -.align 4 -.Lad_u_loop: - movdqu 0(%rsi), MSG_LO - movdqu 16(%rsi), MSG_HI - call __morus1280_update - sub $32, %rdx - add $32, %rsi - cmp $32, %rdx - jge .Lad_u_loop - -.Lad_cont: - /* store the state: */ - movdqu STATE0_LO, (0 * 16)(%rdi) - movdqu STATE0_HI, (1 * 16)(%rdi) - movdqu STATE1_LO, (2 * 16)(%rdi) - movdqu STATE1_HI, (3 * 16)(%rdi) - movdqu STATE2_LO, (4 * 16)(%rdi) - movdqu STATE2_HI, (5 * 16)(%rdi) - movdqu STATE3_LO, (6 * 16)(%rdi) - movdqu STATE3_HI, (7 * 16)(%rdi) - movdqu STATE4_LO, (8 * 16)(%rdi) - movdqu STATE4_HI, (9 * 16)(%rdi) - -.Lad_out: - FRAME_END - ret -ENDPROC(crypto_morus1280_sse2_ad) - -/* - * void crypto_morus1280_sse2_enc(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus1280_sse2_enc) - FRAME_BEGIN - - cmp $32, %rcx - jb .Lenc_out - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0_LO - movdqu (1 * 16)(%rdi), STATE0_HI - movdqu (2 * 16)(%rdi), STATE1_LO - movdqu (3 * 16)(%rdi), STATE1_HI - movdqu (4 * 16)(%rdi), STATE2_LO - movdqu (5 * 16)(%rdi), STATE2_HI - movdqu (6 * 16)(%rdi), STATE3_LO - movdqu (7 * 16)(%rdi), STATE3_HI - movdqu (8 * 16)(%rdi), STATE4_LO - movdqu (9 * 16)(%rdi), STATE4_HI - - mov %rsi, %r8 - or %rdx, %r8 - and $0xF, %r8 - jnz .Lenc_u_loop - -.align 4 -.Lenc_a_loop: - movdqa 0(%rsi), MSG_LO - movdqa 16(%rsi), MSG_HI - movdqa STATE1_LO, T1_LO - movdqa STATE1_HI, T1_HI - rol3 T1_HI, T1_LO - movdqa MSG_LO, T0_LO - movdqa MSG_HI, T0_HI - pxor T1_LO, T0_LO - pxor T1_HI, T0_HI - pxor STATE0_LO, T0_LO - pxor STATE0_HI, T0_HI - movdqa STATE2_LO, T1_LO - movdqa STATE2_HI, T1_HI - pand STATE3_LO, T1_LO - pand STATE3_HI, T1_HI - pxor T1_LO, T0_LO - pxor T1_HI, T0_HI - movdqa T0_LO, 0(%rdx) - movdqa T0_HI, 16(%rdx) - - call __morus1280_update - sub $32, %rcx - add $32, %rsi - add $32, %rdx - cmp $32, %rcx - jge .Lenc_a_loop - - jmp .Lenc_cont -.align 4 -.Lenc_u_loop: - movdqu 0(%rsi), MSG_LO - movdqu 16(%rsi), MSG_HI - movdqa STATE1_LO, T1_LO - movdqa STATE1_HI, T1_HI - rol3 T1_HI, T1_LO - movdqa MSG_LO, T0_LO - movdqa MSG_HI, T0_HI - pxor T1_LO, T0_LO - pxor T1_HI, T0_HI - pxor STATE0_LO, T0_LO - pxor STATE0_HI, T0_HI - movdqa STATE2_LO, T1_LO - movdqa STATE2_HI, T1_HI - pand STATE3_LO, T1_LO - pand STATE3_HI, T1_HI - pxor T1_LO, T0_LO - pxor T1_HI, T0_HI - movdqu T0_LO, 0(%rdx) - movdqu T0_HI, 16(%rdx) - - call __morus1280_update - sub $32, %rcx - add $32, %rsi - add $32, %rdx - cmp $32, %rcx - jge .Lenc_u_loop - -.Lenc_cont: - /* store the state: */ - movdqu STATE0_LO, (0 * 16)(%rdi) - movdqu STATE0_HI, (1 * 16)(%rdi) - movdqu STATE1_LO, (2 * 16)(%rdi) - movdqu STATE1_HI, (3 * 16)(%rdi) - movdqu STATE2_LO, (4 * 16)(%rdi) - movdqu STATE2_HI, (5 * 16)(%rdi) - movdqu STATE3_LO, (6 * 16)(%rdi) - movdqu STATE3_HI, (7 * 16)(%rdi) - movdqu STATE4_LO, (8 * 16)(%rdi) - movdqu STATE4_HI, (9 * 16)(%rdi) - -.Lenc_out: - FRAME_END - ret -ENDPROC(crypto_morus1280_sse2_enc) - -/* - * void crypto_morus1280_sse2_enc_tail(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus1280_sse2_enc_tail) - FRAME_BEGIN - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0_LO - movdqu (1 * 16)(%rdi), STATE0_HI - movdqu (2 * 16)(%rdi), STATE1_LO - movdqu (3 * 16)(%rdi), STATE1_HI - movdqu (4 * 16)(%rdi), STATE2_LO - movdqu (5 * 16)(%rdi), STATE2_HI - movdqu (6 * 16)(%rdi), STATE3_LO - movdqu (7 * 16)(%rdi), STATE3_HI - movdqu (8 * 16)(%rdi), STATE4_LO - movdqu (9 * 16)(%rdi), STATE4_HI - - /* encrypt message: */ - call __load_partial - - movdqa STATE1_LO, T1_LO - movdqa STATE1_HI, T1_HI - rol3 T1_HI, T1_LO - movdqa MSG_LO, T0_LO - movdqa MSG_HI, T0_HI - pxor T1_LO, T0_LO - pxor T1_HI, T0_HI - pxor STATE0_LO, T0_LO - pxor STATE0_HI, T0_HI - movdqa STATE2_LO, T1_LO - movdqa STATE2_HI, T1_HI - pand STATE3_LO, T1_LO - pand STATE3_HI, T1_HI - pxor T1_LO, T0_LO - pxor T1_HI, T0_HI - - call __store_partial - - call __morus1280_update - - /* store the state: */ - movdqu STATE0_LO, (0 * 16)(%rdi) - movdqu STATE0_HI, (1 * 16)(%rdi) - movdqu STATE1_LO, (2 * 16)(%rdi) - movdqu STATE1_HI, (3 * 16)(%rdi) - movdqu STATE2_LO, (4 * 16)(%rdi) - movdqu STATE2_HI, (5 * 16)(%rdi) - movdqu STATE3_LO, (6 * 16)(%rdi) - movdqu STATE3_HI, (7 * 16)(%rdi) - movdqu STATE4_LO, (8 * 16)(%rdi) - movdqu STATE4_HI, (9 * 16)(%rdi) - - FRAME_END - ret -ENDPROC(crypto_morus1280_sse2_enc_tail) - -/* - * void crypto_morus1280_sse2_dec(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus1280_sse2_dec) - FRAME_BEGIN - - cmp $32, %rcx - jb .Ldec_out - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0_LO - movdqu (1 * 16)(%rdi), STATE0_HI - movdqu (2 * 16)(%rdi), STATE1_LO - movdqu (3 * 16)(%rdi), STATE1_HI - movdqu (4 * 16)(%rdi), STATE2_LO - movdqu (5 * 16)(%rdi), STATE2_HI - movdqu (6 * 16)(%rdi), STATE3_LO - movdqu (7 * 16)(%rdi), STATE3_HI - movdqu (8 * 16)(%rdi), STATE4_LO - movdqu (9 * 16)(%rdi), STATE4_HI - - mov %rsi, %r8 - or %rdx, %r8 - and $0xF, %r8 - jnz .Ldec_u_loop - -.align 4 -.Ldec_a_loop: - movdqa 0(%rsi), MSG_LO - movdqa 16(%rsi), MSG_HI - pxor STATE0_LO, MSG_LO - pxor STATE0_HI, MSG_HI - movdqa STATE1_LO, T1_LO - movdqa STATE1_HI, T1_HI - rol3 T1_HI, T1_LO - pxor T1_LO, MSG_LO - pxor T1_HI, MSG_HI - movdqa STATE2_LO, T1_LO - movdqa STATE2_HI, T1_HI - pand STATE3_LO, T1_LO - pand STATE3_HI, T1_HI - pxor T1_LO, MSG_LO - pxor T1_HI, MSG_HI - movdqa MSG_LO, 0(%rdx) - movdqa MSG_HI, 16(%rdx) - - call __morus1280_update - sub $32, %rcx - add $32, %rsi - add $32, %rdx - cmp $32, %rcx - jge .Ldec_a_loop - - jmp .Ldec_cont -.align 4 -.Ldec_u_loop: - movdqu 0(%rsi), MSG_LO - movdqu 16(%rsi), MSG_HI - pxor STATE0_LO, MSG_LO - pxor STATE0_HI, MSG_HI - movdqa STATE1_LO, T1_LO - movdqa STATE1_HI, T1_HI - rol3 T1_HI, T1_LO - pxor T1_LO, MSG_LO - pxor T1_HI, MSG_HI - movdqa STATE2_LO, T1_LO - movdqa STATE2_HI, T1_HI - pand STATE3_LO, T1_LO - pand STATE3_HI, T1_HI - pxor T1_LO, MSG_LO - pxor T1_HI, MSG_HI - movdqu MSG_LO, 0(%rdx) - movdqu MSG_HI, 16(%rdx) - - call __morus1280_update - sub $32, %rcx - add $32, %rsi - add $32, %rdx - cmp $32, %rcx - jge .Ldec_u_loop - -.Ldec_cont: - /* store the state: */ - movdqu STATE0_LO, (0 * 16)(%rdi) - movdqu STATE0_HI, (1 * 16)(%rdi) - movdqu STATE1_LO, (2 * 16)(%rdi) - movdqu STATE1_HI, (3 * 16)(%rdi) - movdqu STATE2_LO, (4 * 16)(%rdi) - movdqu STATE2_HI, (5 * 16)(%rdi) - movdqu STATE3_LO, (6 * 16)(%rdi) - movdqu STATE3_HI, (7 * 16)(%rdi) - movdqu STATE4_LO, (8 * 16)(%rdi) - movdqu STATE4_HI, (9 * 16)(%rdi) - -.Ldec_out: - FRAME_END - ret -ENDPROC(crypto_morus1280_sse2_dec) - -/* - * void crypto_morus1280_sse2_dec_tail(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus1280_sse2_dec_tail) - FRAME_BEGIN - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0_LO - movdqu (1 * 16)(%rdi), STATE0_HI - movdqu (2 * 16)(%rdi), STATE1_LO - movdqu (3 * 16)(%rdi), STATE1_HI - movdqu (4 * 16)(%rdi), STATE2_LO - movdqu (5 * 16)(%rdi), STATE2_HI - movdqu (6 * 16)(%rdi), STATE3_LO - movdqu (7 * 16)(%rdi), STATE3_HI - movdqu (8 * 16)(%rdi), STATE4_LO - movdqu (9 * 16)(%rdi), STATE4_HI - - /* decrypt message: */ - call __load_partial - - pxor STATE0_LO, MSG_LO - pxor STATE0_HI, MSG_HI - movdqa STATE1_LO, T1_LO - movdqa STATE1_HI, T1_HI - rol3 T1_HI, T1_LO - pxor T1_LO, MSG_LO - pxor T1_HI, MSG_HI - movdqa STATE2_LO, T1_LO - movdqa STATE2_HI, T1_HI - pand STATE3_LO, T1_LO - pand STATE3_HI, T1_HI - pxor T1_LO, MSG_LO - pxor T1_HI, MSG_HI - movdqa MSG_LO, T0_LO - movdqa MSG_HI, T0_HI - - call __store_partial - - /* mask with byte count: */ - movq %rcx, T0_LO - punpcklbw T0_LO, T0_LO - punpcklbw T0_LO, T0_LO - punpcklbw T0_LO, T0_LO - punpcklbw T0_LO, T0_LO - movdqa T0_LO, T0_HI - movdqa .Lmorus640_counter_0, T1_LO - movdqa .Lmorus640_counter_1, T1_HI - pcmpgtb T1_LO, T0_LO - pcmpgtb T1_HI, T0_HI - pand T0_LO, MSG_LO - pand T0_HI, MSG_HI - - call __morus1280_update - - /* store the state: */ - movdqu STATE0_LO, (0 * 16)(%rdi) - movdqu STATE0_HI, (1 * 16)(%rdi) - movdqu STATE1_LO, (2 * 16)(%rdi) - movdqu STATE1_HI, (3 * 16)(%rdi) - movdqu STATE2_LO, (4 * 16)(%rdi) - movdqu STATE2_HI, (5 * 16)(%rdi) - movdqu STATE3_LO, (6 * 16)(%rdi) - movdqu STATE3_HI, (7 * 16)(%rdi) - movdqu STATE4_LO, (8 * 16)(%rdi) - movdqu STATE4_HI, (9 * 16)(%rdi) - - FRAME_END - ret -ENDPROC(crypto_morus1280_sse2_dec_tail) - -/* - * void crypto_morus1280_sse2_final(void *state, void *tag_xor, - * u64 assoclen, u64 cryptlen); - */ -ENTRY(crypto_morus1280_sse2_final) - FRAME_BEGIN - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0_LO - movdqu (1 * 16)(%rdi), STATE0_HI - movdqu (2 * 16)(%rdi), STATE1_LO - movdqu (3 * 16)(%rdi), STATE1_HI - movdqu (4 * 16)(%rdi), STATE2_LO - movdqu (5 * 16)(%rdi), STATE2_HI - movdqu (6 * 16)(%rdi), STATE3_LO - movdqu (7 * 16)(%rdi), STATE3_HI - movdqu (8 * 16)(%rdi), STATE4_LO - movdqu (9 * 16)(%rdi), STATE4_HI - - /* xor state[0] into state[4]: */ - pxor STATE0_LO, STATE4_LO - pxor STATE0_HI, STATE4_HI - - /* prepare length block: */ - movq %rdx, MSG_LO - movq %rcx, T0_LO - pslldq $8, T0_LO - pxor T0_LO, MSG_LO - psllq $3, MSG_LO /* multiply by 8 (to get bit count) */ - pxor MSG_HI, MSG_HI - - /* update state: */ - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - call __morus1280_update - - /* xor tag: */ - movdqu 0(%rsi), MSG_LO - movdqu 16(%rsi), MSG_HI - - pxor STATE0_LO, MSG_LO - pxor STATE0_HI, MSG_HI - movdqa STATE1_LO, T0_LO - movdqa STATE1_HI, T0_HI - rol3 T0_HI, T0_LO - pxor T0_LO, MSG_LO - pxor T0_HI, MSG_HI - movdqa STATE2_LO, T0_LO - movdqa STATE2_HI, T0_HI - pand STATE3_LO, T0_LO - pand STATE3_HI, T0_HI - pxor T0_LO, MSG_LO - pxor T0_HI, MSG_HI - - movdqu MSG_LO, 0(%rsi) - movdqu MSG_HI, 16(%rsi) - - FRAME_END - ret -ENDPROC(crypto_morus1280_sse2_final) diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c deleted file mode 100644 index aada9d774293..000000000000 --- a/arch/x86/crypto/morus1280-sse2-glue.c +++ /dev/null @@ -1,61 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * The MORUS-1280 Authenticated-Encryption Algorithm - * Glue for SSE2 implementation - * - * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <crypto/internal/aead.h> -#include <crypto/internal/simd.h> -#include <crypto/morus1280_glue.h> -#include <linux/module.h> -#include <asm/fpu/api.h> -#include <asm/cpu_device_id.h> - -asmlinkage void crypto_morus1280_sse2_init(void *state, const void *key, - const void *iv); -asmlinkage void crypto_morus1280_sse2_ad(void *state, const void *data, - unsigned int length); - -asmlinkage void crypto_morus1280_sse2_enc(void *state, const void *src, - void *dst, unsigned int length); -asmlinkage void crypto_morus1280_sse2_dec(void *state, const void *src, - void *dst, unsigned int length); - -asmlinkage void crypto_morus1280_sse2_enc_tail(void *state, const void *src, - void *dst, unsigned int length); -asmlinkage void crypto_morus1280_sse2_dec_tail(void *state, const void *src, - void *dst, unsigned int length); - -asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor, - u64 assoclen, u64 cryptlen); - -MORUS1280_DECLARE_ALG(sse2, "morus1280-sse2", 350); - -static struct simd_aead_alg *simd_alg; - -static int __init crypto_morus1280_sse2_module_init(void) -{ - if (!boot_cpu_has(X86_FEATURE_XMM2) || - !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) - return -ENODEV; - - return simd_register_aeads_compat(&crypto_morus1280_sse2_alg, 1, - &simd_alg); -} - -static void __exit crypto_morus1280_sse2_module_exit(void) -{ - simd_unregister_aeads(&crypto_morus1280_sse2_alg, 1, &simd_alg); -} - -module_init(crypto_morus1280_sse2_module_init); -module_exit(crypto_morus1280_sse2_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>"); -MODULE_DESCRIPTION("MORUS-1280 AEAD algorithm -- SSE2 implementation"); -MODULE_ALIAS_CRYPTO("morus1280"); -MODULE_ALIAS_CRYPTO("morus1280-sse2"); diff --git a/arch/x86/crypto/morus1280_glue.c b/arch/x86/crypto/morus1280_glue.c deleted file mode 100644 index ffbde8b22838..000000000000 --- a/arch/x86/crypto/morus1280_glue.c +++ /dev/null @@ -1,205 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * The MORUS-1280 Authenticated-Encryption Algorithm - * Common x86 SIMD glue skeleton - * - * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <crypto/internal/aead.h> -#include <crypto/internal/skcipher.h> -#include <crypto/morus1280_glue.h> -#include <crypto/scatterwalk.h> -#include <linux/err.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/scatterlist.h> -#include <asm/fpu/api.h> - -struct morus1280_state { - struct morus1280_block s[MORUS_STATE_BLOCKS]; -}; - -struct morus1280_ops { - int (*skcipher_walk_init)(struct skcipher_walk *walk, - struct aead_request *req, bool atomic); - - void (*crypt_blocks)(void *state, const void *src, void *dst, - unsigned int length); - void (*crypt_tail)(void *state, const void *src, void *dst, - unsigned int length); -}; - -static void crypto_morus1280_glue_process_ad( - struct morus1280_state *state, - const struct morus1280_glue_ops *ops, - struct scatterlist *sg_src, unsigned int assoclen) -{ - struct scatter_walk walk; - struct morus1280_block buf; - unsigned int pos = 0; - - scatterwalk_start(&walk, sg_src); - while (assoclen != 0) { - unsigned int size = scatterwalk_clamp(&walk, assoclen); - unsigned int left = size; - void *mapped = scatterwalk_map(&walk); - const u8 *src = (const u8 *)mapped; - - if (pos + size >= MORUS1280_BLOCK_SIZE) { - if (pos > 0) { - unsigned int fill = MORUS1280_BLOCK_SIZE - pos; - memcpy(buf.bytes + pos, src, fill); - ops->ad(state, buf.bytes, MORUS1280_BLOCK_SIZE); - pos = 0; - left -= fill; - src += fill; - } - - ops->ad(state, src, left); - src += left & ~(MORUS1280_BLOCK_SIZE - 1); - left &= MORUS1280_BLOCK_SIZE - 1; - } - - memcpy(buf.bytes + pos, src, left); - - pos += left; - assoclen -= size; - scatterwalk_unmap(mapped); - scatterwalk_advance(&walk, size); - scatterwalk_done(&walk, 0, assoclen); - } - - if (pos > 0) { - memset(buf.bytes + pos, 0, MORUS1280_BLOCK_SIZE - pos); - ops->ad(state, buf.bytes, MORUS1280_BLOCK_SIZE); - } -} - -static void crypto_morus1280_glue_process_crypt(struct morus1280_state *state, - struct morus1280_ops ops, - struct skcipher_walk *walk) -{ - while (walk->nbytes >= MORUS1280_BLOCK_SIZE) { - ops.crypt_blocks(state, walk->src.virt.addr, - walk->dst.virt.addr, - round_down(walk->nbytes, - MORUS1280_BLOCK_SIZE)); - skcipher_walk_done(walk, walk->nbytes % MORUS1280_BLOCK_SIZE); - } - - if (walk->nbytes) { - ops.crypt_tail(state, walk->src.virt.addr, walk->dst.virt.addr, - walk->nbytes); - skcipher_walk_done(walk, 0); - } -} - -int crypto_morus1280_glue_setkey(struct crypto_aead *aead, const u8 *key, - unsigned int keylen) -{ - struct morus1280_ctx *ctx = crypto_aead_ctx(aead); - - if (keylen == MORUS1280_BLOCK_SIZE) { - memcpy(ctx->key.bytes, key, MORUS1280_BLOCK_SIZE); - } else if (keylen == MORUS1280_BLOCK_SIZE / 2) { - memcpy(ctx->key.bytes, key, keylen); - memcpy(ctx->key.bytes + keylen, key, keylen); - } else { - crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); - return -EINVAL; - } - - return 0; -} -EXPORT_SYMBOL_GPL(crypto_morus1280_glue_setkey); - -int crypto_morus1280_glue_setauthsize(struct crypto_aead *tfm, - unsigned int authsize) -{ - return (authsize <= MORUS_MAX_AUTH_SIZE) ? 0 : -EINVAL; -} -EXPORT_SYMBOL_GPL(crypto_morus1280_glue_setauthsize); - -static void crypto_morus1280_glue_crypt(struct aead_request *req, - struct morus1280_ops ops, - unsigned int cryptlen, - struct morus1280_block *tag_xor) -{ - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct morus1280_ctx *ctx = crypto_aead_ctx(tfm); - struct morus1280_state state; - struct skcipher_walk walk; - - ops.skcipher_walk_init(&walk, req, true); - - kernel_fpu_begin(); - - ctx->ops->init(&state, &ctx->key, req->iv); - crypto_morus1280_glue_process_ad(&state, ctx->ops, req->src, req->assoclen); - crypto_morus1280_glue_process_crypt(&state, ops, &walk); - ctx->ops->final(&state, tag_xor, req->assoclen, cryptlen); - - kernel_fpu_end(); -} - -int crypto_morus1280_glue_encrypt(struct aead_request *req) -{ - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct morus1280_ctx *ctx = crypto_aead_ctx(tfm); - struct morus1280_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_encrypt, - .crypt_blocks = ctx->ops->enc, - .crypt_tail = ctx->ops->enc_tail, - }; - - struct morus1280_block tag = {}; - unsigned int authsize = crypto_aead_authsize(tfm); - unsigned int cryptlen = req->cryptlen; - - crypto_morus1280_glue_crypt(req, OPS, cryptlen, &tag); - - scatterwalk_map_and_copy(tag.bytes, req->dst, - req->assoclen + cryptlen, authsize, 1); - return 0; -} -EXPORT_SYMBOL_GPL(crypto_morus1280_glue_encrypt); - -int crypto_morus1280_glue_decrypt(struct aead_request *req) -{ - static const u8 zeros[MORUS1280_BLOCK_SIZE] = {}; - - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct morus1280_ctx *ctx = crypto_aead_ctx(tfm); - struct morus1280_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_decrypt, - .crypt_blocks = ctx->ops->dec, - .crypt_tail = ctx->ops->dec_tail, - }; - - struct morus1280_block tag; - unsigned int authsize = crypto_aead_authsize(tfm); - unsigned int cryptlen = req->cryptlen - authsize; - - scatterwalk_map_and_copy(tag.bytes, req->src, - req->assoclen + cryptlen, authsize, 0); - - crypto_morus1280_glue_crypt(req, OPS, cryptlen, &tag); - - return crypto_memneq(tag.bytes, zeros, authsize) ? -EBADMSG : 0; -} -EXPORT_SYMBOL_GPL(crypto_morus1280_glue_decrypt); - -void crypto_morus1280_glue_init_ops(struct crypto_aead *aead, - const struct morus1280_glue_ops *ops) -{ - struct morus1280_ctx *ctx = crypto_aead_ctx(aead); - ctx->ops = ops; -} -EXPORT_SYMBOL_GPL(crypto_morus1280_glue_init_ops); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>"); -MODULE_DESCRIPTION("MORUS-1280 AEAD mode -- glue for x86 optimizations"); diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S deleted file mode 100644 index a60891101bbd..000000000000 --- a/arch/x86/crypto/morus640-sse2-asm.S +++ /dev/null @@ -1,612 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * SSE2 implementation of MORUS-640 - * - * Copyright (c) 2017-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <linux/linkage.h> -#include <asm/frame.h> - -#define SHUFFLE_MASK(i0, i1, i2, i3) \ - (i0 | (i1 << 2) | (i2 << 4) | (i3 << 6)) - -#define MASK1 SHUFFLE_MASK(3, 0, 1, 2) -#define MASK2 SHUFFLE_MASK(2, 3, 0, 1) -#define MASK3 SHUFFLE_MASK(1, 2, 3, 0) - -#define STATE0 %xmm0 -#define STATE1 %xmm1 -#define STATE2 %xmm2 -#define STATE3 %xmm3 -#define STATE4 %xmm4 -#define KEY %xmm5 -#define MSG %xmm5 -#define T0 %xmm6 -#define T1 %xmm7 - -.section .rodata.cst16.morus640_const, "aM", @progbits, 32 -.align 16 -.Lmorus640_const_0: - .byte 0x00, 0x01, 0x01, 0x02, 0x03, 0x05, 0x08, 0x0d - .byte 0x15, 0x22, 0x37, 0x59, 0x90, 0xe9, 0x79, 0x62 -.Lmorus640_const_1: - .byte 0xdb, 0x3d, 0x18, 0x55, 0x6d, 0xc2, 0x2f, 0xf1 - .byte 0x20, 0x11, 0x31, 0x42, 0x73, 0xb5, 0x28, 0xdd - -.section .rodata.cst16.morus640_counter, "aM", @progbits, 16 -.align 16 -.Lmorus640_counter: - .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07 - .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f - -.text - -.macro morus640_round s0, s1, s2, s3, s4, b, w - movdqa \s1, T0 - pand \s2, T0 - pxor T0, \s0 - pxor \s3, \s0 - movdqa \s0, T0 - pslld $\b, T0 - psrld $(32 - \b), \s0 - pxor T0, \s0 - pshufd $\w, \s3, \s3 -.endm - -/* - * __morus640_update: internal ABI - * input: - * STATE[0-4] - input state - * MSG - message block - * output: - * STATE[0-4] - output state - * changed: - * T0 - */ -__morus640_update: - morus640_round STATE0, STATE1, STATE2, STATE3, STATE4, 5, MASK1 - pxor MSG, STATE1 - morus640_round STATE1, STATE2, STATE3, STATE4, STATE0, 31, MASK2 - pxor MSG, STATE2 - morus640_round STATE2, STATE3, STATE4, STATE0, STATE1, 7, MASK3 - pxor MSG, STATE3 - morus640_round STATE3, STATE4, STATE0, STATE1, STATE2, 22, MASK2 - pxor MSG, STATE4 - morus640_round STATE4, STATE0, STATE1, STATE2, STATE3, 13, MASK1 - ret -ENDPROC(__morus640_update) - - -/* - * __morus640_update_zero: internal ABI - * input: - * STATE[0-4] - input state - * output: - * STATE[0-4] - output state - * changed: - * T0 - */ -__morus640_update_zero: - morus640_round STATE0, STATE1, STATE2, STATE3, STATE4, 5, MASK1 - morus640_round STATE1, STATE2, STATE3, STATE4, STATE0, 31, MASK2 - morus640_round STATE2, STATE3, STATE4, STATE0, STATE1, 7, MASK3 - morus640_round STATE3, STATE4, STATE0, STATE1, STATE2, 22, MASK2 - morus640_round STATE4, STATE0, STATE1, STATE2, STATE3, 13, MASK1 - ret -ENDPROC(__morus640_update_zero) - -/* - * __load_partial: internal ABI - * input: - * %rsi - src - * %rcx - bytes - * output: - * MSG - message block - * changed: - * T0 - * %r8 - * %r9 - */ -__load_partial: - xor %r9d, %r9d - pxor MSG, MSG - - mov %rcx, %r8 - and $0x1, %r8 - jz .Lld_partial_1 - - mov %rcx, %r8 - and $0x1E, %r8 - add %rsi, %r8 - mov (%r8), %r9b - -.Lld_partial_1: - mov %rcx, %r8 - and $0x2, %r8 - jz .Lld_partial_2 - - mov %rcx, %r8 - and $0x1C, %r8 - add %rsi, %r8 - shl $16, %r9 - mov (%r8), %r9w - -.Lld_partial_2: - mov %rcx, %r8 - and $0x4, %r8 - jz .Lld_partial_4 - - mov %rcx, %r8 - and $0x18, %r8 - add %rsi, %r8 - shl $32, %r9 - mov (%r8), %r8d - xor %r8, %r9 - -.Lld_partial_4: - movq %r9, MSG - - mov %rcx, %r8 - and $0x8, %r8 - jz .Lld_partial_8 - - mov %rcx, %r8 - and $0x10, %r8 - add %rsi, %r8 - pslldq $8, MSG - movq (%r8), T0 - pxor T0, MSG - -.Lld_partial_8: - ret -ENDPROC(__load_partial) - -/* - * __store_partial: internal ABI - * input: - * %rdx - dst - * %rcx - bytes - * output: - * T0 - message block - * changed: - * %r8 - * %r9 - * %r10 - */ -__store_partial: - mov %rcx, %r8 - mov %rdx, %r9 - - movq T0, %r10 - - cmp $8, %r8 - jl .Lst_partial_8 - - mov %r10, (%r9) - psrldq $8, T0 - movq T0, %r10 - - sub $8, %r8 - add $8, %r9 - -.Lst_partial_8: - cmp $4, %r8 - jl .Lst_partial_4 - - mov %r10d, (%r9) - shr $32, %r10 - - sub $4, %r8 - add $4, %r9 - -.Lst_partial_4: - cmp $2, %r8 - jl .Lst_partial_2 - - mov %r10w, (%r9) - shr $16, %r10 - - sub $2, %r8 - add $2, %r9 - -.Lst_partial_2: - cmp $1, %r8 - jl .Lst_partial_1 - - mov %r10b, (%r9) - -.Lst_partial_1: - ret -ENDPROC(__store_partial) - -/* - * void crypto_morus640_sse2_init(void *state, const void *key, const void *iv); - */ -ENTRY(crypto_morus640_sse2_init) - FRAME_BEGIN - - /* load IV: */ - movdqu (%rdx), STATE0 - /* load key: */ - movdqu (%rsi), KEY - movdqa KEY, STATE1 - /* load all ones: */ - pcmpeqd STATE2, STATE2 - /* load the constants: */ - movdqa .Lmorus640_const_0, STATE3 - movdqa .Lmorus640_const_1, STATE4 - - /* update 16 times with zero: */ - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - call __morus640_update_zero - - /* xor-in the key again after updates: */ - pxor KEY, STATE1 - - /* store the state: */ - movdqu STATE0, (0 * 16)(%rdi) - movdqu STATE1, (1 * 16)(%rdi) - movdqu STATE2, (2 * 16)(%rdi) - movdqu STATE3, (3 * 16)(%rdi) - movdqu STATE4, (4 * 16)(%rdi) - - FRAME_END - ret -ENDPROC(crypto_morus640_sse2_init) - -/* - * void crypto_morus640_sse2_ad(void *state, const void *data, - * unsigned int length); - */ -ENTRY(crypto_morus640_sse2_ad) - FRAME_BEGIN - - cmp $16, %rdx - jb .Lad_out - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0 - movdqu (1 * 16)(%rdi), STATE1 - movdqu (2 * 16)(%rdi), STATE2 - movdqu (3 * 16)(%rdi), STATE3 - movdqu (4 * 16)(%rdi), STATE4 - - mov %rsi, %r8 - and $0xF, %r8 - jnz .Lad_u_loop - -.align 4 -.Lad_a_loop: - movdqa (%rsi), MSG - call __morus640_update - sub $16, %rdx - add $16, %rsi - cmp $16, %rdx - jge .Lad_a_loop - - jmp .Lad_cont -.align 4 -.Lad_u_loop: - movdqu (%rsi), MSG - call __morus640_update - sub $16, %rdx - add $16, %rsi - cmp $16, %rdx - jge .Lad_u_loop - -.Lad_cont: - /* store the state: */ - movdqu STATE0, (0 * 16)(%rdi) - movdqu STATE1, (1 * 16)(%rdi) - movdqu STATE2, (2 * 16)(%rdi) - movdqu STATE3, (3 * 16)(%rdi) - movdqu STATE4, (4 * 16)(%rdi) - -.Lad_out: - FRAME_END - ret -ENDPROC(crypto_morus640_sse2_ad) - -/* - * void crypto_morus640_sse2_enc(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus640_sse2_enc) - FRAME_BEGIN - - cmp $16, %rcx - jb .Lenc_out - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0 - movdqu (1 * 16)(%rdi), STATE1 - movdqu (2 * 16)(%rdi), STATE2 - movdqu (3 * 16)(%rdi), STATE3 - movdqu (4 * 16)(%rdi), STATE4 - - mov %rsi, %r8 - or %rdx, %r8 - and $0xF, %r8 - jnz .Lenc_u_loop - -.align 4 -.Lenc_a_loop: - movdqa (%rsi), MSG - movdqa MSG, T0 - pxor STATE0, T0 - pshufd $MASK3, STATE1, T1 - pxor T1, T0 - movdqa STATE2, T1 - pand STATE3, T1 - pxor T1, T0 - movdqa T0, (%rdx) - - call __morus640_update - sub $16, %rcx - add $16, %rsi - add $16, %rdx - cmp $16, %rcx - jge .Lenc_a_loop - - jmp .Lenc_cont -.align 4 -.Lenc_u_loop: - movdqu (%rsi), MSG - movdqa MSG, T0 - pxor STATE0, T0 - pshufd $MASK3, STATE1, T1 - pxor T1, T0 - movdqa STATE2, T1 - pand STATE3, T1 - pxor T1, T0 - movdqu T0, (%rdx) - - call __morus640_update - sub $16, %rcx - add $16, %rsi - add $16, %rdx - cmp $16, %rcx - jge .Lenc_u_loop - -.Lenc_cont: - /* store the state: */ - movdqu STATE0, (0 * 16)(%rdi) - movdqu STATE1, (1 * 16)(%rdi) - movdqu STATE2, (2 * 16)(%rdi) - movdqu STATE3, (3 * 16)(%rdi) - movdqu STATE4, (4 * 16)(%rdi) - -.Lenc_out: - FRAME_END - ret -ENDPROC(crypto_morus640_sse2_enc) - -/* - * void crypto_morus640_sse2_enc_tail(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus640_sse2_enc_tail) - FRAME_BEGIN - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0 - movdqu (1 * 16)(%rdi), STATE1 - movdqu (2 * 16)(%rdi), STATE2 - movdqu (3 * 16)(%rdi), STATE3 - movdqu (4 * 16)(%rdi), STATE4 - - /* encrypt message: */ - call __load_partial - - movdqa MSG, T0 - pxor STATE0, T0 - pshufd $MASK3, STATE1, T1 - pxor T1, T0 - movdqa STATE2, T1 - pand STATE3, T1 - pxor T1, T0 - - call __store_partial - - call __morus640_update - - /* store the state: */ - movdqu STATE0, (0 * 16)(%rdi) - movdqu STATE1, (1 * 16)(%rdi) - movdqu STATE2, (2 * 16)(%rdi) - movdqu STATE3, (3 * 16)(%rdi) - movdqu STATE4, (4 * 16)(%rdi) - - FRAME_END - ret -ENDPROC(crypto_morus640_sse2_enc_tail) - -/* - * void crypto_morus640_sse2_dec(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus640_sse2_dec) - FRAME_BEGIN - - cmp $16, %rcx - jb .Ldec_out - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0 - movdqu (1 * 16)(%rdi), STATE1 - movdqu (2 * 16)(%rdi), STATE2 - movdqu (3 * 16)(%rdi), STATE3 - movdqu (4 * 16)(%rdi), STATE4 - - mov %rsi, %r8 - or %rdx, %r8 - and $0xF, %r8 - jnz .Ldec_u_loop - -.align 4 -.Ldec_a_loop: - movdqa (%rsi), MSG - pxor STATE0, MSG - pshufd $MASK3, STATE1, T0 - pxor T0, MSG - movdqa STATE2, T0 - pand STATE3, T0 - pxor T0, MSG - movdqa MSG, (%rdx) - - call __morus640_update - sub $16, %rcx - add $16, %rsi - add $16, %rdx - cmp $16, %rcx - jge .Ldec_a_loop - - jmp .Ldec_cont -.align 4 -.Ldec_u_loop: - movdqu (%rsi), MSG - pxor STATE0, MSG - pshufd $MASK3, STATE1, T0 - pxor T0, MSG - movdqa STATE2, T0 - pand STATE3, T0 - pxor T0, MSG - movdqu MSG, (%rdx) - - call __morus640_update - sub $16, %rcx - add $16, %rsi - add $16, %rdx - cmp $16, %rcx - jge .Ldec_u_loop - -.Ldec_cont: - /* store the state: */ - movdqu STATE0, (0 * 16)(%rdi) - movdqu STATE1, (1 * 16)(%rdi) - movdqu STATE2, (2 * 16)(%rdi) - movdqu STATE3, (3 * 16)(%rdi) - movdqu STATE4, (4 * 16)(%rdi) - -.Ldec_out: - FRAME_END - ret -ENDPROC(crypto_morus640_sse2_dec) - -/* - * void crypto_morus640_sse2_dec_tail(void *state, const void *src, void *dst, - * unsigned int length); - */ -ENTRY(crypto_morus640_sse2_dec_tail) - FRAME_BEGIN - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0 - movdqu (1 * 16)(%rdi), STATE1 - movdqu (2 * 16)(%rdi), STATE2 - movdqu (3 * 16)(%rdi), STATE3 - movdqu (4 * 16)(%rdi), STATE4 - - /* decrypt message: */ - call __load_partial - - pxor STATE0, MSG - pshufd $MASK3, STATE1, T0 - pxor T0, MSG - movdqa STATE2, T0 - pand STATE3, T0 - pxor T0, MSG - movdqa MSG, T0 - - call __store_partial - - /* mask with byte count: */ - movq %rcx, T0 - punpcklbw T0, T0 - punpcklbw T0, T0 - punpcklbw T0, T0 - punpcklbw T0, T0 - movdqa .Lmorus640_counter, T1 - pcmpgtb T1, T0 - pand T0, MSG - - call __morus640_update - - /* store the state: */ - movdqu STATE0, (0 * 16)(%rdi) - movdqu STATE1, (1 * 16)(%rdi) - movdqu STATE2, (2 * 16)(%rdi) - movdqu STATE3, (3 * 16)(%rdi) - movdqu STATE4, (4 * 16)(%rdi) - - FRAME_END - ret -ENDPROC(crypto_morus640_sse2_dec_tail) - -/* - * void crypto_morus640_sse2_final(void *state, void *tag_xor, - * u64 assoclen, u64 cryptlen); - */ -ENTRY(crypto_morus640_sse2_final) - FRAME_BEGIN - - /* load the state: */ - movdqu (0 * 16)(%rdi), STATE0 - movdqu (1 * 16)(%rdi), STATE1 - movdqu (2 * 16)(%rdi), STATE2 - movdqu (3 * 16)(%rdi), STATE3 - movdqu (4 * 16)(%rdi), STATE4 - - /* xor state[0] into state[4]: */ - pxor STATE0, STATE4 - - /* prepare length block: */ - movq %rdx, MSG - movq %rcx, T0 - pslldq $8, T0 - pxor T0, MSG - psllq $3, MSG /* multiply by 8 (to get bit count) */ - - /* update state: */ - call __morus640_update - call __morus640_update - call __morus640_update - call __morus640_update - call __morus640_update - call __morus640_update - call __morus640_update - call __morus640_update - call __morus640_update - call __morus640_update - - /* xor tag: */ - movdqu (%rsi), MSG - - pxor STATE0, MSG - pshufd $MASK3, STATE1, T0 - pxor T0, MSG - movdqa STATE2, T0 - pand STATE3, T0 - pxor T0, MSG - - movdqu MSG, (%rsi) - - FRAME_END - ret -ENDPROC(crypto_morus640_sse2_final) diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c deleted file mode 100644 index 8ef68134aef4..000000000000 --- a/arch/x86/crypto/morus640-sse2-glue.c +++ /dev/null @@ -1,61 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * The MORUS-640 Authenticated-Encryption Algorithm - * Glue for SSE2 implementation - * - * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <crypto/internal/aead.h> -#include <crypto/internal/simd.h> -#include <crypto/morus640_glue.h> -#include <linux/module.h> -#include <asm/fpu/api.h> -#include <asm/cpu_device_id.h> - -asmlinkage void crypto_morus640_sse2_init(void *state, const void *key, - const void *iv); -asmlinkage void crypto_morus640_sse2_ad(void *state, const void *data, - unsigned int length); - -asmlinkage void crypto_morus640_sse2_enc(void *state, const void *src, - void *dst, unsigned int length); -asmlinkage void crypto_morus640_sse2_dec(void *state, const void *src, - void *dst, unsigned int length); - -asmlinkage void crypto_morus640_sse2_enc_tail(void *state, const void *src, - void *dst, unsigned int length); -asmlinkage void crypto_morus640_sse2_dec_tail(void *state, const void *src, - void *dst, unsigned int length); - -asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor, - u64 assoclen, u64 cryptlen); - -MORUS640_DECLARE_ALG(sse2, "morus640-sse2", 400); - -static struct simd_aead_alg *simd_alg; - -static int __init crypto_morus640_sse2_module_init(void) -{ - if (!boot_cpu_has(X86_FEATURE_XMM2) || - !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) - return -ENODEV; - - return simd_register_aeads_compat(&crypto_morus640_sse2_alg, 1, - &simd_alg); -} - -static void __exit crypto_morus640_sse2_module_exit(void) -{ - simd_unregister_aeads(&crypto_morus640_sse2_alg, 1, &simd_alg); -} - -module_init(crypto_morus640_sse2_module_init); -module_exit(crypto_morus640_sse2_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>"); -MODULE_DESCRIPTION("MORUS-640 AEAD algorithm -- SSE2 implementation"); -MODULE_ALIAS_CRYPTO("morus640"); -MODULE_ALIAS_CRYPTO("morus640-sse2"); diff --git a/arch/x86/crypto/morus640_glue.c b/arch/x86/crypto/morus640_glue.c deleted file mode 100644 index d8b5fd6cef29..000000000000 --- a/arch/x86/crypto/morus640_glue.c +++ /dev/null @@ -1,200 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * The MORUS-640 Authenticated-Encryption Algorithm - * Common x86 SIMD glue skeleton - * - * Copyright (c) 2016-2018 Ondrej Mosnacek <omosnacek@gmail.com> - * Copyright (C) 2017-2018 Red Hat, Inc. All rights reserved. - */ - -#include <crypto/internal/aead.h> -#include <crypto/internal/skcipher.h> -#include <crypto/morus640_glue.h> -#include <crypto/scatterwalk.h> -#include <linux/err.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/scatterlist.h> -#include <asm/fpu/api.h> - -struct morus640_state { - struct morus640_block s[MORUS_STATE_BLOCKS]; -}; - -struct morus640_ops { - int (*skcipher_walk_init)(struct skcipher_walk *walk, - struct aead_request *req, bool atomic); - - void (*crypt_blocks)(void *state, const void *src, void *dst, - unsigned int length); - void (*crypt_tail)(void *state, const void *src, void *dst, - unsigned int length); -}; - -static void crypto_morus640_glue_process_ad( - struct morus640_state *state, - const struct morus640_glue_ops *ops, - struct scatterlist *sg_src, unsigned int assoclen) -{ - struct scatter_walk walk; - struct morus640_block buf; - unsigned int pos = 0; - - scatterwalk_start(&walk, sg_src); - while (assoclen != 0) { - unsigned int size = scatterwalk_clamp(&walk, assoclen); - unsigned int left = size; - void *mapped = scatterwalk_map(&walk); - const u8 *src = (const u8 *)mapped; - - if (pos + size >= MORUS640_BLOCK_SIZE) { - if (pos > 0) { - unsigned int fill = MORUS640_BLOCK_SIZE - pos; - memcpy(buf.bytes + pos, src, fill); - ops->ad(state, buf.bytes, MORUS640_BLOCK_SIZE); - pos = 0; - left -= fill; - src += fill; - } - - ops->ad(state, src, left); - src += left & ~(MORUS640_BLOCK_SIZE - 1); - left &= MORUS640_BLOCK_SIZE - 1; - } - - memcpy(buf.bytes + pos, src, left); - - pos += left; - assoclen -= size; - scatterwalk_unmap(mapped); - scatterwalk_advance(&walk, size); - scatterwalk_done(&walk, 0, assoclen); - } - - if (pos > 0) { - memset(buf.bytes + pos, 0, MORUS640_BLOCK_SIZE - pos); - ops->ad(state, buf.bytes, MORUS640_BLOCK_SIZE); - } -} - -static void crypto_morus640_glue_process_crypt(struct morus640_state *state, - struct morus640_ops ops, - struct skcipher_walk *walk) -{ - while (walk->nbytes >= MORUS640_BLOCK_SIZE) { - ops.crypt_blocks(state, walk->src.virt.addr, - walk->dst.virt.addr, - round_down(walk->nbytes, MORUS640_BLOCK_SIZE)); - skcipher_walk_done(walk, walk->nbytes % MORUS640_BLOCK_SIZE); - } - - if (walk->nbytes) { - ops.crypt_tail(state, walk->src.virt.addr, walk->dst.virt.addr, - walk->nbytes); - skcipher_walk_done(walk, 0); - } -} - -int crypto_morus640_glue_setkey(struct crypto_aead *aead, const u8 *key, - unsigned int keylen) -{ - struct morus640_ctx *ctx = crypto_aead_ctx(aead); - - if (keylen != MORUS640_BLOCK_SIZE) { - crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); - return -EINVAL; - } - - memcpy(ctx->key.bytes, key, MORUS640_BLOCK_SIZE); - return 0; -} -EXPORT_SYMBOL_GPL(crypto_morus640_glue_setkey); - -int crypto_morus640_glue_setauthsize(struct crypto_aead *tfm, - unsigned int authsize) -{ - return (authsize <= MORUS_MAX_AUTH_SIZE) ? 0 : -EINVAL; -} -EXPORT_SYMBOL_GPL(crypto_morus640_glue_setauthsize); - -static void crypto_morus640_glue_crypt(struct aead_request *req, - struct morus640_ops ops, - unsigned int cryptlen, - struct morus640_block *tag_xor) -{ - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct morus640_ctx *ctx = crypto_aead_ctx(tfm); - struct morus640_state state; - struct skcipher_walk walk; - - ops.skcipher_walk_init(&walk, req, true); - - kernel_fpu_begin(); - - ctx->ops->init(&state, &ctx->key, req->iv); - crypto_morus640_glue_process_ad(&state, ctx->ops, req->src, req->assoclen); - crypto_morus640_glue_process_crypt(&state, ops, &walk); - ctx->ops->final(&state, tag_xor, req->assoclen, cryptlen); - - kernel_fpu_end(); -} - -int crypto_morus640_glue_encrypt(struct aead_request *req) -{ - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct morus640_ctx *ctx = crypto_aead_ctx(tfm); - struct morus640_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_encrypt, - .crypt_blocks = ctx->ops->enc, - .crypt_tail = ctx->ops->enc_tail, - }; - - struct morus640_block tag = {}; - unsigned int authsize = crypto_aead_authsize(tfm); - unsigned int cryptlen = req->cryptlen; - - crypto_morus640_glue_crypt(req, OPS, cryptlen, &tag); - - scatterwalk_map_and_copy(tag.bytes, req->dst, - req->assoclen + cryptlen, authsize, 1); - return 0; -} -EXPORT_SYMBOL_GPL(crypto_morus640_glue_encrypt); - -int crypto_morus640_glue_decrypt(struct aead_request *req) -{ - static const u8 zeros[MORUS640_BLOCK_SIZE] = {}; - - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct morus640_ctx *ctx = crypto_aead_ctx(tfm); - struct morus640_ops OPS = { - .skcipher_walk_init = skcipher_walk_aead_decrypt, - .crypt_blocks = ctx->ops->dec, - .crypt_tail = ctx->ops->dec_tail, - }; - - struct morus640_block tag; - unsigned int authsize = crypto_aead_authsize(tfm); - unsigned int cryptlen = req->cryptlen - authsize; - - scatterwalk_map_and_copy(tag.bytes, req->src, - req->assoclen + cryptlen, authsize, 0); - - crypto_morus640_glue_crypt(req, OPS, cryptlen, &tag); - - return crypto_memneq(tag.bytes, zeros, authsize) ? -EBADMSG : 0; -} -EXPORT_SYMBOL_GPL(crypto_morus640_glue_decrypt); - -void crypto_morus640_glue_init_ops(struct crypto_aead *aead, - const struct morus640_glue_ops *ops) -{ - struct morus640_ctx *ctx = crypto_aead_ctx(aead); - ctx->ops = ops; -} -EXPORT_SYMBOL_GPL(crypto_morus640_glue_init_ops); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>"); -MODULE_DESCRIPTION("MORUS-640 AEAD mode -- glue for x86 optimizations"); diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S index f7946ea1b704..b22c7b936272 100644 --- a/arch/x86/crypto/nh-avx2-x86_64.S +++ b/arch/x86/crypto/nh-avx2-x86_64.S @@ -69,7 +69,7 @@ * * It's guaranteed that message_len % 16 == 0. */ -ENTRY(nh_avx2) +SYM_FUNC_START(nh_avx2) vmovdqu 0x00(KEY), K0 vmovdqu 0x10(KEY), K1 @@ -154,4 +154,4 @@ ENTRY(nh_avx2) vpaddq T4, T0, T0 vmovdqu T0, (HASH) ret -ENDPROC(nh_avx2) +SYM_FUNC_END(nh_avx2) diff --git a/arch/x86/crypto/nh-sse2-x86_64.S b/arch/x86/crypto/nh-sse2-x86_64.S index 51f52d4ab4bb..d7ae22dd6683 100644 --- a/arch/x86/crypto/nh-sse2-x86_64.S +++ b/arch/x86/crypto/nh-sse2-x86_64.S @@ -71,7 +71,7 @@ * * It's guaranteed that message_len % 16 == 0. */ -ENTRY(nh_sse2) +SYM_FUNC_START(nh_sse2) movdqu 0x00(KEY), K0 movdqu 0x10(KEY), K1 @@ -120,4 +120,4 @@ ENTRY(nh_sse2) movdqu T0, 0x00(HASH) movdqu T1, 0x10(HASH) ret -ENDPROC(nh_sse2) +SYM_FUNC_END(nh_sse2) diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S deleted file mode 100644 index 8b341bc29d41..000000000000 --- a/arch/x86/crypto/poly1305-avx2-x86_64.S +++ /dev/null @@ -1,390 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Poly1305 authenticator algorithm, RFC7539, x64 AVX2 functions - * - * Copyright (C) 2015 Martin Willi - */ - -#include <linux/linkage.h> - -.section .rodata.cst32.ANMASK, "aM", @progbits, 32 -.align 32 -ANMASK: .octa 0x0000000003ffffff0000000003ffffff - .octa 0x0000000003ffffff0000000003ffffff - -.section .rodata.cst32.ORMASK, "aM", @progbits, 32 -.align 32 -ORMASK: .octa 0x00000000010000000000000001000000 - .octa 0x00000000010000000000000001000000 - -.text - -#define h0 0x00(%rdi) -#define h1 0x04(%rdi) -#define h2 0x08(%rdi) -#define h3 0x0c(%rdi) -#define h4 0x10(%rdi) -#define r0 0x00(%rdx) -#define r1 0x04(%rdx) -#define r2 0x08(%rdx) -#define r3 0x0c(%rdx) -#define r4 0x10(%rdx) -#define u0 0x00(%r8) -#define u1 0x04(%r8) -#define u2 0x08(%r8) -#define u3 0x0c(%r8) -#define u4 0x10(%r8) -#define w0 0x14(%r8) -#define w1 0x18(%r8) -#define w2 0x1c(%r8) -#define w3 0x20(%r8) -#define w4 0x24(%r8) -#define y0 0x28(%r8) -#define y1 0x2c(%r8) -#define y2 0x30(%r8) -#define y3 0x34(%r8) -#define y4 0x38(%r8) -#define m %rsi -#define hc0 %ymm0 -#define hc1 %ymm1 -#define hc2 %ymm2 -#define hc3 %ymm3 -#define hc4 %ymm4 -#define hc0x %xmm0 -#define hc1x %xmm1 -#define hc2x %xmm2 -#define hc3x %xmm3 -#define hc4x %xmm4 -#define t1 %ymm5 -#define t2 %ymm6 -#define t1x %xmm5 -#define t2x %xmm6 -#define ruwy0 %ymm7 -#define ruwy1 %ymm8 -#define ruwy2 %ymm9 -#define ruwy3 %ymm10 -#define ruwy4 %ymm11 -#define ruwy0x %xmm7 -#define ruwy1x %xmm8 -#define ruwy2x %xmm9 -#define ruwy3x %xmm10 -#define ruwy4x %xmm11 -#define svxz1 %ymm12 -#define svxz2 %ymm13 -#define svxz3 %ymm14 -#define svxz4 %ymm15 -#define d0 %r9 -#define d1 %r10 -#define d2 %r11 -#define d3 %r12 -#define d4 %r13 - -ENTRY(poly1305_4block_avx2) - # %rdi: Accumulator h[5] - # %rsi: 64 byte input block m - # %rdx: Poly1305 key r[5] - # %rcx: Quadblock count - # %r8: Poly1305 derived key r^2 u[5], r^3 w[5], r^4 y[5], - - # This four-block variant uses loop unrolled block processing. It - # requires 4 Poly1305 keys: r, r^2, r^3 and r^4: - # h = (h + m) * r => h = (h + m1) * r^4 + m2 * r^3 + m3 * r^2 + m4 * r - - vzeroupper - push %rbx - push %r12 - push %r13 - - # combine r0,u0,w0,y0 - vmovd y0,ruwy0x - vmovd w0,t1x - vpunpcklqdq t1,ruwy0,ruwy0 - vmovd u0,t1x - vmovd r0,t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,ruwy0,ruwy0 - - # combine r1,u1,w1,y1 and s1=r1*5,v1=u1*5,x1=w1*5,z1=y1*5 - vmovd y1,ruwy1x - vmovd w1,t1x - vpunpcklqdq t1,ruwy1,ruwy1 - vmovd u1,t1x - vmovd r1,t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,ruwy1,ruwy1 - vpslld $2,ruwy1,svxz1 - vpaddd ruwy1,svxz1,svxz1 - - # combine r2,u2,w2,y2 and s2=r2*5,v2=u2*5,x2=w2*5,z2=y2*5 - vmovd y2,ruwy2x - vmovd w2,t1x - vpunpcklqdq t1,ruwy2,ruwy2 - vmovd u2,t1x - vmovd r2,t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,ruwy2,ruwy2 - vpslld $2,ruwy2,svxz2 - vpaddd ruwy2,svxz2,svxz2 - - # combine r3,u3,w3,y3 and s3=r3*5,v3=u3*5,x3=w3*5,z3=y3*5 - vmovd y3,ruwy3x - vmovd w3,t1x - vpunpcklqdq t1,ruwy3,ruwy3 - vmovd u3,t1x - vmovd r3,t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,ruwy3,ruwy3 - vpslld $2,ruwy3,svxz3 - vpaddd ruwy3,svxz3,svxz3 - - # combine r4,u4,w4,y4 and s4=r4*5,v4=u4*5,x4=w4*5,z4=y4*5 - vmovd y4,ruwy4x - vmovd w4,t1x - vpunpcklqdq t1,ruwy4,ruwy4 - vmovd u4,t1x - vmovd r4,t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,ruwy4,ruwy4 - vpslld $2,ruwy4,svxz4 - vpaddd ruwy4,svxz4,svxz4 - -.Ldoblock4: - # hc0 = [m[48-51] & 0x3ffffff, m[32-35] & 0x3ffffff, - # m[16-19] & 0x3ffffff, m[ 0- 3] & 0x3ffffff + h0] - vmovd 0x00(m),hc0x - vmovd 0x10(m),t1x - vpunpcklqdq t1,hc0,hc0 - vmovd 0x20(m),t1x - vmovd 0x30(m),t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,hc0,hc0 - vpand ANMASK(%rip),hc0,hc0 - vmovd h0,t1x - vpaddd t1,hc0,hc0 - # hc1 = [(m[51-54] >> 2) & 0x3ffffff, (m[35-38] >> 2) & 0x3ffffff, - # (m[19-22] >> 2) & 0x3ffffff, (m[ 3- 6] >> 2) & 0x3ffffff + h1] - vmovd 0x03(m),hc1x - vmovd 0x13(m),t1x - vpunpcklqdq t1,hc1,hc1 - vmovd 0x23(m),t1x - vmovd 0x33(m),t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,hc1,hc1 - vpsrld $2,hc1,hc1 - vpand ANMASK(%rip),hc1,hc1 - vmovd h1,t1x - vpaddd t1,hc1,hc1 - # hc2 = [(m[54-57] >> 4) & 0x3ffffff, (m[38-41] >> 4) & 0x3ffffff, - # (m[22-25] >> 4) & 0x3ffffff, (m[ 6- 9] >> 4) & 0x3ffffff + h2] - vmovd 0x06(m),hc2x - vmovd 0x16(m),t1x - vpunpcklqdq t1,hc2,hc2 - vmovd 0x26(m),t1x - vmovd 0x36(m),t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,hc2,hc2 - vpsrld $4,hc2,hc2 - vpand ANMASK(%rip),hc2,hc2 - vmovd h2,t1x - vpaddd t1,hc2,hc2 - # hc3 = [(m[57-60] >> 6) & 0x3ffffff, (m[41-44] >> 6) & 0x3ffffff, - # (m[25-28] >> 6) & 0x3ffffff, (m[ 9-12] >> 6) & 0x3ffffff + h3] - vmovd 0x09(m),hc3x - vmovd 0x19(m),t1x - vpunpcklqdq t1,hc3,hc3 - vmovd 0x29(m),t1x - vmovd 0x39(m),t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,hc3,hc3 - vpsrld $6,hc3,hc3 - vpand ANMASK(%rip),hc3,hc3 - vmovd h3,t1x - vpaddd t1,hc3,hc3 - # hc4 = [(m[60-63] >> 8) | (1<<24), (m[44-47] >> 8) | (1<<24), - # (m[28-31] >> 8) | (1<<24), (m[12-15] >> 8) | (1<<24) + h4] - vmovd 0x0c(m),hc4x - vmovd 0x1c(m),t1x - vpunpcklqdq t1,hc4,hc4 - vmovd 0x2c(m),t1x - vmovd 0x3c(m),t2x - vpunpcklqdq t2,t1,t1 - vperm2i128 $0x20,t1,hc4,hc4 - vpsrld $8,hc4,hc4 - vpor ORMASK(%rip),hc4,hc4 - vmovd h4,t1x - vpaddd t1,hc4,hc4 - - # t1 = [ hc0[3] * r0, hc0[2] * u0, hc0[1] * w0, hc0[0] * y0 ] - vpmuludq hc0,ruwy0,t1 - # t1 += [ hc1[3] * s4, hc1[2] * v4, hc1[1] * x4, hc1[0] * z4 ] - vpmuludq hc1,svxz4,t2 - vpaddq t2,t1,t1 - # t1 += [ hc2[3] * s3, hc2[2] * v3, hc2[1] * x3, hc2[0] * z3 ] - vpmuludq hc2,svxz3,t2 - vpaddq t2,t1,t1 - # t1 += [ hc3[3] * s2, hc3[2] * v2, hc3[1] * x2, hc3[0] * z2 ] - vpmuludq hc3,svxz2,t2 - vpaddq t2,t1,t1 - # t1 += [ hc4[3] * s1, hc4[2] * v1, hc4[1] * x1, hc4[0] * z1 ] - vpmuludq hc4,svxz1,t2 - vpaddq t2,t1,t1 - # d0 = t1[0] + t1[1] + t[2] + t[3] - vpermq $0xee,t1,t2 - vpaddq t2,t1,t1 - vpsrldq $8,t1,t2 - vpaddq t2,t1,t1 - vmovq t1x,d0 - - # t1 = [ hc0[3] * r1, hc0[2] * u1,hc0[1] * w1, hc0[0] * y1 ] - vpmuludq hc0,ruwy1,t1 - # t1 += [ hc1[3] * r0, hc1[2] * u0, hc1[1] * w0, hc1[0] * y0 ] - vpmuludq hc1,ruwy0,t2 - vpaddq t2,t1,t1 - # t1 += [ hc2[3] * s4, hc2[2] * v4, hc2[1] * x4, hc2[0] * z4 ] - vpmuludq hc2,svxz4,t2 - vpaddq t2,t1,t1 - # t1 += [ hc3[3] * s3, hc3[2] * v3, hc3[1] * x3, hc3[0] * z3 ] - vpmuludq hc3,svxz3,t2 - vpaddq t2,t1,t1 - # t1 += [ hc4[3] * s2, hc4[2] * v2, hc4[1] * x2, hc4[0] * z2 ] - vpmuludq hc4,svxz2,t2 - vpaddq t2,t1,t1 - # d1 = t1[0] + t1[1] + t1[3] + t1[4] - vpermq $0xee,t1,t2 - vpaddq t2,t1,t1 - vpsrldq $8,t1,t2 - vpaddq t2,t1,t1 - vmovq t1x,d1 - - # t1 = [ hc0[3] * r2, hc0[2] * u2, hc0[1] * w2, hc0[0] * y2 ] - vpmuludq hc0,ruwy2,t1 - # t1 += [ hc1[3] * r1, hc1[2] * u1, hc1[1] * w1, hc1[0] * y1 ] - vpmuludq hc1,ruwy1,t2 - vpaddq t2,t1,t1 - # t1 += [ hc2[3] * r0, hc2[2] * u0, hc2[1] * w0, hc2[0] * y0 ] - vpmuludq hc2,ruwy0,t2 - vpaddq t2,t1,t1 - # t1 += [ hc3[3] * s4, hc3[2] * v4, hc3[1] * x4, hc3[0] * z4 ] - vpmuludq hc3,svxz4,t2 - vpaddq t2,t1,t1 - # t1 += [ hc4[3] * s3, hc4[2] * v3, hc4[1] * x3, hc4[0] * z3 ] - vpmuludq hc4,svxz3,t2 - vpaddq t2,t1,t1 - # d2 = t1[0] + t1[1] + t1[2] + t1[3] - vpermq $0xee,t1,t2 - vpaddq t2,t1,t1 - vpsrldq $8,t1,t2 - vpaddq t2,t1,t1 - vmovq t1x,d2 - - # t1 = [ hc0[3] * r3, hc0[2] * u3, hc0[1] * w3, hc0[0] * y3 ] - vpmuludq hc0,ruwy3,t1 - # t1 += [ hc1[3] * r2, hc1[2] * u2, hc1[1] * w2, hc1[0] * y2 ] - vpmuludq hc1,ruwy2,t2 - vpaddq t2,t1,t1 - # t1 += [ hc2[3] * r1, hc2[2] * u1, hc2[1] * w1, hc2[0] * y1 ] - vpmuludq hc2,ruwy1,t2 - vpaddq t2,t1,t1 - # t1 += [ hc3[3] * r0, hc3[2] * u0, hc3[1] * w0, hc3[0] * y0 ] - vpmuludq hc3,ruwy0,t2 - vpaddq t2,t1,t1 - # t1 += [ hc4[3] * s4, hc4[2] * v4, hc4[1] * x4, hc4[0] * z4 ] - vpmuludq hc4,svxz4,t2 - vpaddq t2,t1,t1 - # d3 = t1[0] + t1[1] + t1[2] + t1[3] - vpermq $0xee,t1,t2 - vpaddq t2,t1,t1 - vpsrldq $8,t1,t2 - vpaddq t2,t1,t1 - vmovq t1x,d3 - - # t1 = [ hc0[3] * r4, hc0[2] * u4, hc0[1] * w4, hc0[0] * y4 ] - vpmuludq hc0,ruwy4,t1 - # t1 += [ hc1[3] * r3, hc1[2] * u3, hc1[1] * w3, hc1[0] * y3 ] - vpmuludq hc1,ruwy3,t2 - vpaddq t2,t1,t1 - # t1 += [ hc2[3] * r2, hc2[2] * u2, hc2[1] * w2, hc2[0] * y2 ] - vpmuludq hc2,ruwy2,t2 - vpaddq t2,t1,t1 - # t1 += [ hc3[3] * r1, hc3[2] * u1, hc3[1] * w1, hc3[0] * y1 ] - vpmuludq hc3,ruwy1,t2 - vpaddq t2,t1,t1 - # t1 += [ hc4[3] * r0, hc4[2] * u0, hc4[1] * w0, hc4[0] * y0 ] - vpmuludq hc4,ruwy0,t2 - vpaddq t2,t1,t1 - # d4 = t1[0] + t1[1] + t1[2] + t1[3] - vpermq $0xee,t1,t2 - vpaddq t2,t1,t1 - vpsrldq $8,t1,t2 - vpaddq t2,t1,t1 - vmovq t1x,d4 - - # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> - # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small - # amount. Careful: we must not assume the carry bits 'd0 >> 26', - # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit - # integers. It's true in a single-block implementation, but not here. - - # d1 += d0 >> 26 - mov d0,%rax - shr $26,%rax - add %rax,d1 - # h0 = d0 & 0x3ffffff - mov d0,%rbx - and $0x3ffffff,%ebx - - # d2 += d1 >> 26 - mov d1,%rax - shr $26,%rax - add %rax,d2 - # h1 = d1 & 0x3ffffff - mov d1,%rax - and $0x3ffffff,%eax - mov %eax,h1 - - # d3 += d2 >> 26 - mov d2,%rax - shr $26,%rax - add %rax,d3 - # h2 = d2 & 0x3ffffff - mov d2,%rax - and $0x3ffffff,%eax - mov %eax,h2 - - # d4 += d3 >> 26 - mov d3,%rax - shr $26,%rax - add %rax,d4 - # h3 = d3 & 0x3ffffff - mov d3,%rax - and $0x3ffffff,%eax - mov %eax,h3 - - # h0 += (d4 >> 26) * 5 - mov d4,%rax - shr $26,%rax - lea (%rax,%rax,4),%rax - add %rax,%rbx - # h4 = d4 & 0x3ffffff - mov d4,%rax - and $0x3ffffff,%eax - mov %eax,h4 - - # h1 += h0 >> 26 - mov %rbx,%rax - shr $26,%rax - add %eax,h1 - # h0 = h0 & 0x3ffffff - andl $0x3ffffff,%ebx - mov %ebx,h0 - - add $0x40,m - dec %rcx - jnz .Ldoblock4 - - vzeroupper - pop %r13 - pop %r12 - pop %rbx - ret -ENDPROC(poly1305_4block_avx2) diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S deleted file mode 100644 index 5578f846e622..000000000000 --- a/arch/x86/crypto/poly1305-sse2-x86_64.S +++ /dev/null @@ -1,590 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Poly1305 authenticator algorithm, RFC7539, x64 SSE2 functions - * - * Copyright (C) 2015 Martin Willi - */ - -#include <linux/linkage.h> - -.section .rodata.cst16.ANMASK, "aM", @progbits, 16 -.align 16 -ANMASK: .octa 0x0000000003ffffff0000000003ffffff - -.section .rodata.cst16.ORMASK, "aM", @progbits, 16 -.align 16 -ORMASK: .octa 0x00000000010000000000000001000000 - -.text - -#define h0 0x00(%rdi) -#define h1 0x04(%rdi) -#define h2 0x08(%rdi) -#define h3 0x0c(%rdi) -#define h4 0x10(%rdi) -#define r0 0x00(%rdx) -#define r1 0x04(%rdx) -#define r2 0x08(%rdx) -#define r3 0x0c(%rdx) -#define r4 0x10(%rdx) -#define s1 0x00(%rsp) -#define s2 0x04(%rsp) -#define s3 0x08(%rsp) -#define s4 0x0c(%rsp) -#define m %rsi -#define h01 %xmm0 -#define h23 %xmm1 -#define h44 %xmm2 -#define t1 %xmm3 -#define t2 %xmm4 -#define t3 %xmm5 -#define t4 %xmm6 -#define mask %xmm7 -#define d0 %r8 -#define d1 %r9 -#define d2 %r10 -#define d3 %r11 -#define d4 %r12 - -ENTRY(poly1305_block_sse2) - # %rdi: Accumulator h[5] - # %rsi: 16 byte input block m - # %rdx: Poly1305 key r[5] - # %rcx: Block count - - # This single block variant tries to improve performance by doing two - # multiplications in parallel using SSE instructions. There is quite - # some quardword packing involved, hence the speedup is marginal. - - push %rbx - push %r12 - sub $0x10,%rsp - - # s1..s4 = r1..r4 * 5 - mov r1,%eax - lea (%eax,%eax,4),%eax - mov %eax,s1 - mov r2,%eax - lea (%eax,%eax,4),%eax - mov %eax,s2 - mov r3,%eax - lea (%eax,%eax,4),%eax - mov %eax,s3 - mov r4,%eax - lea (%eax,%eax,4),%eax - mov %eax,s4 - - movdqa ANMASK(%rip),mask - -.Ldoblock: - # h01 = [0, h1, 0, h0] - # h23 = [0, h3, 0, h2] - # h44 = [0, h4, 0, h4] - movd h0,h01 - movd h1,t1 - movd h2,h23 - movd h3,t2 - movd h4,h44 - punpcklqdq t1,h01 - punpcklqdq t2,h23 - punpcklqdq h44,h44 - - # h01 += [ (m[3-6] >> 2) & 0x3ffffff, m[0-3] & 0x3ffffff ] - movd 0x00(m),t1 - movd 0x03(m),t2 - psrld $2,t2 - punpcklqdq t2,t1 - pand mask,t1 - paddd t1,h01 - # h23 += [ (m[9-12] >> 6) & 0x3ffffff, (m[6-9] >> 4) & 0x3ffffff ] - movd 0x06(m),t1 - movd 0x09(m),t2 - psrld $4,t1 - psrld $6,t2 - punpcklqdq t2,t1 - pand mask,t1 - paddd t1,h23 - # h44 += [ (m[12-15] >> 8) | (1 << 24), (m[12-15] >> 8) | (1 << 24) ] - mov 0x0c(m),%eax - shr $8,%eax - or $0x01000000,%eax - movd %eax,t1 - pshufd $0xc4,t1,t1 - paddd t1,h44 - - # t1[0] = h0 * r0 + h2 * s3 - # t1[1] = h1 * s4 + h3 * s2 - movd r0,t1 - movd s4,t2 - punpcklqdq t2,t1 - pmuludq h01,t1 - movd s3,t2 - movd s2,t3 - punpcklqdq t3,t2 - pmuludq h23,t2 - paddq t2,t1 - # t2[0] = h0 * r1 + h2 * s4 - # t2[1] = h1 * r0 + h3 * s3 - movd r1,t2 - movd r0,t3 - punpcklqdq t3,t2 - pmuludq h01,t2 - movd s4,t3 - movd s3,t4 - punpcklqdq t4,t3 - pmuludq h23,t3 - paddq t3,t2 - # t3[0] = h4 * s1 - # t3[1] = h4 * s2 - movd s1,t3 - movd s2,t4 - punpcklqdq t4,t3 - pmuludq h44,t3 - # d0 = t1[0] + t1[1] + t3[0] - # d1 = t2[0] + t2[1] + t3[1] - movdqa t1,t4 - punpcklqdq t2,t4 - punpckhqdq t2,t1 - paddq t4,t1 - paddq t3,t1 - movq t1,d0 - psrldq $8,t1 - movq t1,d1 - - # t1[0] = h0 * r2 + h2 * r0 - # t1[1] = h1 * r1 + h3 * s4 - movd r2,t1 - movd r1,t2 - punpcklqdq t2,t1 - pmuludq h01,t1 - movd r0,t2 - movd s4,t3 - punpcklqdq t3,t2 - pmuludq h23,t2 - paddq t2,t1 - # t2[0] = h0 * r3 + h2 * r1 - # t2[1] = h1 * r2 + h3 * r0 - movd r3,t2 - movd r2,t3 - punpcklqdq t3,t2 - pmuludq h01,t2 - movd r1,t3 - movd r0,t4 - punpcklqdq t4,t3 - pmuludq h23,t3 - paddq t3,t2 - # t3[0] = h4 * s3 - # t3[1] = h4 * s4 - movd s3,t3 - movd s4,t4 - punpcklqdq t4,t3 - pmuludq h44,t3 - # d2 = t1[0] + t1[1] + t3[0] - # d3 = t2[0] + t2[1] + t3[1] - movdqa t1,t4 - punpcklqdq t2,t4 - punpckhqdq t2,t1 - paddq t4,t1 - paddq t3,t1 - movq t1,d2 - psrldq $8,t1 - movq t1,d3 - - # t1[0] = h0 * r4 + h2 * r2 - # t1[1] = h1 * r3 + h3 * r1 - movd r4,t1 - movd r3,t2 - punpcklqdq t2,t1 - pmuludq h01,t1 - movd r2,t2 - movd r1,t3 - punpcklqdq t3,t2 - pmuludq h23,t2 - paddq t2,t1 - # t3[0] = h4 * r0 - movd r0,t3 - pmuludq h44,t3 - # d4 = t1[0] + t1[1] + t3[0] - movdqa t1,t4 - psrldq $8,t4 - paddq t4,t1 - paddq t3,t1 - movq t1,d4 - - # d1 += d0 >> 26 - mov d0,%rax - shr $26,%rax - add %rax,d1 - # h0 = d0 & 0x3ffffff - mov d0,%rbx - and $0x3ffffff,%ebx - - # d2 += d1 >> 26 - mov d1,%rax - shr $26,%rax - add %rax,d2 - # h1 = d1 & 0x3ffffff - mov d1,%rax - and $0x3ffffff,%eax - mov %eax,h1 - - # d3 += d2 >> 26 - mov d2,%rax - shr $26,%rax - add %rax,d3 - # h2 = d2 & 0x3ffffff - mov d2,%rax - and $0x3ffffff,%eax - mov %eax,h2 - - # d4 += d3 >> 26 - mov d3,%rax - shr $26,%rax - add %rax,d4 - # h3 = d3 & 0x3ffffff - mov d3,%rax - and $0x3ffffff,%eax - mov %eax,h3 - - # h0 += (d4 >> 26) * 5 - mov d4,%rax - shr $26,%rax - lea (%rax,%rax,4),%rax - add %rax,%rbx - # h4 = d4 & 0x3ffffff - mov d4,%rax - and $0x3ffffff,%eax - mov %eax,h4 - - # h1 += h0 >> 26 - mov %rbx,%rax - shr $26,%rax - add %eax,h1 - # h0 = h0 & 0x3ffffff - andl $0x3ffffff,%ebx - mov %ebx,h0 - - add $0x10,m - dec %rcx - jnz .Ldoblock - - # Zeroing of key material - mov %rcx,0x00(%rsp) - mov %rcx,0x08(%rsp) - - add $0x10,%rsp - pop %r12 - pop %rbx - ret -ENDPROC(poly1305_block_sse2) - - -#define u0 0x00(%r8) -#define u1 0x04(%r8) -#define u2 0x08(%r8) -#define u3 0x0c(%r8) -#define u4 0x10(%r8) -#define hc0 %xmm0 -#define hc1 %xmm1 -#define hc2 %xmm2 -#define hc3 %xmm5 -#define hc4 %xmm6 -#define ru0 %xmm7 -#define ru1 %xmm8 -#define ru2 %xmm9 -#define ru3 %xmm10 -#define ru4 %xmm11 -#define sv1 %xmm12 -#define sv2 %xmm13 -#define sv3 %xmm14 -#define sv4 %xmm15 -#undef d0 -#define d0 %r13 - -ENTRY(poly1305_2block_sse2) - # %rdi: Accumulator h[5] - # %rsi: 16 byte input block m - # %rdx: Poly1305 key r[5] - # %rcx: Doubleblock count - # %r8: Poly1305 derived key r^2 u[5] - - # This two-block variant further improves performance by using loop - # unrolled block processing. This is more straight forward and does - # less byte shuffling, but requires a second Poly1305 key r^2: - # h = (h + m) * r => h = (h + m1) * r^2 + m2 * r - - push %rbx - push %r12 - push %r13 - - # combine r0,u0 - movd u0,ru0 - movd r0,t1 - punpcklqdq t1,ru0 - - # combine r1,u1 and s1=r1*5,v1=u1*5 - movd u1,ru1 - movd r1,t1 - punpcklqdq t1,ru1 - movdqa ru1,sv1 - pslld $2,sv1 - paddd ru1,sv1 - - # combine r2,u2 and s2=r2*5,v2=u2*5 - movd u2,ru2 - movd r2,t1 - punpcklqdq t1,ru2 - movdqa ru2,sv2 - pslld $2,sv2 - paddd ru2,sv2 - - # combine r3,u3 and s3=r3*5,v3=u3*5 - movd u3,ru3 - movd r3,t1 - punpcklqdq t1,ru3 - movdqa ru3,sv3 - pslld $2,sv3 - paddd ru3,sv3 - - # combine r4,u4 and s4=r4*5,v4=u4*5 - movd u4,ru4 - movd r4,t1 - punpcklqdq t1,ru4 - movdqa ru4,sv4 - pslld $2,sv4 - paddd ru4,sv4 - -.Ldoblock2: - # hc0 = [ m[16-19] & 0x3ffffff, h0 + m[0-3] & 0x3ffffff ] - movd 0x00(m),hc0 - movd 0x10(m),t1 - punpcklqdq t1,hc0 - pand ANMASK(%rip),hc0 - movd h0,t1 - paddd t1,hc0 - # hc1 = [ (m[19-22] >> 2) & 0x3ffffff, h1 + (m[3-6] >> 2) & 0x3ffffff ] - movd 0x03(m),hc1 - movd 0x13(m),t1 - punpcklqdq t1,hc1 - psrld $2,hc1 - pand ANMASK(%rip),hc1 - movd h1,t1 - paddd t1,hc1 - # hc2 = [ (m[22-25] >> 4) & 0x3ffffff, h2 + (m[6-9] >> 4) & 0x3ffffff ] - movd 0x06(m),hc2 - movd 0x16(m),t1 - punpcklqdq t1,hc2 - psrld $4,hc2 - pand ANMASK(%rip),hc2 - movd h2,t1 - paddd t1,hc2 - # hc3 = [ (m[25-28] >> 6) & 0x3ffffff, h3 + (m[9-12] >> 6) & 0x3ffffff ] - movd 0x09(m),hc3 - movd 0x19(m),t1 - punpcklqdq t1,hc3 - psrld $6,hc3 - pand ANMASK(%rip),hc3 - movd h3,t1 - paddd t1,hc3 - # hc4 = [ (m[28-31] >> 8) | (1<<24), h4 + (m[12-15] >> 8) | (1<<24) ] - movd 0x0c(m),hc4 - movd 0x1c(m),t1 - punpcklqdq t1,hc4 - psrld $8,hc4 - por ORMASK(%rip),hc4 - movd h4,t1 - paddd t1,hc4 - - # t1 = [ hc0[1] * r0, hc0[0] * u0 ] - movdqa ru0,t1 - pmuludq hc0,t1 - # t1 += [ hc1[1] * s4, hc1[0] * v4 ] - movdqa sv4,t2 - pmuludq hc1,t2 - paddq t2,t1 - # t1 += [ hc2[1] * s3, hc2[0] * v3 ] - movdqa sv3,t2 - pmuludq hc2,t2 - paddq t2,t1 - # t1 += [ hc3[1] * s2, hc3[0] * v2 ] - movdqa sv2,t2 - pmuludq hc3,t2 - paddq t2,t1 - # t1 += [ hc4[1] * s1, hc4[0] * v1 ] - movdqa sv1,t2 - pmuludq hc4,t2 - paddq t2,t1 - # d0 = t1[0] + t1[1] - movdqa t1,t2 - psrldq $8,t2 - paddq t2,t1 - movq t1,d0 - - # t1 = [ hc0[1] * r1, hc0[0] * u1 ] - movdqa ru1,t1 - pmuludq hc0,t1 - # t1 += [ hc1[1] * r0, hc1[0] * u0 ] - movdqa ru0,t2 - pmuludq hc1,t2 - paddq t2,t1 - # t1 += [ hc2[1] * s4, hc2[0] * v4 ] - movdqa sv4,t2 - pmuludq hc2,t2 - paddq t2,t1 - # t1 += [ hc3[1] * s3, hc3[0] * v3 ] - movdqa sv3,t2 - pmuludq hc3,t2 - paddq t2,t1 - # t1 += [ hc4[1] * s2, hc4[0] * v2 ] - movdqa sv2,t2 - pmuludq hc4,t2 - paddq t2,t1 - # d1 = t1[0] + t1[1] - movdqa t1,t2 - psrldq $8,t2 - paddq t2,t1 - movq t1,d1 - - # t1 = [ hc0[1] * r2, hc0[0] * u2 ] - movdqa ru2,t1 - pmuludq hc0,t1 - # t1 += [ hc1[1] * r1, hc1[0] * u1 ] - movdqa ru1,t2 - pmuludq hc1,t2 - paddq t2,t1 - # t1 += [ hc2[1] * r0, hc2[0] * u0 ] - movdqa ru0,t2 - pmuludq hc2,t2 - paddq t2,t1 - # t1 += [ hc3[1] * s4, hc3[0] * v4 ] - movdqa sv4,t2 - pmuludq hc3,t2 - paddq t2,t1 - # t1 += [ hc4[1] * s3, hc4[0] * v3 ] - movdqa sv3,t2 - pmuludq hc4,t2 - paddq t2,t1 - # d2 = t1[0] + t1[1] - movdqa t1,t2 - psrldq $8,t2 - paddq t2,t1 - movq t1,d2 - - # t1 = [ hc0[1] * r3, hc0[0] * u3 ] - movdqa ru3,t1 - pmuludq hc0,t1 - # t1 += [ hc1[1] * r2, hc1[0] * u2 ] - movdqa ru2,t2 - pmuludq hc1,t2 - paddq t2,t1 - # t1 += [ hc2[1] * r1, hc2[0] * u1 ] - movdqa ru1,t2 - pmuludq hc2,t2 - paddq t2,t1 - # t1 += [ hc3[1] * r0, hc3[0] * u0 ] - movdqa ru0,t2 - pmuludq hc3,t2 - paddq t2,t1 - # t1 += [ hc4[1] * s4, hc4[0] * v4 ] - movdqa sv4,t2 - pmuludq hc4,t2 - paddq t2,t1 - # d3 = t1[0] + t1[1] - movdqa t1,t2 - psrldq $8,t2 - paddq t2,t1 - movq t1,d3 - - # t1 = [ hc0[1] * r4, hc0[0] * u4 ] - movdqa ru4,t1 - pmuludq hc0,t1 - # t1 += [ hc1[1] * r3, hc1[0] * u3 ] - movdqa ru3,t2 - pmuludq hc1,t2 - paddq t2,t1 - # t1 += [ hc2[1] * r2, hc2[0] * u2 ] - movdqa ru2,t2 - pmuludq hc2,t2 - paddq t2,t1 - # t1 += [ hc3[1] * r1, hc3[0] * u1 ] - movdqa ru1,t2 - pmuludq hc3,t2 - paddq t2,t1 - # t1 += [ hc4[1] * r0, hc4[0] * u0 ] - movdqa ru0,t2 - pmuludq hc4,t2 - paddq t2,t1 - # d4 = t1[0] + t1[1] - movdqa t1,t2 - psrldq $8,t2 - paddq t2,t1 - movq t1,d4 - - # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> - # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small - # amount. Careful: we must not assume the carry bits 'd0 >> 26', - # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit - # integers. It's true in a single-block implementation, but not here. - - # d1 += d0 >> 26 - mov d0,%rax - shr $26,%rax - add %rax,d1 - # h0 = d0 & 0x3ffffff - mov d0,%rbx - and $0x3ffffff,%ebx - - # d2 += d1 >> 26 - mov d1,%rax - shr $26,%rax - add %rax,d2 - # h1 = d1 & 0x3ffffff - mov d1,%rax - and $0x3ffffff,%eax - mov %eax,h1 - - # d3 += d2 >> 26 - mov d2,%rax - shr $26,%rax - add %rax,d3 - # h2 = d2 & 0x3ffffff - mov d2,%rax - and $0x3ffffff,%eax - mov %eax,h2 - - # d4 += d3 >> 26 - mov d3,%rax - shr $26,%rax - add %rax,d4 - # h3 = d3 & 0x3ffffff - mov d3,%rax - and $0x3ffffff,%eax - mov %eax,h3 - - # h0 += (d4 >> 26) * 5 - mov d4,%rax - shr $26,%rax - lea (%rax,%rax,4),%rax - add %rax,%rbx - # h4 = d4 & 0x3ffffff - mov d4,%rax - and $0x3ffffff,%eax - mov %eax,h4 - - # h1 += h0 >> 26 - mov %rbx,%rax - shr $26,%rax - add %eax,h1 - # h0 = h0 & 0x3ffffff - andl $0x3ffffff,%ebx - mov %ebx,h0 - - add $0x20,m - dec %rcx - jnz .Ldoblock2 - - pop %r13 - pop %r12 - pop %rbx - ret -ENDPROC(poly1305_2block_sse2) diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl new file mode 100644 index 000000000000..7a6b5380a46f --- /dev/null +++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl @@ -0,0 +1,4265 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +# +# Copyright (C) 2017-2018 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved. +# Copyright (C) 2017-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. +# Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved. +# +# This code is taken from the OpenSSL project but the author, Andy Polyakov, +# has relicensed it under the licenses specified in the SPDX header above. +# The original headers, including the original license headers, are +# included below for completeness. +# +# ==================================================================== +# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL +# project. The module is, however, dual licensed under OpenSSL and +# CRYPTOGAMS licenses depending on where you obtain it. For further +# details see http://www.openssl.org/~appro/cryptogams/. +# ==================================================================== +# +# This module implements Poly1305 hash for x86_64. +# +# March 2015 +# +# Initial release. +# +# December 2016 +# +# Add AVX512F+VL+BW code path. +# +# November 2017 +# +# Convert AVX512F+VL+BW code path to pure AVX512F, so that it can be +# executed even on Knights Landing. Trigger for modification was +# observation that AVX512 code paths can negatively affect overall +# Skylake-X system performance. Since we are likely to suppress +# AVX512F capability flag [at least on Skylake-X], conversion serves +# as kind of "investment protection". Note that next *lake processor, +# Cannonlake, has AVX512IFMA code path to execute... +# +# Numbers are cycles per processed byte with poly1305_blocks alone, +# measured with rdtsc at fixed clock frequency. +# +# IALU/gcc-4.8(*) AVX(**) AVX2 AVX-512 +# P4 4.46/+120% - +# Core 2 2.41/+90% - +# Westmere 1.88/+120% - +# Sandy Bridge 1.39/+140% 1.10 +# Haswell 1.14/+175% 1.11 0.65 +# Skylake[-X] 1.13/+120% 0.96 0.51 [0.35] +# Silvermont 2.83/+95% - +# Knights L 3.60/? 1.65 1.10 0.41(***) +# Goldmont 1.70/+180% - +# VIA Nano 1.82/+150% - +# Sledgehammer 1.38/+160% - +# Bulldozer 2.30/+130% 0.97 +# Ryzen 1.15/+200% 1.08 1.18 +# +# (*) improvement coefficients relative to clang are more modest and +# are ~50% on most processors, in both cases we are comparing to +# __int128 code; +# (**) SSE2 implementation was attempted, but among non-AVX processors +# it was faster than integer-only code only on older Intel P4 and +# Core processors, 50-30%, less newer processor is, but slower on +# contemporary ones, for example almost 2x slower on Atom, and as +# former are naturally disappearing, SSE2 is deemed unnecessary; +# (***) strangely enough performance seems to vary from core to core, +# listed result is best case; + +$flavour = shift; +$output = shift; +if ($flavour =~ /\./) { $output = $flavour; undef $flavour; } + +$win64=0; $win64=1 if ($flavour =~ /[nm]asm|mingw64/ || $output =~ /\.asm$/); +$kernel=0; $kernel=1 if (!$flavour && !$output); + +if (!$kernel) { + $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; + ( $xlate="${dir}x86_64-xlate.pl" and -f $xlate ) or + ( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or + die "can't locate x86_64-xlate.pl"; + + open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\""; + *STDOUT=*OUT; + + if (`$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1` + =~ /GNU assembler version ([2-9]\.[0-9]+)/) { + $avx = ($1>=2.19) + ($1>=2.22) + ($1>=2.25); + } + + if (!$avx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) && + `nasm -v 2>&1` =~ /NASM version ([2-9]\.[0-9]+)(?:\.([0-9]+))?/) { + $avx = ($1>=2.09) + ($1>=2.10) + ($1>=2.12); + $avx += 1 if ($1==2.11 && $2>=8); + } + + if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) && + `ml64 2>&1` =~ /Version ([0-9]+)\./) { + $avx = ($1>=10) + ($1>=11); + } + + if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/) { + $avx = ($2>=3.0) + ($2>3.0); + } +} else { + $avx = 4; # The kernel uses ifdefs for this. +} + +sub declare_function() { + my ($name, $align, $nargs) = @_; + if($kernel) { + $code .= ".align $align\n"; + $code .= "SYM_FUNC_START($name)\n"; + $code .= ".L$name:\n"; + } else { + $code .= ".globl $name\n"; + $code .= ".type $name,\@function,$nargs\n"; + $code .= ".align $align\n"; + $code .= "$name:\n"; + } +} + +sub end_function() { + my ($name) = @_; + if($kernel) { + $code .= "SYM_FUNC_END($name)\n"; + } else { + $code .= ".size $name,.-$name\n"; + } +} + +$code.=<<___ if $kernel; +#include <linux/linkage.h> +___ + +if ($avx) { +$code.=<<___ if $kernel; +.section .rodata +___ +$code.=<<___; +.align 64 +.Lconst: +.Lmask24: +.long 0x0ffffff,0,0x0ffffff,0,0x0ffffff,0,0x0ffffff,0 +.L129: +.long `1<<24`,0,`1<<24`,0,`1<<24`,0,`1<<24`,0 +.Lmask26: +.long 0x3ffffff,0,0x3ffffff,0,0x3ffffff,0,0x3ffffff,0 +.Lpermd_avx2: +.long 2,2,2,3,2,0,2,1 +.Lpermd_avx512: +.long 0,0,0,1, 0,2,0,3, 0,4,0,5, 0,6,0,7 + +.L2_44_inp_permd: +.long 0,1,1,2,2,3,7,7 +.L2_44_inp_shift: +.quad 0,12,24,64 +.L2_44_mask: +.quad 0xfffffffffff,0xfffffffffff,0x3ffffffffff,0xffffffffffffffff +.L2_44_shift_rgt: +.quad 44,44,42,64 +.L2_44_shift_lft: +.quad 8,8,10,64 + +.align 64 +.Lx_mask44: +.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff +.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff +.Lx_mask42: +.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff +.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff +___ +} +$code.=<<___ if (!$kernel); +.asciz "Poly1305 for x86_64, CRYPTOGAMS by <appro\@openssl.org>" +.align 16 +___ + +my ($ctx,$inp,$len,$padbit)=("%rdi","%rsi","%rdx","%rcx"); +my ($mac,$nonce)=($inp,$len); # *_emit arguments +my ($d1,$d2,$d3, $r0,$r1,$s1)=("%r8","%r9","%rdi","%r11","%r12","%r13"); +my ($h0,$h1,$h2)=("%r14","%rbx","%r10"); + +sub poly1305_iteration { +# input: copy of $r1 in %rax, $h0-$h2, $r0-$r1 +# output: $h0-$h2 *= $r0-$r1 +$code.=<<___; + mulq $h0 # h0*r1 + mov %rax,$d2 + mov $r0,%rax + mov %rdx,$d3 + + mulq $h0 # h0*r0 + mov %rax,$h0 # future $h0 + mov $r0,%rax + mov %rdx,$d1 + + mulq $h1 # h1*r0 + add %rax,$d2 + mov $s1,%rax + adc %rdx,$d3 + + mulq $h1 # h1*s1 + mov $h2,$h1 # borrow $h1 + add %rax,$h0 + adc %rdx,$d1 + + imulq $s1,$h1 # h2*s1 + add $h1,$d2 + mov $d1,$h1 + adc \$0,$d3 + + imulq $r0,$h2 # h2*r0 + add $d2,$h1 + mov \$-4,%rax # mask value + adc $h2,$d3 + + and $d3,%rax # last reduction step + mov $d3,$h2 + shr \$2,$d3 + and \$3,$h2 + add $d3,%rax + add %rax,$h0 + adc \$0,$h1 + adc \$0,$h2 +___ +} + +######################################################################## +# Layout of opaque area is following. +# +# unsigned __int64 h[3]; # current hash value base 2^64 +# unsigned __int64 r[2]; # key value base 2^64 + +$code.=<<___; +.text +___ +$code.=<<___ if (!$kernel); +.extern OPENSSL_ia32cap_P + +.globl poly1305_init_x86_64 +.hidden poly1305_init_x86_64 +.globl poly1305_blocks_x86_64 +.hidden poly1305_blocks_x86_64 +.globl poly1305_emit_x86_64 +.hidden poly1305_emit_x86_64 +___ +&declare_function("poly1305_init_x86_64", 32, 3); +$code.=<<___; + xor %rax,%rax + mov %rax,0($ctx) # initialize hash value + mov %rax,8($ctx) + mov %rax,16($ctx) + + cmp \$0,$inp + je .Lno_key +___ +$code.=<<___ if (!$kernel); + lea poly1305_blocks_x86_64(%rip),%r10 + lea poly1305_emit_x86_64(%rip),%r11 +___ +$code.=<<___ if (!$kernel && $avx); + mov OPENSSL_ia32cap_P+4(%rip),%r9 + lea poly1305_blocks_avx(%rip),%rax + lea poly1305_emit_avx(%rip),%rcx + bt \$`60-32`,%r9 # AVX? + cmovc %rax,%r10 + cmovc %rcx,%r11 +___ +$code.=<<___ if (!$kernel && $avx>1); + lea poly1305_blocks_avx2(%rip),%rax + bt \$`5+32`,%r9 # AVX2? + cmovc %rax,%r10 +___ +$code.=<<___ if (!$kernel && $avx>3); + mov \$`(1<<31|1<<21|1<<16)`,%rax + shr \$32,%r9 + and %rax,%r9 + cmp %rax,%r9 + je .Linit_base2_44 +___ +$code.=<<___; + mov \$0x0ffffffc0fffffff,%rax + mov \$0x0ffffffc0ffffffc,%rcx + and 0($inp),%rax + and 8($inp),%rcx + mov %rax,24($ctx) + mov %rcx,32($ctx) +___ +$code.=<<___ if (!$kernel && $flavour !~ /elf32/); + mov %r10,0(%rdx) + mov %r11,8(%rdx) +___ +$code.=<<___ if (!$kernel && $flavour =~ /elf32/); + mov %r10d,0(%rdx) + mov %r11d,4(%rdx) +___ +$code.=<<___; + mov \$1,%eax +.Lno_key: + ret +___ +&end_function("poly1305_init_x86_64"); + +&declare_function("poly1305_blocks_x86_64", 32, 4); +$code.=<<___; +.cfi_startproc +.Lblocks: + shr \$4,$len + jz .Lno_data # too short + + push %rbx +.cfi_push %rbx + push %r12 +.cfi_push %r12 + push %r13 +.cfi_push %r13 + push %r14 +.cfi_push %r14 + push %r15 +.cfi_push %r15 + push $ctx +.cfi_push $ctx +.Lblocks_body: + + mov $len,%r15 # reassign $len + + mov 24($ctx),$r0 # load r + mov 32($ctx),$s1 + + mov 0($ctx),$h0 # load hash value + mov 8($ctx),$h1 + mov 16($ctx),$h2 + + mov $s1,$r1 + shr \$2,$s1 + mov $r1,%rax + add $r1,$s1 # s1 = r1 + (r1 >> 2) + jmp .Loop + +.align 32 +.Loop: + add 0($inp),$h0 # accumulate input + adc 8($inp),$h1 + lea 16($inp),$inp + adc $padbit,$h2 +___ + + &poly1305_iteration(); + +$code.=<<___; + mov $r1,%rax + dec %r15 # len-=16 + jnz .Loop + + mov 0(%rsp),$ctx +.cfi_restore $ctx + + mov $h0,0($ctx) # store hash value + mov $h1,8($ctx) + mov $h2,16($ctx) + + mov 8(%rsp),%r15 +.cfi_restore %r15 + mov 16(%rsp),%r14 +.cfi_restore %r14 + mov 24(%rsp),%r13 +.cfi_restore %r13 + mov 32(%rsp),%r12 +.cfi_restore %r12 + mov 40(%rsp),%rbx +.cfi_restore %rbx + lea 48(%rsp),%rsp +.cfi_adjust_cfa_offset -48 +.Lno_data: +.Lblocks_epilogue: + ret +.cfi_endproc +___ +&end_function("poly1305_blocks_x86_64"); + +&declare_function("poly1305_emit_x86_64", 32, 3); +$code.=<<___; +.Lemit: + mov 0($ctx),%r8 # load hash value + mov 8($ctx),%r9 + mov 16($ctx),%r10 + + mov %r8,%rax + add \$5,%r8 # compare to modulus + mov %r9,%rcx + adc \$0,%r9 + adc \$0,%r10 + shr \$2,%r10 # did 130-bit value overflow? + cmovnz %r8,%rax + cmovnz %r9,%rcx + + add 0($nonce),%rax # accumulate nonce + adc 8($nonce),%rcx + mov %rax,0($mac) # write result + mov %rcx,8($mac) + + ret +___ +&end_function("poly1305_emit_x86_64"); +if ($avx) { + +if($kernel) { + $code .= "#ifdef CONFIG_AS_AVX\n"; +} + +######################################################################## +# Layout of opaque area is following. +# +# unsigned __int32 h[5]; # current hash value base 2^26 +# unsigned __int32 is_base2_26; +# unsigned __int64 r[2]; # key value base 2^64 +# unsigned __int64 pad; +# struct { unsigned __int32 r^2, r^1, r^4, r^3; } r[9]; +# +# where r^n are base 2^26 digits of degrees of multiplier key. There are +# 5 digits, but last four are interleaved with multiples of 5, totalling +# in 9 elements: r0, r1, 5*r1, r2, 5*r2, r3, 5*r3, r4, 5*r4. + +my ($H0,$H1,$H2,$H3,$H4, $T0,$T1,$T2,$T3,$T4, $D0,$D1,$D2,$D3,$D4, $MASK) = + map("%xmm$_",(0..15)); + +$code.=<<___; +.type __poly1305_block,\@abi-omnipotent +.align 32 +__poly1305_block: + push $ctx +___ + &poly1305_iteration(); +$code.=<<___; + pop $ctx + ret +.size __poly1305_block,.-__poly1305_block + +.type __poly1305_init_avx,\@abi-omnipotent +.align 32 +__poly1305_init_avx: + push %rbp + mov %rsp,%rbp + mov $r0,$h0 + mov $r1,$h1 + xor $h2,$h2 + + lea 48+64($ctx),$ctx # size optimization + + mov $r1,%rax + call __poly1305_block # r^2 + + mov \$0x3ffffff,%eax # save interleaved r^2 and r base 2^26 + mov \$0x3ffffff,%edx + mov $h0,$d1 + and $h0#d,%eax + mov $r0,$d2 + and $r0#d,%edx + mov %eax,`16*0+0-64`($ctx) + shr \$26,$d1 + mov %edx,`16*0+4-64`($ctx) + shr \$26,$d2 + + mov \$0x3ffffff,%eax + mov \$0x3ffffff,%edx + and $d1#d,%eax + and $d2#d,%edx + mov %eax,`16*1+0-64`($ctx) + lea (%rax,%rax,4),%eax # *5 + mov %edx,`16*1+4-64`($ctx) + lea (%rdx,%rdx,4),%edx # *5 + mov %eax,`16*2+0-64`($ctx) + shr \$26,$d1 + mov %edx,`16*2+4-64`($ctx) + shr \$26,$d2 + + mov $h1,%rax + mov $r1,%rdx + shl \$12,%rax + shl \$12,%rdx + or $d1,%rax + or $d2,%rdx + and \$0x3ffffff,%eax + and \$0x3ffffff,%edx + mov %eax,`16*3+0-64`($ctx) + lea (%rax,%rax,4),%eax # *5 + mov %edx,`16*3+4-64`($ctx) + lea (%rdx,%rdx,4),%edx # *5 + mov %eax,`16*4+0-64`($ctx) + mov $h1,$d1 + mov %edx,`16*4+4-64`($ctx) + mov $r1,$d2 + + mov \$0x3ffffff,%eax + mov \$0x3ffffff,%edx + shr \$14,$d1 + shr \$14,$d2 + and $d1#d,%eax + and $d2#d,%edx + mov %eax,`16*5+0-64`($ctx) + lea (%rax,%rax,4),%eax # *5 + mov %edx,`16*5+4-64`($ctx) + lea (%rdx,%rdx,4),%edx # *5 + mov %eax,`16*6+0-64`($ctx) + shr \$26,$d1 + mov %edx,`16*6+4-64`($ctx) + shr \$26,$d2 + + mov $h2,%rax + shl \$24,%rax + or %rax,$d1 + mov $d1#d,`16*7+0-64`($ctx) + lea ($d1,$d1,4),$d1 # *5 + mov $d2#d,`16*7+4-64`($ctx) + lea ($d2,$d2,4),$d2 # *5 + mov $d1#d,`16*8+0-64`($ctx) + mov $d2#d,`16*8+4-64`($ctx) + + mov $r1,%rax + call __poly1305_block # r^3 + + mov \$0x3ffffff,%eax # save r^3 base 2^26 + mov $h0,$d1 + and $h0#d,%eax + shr \$26,$d1 + mov %eax,`16*0+12-64`($ctx) + + mov \$0x3ffffff,%edx + and $d1#d,%edx + mov %edx,`16*1+12-64`($ctx) + lea (%rdx,%rdx,4),%edx # *5 + shr \$26,$d1 + mov %edx,`16*2+12-64`($ctx) + + mov $h1,%rax + shl \$12,%rax + or $d1,%rax + and \$0x3ffffff,%eax + mov %eax,`16*3+12-64`($ctx) + lea (%rax,%rax,4),%eax # *5 + mov $h1,$d1 + mov %eax,`16*4+12-64`($ctx) + + mov \$0x3ffffff,%edx + shr \$14,$d1 + and $d1#d,%edx + mov %edx,`16*5+12-64`($ctx) + lea (%rdx,%rdx,4),%edx # *5 + shr \$26,$d1 + mov %edx,`16*6+12-64`($ctx) + + mov $h2,%rax + shl \$24,%rax + or %rax,$d1 + mov $d1#d,`16*7+12-64`($ctx) + lea ($d1,$d1,4),$d1 # *5 + mov $d1#d,`16*8+12-64`($ctx) + + mov $r1,%rax + call __poly1305_block # r^4 + + mov \$0x3ffffff,%eax # save r^4 base 2^26 + mov $h0,$d1 + and $h0#d,%eax + shr \$26,$d1 + mov %eax,`16*0+8-64`($ctx) + + mov \$0x3ffffff,%edx + and $d1#d,%edx + mov %edx,`16*1+8-64`($ctx) + lea (%rdx,%rdx,4),%edx # *5 + shr \$26,$d1 + mov %edx,`16*2+8-64`($ctx) + + mov $h1,%rax + shl \$12,%rax + or $d1,%rax + and \$0x3ffffff,%eax + mov %eax,`16*3+8-64`($ctx) + lea (%rax,%rax,4),%eax # *5 + mov $h1,$d1 + mov %eax,`16*4+8-64`($ctx) + + mov \$0x3ffffff,%edx + shr \$14,$d1 + and $d1#d,%edx + mov %edx,`16*5+8-64`($ctx) + lea (%rdx,%rdx,4),%edx # *5 + shr \$26,$d1 + mov %edx,`16*6+8-64`($ctx) + + mov $h2,%rax + shl \$24,%rax + or %rax,$d1 + mov $d1#d,`16*7+8-64`($ctx) + lea ($d1,$d1,4),$d1 # *5 + mov $d1#d,`16*8+8-64`($ctx) + + lea -48-64($ctx),$ctx # size [de-]optimization + pop %rbp + ret +.size __poly1305_init_avx,.-__poly1305_init_avx +___ + +&declare_function("poly1305_blocks_avx", 32, 4); +$code.=<<___; +.cfi_startproc + mov 20($ctx),%r8d # is_base2_26 + cmp \$128,$len + jae .Lblocks_avx + test %r8d,%r8d + jz .Lblocks + +.Lblocks_avx: + and \$-16,$len + jz .Lno_data_avx + + vzeroupper + + test %r8d,%r8d + jz .Lbase2_64_avx + + test \$31,$len + jz .Leven_avx + + push %rbp +.cfi_push %rbp + mov %rsp,%rbp + push %rbx +.cfi_push %rbx + push %r12 +.cfi_push %r12 + push %r13 +.cfi_push %r13 + push %r14 +.cfi_push %r14 + push %r15 +.cfi_push %r15 +.Lblocks_avx_body: + + mov $len,%r15 # reassign $len + + mov 0($ctx),$d1 # load hash value + mov 8($ctx),$d2 + mov 16($ctx),$h2#d + + mov 24($ctx),$r0 # load r + mov 32($ctx),$s1 + + ################################# base 2^26 -> base 2^64 + mov $d1#d,$h0#d + and \$`-1*(1<<31)`,$d1 + mov $d2,$r1 # borrow $r1 + mov $d2#d,$h1#d + and \$`-1*(1<<31)`,$d2 + + shr \$6,$d1 + shl \$52,$r1 + add $d1,$h0 + shr \$12,$h1 + shr \$18,$d2 + add $r1,$h0 + adc $d2,$h1 + + mov $h2,$d1 + shl \$40,$d1 + shr \$24,$h2 + add $d1,$h1 + adc \$0,$h2 # can be partially reduced... + + mov \$-4,$d2 # ... so reduce + mov $h2,$d1 + and $h2,$d2 + shr \$2,$d1 + and \$3,$h2 + add $d2,$d1 # =*5 + add $d1,$h0 + adc \$0,$h1 + adc \$0,$h2 + + mov $s1,$r1 + mov $s1,%rax + shr \$2,$s1 + add $r1,$s1 # s1 = r1 + (r1 >> 2) + + add 0($inp),$h0 # accumulate input + adc 8($inp),$h1 + lea 16($inp),$inp + adc $padbit,$h2 + + call __poly1305_block + + test $padbit,$padbit # if $padbit is zero, + jz .Lstore_base2_64_avx # store hash in base 2^64 format + + ################################# base 2^64 -> base 2^26 + mov $h0,%rax + mov $h0,%rdx + shr \$52,$h0 + mov $h1,$r0 + mov $h1,$r1 + shr \$26,%rdx + and \$0x3ffffff,%rax # h[0] + shl \$12,$r0 + and \$0x3ffffff,%rdx # h[1] + shr \$14,$h1 + or $r0,$h0 + shl \$24,$h2 + and \$0x3ffffff,$h0 # h[2] + shr \$40,$r1 + and \$0x3ffffff,$h1 # h[3] + or $r1,$h2 # h[4] + + sub \$16,%r15 + jz .Lstore_base2_26_avx + + vmovd %rax#d,$H0 + vmovd %rdx#d,$H1 + vmovd $h0#d,$H2 + vmovd $h1#d,$H3 + vmovd $h2#d,$H4 + jmp .Lproceed_avx + +.align 32 +.Lstore_base2_64_avx: + mov $h0,0($ctx) + mov $h1,8($ctx) + mov $h2,16($ctx) # note that is_base2_26 is zeroed + jmp .Ldone_avx + +.align 16 +.Lstore_base2_26_avx: + mov %rax#d,0($ctx) # store hash value base 2^26 + mov %rdx#d,4($ctx) + mov $h0#d,8($ctx) + mov $h1#d,12($ctx) + mov $h2#d,16($ctx) +.align 16 +.Ldone_avx: + pop %r15 +.cfi_restore %r15 + pop %r14 +.cfi_restore %r14 + pop %r13 +.cfi_restore %r13 + pop %r12 +.cfi_restore %r12 + pop %rbx +.cfi_restore %rbx + pop %rbp +.cfi_restore %rbp +.Lno_data_avx: +.Lblocks_avx_epilogue: + ret +.cfi_endproc + +.align 32 +.Lbase2_64_avx: +.cfi_startproc + push %rbp +.cfi_push %rbp + mov %rsp,%rbp + push %rbx +.cfi_push %rbx + push %r12 +.cfi_push %r12 + push %r13 +.cfi_push %r13 + push %r14 +.cfi_push %r14 + push %r15 +.cfi_push %r15 +.Lbase2_64_avx_body: + + mov $len,%r15 # reassign $len + + mov 24($ctx),$r0 # load r + mov 32($ctx),$s1 + + mov 0($ctx),$h0 # load hash value + mov 8($ctx),$h1 + mov 16($ctx),$h2#d + + mov $s1,$r1 + mov $s1,%rax + shr \$2,$s1 + add $r1,$s1 # s1 = r1 + (r1 >> 2) + + test \$31,$len + jz .Linit_avx + + add 0($inp),$h0 # accumulate input + adc 8($inp),$h1 + lea 16($inp),$inp + adc $padbit,$h2 + sub \$16,%r15 + + call __poly1305_block + +.Linit_avx: + ################################# base 2^64 -> base 2^26 + mov $h0,%rax + mov $h0,%rdx + shr \$52,$h0 + mov $h1,$d1 + mov $h1,$d2 + shr \$26,%rdx + and \$0x3ffffff,%rax # h[0] + shl \$12,$d1 + and \$0x3ffffff,%rdx # h[1] + shr \$14,$h1 + or $d1,$h0 + shl \$24,$h2 + and \$0x3ffffff,$h0 # h[2] + shr \$40,$d2 + and \$0x3ffffff,$h1 # h[3] + or $d2,$h2 # h[4] + + vmovd %rax#d,$H0 + vmovd %rdx#d,$H1 + vmovd $h0#d,$H2 + vmovd $h1#d,$H3 + vmovd $h2#d,$H4 + movl \$1,20($ctx) # set is_base2_26 + + call __poly1305_init_avx + +.Lproceed_avx: + mov %r15,$len + pop %r15 +.cfi_restore %r15 + pop %r14 +.cfi_restore %r14 + pop %r13 +.cfi_restore %r13 + pop %r12 +.cfi_restore %r12 + pop %rbx +.cfi_restore %rbx + pop %rbp +.cfi_restore %rbp +.Lbase2_64_avx_epilogue: + jmp .Ldo_avx +.cfi_endproc + +.align 32 +.Leven_avx: +.cfi_startproc + vmovd 4*0($ctx),$H0 # load hash value + vmovd 4*1($ctx),$H1 + vmovd 4*2($ctx),$H2 + vmovd 4*3($ctx),$H3 + vmovd 4*4($ctx),$H4 + +.Ldo_avx: +___ +$code.=<<___ if (!$win64); + lea 8(%rsp),%r10 +.cfi_def_cfa_register %r10 + and \$-32,%rsp + sub \$-8,%rsp + lea -0x58(%rsp),%r11 + sub \$0x178,%rsp +___ +$code.=<<___ if ($win64); + lea -0xf8(%rsp),%r11 + sub \$0x218,%rsp + vmovdqa %xmm6,0x50(%r11) + vmovdqa %xmm7,0x60(%r11) + vmovdqa %xmm8,0x70(%r11) + vmovdqa %xmm9,0x80(%r11) + vmovdqa %xmm10,0x90(%r11) + vmovdqa %xmm11,0xa0(%r11) + vmovdqa %xmm12,0xb0(%r11) + vmovdqa %xmm13,0xc0(%r11) + vmovdqa %xmm14,0xd0(%r11) + vmovdqa %xmm15,0xe0(%r11) +.Ldo_avx_body: +___ +$code.=<<___; + sub \$64,$len + lea -32($inp),%rax + cmovc %rax,$inp + + vmovdqu `16*3`($ctx),$D4 # preload r0^2 + lea `16*3+64`($ctx),$ctx # size optimization + lea .Lconst(%rip),%rcx + + ################################################################ + # load input + vmovdqu 16*2($inp),$T0 + vmovdqu 16*3($inp),$T1 + vmovdqa 64(%rcx),$MASK # .Lmask26 + + vpsrldq \$6,$T0,$T2 # splat input + vpsrldq \$6,$T1,$T3 + vpunpckhqdq $T1,$T0,$T4 # 4 + vpunpcklqdq $T1,$T0,$T0 # 0:1 + vpunpcklqdq $T3,$T2,$T3 # 2:3 + + vpsrlq \$40,$T4,$T4 # 4 + vpsrlq \$26,$T0,$T1 + vpand $MASK,$T0,$T0 # 0 + vpsrlq \$4,$T3,$T2 + vpand $MASK,$T1,$T1 # 1 + vpsrlq \$30,$T3,$T3 + vpand $MASK,$T2,$T2 # 2 + vpand $MASK,$T3,$T3 # 3 + vpor 32(%rcx),$T4,$T4 # padbit, yes, always + + jbe .Lskip_loop_avx + + # expand and copy pre-calculated table to stack + vmovdqu `16*1-64`($ctx),$D1 + vmovdqu `16*2-64`($ctx),$D2 + vpshufd \$0xEE,$D4,$D3 # 34xx -> 3434 + vpshufd \$0x44,$D4,$D0 # xx12 -> 1212 + vmovdqa $D3,-0x90(%r11) + vmovdqa $D0,0x00(%rsp) + vpshufd \$0xEE,$D1,$D4 + vmovdqu `16*3-64`($ctx),$D0 + vpshufd \$0x44,$D1,$D1 + vmovdqa $D4,-0x80(%r11) + vmovdqa $D1,0x10(%rsp) + vpshufd \$0xEE,$D2,$D3 + vmovdqu `16*4-64`($ctx),$D1 + vpshufd \$0x44,$D2,$D2 + vmovdqa $D3,-0x70(%r11) + vmovdqa $D2,0x20(%rsp) + vpshufd \$0xEE,$D0,$D4 + vmovdqu `16*5-64`($ctx),$D2 + vpshufd \$0x44,$D0,$D0 + vmovdqa $D4,-0x60(%r11) + vmovdqa $D0,0x30(%rsp) + vpshufd \$0xEE,$D1,$D3 + vmovdqu `16*6-64`($ctx),$D0 + vpshufd \$0x44,$D1,$D1 + vmovdqa $D3,-0x50(%r11) + vmovdqa $D1,0x40(%rsp) + vpshufd \$0xEE,$D2,$D4 + vmovdqu `16*7-64`($ctx),$D1 + vpshufd \$0x44,$D2,$D2 + vmovdqa $D4,-0x40(%r11) + vmovdqa $D2,0x50(%rsp) + vpshufd \$0xEE,$D0,$D3 + vmovdqu `16*8-64`($ctx),$D2 + vpshufd \$0x44,$D0,$D0 + vmovdqa $D3,-0x30(%r11) + vmovdqa $D0,0x60(%rsp) + vpshufd \$0xEE,$D1,$D4 + vpshufd \$0x44,$D1,$D1 + vmovdqa $D4,-0x20(%r11) + vmovdqa $D1,0x70(%rsp) + vpshufd \$0xEE,$D2,$D3 + vmovdqa 0x00(%rsp),$D4 # preload r0^2 + vpshufd \$0x44,$D2,$D2 + vmovdqa $D3,-0x10(%r11) + vmovdqa $D2,0x80(%rsp) + + jmp .Loop_avx + +.align 32 +.Loop_avx: + ################################################################ + # ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2 + # ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r + # \___________________/ + # ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2 + # ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r + # \___________________/ \____________________/ + # + # Note that we start with inp[2:3]*r^2. This is because it + # doesn't depend on reduction in previous iteration. + ################################################################ + # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4 + # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4 + # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4 + # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4 + # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4 + # + # though note that $Tx and $Hx are "reversed" in this section, + # and $D4 is preloaded with r0^2... + + vpmuludq $T0,$D4,$D0 # d0 = h0*r0 + vpmuludq $T1,$D4,$D1 # d1 = h1*r0 + vmovdqa $H2,0x20(%r11) # offload hash + vpmuludq $T2,$D4,$D2 # d3 = h2*r0 + vmovdqa 0x10(%rsp),$H2 # r1^2 + vpmuludq $T3,$D4,$D3 # d3 = h3*r0 + vpmuludq $T4,$D4,$D4 # d4 = h4*r0 + + vmovdqa $H0,0x00(%r11) # + vpmuludq 0x20(%rsp),$T4,$H0 # h4*s1 + vmovdqa $H1,0x10(%r11) # + vpmuludq $T3,$H2,$H1 # h3*r1 + vpaddq $H0,$D0,$D0 # d0 += h4*s1 + vpaddq $H1,$D4,$D4 # d4 += h3*r1 + vmovdqa $H3,0x30(%r11) # + vpmuludq $T2,$H2,$H0 # h2*r1 + vpmuludq $T1,$H2,$H1 # h1*r1 + vpaddq $H0,$D3,$D3 # d3 += h2*r1 + vmovdqa 0x30(%rsp),$H3 # r2^2 + vpaddq $H1,$D2,$D2 # d2 += h1*r1 + vmovdqa $H4,0x40(%r11) # + vpmuludq $T0,$H2,$H2 # h0*r1 + vpmuludq $T2,$H3,$H0 # h2*r2 + vpaddq $H2,$D1,$D1 # d1 += h0*r1 + + vmovdqa 0x40(%rsp),$H4 # s2^2 + vpaddq $H0,$D4,$D4 # d4 += h2*r2 + vpmuludq $T1,$H3,$H1 # h1*r2 + vpmuludq $T0,$H3,$H3 # h0*r2 + vpaddq $H1,$D3,$D3 # d3 += h1*r2 + vmovdqa 0x50(%rsp),$H2 # r3^2 + vpaddq $H3,$D2,$D2 # d2 += h0*r2 + vpmuludq $T4,$H4,$H0 # h4*s2 + vpmuludq $T3,$H4,$H4 # h3*s2 + vpaddq $H0,$D1,$D1 # d1 += h4*s2 + vmovdqa 0x60(%rsp),$H3 # s3^2 + vpaddq $H4,$D0,$D0 # d0 += h3*s2 + + vmovdqa 0x80(%rsp),$H4 # s4^2 + vpmuludq $T1,$H2,$H1 # h1*r3 + vpmuludq $T0,$H2,$H2 # h0*r3 + vpaddq $H1,$D4,$D4 # d4 += h1*r3 + vpaddq $H2,$D3,$D3 # d3 += h0*r3 + vpmuludq $T4,$H3,$H0 # h4*s3 + vpmuludq $T3,$H3,$H1 # h3*s3 + vpaddq $H0,$D2,$D2 # d2 += h4*s3 + vmovdqu 16*0($inp),$H0 # load input + vpaddq $H1,$D1,$D1 # d1 += h3*s3 + vpmuludq $T2,$H3,$H3 # h2*s3 + vpmuludq $T2,$H4,$T2 # h2*s4 + vpaddq $H3,$D0,$D0 # d0 += h2*s3 + + vmovdqu 16*1($inp),$H1 # + vpaddq $T2,$D1,$D1 # d1 += h2*s4 + vpmuludq $T3,$H4,$T3 # h3*s4 + vpmuludq $T4,$H4,$T4 # h4*s4 + vpsrldq \$6,$H0,$H2 # splat input + vpaddq $T3,$D2,$D2 # d2 += h3*s4 + vpaddq $T4,$D3,$D3 # d3 += h4*s4 + vpsrldq \$6,$H1,$H3 # + vpmuludq 0x70(%rsp),$T0,$T4 # h0*r4 + vpmuludq $T1,$H4,$T0 # h1*s4 + vpunpckhqdq $H1,$H0,$H4 # 4 + vpaddq $T4,$D4,$D4 # d4 += h0*r4 + vmovdqa -0x90(%r11),$T4 # r0^4 + vpaddq $T0,$D0,$D0 # d0 += h1*s4 + + vpunpcklqdq $H1,$H0,$H0 # 0:1 + vpunpcklqdq $H3,$H2,$H3 # 2:3 + + #vpsrlq \$40,$H4,$H4 # 4 + vpsrldq \$`40/8`,$H4,$H4 # 4 + vpsrlq \$26,$H0,$H1 + vpand $MASK,$H0,$H0 # 0 + vpsrlq \$4,$H3,$H2 + vpand $MASK,$H1,$H1 # 1 + vpand 0(%rcx),$H4,$H4 # .Lmask24 + vpsrlq \$30,$H3,$H3 + vpand $MASK,$H2,$H2 # 2 + vpand $MASK,$H3,$H3 # 3 + vpor 32(%rcx),$H4,$H4 # padbit, yes, always + + vpaddq 0x00(%r11),$H0,$H0 # add hash value + vpaddq 0x10(%r11),$H1,$H1 + vpaddq 0x20(%r11),$H2,$H2 + vpaddq 0x30(%r11),$H3,$H3 + vpaddq 0x40(%r11),$H4,$H4 + + lea 16*2($inp),%rax + lea 16*4($inp),$inp + sub \$64,$len + cmovc %rax,$inp + + ################################################################ + # Now we accumulate (inp[0:1]+hash)*r^4 + ################################################################ + # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4 + # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4 + # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4 + # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4 + # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4 + + vpmuludq $H0,$T4,$T0 # h0*r0 + vpmuludq $H1,$T4,$T1 # h1*r0 + vpaddq $T0,$D0,$D0 + vpaddq $T1,$D1,$D1 + vmovdqa -0x80(%r11),$T2 # r1^4 + vpmuludq $H2,$T4,$T0 # h2*r0 + vpmuludq $H3,$T4,$T1 # h3*r0 + vpaddq $T0,$D2,$D2 + vpaddq $T1,$D3,$D3 + vpmuludq $H4,$T4,$T4 # h4*r0 + vpmuludq -0x70(%r11),$H4,$T0 # h4*s1 + vpaddq $T4,$D4,$D4 + + vpaddq $T0,$D0,$D0 # d0 += h4*s1 + vpmuludq $H2,$T2,$T1 # h2*r1 + vpmuludq $H3,$T2,$T0 # h3*r1 + vpaddq $T1,$D3,$D3 # d3 += h2*r1 + vmovdqa -0x60(%r11),$T3 # r2^4 + vpaddq $T0,$D4,$D4 # d4 += h3*r1 + vpmuludq $H1,$T2,$T1 # h1*r1 + vpmuludq $H0,$T2,$T2 # h0*r1 + vpaddq $T1,$D2,$D2 # d2 += h1*r1 + vpaddq $T2,$D1,$D1 # d1 += h0*r1 + + vmovdqa -0x50(%r11),$T4 # s2^4 + vpmuludq $H2,$T3,$T0 # h2*r2 + vpmuludq $H1,$T3,$T1 # h1*r2 + vpaddq $T0,$D4,$D4 # d4 += h2*r2 + vpaddq $T1,$D3,$D3 # d3 += h1*r2 + vmovdqa -0x40(%r11),$T2 # r3^4 + vpmuludq $H0,$T3,$T3 # h0*r2 + vpmuludq $H4,$T4,$T0 # h4*s2 + vpaddq $T3,$D2,$D2 # d2 += h0*r2 + vpaddq $T0,$D1,$D1 # d1 += h4*s2 + vmovdqa -0x30(%r11),$T3 # s3^4 + vpmuludq $H3,$T4,$T4 # h3*s2 + vpmuludq $H1,$T2,$T1 # h1*r3 + vpaddq $T4,$D0,$D0 # d0 += h3*s2 + + vmovdqa -0x10(%r11),$T4 # s4^4 + vpaddq $T1,$D4,$D4 # d4 += h1*r3 + vpmuludq $H0,$T2,$T2 # h0*r3 + vpmuludq $H4,$T3,$T0 # h4*s3 + vpaddq $T2,$D3,$D3 # d3 += h0*r3 + vpaddq $T0,$D2,$D2 # d2 += h4*s3 + vmovdqu 16*2($inp),$T0 # load input + vpmuludq $H3,$T3,$T2 # h3*s3 + vpmuludq $H2,$T3,$T3 # h2*s3 + vpaddq $T2,$D1,$D1 # d1 += h3*s3 + vmovdqu 16*3($inp),$T1 # + vpaddq $T3,$D0,$D0 # d0 += h2*s3 + + vpmuludq $H2,$T4,$H2 # h2*s4 + vpmuludq $H3,$T4,$H3 # h3*s4 + vpsrldq \$6,$T0,$T2 # splat input + vpaddq $H2,$D1,$D1 # d1 += h2*s4 + vpmuludq $H4,$T4,$H4 # h4*s4 + vpsrldq \$6,$T1,$T3 # + vpaddq $H3,$D2,$H2 # h2 = d2 + h3*s4 + vpaddq $H4,$D3,$H3 # h3 = d3 + h4*s4 + vpmuludq -0x20(%r11),$H0,$H4 # h0*r4 + vpmuludq $H1,$T4,$H0 + vpunpckhqdq $T1,$T0,$T4 # 4 + vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4 + vpaddq $H0,$D0,$H0 # h0 = d0 + h1*s4 + + vpunpcklqdq $T1,$T0,$T0 # 0:1 + vpunpcklqdq $T3,$T2,$T3 # 2:3 + + #vpsrlq \$40,$T4,$T4 # 4 + vpsrldq \$`40/8`,$T4,$T4 # 4 + vpsrlq \$26,$T0,$T1 + vmovdqa 0x00(%rsp),$D4 # preload r0^2 + vpand $MASK,$T0,$T0 # 0 + vpsrlq \$4,$T3,$T2 + vpand $MASK,$T1,$T1 # 1 + vpand 0(%rcx),$T4,$T4 # .Lmask24 + vpsrlq \$30,$T3,$T3 + vpand $MASK,$T2,$T2 # 2 + vpand $MASK,$T3,$T3 # 3 + vpor 32(%rcx),$T4,$T4 # padbit, yes, always + + ################################################################ + # lazy reduction as discussed in "NEON crypto" by D.J. Bernstein + # and P. Schwabe + + vpsrlq \$26,$H3,$D3 + vpand $MASK,$H3,$H3 + vpaddq $D3,$H4,$H4 # h3 -> h4 + + vpsrlq \$26,$H0,$D0 + vpand $MASK,$H0,$H0 + vpaddq $D0,$D1,$H1 # h0 -> h1 + + vpsrlq \$26,$H4,$D0 + vpand $MASK,$H4,$H4 + + vpsrlq \$26,$H1,$D1 + vpand $MASK,$H1,$H1 + vpaddq $D1,$H2,$H2 # h1 -> h2 + + vpaddq $D0,$H0,$H0 + vpsllq \$2,$D0,$D0 + vpaddq $D0,$H0,$H0 # h4 -> h0 + + vpsrlq \$26,$H2,$D2 + vpand $MASK,$H2,$H2 + vpaddq $D2,$H3,$H3 # h2 -> h3 + + vpsrlq \$26,$H0,$D0 + vpand $MASK,$H0,$H0 + vpaddq $D0,$H1,$H1 # h0 -> h1 + + vpsrlq \$26,$H3,$D3 + vpand $MASK,$H3,$H3 + vpaddq $D3,$H4,$H4 # h3 -> h4 + + ja .Loop_avx + +.Lskip_loop_avx: + ################################################################ + # multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1 + + vpshufd \$0x10,$D4,$D4 # r0^n, xx12 -> x1x2 + add \$32,$len + jnz .Long_tail_avx + + vpaddq $H2,$T2,$T2 + vpaddq $H0,$T0,$T0 + vpaddq $H1,$T1,$T1 + vpaddq $H3,$T3,$T3 + vpaddq $H4,$T4,$T4 + +.Long_tail_avx: + vmovdqa $H2,0x20(%r11) + vmovdqa $H0,0x00(%r11) + vmovdqa $H1,0x10(%r11) + vmovdqa $H3,0x30(%r11) + vmovdqa $H4,0x40(%r11) + + # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4 + # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4 + # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4 + # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4 + # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4 + + vpmuludq $T2,$D4,$D2 # d2 = h2*r0 + vpmuludq $T0,$D4,$D0 # d0 = h0*r0 + vpshufd \$0x10,`16*1-64`($ctx),$H2 # r1^n + vpmuludq $T1,$D4,$D1 # d1 = h1*r0 + vpmuludq $T3,$D4,$D3 # d3 = h3*r0 + vpmuludq $T4,$D4,$D4 # d4 = h4*r0 + + vpmuludq $T3,$H2,$H0 # h3*r1 + vpaddq $H0,$D4,$D4 # d4 += h3*r1 + vpshufd \$0x10,`16*2-64`($ctx),$H3 # s1^n + vpmuludq $T2,$H2,$H1 # h2*r1 + vpaddq $H1,$D3,$D3 # d3 += h2*r1 + vpshufd \$0x10,`16*3-64`($ctx),$H4 # r2^n + vpmuludq $T1,$H2,$H0 # h1*r1 + vpaddq $H0,$D2,$D2 # d2 += h1*r1 + vpmuludq $T0,$H2,$H2 # h0*r1 + vpaddq $H2,$D1,$D1 # d1 += h0*r1 + vpmuludq $T4,$H3,$H3 # h4*s1 + vpaddq $H3,$D0,$D0 # d0 += h4*s1 + + vpshufd \$0x10,`16*4-64`($ctx),$H2 # s2^n + vpmuludq $T2,$H4,$H1 # h2*r2 + vpaddq $H1,$D4,$D4 # d4 += h2*r2 + vpmuludq $T1,$H4,$H0 # h1*r2 + vpaddq $H0,$D3,$D3 # d3 += h1*r2 + vpshufd \$0x10,`16*5-64`($ctx),$H3 # r3^n + vpmuludq $T0,$H4,$H4 # h0*r2 + vpaddq $H4,$D2,$D2 # d2 += h0*r2 + vpmuludq $T4,$H2,$H1 # h4*s2 + vpaddq $H1,$D1,$D1 # d1 += h4*s2 + vpshufd \$0x10,`16*6-64`($ctx),$H4 # s3^n + vpmuludq $T3,$H2,$H2 # h3*s2 + vpaddq $H2,$D0,$D0 # d0 += h3*s2 + + vpmuludq $T1,$H3,$H0 # h1*r3 + vpaddq $H0,$D4,$D4 # d4 += h1*r3 + vpmuludq $T0,$H3,$H3 # h0*r3 + vpaddq $H3,$D3,$D3 # d3 += h0*r3 + vpshufd \$0x10,`16*7-64`($ctx),$H2 # r4^n + vpmuludq $T4,$H4,$H1 # h4*s3 + vpaddq $H1,$D2,$D2 # d2 += h4*s3 + vpshufd \$0x10,`16*8-64`($ctx),$H3 # s4^n + vpmuludq $T3,$H4,$H0 # h3*s3 + vpaddq $H0,$D1,$D1 # d1 += h3*s3 + vpmuludq $T2,$H4,$H4 # h2*s3 + vpaddq $H4,$D0,$D0 # d0 += h2*s3 + + vpmuludq $T0,$H2,$H2 # h0*r4 + vpaddq $H2,$D4,$D4 # h4 = d4 + h0*r4 + vpmuludq $T4,$H3,$H1 # h4*s4 + vpaddq $H1,$D3,$D3 # h3 = d3 + h4*s4 + vpmuludq $T3,$H3,$H0 # h3*s4 + vpaddq $H0,$D2,$D2 # h2 = d2 + h3*s4 + vpmuludq $T2,$H3,$H1 # h2*s4 + vpaddq $H1,$D1,$D1 # h1 = d1 + h2*s4 + vpmuludq $T1,$H3,$H3 # h1*s4 + vpaddq $H3,$D0,$D0 # h0 = d0 + h1*s4 + + jz .Lshort_tail_avx + + vmovdqu 16*0($inp),$H0 # load input + vmovdqu 16*1($inp),$H1 + + vpsrldq \$6,$H0,$H2 # splat input + vpsrldq \$6,$H1,$H3 + vpunpckhqdq $H1,$H0,$H4 # 4 + vpunpcklqdq $H1,$H0,$H0 # 0:1 + vpunpcklqdq $H3,$H2,$H3 # 2:3 + + vpsrlq \$40,$H4,$H4 # 4 + vpsrlq \$26,$H0,$H1 + vpand $MASK,$H0,$H0 # 0 + vpsrlq \$4,$H3,$H2 + vpand $MASK,$H1,$H1 # 1 + vpsrlq \$30,$H3,$H3 + vpand $MASK,$H2,$H2 # 2 + vpand $MASK,$H3,$H3 # 3 + vpor 32(%rcx),$H4,$H4 # padbit, yes, always + + vpshufd \$0x32,`16*0-64`($ctx),$T4 # r0^n, 34xx -> x3x4 + vpaddq 0x00(%r11),$H0,$H0 + vpaddq 0x10(%r11),$H1,$H1 + vpaddq 0x20(%r11),$H2,$H2 + vpaddq 0x30(%r11),$H3,$H3 + vpaddq 0x40(%r11),$H4,$H4 + + ################################################################ + # multiply (inp[0:1]+hash) by r^4:r^3 and accumulate + + vpmuludq $H0,$T4,$T0 # h0*r0 + vpaddq $T0,$D0,$D0 # d0 += h0*r0 + vpmuludq $H1,$T4,$T1 # h1*r0 + vpaddq $T1,$D1,$D1 # d1 += h1*r0 + vpmuludq $H2,$T4,$T0 # h2*r0 + vpaddq $T0,$D2,$D2 # d2 += h2*r0 + vpshufd \$0x32,`16*1-64`($ctx),$T2 # r1^n + vpmuludq $H3,$T4,$T1 # h3*r0 + vpaddq $T1,$D3,$D3 # d3 += h3*r0 + vpmuludq $H4,$T4,$T4 # h4*r0 + vpaddq $T4,$D4,$D4 # d4 += h4*r0 + + vpmuludq $H3,$T2,$T0 # h3*r1 + vpaddq $T0,$D4,$D4 # d4 += h3*r1 + vpshufd \$0x32,`16*2-64`($ctx),$T3 # s1 + vpmuludq $H2,$T2,$T1 # h2*r1 + vpaddq $T1,$D3,$D3 # d3 += h2*r1 + vpshufd \$0x32,`16*3-64`($ctx),$T4 # r2 + vpmuludq $H1,$T2,$T0 # h1*r1 + vpaddq $T0,$D2,$D2 # d2 += h1*r1 + vpmuludq $H0,$T2,$T2 # h0*r1 + vpaddq $T2,$D1,$D1 # d1 += h0*r1 + vpmuludq $H4,$T3,$T3 # h4*s1 + vpaddq $T3,$D0,$D0 # d0 += h4*s1 + + vpshufd \$0x32,`16*4-64`($ctx),$T2 # s2 + vpmuludq $H2,$T4,$T1 # h2*r2 + vpaddq $T1,$D4,$D4 # d4 += h2*r2 + vpmuludq $H1,$T4,$T0 # h1*r2 + vpaddq $T0,$D3,$D3 # d3 += h1*r2 + vpshufd \$0x32,`16*5-64`($ctx),$T3 # r3 + vpmuludq $H0,$T4,$T4 # h0*r2 + vpaddq $T4,$D2,$D2 # d2 += h0*r2 + vpmuludq $H4,$T2,$T1 # h4*s2 + vpaddq $T1,$D1,$D1 # d1 += h4*s2 + vpshufd \$0x32,`16*6-64`($ctx),$T4 # s3 + vpmuludq $H3,$T2,$T2 # h3*s2 + vpaddq $T2,$D0,$D0 # d0 += h3*s2 + + vpmuludq $H1,$T3,$T0 # h1*r3 + vpaddq $T0,$D4,$D4 # d4 += h1*r3 + vpmuludq $H0,$T3,$T3 # h0*r3 + vpaddq $T3,$D3,$D3 # d3 += h0*r3 + vpshufd \$0x32,`16*7-64`($ctx),$T2 # r4 + vpmuludq $H4,$T4,$T1 # h4*s3 + vpaddq $T1,$D2,$D2 # d2 += h4*s3 + vpshufd \$0x32,`16*8-64`($ctx),$T3 # s4 + vpmuludq $H3,$T4,$T0 # h3*s3 + vpaddq $T0,$D1,$D1 # d1 += h3*s3 + vpmuludq $H2,$T4,$T4 # h2*s3 + vpaddq $T4,$D0,$D0 # d0 += h2*s3 + + vpmuludq $H0,$T2,$T2 # h0*r4 + vpaddq $T2,$D4,$D4 # d4 += h0*r4 + vpmuludq $H4,$T3,$T1 # h4*s4 + vpaddq $T1,$D3,$D3 # d3 += h4*s4 + vpmuludq $H3,$T3,$T0 # h3*s4 + vpaddq $T0,$D2,$D2 # d2 += h3*s4 + vpmuludq $H2,$T3,$T1 # h2*s4 + vpaddq $T1,$D1,$D1 # d1 += h2*s4 + vpmuludq $H1,$T3,$T3 # h1*s4 + vpaddq $T3,$D0,$D0 # d0 += h1*s4 + +.Lshort_tail_avx: + ################################################################ + # horizontal addition + + vpsrldq \$8,$D4,$T4 + vpsrldq \$8,$D3,$T3 + vpsrldq \$8,$D1,$T1 + vpsrldq \$8,$D0,$T0 + vpsrldq \$8,$D2,$T2 + vpaddq $T3,$D3,$D3 + vpaddq $T4,$D4,$D4 + vpaddq $T0,$D0,$D0 + vpaddq $T1,$D1,$D1 + vpaddq $T2,$D2,$D2 + + ################################################################ + # lazy reduction + + vpsrlq \$26,$D3,$H3 + vpand $MASK,$D3,$D3 + vpaddq $H3,$D4,$D4 # h3 -> h4 + + vpsrlq \$26,$D0,$H0 + vpand $MASK,$D0,$D0 + vpaddq $H0,$D1,$D1 # h0 -> h1 + + vpsrlq \$26,$D4,$H4 + vpand $MASK,$D4,$D4 + + vpsrlq \$26,$D1,$H1 + vpand $MASK,$D1,$D1 + vpaddq $H1,$D2,$D2 # h1 -> h2 + + vpaddq $H4,$D0,$D0 + vpsllq \$2,$H4,$H4 + vpaddq $H4,$D0,$D0 # h4 -> h0 + + vpsrlq \$26,$D2,$H2 + vpand $MASK,$D2,$D2 + vpaddq $H2,$D3,$D3 # h2 -> h3 + + vpsrlq \$26,$D0,$H0 + vpand $MASK,$D0,$D0 + vpaddq $H0,$D1,$D1 # h0 -> h1 + + vpsrlq \$26,$D3,$H3 + vpand $MASK,$D3,$D3 + vpaddq $H3,$D4,$D4 # h3 -> h4 + + vmovd $D0,`4*0-48-64`($ctx) # save partially reduced + vmovd $D1,`4*1-48-64`($ctx) + vmovd $D2,`4*2-48-64`($ctx) + vmovd $D3,`4*3-48-64`($ctx) + vmovd $D4,`4*4-48-64`($ctx) +___ +$code.=<<___ if ($win64); + vmovdqa 0x50(%r11),%xmm6 + vmovdqa 0x60(%r11),%xmm7 + vmovdqa 0x70(%r11),%xmm8 + vmovdqa 0x80(%r11),%xmm9 + vmovdqa 0x90(%r11),%xmm10 + vmovdqa 0xa0(%r11),%xmm11 + vmovdqa 0xb0(%r11),%xmm12 + vmovdqa 0xc0(%r11),%xmm13 + vmovdqa 0xd0(%r11),%xmm14 + vmovdqa 0xe0(%r11),%xmm15 + lea 0xf8(%r11),%rsp +.Ldo_avx_epilogue: +___ +$code.=<<___ if (!$win64); + lea -8(%r10),%rsp +.cfi_def_cfa_register %rsp +___ +$code.=<<___; + vzeroupper + ret +.cfi_endproc +___ +&end_function("poly1305_blocks_avx"); + +&declare_function("poly1305_emit_avx", 32, 3); +$code.=<<___; + cmpl \$0,20($ctx) # is_base2_26? + je .Lemit + + mov 0($ctx),%eax # load hash value base 2^26 + mov 4($ctx),%ecx + mov 8($ctx),%r8d + mov 12($ctx),%r11d + mov 16($ctx),%r10d + + shl \$26,%rcx # base 2^26 -> base 2^64 + mov %r8,%r9 + shl \$52,%r8 + add %rcx,%rax + shr \$12,%r9 + add %rax,%r8 # h0 + adc \$0,%r9 + + shl \$14,%r11 + mov %r10,%rax + shr \$24,%r10 + add %r11,%r9 + shl \$40,%rax + add %rax,%r9 # h1 + adc \$0,%r10 # h2 + + mov %r10,%rax # could be partially reduced, so reduce + mov %r10,%rcx + and \$3,%r10 + shr \$2,%rax + and \$-4,%rcx + add %rcx,%rax + add %rax,%r8 + adc \$0,%r9 + adc \$0,%r10 + + mov %r8,%rax + add \$5,%r8 # compare to modulus + mov %r9,%rcx + adc \$0,%r9 + adc \$0,%r10 + shr \$2,%r10 # did 130-bit value overflow? + cmovnz %r8,%rax + cmovnz %r9,%rcx + + add 0($nonce),%rax # accumulate nonce + adc 8($nonce),%rcx + mov %rax,0($mac) # write result + mov %rcx,8($mac) + + ret +___ +&end_function("poly1305_emit_avx"); + +if ($kernel) { + $code .= "#endif\n"; +} + +if ($avx>1) { + +if ($kernel) { + $code .= "#ifdef CONFIG_AS_AVX2\n"; +} + +my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) = + map("%ymm$_",(0..15)); +my $S4=$MASK; + +sub poly1305_blocks_avxN { + my ($avx512) = @_; + my $suffix = $avx512 ? "_avx512" : ""; +$code.=<<___; +.cfi_startproc + mov 20($ctx),%r8d # is_base2_26 + cmp \$128,$len + jae .Lblocks_avx2$suffix + test %r8d,%r8d + jz .Lblocks + +.Lblocks_avx2$suffix: + and \$-16,$len + jz .Lno_data_avx2$suffix + + vzeroupper + + test %r8d,%r8d + jz .Lbase2_64_avx2$suffix + + test \$63,$len + jz .Leven_avx2$suffix + + push %rbp +.cfi_push %rbp + mov %rsp,%rbp + push %rbx +.cfi_push %rbx + push %r12 +.cfi_push %r12 + push %r13 +.cfi_push %r13 + push %r14 +.cfi_push %r14 + push %r15 +.cfi_push %r15 +.Lblocks_avx2_body$suffix: + + mov $len,%r15 # reassign $len + + mov 0($ctx),$d1 # load hash value + mov 8($ctx),$d2 + mov 16($ctx),$h2#d + + mov 24($ctx),$r0 # load r + mov 32($ctx),$s1 + + ################################# base 2^26 -> base 2^64 + mov $d1#d,$h0#d + and \$`-1*(1<<31)`,$d1 + mov $d2,$r1 # borrow $r1 + mov $d2#d,$h1#d + and \$`-1*(1<<31)`,$d2 + + shr \$6,$d1 + shl \$52,$r1 + add $d1,$h0 + shr \$12,$h1 + shr \$18,$d2 + add $r1,$h0 + adc $d2,$h1 + + mov $h2,$d1 + shl \$40,$d1 + shr \$24,$h2 + add $d1,$h1 + adc \$0,$h2 # can be partially reduced... + + mov \$-4,$d2 # ... so reduce + mov $h2,$d1 + and $h2,$d2 + shr \$2,$d1 + and \$3,$h2 + add $d2,$d1 # =*5 + add $d1,$h0 + adc \$0,$h1 + adc \$0,$h2 + + mov $s1,$r1 + mov $s1,%rax + shr \$2,$s1 + add $r1,$s1 # s1 = r1 + (r1 >> 2) + +.Lbase2_26_pre_avx2$suffix: + add 0($inp),$h0 # accumulate input + adc 8($inp),$h1 + lea 16($inp),$inp + adc $padbit,$h2 + sub \$16,%r15 + + call __poly1305_block + mov $r1,%rax + + test \$63,%r15 + jnz .Lbase2_26_pre_avx2$suffix + + test $padbit,$padbit # if $padbit is zero, + jz .Lstore_base2_64_avx2$suffix # store hash in base 2^64 format + + ################################# base 2^64 -> base 2^26 + mov $h0,%rax + mov $h0,%rdx + shr \$52,$h0 + mov $h1,$r0 + mov $h1,$r1 + shr \$26,%rdx + and \$0x3ffffff,%rax # h[0] + shl \$12,$r0 + and \$0x3ffffff,%rdx # h[1] + shr \$14,$h1 + or $r0,$h0 + shl \$24,$h2 + and \$0x3ffffff,$h0 # h[2] + shr \$40,$r1 + and \$0x3ffffff,$h1 # h[3] + or $r1,$h2 # h[4] + + test %r15,%r15 + jz .Lstore_base2_26_avx2$suffix + + vmovd %rax#d,%x#$H0 + vmovd %rdx#d,%x#$H1 + vmovd $h0#d,%x#$H2 + vmovd $h1#d,%x#$H3 + vmovd $h2#d,%x#$H4 + jmp .Lproceed_avx2$suffix + +.align 32 +.Lstore_base2_64_avx2$suffix: + mov $h0,0($ctx) + mov $h1,8($ctx) + mov $h2,16($ctx) # note that is_base2_26 is zeroed + jmp .Ldone_avx2$suffix + +.align 16 +.Lstore_base2_26_avx2$suffix: + mov %rax#d,0($ctx) # store hash value base 2^26 + mov %rdx#d,4($ctx) + mov $h0#d,8($ctx) + mov $h1#d,12($ctx) + mov $h2#d,16($ctx) +.align 16 +.Ldone_avx2$suffix: + pop %r15 +.cfi_restore %r15 + pop %r14 +.cfi_restore %r14 + pop %r13 +.cfi_restore %r13 + pop %r12 +.cfi_restore %r12 + pop %rbx +.cfi_restore %rbx + pop %rbp +.cfi_restore %rbp +.Lno_data_avx2$suffix: +.Lblocks_avx2_epilogue$suffix: + ret +.cfi_endproc + +.align 32 +.Lbase2_64_avx2$suffix: +.cfi_startproc + push %rbp +.cfi_push %rbp + mov %rsp,%rbp + push %rbx +.cfi_push %rbx + push %r12 +.cfi_push %r12 + push %r13 +.cfi_push %r13 + push %r14 +.cfi_push %r14 + push %r15 +.cfi_push %r15 +.Lbase2_64_avx2_body$suffix: + + mov $len,%r15 # reassign $len + + mov 24($ctx),$r0 # load r + mov 32($ctx),$s1 + + mov 0($ctx),$h0 # load hash value + mov 8($ctx),$h1 + mov 16($ctx),$h2#d + + mov $s1,$r1 + mov $s1,%rax + shr \$2,$s1 + add $r1,$s1 # s1 = r1 + (r1 >> 2) + + test \$63,$len + jz .Linit_avx2$suffix + +.Lbase2_64_pre_avx2$suffix: + add 0($inp),$h0 # accumulate input + adc 8($inp),$h1 + lea 16($inp),$inp + adc $padbit,$h2 + sub \$16,%r15 + + call __poly1305_block + mov $r1,%rax + + test \$63,%r15 + jnz .Lbase2_64_pre_avx2$suffix + +.Linit_avx2$suffix: + ################################# base 2^64 -> base 2^26 + mov $h0,%rax + mov $h0,%rdx + shr \$52,$h0 + mov $h1,$d1 + mov $h1,$d2 + shr \$26,%rdx + and \$0x3ffffff,%rax # h[0] + shl \$12,$d1 + and \$0x3ffffff,%rdx # h[1] + shr \$14,$h1 + or $d1,$h0 + shl \$24,$h2 + and \$0x3ffffff,$h0 # h[2] + shr \$40,$d2 + and \$0x3ffffff,$h1 # h[3] + or $d2,$h2 # h[4] + + vmovd %rax#d,%x#$H0 + vmovd %rdx#d,%x#$H1 + vmovd $h0#d,%x#$H2 + vmovd $h1#d,%x#$H3 + vmovd $h2#d,%x#$H4 + movl \$1,20($ctx) # set is_base2_26 + + call __poly1305_init_avx + +.Lproceed_avx2$suffix: + mov %r15,$len # restore $len +___ +$code.=<<___ if (!$kernel); + mov OPENSSL_ia32cap_P+8(%rip),%r9d + mov \$`(1<<31|1<<30|1<<16)`,%r11d +___ +$code.=<<___; + pop %r15 +.cfi_restore %r15 + pop %r14 +.cfi_restore %r14 + pop %r13 +.cfi_restore %r13 + pop %r12 +.cfi_restore %r12 + pop %rbx +.cfi_restore %rbx + pop %rbp +.cfi_restore %rbp +.Lbase2_64_avx2_epilogue$suffix: + jmp .Ldo_avx2$suffix +.cfi_endproc + +.align 32 +.Leven_avx2$suffix: +.cfi_startproc +___ +$code.=<<___ if (!$kernel); + mov OPENSSL_ia32cap_P+8(%rip),%r9d +___ +$code.=<<___; + vmovd 4*0($ctx),%x#$H0 # load hash value base 2^26 + vmovd 4*1($ctx),%x#$H1 + vmovd 4*2($ctx),%x#$H2 + vmovd 4*3($ctx),%x#$H3 + vmovd 4*4($ctx),%x#$H4 + +.Ldo_avx2$suffix: +___ +$code.=<<___ if (!$kernel && $avx>2); + cmp \$512,$len + jb .Lskip_avx512 + and %r11d,%r9d + test \$`1<<16`,%r9d # check for AVX512F + jnz .Lblocks_avx512 +.Lskip_avx512$suffix: +___ +$code.=<<___ if ($avx > 2 && $avx512 && $kernel); + cmp \$512,$len + jae .Lblocks_avx512 +___ +$code.=<<___ if (!$win64); + lea 8(%rsp),%r10 +.cfi_def_cfa_register %r10 + sub \$0x128,%rsp +___ +$code.=<<___ if ($win64); + lea 8(%rsp),%r10 + sub \$0x1c8,%rsp + vmovdqa %xmm6,-0xb0(%r10) + vmovdqa %xmm7,-0xa0(%r10) + vmovdqa %xmm8,-0x90(%r10) + vmovdqa %xmm9,-0x80(%r10) + vmovdqa %xmm10,-0x70(%r10) + vmovdqa %xmm11,-0x60(%r10) + vmovdqa %xmm12,-0x50(%r10) + vmovdqa %xmm13,-0x40(%r10) + vmovdqa %xmm14,-0x30(%r10) + vmovdqa %xmm15,-0x20(%r10) +.Ldo_avx2_body$suffix: +___ +$code.=<<___; + lea .Lconst(%rip),%rcx + lea 48+64($ctx),$ctx # size optimization + vmovdqa 96(%rcx),$T0 # .Lpermd_avx2 + + # expand and copy pre-calculated table to stack + vmovdqu `16*0-64`($ctx),%x#$T2 + and \$-512,%rsp + vmovdqu `16*1-64`($ctx),%x#$T3 + vmovdqu `16*2-64`($ctx),%x#$T4 + vmovdqu `16*3-64`($ctx),%x#$D0 + vmovdqu `16*4-64`($ctx),%x#$D1 + vmovdqu `16*5-64`($ctx),%x#$D2 + lea 0x90(%rsp),%rax # size optimization + vmovdqu `16*6-64`($ctx),%x#$D3 + vpermd $T2,$T0,$T2 # 00003412 -> 14243444 + vmovdqu `16*7-64`($ctx),%x#$D4 + vpermd $T3,$T0,$T3 + vmovdqu `16*8-64`($ctx),%x#$MASK + vpermd $T4,$T0,$T4 + vmovdqa $T2,0x00(%rsp) + vpermd $D0,$T0,$D0 + vmovdqa $T3,0x20-0x90(%rax) + vpermd $D1,$T0,$D1 + vmovdqa $T4,0x40-0x90(%rax) + vpermd $D2,$T0,$D2 + vmovdqa $D0,0x60-0x90(%rax) + vpermd $D3,$T0,$D3 + vmovdqa $D1,0x80-0x90(%rax) + vpermd $D4,$T0,$D4 + vmovdqa $D2,0xa0-0x90(%rax) + vpermd $MASK,$T0,$MASK + vmovdqa $D3,0xc0-0x90(%rax) + vmovdqa $D4,0xe0-0x90(%rax) + vmovdqa $MASK,0x100-0x90(%rax) + vmovdqa 64(%rcx),$MASK # .Lmask26 + + ################################################################ + # load input + vmovdqu 16*0($inp),%x#$T0 + vmovdqu 16*1($inp),%x#$T1 + vinserti128 \$1,16*2($inp),$T0,$T0 + vinserti128 \$1,16*3($inp),$T1,$T1 + lea 16*4($inp),$inp + + vpsrldq \$6,$T0,$T2 # splat input + vpsrldq \$6,$T1,$T3 + vpunpckhqdq $T1,$T0,$T4 # 4 + vpunpcklqdq $T3,$T2,$T2 # 2:3 + vpunpcklqdq $T1,$T0,$T0 # 0:1 + + vpsrlq \$30,$T2,$T3 + vpsrlq \$4,$T2,$T2 + vpsrlq \$26,$T0,$T1 + vpsrlq \$40,$T4,$T4 # 4 + vpand $MASK,$T2,$T2 # 2 + vpand $MASK,$T0,$T0 # 0 + vpand $MASK,$T1,$T1 # 1 + vpand $MASK,$T3,$T3 # 3 + vpor 32(%rcx),$T4,$T4 # padbit, yes, always + + vpaddq $H2,$T2,$H2 # accumulate input + sub \$64,$len + jz .Ltail_avx2$suffix + jmp .Loop_avx2$suffix + +.align 32 +.Loop_avx2$suffix: + ################################################################ + # ((inp[0]*r^4+inp[4])*r^4+inp[ 8])*r^4 + # ((inp[1]*r^4+inp[5])*r^4+inp[ 9])*r^3 + # ((inp[2]*r^4+inp[6])*r^4+inp[10])*r^2 + # ((inp[3]*r^4+inp[7])*r^4+inp[11])*r^1 + # \________/\__________/ + ################################################################ + #vpaddq $H2,$T2,$H2 # accumulate input + vpaddq $H0,$T0,$H0 + vmovdqa `32*0`(%rsp),$T0 # r0^4 + vpaddq $H1,$T1,$H1 + vmovdqa `32*1`(%rsp),$T1 # r1^4 + vpaddq $H3,$T3,$H3 + vmovdqa `32*3`(%rsp),$T2 # r2^4 + vpaddq $H4,$T4,$H4 + vmovdqa `32*6-0x90`(%rax),$T3 # s3^4 + vmovdqa `32*8-0x90`(%rax),$S4 # s4^4 + + # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4 + # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4 + # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4 + # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4 + # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4 + # + # however, as h2 is "chronologically" first one available pull + # corresponding operations up, so it's + # + # d4 = h2*r2 + h4*r0 + h3*r1 + h1*r3 + h0*r4 + # d3 = h2*r1 + h3*r0 + h1*r2 + h0*r3 + h4*5*r4 + # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4 + # d1 = h2*5*r4 + h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + # d0 = h2*5*r3 + h0*r0 + h4*5*r1 + h3*5*r2 + h1*5*r4 + + vpmuludq $H2,$T0,$D2 # d2 = h2*r0 + vpmuludq $H2,$T1,$D3 # d3 = h2*r1 + vpmuludq $H2,$T2,$D4 # d4 = h2*r2 + vpmuludq $H2,$T3,$D0 # d0 = h2*s3 + vpmuludq $H2,$S4,$D1 # d1 = h2*s4 + + vpmuludq $H0,$T1,$T4 # h0*r1 + vpmuludq $H1,$T1,$H2 # h1*r1, borrow $H2 as temp + vpaddq $T4,$D1,$D1 # d1 += h0*r1 + vpaddq $H2,$D2,$D2 # d2 += h1*r1 + vpmuludq $H3,$T1,$T4 # h3*r1 + vpmuludq `32*2`(%rsp),$H4,$H2 # h4*s1 + vpaddq $T4,$D4,$D4 # d4 += h3*r1 + vpaddq $H2,$D0,$D0 # d0 += h4*s1 + vmovdqa `32*4-0x90`(%rax),$T1 # s2 + + vpmuludq $H0,$T0,$T4 # h0*r0 + vpmuludq $H1,$T0,$H2 # h1*r0 + vpaddq $T4,$D0,$D0 # d0 += h0*r0 + vpaddq $H2,$D1,$D1 # d1 += h1*r0 + vpmuludq $H3,$T0,$T4 # h3*r0 + vpmuludq $H4,$T0,$H2 # h4*r0 + vmovdqu 16*0($inp),%x#$T0 # load input + vpaddq $T4,$D3,$D3 # d3 += h3*r0 + vpaddq $H2,$D4,$D4 # d4 += h4*r0 + vinserti128 \$1,16*2($inp),$T0,$T0 + + vpmuludq $H3,$T1,$T4 # h3*s2 + vpmuludq $H4,$T1,$H2 # h4*s2 + vmovdqu 16*1($inp),%x#$T1 + vpaddq $T4,$D0,$D0 # d0 += h3*s2 + vpaddq $H2,$D1,$D1 # d1 += h4*s2 + vmovdqa `32*5-0x90`(%rax),$H2 # r3 + vpmuludq $H1,$T2,$T4 # h1*r2 + vpmuludq $H0,$T2,$T2 # h0*r2 + vpaddq $T4,$D3,$D3 # d3 += h1*r2 + vpaddq $T2,$D2,$D2 # d2 += h0*r2 + vinserti128 \$1,16*3($inp),$T1,$T1 + lea 16*4($inp),$inp + + vpmuludq $H1,$H2,$T4 # h1*r3 + vpmuludq $H0,$H2,$H2 # h0*r3 + vpsrldq \$6,$T0,$T2 # splat input + vpaddq $T4,$D4,$D4 # d4 += h1*r3 + vpaddq $H2,$D3,$D3 # d3 += h0*r3 + vpmuludq $H3,$T3,$T4 # h3*s3 + vpmuludq $H4,$T3,$H2 # h4*s3 + vpsrldq \$6,$T1,$T3 + vpaddq $T4,$D1,$D1 # d1 += h3*s3 + vpaddq $H2,$D2,$D2 # d2 += h4*s3 + vpunpckhqdq $T1,$T0,$T4 # 4 + + vpmuludq $H3,$S4,$H3 # h3*s4 + vpmuludq $H4,$S4,$H4 # h4*s4 + vpunpcklqdq $T1,$T0,$T0 # 0:1 + vpaddq $H3,$D2,$H2 # h2 = d2 + h3*r4 + vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4 + vpunpcklqdq $T3,$T2,$T3 # 2:3 + vpmuludq `32*7-0x90`(%rax),$H0,$H4 # h0*r4 + vpmuludq $H1,$S4,$H0 # h1*s4 + vmovdqa 64(%rcx),$MASK # .Lmask26 + vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4 + vpaddq $H0,$D0,$H0 # h0 = d0 + h1*s4 + + ################################################################ + # lazy reduction (interleaved with tail of input splat) + + vpsrlq \$26,$H3,$D3 + vpand $MASK,$H3,$H3 + vpaddq $D3,$H4,$H4 # h3 -> h4 + + vpsrlq \$26,$H0,$D0 + vpand $MASK,$H0,$H0 + vpaddq $D0,$D1,$H1 # h0 -> h1 + + vpsrlq \$26,$H4,$D4 + vpand $MASK,$H4,$H4 + + vpsrlq \$4,$T3,$T2 + + vpsrlq \$26,$H1,$D1 + vpand $MASK,$H1,$H1 + vpaddq $D1,$H2,$H2 # h1 -> h2 + + vpaddq $D4,$H0,$H0 + vpsllq \$2,$D4,$D4 + vpaddq $D4,$H0,$H0 # h4 -> h0 + + vpand $MASK,$T2,$T2 # 2 + vpsrlq \$26,$T0,$T1 + + vpsrlq \$26,$H2,$D2 + vpand $MASK,$H2,$H2 + vpaddq $D2,$H3,$H3 # h2 -> h3 + + vpaddq $T2,$H2,$H2 # modulo-scheduled + vpsrlq \$30,$T3,$T3 + + vpsrlq \$26,$H0,$D0 + vpand $MASK,$H0,$H0 + vpaddq $D0,$H1,$H1 # h0 -> h1 + + vpsrlq \$40,$T4,$T4 # 4 + + vpsrlq \$26,$H3,$D3 + vpand $MASK,$H3,$H3 + vpaddq $D3,$H4,$H4 # h3 -> h4 + + vpand $MASK,$T0,$T0 # 0 + vpand $MASK,$T1,$T1 # 1 + vpand $MASK,$T3,$T3 # 3 + vpor 32(%rcx),$T4,$T4 # padbit, yes, always + + sub \$64,$len + jnz .Loop_avx2$suffix + + .byte 0x66,0x90 +.Ltail_avx2$suffix: + ################################################################ + # while above multiplications were by r^4 in all lanes, in last + # iteration we multiply least significant lane by r^4 and most + # significant one by r, so copy of above except that references + # to the precomputed table are displaced by 4... + + #vpaddq $H2,$T2,$H2 # accumulate input + vpaddq $H0,$T0,$H0 + vmovdqu `32*0+4`(%rsp),$T0 # r0^4 + vpaddq $H1,$T1,$H1 + vmovdqu `32*1+4`(%rsp),$T1 # r1^4 + vpaddq $H3,$T3,$H3 + vmovdqu `32*3+4`(%rsp),$T2 # r2^4 + vpaddq $H4,$T4,$H4 + vmovdqu `32*6+4-0x90`(%rax),$T3 # s3^4 + vmovdqu `32*8+4-0x90`(%rax),$S4 # s4^4 + + vpmuludq $H2,$T0,$D2 # d2 = h2*r0 + vpmuludq $H2,$T1,$D3 # d3 = h2*r1 + vpmuludq $H2,$T2,$D4 # d4 = h2*r2 + vpmuludq $H2,$T3,$D0 # d0 = h2*s3 + vpmuludq $H2,$S4,$D1 # d1 = h2*s4 + + vpmuludq $H0,$T1,$T4 # h0*r1 + vpmuludq $H1,$T1,$H2 # h1*r1 + vpaddq $T4,$D1,$D1 # d1 += h0*r1 + vpaddq $H2,$D2,$D2 # d2 += h1*r1 + vpmuludq $H3,$T1,$T4 # h3*r1 + vpmuludq `32*2+4`(%rsp),$H4,$H2 # h4*s1 + vpaddq $T4,$D4,$D4 # d4 += h3*r1 + vpaddq $H2,$D0,$D0 # d0 += h4*s1 + + vpmuludq $H0,$T0,$T4 # h0*r0 + vpmuludq $H1,$T0,$H2 # h1*r0 + vpaddq $T4,$D0,$D0 # d0 += h0*r0 + vmovdqu `32*4+4-0x90`(%rax),$T1 # s2 + vpaddq $H2,$D1,$D1 # d1 += h1*r0 + vpmuludq $H3,$T0,$T4 # h3*r0 + vpmuludq $H4,$T0,$H2 # h4*r0 + vpaddq $T4,$D3,$D3 # d3 += h3*r0 + vpaddq $H2,$D4,$D4 # d4 += h4*r0 + + vpmuludq $H3,$T1,$T4 # h3*s2 + vpmuludq $H4,$T1,$H2 # h4*s2 + vpaddq $T4,$D0,$D0 # d0 += h3*s2 + vpaddq $H2,$D1,$D1 # d1 += h4*s2 + vmovdqu `32*5+4-0x90`(%rax),$H2 # r3 + vpmuludq $H1,$T2,$T4 # h1*r2 + vpmuludq $H0,$T2,$T2 # h0*r2 + vpaddq $T4,$D3,$D3 # d3 += h1*r2 + vpaddq $T2,$D2,$D2 # d2 += h0*r2 + + vpmuludq $H1,$H2,$T4 # h1*r3 + vpmuludq $H0,$H2,$H2 # h0*r3 + vpaddq $T4,$D4,$D4 # d4 += h1*r3 + vpaddq $H2,$D3,$D3 # d3 += h0*r3 + vpmuludq $H3,$T3,$T4 # h3*s3 + vpmuludq $H4,$T3,$H2 # h4*s3 + vpaddq $T4,$D1,$D1 # d1 += h3*s3 + vpaddq $H2,$D2,$D2 # d2 += h4*s3 + + vpmuludq $H3,$S4,$H3 # h3*s4 + vpmuludq $H4,$S4,$H4 # h4*s4 + vpaddq $H3,$D2,$H2 # h2 = d2 + h3*r4 + vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4 + vpmuludq `32*7+4-0x90`(%rax),$H0,$H4 # h0*r4 + vpmuludq $H1,$S4,$H0 # h1*s4 + vmovdqa 64(%rcx),$MASK # .Lmask26 + vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4 + vpaddq $H0,$D0,$H0 # h0 = d0 + h1*s4 + + ################################################################ + # horizontal addition + + vpsrldq \$8,$D1,$T1 + vpsrldq \$8,$H2,$T2 + vpsrldq \$8,$H3,$T3 + vpsrldq \$8,$H4,$T4 + vpsrldq \$8,$H0,$T0 + vpaddq $T1,$D1,$D1 + vpaddq $T2,$H2,$H2 + vpaddq $T3,$H3,$H3 + vpaddq $T4,$H4,$H4 + vpaddq $T0,$H0,$H0 + + vpermq \$0x2,$H3,$T3 + vpermq \$0x2,$H4,$T4 + vpermq \$0x2,$H0,$T0 + vpermq \$0x2,$D1,$T1 + vpermq \$0x2,$H2,$T2 + vpaddq $T3,$H3,$H3 + vpaddq $T4,$H4,$H4 + vpaddq $T0,$H0,$H0 + vpaddq $T1,$D1,$D1 + vpaddq $T2,$H2,$H2 + + ################################################################ + # lazy reduction + + vpsrlq \$26,$H3,$D3 + vpand $MASK,$H3,$H3 + vpaddq $D3,$H4,$H4 # h3 -> h4 + + vpsrlq \$26,$H0,$D0 + vpand $MASK,$H0,$H0 + vpaddq $D0,$D1,$H1 # h0 -> h1 + + vpsrlq \$26,$H4,$D4 + vpand $MASK,$H4,$H4 + + vpsrlq \$26,$H1,$D1 + vpand $MASK,$H1,$H1 + vpaddq $D1,$H2,$H2 # h1 -> h2 + + vpaddq $D4,$H0,$H0 + vpsllq \$2,$D4,$D4 + vpaddq $D4,$H0,$H0 # h4 -> h0 + + vpsrlq \$26,$H2,$D2 + vpand $MASK,$H2,$H2 + vpaddq $D2,$H3,$H3 # h2 -> h3 + + vpsrlq \$26,$H0,$D0 + vpand $MASK,$H0,$H0 + vpaddq $D0,$H1,$H1 # h0 -> h1 + + vpsrlq \$26,$H3,$D3 + vpand $MASK,$H3,$H3 + vpaddq $D3,$H4,$H4 # h3 -> h4 + + vmovd %x#$H0,`4*0-48-64`($ctx)# save partially reduced + vmovd %x#$H1,`4*1-48-64`($ctx) + vmovd %x#$H2,`4*2-48-64`($ctx) + vmovd %x#$H3,`4*3-48-64`($ctx) + vmovd %x#$H4,`4*4-48-64`($ctx) +___ +$code.=<<___ if ($win64); + vmovdqa -0xb0(%r10),%xmm6 + vmovdqa -0xa0(%r10),%xmm7 + vmovdqa -0x90(%r10),%xmm8 + vmovdqa -0x80(%r10),%xmm9 + vmovdqa -0x70(%r10),%xmm10 + vmovdqa -0x60(%r10),%xmm11 + vmovdqa -0x50(%r10),%xmm12 + vmovdqa -0x40(%r10),%xmm13 + vmovdqa -0x30(%r10),%xmm14 + vmovdqa -0x20(%r10),%xmm15 + lea -8(%r10),%rsp +.Ldo_avx2_epilogue$suffix: +___ +$code.=<<___ if (!$win64); + lea -8(%r10),%rsp +.cfi_def_cfa_register %rsp +___ +$code.=<<___; + vzeroupper + ret +.cfi_endproc +___ +if($avx > 2 && $avx512) { +my ($R0,$R1,$R2,$R3,$R4, $S1,$S2,$S3,$S4) = map("%zmm$_",(16..24)); +my ($M0,$M1,$M2,$M3,$M4) = map("%zmm$_",(25..29)); +my $PADBIT="%zmm30"; + +map(s/%y/%z/,($T4,$T0,$T1,$T2,$T3)); # switch to %zmm domain +map(s/%y/%z/,($D0,$D1,$D2,$D3,$D4)); +map(s/%y/%z/,($H0,$H1,$H2,$H3,$H4)); +map(s/%y/%z/,($MASK)); + +$code.=<<___; +.cfi_startproc +.Lblocks_avx512: + mov \$15,%eax + kmovw %eax,%k2 +___ +$code.=<<___ if (!$win64); + lea 8(%rsp),%r10 +.cfi_def_cfa_register %r10 + sub \$0x128,%rsp +___ +$code.=<<___ if ($win64); + lea 8(%rsp),%r10 + sub \$0x1c8,%rsp + vmovdqa %xmm6,-0xb0(%r10) + vmovdqa %xmm7,-0xa0(%r10) + vmovdqa %xmm8,-0x90(%r10) + vmovdqa %xmm9,-0x80(%r10) + vmovdqa %xmm10,-0x70(%r10) + vmovdqa %xmm11,-0x60(%r10) + vmovdqa %xmm12,-0x50(%r10) + vmovdqa %xmm13,-0x40(%r10) + vmovdqa %xmm14,-0x30(%r10) + vmovdqa %xmm15,-0x20(%r10) +.Ldo_avx512_body: +___ +$code.=<<___; + lea .Lconst(%rip),%rcx + lea 48+64($ctx),$ctx # size optimization + vmovdqa 96(%rcx),%y#$T2 # .Lpermd_avx2 + + # expand pre-calculated table + vmovdqu `16*0-64`($ctx),%x#$D0 # will become expanded ${R0} + and \$-512,%rsp + vmovdqu `16*1-64`($ctx),%x#$D1 # will become ... ${R1} + mov \$0x20,%rax + vmovdqu `16*2-64`($ctx),%x#$T0 # ... ${S1} + vmovdqu `16*3-64`($ctx),%x#$D2 # ... ${R2} + vmovdqu `16*4-64`($ctx),%x#$T1 # ... ${S2} + vmovdqu `16*5-64`($ctx),%x#$D3 # ... ${R3} + vmovdqu `16*6-64`($ctx),%x#$T3 # ... ${S3} + vmovdqu `16*7-64`($ctx),%x#$D4 # ... ${R4} + vmovdqu `16*8-64`($ctx),%x#$T4 # ... ${S4} + vpermd $D0,$T2,$R0 # 00003412 -> 14243444 + vpbroadcastq 64(%rcx),$MASK # .Lmask26 + vpermd $D1,$T2,$R1 + vpermd $T0,$T2,$S1 + vpermd $D2,$T2,$R2 + vmovdqa64 $R0,0x00(%rsp){%k2} # save in case $len%128 != 0 + vpsrlq \$32,$R0,$T0 # 14243444 -> 01020304 + vpermd $T1,$T2,$S2 + vmovdqu64 $R1,0x00(%rsp,%rax){%k2} + vpsrlq \$32,$R1,$T1 + vpermd $D3,$T2,$R3 + vmovdqa64 $S1,0x40(%rsp){%k2} + vpermd $T3,$T2,$S3 + vpermd $D4,$T2,$R4 + vmovdqu64 $R2,0x40(%rsp,%rax){%k2} + vpermd $T4,$T2,$S4 + vmovdqa64 $S2,0x80(%rsp){%k2} + vmovdqu64 $R3,0x80(%rsp,%rax){%k2} + vmovdqa64 $S3,0xc0(%rsp){%k2} + vmovdqu64 $R4,0xc0(%rsp,%rax){%k2} + vmovdqa64 $S4,0x100(%rsp){%k2} + + ################################################################ + # calculate 5th through 8th powers of the key + # + # d0 = r0'*r0 + r1'*5*r4 + r2'*5*r3 + r3'*5*r2 + r4'*5*r1 + # d1 = r0'*r1 + r1'*r0 + r2'*5*r4 + r3'*5*r3 + r4'*5*r2 + # d2 = r0'*r2 + r1'*r1 + r2'*r0 + r3'*5*r4 + r4'*5*r3 + # d3 = r0'*r3 + r1'*r2 + r2'*r1 + r3'*r0 + r4'*5*r4 + # d4 = r0'*r4 + r1'*r3 + r2'*r2 + r3'*r1 + r4'*r0 + + vpmuludq $T0,$R0,$D0 # d0 = r0'*r0 + vpmuludq $T0,$R1,$D1 # d1 = r0'*r1 + vpmuludq $T0,$R2,$D2 # d2 = r0'*r2 + vpmuludq $T0,$R3,$D3 # d3 = r0'*r3 + vpmuludq $T0,$R4,$D4 # d4 = r0'*r4 + vpsrlq \$32,$R2,$T2 + + vpmuludq $T1,$S4,$M0 + vpmuludq $T1,$R0,$M1 + vpmuludq $T1,$R1,$M2 + vpmuludq $T1,$R2,$M3 + vpmuludq $T1,$R3,$M4 + vpsrlq \$32,$R3,$T3 + vpaddq $M0,$D0,$D0 # d0 += r1'*5*r4 + vpaddq $M1,$D1,$D1 # d1 += r1'*r0 + vpaddq $M2,$D2,$D2 # d2 += r1'*r1 + vpaddq $M3,$D3,$D3 # d3 += r1'*r2 + vpaddq $M4,$D4,$D4 # d4 += r1'*r3 + + vpmuludq $T2,$S3,$M0 + vpmuludq $T2,$S4,$M1 + vpmuludq $T2,$R1,$M3 + vpmuludq $T2,$R2,$M4 + vpmuludq $T2,$R0,$M2 + vpsrlq \$32,$R4,$T4 + vpaddq $M0,$D0,$D0 # d0 += r2'*5*r3 + vpaddq $M1,$D1,$D1 # d1 += r2'*5*r4 + vpaddq $M3,$D3,$D3 # d3 += r2'*r1 + vpaddq $M4,$D4,$D4 # d4 += r2'*r2 + vpaddq $M2,$D2,$D2 # d2 += r2'*r0 + + vpmuludq $T3,$S2,$M0 + vpmuludq $T3,$R0,$M3 + vpmuludq $T3,$R1,$M4 + vpmuludq $T3,$S3,$M1 + vpmuludq $T3,$S4,$M2 + vpaddq $M0,$D0,$D0 # d0 += r3'*5*r2 + vpaddq $M3,$D3,$D3 # d3 += r3'*r0 + vpaddq $M4,$D4,$D4 # d4 += r3'*r1 + vpaddq $M1,$D1,$D1 # d1 += r3'*5*r3 + vpaddq $M2,$D2,$D2 # d2 += r3'*5*r4 + + vpmuludq $T4,$S4,$M3 + vpmuludq $T4,$R0,$M4 + vpmuludq $T4,$S1,$M0 + vpmuludq $T4,$S2,$M1 + vpmuludq $T4,$S3,$M2 + vpaddq $M3,$D3,$D3 # d3 += r2'*5*r4 + vpaddq $M4,$D4,$D4 # d4 += r2'*r0 + vpaddq $M0,$D0,$D0 # d0 += r2'*5*r1 + vpaddq $M1,$D1,$D1 # d1 += r2'*5*r2 + vpaddq $M2,$D2,$D2 # d2 += r2'*5*r3 + + ################################################################ + # load input + vmovdqu64 16*0($inp),%z#$T3 + vmovdqu64 16*4($inp),%z#$T4 + lea 16*8($inp),$inp + + ################################################################ + # lazy reduction + + vpsrlq \$26,$D3,$M3 + vpandq $MASK,$D3,$D3 + vpaddq $M3,$D4,$D4 # d3 -> d4 + + vpsrlq \$26,$D0,$M0 + vpandq $MASK,$D0,$D0 + vpaddq $M0,$D1,$D1 # d0 -> d1 + + vpsrlq \$26,$D4,$M4 + vpandq $MASK,$D4,$D4 + + vpsrlq \$26,$D1,$M1 + vpandq $MASK,$D1,$D1 + vpaddq $M1,$D2,$D2 # d1 -> d2 + + vpaddq $M4,$D0,$D0 + vpsllq \$2,$M4,$M4 + vpaddq $M4,$D0,$D0 # d4 -> d0 + + vpsrlq \$26,$D2,$M2 + vpandq $MASK,$D2,$D2 + vpaddq $M2,$D3,$D3 # d2 -> d3 + + vpsrlq \$26,$D0,$M0 + vpandq $MASK,$D0,$D0 + vpaddq $M0,$D1,$D1 # d0 -> d1 + + vpsrlq \$26,$D3,$M3 + vpandq $MASK,$D3,$D3 + vpaddq $M3,$D4,$D4 # d3 -> d4 + + ################################################################ + # at this point we have 14243444 in $R0-$S4 and 05060708 in + # $D0-$D4, ... + + vpunpcklqdq $T4,$T3,$T0 # transpose input + vpunpckhqdq $T4,$T3,$T4 + + # ... since input 64-bit lanes are ordered as 73625140, we could + # "vperm" it to 76543210 (here and in each loop iteration), *or* + # we could just flow along, hence the goal for $R0-$S4 is + # 1858286838784888 ... + + vmovdqa32 128(%rcx),$M0 # .Lpermd_avx512: + mov \$0x7777,%eax + kmovw %eax,%k1 + + vpermd $R0,$M0,$R0 # 14243444 -> 1---2---3---4--- + vpermd $R1,$M0,$R1 + vpermd $R2,$M0,$R2 + vpermd $R3,$M0,$R3 + vpermd $R4,$M0,$R4 + + vpermd $D0,$M0,${R0}{%k1} # 05060708 -> 1858286838784888 + vpermd $D1,$M0,${R1}{%k1} + vpermd $D2,$M0,${R2}{%k1} + vpermd $D3,$M0,${R3}{%k1} + vpermd $D4,$M0,${R4}{%k1} + + vpslld \$2,$R1,$S1 # *5 + vpslld \$2,$R2,$S2 + vpslld \$2,$R3,$S3 + vpslld \$2,$R4,$S4 + vpaddd $R1,$S1,$S1 + vpaddd $R2,$S2,$S2 + vpaddd $R3,$S3,$S3 + vpaddd $R4,$S4,$S4 + + vpbroadcastq 32(%rcx),$PADBIT # .L129 + + vpsrlq \$52,$T0,$T2 # splat input + vpsllq \$12,$T4,$T3 + vporq $T3,$T2,$T2 + vpsrlq \$26,$T0,$T1 + vpsrlq \$14,$T4,$T3 + vpsrlq \$40,$T4,$T4 # 4 + vpandq $MASK,$T2,$T2 # 2 + vpandq $MASK,$T0,$T0 # 0 + #vpandq $MASK,$T1,$T1 # 1 + #vpandq $MASK,$T3,$T3 # 3 + #vporq $PADBIT,$T4,$T4 # padbit, yes, always + + vpaddq $H2,$T2,$H2 # accumulate input + sub \$192,$len + jbe .Ltail_avx512 + jmp .Loop_avx512 + +.align 32 +.Loop_avx512: + ################################################################ + # ((inp[0]*r^8+inp[ 8])*r^8+inp[16])*r^8 + # ((inp[1]*r^8+inp[ 9])*r^8+inp[17])*r^7 + # ((inp[2]*r^8+inp[10])*r^8+inp[18])*r^6 + # ((inp[3]*r^8+inp[11])*r^8+inp[19])*r^5 + # ((inp[4]*r^8+inp[12])*r^8+inp[20])*r^4 + # ((inp[5]*r^8+inp[13])*r^8+inp[21])*r^3 + # ((inp[6]*r^8+inp[14])*r^8+inp[22])*r^2 + # ((inp[7]*r^8+inp[15])*r^8+inp[23])*r^1 + # \________/\___________/ + ################################################################ + #vpaddq $H2,$T2,$H2 # accumulate input + + # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4 + # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4 + # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4 + # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4 + # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4 + # + # however, as h2 is "chronologically" first one available pull + # corresponding operations up, so it's + # + # d3 = h2*r1 + h0*r3 + h1*r2 + h3*r0 + h4*5*r4 + # d4 = h2*r2 + h0*r4 + h1*r3 + h3*r1 + h4*r0 + # d0 = h2*5*r3 + h0*r0 + h1*5*r4 + h3*5*r2 + h4*5*r1 + # d1 = h2*5*r4 + h0*r1 + h1*r0 + h3*5*r3 + h4*5*r2 + # d2 = h2*r0 + h0*r2 + h1*r1 + h3*5*r4 + h4*5*r3 + + vpmuludq $H2,$R1,$D3 # d3 = h2*r1 + vpaddq $H0,$T0,$H0 + vpmuludq $H2,$R2,$D4 # d4 = h2*r2 + vpandq $MASK,$T1,$T1 # 1 + vpmuludq $H2,$S3,$D0 # d0 = h2*s3 + vpandq $MASK,$T3,$T3 # 3 + vpmuludq $H2,$S4,$D1 # d1 = h2*s4 + vporq $PADBIT,$T4,$T4 # padbit, yes, always + vpmuludq $H2,$R0,$D2 # d2 = h2*r0 + vpaddq $H1,$T1,$H1 # accumulate input + vpaddq $H3,$T3,$H3 + vpaddq $H4,$T4,$H4 + + vmovdqu64 16*0($inp),$T3 # load input + vmovdqu64 16*4($inp),$T4 + lea 16*8($inp),$inp + vpmuludq $H0,$R3,$M3 + vpmuludq $H0,$R4,$M4 + vpmuludq $H0,$R0,$M0 + vpmuludq $H0,$R1,$M1 + vpaddq $M3,$D3,$D3 # d3 += h0*r3 + vpaddq $M4,$D4,$D4 # d4 += h0*r4 + vpaddq $M0,$D0,$D0 # d0 += h0*r0 + vpaddq $M1,$D1,$D1 # d1 += h0*r1 + + vpmuludq $H1,$R2,$M3 + vpmuludq $H1,$R3,$M4 + vpmuludq $H1,$S4,$M0 + vpmuludq $H0,$R2,$M2 + vpaddq $M3,$D3,$D3 # d3 += h1*r2 + vpaddq $M4,$D4,$D4 # d4 += h1*r3 + vpaddq $M0,$D0,$D0 # d0 += h1*s4 + vpaddq $M2,$D2,$D2 # d2 += h0*r2 + + vpunpcklqdq $T4,$T3,$T0 # transpose input + vpunpckhqdq $T4,$T3,$T4 + + vpmuludq $H3,$R0,$M3 + vpmuludq $H3,$R1,$M4 + vpmuludq $H1,$R0,$M1 + vpmuludq $H1,$R1,$M2 + vpaddq $M3,$D3,$D3 # d3 += h3*r0 + vpaddq $M4,$D4,$D4 # d4 += h3*r1 + vpaddq $M1,$D1,$D1 # d1 += h1*r0 + vpaddq $M2,$D2,$D2 # d2 += h1*r1 + + vpmuludq $H4,$S4,$M3 + vpmuludq $H4,$R0,$M4 + vpmuludq $H3,$S2,$M0 + vpmuludq $H3,$S3,$M1 + vpaddq $M3,$D3,$D3 # d3 += h4*s4 + vpmuludq $H3,$S4,$M2 + vpaddq $M4,$D4,$D4 # d4 += h4*r0 + vpaddq $M0,$D0,$D0 # d0 += h3*s2 + vpaddq $M1,$D1,$D1 # d1 += h3*s3 + vpaddq $M2,$D2,$D2 # d2 += h3*s4 + + vpmuludq $H4,$S1,$M0 + vpmuludq $H4,$S2,$M1 + vpmuludq $H4,$S3,$M2 + vpaddq $M0,$D0,$H0 # h0 = d0 + h4*s1 + vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2 + vpaddq $M2,$D2,$H2 # h2 = d3 + h4*s3 + + ################################################################ + # lazy reduction (interleaved with input splat) + + vpsrlq \$52,$T0,$T2 # splat input + vpsllq \$12,$T4,$T3 + + vpsrlq \$26,$D3,$H3 + vpandq $MASK,$D3,$D3 + vpaddq $H3,$D4,$H4 # h3 -> h4 + + vporq $T3,$T2,$T2 + + vpsrlq \$26,$H0,$D0 + vpandq $MASK,$H0,$H0 + vpaddq $D0,$H1,$H1 # h0 -> h1 + + vpandq $MASK,$T2,$T2 # 2 + + vpsrlq \$26,$H4,$D4 + vpandq $MASK,$H4,$H4 + + vpsrlq \$26,$H1,$D1 + vpandq $MASK,$H1,$H1 + vpaddq $D1,$H2,$H2 # h1 -> h2 + + vpaddq $D4,$H0,$H0 + vpsllq \$2,$D4,$D4 + vpaddq $D4,$H0,$H0 # h4 -> h0 + + vpaddq $T2,$H2,$H2 # modulo-scheduled + vpsrlq \$26,$T0,$T1 + + vpsrlq \$26,$H2,$D2 + vpandq $MASK,$H2,$H2 + vpaddq $D2,$D3,$H3 # h2 -> h3 + + vpsrlq \$14,$T4,$T3 + + vpsrlq \$26,$H0,$D0 + vpandq $MASK,$H0,$H0 + vpaddq $D0,$H1,$H1 # h0 -> h1 + + vpsrlq \$40,$T4,$T4 # 4 + + vpsrlq \$26,$H3,$D3 + vpandq $MASK,$H3,$H3 + vpaddq $D3,$H4,$H4 # h3 -> h4 + + vpandq $MASK,$T0,$T0 # 0 + #vpandq $MASK,$T1,$T1 # 1 + #vpandq $MASK,$T3,$T3 # 3 + #vporq $PADBIT,$T4,$T4 # padbit, yes, always + + sub \$128,$len + ja .Loop_avx512 + +.Ltail_avx512: + ################################################################ + # while above multiplications were by r^8 in all lanes, in last + # iteration we multiply least significant lane by r^8 and most + # significant one by r, that's why table gets shifted... + + vpsrlq \$32,$R0,$R0 # 0105020603070408 + vpsrlq \$32,$R1,$R1 + vpsrlq \$32,$R2,$R2 + vpsrlq \$32,$S3,$S3 + vpsrlq \$32,$S4,$S4 + vpsrlq \$32,$R3,$R3 + vpsrlq \$32,$R4,$R4 + vpsrlq \$32,$S1,$S1 + vpsrlq \$32,$S2,$S2 + + ################################################################ + # load either next or last 64 byte of input + lea ($inp,$len),$inp + + #vpaddq $H2,$T2,$H2 # accumulate input + vpaddq $H0,$T0,$H0 + + vpmuludq $H2,$R1,$D3 # d3 = h2*r1 + vpmuludq $H2,$R2,$D4 # d4 = h2*r2 + vpmuludq $H2,$S3,$D0 # d0 = h2*s3 + vpandq $MASK,$T1,$T1 # 1 + vpmuludq $H2,$S4,$D1 # d1 = h2*s4 + vpandq $MASK,$T3,$T3 # 3 + vpmuludq $H2,$R0,$D2 # d2 = h2*r0 + vporq $PADBIT,$T4,$T4 # padbit, yes, always + vpaddq $H1,$T1,$H1 # accumulate input + vpaddq $H3,$T3,$H3 + vpaddq $H4,$T4,$H4 + + vmovdqu 16*0($inp),%x#$T0 + vpmuludq $H0,$R3,$M3 + vpmuludq $H0,$R4,$M4 + vpmuludq $H0,$R0,$M0 + vpmuludq $H0,$R1,$M1 + vpaddq $M3,$D3,$D3 # d3 += h0*r3 + vpaddq $M4,$D4,$D4 # d4 += h0*r4 + vpaddq $M0,$D0,$D0 # d0 += h0*r0 + vpaddq $M1,$D1,$D1 # d1 += h0*r1 + + vmovdqu 16*1($inp),%x#$T1 + vpmuludq $H1,$R2,$M3 + vpmuludq $H1,$R3,$M4 + vpmuludq $H1,$S4,$M0 + vpmuludq $H0,$R2,$M2 + vpaddq $M3,$D3,$D3 # d3 += h1*r2 + vpaddq $M4,$D4,$D4 # d4 += h1*r3 + vpaddq $M0,$D0,$D0 # d0 += h1*s4 + vpaddq $M2,$D2,$D2 # d2 += h0*r2 + + vinserti128 \$1,16*2($inp),%y#$T0,%y#$T0 + vpmuludq $H3,$R0,$M3 + vpmuludq $H3,$R1,$M4 + vpmuludq $H1,$R0,$M1 + vpmuludq $H1,$R1,$M2 + vpaddq $M3,$D3,$D3 # d3 += h3*r0 + vpaddq $M4,$D4,$D4 # d4 += h3*r1 + vpaddq $M1,$D1,$D1 # d1 += h1*r0 + vpaddq $M2,$D2,$D2 # d2 += h1*r1 + + vinserti128 \$1,16*3($inp),%y#$T1,%y#$T1 + vpmuludq $H4,$S4,$M3 + vpmuludq $H4,$R0,$M4 + vpmuludq $H3,$S2,$M0 + vpmuludq $H3,$S3,$M1 + vpmuludq $H3,$S4,$M2 + vpaddq $M3,$D3,$H3 # h3 = d3 + h4*s4 + vpaddq $M4,$D4,$D4 # d4 += h4*r0 + vpaddq $M0,$D0,$D0 # d0 += h3*s2 + vpaddq $M1,$D1,$D1 # d1 += h3*s3 + vpaddq $M2,$D2,$D2 # d2 += h3*s4 + + vpmuludq $H4,$S1,$M0 + vpmuludq $H4,$S2,$M1 + vpmuludq $H4,$S3,$M2 + vpaddq $M0,$D0,$H0 # h0 = d0 + h4*s1 + vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2 + vpaddq $M2,$D2,$H2 # h2 = d3 + h4*s3 + + ################################################################ + # horizontal addition + + mov \$1,%eax + vpermq \$0xb1,$H3,$D3 + vpermq \$0xb1,$D4,$H4 + vpermq \$0xb1,$H0,$D0 + vpermq \$0xb1,$H1,$D1 + vpermq \$0xb1,$H2,$D2 + vpaddq $D3,$H3,$H3 + vpaddq $D4,$H4,$H4 + vpaddq $D0,$H0,$H0 + vpaddq $D1,$H1,$H1 + vpaddq $D2,$H2,$H2 + + kmovw %eax,%k3 + vpermq \$0x2,$H3,$D3 + vpermq \$0x2,$H4,$D4 + vpermq \$0x2,$H0,$D0 + vpermq \$0x2,$H1,$D1 + vpermq \$0x2,$H2,$D2 + vpaddq $D3,$H3,$H3 + vpaddq $D4,$H4,$H4 + vpaddq $D0,$H0,$H0 + vpaddq $D1,$H1,$H1 + vpaddq $D2,$H2,$H2 + + vextracti64x4 \$0x1,$H3,%y#$D3 + vextracti64x4 \$0x1,$H4,%y#$D4 + vextracti64x4 \$0x1,$H0,%y#$D0 + vextracti64x4 \$0x1,$H1,%y#$D1 + vextracti64x4 \$0x1,$H2,%y#$D2 + vpaddq $D3,$H3,${H3}{%k3}{z} # keep single qword in case + vpaddq $D4,$H4,${H4}{%k3}{z} # it's passed to .Ltail_avx2 + vpaddq $D0,$H0,${H0}{%k3}{z} + vpaddq $D1,$H1,${H1}{%k3}{z} + vpaddq $D2,$H2,${H2}{%k3}{z} +___ +map(s/%z/%y/,($T0,$T1,$T2,$T3,$T4, $PADBIT)); +map(s/%z/%y/,($H0,$H1,$H2,$H3,$H4, $D0,$D1,$D2,$D3,$D4, $MASK)); +$code.=<<___; + ################################################################ + # lazy reduction (interleaved with input splat) + + vpsrlq \$26,$H3,$D3 + vpand $MASK,$H3,$H3 + vpsrldq \$6,$T0,$T2 # splat input + vpsrldq \$6,$T1,$T3 + vpunpckhqdq $T1,$T0,$T4 # 4 + vpaddq $D3,$H4,$H4 # h3 -> h4 + + vpsrlq \$26,$H0,$D0 + vpand $MASK,$H0,$H0 + vpunpcklqdq $T3,$T2,$T2 # 2:3 + vpunpcklqdq $T1,$T0,$T0 # 0:1 + vpaddq $D0,$H1,$H1 # h0 -> h1 + + vpsrlq \$26,$H4,$D4 + vpand $MASK,$H4,$H4 + + vpsrlq \$26,$H1,$D1 + vpand $MASK,$H1,$H1 + vpsrlq \$30,$T2,$T3 + vpsrlq \$4,$T2,$T2 + vpaddq $D1,$H2,$H2 # h1 -> h2 + + vpaddq $D4,$H0,$H0 + vpsllq \$2,$D4,$D4 + vpsrlq \$26,$T0,$T1 + vpsrlq \$40,$T4,$T4 # 4 + vpaddq $D4,$H0,$H0 # h4 -> h0 + + vpsrlq \$26,$H2,$D2 + vpand $MASK,$H2,$H2 + vpand $MASK,$T2,$T2 # 2 + vpand $MASK,$T0,$T0 # 0 + vpaddq $D2,$H3,$H3 # h2 -> h3 + + vpsrlq \$26,$H0,$D0 + vpand $MASK,$H0,$H0 + vpaddq $H2,$T2,$H2 # accumulate input for .Ltail_avx2 + vpand $MASK,$T1,$T1 # 1 + vpaddq $D0,$H1,$H1 # h0 -> h1 + + vpsrlq \$26,$H3,$D3 + vpand $MASK,$H3,$H3 + vpand $MASK,$T3,$T3 # 3 + vpor 32(%rcx),$T4,$T4 # padbit, yes, always + vpaddq $D3,$H4,$H4 # h3 -> h4 + + lea 0x90(%rsp),%rax # size optimization for .Ltail_avx2 + add \$64,$len + jnz .Ltail_avx2$suffix + + vpsubq $T2,$H2,$H2 # undo input accumulation + vmovd %x#$H0,`4*0-48-64`($ctx)# save partially reduced + vmovd %x#$H1,`4*1-48-64`($ctx) + vmovd %x#$H2,`4*2-48-64`($ctx) + vmovd %x#$H3,`4*3-48-64`($ctx) + vmovd %x#$H4,`4*4-48-64`($ctx) + vzeroall +___ +$code.=<<___ if ($win64); + movdqa -0xb0(%r10),%xmm6 + movdqa -0xa0(%r10),%xmm7 + movdqa -0x90(%r10),%xmm8 + movdqa -0x80(%r10),%xmm9 + movdqa -0x70(%r10),%xmm10 + movdqa -0x60(%r10),%xmm11 + movdqa -0x50(%r10),%xmm12 + movdqa -0x40(%r10),%xmm13 + movdqa -0x30(%r10),%xmm14 + movdqa -0x20(%r10),%xmm15 + lea -8(%r10),%rsp +.Ldo_avx512_epilogue: +___ +$code.=<<___ if (!$win64); + lea -8(%r10),%rsp +.cfi_def_cfa_register %rsp +___ +$code.=<<___; + ret +.cfi_endproc +___ + +} + +} + +&declare_function("poly1305_blocks_avx2", 32, 4); +poly1305_blocks_avxN(0); +&end_function("poly1305_blocks_avx2"); + +if($kernel) { + $code .= "#endif\n"; +} + +####################################################################### +if ($avx>2) { +# On entry we have input length divisible by 64. But since inner loop +# processes 128 bytes per iteration, cases when length is not divisible +# by 128 are handled by passing tail 64 bytes to .Ltail_avx2. For this +# reason stack layout is kept identical to poly1305_blocks_avx2. If not +# for this tail, we wouldn't have to even allocate stack frame... + +if($kernel) { + $code .= "#ifdef CONFIG_AS_AVX512\n"; +} + +&declare_function("poly1305_blocks_avx512", 32, 4); +poly1305_blocks_avxN(1); +&end_function("poly1305_blocks_avx512"); + +if ($kernel) { + $code .= "#endif\n"; +} + +if (!$kernel && $avx>3) { +######################################################################## +# VPMADD52 version using 2^44 radix. +# +# One can argue that base 2^52 would be more natural. Well, even though +# some operations would be more natural, one has to recognize couple of +# things. Base 2^52 doesn't provide advantage over base 2^44 if you look +# at amount of multiply-n-accumulate operations. Secondly, it makes it +# impossible to pre-compute multiples of 5 [referred to as s[]/sN in +# reference implementations], which means that more such operations +# would have to be performed in inner loop, which in turn makes critical +# path longer. In other words, even though base 2^44 reduction might +# look less elegant, overall critical path is actually shorter... + +######################################################################## +# Layout of opaque area is following. +# +# unsigned __int64 h[3]; # current hash value base 2^44 +# unsigned __int64 s[2]; # key value*20 base 2^44 +# unsigned __int64 r[3]; # key value base 2^44 +# struct { unsigned __int64 r^1, r^3, r^2, r^4; } R[4]; +# # r^n positions reflect +# # placement in register, not +# # memory, R[3] is R[1]*20 + +$code.=<<___; +.type poly1305_init_base2_44,\@function,3 +.align 32 +poly1305_init_base2_44: + xor %rax,%rax + mov %rax,0($ctx) # initialize hash value + mov %rax,8($ctx) + mov %rax,16($ctx) + +.Linit_base2_44: + lea poly1305_blocks_vpmadd52(%rip),%r10 + lea poly1305_emit_base2_44(%rip),%r11 + + mov \$0x0ffffffc0fffffff,%rax + mov \$0x0ffffffc0ffffffc,%rcx + and 0($inp),%rax + mov \$0x00000fffffffffff,%r8 + and 8($inp),%rcx + mov \$0x00000fffffffffff,%r9 + and %rax,%r8 + shrd \$44,%rcx,%rax + mov %r8,40($ctx) # r0 + and %r9,%rax + shr \$24,%rcx + mov %rax,48($ctx) # r1 + lea (%rax,%rax,4),%rax # *5 + mov %rcx,56($ctx) # r2 + shl \$2,%rax # magic <<2 + lea (%rcx,%rcx,4),%rcx # *5 + shl \$2,%rcx # magic <<2 + mov %rax,24($ctx) # s1 + mov %rcx,32($ctx) # s2 + movq \$-1,64($ctx) # write impossible value +___ +$code.=<<___ if ($flavour !~ /elf32/); + mov %r10,0(%rdx) + mov %r11,8(%rdx) +___ +$code.=<<___ if ($flavour =~ /elf32/); + mov %r10d,0(%rdx) + mov %r11d,4(%rdx) +___ +$code.=<<___; + mov \$1,%eax + ret +.size poly1305_init_base2_44,.-poly1305_init_base2_44 +___ +{ +my ($H0,$H1,$H2,$r2r1r0,$r1r0s2,$r0s2s1,$Dlo,$Dhi) = map("%ymm$_",(0..5,16,17)); +my ($T0,$inp_permd,$inp_shift,$PAD) = map("%ymm$_",(18..21)); +my ($reduc_mask,$reduc_rght,$reduc_left) = map("%ymm$_",(22..25)); + +$code.=<<___; +.type poly1305_blocks_vpmadd52,\@function,4 +.align 32 +poly1305_blocks_vpmadd52: + shr \$4,$len + jz .Lno_data_vpmadd52 # too short + + shl \$40,$padbit + mov 64($ctx),%r8 # peek on power of the key + + # if powers of the key are not calculated yet, process up to 3 + # blocks with this single-block subroutine, otherwise ensure that + # length is divisible by 2 blocks and pass the rest down to next + # subroutine... + + mov \$3,%rax + mov \$1,%r10 + cmp \$4,$len # is input long + cmovae %r10,%rax + test %r8,%r8 # is power value impossible? + cmovns %r10,%rax + + and $len,%rax # is input of favourable length? + jz .Lblocks_vpmadd52_4x + + sub %rax,$len + mov \$7,%r10d + mov \$1,%r11d + kmovw %r10d,%k7 + lea .L2_44_inp_permd(%rip),%r10 + kmovw %r11d,%k1 + + vmovq $padbit,%x#$PAD + vmovdqa64 0(%r10),$inp_permd # .L2_44_inp_permd + vmovdqa64 32(%r10),$inp_shift # .L2_44_inp_shift + vpermq \$0xcf,$PAD,$PAD + vmovdqa64 64(%r10),$reduc_mask # .L2_44_mask + + vmovdqu64 0($ctx),${Dlo}{%k7}{z} # load hash value + vmovdqu64 40($ctx),${r2r1r0}{%k7}{z} # load keys + vmovdqu64 32($ctx),${r1r0s2}{%k7}{z} + vmovdqu64 24($ctx),${r0s2s1}{%k7}{z} + + vmovdqa64 96(%r10),$reduc_rght # .L2_44_shift_rgt + vmovdqa64 128(%r10),$reduc_left # .L2_44_shift_lft + + jmp .Loop_vpmadd52 + +.align 32 +.Loop_vpmadd52: + vmovdqu32 0($inp),%x#$T0 # load input as ----3210 + lea 16($inp),$inp + + vpermd $T0,$inp_permd,$T0 # ----3210 -> --322110 + vpsrlvq $inp_shift,$T0,$T0 + vpandq $reduc_mask,$T0,$T0 + vporq $PAD,$T0,$T0 + + vpaddq $T0,$Dlo,$Dlo # accumulate input + + vpermq \$0,$Dlo,${H0}{%k7}{z} # smash hash value + vpermq \$0b01010101,$Dlo,${H1}{%k7}{z} + vpermq \$0b10101010,$Dlo,${H2}{%k7}{z} + + vpxord $Dlo,$Dlo,$Dlo + vpxord $Dhi,$Dhi,$Dhi + + vpmadd52luq $r2r1r0,$H0,$Dlo + vpmadd52huq $r2r1r0,$H0,$Dhi + + vpmadd52luq $r1r0s2,$H1,$Dlo + vpmadd52huq $r1r0s2,$H1,$Dhi + + vpmadd52luq $r0s2s1,$H2,$Dlo + vpmadd52huq $r0s2s1,$H2,$Dhi + + vpsrlvq $reduc_rght,$Dlo,$T0 # 0 in topmost qword + vpsllvq $reduc_left,$Dhi,$Dhi # 0 in topmost qword + vpandq $reduc_mask,$Dlo,$Dlo + + vpaddq $T0,$Dhi,$Dhi + + vpermq \$0b10010011,$Dhi,$Dhi # 0 in lowest qword + + vpaddq $Dhi,$Dlo,$Dlo # note topmost qword :-) + + vpsrlvq $reduc_rght,$Dlo,$T0 # 0 in topmost word + vpandq $reduc_mask,$Dlo,$Dlo + + vpermq \$0b10010011,$T0,$T0 + + vpaddq $T0,$Dlo,$Dlo + + vpermq \$0b10010011,$Dlo,${T0}{%k1}{z} + + vpaddq $T0,$Dlo,$Dlo + vpsllq \$2,$T0,$T0 + + vpaddq $T0,$Dlo,$Dlo + + dec %rax # len-=16 + jnz .Loop_vpmadd52 + + vmovdqu64 $Dlo,0($ctx){%k7} # store hash value + + test $len,$len + jnz .Lblocks_vpmadd52_4x + +.Lno_data_vpmadd52: + ret +.size poly1305_blocks_vpmadd52,.-poly1305_blocks_vpmadd52 +___ +} +{ +######################################################################## +# As implied by its name 4x subroutine processes 4 blocks in parallel +# (but handles even 4*n+2 blocks lengths). It takes up to 4th key power +# and is handled in 256-bit %ymm registers. + +my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17)); +my ($D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi) = map("%ymm$_",(18..23)); +my ($T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD) = map("%ymm$_",(24..31)); + +$code.=<<___; +.type poly1305_blocks_vpmadd52_4x,\@function,4 +.align 32 +poly1305_blocks_vpmadd52_4x: + shr \$4,$len + jz .Lno_data_vpmadd52_4x # too short + + shl \$40,$padbit + mov 64($ctx),%r8 # peek on power of the key + +.Lblocks_vpmadd52_4x: + vpbroadcastq $padbit,$PAD + + vmovdqa64 .Lx_mask44(%rip),$mask44 + mov \$5,%eax + vmovdqa64 .Lx_mask42(%rip),$mask42 + kmovw %eax,%k1 # used in 2x path + + test %r8,%r8 # is power value impossible? + js .Linit_vpmadd52 # if it is, then init R[4] + + vmovq 0($ctx),%x#$H0 # load current hash value + vmovq 8($ctx),%x#$H1 + vmovq 16($ctx),%x#$H2 + + test \$3,$len # is length 4*n+2? + jnz .Lblocks_vpmadd52_2x_do + +.Lblocks_vpmadd52_4x_do: + vpbroadcastq 64($ctx),$R0 # load 4th power of the key + vpbroadcastq 96($ctx),$R1 + vpbroadcastq 128($ctx),$R2 + vpbroadcastq 160($ctx),$S1 + +.Lblocks_vpmadd52_4x_key_loaded: + vpsllq \$2,$R2,$S2 # S2 = R2*5*4 + vpaddq $R2,$S2,$S2 + vpsllq \$2,$S2,$S2 + + test \$7,$len # is len 8*n? + jz .Lblocks_vpmadd52_8x + + vmovdqu64 16*0($inp),$T2 # load data + vmovdqu64 16*2($inp),$T3 + lea 16*4($inp),$inp + + vpunpcklqdq $T3,$T2,$T1 # transpose data + vpunpckhqdq $T3,$T2,$T3 + + # at this point 64-bit lanes are ordered as 3-1-2-0 + + vpsrlq \$24,$T3,$T2 # splat the data + vporq $PAD,$T2,$T2 + vpaddq $T2,$H2,$H2 # accumulate input + vpandq $mask44,$T1,$T0 + vpsrlq \$44,$T1,$T1 + vpsllq \$20,$T3,$T3 + vporq $T3,$T1,$T1 + vpandq $mask44,$T1,$T1 + + sub \$4,$len + jz .Ltail_vpmadd52_4x + jmp .Loop_vpmadd52_4x + ud2 + +.align 32 +.Linit_vpmadd52: + vmovq 24($ctx),%x#$S1 # load key + vmovq 56($ctx),%x#$H2 + vmovq 32($ctx),%x#$S2 + vmovq 40($ctx),%x#$R0 + vmovq 48($ctx),%x#$R1 + + vmovdqa $R0,$H0 + vmovdqa $R1,$H1 + vmovdqa $H2,$R2 + + mov \$2,%eax + +.Lmul_init_vpmadd52: + vpxorq $D0lo,$D0lo,$D0lo + vpmadd52luq $H2,$S1,$D0lo + vpxorq $D0hi,$D0hi,$D0hi + vpmadd52huq $H2,$S1,$D0hi + vpxorq $D1lo,$D1lo,$D1lo + vpmadd52luq $H2,$S2,$D1lo + vpxorq $D1hi,$D1hi,$D1hi + vpmadd52huq $H2,$S2,$D1hi + vpxorq $D2lo,$D2lo,$D2lo + vpmadd52luq $H2,$R0,$D2lo + vpxorq $D2hi,$D2hi,$D2hi + vpmadd52huq $H2,$R0,$D2hi + + vpmadd52luq $H0,$R0,$D0lo + vpmadd52huq $H0,$R0,$D0hi + vpmadd52luq $H0,$R1,$D1lo + vpmadd52huq $H0,$R1,$D1hi + vpmadd52luq $H0,$R2,$D2lo + vpmadd52huq $H0,$R2,$D2hi + + vpmadd52luq $H1,$S2,$D0lo + vpmadd52huq $H1,$S2,$D0hi + vpmadd52luq $H1,$R0,$D1lo + vpmadd52huq $H1,$R0,$D1hi + vpmadd52luq $H1,$R1,$D2lo + vpmadd52huq $H1,$R1,$D2hi + + ################################################################ + # partial reduction + vpsrlq \$44,$D0lo,$tmp + vpsllq \$8,$D0hi,$D0hi + vpandq $mask44,$D0lo,$H0 + vpaddq $tmp,$D0hi,$D0hi + + vpaddq $D0hi,$D1lo,$D1lo + + vpsrlq \$44,$D1lo,$tmp + vpsllq \$8,$D1hi,$D1hi + vpandq $mask44,$D1lo,$H1 + vpaddq $tmp,$D1hi,$D1hi + + vpaddq $D1hi,$D2lo,$D2lo + + vpsrlq \$42,$D2lo,$tmp + vpsllq \$10,$D2hi,$D2hi + vpandq $mask42,$D2lo,$H2 + vpaddq $tmp,$D2hi,$D2hi + + vpaddq $D2hi,$H0,$H0 + vpsllq \$2,$D2hi,$D2hi + + vpaddq $D2hi,$H0,$H0 + + vpsrlq \$44,$H0,$tmp # additional step + vpandq $mask44,$H0,$H0 + + vpaddq $tmp,$H1,$H1 + + dec %eax + jz .Ldone_init_vpmadd52 + + vpunpcklqdq $R1,$H1,$R1 # 1,2 + vpbroadcastq %x#$H1,%x#$H1 # 2,2 + vpunpcklqdq $R2,$H2,$R2 + vpbroadcastq %x#$H2,%x#$H2 + vpunpcklqdq $R0,$H0,$R0 + vpbroadcastq %x#$H0,%x#$H0 + + vpsllq \$2,$R1,$S1 # S1 = R1*5*4 + vpsllq \$2,$R2,$S2 # S2 = R2*5*4 + vpaddq $R1,$S1,$S1 + vpaddq $R2,$S2,$S2 + vpsllq \$2,$S1,$S1 + vpsllq \$2,$S2,$S2 + + jmp .Lmul_init_vpmadd52 + ud2 + +.align 32 +.Ldone_init_vpmadd52: + vinserti128 \$1,%x#$R1,$H1,$R1 # 1,2,3,4 + vinserti128 \$1,%x#$R2,$H2,$R2 + vinserti128 \$1,%x#$R0,$H0,$R0 + + vpermq \$0b11011000,$R1,$R1 # 1,3,2,4 + vpermq \$0b11011000,$R2,$R2 + vpermq \$0b11011000,$R0,$R0 + + vpsllq \$2,$R1,$S1 # S1 = R1*5*4 + vpaddq $R1,$S1,$S1 + vpsllq \$2,$S1,$S1 + + vmovq 0($ctx),%x#$H0 # load current hash value + vmovq 8($ctx),%x#$H1 + vmovq 16($ctx),%x#$H2 + + test \$3,$len # is length 4*n+2? + jnz .Ldone_init_vpmadd52_2x + + vmovdqu64 $R0,64($ctx) # save key powers + vpbroadcastq %x#$R0,$R0 # broadcast 4th power + vmovdqu64 $R1,96($ctx) + vpbroadcastq %x#$R1,$R1 + vmovdqu64 $R2,128($ctx) + vpbroadcastq %x#$R2,$R2 + vmovdqu64 $S1,160($ctx) + vpbroadcastq %x#$S1,$S1 + + jmp .Lblocks_vpmadd52_4x_key_loaded + ud2 + +.align 32 +.Ldone_init_vpmadd52_2x: + vmovdqu64 $R0,64($ctx) # save key powers + vpsrldq \$8,$R0,$R0 # 0-1-0-2 + vmovdqu64 $R1,96($ctx) + vpsrldq \$8,$R1,$R1 + vmovdqu64 $R2,128($ctx) + vpsrldq \$8,$R2,$R2 + vmovdqu64 $S1,160($ctx) + vpsrldq \$8,$S1,$S1 + jmp .Lblocks_vpmadd52_2x_key_loaded + ud2 + +.align 32 +.Lblocks_vpmadd52_2x_do: + vmovdqu64 128+8($ctx),${R2}{%k1}{z}# load 2nd and 1st key powers + vmovdqu64 160+8($ctx),${S1}{%k1}{z} + vmovdqu64 64+8($ctx),${R0}{%k1}{z} + vmovdqu64 96+8($ctx),${R1}{%k1}{z} + +.Lblocks_vpmadd52_2x_key_loaded: + vmovdqu64 16*0($inp),$T2 # load data + vpxorq $T3,$T3,$T3 + lea 16*2($inp),$inp + + vpunpcklqdq $T3,$T2,$T1 # transpose data + vpunpckhqdq $T3,$T2,$T3 + + # at this point 64-bit lanes are ordered as x-1-x-0 + + vpsrlq \$24,$T3,$T2 # splat the data + vporq $PAD,$T2,$T2 + vpaddq $T2,$H2,$H2 # accumulate input + vpandq $mask44,$T1,$T0 + vpsrlq \$44,$T1,$T1 + vpsllq \$20,$T3,$T3 + vporq $T3,$T1,$T1 + vpandq $mask44,$T1,$T1 + + jmp .Ltail_vpmadd52_2x + ud2 + +.align 32 +.Loop_vpmadd52_4x: + #vpaddq $T2,$H2,$H2 # accumulate input + vpaddq $T0,$H0,$H0 + vpaddq $T1,$H1,$H1 + + vpxorq $D0lo,$D0lo,$D0lo + vpmadd52luq $H2,$S1,$D0lo + vpxorq $D0hi,$D0hi,$D0hi + vpmadd52huq $H2,$S1,$D0hi + vpxorq $D1lo,$D1lo,$D1lo + vpmadd52luq $H2,$S2,$D1lo + vpxorq $D1hi,$D1hi,$D1hi + vpmadd52huq $H2,$S2,$D1hi + vpxorq $D2lo,$D2lo,$D2lo + vpmadd52luq $H2,$R0,$D2lo + vpxorq $D2hi,$D2hi,$D2hi + vpmadd52huq $H2,$R0,$D2hi + + vmovdqu64 16*0($inp),$T2 # load data + vmovdqu64 16*2($inp),$T3 + lea 16*4($inp),$inp + vpmadd52luq $H0,$R0,$D0lo + vpmadd52huq $H0,$R0,$D0hi + vpmadd52luq $H0,$R1,$D1lo + vpmadd52huq $H0,$R1,$D1hi + vpmadd52luq $H0,$R2,$D2lo + vpmadd52huq $H0,$R2,$D2hi + + vpunpcklqdq $T3,$T2,$T1 # transpose data + vpunpckhqdq $T3,$T2,$T3 + vpmadd52luq $H1,$S2,$D0lo + vpmadd52huq $H1,$S2,$D0hi + vpmadd52luq $H1,$R0,$D1lo + vpmadd52huq $H1,$R0,$D1hi + vpmadd52luq $H1,$R1,$D2lo + vpmadd52huq $H1,$R1,$D2hi + + ################################################################ + # partial reduction (interleaved with data splat) + vpsrlq \$44,$D0lo,$tmp + vpsllq \$8,$D0hi,$D0hi + vpandq $mask44,$D0lo,$H0 + vpaddq $tmp,$D0hi,$D0hi + + vpsrlq \$24,$T3,$T2 + vporq $PAD,$T2,$T2 + vpaddq $D0hi,$D1lo,$D1lo + + vpsrlq \$44,$D1lo,$tmp + vpsllq \$8,$D1hi,$D1hi + vpandq $mask44,$D1lo,$H1 + vpaddq $tmp,$D1hi,$D1hi + + vpandq $mask44,$T1,$T0 + vpsrlq \$44,$T1,$T1 + vpsllq \$20,$T3,$T3 + vpaddq $D1hi,$D2lo,$D2lo + + vpsrlq \$42,$D2lo,$tmp + vpsllq \$10,$D2hi,$D2hi + vpandq $mask42,$D2lo,$H2 + vpaddq $tmp,$D2hi,$D2hi + + vpaddq $T2,$H2,$H2 # accumulate input + vpaddq $D2hi,$H0,$H0 + vpsllq \$2,$D2hi,$D2hi + + vpaddq $D2hi,$H0,$H0 + vporq $T3,$T1,$T1 + vpandq $mask44,$T1,$T1 + + vpsrlq \$44,$H0,$tmp # additional step + vpandq $mask44,$H0,$H0 + + vpaddq $tmp,$H1,$H1 + + sub \$4,$len # len-=64 + jnz .Loop_vpmadd52_4x + +.Ltail_vpmadd52_4x: + vmovdqu64 128($ctx),$R2 # load all key powers + vmovdqu64 160($ctx),$S1 + vmovdqu64 64($ctx),$R0 + vmovdqu64 96($ctx),$R1 + +.Ltail_vpmadd52_2x: + vpsllq \$2,$R2,$S2 # S2 = R2*5*4 + vpaddq $R2,$S2,$S2 + vpsllq \$2,$S2,$S2 + + #vpaddq $T2,$H2,$H2 # accumulate input + vpaddq $T0,$H0,$H0 + vpaddq $T1,$H1,$H1 + + vpxorq $D0lo,$D0lo,$D0lo + vpmadd52luq $H2,$S1,$D0lo + vpxorq $D0hi,$D0hi,$D0hi + vpmadd52huq $H2,$S1,$D0hi + vpxorq $D1lo,$D1lo,$D1lo + vpmadd52luq $H2,$S2,$D1lo + vpxorq $D1hi,$D1hi,$D1hi + vpmadd52huq $H2,$S2,$D1hi + vpxorq $D2lo,$D2lo,$D2lo + vpmadd52luq $H2,$R0,$D2lo + vpxorq $D2hi,$D2hi,$D2hi + vpmadd52huq $H2,$R0,$D2hi + + vpmadd52luq $H0,$R0,$D0lo + vpmadd52huq $H0,$R0,$D0hi + vpmadd52luq $H0,$R1,$D1lo + vpmadd52huq $H0,$R1,$D1hi + vpmadd52luq $H0,$R2,$D2lo + vpmadd52huq $H0,$R2,$D2hi + + vpmadd52luq $H1,$S2,$D0lo + vpmadd52huq $H1,$S2,$D0hi + vpmadd52luq $H1,$R0,$D1lo + vpmadd52huq $H1,$R0,$D1hi + vpmadd52luq $H1,$R1,$D2lo + vpmadd52huq $H1,$R1,$D2hi + + ################################################################ + # horizontal addition + + mov \$1,%eax + kmovw %eax,%k1 + vpsrldq \$8,$D0lo,$T0 + vpsrldq \$8,$D0hi,$H0 + vpsrldq \$8,$D1lo,$T1 + vpsrldq \$8,$D1hi,$H1 + vpaddq $T0,$D0lo,$D0lo + vpaddq $H0,$D0hi,$D0hi + vpsrldq \$8,$D2lo,$T2 + vpsrldq \$8,$D2hi,$H2 + vpaddq $T1,$D1lo,$D1lo + vpaddq $H1,$D1hi,$D1hi + vpermq \$0x2,$D0lo,$T0 + vpermq \$0x2,$D0hi,$H0 + vpaddq $T2,$D2lo,$D2lo + vpaddq $H2,$D2hi,$D2hi + + vpermq \$0x2,$D1lo,$T1 + vpermq \$0x2,$D1hi,$H1 + vpaddq $T0,$D0lo,${D0lo}{%k1}{z} + vpaddq $H0,$D0hi,${D0hi}{%k1}{z} + vpermq \$0x2,$D2lo,$T2 + vpermq \$0x2,$D2hi,$H2 + vpaddq $T1,$D1lo,${D1lo}{%k1}{z} + vpaddq $H1,$D1hi,${D1hi}{%k1}{z} + vpaddq $T2,$D2lo,${D2lo}{%k1}{z} + vpaddq $H2,$D2hi,${D2hi}{%k1}{z} + + ################################################################ + # partial reduction + vpsrlq \$44,$D0lo,$tmp + vpsllq \$8,$D0hi,$D0hi + vpandq $mask44,$D0lo,$H0 + vpaddq $tmp,$D0hi,$D0hi + + vpaddq $D0hi,$D1lo,$D1lo + + vpsrlq \$44,$D1lo,$tmp + vpsllq \$8,$D1hi,$D1hi + vpandq $mask44,$D1lo,$H1 + vpaddq $tmp,$D1hi,$D1hi + + vpaddq $D1hi,$D2lo,$D2lo + + vpsrlq \$42,$D2lo,$tmp + vpsllq \$10,$D2hi,$D2hi + vpandq $mask42,$D2lo,$H2 + vpaddq $tmp,$D2hi,$D2hi + + vpaddq $D2hi,$H0,$H0 + vpsllq \$2,$D2hi,$D2hi + + vpaddq $D2hi,$H0,$H0 + + vpsrlq \$44,$H0,$tmp # additional step + vpandq $mask44,$H0,$H0 + + vpaddq $tmp,$H1,$H1 + # at this point $len is + # either 4*n+2 or 0... + sub \$2,$len # len-=32 + ja .Lblocks_vpmadd52_4x_do + + vmovq %x#$H0,0($ctx) + vmovq %x#$H1,8($ctx) + vmovq %x#$H2,16($ctx) + vzeroall + +.Lno_data_vpmadd52_4x: + ret +.size poly1305_blocks_vpmadd52_4x,.-poly1305_blocks_vpmadd52_4x +___ +} +{ +######################################################################## +# As implied by its name 8x subroutine processes 8 blocks in parallel... +# This is intermediate version, as it's used only in cases when input +# length is either 8*n, 8*n+1 or 8*n+2... + +my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17)); +my ($D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi) = map("%ymm$_",(18..23)); +my ($T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD) = map("%ymm$_",(24..31)); +my ($RR0,$RR1,$RR2,$SS1,$SS2) = map("%ymm$_",(6..10)); + +$code.=<<___; +.type poly1305_blocks_vpmadd52_8x,\@function,4 +.align 32 +poly1305_blocks_vpmadd52_8x: + shr \$4,$len + jz .Lno_data_vpmadd52_8x # too short + + shl \$40,$padbit + mov 64($ctx),%r8 # peek on power of the key + + vmovdqa64 .Lx_mask44(%rip),$mask44 + vmovdqa64 .Lx_mask42(%rip),$mask42 + + test %r8,%r8 # is power value impossible? + js .Linit_vpmadd52 # if it is, then init R[4] + + vmovq 0($ctx),%x#$H0 # load current hash value + vmovq 8($ctx),%x#$H1 + vmovq 16($ctx),%x#$H2 + +.Lblocks_vpmadd52_8x: + ################################################################ + # fist we calculate more key powers + + vmovdqu64 128($ctx),$R2 # load 1-3-2-4 powers + vmovdqu64 160($ctx),$S1 + vmovdqu64 64($ctx),$R0 + vmovdqu64 96($ctx),$R1 + + vpsllq \$2,$R2,$S2 # S2 = R2*5*4 + vpaddq $R2,$S2,$S2 + vpsllq \$2,$S2,$S2 + + vpbroadcastq %x#$R2,$RR2 # broadcast 4th power + vpbroadcastq %x#$R0,$RR0 + vpbroadcastq %x#$R1,$RR1 + + vpxorq $D0lo,$D0lo,$D0lo + vpmadd52luq $RR2,$S1,$D0lo + vpxorq $D0hi,$D0hi,$D0hi + vpmadd52huq $RR2,$S1,$D0hi + vpxorq $D1lo,$D1lo,$D1lo + vpmadd52luq $RR2,$S2,$D1lo + vpxorq $D1hi,$D1hi,$D1hi + vpmadd52huq $RR2,$S2,$D1hi + vpxorq $D2lo,$D2lo,$D2lo + vpmadd52luq $RR2,$R0,$D2lo + vpxorq $D2hi,$D2hi,$D2hi + vpmadd52huq $RR2,$R0,$D2hi + + vpmadd52luq $RR0,$R0,$D0lo + vpmadd52huq $RR0,$R0,$D0hi + vpmadd52luq $RR0,$R1,$D1lo + vpmadd52huq $RR0,$R1,$D1hi + vpmadd52luq $RR0,$R2,$D2lo + vpmadd52huq $RR0,$R2,$D2hi + + vpmadd52luq $RR1,$S2,$D0lo + vpmadd52huq $RR1,$S2,$D0hi + vpmadd52luq $RR1,$R0,$D1lo + vpmadd52huq $RR1,$R0,$D1hi + vpmadd52luq $RR1,$R1,$D2lo + vpmadd52huq $RR1,$R1,$D2hi + + ################################################################ + # partial reduction + vpsrlq \$44,$D0lo,$tmp + vpsllq \$8,$D0hi,$D0hi + vpandq $mask44,$D0lo,$RR0 + vpaddq $tmp,$D0hi,$D0hi + + vpaddq $D0hi,$D1lo,$D1lo + + vpsrlq \$44,$D1lo,$tmp + vpsllq \$8,$D1hi,$D1hi + vpandq $mask44,$D1lo,$RR1 + vpaddq $tmp,$D1hi,$D1hi + + vpaddq $D1hi,$D2lo,$D2lo + + vpsrlq \$42,$D2lo,$tmp + vpsllq \$10,$D2hi,$D2hi + vpandq $mask42,$D2lo,$RR2 + vpaddq $tmp,$D2hi,$D2hi + + vpaddq $D2hi,$RR0,$RR0 + vpsllq \$2,$D2hi,$D2hi + + vpaddq $D2hi,$RR0,$RR0 + + vpsrlq \$44,$RR0,$tmp # additional step + vpandq $mask44,$RR0,$RR0 + + vpaddq $tmp,$RR1,$RR1 + + ################################################################ + # At this point Rx holds 1324 powers, RRx - 5768, and the goal + # is 15263748, which reflects how data is loaded... + + vpunpcklqdq $R2,$RR2,$T2 # 3748 + vpunpckhqdq $R2,$RR2,$R2 # 1526 + vpunpcklqdq $R0,$RR0,$T0 + vpunpckhqdq $R0,$RR0,$R0 + vpunpcklqdq $R1,$RR1,$T1 + vpunpckhqdq $R1,$RR1,$R1 +___ +######## switch to %zmm +map(s/%y/%z/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2); +map(s/%y/%z/, $D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi); +map(s/%y/%z/, $T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD); +map(s/%y/%z/, $RR0,$RR1,$RR2,$SS1,$SS2); + +$code.=<<___; + vshufi64x2 \$0x44,$R2,$T2,$RR2 # 15263748 + vshufi64x2 \$0x44,$R0,$T0,$RR0 + vshufi64x2 \$0x44,$R1,$T1,$RR1 + + vmovdqu64 16*0($inp),$T2 # load data + vmovdqu64 16*4($inp),$T3 + lea 16*8($inp),$inp + + vpsllq \$2,$RR2,$SS2 # S2 = R2*5*4 + vpsllq \$2,$RR1,$SS1 # S1 = R1*5*4 + vpaddq $RR2,$SS2,$SS2 + vpaddq $RR1,$SS1,$SS1 + vpsllq \$2,$SS2,$SS2 + vpsllq \$2,$SS1,$SS1 + + vpbroadcastq $padbit,$PAD + vpbroadcastq %x#$mask44,$mask44 + vpbroadcastq %x#$mask42,$mask42 + + vpbroadcastq %x#$SS1,$S1 # broadcast 8th power + vpbroadcastq %x#$SS2,$S2 + vpbroadcastq %x#$RR0,$R0 + vpbroadcastq %x#$RR1,$R1 + vpbroadcastq %x#$RR2,$R2 + + vpunpcklqdq $T3,$T2,$T1 # transpose data + vpunpckhqdq $T3,$T2,$T3 + + # at this point 64-bit lanes are ordered as 73625140 + + vpsrlq \$24,$T3,$T2 # splat the data + vporq $PAD,$T2,$T2 + vpaddq $T2,$H2,$H2 # accumulate input + vpandq $mask44,$T1,$T0 + vpsrlq \$44,$T1,$T1 + vpsllq \$20,$T3,$T3 + vporq $T3,$T1,$T1 + vpandq $mask44,$T1,$T1 + + sub \$8,$len + jz .Ltail_vpmadd52_8x + jmp .Loop_vpmadd52_8x + +.align 32 +.Loop_vpmadd52_8x: + #vpaddq $T2,$H2,$H2 # accumulate input + vpaddq $T0,$H0,$H0 + vpaddq $T1,$H1,$H1 + + vpxorq $D0lo,$D0lo,$D0lo + vpmadd52luq $H2,$S1,$D0lo + vpxorq $D0hi,$D0hi,$D0hi + vpmadd52huq $H2,$S1,$D0hi + vpxorq $D1lo,$D1lo,$D1lo + vpmadd52luq $H2,$S2,$D1lo + vpxorq $D1hi,$D1hi,$D1hi + vpmadd52huq $H2,$S2,$D1hi + vpxorq $D2lo,$D2lo,$D2lo + vpmadd52luq $H2,$R0,$D2lo + vpxorq $D2hi,$D2hi,$D2hi + vpmadd52huq $H2,$R0,$D2hi + + vmovdqu64 16*0($inp),$T2 # load data + vmovdqu64 16*4($inp),$T3 + lea 16*8($inp),$inp + vpmadd52luq $H0,$R0,$D0lo + vpmadd52huq $H0,$R0,$D0hi + vpmadd52luq $H0,$R1,$D1lo + vpmadd52huq $H0,$R1,$D1hi + vpmadd52luq $H0,$R2,$D2lo + vpmadd52huq $H0,$R2,$D2hi + + vpunpcklqdq $T3,$T2,$T1 # transpose data + vpunpckhqdq $T3,$T2,$T3 + vpmadd52luq $H1,$S2,$D0lo + vpmadd52huq $H1,$S2,$D0hi + vpmadd52luq $H1,$R0,$D1lo + vpmadd52huq $H1,$R0,$D1hi + vpmadd52luq $H1,$R1,$D2lo + vpmadd52huq $H1,$R1,$D2hi + + ################################################################ + # partial reduction (interleaved with data splat) + vpsrlq \$44,$D0lo,$tmp + vpsllq \$8,$D0hi,$D0hi + vpandq $mask44,$D0lo,$H0 + vpaddq $tmp,$D0hi,$D0hi + + vpsrlq \$24,$T3,$T2 + vporq $PAD,$T2,$T2 + vpaddq $D0hi,$D1lo,$D1lo + + vpsrlq \$44,$D1lo,$tmp + vpsllq \$8,$D1hi,$D1hi + vpandq $mask44,$D1lo,$H1 + vpaddq $tmp,$D1hi,$D1hi + + vpandq $mask44,$T1,$T0 + vpsrlq \$44,$T1,$T1 + vpsllq \$20,$T3,$T3 + vpaddq $D1hi,$D2lo,$D2lo + + vpsrlq \$42,$D2lo,$tmp + vpsllq \$10,$D2hi,$D2hi + vpandq $mask42,$D2lo,$H2 + vpaddq $tmp,$D2hi,$D2hi + + vpaddq $T2,$H2,$H2 # accumulate input + vpaddq $D2hi,$H0,$H0 + vpsllq \$2,$D2hi,$D2hi + + vpaddq $D2hi,$H0,$H0 + vporq $T3,$T1,$T1 + vpandq $mask44,$T1,$T1 + + vpsrlq \$44,$H0,$tmp # additional step + vpandq $mask44,$H0,$H0 + + vpaddq $tmp,$H1,$H1 + + sub \$8,$len # len-=128 + jnz .Loop_vpmadd52_8x + +.Ltail_vpmadd52_8x: + #vpaddq $T2,$H2,$H2 # accumulate input + vpaddq $T0,$H0,$H0 + vpaddq $T1,$H1,$H1 + + vpxorq $D0lo,$D0lo,$D0lo + vpmadd52luq $H2,$SS1,$D0lo + vpxorq $D0hi,$D0hi,$D0hi + vpmadd52huq $H2,$SS1,$D0hi + vpxorq $D1lo,$D1lo,$D1lo + vpmadd52luq $H2,$SS2,$D1lo + vpxorq $D1hi,$D1hi,$D1hi + vpmadd52huq $H2,$SS2,$D1hi + vpxorq $D2lo,$D2lo,$D2lo + vpmadd52luq $H2,$RR0,$D2lo + vpxorq $D2hi,$D2hi,$D2hi + vpmadd52huq $H2,$RR0,$D2hi + + vpmadd52luq $H0,$RR0,$D0lo + vpmadd52huq $H0,$RR0,$D0hi + vpmadd52luq $H0,$RR1,$D1lo + vpmadd52huq $H0,$RR1,$D1hi + vpmadd52luq $H0,$RR2,$D2lo + vpmadd52huq $H0,$RR2,$D2hi + + vpmadd52luq $H1,$SS2,$D0lo + vpmadd52huq $H1,$SS2,$D0hi + vpmadd52luq $H1,$RR0,$D1lo + vpmadd52huq $H1,$RR0,$D1hi + vpmadd52luq $H1,$RR1,$D2lo + vpmadd52huq $H1,$RR1,$D2hi + + ################################################################ + # horizontal addition + + mov \$1,%eax + kmovw %eax,%k1 + vpsrldq \$8,$D0lo,$T0 + vpsrldq \$8,$D0hi,$H0 + vpsrldq \$8,$D1lo,$T1 + vpsrldq \$8,$D1hi,$H1 + vpaddq $T0,$D0lo,$D0lo + vpaddq $H0,$D0hi,$D0hi + vpsrldq \$8,$D2lo,$T2 + vpsrldq \$8,$D2hi,$H2 + vpaddq $T1,$D1lo,$D1lo + vpaddq $H1,$D1hi,$D1hi + vpermq \$0x2,$D0lo,$T0 + vpermq \$0x2,$D0hi,$H0 + vpaddq $T2,$D2lo,$D2lo + vpaddq $H2,$D2hi,$D2hi + + vpermq \$0x2,$D1lo,$T1 + vpermq \$0x2,$D1hi,$H1 + vpaddq $T0,$D0lo,$D0lo + vpaddq $H0,$D0hi,$D0hi + vpermq \$0x2,$D2lo,$T2 + vpermq \$0x2,$D2hi,$H2 + vpaddq $T1,$D1lo,$D1lo + vpaddq $H1,$D1hi,$D1hi + vextracti64x4 \$1,$D0lo,%y#$T0 + vextracti64x4 \$1,$D0hi,%y#$H0 + vpaddq $T2,$D2lo,$D2lo + vpaddq $H2,$D2hi,$D2hi + + vextracti64x4 \$1,$D1lo,%y#$T1 + vextracti64x4 \$1,$D1hi,%y#$H1 + vextracti64x4 \$1,$D2lo,%y#$T2 + vextracti64x4 \$1,$D2hi,%y#$H2 +___ +######## switch back to %ymm +map(s/%z/%y/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2); +map(s/%z/%y/, $D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi); +map(s/%z/%y/, $T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD); + +$code.=<<___; + vpaddq $T0,$D0lo,${D0lo}{%k1}{z} + vpaddq $H0,$D0hi,${D0hi}{%k1}{z} + vpaddq $T1,$D1lo,${D1lo}{%k1}{z} + vpaddq $H1,$D1hi,${D1hi}{%k1}{z} + vpaddq $T2,$D2lo,${D2lo}{%k1}{z} + vpaddq $H2,$D2hi,${D2hi}{%k1}{z} + + ################################################################ + # partial reduction + vpsrlq \$44,$D0lo,$tmp + vpsllq \$8,$D0hi,$D0hi + vpandq $mask44,$D0lo,$H0 + vpaddq $tmp,$D0hi,$D0hi + + vpaddq $D0hi,$D1lo,$D1lo + + vpsrlq \$44,$D1lo,$tmp + vpsllq \$8,$D1hi,$D1hi + vpandq $mask44,$D1lo,$H1 + vpaddq $tmp,$D1hi,$D1hi + + vpaddq $D1hi,$D2lo,$D2lo + + vpsrlq \$42,$D2lo,$tmp + vpsllq \$10,$D2hi,$D2hi + vpandq $mask42,$D2lo,$H2 + vpaddq $tmp,$D2hi,$D2hi + + vpaddq $D2hi,$H0,$H0 + vpsllq \$2,$D2hi,$D2hi + + vpaddq $D2hi,$H0,$H0 + + vpsrlq \$44,$H0,$tmp # additional step + vpandq $mask44,$H0,$H0 + + vpaddq $tmp,$H1,$H1 + + ################################################################ + + vmovq %x#$H0,0($ctx) + vmovq %x#$H1,8($ctx) + vmovq %x#$H2,16($ctx) + vzeroall + +.Lno_data_vpmadd52_8x: + ret +.size poly1305_blocks_vpmadd52_8x,.-poly1305_blocks_vpmadd52_8x +___ +} +$code.=<<___; +.type poly1305_emit_base2_44,\@function,3 +.align 32 +poly1305_emit_base2_44: + mov 0($ctx),%r8 # load hash value + mov 8($ctx),%r9 + mov 16($ctx),%r10 + + mov %r9,%rax + shr \$20,%r9 + shl \$44,%rax + mov %r10,%rcx + shr \$40,%r10 + shl \$24,%rcx + + add %rax,%r8 + adc %rcx,%r9 + adc \$0,%r10 + + mov %r8,%rax + add \$5,%r8 # compare to modulus + mov %r9,%rcx + adc \$0,%r9 + adc \$0,%r10 + shr \$2,%r10 # did 130-bit value overflow? + cmovnz %r8,%rax + cmovnz %r9,%rcx + + add 0($nonce),%rax # accumulate nonce + adc 8($nonce),%rcx + mov %rax,0($mac) # write result + mov %rcx,8($mac) + + ret +.size poly1305_emit_base2_44,.-poly1305_emit_base2_44 +___ +} } } +} + +if (!$kernel) +{ # chacha20-poly1305 helpers +my ($out,$inp,$otp,$len)=$win64 ? ("%rcx","%rdx","%r8", "%r9") : # Win64 order + ("%rdi","%rsi","%rdx","%rcx"); # Unix order +$code.=<<___; +.globl xor128_encrypt_n_pad +.type xor128_encrypt_n_pad,\@abi-omnipotent +.align 16 +xor128_encrypt_n_pad: + sub $otp,$inp + sub $otp,$out + mov $len,%r10 # put len aside + shr \$4,$len # len / 16 + jz .Ltail_enc + nop +.Loop_enc_xmm: + movdqu ($inp,$otp),%xmm0 + pxor ($otp),%xmm0 + movdqu %xmm0,($out,$otp) + movdqa %xmm0,($otp) + lea 16($otp),$otp + dec $len + jnz .Loop_enc_xmm + + and \$15,%r10 # len % 16 + jz .Ldone_enc + +.Ltail_enc: + mov \$16,$len + sub %r10,$len + xor %eax,%eax +.Loop_enc_byte: + mov ($inp,$otp),%al + xor ($otp),%al + mov %al,($out,$otp) + mov %al,($otp) + lea 1($otp),$otp + dec %r10 + jnz .Loop_enc_byte + + xor %eax,%eax +.Loop_enc_pad: + mov %al,($otp) + lea 1($otp),$otp + dec $len + jnz .Loop_enc_pad + +.Ldone_enc: + mov $otp,%rax + ret +.size xor128_encrypt_n_pad,.-xor128_encrypt_n_pad + +.globl xor128_decrypt_n_pad +.type xor128_decrypt_n_pad,\@abi-omnipotent +.align 16 +xor128_decrypt_n_pad: + sub $otp,$inp + sub $otp,$out + mov $len,%r10 # put len aside + shr \$4,$len # len / 16 + jz .Ltail_dec + nop +.Loop_dec_xmm: + movdqu ($inp,$otp),%xmm0 + movdqa ($otp),%xmm1 + pxor %xmm0,%xmm1 + movdqu %xmm1,($out,$otp) + movdqa %xmm0,($otp) + lea 16($otp),$otp + dec $len + jnz .Loop_dec_xmm + + pxor %xmm1,%xmm1 + and \$15,%r10 # len % 16 + jz .Ldone_dec + +.Ltail_dec: + mov \$16,$len + sub %r10,$len + xor %eax,%eax + xor %r11,%r11 +.Loop_dec_byte: + mov ($inp,$otp),%r11b + mov ($otp),%al + xor %r11b,%al + mov %al,($out,$otp) + mov %r11b,($otp) + lea 1($otp),$otp + dec %r10 + jnz .Loop_dec_byte + + xor %eax,%eax +.Loop_dec_pad: + mov %al,($otp) + lea 1($otp),$otp + dec $len + jnz .Loop_dec_pad + +.Ldone_dec: + mov $otp,%rax + ret +.size xor128_decrypt_n_pad,.-xor128_decrypt_n_pad +___ +} + +# EXCEPTION_DISPOSITION handler (EXCEPTION_RECORD *rec,ULONG64 frame, +# CONTEXT *context,DISPATCHER_CONTEXT *disp) +if ($win64) { +$rec="%rcx"; +$frame="%rdx"; +$context="%r8"; +$disp="%r9"; + +$code.=<<___; +.extern __imp_RtlVirtualUnwind +.type se_handler,\@abi-omnipotent +.align 16 +se_handler: + push %rsi + push %rdi + push %rbx + push %rbp + push %r12 + push %r13 + push %r14 + push %r15 + pushfq + sub \$64,%rsp + + mov 120($context),%rax # pull context->Rax + mov 248($context),%rbx # pull context->Rip + + mov 8($disp),%rsi # disp->ImageBase + mov 56($disp),%r11 # disp->HandlerData + + mov 0(%r11),%r10d # HandlerData[0] + lea (%rsi,%r10),%r10 # prologue label + cmp %r10,%rbx # context->Rip<.Lprologue + jb .Lcommon_seh_tail + + mov 152($context),%rax # pull context->Rsp + + mov 4(%r11),%r10d # HandlerData[1] + lea (%rsi,%r10),%r10 # epilogue label + cmp %r10,%rbx # context->Rip>=.Lepilogue + jae .Lcommon_seh_tail + + lea 48(%rax),%rax + + mov -8(%rax),%rbx + mov -16(%rax),%rbp + mov -24(%rax),%r12 + mov -32(%rax),%r13 + mov -40(%rax),%r14 + mov -48(%rax),%r15 + mov %rbx,144($context) # restore context->Rbx + mov %rbp,160($context) # restore context->Rbp + mov %r12,216($context) # restore context->R12 + mov %r13,224($context) # restore context->R13 + mov %r14,232($context) # restore context->R14 + mov %r15,240($context) # restore context->R14 + + jmp .Lcommon_seh_tail +.size se_handler,.-se_handler + +.type avx_handler,\@abi-omnipotent +.align 16 +avx_handler: + push %rsi + push %rdi + push %rbx + push %rbp + push %r12 + push %r13 + push %r14 + push %r15 + pushfq + sub \$64,%rsp + + mov 120($context),%rax # pull context->Rax + mov 248($context),%rbx # pull context->Rip + + mov 8($disp),%rsi # disp->ImageBase + mov 56($disp),%r11 # disp->HandlerData + + mov 0(%r11),%r10d # HandlerData[0] + lea (%rsi,%r10),%r10 # prologue label + cmp %r10,%rbx # context->Rip<prologue label + jb .Lcommon_seh_tail + + mov 152($context),%rax # pull context->Rsp + + mov 4(%r11),%r10d # HandlerData[1] + lea (%rsi,%r10),%r10 # epilogue label + cmp %r10,%rbx # context->Rip>=epilogue label + jae .Lcommon_seh_tail + + mov 208($context),%rax # pull context->R11 + + lea 0x50(%rax),%rsi + lea 0xf8(%rax),%rax + lea 512($context),%rdi # &context.Xmm6 + mov \$20,%ecx + .long 0xa548f3fc # cld; rep movsq + +.Lcommon_seh_tail: + mov 8(%rax),%rdi + mov 16(%rax),%rsi + mov %rax,152($context) # restore context->Rsp + mov %rsi,168($context) # restore context->Rsi + mov %rdi,176($context) # restore context->Rdi + + mov 40($disp),%rdi # disp->ContextRecord + mov $context,%rsi # context + mov \$154,%ecx # sizeof(CONTEXT) + .long 0xa548f3fc # cld; rep movsq + + mov $disp,%rsi + xor %rcx,%rcx # arg1, UNW_FLAG_NHANDLER + mov 8(%rsi),%rdx # arg2, disp->ImageBase + mov 0(%rsi),%r8 # arg3, disp->ControlPc + mov 16(%rsi),%r9 # arg4, disp->FunctionEntry + mov 40(%rsi),%r10 # disp->ContextRecord + lea 56(%rsi),%r11 # &disp->HandlerData + lea 24(%rsi),%r12 # &disp->EstablisherFrame + mov %r10,32(%rsp) # arg5 + mov %r11,40(%rsp) # arg6 + mov %r12,48(%rsp) # arg7 + mov %rcx,56(%rsp) # arg8, (NULL) + call *__imp_RtlVirtualUnwind(%rip) + + mov \$1,%eax # ExceptionContinueSearch + add \$64,%rsp + popfq + pop %r15 + pop %r14 + pop %r13 + pop %r12 + pop %rbp + pop %rbx + pop %rdi + pop %rsi + ret +.size avx_handler,.-avx_handler + +.section .pdata +.align 4 + .rva .LSEH_begin_poly1305_init_x86_64 + .rva .LSEH_end_poly1305_init_x86_64 + .rva .LSEH_info_poly1305_init_x86_64 + + .rva .LSEH_begin_poly1305_blocks_x86_64 + .rva .LSEH_end_poly1305_blocks_x86_64 + .rva .LSEH_info_poly1305_blocks_x86_64 + + .rva .LSEH_begin_poly1305_emit_x86_64 + .rva .LSEH_end_poly1305_emit_x86_64 + .rva .LSEH_info_poly1305_emit_x86_64 +___ +$code.=<<___ if ($avx); + .rva .LSEH_begin_poly1305_blocks_avx + .rva .Lbase2_64_avx + .rva .LSEH_info_poly1305_blocks_avx_1 + + .rva .Lbase2_64_avx + .rva .Leven_avx + .rva .LSEH_info_poly1305_blocks_avx_2 + + .rva .Leven_avx + .rva .LSEH_end_poly1305_blocks_avx + .rva .LSEH_info_poly1305_blocks_avx_3 + + .rva .LSEH_begin_poly1305_emit_avx + .rva .LSEH_end_poly1305_emit_avx + .rva .LSEH_info_poly1305_emit_avx +___ +$code.=<<___ if ($avx>1); + .rva .LSEH_begin_poly1305_blocks_avx2 + .rva .Lbase2_64_avx2 + .rva .LSEH_info_poly1305_blocks_avx2_1 + + .rva .Lbase2_64_avx2 + .rva .Leven_avx2 + .rva .LSEH_info_poly1305_blocks_avx2_2 + + .rva .Leven_avx2 + .rva .LSEH_end_poly1305_blocks_avx2 + .rva .LSEH_info_poly1305_blocks_avx2_3 +___ +$code.=<<___ if ($avx>2); + .rva .LSEH_begin_poly1305_blocks_avx512 + .rva .LSEH_end_poly1305_blocks_avx512 + .rva .LSEH_info_poly1305_blocks_avx512 +___ +$code.=<<___; +.section .xdata +.align 8 +.LSEH_info_poly1305_init_x86_64: + .byte 9,0,0,0 + .rva se_handler + .rva .LSEH_begin_poly1305_init_x86_64,.LSEH_begin_poly1305_init_x86_64 + +.LSEH_info_poly1305_blocks_x86_64: + .byte 9,0,0,0 + .rva se_handler + .rva .Lblocks_body,.Lblocks_epilogue + +.LSEH_info_poly1305_emit_x86_64: + .byte 9,0,0,0 + .rva se_handler + .rva .LSEH_begin_poly1305_emit_x86_64,.LSEH_begin_poly1305_emit_x86_64 +___ +$code.=<<___ if ($avx); +.LSEH_info_poly1305_blocks_avx_1: + .byte 9,0,0,0 + .rva se_handler + .rva .Lblocks_avx_body,.Lblocks_avx_epilogue # HandlerData[] + +.LSEH_info_poly1305_blocks_avx_2: + .byte 9,0,0,0 + .rva se_handler + .rva .Lbase2_64_avx_body,.Lbase2_64_avx_epilogue # HandlerData[] + +.LSEH_info_poly1305_blocks_avx_3: + .byte 9,0,0,0 + .rva avx_handler + .rva .Ldo_avx_body,.Ldo_avx_epilogue # HandlerData[] + +.LSEH_info_poly1305_emit_avx: + .byte 9,0,0,0 + .rva se_handler + .rva .LSEH_begin_poly1305_emit_avx,.LSEH_begin_poly1305_emit_avx +___ +$code.=<<___ if ($avx>1); +.LSEH_info_poly1305_blocks_avx2_1: + .byte 9,0,0,0 + .rva se_handler + .rva .Lblocks_avx2_body,.Lblocks_avx2_epilogue # HandlerData[] + +.LSEH_info_poly1305_blocks_avx2_2: + .byte 9,0,0,0 + .rva se_handler + .rva .Lbase2_64_avx2_body,.Lbase2_64_avx2_epilogue # HandlerData[] + +.LSEH_info_poly1305_blocks_avx2_3: + .byte 9,0,0,0 + .rva avx_handler + .rva .Ldo_avx2_body,.Ldo_avx2_epilogue # HandlerData[] +___ +$code.=<<___ if ($avx>2); +.LSEH_info_poly1305_blocks_avx512: + .byte 9,0,0,0 + .rva avx_handler + .rva .Ldo_avx512_body,.Ldo_avx512_epilogue # HandlerData[] +___ +} + +open SELF,$0; +while(<SELF>) { + next if (/^#!/); + last if (!s/^#/\/\// and !/^$/); + print; +} +close SELF; + +foreach (split('\n',$code)) { + s/\`([^\`]*)\`/eval($1)/ge; + s/%r([a-z]+)#d/%e$1/g; + s/%r([0-9]+)#d/%r$1d/g; + s/%x#%[yz]/%x/g or s/%y#%z/%y/g or s/%z#%[yz]/%z/g; + + if ($kernel) { + s/(^\.type.*),[0-9]+$/\1/; + s/(^\.type.*),\@abi-omnipotent+$/\1,\@function/; + next if /^\.cfi.*/; + } + + print $_,"\n"; +} +close STDOUT; diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 4a1c05dce950..79bb58737d52 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -1,131 +1,176 @@ -// SPDX-License-Identifier: GPL-2.0-or-later +// SPDX-License-Identifier: GPL-2.0 OR MIT /* - * Poly1305 authenticator algorithm, RFC7539, SIMD glue code - * - * Copyright (C) 2015 Martin Willi + * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include <crypto/algapi.h> #include <crypto/internal/hash.h> +#include <crypto/internal/poly1305.h> #include <crypto/internal/simd.h> -#include <crypto/poly1305.h> #include <linux/crypto.h> +#include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/module.h> +#include <asm/intel-family.h> #include <asm/simd.h> -struct poly1305_simd_desc_ctx { - struct poly1305_desc_ctx base; - /* derived key u set? */ - bool uset; -#ifdef CONFIG_AS_AVX2 - /* derived keys r^3, r^4 set? */ - bool wset; -#endif - /* derived Poly1305 key r^2 */ - u32 u[5]; - /* ... silently appended r^3 and r^4 when using AVX2 */ +asmlinkage void poly1305_init_x86_64(void *ctx, + const u8 key[POLY1305_KEY_SIZE]); +asmlinkage void poly1305_blocks_x86_64(void *ctx, const u8 *inp, + const size_t len, const u32 padbit); +asmlinkage void poly1305_emit_x86_64(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], + const u32 nonce[4]); +asmlinkage void poly1305_emit_avx(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], + const u32 nonce[4]); +asmlinkage void poly1305_blocks_avx(void *ctx, const u8 *inp, const size_t len, + const u32 padbit); +asmlinkage void poly1305_blocks_avx2(void *ctx, const u8 *inp, const size_t len, + const u32 padbit); +asmlinkage void poly1305_blocks_avx512(void *ctx, const u8 *inp, + const size_t len, const u32 padbit); + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx); +static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2); +static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx512); + +struct poly1305_arch_internal { + union { + struct { + u32 h[5]; + u32 is_base2_26; + }; + u64 hs[3]; + }; + u64 r[2]; + u64 pad; + struct { u32 r2, r1, r4, r3; } rn[9]; }; -asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src, - const u32 *r, unsigned int blocks); -asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r, - unsigned int blocks, const u32 *u); -#ifdef CONFIG_AS_AVX2 -asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r, - unsigned int blocks, const u32 *u); -static bool poly1305_use_avx2; -#endif - -static int poly1305_simd_init(struct shash_desc *desc) +/* The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit + * the unfortunate situation of using AVX and then having to go back to scalar + * -- because the user is silly and has called the update function from two + * separate contexts -- then we need to convert back to the original base before + * proceeding. It is possible to reason that the initial reduction below is + * sufficient given the implementation invariants. However, for an avoidance of + * doubt and because this is not performance critical, we do the full reduction + * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py + */ +static void convert_to_base2_64(void *ctx) { - struct poly1305_simd_desc_ctx *sctx = shash_desc_ctx(desc); + struct poly1305_arch_internal *state = ctx; + u32 cy; - sctx->uset = false; -#ifdef CONFIG_AS_AVX2 - sctx->wset = false; -#endif + if (!state->is_base2_26) + return; - return crypto_poly1305_init(desc); + cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy; + cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy; + cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy; + cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy; + state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0]; + state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12); + state->hs[2] = state->h[4] >> 24; +#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1)) + cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL); + state->hs[2] &= 3; + state->hs[0] += cy; + state->hs[1] += (cy = ULT(state->hs[0], cy)); + state->hs[2] += ULT(state->hs[1], cy); +#undef ULT + state->is_base2_26 = 0; } -static void poly1305_simd_mult(u32 *a, const u32 *b) +static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_KEY_SIZE]) { - u8 m[POLY1305_BLOCK_SIZE]; - - memset(m, 0, sizeof(m)); - /* The poly1305 block function adds a hi-bit to the accumulator which - * we don't need for key multiplication; compensate for it. */ - a[4] -= 1 << 24; - poly1305_block_sse2(a, m, b, 1); + poly1305_init_x86_64(ctx, key); } -static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx, - const u8 *src, unsigned int srclen) +static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, + const u32 padbit) { - struct poly1305_simd_desc_ctx *sctx; - unsigned int blocks, datalen; + struct poly1305_arch_internal *state = ctx; - BUILD_BUG_ON(offsetof(struct poly1305_simd_desc_ctx, base)); - sctx = container_of(dctx, struct poly1305_simd_desc_ctx, base); + /* SIMD disables preemption, so relax after processing each page. */ + BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE || + PAGE_SIZE % POLY1305_BLOCK_SIZE); - if (unlikely(!dctx->sset)) { - datalen = crypto_poly1305_setdesckey(dctx, src, srclen); - src += srclen - datalen; - srclen = datalen; + if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx) || + (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) || + !crypto_simd_usable()) { + convert_to_base2_64(ctx); + poly1305_blocks_x86_64(ctx, inp, len, padbit); + return; } -#ifdef CONFIG_AS_AVX2 - if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) { - if (unlikely(!sctx->wset)) { - if (!sctx->uset) { - memcpy(sctx->u, dctx->r.r, sizeof(sctx->u)); - poly1305_simd_mult(sctx->u, dctx->r.r); - sctx->uset = true; - } - memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u)); - poly1305_simd_mult(sctx->u + 5, dctx->r.r); - memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u)); - poly1305_simd_mult(sctx->u + 10, dctx->r.r); - sctx->wset = true; - } - blocks = srclen / (POLY1305_BLOCK_SIZE * 4); - poly1305_4block_avx2(dctx->h.h, src, dctx->r.r, blocks, - sctx->u); - src += POLY1305_BLOCK_SIZE * 4 * blocks; - srclen -= POLY1305_BLOCK_SIZE * 4 * blocks; - } -#endif - if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) { - if (unlikely(!sctx->uset)) { - memcpy(sctx->u, dctx->r.r, sizeof(sctx->u)); - poly1305_simd_mult(sctx->u, dctx->r.r); - sctx->uset = true; - } - blocks = srclen / (POLY1305_BLOCK_SIZE * 2); - poly1305_2block_sse2(dctx->h.h, src, dctx->r.r, blocks, - sctx->u); - src += POLY1305_BLOCK_SIZE * 2 * blocks; - srclen -= POLY1305_BLOCK_SIZE * 2 * blocks; - } - if (srclen >= POLY1305_BLOCK_SIZE) { - poly1305_block_sse2(dctx->h.h, src, dctx->r.r, 1); - srclen -= POLY1305_BLOCK_SIZE; + for (;;) { + const size_t bytes = min_t(size_t, len, PAGE_SIZE); + + kernel_fpu_begin(); + if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512)) + poly1305_blocks_avx512(ctx, inp, bytes, padbit); + else if (IS_ENABLED(CONFIG_AS_AVX2) && static_branch_likely(&poly1305_use_avx2)) + poly1305_blocks_avx2(ctx, inp, bytes, padbit); + else + poly1305_blocks_avx(ctx, inp, bytes, padbit); + kernel_fpu_end(); + len -= bytes; + if (!len) + break; + inp += bytes; } - return srclen; } -static int poly1305_simd_update(struct shash_desc *desc, - const u8 *src, unsigned int srclen) +static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], + const u32 nonce[4]) { - struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); - unsigned int bytes; + if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx)) + poly1305_emit_x86_64(ctx, mac, nonce); + else + poly1305_emit_avx(ctx, mac, nonce); +} - /* kernel_fpu_begin/end is costly, use fallback for small updates */ - if (srclen <= 288 || !crypto_simd_usable()) - return crypto_poly1305_update(desc, src, srclen); +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +{ + poly1305_simd_init(&dctx->h, key); + dctx->s[0] = get_unaligned_le32(&key[16]); + dctx->s[1] = get_unaligned_le32(&key[20]); + dctx->s[2] = get_unaligned_le32(&key[24]); + dctx->s[3] = get_unaligned_le32(&key[28]); + dctx->buflen = 0; + dctx->sset = true; +} +EXPORT_SYMBOL(poly1305_init_arch); + +static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx, + const u8 *inp, unsigned int len) +{ + unsigned int acc = 0; + if (unlikely(!dctx->sset)) { + if (!dctx->rset && len >= POLY1305_BLOCK_SIZE) { + poly1305_simd_init(&dctx->h, inp); + inp += POLY1305_BLOCK_SIZE; + len -= POLY1305_BLOCK_SIZE; + acc += POLY1305_BLOCK_SIZE; + dctx->rset = 1; + } + if (len >= POLY1305_BLOCK_SIZE) { + dctx->s[0] = get_unaligned_le32(&inp[0]); + dctx->s[1] = get_unaligned_le32(&inp[4]); + dctx->s[2] = get_unaligned_le32(&inp[8]); + dctx->s[3] = get_unaligned_le32(&inp[12]); + inp += POLY1305_BLOCK_SIZE; + len -= POLY1305_BLOCK_SIZE; + acc += POLY1305_BLOCK_SIZE; + dctx->sset = true; + } + } + return acc; +} - kernel_fpu_begin(); +void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, + unsigned int srclen) +{ + unsigned int bytes, used; if (unlikely(dctx->buflen)) { bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen); @@ -135,34 +180,76 @@ static int poly1305_simd_update(struct shash_desc *desc, dctx->buflen += bytes; if (dctx->buflen == POLY1305_BLOCK_SIZE) { - poly1305_simd_blocks(dctx, dctx->buf, - POLY1305_BLOCK_SIZE); + if (likely(!crypto_poly1305_setdctxkey(dctx, dctx->buf, POLY1305_BLOCK_SIZE))) + poly1305_simd_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 1); dctx->buflen = 0; } } if (likely(srclen >= POLY1305_BLOCK_SIZE)) { - bytes = poly1305_simd_blocks(dctx, src, srclen); - src += srclen - bytes; - srclen = bytes; + bytes = round_down(srclen, POLY1305_BLOCK_SIZE); + srclen -= bytes; + used = crypto_poly1305_setdctxkey(dctx, src, bytes); + if (likely(bytes - used)) + poly1305_simd_blocks(&dctx->h, src + used, bytes - used, 1); + src += bytes; } - kernel_fpu_end(); - if (unlikely(srclen)) { dctx->buflen = srclen; memcpy(dctx->buf, src, srclen); } +} +EXPORT_SYMBOL(poly1305_update_arch); + +void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst) +{ + if (unlikely(dctx->buflen)) { + dctx->buf[dctx->buflen++] = 1; + memset(dctx->buf + dctx->buflen, 0, + POLY1305_BLOCK_SIZE - dctx->buflen); + poly1305_simd_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0); + } + + poly1305_simd_emit(&dctx->h, dst, dctx->s); + *dctx = (struct poly1305_desc_ctx){}; +} +EXPORT_SYMBOL(poly1305_final_arch); + +static int crypto_poly1305_init(struct shash_desc *desc) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + + *dctx = (struct poly1305_desc_ctx){}; + return 0; +} + +static int crypto_poly1305_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + + poly1305_update_arch(dctx, src, srclen); + return 0; +} + +static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + + if (unlikely(!dctx->sset)) + return -ENOKEY; + poly1305_final_arch(dctx, dst); return 0; } static struct shash_alg alg = { .digestsize = POLY1305_DIGEST_SIZE, - .init = poly1305_simd_init, - .update = poly1305_simd_update, + .init = crypto_poly1305_init, + .update = crypto_poly1305_update, .final = crypto_poly1305_final, - .descsize = sizeof(struct poly1305_simd_desc_ctx), + .descsize = sizeof(struct poly1305_desc_ctx), .base = { .cra_name = "poly1305", .cra_driver_name = "poly1305-simd", @@ -174,30 +261,33 @@ static struct shash_alg alg = { static int __init poly1305_simd_mod_init(void) { - if (!boot_cpu_has(X86_FEATURE_XMM2)) - return -ENODEV; - -#ifdef CONFIG_AS_AVX2 - poly1305_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) && - boot_cpu_has(X86_FEATURE_AVX2) && - cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); - alg.descsize = sizeof(struct poly1305_simd_desc_ctx); - if (poly1305_use_avx2) - alg.descsize += 10 * sizeof(u32); -#endif - return crypto_register_shash(&alg); + if (IS_ENABLED(CONFIG_AS_AVX) && boot_cpu_has(X86_FEATURE_AVX) && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) + static_branch_enable(&poly1305_use_avx); + if (IS_ENABLED(CONFIG_AS_AVX2) && boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) + static_branch_enable(&poly1305_use_avx2); + if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL) && + /* Skylake downclocks unacceptably much when using zmm, but later generations are fast. */ + boot_cpu_data.x86_model != INTEL_FAM6_SKYLAKE_X) + static_branch_enable(&poly1305_use_avx512); + return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? crypto_register_shash(&alg) : 0; } static void __exit poly1305_simd_mod_exit(void) { - crypto_unregister_shash(&alg); + if (IS_REACHABLE(CONFIG_CRYPTO_HASH)) + crypto_unregister_shash(&alg); } module_init(poly1305_simd_mod_init); module_exit(poly1305_simd_mod_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); +MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>"); MODULE_DESCRIPTION("Poly1305 authenticator"); MODULE_ALIAS_CRYPTO("poly1305"); MODULE_ALIAS_CRYPTO("poly1305-simd"); diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S index ddc51dbba3af..ba9e4c1e7f5c 100644 --- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S @@ -555,7 +555,7 @@ transpose_4x4(x0, x1, x2, x3, t0, t1, t2) .align 8 -__serpent_enc_blk8_avx: +SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx) /* input: * %rdi: ctx, CTX * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks @@ -606,10 +606,10 @@ __serpent_enc_blk8_avx: write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2); ret; -ENDPROC(__serpent_enc_blk8_avx) +SYM_FUNC_END(__serpent_enc_blk8_avx) .align 8 -__serpent_dec_blk8_avx: +SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx) /* input: * %rdi: ctx, CTX * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks @@ -660,9 +660,9 @@ __serpent_dec_blk8_avx: write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2); ret; -ENDPROC(__serpent_dec_blk8_avx) +SYM_FUNC_END(__serpent_dec_blk8_avx) -ENTRY(serpent_ecb_enc_8way_avx) +SYM_FUNC_START(serpent_ecb_enc_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -678,9 +678,9 @@ ENTRY(serpent_ecb_enc_8way_avx) FRAME_END ret; -ENDPROC(serpent_ecb_enc_8way_avx) +SYM_FUNC_END(serpent_ecb_enc_8way_avx) -ENTRY(serpent_ecb_dec_8way_avx) +SYM_FUNC_START(serpent_ecb_dec_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -696,9 +696,9 @@ ENTRY(serpent_ecb_dec_8way_avx) FRAME_END ret; -ENDPROC(serpent_ecb_dec_8way_avx) +SYM_FUNC_END(serpent_ecb_dec_8way_avx) -ENTRY(serpent_cbc_dec_8way_avx) +SYM_FUNC_START(serpent_cbc_dec_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -714,9 +714,9 @@ ENTRY(serpent_cbc_dec_8way_avx) FRAME_END ret; -ENDPROC(serpent_cbc_dec_8way_avx) +SYM_FUNC_END(serpent_cbc_dec_8way_avx) -ENTRY(serpent_ctr_8way_avx) +SYM_FUNC_START(serpent_ctr_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -734,9 +734,9 @@ ENTRY(serpent_ctr_8way_avx) FRAME_END ret; -ENDPROC(serpent_ctr_8way_avx) +SYM_FUNC_END(serpent_ctr_8way_avx) -ENTRY(serpent_xts_enc_8way_avx) +SYM_FUNC_START(serpent_xts_enc_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -756,9 +756,9 @@ ENTRY(serpent_xts_enc_8way_avx) FRAME_END ret; -ENDPROC(serpent_xts_enc_8way_avx) +SYM_FUNC_END(serpent_xts_enc_8way_avx) -ENTRY(serpent_xts_dec_8way_avx) +SYM_FUNC_START(serpent_xts_dec_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -778,4 +778,4 @@ ENTRY(serpent_xts_dec_8way_avx) FRAME_END ret; -ENDPROC(serpent_xts_dec_8way_avx) +SYM_FUNC_END(serpent_xts_dec_8way_avx) diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S index 37bc1d48106c..c9648aeae705 100644 --- a/arch/x86/crypto/serpent-avx2-asm_64.S +++ b/arch/x86/crypto/serpent-avx2-asm_64.S @@ -561,7 +561,7 @@ transpose_4x4(x0, x1, x2, x3, t0, t1, t2) .align 8 -__serpent_enc_blk16: +SYM_FUNC_START_LOCAL(__serpent_enc_blk16) /* input: * %rdi: ctx, CTX * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: plaintext @@ -612,10 +612,10 @@ __serpent_enc_blk16: write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2); ret; -ENDPROC(__serpent_enc_blk16) +SYM_FUNC_END(__serpent_enc_blk16) .align 8 -__serpent_dec_blk16: +SYM_FUNC_START_LOCAL(__serpent_dec_blk16) /* input: * %rdi: ctx, CTX * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: ciphertext @@ -666,9 +666,9 @@ __serpent_dec_blk16: write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2); ret; -ENDPROC(__serpent_dec_blk16) +SYM_FUNC_END(__serpent_dec_blk16) -ENTRY(serpent_ecb_enc_16way) +SYM_FUNC_START(serpent_ecb_enc_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -688,9 +688,9 @@ ENTRY(serpent_ecb_enc_16way) FRAME_END ret; -ENDPROC(serpent_ecb_enc_16way) +SYM_FUNC_END(serpent_ecb_enc_16way) -ENTRY(serpent_ecb_dec_16way) +SYM_FUNC_START(serpent_ecb_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -710,9 +710,9 @@ ENTRY(serpent_ecb_dec_16way) FRAME_END ret; -ENDPROC(serpent_ecb_dec_16way) +SYM_FUNC_END(serpent_ecb_dec_16way) -ENTRY(serpent_cbc_dec_16way) +SYM_FUNC_START(serpent_cbc_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -733,9 +733,9 @@ ENTRY(serpent_cbc_dec_16way) FRAME_END ret; -ENDPROC(serpent_cbc_dec_16way) +SYM_FUNC_END(serpent_cbc_dec_16way) -ENTRY(serpent_ctr_16way) +SYM_FUNC_START(serpent_ctr_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -758,9 +758,9 @@ ENTRY(serpent_ctr_16way) FRAME_END ret; -ENDPROC(serpent_ctr_16way) +SYM_FUNC_END(serpent_ctr_16way) -ENTRY(serpent_xts_enc_16way) +SYM_FUNC_START(serpent_xts_enc_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -784,9 +784,9 @@ ENTRY(serpent_xts_enc_16way) FRAME_END ret; -ENDPROC(serpent_xts_enc_16way) +SYM_FUNC_END(serpent_xts_enc_16way) -ENTRY(serpent_xts_dec_16way) +SYM_FUNC_START(serpent_xts_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -810,4 +810,4 @@ ENTRY(serpent_xts_dec_16way) FRAME_END ret; -ENDPROC(serpent_xts_dec_16way) +SYM_FUNC_END(serpent_xts_dec_16way) diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S index e5c4a4690ca9..6379b99cb722 100644 --- a/arch/x86/crypto/serpent-sse2-i586-asm_32.S +++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S @@ -497,7 +497,7 @@ pxor t0, x3; \ movdqu x3, (3*4*4)(out); -ENTRY(__serpent_enc_blk_4way) +SYM_FUNC_START(__serpent_enc_blk_4way) /* input: * arg_ctx(%esp): ctx, CTX * arg_dst(%esp): dst @@ -559,9 +559,9 @@ ENTRY(__serpent_enc_blk_4way) xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE); ret; -ENDPROC(__serpent_enc_blk_4way) +SYM_FUNC_END(__serpent_enc_blk_4way) -ENTRY(serpent_dec_blk_4way) +SYM_FUNC_START(serpent_dec_blk_4way) /* input: * arg_ctx(%esp): ctx, CTX * arg_dst(%esp): dst @@ -613,4 +613,4 @@ ENTRY(serpent_dec_blk_4way) write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA); ret; -ENDPROC(serpent_dec_blk_4way) +SYM_FUNC_END(serpent_dec_blk_4way) diff --git a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S index 5e0b3a3e97af..efb6dc17dc90 100644 --- a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S @@ -619,7 +619,7 @@ pxor t0, x3; \ movdqu x3, (3*4*4)(out); -ENTRY(__serpent_enc_blk_8way) +SYM_FUNC_START(__serpent_enc_blk_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -682,9 +682,9 @@ ENTRY(__serpent_enc_blk_8way) xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2); ret; -ENDPROC(__serpent_enc_blk_8way) +SYM_FUNC_END(__serpent_enc_blk_8way) -ENTRY(serpent_dec_blk_8way) +SYM_FUNC_START(serpent_dec_blk_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -736,4 +736,4 @@ ENTRY(serpent_dec_blk_8way) write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2); ret; -ENDPROC(serpent_dec_blk_8way) +SYM_FUNC_END(serpent_dec_blk_8way) diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index b871728e0b2f..f973ace44ad3 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -19,18 +19,16 @@ #define SERPENT_AVX2_PARALLEL_BLOCKS 16 /* 16-way AVX2 parallel cipher functions */ -asmlinkage void serpent_ecb_enc_16way(struct serpent_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void serpent_ecb_dec_16way(struct serpent_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void serpent_cbc_dec_16way(void *ctx, u128 *dst, const u128 *src); +asmlinkage void serpent_ecb_enc_16way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void serpent_ecb_dec_16way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void serpent_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void serpent_ctr_16way(void *ctx, u128 *dst, const u128 *src, +asmlinkage void serpent_ctr_16way(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -asmlinkage void serpent_xts_enc_16way(struct serpent_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); -asmlinkage void serpent_xts_dec_16way(struct serpent_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void serpent_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); +asmlinkage void serpent_xts_dec_16way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); static int serpent_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) @@ -44,13 +42,13 @@ static const struct common_glue_ctx serpent_enc = { .funcs = { { .num_blocks = 16, - .fn_u = { .ecb = GLUE_FUNC_CAST(serpent_ecb_enc_16way) } + .fn_u = { .ecb = serpent_ecb_enc_16way } }, { .num_blocks = 8, - .fn_u = { .ecb = GLUE_FUNC_CAST(serpent_ecb_enc_8way_avx) } + .fn_u = { .ecb = serpent_ecb_enc_8way_avx } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_encrypt) } + .fn_u = { .ecb = __serpent_encrypt } } } }; @@ -60,13 +58,13 @@ static const struct common_glue_ctx serpent_ctr = { .funcs = { { .num_blocks = 16, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(serpent_ctr_16way) } + .fn_u = { .ctr = serpent_ctr_16way } }, { .num_blocks = 8, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(serpent_ctr_8way_avx) } + .fn_u = { .ctr = serpent_ctr_8way_avx } }, { .num_blocks = 1, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(__serpent_crypt_ctr) } + .fn_u = { .ctr = __serpent_crypt_ctr } } } }; @@ -76,13 +74,13 @@ static const struct common_glue_ctx serpent_enc_xts = { .funcs = { { .num_blocks = 16, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_enc_16way) } + .fn_u = { .xts = serpent_xts_enc_16way } }, { .num_blocks = 8, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_enc_8way_avx) } + .fn_u = { .xts = serpent_xts_enc_8way_avx } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_enc) } + .fn_u = { .xts = serpent_xts_enc } } } }; @@ -92,13 +90,13 @@ static const struct common_glue_ctx serpent_dec = { .funcs = { { .num_blocks = 16, - .fn_u = { .ecb = GLUE_FUNC_CAST(serpent_ecb_dec_16way) } + .fn_u = { .ecb = serpent_ecb_dec_16way } }, { .num_blocks = 8, - .fn_u = { .ecb = GLUE_FUNC_CAST(serpent_ecb_dec_8way_avx) } + .fn_u = { .ecb = serpent_ecb_dec_8way_avx } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_decrypt) } + .fn_u = { .ecb = __serpent_decrypt } } } }; @@ -108,13 +106,13 @@ static const struct common_glue_ctx serpent_dec_cbc = { .funcs = { { .num_blocks = 16, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(serpent_cbc_dec_16way) } + .fn_u = { .cbc = serpent_cbc_dec_16way } }, { .num_blocks = 8, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(serpent_cbc_dec_8way_avx) } + .fn_u = { .cbc = serpent_cbc_dec_8way_avx } }, { .num_blocks = 1, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(__serpent_decrypt) } + .fn_u = { .cbc = __serpent_decrypt } } } }; @@ -124,13 +122,13 @@ static const struct common_glue_ctx serpent_dec_xts = { .funcs = { { .num_blocks = 16, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_dec_16way) } + .fn_u = { .xts = serpent_xts_dec_16way } }, { .num_blocks = 8, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_dec_8way_avx) } + .fn_u = { .xts = serpent_xts_dec_8way_avx } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_dec) } + .fn_u = { .xts = serpent_xts_dec } } } }; @@ -146,8 +144,7 @@ static int ecb_decrypt(struct skcipher_request *req) static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(__serpent_encrypt), - req); + return glue_cbc_encrypt_req_128bit(__serpent_encrypt, req); } static int cbc_decrypt(struct skcipher_request *req) @@ -166,8 +163,8 @@ static int xts_encrypt(struct skcipher_request *req) struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm); return glue_xts_req_128bit(&serpent_enc_xts, req, - XTS_TWEAK_CAST(__serpent_encrypt), - &ctx->tweak_ctx, &ctx->crypt_ctx); + __serpent_encrypt, &ctx->tweak_ctx, + &ctx->crypt_ctx, false); } static int xts_decrypt(struct skcipher_request *req) @@ -176,8 +173,8 @@ static int xts_decrypt(struct skcipher_request *req) struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm); return glue_xts_req_128bit(&serpent_dec_xts, req, - XTS_TWEAK_CAST(__serpent_encrypt), - &ctx->tweak_ctx, &ctx->crypt_ctx); + __serpent_encrypt, &ctx->tweak_ctx, + &ctx->crypt_ctx, true); } static struct skcipher_alg serpent_algs[] = { diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c index 4a9a9f2ee1d8..7806d1cbe854 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -20,33 +20,35 @@ #include <asm/crypto/serpent-avx.h> /* 8-way parallel cipher functions */ -asmlinkage void serpent_ecb_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_ecb_enc_8way_avx(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(serpent_ecb_enc_8way_avx); -asmlinkage void serpent_ecb_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_ecb_dec_8way_avx(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(serpent_ecb_dec_8way_avx); -asmlinkage void serpent_cbc_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_cbc_dec_8way_avx(const void *ctx, u8 *dst, const u8 *src); EXPORT_SYMBOL_GPL(serpent_cbc_dec_8way_avx); -asmlinkage void serpent_ctr_8way_avx(struct serpent_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void serpent_ctr_8way_avx(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); EXPORT_SYMBOL_GPL(serpent_ctr_8way_avx); -asmlinkage void serpent_xts_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_xts_enc_8way_avx(const void *ctx, u8 *dst, const u8 *src, le128 *iv); EXPORT_SYMBOL_GPL(serpent_xts_enc_8way_avx); -asmlinkage void serpent_xts_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_xts_dec_8way_avx(const void *ctx, u8 *dst, const u8 *src, le128 *iv); EXPORT_SYMBOL_GPL(serpent_xts_dec_8way_avx); -void __serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv) +void __serpent_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) { be128 ctrblk; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; le128_to_be128(&ctrblk, iv); le128_inc(iv); @@ -56,17 +58,15 @@ void __serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv) } EXPORT_SYMBOL_GPL(__serpent_crypt_ctr); -void serpent_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv) +void serpent_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, - GLUE_FUNC_CAST(__serpent_encrypt)); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, __serpent_encrypt); } EXPORT_SYMBOL_GPL(serpent_xts_enc); -void serpent_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv) +void serpent_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, - GLUE_FUNC_CAST(__serpent_decrypt)); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, __serpent_decrypt); } EXPORT_SYMBOL_GPL(serpent_xts_dec); @@ -102,10 +102,10 @@ static const struct common_glue_ctx serpent_enc = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(serpent_ecb_enc_8way_avx) } + .fn_u = { .ecb = serpent_ecb_enc_8way_avx } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_encrypt) } + .fn_u = { .ecb = __serpent_encrypt } } } }; @@ -115,10 +115,10 @@ static const struct common_glue_ctx serpent_ctr = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(serpent_ctr_8way_avx) } + .fn_u = { .ctr = serpent_ctr_8way_avx } }, { .num_blocks = 1, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(__serpent_crypt_ctr) } + .fn_u = { .ctr = __serpent_crypt_ctr } } } }; @@ -128,10 +128,10 @@ static const struct common_glue_ctx serpent_enc_xts = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_enc_8way_avx) } + .fn_u = { .xts = serpent_xts_enc_8way_avx } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_enc) } + .fn_u = { .xts = serpent_xts_enc } } } }; @@ -141,10 +141,10 @@ static const struct common_glue_ctx serpent_dec = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(serpent_ecb_dec_8way_avx) } + .fn_u = { .ecb = serpent_ecb_dec_8way_avx } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_decrypt) } + .fn_u = { .ecb = __serpent_decrypt } } } }; @@ -154,10 +154,10 @@ static const struct common_glue_ctx serpent_dec_cbc = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(serpent_cbc_dec_8way_avx) } + .fn_u = { .cbc = serpent_cbc_dec_8way_avx } }, { .num_blocks = 1, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(__serpent_decrypt) } + .fn_u = { .cbc = __serpent_decrypt } } } }; @@ -167,10 +167,10 @@ static const struct common_glue_ctx serpent_dec_xts = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_dec_8way_avx) } + .fn_u = { .xts = serpent_xts_dec_8way_avx } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(serpent_xts_dec) } + .fn_u = { .xts = serpent_xts_dec } } } }; @@ -186,8 +186,7 @@ static int ecb_decrypt(struct skcipher_request *req) static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(__serpent_encrypt), - req); + return glue_cbc_encrypt_req_128bit(__serpent_encrypt, req); } static int cbc_decrypt(struct skcipher_request *req) @@ -206,8 +205,8 @@ static int xts_encrypt(struct skcipher_request *req) struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm); return glue_xts_req_128bit(&serpent_enc_xts, req, - XTS_TWEAK_CAST(__serpent_encrypt), - &ctx->tweak_ctx, &ctx->crypt_ctx); + __serpent_encrypt, &ctx->tweak_ctx, + &ctx->crypt_ctx, false); } static int xts_decrypt(struct skcipher_request *req) @@ -216,8 +215,8 @@ static int xts_decrypt(struct skcipher_request *req) struct serpent_xts_ctx *ctx = crypto_skcipher_ctx(tfm); return glue_xts_req_128bit(&serpent_dec_xts, req, - XTS_TWEAK_CAST(__serpent_encrypt), - &ctx->tweak_ctx, &ctx->crypt_ctx); + __serpent_encrypt, &ctx->tweak_ctx, + &ctx->crypt_ctx, true); } static struct skcipher_alg serpent_algs[] = { diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c index 5fdf1931d069..4fed8d26b91a 100644 --- a/arch/x86/crypto/serpent_sse2_glue.c +++ b/arch/x86/crypto/serpent_sse2_glue.c @@ -31,9 +31,11 @@ static int serpent_setkey_skcipher(struct crypto_skcipher *tfm, return __serpent_setkey(crypto_skcipher_ctx(tfm), key, keylen); } -static void serpent_decrypt_cbc_xway(void *ctx, u128 *dst, const u128 *src) +static void serpent_decrypt_cbc_xway(const void *ctx, u8 *d, const u8 *s) { u128 ivs[SERPENT_PARALLEL_BLOCKS - 1]; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; unsigned int j; for (j = 0; j < SERPENT_PARALLEL_BLOCKS - 1; j++) @@ -45,9 +47,11 @@ static void serpent_decrypt_cbc_xway(void *ctx, u128 *dst, const u128 *src) u128_xor(dst + (j + 1), dst + (j + 1), ivs + j); } -static void serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv) +static void serpent_crypt_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) { be128 ctrblk; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; le128_to_be128(&ctrblk, iv); le128_inc(iv); @@ -56,10 +60,12 @@ static void serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv) u128_xor(dst, src, (u128 *)&ctrblk); } -static void serpent_crypt_ctr_xway(void *ctx, u128 *dst, const u128 *src, +static void serpent_crypt_ctr_xway(const void *ctx, u8 *d, const u8 *s, le128 *iv) { be128 ctrblks[SERPENT_PARALLEL_BLOCKS]; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; unsigned int i; for (i = 0; i < SERPENT_PARALLEL_BLOCKS; i++) { @@ -79,10 +85,10 @@ static const struct common_glue_ctx serpent_enc = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(serpent_enc_blk_xway) } + .fn_u = { .ecb = serpent_enc_blk_xway } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_encrypt) } + .fn_u = { .ecb = __serpent_encrypt } } } }; @@ -92,10 +98,10 @@ static const struct common_glue_ctx serpent_ctr = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(serpent_crypt_ctr_xway) } + .fn_u = { .ctr = serpent_crypt_ctr_xway } }, { .num_blocks = 1, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(serpent_crypt_ctr) } + .fn_u = { .ctr = serpent_crypt_ctr } } } }; @@ -105,10 +111,10 @@ static const struct common_glue_ctx serpent_dec = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(serpent_dec_blk_xway) } + .fn_u = { .ecb = serpent_dec_blk_xway } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_decrypt) } + .fn_u = { .ecb = __serpent_decrypt } } } }; @@ -118,10 +124,10 @@ static const struct common_glue_ctx serpent_dec_cbc = { .funcs = { { .num_blocks = SERPENT_PARALLEL_BLOCKS, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(serpent_decrypt_cbc_xway) } + .fn_u = { .cbc = serpent_decrypt_cbc_xway } }, { .num_blocks = 1, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(__serpent_decrypt) } + .fn_u = { .cbc = __serpent_decrypt } } } }; @@ -137,7 +143,7 @@ static int ecb_decrypt(struct skcipher_request *req) static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(__serpent_encrypt), + return glue_cbc_encrypt_req_128bit(__serpent_encrypt, req); } diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S index 9f712a7dfd79..1e594d60afa5 100644 --- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S +++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S @@ -62,11 +62,11 @@ *Visit http://software.intel.com/en-us/articles/ *and refer to improving-the-performance-of-the-secure-hash-algorithm-1/ * - *Updates 20-byte SHA-1 record in 'hash' for even number of - *'num_blocks' consecutive 64-byte blocks + *Updates 20-byte SHA-1 record at start of 'state', from 'input', for + *even number of 'blocks' consecutive 64-byte blocks. * *extern "C" void sha1_transform_avx2( - * int *hash, const char* input, size_t num_blocks ); + * struct sha1_state *state, const u8* input, int blocks ); */ #include <linux/linkage.h> @@ -634,7 +634,7 @@ _loop3: * param: function's name */ .macro SHA1_VECTOR_ASM name - ENTRY(\name) + SYM_FUNC_START(\name) push %rbx push %r12 @@ -676,7 +676,7 @@ _loop3: ret - ENDPROC(\name) + SYM_FUNC_END(\name) .endm .section .rodata diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S index ebbdba72ae07..11efe3a45a1f 100644 --- a/arch/x86/crypto/sha1_ni_asm.S +++ b/arch/x86/crypto/sha1_ni_asm.S @@ -95,7 +95,7 @@ */ .text .align 32 -ENTRY(sha1_ni_transform) +SYM_FUNC_START(sha1_ni_transform) mov %rsp, RSPSAVE sub $FRAME_SIZE, %rsp and $~0xF, %rsp @@ -291,7 +291,7 @@ ENTRY(sha1_ni_transform) mov RSPSAVE, %rsp ret -ENDPROC(sha1_ni_transform) +SYM_FUNC_END(sha1_ni_transform) .section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16 .align 16 diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index 99c5b8c4dc38..12e2d19d7402 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -67,7 +67,7 @@ * param: function's name */ .macro SHA1_VECTOR_ASM name - ENTRY(\name) + SYM_FUNC_START(\name) push %rbx push %r12 @@ -101,7 +101,7 @@ pop %rbx ret - ENDPROC(\name) + SYM_FUNC_END(\name) .endm /* @@ -457,9 +457,13 @@ W_PRECALC_SSSE3 movdqu \a,\b .endm -/* SSSE3 optimized implementation: - * extern "C" void sha1_transform_ssse3(u32 *digest, const char *data, u32 *ws, - * unsigned int rounds); +/* + * SSSE3 optimized implementation: + * + * extern "C" void sha1_transform_ssse3(struct sha1_state *state, + * const u8 *data, int blocks); + * + * Note that struct sha1_state is assumed to begin with u32 state[5]. */ SHA1_VECTOR_ASM sha1_transform_ssse3 @@ -545,8 +549,8 @@ W_PRECALC_AVX /* AVX optimized implementation: - * extern "C" void sha1_transform_avx(u32 *digest, const char *data, u32 *ws, - * unsigned int rounds); + * extern "C" void sha1_transform_avx(struct sha1_state *state, + * const u8 *data, int blocks); */ SHA1_VECTOR_ASM sha1_transform_avx diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 639d4c2fd6a8..d70b40ad594c 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -27,11 +27,8 @@ #include <crypto/sha1_base.h> #include <asm/simd.h> -typedef void (sha1_transform_fn)(u32 *digest, const char *data, - unsigned int rounds); - static int sha1_update(struct shash_desc *desc, const u8 *data, - unsigned int len, sha1_transform_fn *sha1_xform) + unsigned int len, sha1_block_fn *sha1_xform) { struct sha1_state *sctx = shash_desc_ctx(desc); @@ -39,48 +36,47 @@ static int sha1_update(struct shash_desc *desc, const u8 *data, (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE) return crypto_sha1_update(desc, data, len); - /* make sure casting to sha1_block_fn() is safe */ + /* + * Make sure struct sha1_state begins directly with the SHA1 + * 160-bit internal state, as this is what the asm functions expect. + */ BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0); kernel_fpu_begin(); - sha1_base_do_update(desc, data, len, - (sha1_block_fn *)sha1_xform); + sha1_base_do_update(desc, data, len, sha1_xform); kernel_fpu_end(); return 0; } static int sha1_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out, sha1_transform_fn *sha1_xform) + unsigned int len, u8 *out, sha1_block_fn *sha1_xform) { if (!crypto_simd_usable()) return crypto_sha1_finup(desc, data, len, out); kernel_fpu_begin(); if (len) - sha1_base_do_update(desc, data, len, - (sha1_block_fn *)sha1_xform); - sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_xform); + sha1_base_do_update(desc, data, len, sha1_xform); + sha1_base_do_finalize(desc, sha1_xform); kernel_fpu_end(); return sha1_base_finish(desc, out); } -asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data, - unsigned int rounds); +asmlinkage void sha1_transform_ssse3(struct sha1_state *state, + const u8 *data, int blocks); static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha1_update(desc, data, len, - (sha1_transform_fn *) sha1_transform_ssse3); + return sha1_update(desc, data, len, sha1_transform_ssse3); } static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - return sha1_finup(desc, data, len, out, - (sha1_transform_fn *) sha1_transform_ssse3); + return sha1_finup(desc, data, len, out, sha1_transform_ssse3); } /* Add padding and return the message digest. */ @@ -119,21 +115,19 @@ static void unregister_sha1_ssse3(void) } #ifdef CONFIG_AS_AVX -asmlinkage void sha1_transform_avx(u32 *digest, const char *data, - unsigned int rounds); +asmlinkage void sha1_transform_avx(struct sha1_state *state, + const u8 *data, int blocks); static int sha1_avx_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha1_update(desc, data, len, - (sha1_transform_fn *) sha1_transform_avx); + return sha1_update(desc, data, len, sha1_transform_avx); } static int sha1_avx_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - return sha1_finup(desc, data, len, out, - (sha1_transform_fn *) sha1_transform_avx); + return sha1_finup(desc, data, len, out, sha1_transform_avx); } static int sha1_avx_final(struct shash_desc *desc, u8 *out) @@ -190,8 +184,8 @@ static inline void unregister_sha1_avx(void) { } #if defined(CONFIG_AS_AVX2) && (CONFIG_AS_AVX) #define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */ -asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, - unsigned int rounds); +asmlinkage void sha1_transform_avx2(struct sha1_state *state, + const u8 *data, int blocks); static bool avx2_usable(void) { @@ -203,28 +197,26 @@ static bool avx2_usable(void) return false; } -static void sha1_apply_transform_avx2(u32 *digest, const char *data, - unsigned int rounds) +static void sha1_apply_transform_avx2(struct sha1_state *state, + const u8 *data, int blocks) { /* Select the optimal transform based on data block size */ - if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE) - sha1_transform_avx2(digest, data, rounds); + if (blocks >= SHA1_AVX2_BLOCK_OPTSIZE) + sha1_transform_avx2(state, data, blocks); else - sha1_transform_avx(digest, data, rounds); + sha1_transform_avx(state, data, blocks); } static int sha1_avx2_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha1_update(desc, data, len, - (sha1_transform_fn *) sha1_apply_transform_avx2); + return sha1_update(desc, data, len, sha1_apply_transform_avx2); } static int sha1_avx2_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - return sha1_finup(desc, data, len, out, - (sha1_transform_fn *) sha1_apply_transform_avx2); + return sha1_finup(desc, data, len, out, sha1_apply_transform_avx2); } static int sha1_avx2_final(struct shash_desc *desc, u8 *out) @@ -267,21 +259,19 @@ static inline void unregister_sha1_avx2(void) { } #endif #ifdef CONFIG_AS_SHA1_NI -asmlinkage void sha1_ni_transform(u32 *digest, const char *data, - unsigned int rounds); +asmlinkage void sha1_ni_transform(struct sha1_state *digest, const u8 *data, + int rounds); static int sha1_ni_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha1_update(desc, data, len, - (sha1_transform_fn *) sha1_ni_transform); + return sha1_update(desc, data, len, sha1_ni_transform); } static int sha1_ni_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - return sha1_finup(desc, data, len, out, - (sha1_transform_fn *) sha1_ni_transform); + return sha1_finup(desc, data, len, out, sha1_ni_transform); } static int sha1_ni_final(struct shash_desc *desc, u8 *out) diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index 001bbcf93c79..fcbc30f58c38 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -341,13 +341,13 @@ a = TMP_ .endm ######################################################################## -## void sha256_transform_avx(void *input_data, UINT32 digest[8], UINT64 num_blks) -## arg 1 : pointer to digest +## void sha256_transform_avx(state sha256_state *state, const u8 *data, int blocks) +## arg 1 : pointer to state ## arg 2 : pointer to input data ## arg 3 : Num blocks ######################################################################## .text -ENTRY(sha256_transform_avx) +SYM_FUNC_START(sha256_transform_avx) .align 32 pushq %rbx pushq %r12 @@ -460,7 +460,7 @@ done_hash: popq %r12 popq %rbx ret -ENDPROC(sha256_transform_avx) +SYM_FUNC_END(sha256_transform_avx) .section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 1420db15dcdd..499d9ec129de 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -520,13 +520,13 @@ STACK_SIZE = _RSP + _RSP_SIZE .endm ######################################################################## -## void sha256_transform_rorx(void *input_data, UINT32 digest[8], UINT64 num_blks) -## arg 1 : pointer to digest +## void sha256_transform_rorx(struct sha256_state *state, const u8 *data, int blocks) +## arg 1 : pointer to state ## arg 2 : pointer to input data ## arg 3 : Num blocks ######################################################################## .text -ENTRY(sha256_transform_rorx) +SYM_FUNC_START(sha256_transform_rorx) .align 32 pushq %rbx pushq %r12 @@ -713,7 +713,7 @@ done_hash: popq %r12 popq %rbx ret -ENDPROC(sha256_transform_rorx) +SYM_FUNC_END(sha256_transform_rorx) .section .rodata.cst512.K256, "aM", @progbits, 512 .align 64 diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index c6c05ed2c16a..ddfa863b4ee3 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -347,13 +347,15 @@ a = TMP_ .endm ######################################################################## -## void sha256_transform_ssse3(void *input_data, UINT32 digest[8], UINT64 num_blks) -## arg 1 : pointer to digest +## void sha256_transform_ssse3(struct sha256_state *state, const u8 *data, +## int blocks); +## arg 1 : pointer to state +## (struct sha256_state is assumed to begin with u32 state[8]) ## arg 2 : pointer to input data ## arg 3 : Num blocks ######################################################################## .text -ENTRY(sha256_transform_ssse3) +SYM_FUNC_START(sha256_transform_ssse3) .align 32 pushq %rbx pushq %r12 @@ -471,7 +473,7 @@ done_hash: popq %rbx ret -ENDPROC(sha256_transform_ssse3) +SYM_FUNC_END(sha256_transform_ssse3) .section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S index fb58f58ecfbc..7abade04a3a3 100644 --- a/arch/x86/crypto/sha256_ni_asm.S +++ b/arch/x86/crypto/sha256_ni_asm.S @@ -97,7 +97,7 @@ .text .align 32 -ENTRY(sha256_ni_transform) +SYM_FUNC_START(sha256_ni_transform) shl $6, NUM_BLKS /* convert to bytes */ jz .Ldone_hash @@ -327,7 +327,7 @@ ENTRY(sha256_ni_transform) .Ldone_hash: ret -ENDPROC(sha256_ni_transform) +SYM_FUNC_END(sha256_ni_transform) .section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 73867da3cbee..03ad657c04bd 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -41,12 +41,11 @@ #include <linux/string.h> #include <asm/simd.h> -asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data, - u64 rounds); -typedef void (sha256_transform_fn)(u32 *digest, const char *data, u64 rounds); +asmlinkage void sha256_transform_ssse3(struct sha256_state *state, + const u8 *data, int blocks); -static int sha256_update(struct shash_desc *desc, const u8 *data, - unsigned int len, sha256_transform_fn *sha256_xform) +static int _sha256_update(struct shash_desc *desc, const u8 *data, + unsigned int len, sha256_block_fn *sha256_xform) { struct sha256_state *sctx = shash_desc_ctx(desc); @@ -54,28 +53,29 @@ static int sha256_update(struct shash_desc *desc, const u8 *data, (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE) return crypto_sha256_update(desc, data, len); - /* make sure casting to sha256_block_fn() is safe */ + /* + * Make sure struct sha256_state begins directly with the SHA256 + * 256-bit internal state, as this is what the asm functions expect. + */ BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); kernel_fpu_begin(); - sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_xform); + sha256_base_do_update(desc, data, len, sha256_xform); kernel_fpu_end(); return 0; } static int sha256_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out, sha256_transform_fn *sha256_xform) + unsigned int len, u8 *out, sha256_block_fn *sha256_xform) { if (!crypto_simd_usable()) return crypto_sha256_finup(desc, data, len, out); kernel_fpu_begin(); if (len) - sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_xform); - sha256_base_do_finalize(desc, (sha256_block_fn *)sha256_xform); + sha256_base_do_update(desc, data, len, sha256_xform); + sha256_base_do_finalize(desc, sha256_xform); kernel_fpu_end(); return sha256_base_finish(desc, out); @@ -84,7 +84,7 @@ static int sha256_finup(struct shash_desc *desc, const u8 *data, static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha256_update(desc, data, len, sha256_transform_ssse3); + return _sha256_update(desc, data, len, sha256_transform_ssse3); } static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, @@ -145,13 +145,13 @@ static void unregister_sha256_ssse3(void) } #ifdef CONFIG_AS_AVX -asmlinkage void sha256_transform_avx(u32 *digest, const char *data, - u64 rounds); +asmlinkage void sha256_transform_avx(struct sha256_state *state, + const u8 *data, int blocks); static int sha256_avx_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha256_update(desc, data, len, sha256_transform_avx); + return _sha256_update(desc, data, len, sha256_transform_avx); } static int sha256_avx_finup(struct shash_desc *desc, const u8 *data, @@ -227,13 +227,13 @@ static inline void unregister_sha256_avx(void) { } #endif #if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) -asmlinkage void sha256_transform_rorx(u32 *digest, const char *data, - u64 rounds); +asmlinkage void sha256_transform_rorx(struct sha256_state *state, + const u8 *data, int blocks); static int sha256_avx2_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha256_update(desc, data, len, sha256_transform_rorx); + return _sha256_update(desc, data, len, sha256_transform_rorx); } static int sha256_avx2_finup(struct shash_desc *desc, const u8 *data, @@ -307,13 +307,13 @@ static inline void unregister_sha256_avx2(void) { } #endif #ifdef CONFIG_AS_SHA256_NI -asmlinkage void sha256_ni_transform(u32 *digest, const char *data, - u64 rounds); /*unsigned int rounds);*/ +asmlinkage void sha256_ni_transform(struct sha256_state *digest, + const u8 *data, int rounds); static int sha256_ni_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha256_update(desc, data, len, sha256_ni_transform); + return _sha256_update(desc, data, len, sha256_ni_transform); } static int sha256_ni_finup(struct shash_desc *desc, const u8 *data, diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S index 39235fefe6f7..90ea945ba5e6 100644 --- a/arch/x86/crypto/sha512-avx-asm.S +++ b/arch/x86/crypto/sha512-avx-asm.S @@ -271,13 +271,14 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE .endm ######################################################################## -# void sha512_transform_avx(void* D, const void* M, u64 L) -# Purpose: Updates the SHA512 digest stored at D with the message stored in M. -# The size of the message pointed to by M must be an integer multiple of SHA512 -# message blocks. -# L is the message length in SHA512 blocks +# void sha512_transform_avx(sha512_state *state, const u8 *data, int blocks) +# Purpose: Updates the SHA512 digest stored at "state" with the message +# stored in "data". +# The size of the message pointed to by "data" must be an integer multiple +# of SHA512 message blocks. +# "blocks" is the message length in SHA512 blocks ######################################################################## -ENTRY(sha512_transform_avx) +SYM_FUNC_START(sha512_transform_avx) cmp $0, msglen je nowork @@ -365,7 +366,7 @@ updateblock: nowork: ret -ENDPROC(sha512_transform_avx) +SYM_FUNC_END(sha512_transform_avx) ######################################################################## ### Binary Data diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index b16d56005162..3dd886b14e7d 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -563,13 +563,14 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE .endm ######################################################################## -# void sha512_transform_rorx(void* D, const void* M, uint64_t L)# -# Purpose: Updates the SHA512 digest stored at D with the message stored in M. -# The size of the message pointed to by M must be an integer multiple of SHA512 -# message blocks. -# L is the message length in SHA512 blocks +# void sha512_transform_rorx(sha512_state *state, const u8 *data, int blocks) +# Purpose: Updates the SHA512 digest stored at "state" with the message +# stored in "data". +# The size of the message pointed to by "data" must be an integer multiple +# of SHA512 message blocks. +# "blocks" is the message length in SHA512 blocks ######################################################################## -ENTRY(sha512_transform_rorx) +SYM_FUNC_START(sha512_transform_rorx) # Allocate Stack Space mov %rsp, %rax sub $frame_size, %rsp @@ -682,7 +683,7 @@ done_hash: # Restore Stack Pointer mov frame_RSPSAVE(%rsp), %rsp ret -ENDPROC(sha512_transform_rorx) +SYM_FUNC_END(sha512_transform_rorx) ######################################################################## ### Binary Data diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S index 66bbd9058a90..7946a1bee85b 100644 --- a/arch/x86/crypto/sha512-ssse3-asm.S +++ b/arch/x86/crypto/sha512-ssse3-asm.S @@ -269,13 +269,16 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE .endm ######################################################################## -# void sha512_transform_ssse3(void* D, const void* M, u64 L)# -# Purpose: Updates the SHA512 digest stored at D with the message stored in M. -# The size of the message pointed to by M must be an integer multiple of SHA512 -# message blocks. -# L is the message length in SHA512 blocks. +## void sha512_transform_ssse3(struct sha512_state *state, const u8 *data, +## int blocks); +# (struct sha512_state is assumed to begin with u64 state[8]) +# Purpose: Updates the SHA512 digest stored at "state" with the message +# stored in "data". +# The size of the message pointed to by "data" must be an integer multiple +# of SHA512 message blocks. +# "blocks" is the message length in SHA512 blocks. ######################################################################## -ENTRY(sha512_transform_ssse3) +SYM_FUNC_START(sha512_transform_ssse3) cmp $0, msglen je nowork @@ -364,7 +367,7 @@ updateblock: nowork: ret -ENDPROC(sha512_transform_ssse3) +SYM_FUNC_END(sha512_transform_ssse3) ######################################################################## ### Binary Data diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 458356a3f124..1c444f41037c 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -39,13 +39,11 @@ #include <crypto/sha512_base.h> #include <asm/simd.h> -asmlinkage void sha512_transform_ssse3(u64 *digest, const char *data, - u64 rounds); - -typedef void (sha512_transform_fn)(u64 *digest, const char *data, u64 rounds); +asmlinkage void sha512_transform_ssse3(struct sha512_state *state, + const u8 *data, int blocks); static int sha512_update(struct shash_desc *desc, const u8 *data, - unsigned int len, sha512_transform_fn *sha512_xform) + unsigned int len, sha512_block_fn *sha512_xform) { struct sha512_state *sctx = shash_desc_ctx(desc); @@ -53,28 +51,29 @@ static int sha512_update(struct shash_desc *desc, const u8 *data, (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE) return crypto_sha512_update(desc, data, len); - /* make sure casting to sha512_block_fn() is safe */ + /* + * Make sure struct sha512_state begins directly with the SHA512 + * 512-bit internal state, as this is what the asm functions expect. + */ BUILD_BUG_ON(offsetof(struct sha512_state, state) != 0); kernel_fpu_begin(); - sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_xform); + sha512_base_do_update(desc, data, len, sha512_xform); kernel_fpu_end(); return 0; } static int sha512_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out, sha512_transform_fn *sha512_xform) + unsigned int len, u8 *out, sha512_block_fn *sha512_xform) { if (!crypto_simd_usable()) return crypto_sha512_finup(desc, data, len, out); kernel_fpu_begin(); if (len) - sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_xform); - sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_xform); + sha512_base_do_update(desc, data, len, sha512_xform); + sha512_base_do_finalize(desc, sha512_xform); kernel_fpu_end(); return sha512_base_finish(desc, out); @@ -144,8 +143,8 @@ static void unregister_sha512_ssse3(void) } #ifdef CONFIG_AS_AVX -asmlinkage void sha512_transform_avx(u64 *digest, const char *data, - u64 rounds); +asmlinkage void sha512_transform_avx(struct sha512_state *state, + const u8 *data, int blocks); static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { @@ -225,8 +224,8 @@ static inline void unregister_sha512_avx(void) { } #endif #if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) -asmlinkage void sha512_transform_rorx(u64 *digest, const char *data, - u64 rounds); +asmlinkage void sha512_transform_rorx(struct sha512_state *state, + const u8 *data, int blocks); static int sha512_avx2_update(struct shash_desc *desc, const u8 *data, unsigned int len) diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S index 698b8f2a56e2..a5151393bb2f 100644 --- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S @@ -234,7 +234,7 @@ vpxor x3, wkey, x3; .align 8 -__twofish_enc_blk8: +SYM_FUNC_START_LOCAL(__twofish_enc_blk8) /* input: * %rdi: ctx, CTX * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks @@ -273,10 +273,10 @@ __twofish_enc_blk8: outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2); ret; -ENDPROC(__twofish_enc_blk8) +SYM_FUNC_END(__twofish_enc_blk8) .align 8 -__twofish_dec_blk8: +SYM_FUNC_START_LOCAL(__twofish_dec_blk8) /* input: * %rdi: ctx, CTX * RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2: encrypted blocks @@ -313,9 +313,9 @@ __twofish_dec_blk8: outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2); ret; -ENDPROC(__twofish_dec_blk8) +SYM_FUNC_END(__twofish_dec_blk8) -ENTRY(twofish_ecb_enc_8way) +SYM_FUNC_START(twofish_ecb_enc_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -333,9 +333,9 @@ ENTRY(twofish_ecb_enc_8way) FRAME_END ret; -ENDPROC(twofish_ecb_enc_8way) +SYM_FUNC_END(twofish_ecb_enc_8way) -ENTRY(twofish_ecb_dec_8way) +SYM_FUNC_START(twofish_ecb_dec_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -353,9 +353,9 @@ ENTRY(twofish_ecb_dec_8way) FRAME_END ret; -ENDPROC(twofish_ecb_dec_8way) +SYM_FUNC_END(twofish_ecb_dec_8way) -ENTRY(twofish_cbc_dec_8way) +SYM_FUNC_START(twofish_cbc_dec_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -378,9 +378,9 @@ ENTRY(twofish_cbc_dec_8way) FRAME_END ret; -ENDPROC(twofish_cbc_dec_8way) +SYM_FUNC_END(twofish_cbc_dec_8way) -ENTRY(twofish_ctr_8way) +SYM_FUNC_START(twofish_ctr_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -405,9 +405,9 @@ ENTRY(twofish_ctr_8way) FRAME_END ret; -ENDPROC(twofish_ctr_8way) +SYM_FUNC_END(twofish_ctr_8way) -ENTRY(twofish_xts_enc_8way) +SYM_FUNC_START(twofish_xts_enc_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -429,9 +429,9 @@ ENTRY(twofish_xts_enc_8way) FRAME_END ret; -ENDPROC(twofish_xts_enc_8way) +SYM_FUNC_END(twofish_xts_enc_8way) -ENTRY(twofish_xts_dec_8way) +SYM_FUNC_START(twofish_xts_dec_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -453,4 +453,4 @@ ENTRY(twofish_xts_dec_8way) FRAME_END ret; -ENDPROC(twofish_xts_dec_8way) +SYM_FUNC_END(twofish_xts_dec_8way) diff --git a/arch/x86/crypto/twofish-i586-asm_32.S b/arch/x86/crypto/twofish-i586-asm_32.S index 290cc4e9a6fe..a6f09e4f2e46 100644 --- a/arch/x86/crypto/twofish-i586-asm_32.S +++ b/arch/x86/crypto/twofish-i586-asm_32.S @@ -207,7 +207,7 @@ xor %esi, d ## D;\ ror $1, d ## D; -ENTRY(twofish_enc_blk) +SYM_FUNC_START(twofish_enc_blk) push %ebp /* save registers according to calling convention*/ push %ebx push %esi @@ -261,9 +261,9 @@ ENTRY(twofish_enc_blk) pop %ebp mov $1, %eax ret -ENDPROC(twofish_enc_blk) +SYM_FUNC_END(twofish_enc_blk) -ENTRY(twofish_dec_blk) +SYM_FUNC_START(twofish_dec_blk) push %ebp /* save registers according to calling convention*/ push %ebx push %esi @@ -318,4 +318,4 @@ ENTRY(twofish_dec_blk) pop %ebp mov $1, %eax ret -ENDPROC(twofish_dec_blk) +SYM_FUNC_END(twofish_dec_blk) diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S index e495e07c7f1b..fc23552afe37 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S @@ -220,7 +220,7 @@ rorq $32, RAB2; \ outunpack3(mov, RIO, 2, RAB, 2); -ENTRY(__twofish_enc_blk_3way) +SYM_FUNC_START(__twofish_enc_blk_3way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -267,9 +267,9 @@ ENTRY(__twofish_enc_blk_3way) popq %r12; popq %r13; ret; -ENDPROC(__twofish_enc_blk_3way) +SYM_FUNC_END(__twofish_enc_blk_3way) -ENTRY(twofish_dec_blk_3way) +SYM_FUNC_START(twofish_dec_blk_3way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -302,4 +302,4 @@ ENTRY(twofish_dec_blk_3way) popq %r12; popq %r13; ret; -ENDPROC(twofish_dec_blk_3way) +SYM_FUNC_END(twofish_dec_blk_3way) diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S index ecef2cb9f43f..d2e56232494a 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64.S @@ -202,7 +202,7 @@ xor %r8d, d ## D;\ ror $1, d ## D; -ENTRY(twofish_enc_blk) +SYM_FUNC_START(twofish_enc_blk) pushq R1 /* %rdi contains the ctx address */ @@ -253,9 +253,9 @@ ENTRY(twofish_enc_blk) popq R1 movl $1,%eax ret -ENDPROC(twofish_enc_blk) +SYM_FUNC_END(twofish_enc_blk) -ENTRY(twofish_dec_blk) +SYM_FUNC_START(twofish_dec_blk) pushq R1 /* %rdi contains the ctx address */ @@ -305,4 +305,4 @@ ENTRY(twofish_dec_blk) popq R1 movl $1,%eax ret -ENDPROC(twofish_dec_blk) +SYM_FUNC_END(twofish_dec_blk) diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index 0dbf8e8b09d7..2dbc8ce3730e 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -22,20 +22,17 @@ #define TWOFISH_PARALLEL_BLOCKS 8 /* 8-way parallel cipher functions */ -asmlinkage void twofish_ecb_enc_8way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void twofish_ecb_dec_8way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void twofish_ecb_enc_8way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void twofish_ecb_dec_8way(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void twofish_cbc_dec_8way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void twofish_ctr_8way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void twofish_cbc_dec_8way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void twofish_ctr_8way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); -asmlinkage void twofish_xts_enc_8way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); -asmlinkage void twofish_xts_dec_8way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void twofish_xts_enc_8way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); +asmlinkage void twofish_xts_dec_8way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); static int twofish_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) @@ -43,22 +40,19 @@ static int twofish_setkey_skcipher(struct crypto_skcipher *tfm, return twofish_setkey(&tfm->base, key, keylen); } -static inline void twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src) +static inline void twofish_enc_blk_3way(const void *ctx, u8 *dst, const u8 *src) { __twofish_enc_blk_3way(ctx, dst, src, false); } -static void twofish_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv) +static void twofish_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, - GLUE_FUNC_CAST(twofish_enc_blk)); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, twofish_enc_blk); } -static void twofish_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv) +static void twofish_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv) { - glue_xts_crypt_128bit_one(ctx, dst, src, iv, - GLUE_FUNC_CAST(twofish_dec_blk)); + glue_xts_crypt_128bit_one(ctx, dst, src, iv, twofish_dec_blk); } struct twofish_xts_ctx { @@ -70,7 +64,6 @@ static int xts_twofish_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - u32 *flags = &tfm->base.crt_flags; int err; err = xts_verify_key(tfm, key, keylen); @@ -78,13 +71,12 @@ static int xts_twofish_setkey(struct crypto_skcipher *tfm, const u8 *key, return err; /* first half of xts-key is for crypt */ - err = __twofish_setkey(&ctx->crypt_ctx, key, keylen / 2, flags); + err = __twofish_setkey(&ctx->crypt_ctx, key, keylen / 2); if (err) return err; /* second half of xts-key is for tweak */ - return __twofish_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2, - flags); + return __twofish_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2); } static const struct common_glue_ctx twofish_enc = { @@ -93,13 +85,13 @@ static const struct common_glue_ctx twofish_enc = { .funcs = { { .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_ecb_enc_8way) } + .fn_u = { .ecb = twofish_ecb_enc_8way } }, { .num_blocks = 3, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk_3way) } + .fn_u = { .ecb = twofish_enc_blk_3way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk) } + .fn_u = { .ecb = twofish_enc_blk } } } }; @@ -109,13 +101,13 @@ static const struct common_glue_ctx twofish_ctr = { .funcs = { { .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(twofish_ctr_8way) } + .fn_u = { .ctr = twofish_ctr_8way } }, { .num_blocks = 3, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(twofish_enc_blk_ctr_3way) } + .fn_u = { .ctr = twofish_enc_blk_ctr_3way } }, { .num_blocks = 1, - .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(twofish_enc_blk_ctr) } + .fn_u = { .ctr = twofish_enc_blk_ctr } } } }; @@ -125,10 +117,10 @@ static const struct common_glue_ctx twofish_enc_xts = { .funcs = { { .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(twofish_xts_enc_8way) } + .fn_u = { .xts = twofish_xts_enc_8way } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(twofish_xts_enc) } + .fn_u = { .xts = twofish_xts_enc } } } }; @@ -138,13 +130,13 @@ static const struct common_glue_ctx twofish_dec = { .funcs = { { .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_ecb_dec_8way) } + .fn_u = { .ecb = twofish_ecb_dec_8way } }, { .num_blocks = 3, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_dec_blk_3way) } + .fn_u = { .ecb = twofish_dec_blk_3way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_dec_blk) } + .fn_u = { .ecb = twofish_dec_blk } } } }; @@ -154,13 +146,13 @@ static const struct common_glue_ctx twofish_dec_cbc = { .funcs = { { .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_cbc_dec_8way) } + .fn_u = { .cbc = twofish_cbc_dec_8way } }, { .num_blocks = 3, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_dec_blk_cbc_3way) } + .fn_u = { .cbc = twofish_dec_blk_cbc_3way } }, { .num_blocks = 1, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_dec_blk) } + .fn_u = { .cbc = twofish_dec_blk } } } }; @@ -170,10 +162,10 @@ static const struct common_glue_ctx twofish_dec_xts = { .funcs = { { .num_blocks = TWOFISH_PARALLEL_BLOCKS, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(twofish_xts_dec_8way) } + .fn_u = { .xts = twofish_xts_dec_8way } }, { .num_blocks = 1, - .fn_u = { .xts = GLUE_XTS_FUNC_CAST(twofish_xts_dec) } + .fn_u = { .xts = twofish_xts_dec } } } }; @@ -189,8 +181,7 @@ static int ecb_decrypt(struct skcipher_request *req) static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(twofish_enc_blk), - req); + return glue_cbc_encrypt_req_128bit(twofish_enc_blk, req); } static int cbc_decrypt(struct skcipher_request *req) @@ -208,9 +199,8 @@ static int xts_encrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&twofish_enc_xts, req, - XTS_TWEAK_CAST(twofish_enc_blk), - &ctx->tweak_ctx, &ctx->crypt_ctx); + return glue_xts_req_128bit(&twofish_enc_xts, req, twofish_enc_blk, + &ctx->tweak_ctx, &ctx->crypt_ctx, false); } static int xts_decrypt(struct skcipher_request *req) @@ -218,9 +208,8 @@ static int xts_decrypt(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct twofish_xts_ctx *ctx = crypto_skcipher_ctx(tfm); - return glue_xts_req_128bit(&twofish_dec_xts, req, - XTS_TWEAK_CAST(twofish_enc_blk), - &ctx->tweak_ctx, &ctx->crypt_ctx); + return glue_xts_req_128bit(&twofish_dec_xts, req, twofish_enc_blk, + &ctx->tweak_ctx, &ctx->crypt_ctx, true); } static struct skcipher_alg twofish_algs[] = { diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c index 1dc9e29f221e..768af6075479 100644 --- a/arch/x86/crypto/twofish_glue_3way.c +++ b/arch/x86/crypto/twofish_glue_3way.c @@ -25,21 +25,22 @@ static int twofish_setkey_skcipher(struct crypto_skcipher *tfm, return twofish_setkey(&tfm->base, key, keylen); } -static inline void twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src) +static inline void twofish_enc_blk_3way(const void *ctx, u8 *dst, const u8 *src) { __twofish_enc_blk_3way(ctx, dst, src, false); } -static inline void twofish_enc_blk_xor_3way(struct twofish_ctx *ctx, u8 *dst, +static inline void twofish_enc_blk_xor_3way(const void *ctx, u8 *dst, const u8 *src) { __twofish_enc_blk_3way(ctx, dst, src, true); } -void twofish_dec_blk_cbc_3way(void *ctx, u128 *dst, const u128 *src) +void twofish_dec_blk_cbc_3way(const void *ctx, u8 *d, const u8 *s) { u128 ivs[2]; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; ivs[0] = src[0]; ivs[1] = src[1]; @@ -51,9 +52,11 @@ void twofish_dec_blk_cbc_3way(void *ctx, u128 *dst, const u128 *src) } EXPORT_SYMBOL_GPL(twofish_dec_blk_cbc_3way); -void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv) +void twofish_enc_blk_ctr(const void *ctx, u8 *d, const u8 *s, le128 *iv) { be128 ctrblk; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; if (dst != src) *dst = *src; @@ -66,10 +69,11 @@ void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv) } EXPORT_SYMBOL_GPL(twofish_enc_blk_ctr); -void twofish_enc_blk_ctr_3way(void *ctx, u128 *dst, const u128 *src, - le128 *iv) +void twofish_enc_blk_ctr_3way(const void *ctx, u8 *d, const u8 *s, le128 *iv) { be128 ctrblks[3]; + u128 *dst = (u128 *)d; + const u128 *src = (const u128 *)s; if (dst != src) { dst[0] = src[0]; @@ -94,10 +98,10 @@ static const struct common_glue_ctx twofish_enc = { .funcs = { { .num_blocks = 3, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk_3way) } + .fn_u = { .ecb = twofish_enc_blk_3way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk) } + .fn_u = { .ecb = twofish_enc_blk } } } }; @@ -107,10 +111,10 @@ static const struct common_glue_ctx twofish_ctr = { .funcs = { { .num_blocks = 3, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk_ctr_3way) } + .fn_u = { .ctr = twofish_enc_blk_ctr_3way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk_ctr) } + .fn_u = { .ctr = twofish_enc_blk_ctr } } } }; @@ -120,10 +124,10 @@ static const struct common_glue_ctx twofish_dec = { .funcs = { { .num_blocks = 3, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_dec_blk_3way) } + .fn_u = { .ecb = twofish_dec_blk_3way } }, { .num_blocks = 1, - .fn_u = { .ecb = GLUE_FUNC_CAST(twofish_dec_blk) } + .fn_u = { .ecb = twofish_dec_blk } } } }; @@ -133,10 +137,10 @@ static const struct common_glue_ctx twofish_dec_cbc = { .funcs = { { .num_blocks = 3, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_dec_blk_cbc_3way) } + .fn_u = { .cbc = twofish_dec_blk_cbc_3way } }, { .num_blocks = 1, - .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_dec_blk) } + .fn_u = { .cbc = twofish_dec_blk } } } }; @@ -152,8 +156,7 @@ static int ecb_decrypt(struct skcipher_request *req) static int cbc_encrypt(struct skcipher_request *req) { - return glue_cbc_encrypt_req_128bit(GLUE_FUNC_CAST(twofish_enc_blk), - req); + return glue_cbc_encrypt_req_128bit(twofish_enc_blk, req); } static int cbc_decrypt(struct skcipher_request *req) diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 515c0ceeb4a3..0789e13ece90 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -354,7 +354,7 @@ For 32-bit we have the following conventions - kernel is built with .macro CALL_enter_from_user_mode #ifdef CONFIG_CONTEXT_TRACKING #ifdef CONFIG_JUMP_LABEL - STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_key, def=0 #endif call enter_from_user_mode .Lafter_call_\@: diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 536b574b6161..9747876980b5 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -33,6 +33,7 @@ #include <asm/cpufeature.h> #include <asm/fpu/api.h> #include <asm/nospec-branch.h> +#include <asm/io_bitmap.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -196,6 +197,9 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) /* Reload ti->flags; we may have rescheduled above. */ cached_flags = READ_ONCE(ti->flags); + if (unlikely(cached_flags & _TIF_IO_BITMAP)) + tss_update_io_bitmap(); + fpregs_assert_state_consistent(); if (unlikely(cached_flags & _TIF_NEED_FPU_LOAD)) switch_fpu_return(); @@ -285,15 +289,16 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs) if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) nr = syscall_trace_enter(regs); - /* - * NB: Native and x32 syscalls are dispatched from the same - * table. The only functional difference is the x32 bit in - * regs->orig_ax, which changes the behavior of some syscalls. - */ - nr &= __SYSCALL_MASK; if (likely(nr < NR_syscalls)) { nr = array_index_nospec(nr, NR_syscalls); regs->ax = sys_call_table[nr](regs); +#ifdef CONFIG_X86_X32_ABI + } else if (likely((nr & __X32_SYSCALL_BIT) && + (nr & ~__X32_SYSCALL_BIT) < X32_NR_syscalls)) { + nr = array_index_nospec(nr & ~__X32_SYSCALL_BIT, + X32_NR_syscalls); + regs->ax = x32_sys_call_table[nr](regs); +#endif } syscall_return_slowpath(regs); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 4f86928246e7..7e0560442538 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -63,7 +63,7 @@ * enough to patch inline, increasing performance. */ -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION # define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF #else # define preempt_stop(clobbers) @@ -172,7 +172,7 @@ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI .if \no_user_check == 0 /* coming from usermode? */ - testl $SEGMENT_RPL_MASK, PT_CS(%esp) + testl $USER_SEGMENT_RPL_MASK, PT_CS(%esp) jz .Lend_\@ .endif /* On user-cr3? */ @@ -205,64 +205,76 @@ #define CS_FROM_ENTRY_STACK (1 << 31) #define CS_FROM_USER_CR3 (1 << 30) #define CS_FROM_KERNEL (1 << 29) +#define CS_FROM_ESPFIX (1 << 28) .macro FIXUP_FRAME /* * The high bits of the CS dword (__csh) are used for CS_FROM_*. * Clear them in case hardware didn't do this for us. */ - andl $0x0000ffff, 3*4(%esp) + andl $0x0000ffff, 4*4(%esp) #ifdef CONFIG_VM86 - testl $X86_EFLAGS_VM, 4*4(%esp) + testl $X86_EFLAGS_VM, 5*4(%esp) jnz .Lfrom_usermode_no_fixup_\@ #endif - testl $SEGMENT_RPL_MASK, 3*4(%esp) + testl $USER_SEGMENT_RPL_MASK, 4*4(%esp) jnz .Lfrom_usermode_no_fixup_\@ - orl $CS_FROM_KERNEL, 3*4(%esp) + orl $CS_FROM_KERNEL, 4*4(%esp) /* * When we're here from kernel mode; the (exception) stack looks like: * - * 5*4(%esp) - <previous context> - * 4*4(%esp) - flags - * 3*4(%esp) - cs - * 2*4(%esp) - ip - * 1*4(%esp) - orig_eax - * 0*4(%esp) - gs / function + * 6*4(%esp) - <previous context> + * 5*4(%esp) - flags + * 4*4(%esp) - cs + * 3*4(%esp) - ip + * 2*4(%esp) - orig_eax + * 1*4(%esp) - gs / function + * 0*4(%esp) - fs * * Lets build a 5 entry IRET frame after that, such that struct pt_regs * is complete and in particular regs->sp is correct. This gives us - * the original 5 enties as gap: + * the original 6 enties as gap: * - * 12*4(%esp) - <previous context> - * 11*4(%esp) - gap / flags - * 10*4(%esp) - gap / cs - * 9*4(%esp) - gap / ip - * 8*4(%esp) - gap / orig_eax - * 7*4(%esp) - gap / gs / function - * 6*4(%esp) - ss - * 5*4(%esp) - sp - * 4*4(%esp) - flags - * 3*4(%esp) - cs - * 2*4(%esp) - ip - * 1*4(%esp) - orig_eax - * 0*4(%esp) - gs / function + * 14*4(%esp) - <previous context> + * 13*4(%esp) - gap / flags + * 12*4(%esp) - gap / cs + * 11*4(%esp) - gap / ip + * 10*4(%esp) - gap / orig_eax + * 9*4(%esp) - gap / gs / function + * 8*4(%esp) - gap / fs + * 7*4(%esp) - ss + * 6*4(%esp) - sp + * 5*4(%esp) - flags + * 4*4(%esp) - cs + * 3*4(%esp) - ip + * 2*4(%esp) - orig_eax + * 1*4(%esp) - gs / function + * 0*4(%esp) - fs */ pushl %ss # ss pushl %esp # sp (points at ss) - addl $6*4, (%esp) # point sp back at the previous context - pushl 6*4(%esp) # flags - pushl 6*4(%esp) # cs - pushl 6*4(%esp) # ip - pushl 6*4(%esp) # orig_eax - pushl 6*4(%esp) # gs / function + addl $7*4, (%esp) # point sp back at the previous context + pushl 7*4(%esp) # flags + pushl 7*4(%esp) # cs + pushl 7*4(%esp) # ip + pushl 7*4(%esp) # orig_eax + pushl 7*4(%esp) # gs / function + pushl 7*4(%esp) # fs .Lfrom_usermode_no_fixup_\@: .endm .macro IRET_FRAME + /* + * We're called with %ds, %es, %fs, and %gs from the interrupted + * frame, so we shouldn't use them. Also, we may be in ESPFIX + * mode and therefore have a nonzero SS base and an offset ESP, + * so any attempt to access the stack needs to use SS. (except for + * accesses through %esp, which automatically use SS.) + */ testl $CS_FROM_KERNEL, 1*4(%esp) jz .Lfinished_frame_\@ @@ -276,31 +288,40 @@ movl 5*4(%esp), %eax # (modified) regs->sp movl 4*4(%esp), %ecx # flags - movl %ecx, -4(%eax) + movl %ecx, %ss:-1*4(%eax) movl 3*4(%esp), %ecx # cs andl $0x0000ffff, %ecx - movl %ecx, -8(%eax) + movl %ecx, %ss:-2*4(%eax) movl 2*4(%esp), %ecx # ip - movl %ecx, -12(%eax) + movl %ecx, %ss:-3*4(%eax) movl 1*4(%esp), %ecx # eax - movl %ecx, -16(%eax) + movl %ecx, %ss:-4*4(%eax) popl %ecx - lea -16(%eax), %esp + lea -4*4(%eax), %esp popl %eax .Lfinished_frame_\@: .endm -.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 +.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 unwind_espfix=0 cld .if \skip_gs == 0 PUSH_GS .endif - FIXUP_FRAME pushl %fs + + pushl %eax + movl $(__KERNEL_PERCPU), %eax + movl %eax, %fs +.if \unwind_espfix > 0 + UNWIND_ESPFIX_STACK +.endif + popl %eax + + FIXUP_FRAME pushl %es pushl %ds pushl \pt_regs_ax @@ -313,8 +334,6 @@ movl $(__USER_DS), %edx movl %edx, %ds movl %edx, %es - movl $(__KERNEL_PERCPU), %edx - movl %edx, %fs .if \skip_gs == 0 SET_KERNEL_GS %edx .endif @@ -324,8 +343,8 @@ .endif .endm -.macro SAVE_ALL_NMI cr3_reg:req - SAVE_ALL +.macro SAVE_ALL_NMI cr3_reg:req unwind_espfix=0 + SAVE_ALL unwind_espfix=\unwind_espfix BUG_IF_WRONG_CR3 @@ -357,6 +376,7 @@ 2: popl %es 3: popl %fs POP_GS \pop + IRET_FRAME .pushsection .fixup, "ax" 4: movl $0, (%esp) jmp 1b @@ -395,7 +415,8 @@ .macro CHECK_AND_APPLY_ESPFIX #ifdef CONFIG_X86_ESPFIX32 -#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) +#define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8) +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX @@ -709,7 +730,7 @@ * %eax: prev task * %edx: next task */ -ENTRY(__switch_to_asm) +SYM_CODE_START(__switch_to_asm) /* * Save callee-saved registers * This must match the order in struct inactive_task_frame @@ -718,6 +739,11 @@ ENTRY(__switch_to_asm) pushl %ebx pushl %edi pushl %esi + /* + * Flags are saved to prevent AC leakage. This could go + * away if objtool would have 32bit support to verify + * the STAC/CLAC correctness. + */ pushfl /* switch stack */ @@ -740,15 +766,16 @@ ENTRY(__switch_to_asm) FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif - /* restore callee-saved registers */ + /* Restore flags or the incoming task to restore AC state. */ popfl + /* restore callee-saved registers */ popl %esi popl %edi popl %ebx popl %ebp jmp __switch_to -END(__switch_to_asm) +SYM_CODE_END(__switch_to_asm) /* * The unwinder expects the last frame on the stack to always be at the same @@ -757,7 +784,7 @@ END(__switch_to_asm) * asmlinkage function so its argument has to be pushed on the stack. This * wrapper creates a proper "end of stack" frame header before the call. */ -ENTRY(schedule_tail_wrapper) +SYM_FUNC_START(schedule_tail_wrapper) FRAME_BEGIN pushl %eax @@ -766,7 +793,7 @@ ENTRY(schedule_tail_wrapper) FRAME_END ret -ENDPROC(schedule_tail_wrapper) +SYM_FUNC_END(schedule_tail_wrapper) /* * A newly forked process directly context switches into this address. * @@ -774,7 +801,7 @@ ENDPROC(schedule_tail_wrapper) * ebx: kernel thread func (NULL for user thread) * edi: kernel thread arg */ -ENTRY(ret_from_fork) +SYM_CODE_START(ret_from_fork) call schedule_tail_wrapper testl %ebx, %ebx @@ -797,7 +824,7 @@ ENTRY(ret_from_fork) */ movl $0, PT_EAX(%esp) jmp 2b -END(ret_from_fork) +SYM_CODE_END(ret_from_fork) /* * Return to user mode is not as complex as all this looks, @@ -807,8 +834,7 @@ END(ret_from_fork) */ # userspace resumption stub bypassing syscall exit tracing - ALIGN -ret_from_exception: +SYM_CODE_START_LOCAL(ret_from_exception) preempt_stop(CLBR_ANY) ret_from_intr: #ifdef CONFIG_VM86 @@ -825,15 +851,14 @@ ret_from_intr: cmpl $USER_RPL, %eax jb restore_all_kernel # not returning to v8086 or userspace -ENTRY(resume_userspace) DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF movl %esp, %eax call prepare_exit_to_usermode jmp restore_all -END(ret_from_exception) +SYM_CODE_END(ret_from_exception) -GLOBAL(__begin_SYSENTER_singlestep_region) +SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE) /* * All code from here through __end_SYSENTER_singlestep_region is subject * to being single-stepped if a user program sets TF and executes SYSENTER. @@ -848,9 +873,10 @@ GLOBAL(__begin_SYSENTER_singlestep_region) * Xen doesn't set %esp to be precisely what the normal SYSENTER * entry point expects, so fix it up before using the normal path. */ -ENTRY(xen_sysenter_target) +SYM_CODE_START(xen_sysenter_target) addl $5*4, %esp /* remove xen-provided frame */ jmp .Lsysenter_past_esp +SYM_CODE_END(xen_sysenter_target) #endif /* @@ -885,7 +911,7 @@ ENTRY(xen_sysenter_target) * ebp user stack * 0(%ebp) arg6 */ -ENTRY(entry_SYSENTER_32) +SYM_FUNC_START(entry_SYSENTER_32) /* * On entry-stack with all userspace-regs live - save and * restore eflags and %eax to use it as scratch-reg for the cr3 @@ -1012,8 +1038,8 @@ ENTRY(entry_SYSENTER_32) pushl $X86_EFLAGS_FIXED popfl jmp .Lsysenter_flags_fixed -GLOBAL(__end_SYSENTER_singlestep_region) -ENDPROC(entry_SYSENTER_32) +SYM_ENTRY(__end_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE) +SYM_FUNC_END(entry_SYSENTER_32) /* * 32-bit legacy system call entry. @@ -1043,7 +1069,7 @@ ENDPROC(entry_SYSENTER_32) * edi arg5 * ebp arg6 */ -ENTRY(entry_INT80_32) +SYM_FUNC_START(entry_INT80_32) ASM_CLAC pushl %eax /* pt_regs->orig_ax */ @@ -1064,7 +1090,6 @@ ENTRY(entry_INT80_32) restore_all: TRACE_IRQS_IRET SWITCH_TO_ENTRY_STACK -.Lrestore_all_notrace: CHECK_AND_APPLY_ESPFIX .Lrestore_nocheck: /* Switch back to user CR3 */ @@ -1075,7 +1100,6 @@ restore_all: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code .Lirq_return: - IRET_FRAME /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization * when returning from IPI handler and when returning from @@ -1084,7 +1108,7 @@ restore_all: INTERRUPT_RETURN restore_all_kernel: -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION DISABLE_INTERRUPTS(CLBR_ANY) cmpl $0, PER_CPU_VAR(__preempt_count) jnz .Lno_preempt @@ -1100,7 +1124,7 @@ restore_all_kernel: jmp .Lirq_return .section .fixup, "ax" -ENTRY(iret_exc ) +SYM_CODE_START(iret_exc) pushl $0 # no error code pushl $do_iret_error @@ -1117,9 +1141,10 @@ ENTRY(iret_exc ) #endif jmp common_exception +SYM_CODE_END(iret_exc) .previous _ASM_EXTABLE(.Lirq_return, iret_exc) -ENDPROC(entry_INT80_32) +SYM_FUNC_END(entry_INT80_32) .macro FIXUP_ESPFIX_STACK /* @@ -1128,30 +1153,43 @@ ENDPROC(entry_INT80_32) * We can't call C functions using the ESPFIX stack. This code reads * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. + * + * We might be on user CR3 here, so percpu data is not mapped and we can't + * access the GDT through the percpu segment. Instead, use SGDT to find + * the cpu_entry_area alias of the GDT. */ #ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ - mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ - mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ + pushl %ecx + subl $2*4, %esp + sgdt (%esp) + movl 2(%esp), %ecx /* GDT address */ + /* + * Careful: ECX is a linear pointer, so we need to force base + * zero. %cs is the only known-linear segment we have right now. + */ + mov %cs:GDT_ESPFIX_OFFSET + 4(%ecx), %al /* bits 16..23 */ + mov %cs:GDT_ESPFIX_OFFSET + 7(%ecx), %ah /* bits 24..31 */ shl $16, %eax + addl $2*4, %esp + popl %ecx addl %esp, %eax /* the adjusted stack pointer */ pushl $__KERNEL_DS pushl %eax lss (%esp), %esp /* switch to the normal stack segment */ #endif .endm + .macro UNWIND_ESPFIX_STACK + /* It's safe to clobber %eax, all other regs need to be preserved */ #ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax - jne 27f - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es + jne .Lno_fixup_\@ /* switch to normal stack */ FIXUP_ESPFIX_STACK -27: +.Lno_fixup_\@: #endif .endm @@ -1160,7 +1198,7 @@ ENDPROC(entry_INT80_32) * We pack 1 stub into every 8-byte block. */ .align 8 -ENTRY(irq_entries_start) +SYM_CODE_START(irq_entries_start) vector=FIRST_EXTERNAL_VECTOR .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) pushl $(~vector+0x80) /* Note: always in signed byte range */ @@ -1168,11 +1206,11 @@ ENTRY(irq_entries_start) jmp common_interrupt .align 8 .endr -END(irq_entries_start) +SYM_CODE_END(irq_entries_start) #ifdef CONFIG_X86_LOCAL_APIC .align 8 -ENTRY(spurious_entries_start) +SYM_CODE_START(spurious_entries_start) vector=FIRST_SYSTEM_VECTOR .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR) pushl $(~vector+0x80) /* Note: always in signed byte range */ @@ -1180,9 +1218,9 @@ ENTRY(spurious_entries_start) jmp common_spurious .align 8 .endr -END(spurious_entries_start) +SYM_CODE_END(spurious_entries_start) -common_spurious: +SYM_CODE_START_LOCAL(common_spurious) ASM_CLAC addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */ SAVE_ALL switch_stacks=1 @@ -1191,7 +1229,7 @@ common_spurious: movl %esp, %eax call smp_spurious_interrupt jmp ret_from_intr -ENDPROC(common_spurious) +SYM_CODE_END(common_spurious) #endif /* @@ -1199,7 +1237,7 @@ ENDPROC(common_spurious) * so IRQ-flags tracing has to follow that: */ .p2align CONFIG_X86_L1_CACHE_SHIFT -common_interrupt: +SYM_CODE_START_LOCAL(common_interrupt) ASM_CLAC addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */ @@ -1209,10 +1247,10 @@ common_interrupt: movl %esp, %eax call do_IRQ jmp ret_from_intr -ENDPROC(common_interrupt) +SYM_CODE_END(common_interrupt) #define BUILD_INTERRUPT3(name, nr, fn) \ -ENTRY(name) \ +SYM_FUNC_START(name) \ ASM_CLAC; \ pushl $~(nr); \ SAVE_ALL switch_stacks=1; \ @@ -1221,7 +1259,7 @@ ENTRY(name) \ movl %esp, %eax; \ call fn; \ jmp ret_from_intr; \ -ENDPROC(name) +SYM_FUNC_END(name) #define BUILD_INTERRUPT(name, nr) \ BUILD_INTERRUPT3(name, nr, smp_##name); \ @@ -1229,14 +1267,14 @@ ENDPROC(name) /* The include is where all of the SMP etc. interrupts come from */ #include <asm/entry_arch.h> -ENTRY(coprocessor_error) +SYM_CODE_START(coprocessor_error) ASM_CLAC pushl $0 pushl $do_coprocessor_error jmp common_exception -END(coprocessor_error) +SYM_CODE_END(coprocessor_error) -ENTRY(simd_coprocessor_error) +SYM_CODE_START(simd_coprocessor_error) ASM_CLAC pushl $0 #ifdef CONFIG_X86_INVD_BUG @@ -1248,104 +1286,99 @@ ENTRY(simd_coprocessor_error) pushl $do_simd_coprocessor_error #endif jmp common_exception -END(simd_coprocessor_error) +SYM_CODE_END(simd_coprocessor_error) -ENTRY(device_not_available) +SYM_CODE_START(device_not_available) ASM_CLAC pushl $-1 # mark this as an int pushl $do_device_not_available jmp common_exception -END(device_not_available) +SYM_CODE_END(device_not_available) #ifdef CONFIG_PARAVIRT -ENTRY(native_iret) +SYM_CODE_START(native_iret) iret _ASM_EXTABLE(native_iret, iret_exc) -END(native_iret) +SYM_CODE_END(native_iret) #endif -ENTRY(overflow) +SYM_CODE_START(overflow) ASM_CLAC pushl $0 pushl $do_overflow jmp common_exception -END(overflow) +SYM_CODE_END(overflow) -ENTRY(bounds) +SYM_CODE_START(bounds) ASM_CLAC pushl $0 pushl $do_bounds jmp common_exception -END(bounds) +SYM_CODE_END(bounds) -ENTRY(invalid_op) +SYM_CODE_START(invalid_op) ASM_CLAC pushl $0 pushl $do_invalid_op jmp common_exception -END(invalid_op) +SYM_CODE_END(invalid_op) -ENTRY(coprocessor_segment_overrun) +SYM_CODE_START(coprocessor_segment_overrun) ASM_CLAC pushl $0 pushl $do_coprocessor_segment_overrun jmp common_exception -END(coprocessor_segment_overrun) +SYM_CODE_END(coprocessor_segment_overrun) -ENTRY(invalid_TSS) +SYM_CODE_START(invalid_TSS) ASM_CLAC pushl $do_invalid_TSS jmp common_exception -END(invalid_TSS) +SYM_CODE_END(invalid_TSS) -ENTRY(segment_not_present) +SYM_CODE_START(segment_not_present) ASM_CLAC pushl $do_segment_not_present jmp common_exception -END(segment_not_present) +SYM_CODE_END(segment_not_present) -ENTRY(stack_segment) +SYM_CODE_START(stack_segment) ASM_CLAC pushl $do_stack_segment jmp common_exception -END(stack_segment) +SYM_CODE_END(stack_segment) -ENTRY(alignment_check) +SYM_CODE_START(alignment_check) ASM_CLAC pushl $do_alignment_check jmp common_exception -END(alignment_check) +SYM_CODE_END(alignment_check) -ENTRY(divide_error) +SYM_CODE_START(divide_error) ASM_CLAC pushl $0 # no error code pushl $do_divide_error jmp common_exception -END(divide_error) +SYM_CODE_END(divide_error) #ifdef CONFIG_X86_MCE -ENTRY(machine_check) +SYM_CODE_START(machine_check) ASM_CLAC pushl $0 pushl machine_check_vector jmp common_exception -END(machine_check) +SYM_CODE_END(machine_check) #endif -ENTRY(spurious_interrupt_bug) +SYM_CODE_START(spurious_interrupt_bug) ASM_CLAC pushl $0 pushl $do_spurious_interrupt_bug jmp common_exception -END(spurious_interrupt_bug) +SYM_CODE_END(spurious_interrupt_bug) #ifdef CONFIG_XEN_PV -ENTRY(xen_hypervisor_callback) - pushl $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - ENCODE_FRAME_POINTER - TRACE_IRQS_OFF - +SYM_FUNC_START(xen_hypervisor_callback) /* * Check to see if we got the event in the critical * region in xen_iret_direct, after we've reenabled @@ -1353,22 +1386,23 @@ ENTRY(xen_hypervisor_callback) * iret instruction's behaviour where it delivers a * pending interrupt when enabling interrupts: */ - movl PT_EIP(%esp), %eax - cmpl $xen_iret_start_crit, %eax + cmpl $xen_iret_start_crit, (%esp) jb 1f - cmpl $xen_iret_end_crit, %eax + cmpl $xen_iret_end_crit, (%esp) jae 1f - - jmp xen_iret_crit_fixup - -ENTRY(xen_do_upcall) -1: mov %esp, %eax + call xen_iret_crit_fixup +1: + pushl $-1 /* orig_ax = -1 => not a system call */ + SAVE_ALL + ENCODE_FRAME_POINTER + TRACE_IRQS_OFF + mov %esp, %eax call xen_evtchn_do_upcall -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION call xen_maybe_preempt_hcall #endif jmp ret_from_intr -ENDPROC(xen_hypervisor_callback) +SYM_FUNC_END(xen_hypervisor_callback) /* * Hypervisor uses this for application faults while it executes. @@ -1382,7 +1416,7 @@ ENDPROC(xen_hypervisor_callback) * to pop the stack frame we end up in an infinite loop of failsafe callbacks. * We distinguish between categories by maintaining a status value in EAX. */ -ENTRY(xen_failsafe_callback) +SYM_FUNC_START(xen_failsafe_callback) pushl %eax movl $1, %eax 1: mov 4(%esp), %ds @@ -1419,7 +1453,7 @@ ENTRY(xen_failsafe_callback) _ASM_EXTABLE(2b, 7b) _ASM_EXTABLE(3b, 8b) _ASM_EXTABLE(4b, 9b) -ENDPROC(xen_failsafe_callback) +SYM_FUNC_END(xen_failsafe_callback) #endif /* CONFIG_XEN_PV */ #ifdef CONFIG_XEN_PVHVM @@ -1441,18 +1475,17 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR, #endif /* CONFIG_HYPERV */ -ENTRY(page_fault) +SYM_CODE_START(page_fault) ASM_CLAC pushl $do_page_fault jmp common_exception_read_cr2 -END(page_fault) +SYM_CODE_END(page_fault) -common_exception_read_cr2: +SYM_CODE_START_LOCAL_NOALIGN(common_exception_read_cr2) /* the function address is in %gs's slot on the stack */ - SAVE_ALL switch_stacks=1 skip_gs=1 + SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1 ENCODE_FRAME_POINTER - UNWIND_ESPFIX_STACK /* fixup %gs */ GS_TO_REG %ecx @@ -1470,13 +1503,12 @@ common_exception_read_cr2: movl %esp, %eax # pt_regs pointer CALL_NOSPEC %edi jmp ret_from_exception -END(common_exception_read_cr2) +SYM_CODE_END(common_exception_read_cr2) -common_exception: +SYM_CODE_START_LOCAL_NOALIGN(common_exception) /* the function address is in %gs's slot on the stack */ - SAVE_ALL switch_stacks=1 skip_gs=1 + SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1 ENCODE_FRAME_POINTER - UNWIND_ESPFIX_STACK /* fixup %gs */ GS_TO_REG %ecx @@ -1492,9 +1524,9 @@ common_exception: movl %esp, %eax # pt_regs pointer CALL_NOSPEC %edi jmp ret_from_exception -END(common_exception) +SYM_CODE_END(common_exception) -ENTRY(debug) +SYM_CODE_START(debug) /* * Entry from sysenter is now handled in common_exception */ @@ -1502,7 +1534,49 @@ ENTRY(debug) pushl $-1 # mark this as an int pushl $do_debug jmp common_exception -END(debug) +SYM_CODE_END(debug) + +#ifdef CONFIG_DOUBLEFAULT +SYM_CODE_START(double_fault) +1: + /* + * This is a task gate handler, not an interrupt gate handler. + * The error code is on the stack, but the stack is otherwise + * empty. Interrupts are off. Our state is sane with the following + * exceptions: + * + * - CR0.TS is set. "TS" literally means "task switched". + * - EFLAGS.NT is set because we're a "nested task". + * - The doublefault TSS has back_link set and has been marked busy. + * - TR points to the doublefault TSS and the normal TSS is busy. + * - CR3 is the normal kernel PGD. This would be delightful, except + * that the CPU didn't bother to save the old CR3 anywhere. This + * would make it very awkward to return back to the context we came + * from. + * + * The rest of EFLAGS is sanitized for us, so we don't need to + * worry about AC or DF. + * + * Don't even bother popping the error code. It's always zero, + * and ignoring it makes us a bit more robust against buggy + * hypervisor task gate implementations. + * + * We will manually undo the task switch instead of doing a + * task-switching IRET. + */ + + clts /* clear CR0.TS */ + pushl $X86_EFLAGS_FIXED + popfl /* clear EFLAGS.NT */ + + call doublefault_shim + + /* We don't support returning, so we have no IRET here. */ +1: + hlt + jmp 1b +SYM_CODE_END(double_fault) +#endif /* * NMI is doubly nasty. It can happen on the first instruction of @@ -1511,10 +1585,14 @@ END(debug) * switched stacks. We handle both conditions by simply checking whether we * interrupted kernel code running on the SYSENTER stack. */ -ENTRY(nmi) +SYM_CODE_START(nmi) ASM_CLAC #ifdef CONFIG_X86_ESPFIX32 + /* + * ESPFIX_SS is only ever set on the return to user path + * after we've switched to the entry stack. + */ pushl %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax @@ -1550,6 +1628,11 @@ ENTRY(nmi) movl %ebx, %esp .Lnmi_return: +#ifdef CONFIG_X86_ESPFIX32 + testl $CS_FROM_ESPFIX, PT_CS(%esp) + jnz .Lnmi_from_espfix +#endif + CHECK_AND_APPLY_ESPFIX RESTORE_ALL_NMI cr3_reg=%edi pop=4 jmp .Lirq_return @@ -1557,28 +1640,47 @@ ENTRY(nmi) #ifdef CONFIG_X86_ESPFIX32 .Lnmi_espfix_stack: /* - * create the pointer to lss back + * Create the pointer to LSS back */ pushl %ss pushl %esp addl $4, (%esp) - /* copy the iret frame of 12 bytes */ - .rept 3 - pushl 16(%esp) - .endr - pushl %eax - SAVE_ALL_NMI cr3_reg=%edi + + /* Copy the (short) IRET frame */ + pushl 4*4(%esp) # flags + pushl 4*4(%esp) # cs + pushl 4*4(%esp) # ip + + pushl %eax # orig_ax + + SAVE_ALL_NMI cr3_reg=%edi unwind_espfix=1 ENCODE_FRAME_POINTER - FIXUP_ESPFIX_STACK # %eax == %esp + + /* clear CS_FROM_KERNEL, set CS_FROM_ESPFIX */ + xorl $(CS_FROM_ESPFIX | CS_FROM_KERNEL), PT_CS(%esp) + xorl %edx, %edx # zero error code - call do_nmi + movl %esp, %eax # pt_regs pointer + jmp .Lnmi_from_sysenter_stack + +.Lnmi_from_espfix: RESTORE_ALL_NMI cr3_reg=%edi - lss 12+4(%esp), %esp # back to espfix stack + /* + * Because we cleared CS_FROM_KERNEL, IRET_FRAME 'forgot' to + * fix up the gap and long frame: + * + * 3 - original frame (exception) + * 2 - ESPFIX block (above) + * 6 - gap (FIXUP_FRAME) + * 5 - long frame (FIXUP_FRAME) + * 1 - orig_ax + */ + lss (1+5+6)*4(%esp), %esp # back to espfix stack jmp .Lirq_return #endif -END(nmi) +SYM_CODE_END(nmi) -ENTRY(int3) +SYM_CODE_START(int3) ASM_CLAC pushl $-1 # mark this as an int @@ -1589,22 +1691,22 @@ ENTRY(int3) movl %esp, %eax # pt_regs pointer call do_int3 jmp ret_from_exception -END(int3) +SYM_CODE_END(int3) -ENTRY(general_protection) +SYM_CODE_START(general_protection) pushl $do_general_protection jmp common_exception -END(general_protection) +SYM_CODE_END(general_protection) #ifdef CONFIG_KVM_GUEST -ENTRY(async_page_fault) +SYM_CODE_START(async_page_fault) ASM_CLAC pushl $do_async_page_fault jmp common_exception_read_cr2 -END(async_page_fault) +SYM_CODE_END(async_page_fault) #endif -ENTRY(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_do_exit) /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp @@ -1613,4 +1715,4 @@ ENTRY(rewind_stack_do_exit) call do_exit 1: jmp 1b -END(rewind_stack_do_exit) +SYM_CODE_END(rewind_stack_do_exit) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index be9ca198c581..f2bb91e87877 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -15,7 +15,7 @@ * at the top of the kernel process stack. * * Some macro usage: - * - ENTRY/END: Define functions in the symbol table. + * - SYM_FUNC_START/END:Define functions in the symbol table. * - TRACE_IRQ_*: Trace hardirq state for lock debugging. * - idtentry: Define exception entry points. */ @@ -46,11 +46,11 @@ .section .entry.text, "ax" #ifdef CONFIG_PARAVIRT -ENTRY(native_usergs_sysret64) +SYM_CODE_START(native_usergs_sysret64) UNWIND_HINT_EMPTY swapgs sysretq -END(native_usergs_sysret64) +SYM_CODE_END(native_usergs_sysret64) #endif /* CONFIG_PARAVIRT */ .macro TRACE_IRQS_FLAGS flags:req @@ -142,7 +142,7 @@ END(native_usergs_sysret64) * with them due to bugs in both AMD and Intel CPUs. */ -ENTRY(entry_SYSCALL_64) +SYM_CODE_START(entry_SYSCALL_64) UNWIND_HINT_EMPTY /* * Interrupts are off on entry. @@ -162,7 +162,7 @@ ENTRY(entry_SYSCALL_64) pushq %r11 /* pt_regs->flags */ pushq $__USER_CS /* pt_regs->cs */ pushq %rcx /* pt_regs->ip */ -GLOBAL(entry_SYSCALL_64_after_hwframe) +SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) pushq %rax /* pt_regs->orig_ax */ PUSH_AND_CLEAR_REGS rax=$-ENOSYS @@ -273,13 +273,13 @@ syscall_return_via_sysret: popq %rdi popq %rsp USERGS_SYSRET64 -END(entry_SYSCALL_64) +SYM_CODE_END(entry_SYSCALL_64) /* * %rdi: prev task * %rsi: next task */ -ENTRY(__switch_to_asm) +SYM_CODE_START(__switch_to_asm) UNWIND_HINT_FUNC /* * Save callee-saved registers @@ -321,7 +321,7 @@ ENTRY(__switch_to_asm) popq %rbp jmp __switch_to -END(__switch_to_asm) +SYM_CODE_END(__switch_to_asm) /* * A newly forked process directly context switches into this address. @@ -330,7 +330,7 @@ END(__switch_to_asm) * rbx: kernel thread func (NULL for user thread) * r12: kernel thread arg */ -ENTRY(ret_from_fork) +SYM_CODE_START(ret_from_fork) UNWIND_HINT_EMPTY movq %rax, %rdi call schedule_tail /* rdi: 'prev' task parameter */ @@ -357,14 +357,14 @@ ENTRY(ret_from_fork) */ movq $0, RAX(%rsp) jmp 2b -END(ret_from_fork) +SYM_CODE_END(ret_from_fork) /* * Build the entry stubs with some assembler magic. * We pack 1 stub into every 8-byte block. */ .align 8 -ENTRY(irq_entries_start) +SYM_CODE_START(irq_entries_start) vector=FIRST_EXTERNAL_VECTOR .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) UNWIND_HINT_IRET_REGS @@ -373,10 +373,10 @@ ENTRY(irq_entries_start) .align 8 vector=vector+1 .endr -END(irq_entries_start) +SYM_CODE_END(irq_entries_start) .align 8 -ENTRY(spurious_entries_start) +SYM_CODE_START(spurious_entries_start) vector=FIRST_SYSTEM_VECTOR .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR) UNWIND_HINT_IRET_REGS @@ -385,7 +385,7 @@ ENTRY(spurious_entries_start) .align 8 vector=vector+1 .endr -END(spurious_entries_start) +SYM_CODE_END(spurious_entries_start) .macro DEBUG_ENTRY_ASSERT_IRQS_OFF #ifdef CONFIG_DEBUG_ENTRY @@ -511,7 +511,7 @@ END(spurious_entries_start) * | return address | * +----------------------------------------------------+ */ -ENTRY(interrupt_entry) +SYM_CODE_START(interrupt_entry) UNWIND_HINT_FUNC ASM_CLAC cld @@ -579,7 +579,7 @@ ENTRY(interrupt_entry) TRACE_IRQS_OFF ret -END(interrupt_entry) +SYM_CODE_END(interrupt_entry) _ASM_NOKPROBE(interrupt_entry) @@ -589,18 +589,18 @@ _ASM_NOKPROBE(interrupt_entry) * The interrupt stubs push (~vector+0x80) onto the stack and * then jump to common_spurious/interrupt. */ -common_spurious: +SYM_CODE_START_LOCAL(common_spurious) addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ call interrupt_entry UNWIND_HINT_REGS indirect=1 call smp_spurious_interrupt /* rdi points to pt_regs */ jmp ret_from_intr -END(common_spurious) +SYM_CODE_END(common_spurious) _ASM_NOKPROBE(common_spurious) /* common_interrupt is a hotpath. Align it */ .p2align CONFIG_X86_L1_CACHE_SHIFT -common_interrupt: +SYM_CODE_START_LOCAL(common_interrupt) addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ call interrupt_entry UNWIND_HINT_REGS indirect=1 @@ -616,12 +616,12 @@ ret_from_intr: jz retint_kernel /* Interrupt came from user space */ -GLOBAL(retint_user) +.Lretint_user: mov %rsp,%rdi call prepare_exit_to_usermode TRACE_IRQS_IRETQ -GLOBAL(swapgs_restore_regs_and_return_to_usermode) +SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates user mode. */ testb $3, CS(%rsp) @@ -664,7 +664,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) /* Returning to kernel space */ retint_kernel: -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* Interrupts are off */ /* Check if we need preemption */ btl $9, EFLAGS(%rsp) /* were interrupts off? */ @@ -679,7 +679,7 @@ retint_kernel: */ TRACE_IRQS_IRETQ -GLOBAL(restore_regs_and_return_to_kernel) +SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL) #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates kernel mode. */ testb $3, CS(%rsp) @@ -695,7 +695,7 @@ GLOBAL(restore_regs_and_return_to_kernel) */ INTERRUPT_RETURN -ENTRY(native_iret) +SYM_INNER_LABEL_ALIGN(native_iret, SYM_L_GLOBAL) UNWIND_HINT_IRET_REGS /* * Are we returning to a stack segment from the LDT? Note: in @@ -706,8 +706,7 @@ ENTRY(native_iret) jnz native_irq_return_ldt #endif -.global native_irq_return_iret -native_irq_return_iret: +SYM_INNER_LABEL(native_irq_return_iret, SYM_L_GLOBAL) /* * This may fault. Non-paranoid faults on return to userspace are * handled by fixup_bad_iret. These include #SS, #GP, and #NP. @@ -789,14 +788,14 @@ native_irq_return_ldt: */ jmp native_irq_return_iret #endif -END(common_interrupt) +SYM_CODE_END(common_interrupt) _ASM_NOKPROBE(common_interrupt) /* * APIC interrupts. */ .macro apicinterrupt3 num sym do_sym -ENTRY(\sym) +SYM_CODE_START(\sym) UNWIND_HINT_IRET_REGS pushq $~(\num) .Lcommon_\sym: @@ -804,7 +803,7 @@ ENTRY(\sym) UNWIND_HINT_REGS indirect=1 call \do_sym /* rdi points to pt_regs */ jmp ret_from_intr -END(\sym) +SYM_CODE_END(\sym) _ASM_NOKPROBE(\sym) .endm @@ -969,7 +968,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS. */ .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0 read_cr2=0 -ENTRY(\sym) +SYM_CODE_START(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 /* Sanity check */ @@ -1019,7 +1018,7 @@ ENTRY(\sym) .endif _ASM_NOKPROBE(\sym) -END(\sym) +SYM_CODE_END(\sym) .endm idtentry divide_error do_divide_error has_error_code=0 @@ -1041,7 +1040,7 @@ idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 * Reload gs selector with exception handling * edi: new selector */ -ENTRY(native_load_gs_index) +SYM_FUNC_START(native_load_gs_index) FRAME_BEGIN pushfq DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) @@ -1055,13 +1054,13 @@ ENTRY(native_load_gs_index) popfq FRAME_END ret -ENDPROC(native_load_gs_index) +SYM_FUNC_END(native_load_gs_index) EXPORT_SYMBOL(native_load_gs_index) - _ASM_EXTABLE(.Lgs_change, bad_gs) + _ASM_EXTABLE(.Lgs_change, .Lbad_gs) .section .fixup, "ax" /* running with kernelgs */ -bad_gs: +SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs) SWAPGS /* switch back to user gs */ .macro ZAP_GS /* This can't be a string because the preprocessor needs to see it. */ @@ -1072,10 +1071,11 @@ bad_gs: xorl %eax, %eax movl %eax, %gs jmp 2b +SYM_CODE_END(.Lbad_gs) .previous /* Call softirq on interrupt stack. Interrupts are off. */ -ENTRY(do_softirq_own_stack) +SYM_FUNC_START(do_softirq_own_stack) pushq %rbp mov %rsp, %rbp ENTER_IRQ_STACK regs=0 old_rsp=%r11 @@ -1083,7 +1083,7 @@ ENTRY(do_softirq_own_stack) LEAVE_IRQ_STACK regs=0 leaveq ret -ENDPROC(do_softirq_own_stack) +SYM_FUNC_END(do_softirq_own_stack) #ifdef CONFIG_XEN_PV idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 @@ -1101,7 +1101,8 @@ idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 * existing activation in its critical region -- if so, we pop the current * activation and restart the handler using the previous one. */ -ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */ +/* do_hypervisor_callback(struct *pt_regs) */ +SYM_CODE_START_LOCAL(xen_do_hypervisor_callback) /* * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will @@ -1115,11 +1116,11 @@ ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */ call xen_evtchn_do_upcall LEAVE_IRQ_STACK -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION call xen_maybe_preempt_hcall #endif jmp error_exit -END(xen_do_hypervisor_callback) +SYM_CODE_END(xen_do_hypervisor_callback) /* * Hypervisor uses this for application faults while it executes. @@ -1134,7 +1135,7 @@ END(xen_do_hypervisor_callback) * We distinguish between categories by comparing each saved segment register * with its current contents: any discrepancy means we in category 1. */ -ENTRY(xen_failsafe_callback) +SYM_CODE_START(xen_failsafe_callback) UNWIND_HINT_EMPTY movl %ds, %ecx cmpw %cx, 0x10(%rsp) @@ -1164,7 +1165,7 @@ ENTRY(xen_failsafe_callback) PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER jmp error_exit -END(xen_failsafe_callback) +SYM_CODE_END(xen_failsafe_callback) #endif /* CONFIG_XEN_PV */ #ifdef CONFIG_XEN_PVHVM @@ -1214,7 +1215,7 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 * Use slow, but surefire "are we in kernel?" check. * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ -ENTRY(paranoid_entry) +SYM_CODE_START_LOCAL(paranoid_entry) UNWIND_HINT_FUNC cld PUSH_AND_CLEAR_REGS save_ret=1 @@ -1248,7 +1249,7 @@ ENTRY(paranoid_entry) FENCE_SWAPGS_KERNEL_ENTRY ret -END(paranoid_entry) +SYM_CODE_END(paranoid_entry) /* * "Paranoid" exit path from exception stack. This is invoked @@ -1262,7 +1263,7 @@ END(paranoid_entry) * * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ -ENTRY(paranoid_exit) +SYM_CODE_START_LOCAL(paranoid_exit) UNWIND_HINT_REGS DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF_DEBUG @@ -1272,19 +1273,18 @@ ENTRY(paranoid_exit) /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 SWAPGS_UNSAFE_STACK - jmp .Lparanoid_exit_restore + jmp restore_regs_and_return_to_kernel .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 -.Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel -END(paranoid_exit) +SYM_CODE_END(paranoid_exit) /* * Save all registers in pt_regs, and switch GS if needed. */ -ENTRY(error_entry) +SYM_CODE_START_LOCAL(error_entry) UNWIND_HINT_FUNC cld PUSH_AND_CLEAR_REGS save_ret=1 @@ -1364,16 +1364,16 @@ ENTRY(error_entry) call fixup_bad_iret mov %rax, %rsp jmp .Lerror_entry_from_usermode_after_swapgs -END(error_entry) +SYM_CODE_END(error_entry) -ENTRY(error_exit) +SYM_CODE_START_LOCAL(error_exit) UNWIND_HINT_REGS DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF testb $3, CS(%rsp) jz retint_kernel - jmp retint_user -END(error_exit) + jmp .Lretint_user +SYM_CODE_END(error_exit) /* * Runs on exception stack. Xen PV does not go through this path at all, @@ -1383,7 +1383,7 @@ END(error_exit) * %r14: Used to save/restore the CR3 of the interrupted context * when PAGE_TABLE_ISOLATION is in use. Do not clobber. */ -ENTRY(nmi) +SYM_CODE_START(nmi) UNWIND_HINT_IRET_REGS /* @@ -1718,21 +1718,21 @@ nmi_restore: * about espfix64 on the way back to kernel mode. */ iretq -END(nmi) +SYM_CODE_END(nmi) #ifndef CONFIG_IA32_EMULATION /* * This handles SYSCALL from 32-bit code. There is no way to program * MSRs to fully disable 32-bit SYSCALL. */ -ENTRY(ignore_sysret) +SYM_CODE_START(ignore_sysret) UNWIND_HINT_EMPTY mov $-ENOSYS, %eax - sysret -END(ignore_sysret) + sysretl +SYM_CODE_END(ignore_sysret) #endif -ENTRY(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_do_exit) UNWIND_HINT_FUNC /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp @@ -1742,4 +1742,4 @@ ENTRY(rewind_stack_do_exit) UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE call do_exit -END(rewind_stack_do_exit) +SYM_CODE_END(rewind_stack_do_exit) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 39913770a44d..f1d3ccae5dd5 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -46,7 +46,7 @@ * ebp user stack * 0(%ebp) arg6 */ -ENTRY(entry_SYSENTER_compat) +SYM_FUNC_START(entry_SYSENTER_compat) /* Interrupts are off on entry. */ SWAPGS @@ -146,8 +146,8 @@ ENTRY(entry_SYSENTER_compat) pushq $X86_EFLAGS_FIXED popfq jmp .Lsysenter_flags_fixed -GLOBAL(__end_entry_SYSENTER_compat) -ENDPROC(entry_SYSENTER_compat) +SYM_INNER_LABEL(__end_entry_SYSENTER_compat, SYM_L_GLOBAL) +SYM_FUNC_END(entry_SYSENTER_compat) /* * 32-bit SYSCALL entry. @@ -196,7 +196,7 @@ ENDPROC(entry_SYSENTER_compat) * esp user stack * 0(%esp) arg6 */ -ENTRY(entry_SYSCALL_compat) +SYM_CODE_START(entry_SYSCALL_compat) /* Interrupts are off on entry. */ swapgs @@ -215,7 +215,7 @@ ENTRY(entry_SYSCALL_compat) pushq %r11 /* pt_regs->flags */ pushq $__USER32_CS /* pt_regs->cs */ pushq %rcx /* pt_regs->ip */ -GLOBAL(entry_SYSCALL_compat_after_hwframe) +SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) movl %eax, %eax /* discard orig_ax high bits */ pushq %rax /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ @@ -311,7 +311,7 @@ sysret32_from_system_call: xorl %r10d, %r10d swapgs sysretl -END(entry_SYSCALL_compat) +SYM_CODE_END(entry_SYSCALL_compat) /* * 32-bit legacy system call entry. @@ -339,7 +339,7 @@ END(entry_SYSCALL_compat) * edi arg5 * ebp arg6 */ -ENTRY(entry_INT80_compat) +SYM_CODE_START(entry_INT80_compat) /* * Interrupts are off on entry. */ @@ -416,4 +416,4 @@ ENTRY(entry_INT80_compat) /* Go back to user mode. */ TRACE_IRQS_ON jmp swapgs_restore_regs_and_return_to_usermode -END(entry_INT80_compat) +SYM_CODE_END(entry_INT80_compat) diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index aa3336a7cb15..7d17b3addbbb 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -10,13 +10,11 @@ #ifdef CONFIG_IA32_EMULATION /* On X86_64, we use struct pt_regs * to pass parameters to syscalls */ #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); - -/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */ -extern asmlinkage long sys_ni_syscall(const struct pt_regs *); - +#define __sys_ni_syscall __ia32_sys_ni_syscall #else /* CONFIG_IA32_EMULATION */ #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __sys_ni_syscall sys_ni_syscall #endif /* CONFIG_IA32_EMULATION */ #include <asm/syscalls_32.h> @@ -29,6 +27,6 @@ __visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_syscall_compat_max] = &sys_ni_syscall, + [0 ... __NR_syscall_compat_max] = &__sys_ni_syscall, #include <asm/syscalls_32.h> }; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index d5252bc1e380..adf619a856e8 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -4,22 +4,53 @@ #include <linux/linkage.h> #include <linux/sys.h> #include <linux/cache.h> +#include <linux/syscalls.h> #include <asm/asm-offsets.h> #include <asm/syscall.h> -/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */ -extern asmlinkage long sys_ni_syscall(const struct pt_regs *); +extern asmlinkage long sys_ni_syscall(void); + +SYSCALL_DEFINE0(ni_syscall) +{ + return sys_ni_syscall(); +} + #define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); +#define __SYSCALL_X32(nr, sym, qual) __SYSCALL_64(nr, sym, qual) #include <asm/syscalls_64.h> #undef __SYSCALL_64 +#undef __SYSCALL_X32 #define __SYSCALL_64(nr, sym, qual) [nr] = sym, +#define __SYSCALL_X32(nr, sym, qual) asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_syscall_max] = &sys_ni_syscall, + [0 ... __NR_syscall_max] = &__x64_sys_ni_syscall, +#include <asm/syscalls_64.h> +}; + +#undef __SYSCALL_64 +#undef __SYSCALL_X32 + +#ifdef CONFIG_X86_X32_ABI + +#define __SYSCALL_64(nr, sym, qual) +#define __SYSCALL_X32(nr, sym, qual) [nr] = sym, + +asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_syscall_x32_max+1] = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_x32_max] = &__x64_sys_ni_syscall, #include <asm/syscalls_64.h> }; + +#undef __SYSCALL_64 +#undef __SYSCALL_X32 + +#endif diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index c00019abd076..c17cb77eb150 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -124,13 +124,13 @@ 110 i386 iopl sys_iopl __ia32_sys_iopl 111 i386 vhangup sys_vhangup __ia32_sys_vhangup 112 i386 idle -113 i386 vm86old sys_vm86old sys_ni_syscall +113 i386 vm86old sys_vm86old __ia32_sys_ni_syscall 114 i386 wait4 sys_wait4 __ia32_compat_sys_wait4 115 i386 swapoff sys_swapoff __ia32_sys_swapoff 116 i386 sysinfo sys_sysinfo __ia32_compat_sys_sysinfo 117 i386 ipc sys_ipc __ia32_compat_sys_ipc 118 i386 fsync sys_fsync __ia32_sys_fsync -119 i386 sigreturn sys_sigreturn sys32_sigreturn +119 i386 sigreturn sys_sigreturn __ia32_compat_sys_sigreturn 120 i386 clone sys_clone __ia32_compat_sys_x86_clone 121 i386 setdomainname sys_setdomainname __ia32_sys_setdomainname 122 i386 uname sys_newuname __ia32_sys_newuname @@ -177,20 +177,20 @@ 163 i386 mremap sys_mremap __ia32_sys_mremap 164 i386 setresuid sys_setresuid16 __ia32_sys_setresuid16 165 i386 getresuid sys_getresuid16 __ia32_sys_getresuid16 -166 i386 vm86 sys_vm86 sys_ni_syscall +166 i386 vm86 sys_vm86 __ia32_sys_ni_syscall 167 i386 query_module 168 i386 poll sys_poll __ia32_sys_poll 169 i386 nfsservctl 170 i386 setresgid sys_setresgid16 __ia32_sys_setresgid16 171 i386 getresgid sys_getresgid16 __ia32_sys_getresgid16 172 i386 prctl sys_prctl __ia32_sys_prctl -173 i386 rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn +173 i386 rt_sigreturn sys_rt_sigreturn __ia32_compat_sys_rt_sigreturn 174 i386 rt_sigaction sys_rt_sigaction __ia32_compat_sys_rt_sigaction -175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_sys_rt_sigprocmask +175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_compat_sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending __ia32_compat_sys_rt_sigpending 177 i386 rt_sigtimedwait sys_rt_sigtimedwait_time32 __ia32_compat_sys_rt_sigtimedwait_time32 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo __ia32_compat_sys_rt_sigqueueinfo -179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_sys_rt_sigsuspend +179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_compat_sys_rt_sigsuspend 180 i386 pread64 sys_pread64 __ia32_compat_sys_x86_pread 181 i386 pwrite64 sys_pwrite64 __ia32_compat_sys_x86_pwrite 182 i386 chown sys_chown16 __ia32_sys_chown16 @@ -440,3 +440,5 @@ 433 i386 fspick sys_fspick __ia32_sys_fspick 434 i386 pidfd_open sys_pidfd_open __ia32_sys_pidfd_open 435 i386 clone3 sys_clone3 __ia32_sys_clone3 +437 i386 openat2 sys_openat2 __ia32_sys_openat2 +438 i386 pidfd_getfd sys_pidfd_getfd __ia32_sys_pidfd_getfd diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index c29976eca4a8..44d510bc9b78 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -357,6 +357,8 @@ 433 common fspick __x64_sys_fspick 434 common pidfd_open __x64_sys_pidfd_open 435 common clone3 __x64_sys_clone3/ptregs +437 common openat2 __x64_sys_openat2 +438 common pidfd_getfd __x64_sys_pidfd_getfd # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh index 94fcd1951aca..1af2be39e7d9 100644 --- a/arch/x86/entry/syscalls/syscalltbl.sh +++ b/arch/x86/entry/syscalls/syscalltbl.sh @@ -1,13 +1,13 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 in="$1" out="$2" syscall_macro() { - abi="$1" - nr="$2" - entry="$3" + local abi="$1" + local nr="$2" + local entry="$3" # Entry can be either just a function name or "function/qualifier" real_entry="${entry%%/*}" @@ -21,14 +21,14 @@ syscall_macro() { } emit() { - abi="$1" - nr="$2" - entry="$3" - compat="$4" - umlentry="" + local abi="$1" + local nr="$2" + local entry="$3" + local compat="$4" + local umlentry="" - if [ "$abi" = "64" -a -n "$compat" ]; then - echo "a compat entry for a 64-bit syscall makes no sense" >&2 + if [ "$abi" != "I386" -a -n "$compat" ]; then + echo "a compat entry ($abi: $compat) for a 64-bit syscall makes no sense" >&2 exit 1 fi @@ -62,14 +62,17 @@ grep '^[0-9]' "$in" | sort -n | ( while read nr abi name entry compat; do abi=`echo "$abi" | tr '[a-z]' '[A-Z]'` if [ "$abi" = "COMMON" -o "$abi" = "64" ]; then - # COMMON is the same as 64, except that we don't expect X32 - # programs to use it. Our expectation has nothing to do with - # any generated code, so treat them the same. emit 64 "$nr" "$entry" "$compat" + if [ "$abi" = "COMMON" ]; then + # COMMON means that this syscall exists in the same form for + # 64-bit and X32. + echo "#ifdef CONFIG_X86_X32_ABI" + emit X32 "$nr" "$entry" "$compat" + echo "#endif" + fi elif [ "$abi" = "X32" ]; then - # X32 is equivalent to 64 on an X32-compatible kernel. echo "#ifdef CONFIG_X86_X32_ABI" - emit 64 "$nr" "$entry" "$compat" + emit X32 "$nr" "$entry" "$compat" echo "#endif" elif [ "$abi" = "I386" ]; then emit "$abi" "$nr" "$entry" "$compat" diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index cb3464525b37..e010d4ae11f1 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -10,8 +10,7 @@ /* put return address in eax (arg1) */ .macro THUNK name, func, put_ret_addr_in_eax=0 - .globl \name -\name: +SYM_CODE_START_NOALIGN(\name) pushl %eax pushl %ecx pushl %edx @@ -27,6 +26,7 @@ popl %eax ret _ASM_NOKPROBE(\name) +SYM_CODE_END(\name) .endm #ifdef CONFIG_TRACE_IRQFLAGS @@ -34,7 +34,7 @@ THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1 #endif -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION THUNK ___preempt_schedule, preempt_schedule THUNK ___preempt_schedule_notrace, preempt_schedule_notrace EXPORT_SYMBOL(___preempt_schedule) diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index cc20465b2867..c5c3b6e86e62 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -12,7 +12,7 @@ /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ .macro THUNK name, func, put_ret_addr_in_rdi=0 - ENTRY(\name) +SYM_FUNC_START_NOALIGN(\name) pushq %rbp movq %rsp, %rbp @@ -33,7 +33,7 @@ call \func jmp .L_restore - ENDPROC(\name) +SYM_FUNC_END(\name) _ASM_NOKPROBE(\name) .endm @@ -46,7 +46,7 @@ THUNK lockdep_sys_exit_thunk,lockdep_sys_exit #endif -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION THUNK ___preempt_schedule, preempt_schedule THUNK ___preempt_schedule_notrace, preempt_schedule_notrace EXPORT_SYMBOL(___preempt_schedule) @@ -55,8 +55,8 @@ #if defined(CONFIG_TRACE_IRQFLAGS) \ || defined(CONFIG_DEBUG_LOCK_ALLOC) \ - || defined(CONFIG_PREEMPT) -.L_restore: + || defined(CONFIG_PREEMPTION) +SYM_CODE_START_LOCAL_NOALIGN(.L_restore) popq %r11 popq %r10 popq %r9 @@ -69,4 +69,5 @@ popq %rbp ret _ASM_NOKPROBE(.L_restore) +SYM_CODE_END(.L_restore) #endif diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 8df549138193..433a1259f61d 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -59,7 +59,7 @@ $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso_and_check) HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi -hostprogs-y += vdso2c +hostprogs += vdso2c quiet_cmd_vdso2c = VDSO2C $@ cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@ @@ -87,10 +87,9 @@ $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. # -CFLAGS_REMOVE_vdso-note.o = -pg CFLAGS_REMOVE_vclock_gettime.o = -pg +CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg CFLAGS_REMOVE_vgetcpu.o = -pg -CFLAGS_REMOVE_vvar.o = -pg # # X32 processes use x32 vDSO to access 64bit kernel data. @@ -128,7 +127,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE $(call if_changed,vdso_and_check) -CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) +CPPFLAGS_vdso32/vdso32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1 targets += vdso32/vdso32.lds diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index d9ff616bb0f6..7d70935b6758 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -15,7 +15,7 @@ #include "../../../../lib/vdso/gettimeofday.c" extern int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); -extern time_t __vdso_time(time_t *t); +extern __kernel_old_time_t __vdso_time(__kernel_old_time_t *t); int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { @@ -25,12 +25,12 @@ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) int gettimeofday(struct __kernel_old_timeval *, struct timezone *) __attribute__((weak, alias("__vdso_gettimeofday"))); -time_t __vdso_time(time_t *t) +__kernel_old_time_t __vdso_time(__kernel_old_time_t *t) { return __cvdso_time(t); } -time_t time(time_t *t) __attribute__((weak, alias("__vdso_time"))); +__kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time"))); #if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64) diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index 93c6dc7812d0..ea7e0155c604 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -16,18 +16,23 @@ SECTIONS * segment. */ - vvar_start = . - 3 * PAGE_SIZE; - vvar_page = vvar_start; + vvar_start = . - 4 * PAGE_SIZE; + vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ #define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset; -#define __VVAR_KERNEL_LDS #include <asm/vvar.h> -#undef __VVAR_KERNEL_LDS #undef EMIT_VVAR pvclock_page = vvar_start + PAGE_SIZE; hvclock_page = vvar_start + 2 * PAGE_SIZE; + timens_page = vvar_start + 3 * PAGE_SIZE; + +#undef _ASM_X86_VVAR_H + /* Place all vvars in timens too at the offsets in asm/vvar.h. */ +#define EMIT_VVAR(name, offset) timens_ ## name = timens_page + offset; +#include <asm/vvar.h> +#undef EMIT_VVAR . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 3a4d8d4d39f8..3842873b3ae3 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -75,12 +75,14 @@ enum { sym_vvar_page, sym_pvclock_page, sym_hvclock_page, + sym_timens_page, }; const int special_pages[] = { sym_vvar_page, sym_pvclock_page, sym_hvclock_page, + sym_timens_page, }; struct vdso_sym { @@ -93,6 +95,7 @@ struct vdso_sym required_syms[] = { [sym_vvar_page] = {"vvar_page", true}, [sym_pvclock_page] = {"pvclock_page", true}, [sym_hvclock_page] = {"hvclock_page", true}, + [sym_timens_page] = {"timens_page", true}, {"VDSO32_NOTE_MASK", true}, {"__kernel_vsyscall", true}, {"__kernel_sigreturn", true}, diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 240626e7f55a..43842fade8fa 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -11,6 +11,7 @@ #include <linux/smp.h> #include <linux/kernel.h> #include <linux/mm_types.h> +#include <linux/elf.h> #include <asm/processor.h> #include <asm/vdso.h> diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index 263d7433dea8..de1fff7188aa 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -62,7 +62,7 @@ __kernel_vsyscall: /* Enter using int $0x80 */ int $0x80 -GLOBAL(int80_landing_pad) +SYM_INNER_LABEL(int80_landing_pad, SYM_L_GLOBAL) /* * Restore EDX and ECX in case they were clobbered. EBP is not diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 349a61d8bf34..c1b8496b5606 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -14,16 +14,30 @@ #include <linux/elf.h> #include <linux/cpu.h> #include <linux/ptrace.h> +#include <linux/time_namespace.h> + #include <asm/pvclock.h> #include <asm/vgtod.h> #include <asm/proto.h> #include <asm/vdso.h> #include <asm/vvar.h> +#include <asm/tlb.h> #include <asm/page.h> #include <asm/desc.h> #include <asm/cpufeature.h> #include <clocksource/hyperv_timer.h> +#undef _ASM_X86_VVAR_H +#define EMIT_VVAR(name, offset) \ + const size_t name ## _offset = offset; +#include <asm/vvar.h> + +struct vdso_data *arch_get_vdso_data(void *vvar_page) +{ + return (struct vdso_data *)(vvar_page + _vdso_data_offset); +} +#undef EMIT_VVAR + #if defined(CONFIG_X86_64) unsigned int __read_mostly vdso64_enabled = 1; #endif @@ -37,6 +51,7 @@ void __init init_vdso_image(const struct vdso_image *image) image->alt_len)); } +static const struct vm_special_mapping vvar_mapping; struct linux_binprm; static vm_fault_t vdso_fault(const struct vm_special_mapping *sm, @@ -84,10 +99,74 @@ static int vdso_mremap(const struct vm_special_mapping *sm, return 0; } +static int vvar_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + const struct vdso_image *image = new_vma->vm_mm->context.vdso_image; + unsigned long new_size = new_vma->vm_end - new_vma->vm_start; + + if (new_size != -image->sym_vvar_start) + return -EINVAL; + + return 0; +} + +#ifdef CONFIG_TIME_NS +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + if (likely(vma->vm_mm == current->mm)) + return current->nsproxy->time_ns->vvar_page; + + /* + * VM_PFNMAP | VM_IO protect .fault() handler from being called + * through interfaces like /proc/$pid/mem or + * process_vm_{readv,writev}() as long as there's no .access() + * in special_mapping_vmops(). + * For more details check_vma_flags() and __access_remote_vm() + */ + + WARN(1, "vvar_page accessed remotely"); + + return NULL; +} + +/* + * The vvar page layout depends on whether a task belongs to the root or + * non-root time namespace. Whenever a task changes its namespace, the VVAR + * page tables are cleared and then they will re-faulted with a + * corresponding layout. + * See also the comment near timens_setup_vdso_data() for details. + */ +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) +{ + struct mm_struct *mm = task->mm; + struct vm_area_struct *vma; + + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long size = vma->vm_end - vma->vm_start; + + if (vma_is_special_mapping(vma, &vvar_mapping)) + zap_page_range(vma, vma->vm_start, size); + } + + up_write(&mm->mmap_sem); + return 0; +} +#else +static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + return NULL; +} +#endif + static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf) { const struct vdso_image *image = vma->vm_mm->context.vdso_image; + unsigned long pfn; long sym_offset; if (!image) @@ -107,8 +186,36 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, return VM_FAULT_SIGBUS; if (sym_offset == image->sym_vvar_page) { - return vmf_insert_pfn(vma, vmf->address, - __pa_symbol(&__vvar_page) >> PAGE_SHIFT); + struct page *timens_page = find_timens_vvar_page(vma); + + pfn = __pa_symbol(&__vvar_page) >> PAGE_SHIFT; + + /* + * If a task belongs to a time namespace then a namespace + * specific VVAR is mapped with the sym_vvar_page offset and + * the real VVAR page is mapped with the sym_timens_page + * offset. + * See also the comment near timens_setup_vdso_data(). + */ + if (timens_page) { + unsigned long addr; + vm_fault_t err; + + /* + * Optimization: inside time namespace pre-fault + * VVAR page too. As on timens page there are only + * offsets for clocks on VVAR, it'll be faulted + * shortly by VDSO code. + */ + addr = vmf->address + (image->sym_timens_page - sym_offset); + err = vmf_insert_pfn(vma, addr, pfn); + if (unlikely(err & VM_FAULT_ERROR)) + return err; + + pfn = page_to_pfn(timens_page); + } + + return vmf_insert_pfn(vma, vmf->address, pfn); } else if (sym_offset == image->sym_pvclock_page) { struct pvclock_vsyscall_time_info *pvti = pvclock_get_pvti_cpu0_va(); @@ -122,7 +229,15 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK)) return vmf_insert_pfn(vma, vmf->address, - vmalloc_to_pfn(tsc_pg)); + virt_to_phys(tsc_pg) >> PAGE_SHIFT); + } else if (sym_offset == image->sym_timens_page) { + struct page *timens_page = find_timens_vvar_page(vma); + + if (!timens_page) + return VM_FAULT_SIGBUS; + + pfn = __pa_symbol(&__vvar_page) >> PAGE_SHIFT; + return vmf_insert_pfn(vma, vmf->address, pfn); } return VM_FAULT_SIGBUS; @@ -136,6 +251,7 @@ static const struct vm_special_mapping vdso_mapping = { static const struct vm_special_mapping vvar_mapping = { .name = "[vvar]", .fault = vvar_fault, + .mremap = vvar_mremap, }; /* diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index e7c596dea947..44c33103a955 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -184,7 +184,7 @@ bool emulate_vsyscall(unsigned long error_code, */ switch (vsyscall_nr) { case 0: - if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) || + if (!write_ok_or_segv(regs->di, sizeof(struct __kernel_old_timeval)) || !write_ok_or_segv(regs->si, sizeof(struct timezone))) { ret = -EFAULT; goto check_fault; @@ -194,7 +194,7 @@ bool emulate_vsyscall(unsigned long error_code, break; case 1: - if (!write_ok_or_segv(regs->di, sizeof(time_t))) { + if (!write_ok_or_segv(regs->di, sizeof(__kernel_old_time_t))) { ret = -EFAULT; goto check_fault; } @@ -222,7 +222,7 @@ bool emulate_vsyscall(unsigned long error_code, */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; - tmp = secure_computing(NULL); + tmp = secure_computing(); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index e7d35f60d53f..39eb276d0277 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -5,12 +5,18 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/delay.h> +#include <linux/jiffies.h> #include <asm/apicdef.h> #include <asm/nmi.h> #include "../perf_event.h" -static DEFINE_PER_CPU(unsigned int, perf_nmi_counter); +static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp); +static unsigned long perf_nmi_window; + +/* AMD Event 0xFFF: Merge. Used with Large Increment per Cycle events */ +#define AMD_MERGE_EVENT ((0xFULL << 32) | 0xFFULL) +#define AMD_MERGE_EVENT_ENABLE (AMD_MERGE_EVENT | ARCH_PERFMON_EVENTSEL_ENABLE) static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] @@ -244,6 +250,7 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, @@ -299,6 +306,25 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) return offset; } +/* + * AMD64 events are detected based on their event codes. + */ +static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) +{ + return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); +} + +static inline bool amd_is_pair_event_code(struct hw_perf_event *hwc) +{ + if (!(x86_pmu.flags & PMU_FL_PAIR)) + return false; + + switch (amd_get_event_code(hwc)) { + case 0x003: return true; /* Retired SSE/AVX FLOPs */ + default: return false; + } +} + static int amd_core_hw_config(struct perf_event *event) { if (event->attr.exclude_host && event->attr.exclude_guest) @@ -314,15 +340,10 @@ static int amd_core_hw_config(struct perf_event *event) else if (event->attr.exclude_guest) event->hw.config |= AMD64_EVENTSEL_HOSTONLY; - return 0; -} + if ((x86_pmu.flags & PMU_FL_PAIR) && amd_is_pair_event_code(&event->hw)) + event->hw.flags |= PERF_X86_EVENT_PAIR; -/* - * AMD64 events are detected based on their event codes. - */ -static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) -{ - return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); + return 0; } static inline int amd_is_nb_event(struct hw_perf_event *hwc) @@ -641,43 +662,33 @@ static void amd_pmu_disable_event(struct perf_event *event) * handler when multiple PMCs are active or PMC overflow while handling some * other source of an NMI. * - * Attempt to mitigate this by using the number of active PMCs to determine - * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset - * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the - * number of active PMCs or 2. The value of 2 is used in case an NMI does not - * arrive at the LAPIC in time to be collapsed into an already pending NMI. + * Attempt to mitigate this by creating an NMI window in which un-handled NMIs + * received during this window will be claimed. This prevents extending the + * window past when it is possible that latent NMIs should be received. The + * per-CPU perf_nmi_tstamp will be set to the window end time whenever perf has + * handled a counter. When an un-handled NMI is received, it will be claimed + * only if arriving within that window. */ static int amd_pmu_handle_irq(struct pt_regs *regs) { - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - int active, handled; - - /* - * Obtain the active count before calling x86_pmu_handle_irq() since - * it is possible that x86_pmu_handle_irq() may make a counter - * inactive (through x86_pmu_stop). - */ - active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX); + int handled; /* Process any counter overflows */ handled = x86_pmu_handle_irq(regs); /* - * If a counter was handled, record the number of possible remaining - * NMIs that can occur. + * If a counter was handled, record a timestamp such that un-handled + * NMIs will be claimed if arriving within that window. */ if (handled) { - this_cpu_write(perf_nmi_counter, - min_t(unsigned int, 2, active)); + this_cpu_write(perf_nmi_tstamp, jiffies + perf_nmi_window); return handled; } - if (!this_cpu_read(perf_nmi_counter)) + if (time_after(jiffies, this_cpu_read(perf_nmi_tstamp))) return NMI_DONE; - this_cpu_dec(perf_nmi_counter); - return NMI_HANDLED; } @@ -863,6 +874,29 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, } } +static struct event_constraint pair_constraint; + +static struct event_constraint * +amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (amd_is_pair_event_code(hwc)) + return &pair_constraint; + + return &unconstrained; +} + +static void amd_put_event_constraints_f17h(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (is_counter_pair(hwc)) + --cpuc->n_pair; +} + static ssize_t amd_event_sysfs_show(char *page, u64 config) { u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) | @@ -906,29 +940,14 @@ static __initconst const struct x86_pmu amd_pmu = { static int __init amd_core_pmu_init(void) { + u64 even_ctr_mask = 0ULL; + int i; + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; - switch (boot_cpu_data.x86) { - case 0x15: - pr_cont("Fam15h "); - x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; - break; - case 0x17: - pr_cont("Fam17h "); - /* - * In family 17h, there are no event constraints in the PMC hardware. - * We fallback to using default amd_get_event_constraints. - */ - break; - case 0x18: - pr_cont("Fam18h "); - /* Using default amd_get_event_constraints. */ - break; - default: - pr_err("core perfctr but no constraints; unknown hardware!\n"); - return -ENODEV; - } + /* Avoid calculating the value each time in the NMI handler */ + perf_nmi_window = msecs_to_jiffies(100); /* * If core performance counter extensions exists, we must use @@ -944,6 +963,32 @@ static int __init amd_core_pmu_init(void) */ x86_pmu.amd_nb_constraints = 0; + if (boot_cpu_data.x86 == 0x15) { + pr_cont("Fam15h "); + x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; + } + if (boot_cpu_data.x86 >= 0x17) { + pr_cont("Fam17h+ "); + /* + * Family 17h and compatibles have constraints for Large + * Increment per Cycle events: they may only be assigned an + * even numbered counter that has a consecutive adjacent odd + * numbered counter following it. + */ + for (i = 0; i < x86_pmu.num_counters - 1; i += 2) + even_ctr_mask |= 1 << i; + + pair_constraint = (struct event_constraint) + __EVENT_CONSTRAINT(0, even_ctr_mask, 0, + x86_pmu.num_counters / 2, 0, + PERF_X86_EVENT_PAIR); + + x86_pmu.get_event_constraints = amd_get_event_constraints_f17h; + x86_pmu.put_event_constraints = amd_put_event_constraints_f17h; + x86_pmu.perf_ctr_pair_en = AMD_MERGE_EVENT_ENABLE; + x86_pmu.flags |= PMU_FL_PAIR; + } + pr_cont("core perfctr, "); return 0; } diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 62f317c9113a..26c36357c4c9 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -377,7 +377,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { config &= ~perf_ibs->cnt_mask; - wrmsrl(hwc->config_base, config); + if (boot_cpu_data.x86 == 0x10) + wrmsrl(hwc->config_base, config); config &= ~perf_ibs->enable_mask; wrmsrl(hwc->config_base, config); } @@ -553,7 +554,8 @@ static struct perf_ibs perf_ibs_op = { }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, - .cnt_mask = IBS_OP_MAX_CNT, + .cnt_mask = IBS_OP_MAX_CNT | IBS_OP_CUR_CNT | + IBS_OP_CUR_CNT_RAND, .enable_mask = IBS_OP_ENABLE, .valid_mask = IBS_OP_VAL, .max_period = IBS_OP_MAX_CNT << 4, @@ -614,7 +616,7 @@ fail: if (event->attr.sample_type & PERF_SAMPLE_RAW) offset_max = perf_ibs->offset_max; else if (check_rip) - offset_max = 2; + offset_max = 3; else offset_max = 1; do { @@ -661,10 +663,17 @@ fail: throttle = perf_event_overflow(event, &data, ®s); out: - if (throttle) + if (throttle) { perf_ibs_stop(event, 0); - else - perf_ibs_enable_event(perf_ibs, hwc, period >> 4); + } else { + period >>= 4; + + if ((ibs_caps & IBS_CAPS_RDWROPCNT) && + (*config & IBS_OP_CNT_CTL)) + period |= *config & IBS_OP_CUR_CNT_RAND; + + perf_ibs_enable_event(perf_ibs, hwc, period); + } perf_event_update_userpage(event); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 81b005e4c7d9..3bb738f5a472 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -49,6 +49,7 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; +DEFINE_STATIC_KEY_FALSE(rdpmc_never_available_key); DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key); u64 __read_mostly hw_cache_event_ids @@ -375,7 +376,7 @@ int x86_add_exclusive(unsigned int what) * LBR and BTS are still mutually exclusive. */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) - return 0; + goto out; if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); @@ -387,6 +388,7 @@ int x86_add_exclusive(unsigned int what) mutex_unlock(&pmc_reserve_mutex); } +out: atomic_inc(&active_events); return 0; @@ -397,11 +399,15 @@ fail_unlock: void x86_del_exclusive(unsigned int what) { + atomic_dec(&active_events); + + /* + * See the comment in x86_add_exclusive(). + */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) return; atomic_dec(&x86_pmu.lbr_exclusive[what]); - atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) @@ -612,6 +618,7 @@ void x86_pmu_disable_all(void) int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { + struct hw_perf_event *hwc = &cpuc->events[idx]->hw; u64 val; if (!test_bit(idx, cpuc->active_mask)) @@ -621,6 +628,8 @@ void x86_pmu_disable_all(void) continue; val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(x86_pmu_config_addr(idx), val); + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_config_addr(idx + 1), 0); } } @@ -693,7 +702,7 @@ struct sched_state { int counter; /* counter index */ int unassigned; /* number of events to be assigned left */ int nr_gp; /* number of GP counters used */ - unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + u64 used; }; /* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */ @@ -750,8 +759,12 @@ static bool perf_sched_restore_state(struct perf_sched *sched) sched->saved_states--; sched->state = sched->saved[sched->saved_states]; - /* continue with next counter: */ - clear_bit(sched->state.counter++, sched->state.used); + /* this assignment didn't work out */ + /* XXX broken vs EVENT_PAIR */ + sched->state.used &= ~BIT_ULL(sched->state.counter); + + /* try the next one */ + sched->state.counter++; return true; } @@ -776,20 +789,32 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { - if (!__test_and_set_bit(idx, sched->state.used)) - goto done; + u64 mask = BIT_ULL(idx); + + if (sched->state.used & mask) + continue; + + sched->state.used |= mask; + goto done; } } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { - if (!__test_and_set_bit(idx, sched->state.used)) { - if (sched->state.nr_gp++ >= sched->max_gp) - return false; + u64 mask = BIT_ULL(idx); - goto done; - } + if (c->flags & PERF_X86_EVENT_PAIR) + mask |= mask << 1; + + if (sched->state.used & mask) + continue; + + if (sched->state.nr_gp++ >= sched->max_gp) + return false; + + sched->state.used |= mask; + goto done; } return false; @@ -866,12 +891,10 @@ EXPORT_SYMBOL_GPL(perf_assign_events); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { struct event_constraint *c; - unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; struct perf_event *e; int n0, i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; - - bitmap_zero(used_mask, X86_PMC_IDX_MAX); + u64 used_mask = 0; /* * Compute the number of events already present; see x86_pmu_add(), @@ -914,6 +937,8 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) * fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { + u64 mask; + hwc = &cpuc->event_list[i]->hw; c = cpuc->event_constraint[i]; @@ -925,11 +950,16 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (!test_bit(hwc->idx, c->idxmsk)) break; + mask = BIT_ULL(hwc->idx); + if (is_counter_pair(hwc)) + mask |= mask << 1; + /* not already used */ - if (test_bit(hwc->idx, used_mask)) + if (used_mask & mask) break; - __set_bit(hwc->idx, used_mask); + used_mask |= mask; + if (assign) assign[i] = hwc->idx; } @@ -952,6 +982,15 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) READ_ONCE(cpuc->excl_cntrs->exclusive_present)) gpmax /= 2; + /* + * Reduce the amount of available counters to allow fitting + * the extra Merge events needed by large increment events. + */ + if (x86_pmu.flags & PMU_FL_PAIR) { + gpmax = x86_pmu.num_counters - cpuc->n_pair; + WARN_ON(gpmax <= 0); + } + unsched = perf_assign_events(cpuc->event_constraint, n, wmin, wmax, gpmax, assign); } @@ -1005,12 +1044,35 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, /* current number of events already accepted */ n = cpuc->n_events; + if (!cpuc->n_events) + cpuc->pebs_output = 0; + + if (!cpuc->is_fake && leader->attr.precise_ip) { + /* + * For PEBS->PT, if !aux_event, the group leader (PT) went + * away, the group was broken down and this singleton event + * can't schedule any more. + */ + if (is_pebs_pt(leader) && !leader->aux_event) + return -EINVAL; + + /* + * pebs_output: 0: no PEBS so far, 1: PT, 2: DS + */ + if (cpuc->pebs_output && + cpuc->pebs_output != is_pebs_pt(leader) + 1) + return -EINVAL; + + cpuc->pebs_output = is_pebs_pt(leader) + 1; + } if (is_x86_event(leader)) { if (n >= max_count) return -EINVAL; cpuc->event_list[n] = leader; n++; + if (is_counter_pair(&leader->hw)) + cpuc->n_pair++; } if (!dogrp) return n; @@ -1025,6 +1087,8 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, cpuc->event_list[n] = event; n++; + if (is_counter_pair(&event->hw)) + cpuc->n_pair++; } return n; } @@ -1211,6 +1275,13 @@ int x86_perf_event_set_period(struct perf_event *event) wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* + * Clear the Merge event counter's upper 16 bits since + * we currently declare a 48-bit counter width + */ + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_event_addr(idx + 1), 0); + + /* * Due to erratum on certan cpu we need * a second write to be sure the register * is updated properly @@ -1236,7 +1307,7 @@ void x86_pmu_enable_event(struct perf_event *event) * Add a single event to the PMU. * * The event is added to the group of enabled events - * but only if it can be scehduled with existing events. + * but only if it can be scheduled with existing events. */ static int x86_pmu_add(struct perf_event *event, int flags) { @@ -1620,9 +1691,12 @@ static struct attribute_group x86_pmu_format_group __ro_after_init = { ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { - struct perf_pmu_events_attr *pmu_attr = \ + struct perf_pmu_events_attr *pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); - u64 config = x86_pmu.event_map(pmu_attr->id); + u64 config = 0; + + if (pmu_attr->id < x86_pmu.max_events) + config = x86_pmu.event_map(pmu_attr->id); /* string trumps id */ if (pmu_attr->event_str) @@ -1691,6 +1765,9 @@ is_visible(struct kobject *kobj, struct attribute *attr, int idx) { struct perf_pmu_events_attr *pmu_attr; + if (idx >= x86_pmu.max_events) + return 0; + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); /* str trumps id */ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0; @@ -2087,7 +2164,7 @@ static int x86_pmu_event_init(struct perf_event *event) static void refresh_pce(void *ignored) { - load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm)); + load_mm_cr4_irqsoff(this_cpu_read(cpu_tlbstate.loaded_mm)); } static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) @@ -2160,21 +2237,26 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (x86_pmu.attr_rdpmc_broken) return -ENOTSUPP; - if ((val == 2) != (x86_pmu.attr_rdpmc == 2)) { + if (val != x86_pmu.attr_rdpmc) { /* - * Changing into or out of always available, aka - * perf-event-bypassing mode. This path is extremely slow, + * Changing into or out of never available or always available, + * aka perf-event-bypassing mode. This path is extremely slow, * but only root can trigger it, so it's okay. */ + if (val == 0) + static_branch_inc(&rdpmc_never_available_key); + else if (x86_pmu.attr_rdpmc == 0) + static_branch_dec(&rdpmc_never_available_key); + if (val == 2) static_branch_inc(&rdpmc_always_available_key); - else + else if (x86_pmu.attr_rdpmc == 2) static_branch_dec(&rdpmc_always_available_key); + on_each_cpu(refresh_pce, NULL, 1); + x86_pmu.attr_rdpmc = val; } - x86_pmu.attr_rdpmc = val; - return count; } @@ -2222,6 +2304,13 @@ static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) x86_pmu.sched_task(ctx, sched_in); } +static void x86_pmu_swap_task_ctx(struct perf_event_context *prev, + struct perf_event_context *next) +{ + if (x86_pmu.swap_task_ctx) + x86_pmu.swap_task_ctx(prev, next); +} + void perf_check_microcode(void) { if (x86_pmu.check_microcode) @@ -2241,6 +2330,17 @@ static int x86_pmu_check_period(struct perf_event *event, u64 value) return 0; } +static int x86_pmu_aux_output_match(struct perf_event *event) +{ + if (!(pmu.capabilities & PERF_PMU_CAP_AUX_OUTPUT)) + return 0; + + if (x86_pmu.aux_output_match) + return x86_pmu.aux_output_match(event); + + return 0; +} + static struct pmu pmu = { .pmu_enable = x86_pmu_enable, .pmu_disable = x86_pmu_disable, @@ -2265,7 +2365,10 @@ static struct pmu pmu = { .event_idx = x86_pmu_event_idx, .sched_task = x86_pmu_sched_task, .task_ctx_size = sizeof(struct x86_perf_task_context), + .swap_task_ctx = x86_pmu_swap_task_ctx, .check_period = x86_pmu_check_period, + + .aux_output_match = x86_pmu_aux_output_match, }; void arch_perf_update_userpage(struct perf_event *event, diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 5ee3fed881d3..6a3b599ee0fe 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -63,9 +63,17 @@ struct bts_buffer { static struct pmu bts_pmu; +static int buf_nr_pages(struct page *page) +{ + if (!PagePrivate(page)) + return 1; + + return 1 << page_private(page); +} + static size_t buf_size(struct page *page) { - return 1 << (PAGE_SHIFT + page_private(page)); + return buf_nr_pages(page) * PAGE_SIZE; } static void * @@ -83,9 +91,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, /* count all the high order buffers */ for (pg = 0, nbuf = 0; pg < nr_pages;) { page = virt_to_page(pages[pg]); - if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1)) - return NULL; - pg += 1 << page_private(page); + pg += buf_nr_pages(page); nbuf++; } @@ -109,7 +115,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, unsigned int __nr_pages; page = virt_to_page(pages[pg]); - __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; + __nr_pages = buf_nr_pages(page); buf->buf[nbuf].page = page; buf->buf[nbuf].offset = offset; buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); @@ -549,9 +555,11 @@ static int bts_event_init(struct perf_event *event) * Note that the default paranoia setting permits unprivileged * users to profile the kernel. */ - if (event->attr.exclude_kernel && perf_paranoid_kernel() && - !capable(CAP_SYS_ADMIN)) - return -EACCES; + if (event->attr.exclude_kernel) { + ret = perf_allow_kernel(&event->attr); + if (ret) + return ret; + } if (x86_add_exclusive(x86_lbr_exclusive_bts)) return -EBUSY; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 648260b5f367..dff6623804c2 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -18,6 +18,7 @@ #include <asm/cpufeature.h> #include <asm/hardirq.h> #include <asm/intel-family.h> +#include <asm/intel_pt.h> #include <asm/apic.h> #include <asm/cpu_device_id.h> @@ -3298,6 +3299,13 @@ static int intel_pmu_hw_config(struct perf_event *event) } } + if (event->attr.aux_output) { + if (!event->attr.precise_ip) + return -EINVAL; + + event->hw.flags |= PERF_X86_EVENT_PEBS_VIA_PT; + } + if (event->attr.type != PERF_TYPE_RAW) return 0; @@ -3307,16 +3315,28 @@ static int intel_pmu_hw_config(struct perf_event *event) if (x86_pmu.version < 3) return -EINVAL; - if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + ret = perf_allow_cpu(&event->attr); + if (ret) + return ret; event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY; return 0; } +#ifdef CONFIG_RETPOLINE +static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr); +static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr); +#endif + struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) { +#ifdef CONFIG_RETPOLINE + if (x86_pmu.guest_get_msrs == intel_guest_get_msrs) + return intel_guest_get_msrs(nr); + else if (x86_pmu.guest_get_msrs == core_guest_get_msrs) + return core_guest_get_msrs(nr); +#endif if (x86_pmu.guest_get_msrs) return x86_pmu.guest_get_msrs(nr); *nr = 0; @@ -3572,6 +3592,11 @@ static u64 bdw_limit_period(struct perf_event *event, u64 left) return left; } +static u64 nhm_limit_period(struct perf_event *event, u64 left) +{ + return max(left, 32ULL); +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -3806,11 +3831,25 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx, intel_pmu_lbr_sched_task(ctx, sched_in); } +static void intel_pmu_swap_task_ctx(struct perf_event_context *prev, + struct perf_event_context *next) +{ + intel_pmu_lbr_swap_task_ctx(prev, next); +} + static int intel_pmu_check_period(struct perf_event *event, u64 value) { return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0; } +static int intel_pmu_aux_output_match(struct perf_event *event) +{ + if (!x86_pmu.intel_cap.pebs_output_pt_available) + return 0; + + return is_intel_pt_event(event); +} + PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); @@ -3933,8 +3972,11 @@ static __initconst const struct x86_pmu intel_pmu = { .guest_get_msrs = intel_guest_get_msrs, .sched_task = intel_pmu_sched_task, + .swap_task_ctx = intel_pmu_swap_task_ctx, .check_period = intel_pmu_check_period, + + .aux_output_match = intel_pmu_aux_output_match, }; static __init void intel_clovertown_quirk(void) @@ -3964,31 +4006,31 @@ static __init void intel_clovertown_quirk(void) } static const struct x86_cpu_desc isolation_ucodes[] = { - INTEL_CPU_DESC(INTEL_FAM6_HASWELL_CORE, 3, 0x0000001f), - INTEL_CPU_DESC(INTEL_FAM6_HASWELL_ULT, 1, 0x0000001e), - INTEL_CPU_DESC(INTEL_FAM6_HASWELL_GT3E, 1, 0x00000015), + INTEL_CPU_DESC(INTEL_FAM6_HASWELL, 3, 0x0000001f), + INTEL_CPU_DESC(INTEL_FAM6_HASWELL_L, 1, 0x0000001e), + INTEL_CPU_DESC(INTEL_FAM6_HASWELL_G, 1, 0x00000015), INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 2, 0x00000037), INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 4, 0x0000000a), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_CORE, 4, 0x00000023), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_GT3E, 1, 0x00000014), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D, 2, 0x00000010), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D, 3, 0x07000009), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D, 4, 0x0f000009), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D, 5, 0x0e000002), + INTEL_CPU_DESC(INTEL_FAM6_BROADWELL, 4, 0x00000023), + INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_G, 1, 0x00000014), + INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 2, 0x00000010), + INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 3, 0x07000009), + INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 4, 0x0f000009), + INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 5, 0x0e000002), INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 2, 0x0b000014), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 3, 0x00000021), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 4, 0x00000000), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_MOBILE, 3, 0x0000007c), - INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_DESKTOP, 3, 0x0000007c), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP, 9, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE, 9, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE, 10, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE, 11, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE, 12, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP, 10, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP, 11, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP, 12, 0x0000004e), - INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP, 13, 0x0000004e), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c), + INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e), + INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 9, 0x0000004e), + INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 10, 0x0000004e), + INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 11, 0x0000004e), + INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 12, 0x0000004e), + INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 10, 0x0000004e), + INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 11, 0x0000004e), + INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 12, 0x0000004e), + INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 13, 0x0000004e), {} }; @@ -4146,7 +4188,7 @@ static const struct x86_cpu_desc counter_freezing_ucodes[] = { INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 2, 0x0000000e), INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 9, 0x0000002e), INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 10, 0x00000008), - INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_X, 1, 0x00000028), + INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_D, 1, 0x00000028), INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS, 1, 0x00000028), INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS, 8, 0x00000006), {} @@ -4606,6 +4648,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.extra_regs = intel_nehalem_extra_regs; + x86_pmu.limit_period = nhm_limit_period; mem_attr = nhm_mem_events_attrs; @@ -4643,7 +4686,7 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_ATOM_SILVERMONT: - case INTEL_FAM6_ATOM_SILVERMONT_X: + case INTEL_FAM6_ATOM_SILVERMONT_D: case INTEL_FAM6_ATOM_SILVERMONT_MID: case INTEL_FAM6_ATOM_AIRMONT: case INTEL_FAM6_ATOM_AIRMONT_MID: @@ -4665,7 +4708,7 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_GOLDMONT_X: + case INTEL_FAM6_ATOM_GOLDMONT_D: x86_add_quirk(intel_counter_freezing_quirk); memcpy(hw_cache_event_ids, glm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -4721,7 +4764,8 @@ __init int intel_pmu_init(void) name = "goldmont_plus"; break; - case INTEL_FAM6_ATOM_TREMONT_X: + case INTEL_FAM6_ATOM_TREMONT_D: + case INTEL_FAM6_ATOM_TREMONT: x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -4857,10 +4901,10 @@ __init int intel_pmu_init(void) break; - case INTEL_FAM6_HASWELL_CORE: + case INTEL_FAM6_HASWELL: case INTEL_FAM6_HASWELL_X: - case INTEL_FAM6_HASWELL_ULT: - case INTEL_FAM6_HASWELL_GT3E: + case INTEL_FAM6_HASWELL_L: + case INTEL_FAM6_HASWELL_G: x86_add_quirk(intel_ht_bug); x86_add_quirk(intel_pebs_isolation_quirk); x86_pmu.late_ack = true; @@ -4890,9 +4934,9 @@ __init int intel_pmu_init(void) name = "haswell"; break; - case INTEL_FAM6_BROADWELL_CORE: - case INTEL_FAM6_BROADWELL_XEON_D: - case INTEL_FAM6_BROADWELL_GT3E: + case INTEL_FAM6_BROADWELL: + case INTEL_FAM6_BROADWELL_D: + case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: x86_add_quirk(intel_pebs_isolation_quirk); x86_pmu.late_ack = true; @@ -4955,10 +4999,12 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SKYLAKE_X: pmem = true; /* fall through */ - case INTEL_FAM6_SKYLAKE_MOBILE: - case INTEL_FAM6_SKYLAKE_DESKTOP: - case INTEL_FAM6_KABYLAKE_MOBILE: - case INTEL_FAM6_KABYLAKE_DESKTOP: + case INTEL_FAM6_SKYLAKE_L: + case INTEL_FAM6_SKYLAKE: + case INTEL_FAM6_KABYLAKE_L: + case INTEL_FAM6_KABYLAKE: + case INTEL_FAM6_COMETLAKE_L: + case INTEL_FAM6_COMETLAKE: x86_add_quirk(intel_pebs_isolation_quirk); x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -5002,11 +5048,13 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_ICELAKE_X: - case INTEL_FAM6_ICELAKE_XEON_D: + case INTEL_FAM6_ICELAKE_D: pmem = true; /* fall through */ - case INTEL_FAM6_ICELAKE_MOBILE: - case INTEL_FAM6_ICELAKE_DESKTOP: + case INTEL_FAM6_ICELAKE_L: + case INTEL_FAM6_ICELAKE: + case INTEL_FAM6_TIGERLAKE_L: + case INTEL_FAM6_TIGERLAKE: x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 688592b34564..4814c964692c 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,51 +40,57 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL + * Available model: SLM,AMT,GLM,CNL,TNT * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM, - CNL + * CNL,KBL,CML,TNT * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, - * SKL,KNL,GLM,CNL + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL, + * TNT * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 - * Available model: SNB,IVB,HSW,BDW,SKL,CNL + * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, + * ICL,TGL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 - * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL + * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, + * KBL,CML,ICL,TGL,TNT * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, - * GLM,CNL + * GLM,CNL,KBL,CML,ICL,TGL,TNT * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 - * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL,GLM,CNL + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL, + * TNT * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 - * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, + * KBL,CML,ICL,TGL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 - * Available model: HSW ULT,KBL,CNL + * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 - * Available model: HSW ULT,KBL,CNL + * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT,KBL,GLM,CNL + * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, + * TNT * Scope: Package (physical package) * */ @@ -446,7 +452,7 @@ static int cstate_cpu_init(unsigned int cpu) return 0; } -const struct attribute_group *core_attr_update[] = { +static const struct attribute_group *core_attr_update[] = { &group_cstate_core_c1, &group_cstate_core_c3, &group_cstate_core_c6, @@ -454,7 +460,7 @@ const struct attribute_group *core_attr_update[] = { NULL, }; -const struct attribute_group *pkg_attr_update[] = { +static const struct attribute_group *pkg_attr_update[] = { &group_cstate_pkg_c2, &group_cstate_pkg_c3, &group_cstate_pkg_c6, @@ -544,6 +550,19 @@ static const struct cstate_model cnl_cstates __initconst = { BIT(PERF_CSTATE_PKG_C10_RES), }; +static const struct cstate_model icl_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C6_RES) | + BIT(PERF_CSTATE_CORE_C7_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES) | + BIT(PERF_CSTATE_PKG_C8_RES) | + BIT(PERF_CSTATE_PKG_C9_RES) | + BIT(PERF_CSTATE_PKG_C10_RES), +}; + static const struct cstate_model slm_cstates __initconst = { .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | BIT(PERF_CSTATE_CORE_C6_RES), @@ -593,40 +612,45 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE_X, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_CORE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_X, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_GT3E, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_HASWELL, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_X, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_G, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_ULT, hswult_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_L, hswult_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT, slm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_X, slm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT, slm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT, slm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_D, slm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT, slm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_CORE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_XEON_D, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_GT3E, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_X, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_D, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_G, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_X, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_L, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, hswult_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_L, hswult_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE, hswult_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE_L, hswult_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE, hswult_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_L, cnl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates), - + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT_D, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE, icl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE_L, icl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE, icl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index f1269e804e9b..dc43cc124e09 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -7,6 +7,7 @@ #include <asm/perf_event.h> #include <asm/tlbflush.h> #include <asm/insn.h> +#include <asm/io.h> #include "../perf_event.h" @@ -902,6 +903,9 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) */ static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc) { + if (cpuc->n_pebs == cpuc->n_pebs_via_pt) + return false; + return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs); } @@ -919,6 +923,9 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) u64 threshold; int reserved; + if (cpuc->n_pebs_via_pt) + return; + if (x86_pmu.flags & PMU_FL_PEBS_ALL) reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed; else @@ -1059,10 +1066,40 @@ void intel_pmu_pebs_add(struct perf_event *event) cpuc->n_pebs++; if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs++; + if (hwc->flags & PERF_X86_EVENT_PEBS_VIA_PT) + cpuc->n_pebs_via_pt++; pebs_update_state(needed_cb, cpuc, event, true); } +static void intel_pmu_pebs_via_pt_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + if (!is_pebs_pt(event)) + return; + + if (!(cpuc->pebs_enabled & ~PEBS_VIA_PT_MASK)) + cpuc->pebs_enabled &= ~PEBS_VIA_PT_MASK; +} + +static void intel_pmu_pebs_via_pt_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; + + if (!is_pebs_pt(event)) + return; + + if (!(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS)) + cpuc->pebs_enabled |= PEBS_PMI_AFTER_EACH_RECORD; + + cpuc->pebs_enabled |= PEBS_OUTPUT_PT; + + wrmsrl(MSR_RELOAD_PMC0 + hwc->idx, ds->pebs_event_reset[hwc->idx]); +} + void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1100,6 +1137,8 @@ void intel_pmu_pebs_enable(struct perf_event *event) } else { ds->pebs_event_reset[hwc->idx] = 0; } + + intel_pmu_pebs_via_pt_enable(event); } void intel_pmu_pebs_del(struct perf_event *event) @@ -1111,6 +1150,8 @@ void intel_pmu_pebs_del(struct perf_event *event) cpuc->n_pebs--; if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs--; + if (hwc->flags & PERF_X86_EVENT_PEBS_VIA_PT) + cpuc->n_pebs_via_pt--; pebs_update_state(needed_cb, cpuc, event, false); } @@ -1120,7 +1161,8 @@ void intel_pmu_pebs_disable(struct perf_event *event) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - if (cpuc->n_pebs == cpuc->n_large_pebs) + if (cpuc->n_pebs == cpuc->n_large_pebs && + cpuc->n_pebs != cpuc->n_pebs_via_pt) intel_pmu_drain_pebs_buffer(); cpuc->pebs_enabled &= ~(1ULL << hwc->idx); @@ -1131,6 +1173,8 @@ void intel_pmu_pebs_disable(struct perf_event *event) else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); + intel_pmu_pebs_via_pt_disable(event); + if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -1670,6 +1714,8 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) old = ((s64)(prev_raw_count << shift) >> shift); local64_add(new - old + count * period, &event->count); + local64_set(&hwc->period_left, -new); + perf_event_update_userpage(event); return 0; @@ -2031,6 +2077,12 @@ void __init intel_ds_init(void) PERF_SAMPLE_REGS_INTR); } pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual); + + if (x86_pmu.intel_cap.pebs_output_pt_available) { + pr_cont("PEBS-via-PT, "); + x86_get_pmu()->capabilities |= PERF_PMU_CAP_AUX_OUTPUT; + } + break; default: diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 6f814a27416b..534c76606049 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -273,7 +273,7 @@ static inline bool lbr_from_signext_quirk_needed(void) return !tsx_support && (lbr_desc[lbr_format] & LBR_TSX); } -DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key); +static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key); /* If quirk is enabled, ensure sign extension is 63 bits: */ inline u64 lbr_from_signext_quirk_wr(u64 val) @@ -417,6 +417,29 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) cpuc->last_log_id = ++task_ctx->log_id; } +void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev, + struct perf_event_context *next) +{ + struct x86_perf_task_context *prev_ctx_data, *next_ctx_data; + + swap(prev->task_ctx_data, next->task_ctx_data); + + /* + * Architecture specific synchronization makes sense in + * case both prev->task_ctx_data and next->task_ctx_data + * pointers are allocated. + */ + + prev_ctx_data = next->task_ctx_data; + next_ctx_data = prev->task_ctx_data; + + if (!prev_ctx_data || !next_ctx_data) + return; + + swap(prev_ctx_data->lbr_callstack_users, + next_ctx_data->lbr_callstack_users); +} + void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c index dee579efb2b2..a4cc66005ce8 100644 --- a/arch/x86/events/intel/p4.c +++ b/arch/x86/events/intel/p4.c @@ -776,8 +776,9 @@ static int p4_validate_raw_event(struct perf_event *event) * the user needs special permissions to be able to use it */ if (p4_ht_active() && p4_event_bind_map[v].shared) { - if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + v = perf_allow_cpu(&event->attr); + if (v) + return v; } /* ESCR EventMask bits may be invalid */ diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index d3dc2274ddd4..1db7a51d9792 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -204,9 +204,9 @@ static int __init pt_pmu_hw_init(void) /* model-specific quirks */ switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_BROADWELL_CORE: - case INTEL_FAM6_BROADWELL_XEON_D: - case INTEL_FAM6_BROADWELL_GT3E: + case INTEL_FAM6_BROADWELL: + case INTEL_FAM6_BROADWELL_D: + case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: /* not setting BRANCH_EN will #GP, erratum BDM106 */ pt_pmu.branch_en_always_on = true; @@ -397,6 +397,20 @@ static bool pt_event_valid(struct perf_event *event) * These all are cpu affine and operate on a local PT */ +static void pt_config_start(struct perf_event *event) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + u64 ctl = event->hw.config; + + ctl |= RTIT_CTL_TRACEEN; + if (READ_ONCE(pt->vmx_on)) + perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL); + else + wrmsrl(MSR_IA32_RTIT_CTL, ctl); + + WRITE_ONCE(event->hw.config, ctl); +} + /* Address ranges and their corresponding msr configuration registers */ static const struct pt_address_range { unsigned long msr_a; @@ -469,6 +483,7 @@ static u64 pt_config_filters(struct perf_event *event) static void pt_config(struct perf_event *event) { struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf = perf_get_aux(&pt->handle); u64 reg; /* First round: clear STATUS, in particular the PSB byte counter. */ @@ -478,7 +493,9 @@ static void pt_config(struct perf_event *event) } reg = pt_config_filters(event); - reg |= RTIT_CTL_TOPA | RTIT_CTL_TRACEEN; + reg |= RTIT_CTL_TRACEEN; + if (!buf->single) + reg |= RTIT_CTL_TOPA; /* * Previously, we had BRANCH_EN on by default, but now that PT has @@ -501,10 +518,7 @@ static void pt_config(struct perf_event *event) reg |= (event->attr.config & PT_CONFIG_MASK); event->hw.config = reg; - if (READ_ONCE(pt->vmx_on)) - perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL); - else - wrmsrl(MSR_IA32_RTIT_CTL, reg); + pt_config_start(event); } static void pt_config_stop(struct perf_event *event) @@ -533,45 +547,89 @@ static void pt_config_stop(struct perf_event *event) wmb(); } -static void pt_config_buffer(void *buf, unsigned int topa_idx, - unsigned int output_off) -{ - u64 reg; - - wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, virt_to_phys(buf)); - - reg = 0x7f | ((u64)topa_idx << 7) | ((u64)output_off << 32); - - wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg); -} - -/* - * Keep ToPA table-related metadata on the same page as the actual table, - * taking up a few words from the top - */ - -#define TENTS_PER_PAGE (((PAGE_SIZE - 40) / sizeof(struct topa_entry)) - 1) - /** - * struct topa - page-sized ToPA table with metadata at the top - * @table: actual ToPA table entries, as understood by PT hardware + * struct topa - ToPA metadata * @list: linkage to struct pt_buffer's list of tables - * @phys: physical address of this page * @offset: offset of the first entry in this table in the buffer * @size: total size of all entries in this table * @last: index of the last initialized entry in this table + * @z_count: how many times the first entry repeats */ struct topa { - struct topa_entry table[TENTS_PER_PAGE]; struct list_head list; - u64 phys; u64 offset; size_t size; int last; + unsigned int z_count; }; +/* + * Keep ToPA table-related metadata on the same page as the actual table, + * taking up a few words from the top + */ + +#define TENTS_PER_PAGE \ + ((PAGE_SIZE - sizeof(struct topa)) / sizeof(struct topa_entry)) + +/** + * struct topa_page - page-sized ToPA table with metadata at the top + * @table: actual ToPA table entries, as understood by PT hardware + * @topa: metadata + */ +struct topa_page { + struct topa_entry table[TENTS_PER_PAGE]; + struct topa topa; +}; + +static inline struct topa_page *topa_to_page(struct topa *topa) +{ + return container_of(topa, struct topa_page, topa); +} + +static inline struct topa_page *topa_entry_to_page(struct topa_entry *te) +{ + return (struct topa_page *)((unsigned long)te & PAGE_MASK); +} + +static inline phys_addr_t topa_pfn(struct topa *topa) +{ + return PFN_DOWN(virt_to_phys(topa_to_page(topa))); +} + /* make -1 stand for the last table entry */ -#define TOPA_ENTRY(t, i) ((i) == -1 ? &(t)->table[(t)->last] : &(t)->table[(i)]) +#define TOPA_ENTRY(t, i) \ + ((i) == -1 \ + ? &topa_to_page(t)->table[(t)->last] \ + : &topa_to_page(t)->table[(i)]) +#define TOPA_ENTRY_SIZE(t, i) (sizes(TOPA_ENTRY((t), (i))->size)) +#define TOPA_ENTRY_PAGES(t, i) (1 << TOPA_ENTRY((t), (i))->size) + +static void pt_config_buffer(struct pt_buffer *buf) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + u64 reg, mask; + void *base; + + if (buf->single) { + base = buf->data_pages[0]; + mask = (buf->nr_pages * PAGE_SIZE - 1) >> 7; + } else { + base = topa_to_page(buf->cur)->table; + mask = (u64)buf->cur_idx; + } + + reg = virt_to_phys(base); + if (pt->output_base != reg) { + pt->output_base = reg; + wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, reg); + } + + reg = 0x7f | (mask << 7) | ((u64)buf->output_off << 32); + if (pt->output_mask != reg) { + pt->output_mask = reg; + wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg); + } +} /** * topa_alloc() - allocate page-sized ToPA table @@ -583,27 +641,26 @@ struct topa { static struct topa *topa_alloc(int cpu, gfp_t gfp) { int node = cpu_to_node(cpu); - struct topa *topa; + struct topa_page *tp; struct page *p; p = alloc_pages_node(node, gfp | __GFP_ZERO, 0); if (!p) return NULL; - topa = page_address(p); - topa->last = 0; - topa->phys = page_to_phys(p); + tp = page_address(p); + tp->topa.last = 0; /* * In case of singe-entry ToPA, always put the self-referencing END * link as the 2nd entry in the table */ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) { - TOPA_ENTRY(topa, 1)->base = topa->phys >> TOPA_SHIFT; - TOPA_ENTRY(topa, 1)->end = 1; + TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p) >> TOPA_SHIFT; + TOPA_ENTRY(&tp->topa, 1)->end = 1; } - return topa; + return &tp->topa; } /** @@ -643,7 +700,7 @@ static void topa_insert_table(struct pt_buffer *buf, struct topa *topa) BUG_ON(last->last != TENTS_PER_PAGE - 1); - TOPA_ENTRY(last, -1)->base = topa->phys >> TOPA_SHIFT; + TOPA_ENTRY(last, -1)->base = topa_pfn(topa); TOPA_ENTRY(last, -1)->end = 1; } @@ -670,7 +727,7 @@ static bool topa_table_full(struct topa *topa) * * Return: 0 on success or error code. */ -static int topa_insert_pages(struct pt_buffer *buf, gfp_t gfp) +static int topa_insert_pages(struct pt_buffer *buf, int cpu, gfp_t gfp) { struct topa *topa = buf->last; int order = 0; @@ -681,13 +738,18 @@ static int topa_insert_pages(struct pt_buffer *buf, gfp_t gfp) order = page_private(p); if (topa_table_full(topa)) { - topa = topa_alloc(buf->cpu, gfp); + topa = topa_alloc(cpu, gfp); if (!topa) return -ENOMEM; topa_insert_table(buf, topa); } + if (topa->z_count == topa->last - 1) { + if (order == TOPA_ENTRY(topa, topa->last - 1)->size) + topa->z_count++; + } + TOPA_ENTRY(topa, -1)->base = page_to_phys(p) >> TOPA_SHIFT; TOPA_ENTRY(topa, -1)->size = order; if (!buf->snapshot && @@ -713,23 +775,26 @@ static void pt_topa_dump(struct pt_buffer *buf) struct topa *topa; list_for_each_entry(topa, &buf->tables, list) { + struct topa_page *tp = topa_to_page(topa); int i; - pr_debug("# table @%p (%016Lx), off %llx size %zx\n", topa->table, - topa->phys, topa->offset, topa->size); + pr_debug("# table @%p, off %llx size %zx\n", tp->table, + topa->offset, topa->size); for (i = 0; i < TENTS_PER_PAGE; i++) { pr_debug("# entry @%p (%lx sz %u %c%c%c) raw=%16llx\n", - &topa->table[i], - (unsigned long)topa->table[i].base << TOPA_SHIFT, - sizes(topa->table[i].size), - topa->table[i].end ? 'E' : ' ', - topa->table[i].intr ? 'I' : ' ', - topa->table[i].stop ? 'S' : ' ', - *(u64 *)&topa->table[i]); + &tp->table[i], + (unsigned long)tp->table[i].base << TOPA_SHIFT, + sizes(tp->table[i].size), + tp->table[i].end ? 'E' : ' ', + tp->table[i].intr ? 'I' : ' ', + tp->table[i].stop ? 'S' : ' ', + *(u64 *)&tp->table[i]); if ((intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries) && - topa->table[i].stop) || - topa->table[i].end) + tp->table[i].stop) || + tp->table[i].end) break; + if (!i && topa->z_count) + i += topa->z_count; } } } @@ -766,12 +831,17 @@ static void pt_update_head(struct pt *pt) struct pt_buffer *buf = perf_get_aux(&pt->handle); u64 topa_idx, base, old; + if (buf->single) { + local_set(&buf->data_size, buf->output_off); + return; + } + /* offset of the first region in this table from the beginning of buf */ base = buf->cur->offset + buf->output_off; /* offset of the current output region within this table */ for (topa_idx = 0; topa_idx < buf->cur_idx; topa_idx++) - base += sizes(buf->cur->table[topa_idx].size); + base += TOPA_ENTRY_SIZE(buf->cur, topa_idx); if (buf->snapshot) { local_set(&buf->data_size, base); @@ -791,7 +861,7 @@ static void pt_update_head(struct pt *pt) */ static void *pt_buffer_region(struct pt_buffer *buf) { - return phys_to_virt(buf->cur->table[buf->cur_idx].base << TOPA_SHIFT); + return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT); } /** @@ -800,7 +870,7 @@ static void *pt_buffer_region(struct pt_buffer *buf) */ static size_t pt_buffer_region_size(struct pt_buffer *buf) { - return sizes(buf->cur->table[buf->cur_idx].size); + return TOPA_ENTRY_SIZE(buf->cur, buf->cur_idx); } /** @@ -830,7 +900,7 @@ static void pt_handle_status(struct pt *pt) * know. */ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries) || - buf->output_off == sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) { + buf->output_off == pt_buffer_region_size(buf)) { perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_TRUNCATED); advance++; @@ -867,41 +937,114 @@ static void pt_handle_status(struct pt *pt) */ static void pt_read_offset(struct pt_buffer *buf) { - u64 offset, base_topa; + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct topa_page *tp; - rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, base_topa); - buf->cur = phys_to_virt(base_topa); + if (!buf->single) { + rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, pt->output_base); + tp = phys_to_virt(pt->output_base); + buf->cur = &tp->topa; + } - rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, offset); + rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, pt->output_mask); /* offset within current output region */ - buf->output_off = offset >> 32; + buf->output_off = pt->output_mask >> 32; /* index of current output region within this table */ - buf->cur_idx = (offset & 0xffffff80) >> 7; + if (!buf->single) + buf->cur_idx = (pt->output_mask & 0xffffff80) >> 7; } -/** - * pt_topa_next_entry() - obtain index of the first page in the next ToPA entry - * @buf: PT buffer. - * @pg: Page offset in the buffer. - * - * When advancing to the next output region (ToPA entry), given a page offset - * into the buffer, we need to find the offset of the first page in the next - * region. - */ -static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg) +static struct topa_entry * +pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg) { - struct topa_entry *te = buf->topa_index[pg]; + struct topa_page *tp; + struct topa *topa; + unsigned int idx, cur_pg = 0, z_pg = 0, start_idx = 0; - /* one region */ - if (buf->first == buf->last && buf->first->last == 1) - return pg; + /* + * Indicates a bug in the caller. + */ + if (WARN_ON_ONCE(pg >= buf->nr_pages)) + return NULL; - do { - pg++; - pg &= buf->nr_pages - 1; - } while (buf->topa_index[pg] == te); + /* + * First, find the ToPA table where @pg fits. With high + * order allocations, there shouldn't be many of these. + */ + list_for_each_entry(topa, &buf->tables, list) { + if (topa->offset + topa->size > pg << PAGE_SHIFT) + goto found; + } - return pg; + /* + * Hitting this means we have a problem in the ToPA + * allocation code. + */ + WARN_ON_ONCE(1); + + return NULL; + +found: + /* + * Indicates a problem in the ToPA allocation code. + */ + if (WARN_ON_ONCE(topa->last == -1)) + return NULL; + + tp = topa_to_page(topa); + cur_pg = PFN_DOWN(topa->offset); + if (topa->z_count) { + z_pg = TOPA_ENTRY_PAGES(topa, 0) * (topa->z_count + 1); + start_idx = topa->z_count + 1; + } + + /* + * Multiple entries at the beginning of the table have the same size, + * ideally all of them; if @pg falls there, the search is done. + */ + if (pg >= cur_pg && pg < cur_pg + z_pg) { + idx = (pg - cur_pg) / TOPA_ENTRY_PAGES(topa, 0); + return &tp->table[idx]; + } + + /* + * Otherwise, slow path: iterate through the remaining entries. + */ + for (idx = start_idx, cur_pg += z_pg; idx < topa->last; idx++) { + if (cur_pg + TOPA_ENTRY_PAGES(topa, idx) > pg) + return &tp->table[idx]; + + cur_pg += TOPA_ENTRY_PAGES(topa, idx); + } + + /* + * Means we couldn't find a ToPA entry in the table that does match. + */ + WARN_ON_ONCE(1); + + return NULL; +} + +static struct topa_entry * +pt_topa_prev_entry(struct pt_buffer *buf, struct topa_entry *te) +{ + unsigned long table = (unsigned long)te & ~(PAGE_SIZE - 1); + struct topa_page *tp; + struct topa *topa; + + tp = (struct topa_page *)table; + if (tp->table != te) + return --te; + + topa = &tp->topa; + if (topa == buf->first) + topa = buf->last; + else + topa = list_prev_entry(topa, list); + + tp = topa_to_page(topa); + + return &tp->table[topa->last - 1]; } /** @@ -924,9 +1067,11 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, unsigned long head = local64_read(&buf->head); unsigned long idx, npages, wakeup; + if (buf->single) + return 0; + /* can't stop in the middle of an output region */ - if (buf->output_off + handle->size + 1 < - sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) { + if (buf->output_off + handle->size + 1 < pt_buffer_region_size(buf)) { perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); return -EINVAL; } @@ -937,9 +1082,13 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, return 0; /* clear STOP and INT from current entry */ - buf->topa_index[buf->stop_pos]->stop = 0; - buf->topa_index[buf->stop_pos]->intr = 0; - buf->topa_index[buf->intr_pos]->intr = 0; + if (buf->stop_te) { + buf->stop_te->stop = 0; + buf->stop_te->intr = 0; + } + + if (buf->intr_te) + buf->intr_te->intr = 0; /* how many pages till the STOP marker */ npages = handle->size >> PAGE_SHIFT; @@ -950,7 +1099,12 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, idx = (head >> PAGE_SHIFT) + npages; idx &= buf->nr_pages - 1; - buf->stop_pos = idx; + + if (idx != buf->stop_pos) { + buf->stop_pos = idx; + buf->stop_te = pt_topa_entry_for_page(buf, idx); + buf->stop_te = pt_topa_prev_entry(buf, buf->stop_te); + } wakeup = handle->wakeup >> PAGE_SHIFT; @@ -960,51 +1114,20 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, idx = wakeup; idx &= buf->nr_pages - 1; - buf->intr_pos = idx; + if (idx != buf->intr_pos) { + buf->intr_pos = idx; + buf->intr_te = pt_topa_entry_for_page(buf, idx); + buf->intr_te = pt_topa_prev_entry(buf, buf->intr_te); + } - buf->topa_index[buf->stop_pos]->stop = 1; - buf->topa_index[buf->stop_pos]->intr = 1; - buf->topa_index[buf->intr_pos]->intr = 1; + buf->stop_te->stop = 1; + buf->stop_te->intr = 1; + buf->intr_te->intr = 1; return 0; } /** - * pt_buffer_setup_topa_index() - build topa_index[] table of regions - * @buf: PT buffer. - * - * topa_index[] references output regions indexed by offset into the - * buffer for purposes of quick reverse lookup. - */ -static void pt_buffer_setup_topa_index(struct pt_buffer *buf) -{ - struct topa *cur = buf->first, *prev = buf->last; - struct topa_entry *te_cur = TOPA_ENTRY(cur, 0), - *te_prev = TOPA_ENTRY(prev, prev->last - 1); - int pg = 0, idx = 0; - - while (pg < buf->nr_pages) { - int tidx; - - /* pages within one topa entry */ - for (tidx = 0; tidx < 1 << te_cur->size; tidx++, pg++) - buf->topa_index[pg] = te_prev; - - te_prev = te_cur; - - if (idx == cur->last - 1) { - /* advance to next topa table */ - idx = 0; - cur = list_entry(cur->list.next, struct topa, list); - } else { - idx++; - } - te_cur = TOPA_ENTRY(cur, idx); - } - -} - -/** * pt_buffer_reset_offsets() - adjust buffer's write pointers from aux_head * @buf: PT buffer. * @head: Write pointer (aux_head) from AUX buffer. @@ -1021,18 +1144,24 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) */ static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head) { + struct topa_page *cur_tp; + struct topa_entry *te; int pg; if (buf->snapshot) head &= (buf->nr_pages << PAGE_SHIFT) - 1; - pg = (head >> PAGE_SHIFT) & (buf->nr_pages - 1); - pg = pt_topa_next_entry(buf, pg); + if (!buf->single) { + pg = (head >> PAGE_SHIFT) & (buf->nr_pages - 1); + te = pt_topa_entry_for_page(buf, pg); - buf->cur = (struct topa *)((unsigned long)buf->topa_index[pg] & PAGE_MASK); - buf->cur_idx = ((unsigned long)buf->topa_index[pg] - - (unsigned long)buf->cur) / sizeof(struct topa_entry); - buf->output_off = head & (sizes(buf->cur->table[buf->cur_idx].size) - 1); + cur_tp = topa_entry_to_page(te); + buf->cur = &cur_tp->topa; + buf->cur_idx = te - TOPA_ENTRY(buf->cur, 0); + buf->output_off = head & (pt_buffer_region_size(buf) - 1); + } else { + buf->output_off = head; + } local64_set(&buf->head, head); local_set(&buf->data_size, 0); @@ -1046,6 +1175,9 @@ static void pt_buffer_fini_topa(struct pt_buffer *buf) { struct topa *topa, *iter; + if (buf->single) + return; + list_for_each_entry_safe(topa, iter, &buf->tables, list) { /* * right now, this is in free_aux() path only, so @@ -1061,31 +1193,29 @@ static void pt_buffer_fini_topa(struct pt_buffer *buf) * @size: Total size of all regions within this ToPA. * @gfp: Allocation flags. */ -static int pt_buffer_init_topa(struct pt_buffer *buf, unsigned long nr_pages, - gfp_t gfp) +static int pt_buffer_init_topa(struct pt_buffer *buf, int cpu, + unsigned long nr_pages, gfp_t gfp) { struct topa *topa; int err; - topa = topa_alloc(buf->cpu, gfp); + topa = topa_alloc(cpu, gfp); if (!topa) return -ENOMEM; topa_insert_table(buf, topa); while (buf->nr_pages < nr_pages) { - err = topa_insert_pages(buf, gfp); + err = topa_insert_pages(buf, cpu, gfp); if (err) { pt_buffer_fini_topa(buf); return -ENOMEM; } } - pt_buffer_setup_topa_index(buf); - /* link last table to the first one, unless we're double buffering */ if (intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) { - TOPA_ENTRY(buf->last, -1)->base = buf->first->phys >> TOPA_SHIFT; + TOPA_ENTRY(buf->last, -1)->base = topa_pfn(buf->first); TOPA_ENTRY(buf->last, -1)->end = 1; } @@ -1093,6 +1223,36 @@ static int pt_buffer_init_topa(struct pt_buffer *buf, unsigned long nr_pages, return 0; } +static int pt_buffer_try_single(struct pt_buffer *buf, int nr_pages) +{ + struct page *p = virt_to_page(buf->data_pages[0]); + int ret = -ENOTSUPP, order = 0; + + /* + * We can use single range output mode + * + in snapshot mode, where we don't need interrupts; + * + if the hardware supports it; + * + if the entire buffer is one contiguous allocation. + */ + if (!buf->snapshot) + goto out; + + if (!intel_pt_validate_hw_cap(PT_CAP_single_range_output)) + goto out; + + if (PagePrivate(p)) + order = page_private(p); + + if (1 << order != nr_pages) + goto out; + + buf->single = true; + buf->nr_pages = nr_pages; + ret = 0; +out: + return ret; +} + /** * pt_buffer_setup_aux() - set up topa tables for a PT buffer * @cpu: Cpu on which to allocate, -1 means current. @@ -1115,22 +1275,33 @@ pt_buffer_setup_aux(struct perf_event *event, void **pages, if (!nr_pages) return NULL; + /* + * Only support AUX sampling in snapshot mode, where we don't + * generate NMIs. + */ + if (event->attr.aux_sample_size && !snapshot) + return NULL; + if (cpu == -1) cpu = raw_smp_processor_id(); node = cpu_to_node(cpu); - buf = kzalloc_node(offsetof(struct pt_buffer, topa_index[nr_pages]), - GFP_KERNEL, node); + buf = kzalloc_node(sizeof(struct pt_buffer), GFP_KERNEL, node); if (!buf) return NULL; - buf->cpu = cpu; buf->snapshot = snapshot; buf->data_pages = pages; + buf->stop_pos = -1; + buf->intr_pos = -1; INIT_LIST_HEAD(&buf->tables); - ret = pt_buffer_init_topa(buf, nr_pages, GFP_KERNEL); + ret = pt_buffer_try_single(buf, nr_pages); + if (!ret) + return buf; + + ret = pt_buffer_init_topa(buf, cpu, nr_pages, GFP_KERNEL); if (ret) { kfree(buf); return NULL; @@ -1296,9 +1467,8 @@ void intel_pt_interrupt(void) return; } - pt_config_buffer(buf->cur->table, buf->cur_idx, - buf->output_off); - pt_config(event); + pt_config_buffer(buf); + pt_config_start(event); } } @@ -1361,8 +1531,7 @@ static void pt_event_start(struct perf_event *event, int mode) WRITE_ONCE(pt->handle_nmi, 1); hwc->state = 0; - pt_config_buffer(buf->cur->table, buf->cur_idx, - buf->output_off); + pt_config_buffer(buf); pt_config(event); return; @@ -1413,6 +1582,52 @@ static void pt_event_stop(struct perf_event *event, int mode) } } +static long pt_event_snapshot_aux(struct perf_event *event, + struct perf_output_handle *handle, + unsigned long size) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf = perf_get_aux(&pt->handle); + unsigned long from = 0, to; + long ret; + + if (WARN_ON_ONCE(!buf)) + return 0; + + /* + * Sampling is only allowed on snapshot events; + * see pt_buffer_setup_aux(). + */ + if (WARN_ON_ONCE(!buf->snapshot)) + return 0; + + /* + * Here, handle_nmi tells us if the tracing is on + */ + if (READ_ONCE(pt->handle_nmi)) + pt_config_stop(event); + + pt_read_offset(buf); + pt_update_head(pt); + + to = local_read(&buf->data_size); + if (to < size) + from = buf->nr_pages << PAGE_SHIFT; + from += to - size; + + ret = perf_output_copy_aux(&pt->handle, handle, from, to); + + /* + * If the tracing was on when we turned up, restart it. + * Compiler barrier not needed as we couldn't have been + * preempted by anything that touches pt->handle_nmi. + */ + if (pt->handle_nmi) + pt_config_start(event); + + return ret; +} + static void pt_event_del(struct perf_event *event, int mode) { pt_event_stop(event, PERF_EF_UPDATE); @@ -1481,6 +1696,11 @@ void cpu_emergency_stop_pt(void) pt_event_stop(pt->handle.event, PERF_EF_UPDATE); } +int is_intel_pt_event(struct perf_event *event) +{ + return event->pmu == &pt_pmu.pmu; +} + static __init int pt_init(void) { int ret, cpu, prior_warn = 0; @@ -1527,6 +1747,7 @@ static __init int pt_init(void) pt_pmu.pmu.del = pt_event_del; pt_pmu.pmu.start = pt_event_start; pt_pmu.pmu.stop = pt_event_stop; + pt_pmu.pmu.snapshot_aux = pt_event_snapshot_aux; pt_pmu.pmu.read = pt_event_read; pt_pmu.pmu.setup_aux = pt_buffer_setup_aux; pt_pmu.pmu.free_aux = pt_buffer_free_aux; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 63fe4063fbd6..96906a62aacd 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -53,7 +53,6 @@ struct pt_pmu { /** * struct pt_buffer - buffer configuration; one buffer per task_struct or * cpu, depending on perf event configuration - * @cpu: cpu for per-cpu allocation * @tables: list of ToPA tables in this buffer * @first: shorthand for first topa table * @last: shorthand for last topa table @@ -65,13 +64,15 @@ struct pt_pmu { * @lost: if data was lost/truncated * @head: logical write offset inside the buffer * @snapshot: if this is for a snapshot/overwrite counter - * @stop_pos: STOP topa entry in the buffer - * @intr_pos: INT topa entry in the buffer + * @single: use Single Range Output instead of ToPA + * @stop_pos: STOP topa entry index + * @intr_pos: INT topa entry index + * @stop_te: STOP topa entry pointer + * @intr_te: INT topa entry pointer * @data_pages: array of pages from perf * @topa_index: table of topa entries indexed by page offset */ struct pt_buffer { - int cpu; struct list_head tables; struct topa *first, *last, *cur; unsigned int cur_idx; @@ -80,9 +81,10 @@ struct pt_buffer { local_t data_size; local64_t head; bool snapshot; - unsigned long stop_pos, intr_pos; + bool single; + long stop_pos, intr_pos; + struct topa_entry *stop_te, *intr_te; void **data_pages; - struct topa_entry *topa_index[0]; }; #define PT_FILTERS_NUM 4 @@ -111,16 +113,20 @@ struct pt_filters { /** * struct pt - per-cpu pt context - * @handle: perf output handle + * @handle: perf output handle * @filters: last configured filters - * @handle_nmi: do handle PT PMI on this cpu, there's an active event - * @vmx_on: 1 if VMX is ON on this cpu + * @handle_nmi: do handle PT PMI on this cpu, there's an active event + * @vmx_on: 1 if VMX is ON on this cpu + * @output_base: cached RTIT_OUTPUT_BASE MSR value + * @output_mask: cached RTIT_OUTPUT_MASK MSR value */ struct pt { struct perf_output_handle handle; struct pt_filters filters; int handle_nmi; int vmx_on; + u64 output_base; + u64 output_mask; }; #endif /* __INTEL_PT_H__ */ diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 64ab51ffdf06..09913121e726 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -634,7 +634,7 @@ static void cleanup_rapl_pmus(void) kfree(rapl_pmus); } -const struct attribute_group *rapl_attr_update[] = { +static const struct attribute_group *rapl_attr_update[] = { &rapl_events_cores_group, &rapl_events_pkg_group, &rapl_events_ram_group, @@ -720,27 +720,29 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, model_snbep), X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, model_snb), X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, model_snbep), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, model_hsw), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL, model_hsw), X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, model_hsx), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, model_hsw), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_L, model_hsw), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_G, model_hsw), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL, model_hsw), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_G, model_hsw), X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, model_hsx), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, model_hsx), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_D, model_hsx), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, model_knl), X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, model_knl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE, model_skl), X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, model_hsx), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_L, model_skl), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, model_hsw), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_D, model_hsw), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, model_skl), - X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE_L, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE, model_skl), {}, }; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 3694a5d0703d..86467f85c383 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -502,10 +502,8 @@ void uncore_pmu_event_start(struct perf_event *event, int flags) local64_set(&event->hw.prev_count, uncore_read_counter(box, event)); uncore_enable_event(box, event); - if (box->n_active == 1) { - uncore_enable_box(box); + if (box->n_active == 1) uncore_pmu_start_hrtimer(box); - } } void uncore_pmu_event_stop(struct perf_event *event, int flags) @@ -529,10 +527,8 @@ void uncore_pmu_event_stop(struct perf_event *event, int flags) WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; - if (box->n_active == 0) { - uncore_disable_box(box); + if (box->n_active == 0) uncore_pmu_cancel_hrtimer(box); - } } if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { @@ -778,6 +774,40 @@ static int uncore_pmu_event_init(struct perf_event *event) return ret; } +static void uncore_pmu_enable(struct pmu *pmu) +{ + struct intel_uncore_pmu *uncore_pmu; + struct intel_uncore_box *box; + + uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->enable_box) + uncore_pmu->type->ops->enable_box(box); +} + +static void uncore_pmu_disable(struct pmu *pmu) +{ + struct intel_uncore_pmu *uncore_pmu; + struct intel_uncore_box *box; + + uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->disable_box) + uncore_pmu->type->ops->disable_box(box); +} + static ssize_t uncore_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) { @@ -803,6 +833,8 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu) pmu->pmu = (struct pmu) { .attr_groups = pmu->type->attr_groups, .task_ctx_nr = perf_invalid_context, + .pmu_enable = uncore_pmu_enable, + .pmu_disable = uncore_pmu_disable, .event_init = uncore_pmu_event_init, .add = uncore_pmu_event_add, .del = uncore_pmu_event_del, @@ -1451,29 +1483,29 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EP, nhm_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, snb_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, ivb_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, bdw_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, bdw_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL, hsw_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_L, hsw_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_G, hsw_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL, bdw_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_G, bdw_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, snbep_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EX, nhmex_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EX, nhmex_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, ivbep_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hswep_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, bdx_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, bdx_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_D, bdx_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L, skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, icl_uncore_init), - X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ATOM_TREMONT_X, snr_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, icl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE, icl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ATOM_TREMONT_D, snr_uncore_init), {}, }; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index f36f7bebbc1b..bbfdaa720b45 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -441,18 +441,6 @@ static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box, return -EINVAL; } -static inline void uncore_disable_box(struct intel_uncore_box *box) -{ - if (box->pmu->type->ops->disable_box) - box->pmu->type->ops->disable_box(box); -} - -static inline void uncore_enable_box(struct intel_uncore_box *box) -{ - if (box->pmu->type->ops->enable_box) - box->pmu->type->ops->enable_box(box); -} - static inline void uncore_disable_event(struct intel_uncore_box *box, struct perf_event *event) { diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index dbaa1b088a30..c37cb12d0ef6 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -15,6 +15,7 @@ #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f +#define PCI_DEVICE_ID_INTEL_SKL_E3_IMC 0x1918 #define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c #define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904 #define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914 @@ -658,6 +659,10 @@ static const struct pci_device_id skl_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_E3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, @@ -826,6 +831,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */ IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */ IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */ + IMC_DEV(SKL_E3_IMC, &skl_uncore_pci_driver), /* Xeon E3 V5 Gen Core processor */ IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver), /* 7th Gen Core Y */ IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U */ IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index b10a5ec79e48..ad20220af303 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -369,11 +369,6 @@ #define SNR_M2M_PCI_PMON_BOX_CTL 0x438 #define SNR_M2M_PCI_PMON_UMASK_EXT 0xff -/* SNR PCIE3 */ -#define SNR_PCIE3_PCI_PMON_CTL0 0x508 -#define SNR_PCIE3_PCI_PMON_CTR0 0x4e8 -#define SNR_PCIE3_PCI_PMON_BOX_CTL 0x4e4 - /* SNR IMC */ #define SNR_IMC_MMIO_PMON_FIXED_CTL 0x54 #define SNR_IMC_MMIO_PMON_FIXED_CTR 0x38 @@ -4328,27 +4323,12 @@ static struct intel_uncore_type snr_uncore_m2m = { .format_group = &snr_m2m_uncore_format_group, }; -static struct intel_uncore_type snr_uncore_pcie3 = { - .name = "pcie3", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .perf_ctr = SNR_PCIE3_PCI_PMON_CTR0, - .event_ctl = SNR_PCIE3_PCI_PMON_CTL0, - .event_mask = SNBEP_PMON_RAW_EVENT_MASK, - .box_ctl = SNR_PCIE3_PCI_PMON_BOX_CTL, - .ops = &ivbep_uncore_pci_ops, - .format_group = &ivbep_uncore_format_group, -}; - enum { SNR_PCI_UNCORE_M2M, - SNR_PCI_UNCORE_PCIE3, }; static struct intel_uncore_type *snr_pci_uncores[] = { [SNR_PCI_UNCORE_M2M] = &snr_uncore_m2m, - [SNR_PCI_UNCORE_PCIE3] = &snr_uncore_pcie3, NULL, }; @@ -4357,10 +4337,6 @@ static const struct pci_device_id snr_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, SNR_PCI_UNCORE_M2M, 0), }, - { /* PCIe3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0), - }, { /* end: all zeroes */ } }; @@ -4536,6 +4512,7 @@ static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), + { /* end: all zeroes */ }, }; static struct intel_uncore_ops snr_uncore_imc_freerunning_ops = { diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 9431447541e9..a949f6f55991 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -59,24 +59,25 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_IVYBRIDGE: case INTEL_FAM6_IVYBRIDGE_X: - case INTEL_FAM6_HASWELL_CORE: + case INTEL_FAM6_HASWELL: case INTEL_FAM6_HASWELL_X: - case INTEL_FAM6_HASWELL_ULT: - case INTEL_FAM6_HASWELL_GT3E: + case INTEL_FAM6_HASWELL_L: + case INTEL_FAM6_HASWELL_G: - case INTEL_FAM6_BROADWELL_CORE: - case INTEL_FAM6_BROADWELL_XEON_D: - case INTEL_FAM6_BROADWELL_GT3E: + case INTEL_FAM6_BROADWELL: + case INTEL_FAM6_BROADWELL_D: + case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_ATOM_SILVERMONT: - case INTEL_FAM6_ATOM_SILVERMONT_X: + case INTEL_FAM6_ATOM_SILVERMONT_D: case INTEL_FAM6_ATOM_AIRMONT: case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_GOLDMONT_X: - + case INTEL_FAM6_ATOM_GOLDMONT_D: case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_FAM6_ATOM_TREMONT_D: + case INTEL_FAM6_ATOM_TREMONT: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: @@ -84,12 +85,19 @@ static bool test_intel(int idx, void *data) return true; break; - case INTEL_FAM6_SKYLAKE_MOBILE: - case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_SKYLAKE_L: + case INTEL_FAM6_SKYLAKE: case INTEL_FAM6_SKYLAKE_X: - case INTEL_FAM6_KABYLAKE_MOBILE: - case INTEL_FAM6_KABYLAKE_DESKTOP: - case INTEL_FAM6_ICELAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_L: + case INTEL_FAM6_KABYLAKE: + case INTEL_FAM6_COMETLAKE_L: + case INTEL_FAM6_COMETLAKE: + case INTEL_FAM6_ICELAKE_L: + case INTEL_FAM6_ICELAKE: + case INTEL_FAM6_ICELAKE_X: + case INTEL_FAM6_ICELAKE_D: + case INTEL_FAM6_TIGERLAKE_L: + case INTEL_FAM6_TIGERLAKE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; @@ -167,7 +175,7 @@ static const struct attribute_group *attr_groups[] = { NULL, }; -const struct attribute_group *attr_update[] = { +static const struct attribute_group *attr_update[] = { &group_aperf, &group_mperf, &group_pperf, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 8751008fc170..f1cd1ca1a77b 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -76,6 +76,8 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */ #define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ #define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ +#define PERF_X86_EVENT_PEBS_VIA_PT 0x0800 /* use PT buffer for PEBS */ +#define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -85,6 +87,11 @@ struct amd_nb { }; #define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1) +#define PEBS_PMI_AFTER_EACH_RECORD BIT_ULL(60) +#define PEBS_OUTPUT_OFFSET 61 +#define PEBS_OUTPUT_MASK (3ull << PEBS_OUTPUT_OFFSET) +#define PEBS_OUTPUT_PT (1ull << PEBS_OUTPUT_OFFSET) +#define PEBS_VIA_PT_MASK (PEBS_OUTPUT_PT | PEBS_PMI_AFTER_EACH_RECORD) /* * Flags PEBS can handle without an PMI. @@ -211,6 +218,8 @@ struct cpu_hw_events { u64 pebs_enabled; int n_pebs; int n_large_pebs; + int n_pebs_via_pt; + int pebs_output; /* Current super set of events hardware configuration */ u64 pebs_data_cfg; @@ -264,6 +273,7 @@ struct cpu_hw_events { struct amd_nb *amd_nb; /* Inverted mask of bits to clear in the perf_ctr ctrl registers */ u64 perf_ctr_virt_mask; + int n_pair; /* Large increment events */ void *kfree_on_online[X86_PERF_KFREE_MAX]; }; @@ -510,6 +520,8 @@ union perf_capabilities { */ u64 full_width_write:1; u64 pebs_baseline:1; + u64 pebs_metrics_available:1; + u64 pebs_output_pt_available:1; }; u64 capabilities; }; @@ -673,9 +685,18 @@ struct x86_pmu { atomic_t lbr_exclusive[x86_lbr_exclusive_max]; /* + * perf task context (i.e. struct perf_event_context::task_ctx_data) + * switch helper to bridge calls from perf/core to perf/x86. + * See struct pmu::swap_task_ctx() usage for examples; + */ + void (*swap_task_ctx)(struct perf_event_context *prev, + struct perf_event_context *next); + + /* * AMD bits */ unsigned int amd_nb_constraints : 1; + u64 perf_ctr_pair_en; /* * Extra registers for events @@ -692,6 +713,8 @@ struct x86_pmu { * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 period); + + int (*aux_output_match) (struct perf_event *event); }; struct x86_perf_task_context { @@ -723,6 +746,7 @@ do { \ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ #define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ #define PMU_FL_TFA 0x20 /* deal with TSX force abort */ +#define PMU_FL_PAIR 0x40 /* merge counters for large incr. events */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -818,6 +842,11 @@ int x86_pmu_hw_config(struct perf_event *event); void x86_pmu_disable_all(void); +static inline bool is_counter_pair(struct hw_perf_event *hwc) +{ + return hwc->flags & PERF_X86_EVENT_PAIR; +} + static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, u64 enable_mask) { @@ -825,6 +854,14 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, if (hwc->extra_reg.reg) wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); + + /* + * Add enabled Merge event on next counter + * if large increment event being enabled on this counter + */ + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en); + wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask); } @@ -841,6 +878,9 @@ static inline void x86_pmu_disable_event(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; wrmsrl(hwc->config_base, hwc->config); + + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0); } void x86_pmu_enable_event(struct perf_event *event); @@ -901,6 +941,11 @@ static inline int amd_pmu_init(void) #endif /* CONFIG_CPU_SUP_AMD */ +static inline int is_pebs_pt(struct perf_event *event) +{ + return !!(event->hw.flags & PERF_X86_EVENT_PEBS_VIA_PT); +} + #ifdef CONFIG_CPU_SUP_INTEL static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period) @@ -999,6 +1044,9 @@ void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr); void intel_ds_init(void); +void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev, + struct perf_event_context *next); + void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); u64 lbr_from_signext_quirk_wr(u64 val); diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5c056b8aebef..40e0e322161d 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -194,10 +194,20 @@ do_ex_hypercall: static bool __send_ipi_one(int cpu, int vector) { - struct cpumask mask = CPU_MASK_NONE; + int vp = hv_cpu_number_to_vp_number(cpu); - cpumask_set_cpu(cpu, &mask); - return __send_ipi_mask(&mask, vector); + trace_hyperv_send_ipi_one(cpu, vector); + + if (!hv_hypercall_pg || (vp == VP_INVAL)) + return false; + + if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) + return false; + + if (vp >= 64) + return __send_ipi_mask_ex(cpumask_of(cpu), vector); + + return !hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp)); } static void hv_send_ipi(int cpu, int vector) @@ -260,11 +270,21 @@ void __init hv_apic_init(void) } if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) { - pr_info("Hyper-V: Using MSR based APIC access\n"); + pr_info("Hyper-V: Using enlightened APIC (%s mode)", + x2apic_enabled() ? "x2apic" : "xapic"); + /* + * With x2apic, architectural x2apic MSRs are equivalent to the + * respective synthetic MSRs, so there's no need to override + * the apic accessors. The only exception is + * hv_apic_eoi_write, because it benefits from lazy EOI when + * available, but it works for both xapic and x2apic modes. + */ apic_set_eoi_write(hv_apic_eoi_write); - apic->read = hv_apic_read; - apic->write = hv_apic_write; - apic->icr_write = hv_apic_icr_write; - apic->icr_read = hv_apic_icr_read; + if (!x2apic_enabled()) { + apic->read = hv_apic_read; + apic->write = hv_apic_write; + apic->icr_write = hv_apic_icr_write; + apic->icr_read = hv_apic_icr_read; + } } } diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 0d258688c8cf..b0da5320bcff 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -7,6 +7,7 @@ * Author : K. Y. Srinivasan <kys@microsoft.com> */ +#include <linux/acpi.h> #include <linux/efi.h> #include <linux/types.h> #include <asm/apic.h> @@ -20,11 +21,15 @@ #include <linux/hyperv.h> #include <linux/slab.h> #include <linux/cpuhotplug.h> +#include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); +/* Storage to save the hypercall page temporarily for hibernation */ +static void *hv_hypercall_pg_saved; + u32 *hv_vp_index; EXPORT_SYMBOL_GPL(hv_vp_index); @@ -37,6 +42,28 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); u32 hv_max_vp_index; EXPORT_SYMBOL_GPL(hv_max_vp_index); +void *hv_alloc_hyperv_page(void) +{ + BUILD_BUG_ON(PAGE_SIZE != HV_HYP_PAGE_SIZE); + + return (void *)__get_free_page(GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page); + +void *hv_alloc_hyperv_zeroed_page(void) +{ + BUILD_BUG_ON(PAGE_SIZE != HV_HYP_PAGE_SIZE); + + return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO); +} +EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page); + +void hv_free_hyperv_page(unsigned long addr) +{ + free_page(addr); +} +EXPORT_SYMBOL_GPL(hv_free_hyperv_page); + static int hv_cpu_init(unsigned int cpu) { u64 msr_vp_index; @@ -223,6 +250,48 @@ static int __init hv_pci_init(void) return 1; } +static int hv_suspend(void) +{ + union hv_x64_msr_hypercall_contents hypercall_msr; + + /* + * Reset the hypercall page as it is going to be invalidated + * accross hibernation. Setting hv_hypercall_pg to NULL ensures + * that any subsequent hypercall operation fails safely instead of + * crashing due to an access of an invalid page. The hypercall page + * pointer is restored on resume. + */ + hv_hypercall_pg_saved = hv_hypercall_pg; + hv_hypercall_pg = NULL; + + /* Disable the hypercall page in the hypervisor */ + rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hypercall_msr.enable = 0; + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + return 0; +} + +static void hv_resume(void) +{ + union hv_x64_msr_hypercall_contents hypercall_msr; + + /* Re-enable the hypercall page */ + rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hypercall_msr.enable = 1; + hypercall_msr.guest_physical_address = + vmalloc_to_pfn(hv_hypercall_pg_saved); + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + hv_hypercall_pg = hv_hypercall_pg_saved; + hv_hypercall_pg_saved = NULL; +} + +static struct syscore_ops hv_syscore_ops = { + .suspend = hv_suspend, + .resume = hv_resume, +}; + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -297,12 +366,18 @@ void __init hyperv_init(void) hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + /* + * Ignore any errors in setting up stimer clockevents + * as we can run with the LAPIC timer as a fallback. + */ + (void)hv_stimer_alloc(); + hv_apic_init(); x86_init.pci.arch_init = hv_pci_init; - /* Register Hyper-V specific clocksource */ - hv_init_clocksource(); + register_syscore_ops(&hv_syscore_ops); + return; remove_cpuhp_state: @@ -322,6 +397,8 @@ void hyperv_cleanup(void) { union hv_x64_msr_hypercall_contents hypercall_msr; + unregister_syscore_ops(&hv_syscore_ops); + /* Reset our OS id */ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); @@ -419,3 +496,9 @@ bool hv_is_hyperv_initialized(void) return hypercall_msr.enable; } EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized); + +bool hv_is_hibernation_supported(void) +{ + return acpi_sleep_state_supported(ACPI_STATE_S4); +} +EXPORT_SYMBOL_GPL(hv_is_hibernation_supported); diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index e65d7fe6489f..5208ba49c89a 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -37,12 +37,14 @@ static inline int fill_gva_list(u64 gva_list[], int offset, * Lower 12 bits encode the number of additional * pages to flush (in addition to the 'cur' page). */ - if (diff >= HV_TLB_FLUSH_UNIT) + if (diff >= HV_TLB_FLUSH_UNIT) { gva_list[gva_n] |= ~PAGE_MASK; - else if (diff) + cur += HV_TLB_FLUSH_UNIT; + } else if (diff) { gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT; + cur = end; + } - cur += HV_TLB_FLUSH_UNIT; gva_n++; } while (cur < end); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 1cee10091b9f..a3aefe9b9401 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -21,6 +21,7 @@ #include <linux/personality.h> #include <linux/compat.h> #include <linux/binfmts.h> +#include <linux/syscalls.h> #include <asm/ucontext.h> #include <linux/uaccess.h> #include <asm/fpu/internal.h> @@ -113,12 +114,10 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, err |= fpu__restore_sig(buf, 1); - force_iret(); - return err; } -asmlinkage long sys32_sigreturn(void) +COMPAT_SYSCALL_DEFINE0(sigreturn) { struct pt_regs *regs = current_pt_regs(); struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8); @@ -144,7 +143,7 @@ badframe: return 0; } -asmlinkage long sys32_rt_sigreturn(void) +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_ia32 __user *frame; diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 8b52bc5ddf69..ea34464d6221 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -7,7 +7,6 @@ generated-y += unistd_32_ia32.h generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h -generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += export.h generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index aac686e1e005..ca0976456a6b 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -13,7 +13,6 @@ #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mpspec.h> -#include <asm/realmode.h> #include <asm/x86_init.h> #ifdef CONFIG_ACPI_APEI @@ -62,7 +61,7 @@ static inline void acpi_disable_pci(void) extern int (*acpi_suspend_lowlevel)(void); /* Physical address to resume after wakeup */ -#define acpi_wakeup_address ((unsigned long)(real_mode_header->wakeup_start)) +unsigned long acpi_get_wakeup_address(void); /* * Check if the CPU can handle C2 and deeper @@ -117,6 +116,12 @@ static inline bool acpi_has_cpu_in_madt(void) return !!acpi_lapic; } +#define ACPI_HAVE_ARCH_SET_ROOT_POINTER +static inline void acpi_arch_set_root_pointer(u64 addr) +{ + x86_init.acpi.set_root_pointer(addr); +} + #define ACPI_HAVE_ARCH_GET_ROOT_POINTER static inline u64 acpi_arch_get_root_pointer(void) { @@ -125,6 +130,7 @@ static inline u64 acpi_arch_get_root_pointer(void) void acpi_generic_reduced_hw_init(void); +void x86_default_set_root_pointer(u64 addr); u64 x86_default_get_root_pointer(void); #else /* !CONFIG_ACPI */ @@ -138,6 +144,8 @@ static inline void disable_acpi(void) { } static inline void acpi_generic_reduced_hw_init(void) { } +static inline void x86_default_set_root_pointer(u64 addr) { } + static inline u64 x86_default_get_root_pointer(void) { return 0; diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 094fbc9c0b1c..13adca37c99a 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -201,10 +201,10 @@ static inline int alternatives_text_reserved(void *start, void *end) * without volatile and memory clobber. */ #define alternative(oldinstr, newinstr, feature) \ - asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory") + asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory") #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \ - asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory") + asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory") /* * Alternative inline assembly with input. @@ -218,7 +218,7 @@ static inline int alternatives_text_reserved(void *start, void *end) * Leaving an unused argument 0 to keep API compatibility. */ #define alternative_input(oldinstr, newinstr, feature, input...) \ - asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \ + asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, feature) \ : : "i" (0), ## input) /* @@ -231,18 +231,18 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define alternative_input_2(oldinstr, newinstr1, feature1, newinstr2, \ feature2, input...) \ - asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, \ newinstr2, feature2) \ : : "i" (0), ## input) /* Like alternative_input, but with a single output argument */ #define alternative_io(oldinstr, newinstr, feature, output, input...) \ - asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \ + asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, feature) \ : output : "i" (0), ## input) /* Like alternative_io, but for replacing a direct call with another one. */ #define alternative_call(oldfunc, newfunc, feature, output, input...) \ - asm volatile (ALTERNATIVE("call %P[old]", "call %P[new]", feature) \ + asm_inline volatile (ALTERNATIVE("call %P[old]", "call %P[new]", feature) \ : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input) /* @@ -253,7 +253,7 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ output, input...) \ - asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ + asm_inline volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ "call %P[new2]", feature2) \ : output, ASM_CALL_CONSTRAINT \ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index e647aa095867..19e94af9cc5d 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -136,9 +136,11 @@ extern int lapic_get_maxlvt(void); extern void clear_local_APIC(void); extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); +extern void apic_soft_disable(void); extern void lapic_shutdown(void); extern void sync_Arb_IDs(void); extern void init_bsp_APIC(void); +extern void apic_intr_mode_select(void); extern void apic_intr_mode_init(void); extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); @@ -176,6 +178,8 @@ extern void lapic_online(void); extern void lapic_offline(void); extern bool apic_needs_pit(void); +extern void apic_send_IPI_allbutself(unsigned int vector); + #else /* !CONFIG_X86_LOCAL_APIC */ static inline void lapic_shutdown(void) { } #define local_apic_timer_c2_ok 1 @@ -185,6 +189,7 @@ static inline void disable_local_APIC(void) { } # define setup_secondary_APIC_clock x86_init_noop static inline void lapic_update_tsc_freq(void) { } static inline void init_bsp_APIC(void) { } +static inline void apic_intr_mode_select(void) { } static inline void apic_intr_mode_init(void) { } static inline void lapic_assign_system_vectors(void) { } static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { } @@ -449,6 +454,14 @@ static inline void ack_APIC_irq(void) apic_eoi(); } + +static inline bool lapic_vector_set_in_irr(unsigned int vector) +{ + u32 irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); + + return !!(irr & (1U << (vector % 32))); +} + static inline unsigned default_get_apic_id(unsigned long x) { unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); @@ -465,12 +478,6 @@ static inline unsigned default_get_apic_id(unsigned long x) #define TRAMPOLINE_PHYS_LOW 0x467 #define TRAMPOLINE_PHYS_HIGH 0x469 -#ifdef CONFIG_X86_64 -extern void apic_send_IPI_self(int vector); - -DECLARE_PER_CPU(int, x2apic_extra_bits); -#endif - extern void generic_bigsmp_probe(void); #ifdef CONFIG_X86_LOCAL_APIC @@ -506,8 +513,10 @@ extern int default_check_phys_apicid_present(int phys_apicid); #ifdef CONFIG_SMP bool apic_id_is_primary_thread(unsigned int id); +void apic_smt_update(void); #else static inline bool apic_id_is_primary_thread(unsigned int id) { return false; } +static inline void apic_smt_update(void) { } #endif extern void irq_enter(void); diff --git a/arch/x86/include/asm/apic_flat_64.h b/arch/x86/include/asm/apic_flat_64.h deleted file mode 100644 index d3a2b3876ce6..000000000000 --- a/arch/x86/include/asm/apic_flat_64.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_APIC_FLAT_64_H -#define _ASM_X86_APIC_FLAT_64_H - -extern void flat_init_apic_ldr(void); - -#endif - diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h index af45e1452f09..7a4bb1bd4bdb 100644 --- a/arch/x86/include/asm/archrandom.h +++ b/arch/x86/include/asm/archrandom.h @@ -27,7 +27,7 @@ /* Unconditional execution of RDRAND and RDSEED */ -static inline bool rdrand_long(unsigned long *v) +static inline bool __must_check rdrand_long(unsigned long *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; @@ -41,7 +41,7 @@ static inline bool rdrand_long(unsigned long *v) return false; } -static inline bool rdrand_int(unsigned int *v) +static inline bool __must_check rdrand_int(unsigned int *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; @@ -55,7 +55,7 @@ static inline bool rdrand_int(unsigned int *v) return false; } -static inline bool rdseed_long(unsigned long *v) +static inline bool __must_check rdseed_long(unsigned long *v) { bool ok; asm volatile(RDSEED_LONG @@ -64,7 +64,7 @@ static inline bool rdseed_long(unsigned long *v) return ok; } -static inline bool rdseed_int(unsigned int *v) +static inline bool __must_check rdseed_int(unsigned int *v) { bool ok; asm volatile(RDSEED_INT @@ -73,10 +73,6 @@ static inline bool rdseed_int(unsigned int *v) return ok; } -/* Conditional execution based on CPU type */ -#define arch_has_random() static_cpu_has(X86_FEATURE_RDRAND) -#define arch_has_random_seed() static_cpu_has(X86_FEATURE_RDSEED) - /* * These are the generic interfaces; they must not be declared if the * stubs in <linux/random.h> are to be invoked, @@ -84,24 +80,24 @@ static inline bool rdseed_int(unsigned int *v) */ #ifdef CONFIG_ARCH_RANDOM -static inline bool arch_get_random_long(unsigned long *v) +static inline bool __must_check arch_get_random_long(unsigned long *v) { - return arch_has_random() ? rdrand_long(v) : false; + return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_long(v) : false; } -static inline bool arch_get_random_int(unsigned int *v) +static inline bool __must_check arch_get_random_int(unsigned int *v) { - return arch_has_random() ? rdrand_int(v) : false; + return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_int(v) : false; } -static inline bool arch_get_random_seed_long(unsigned long *v) +static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { - return arch_has_random_seed() ? rdseed_long(v) : false; + return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_long(v) : false; } -static inline bool arch_get_random_seed_int(unsigned int *v) +static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { - return arch_has_random_seed() ? rdseed_int(v) : false; + return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_int(v) : false; } extern void x86_init_rdrand(struct cpuinfo_x86 *c); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 3ff577c0b102..cd339b88d5d4 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -7,9 +7,11 @@ # define __ASM_FORM_RAW(x) x # define __ASM_FORM_COMMA(x) x, #else -# define __ASM_FORM(x) " " #x " " -# define __ASM_FORM_RAW(x) #x -# define __ASM_FORM_COMMA(x) " " #x "," +#include <linux/stringify.h> + +# define __ASM_FORM(x) " " __stringify(x) " " +# define __ASM_FORM_RAW(x) __stringify(x) +# define __ASM_FORM_COMMA(x) " " __stringify(x) "," #endif #ifndef __x86_64__ @@ -139,9 +141,6 @@ # define _ASM_EXTABLE_EX(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) -# define _ASM_EXTABLE_REFCOUNT(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount) - # define _ASM_NOKPROBE(entry) \ .pushsection "_kprobe_blacklist","aw" ; \ _ASM_ALIGN ; \ @@ -170,9 +169,6 @@ # define _ASM_EXTABLE_EX(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) -# define _ASM_EXTABLE_REFCOUNT(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount) - /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 84f848c2541a..7f828fe49797 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -49,8 +49,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, #define array_index_mask_nospec array_index_mask_nospec /* Prevent speculative execution past this barrier. */ -#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ - "lfence", X86_FEATURE_LFENCE_RDTSC) +#define barrier_nospec() alternative("", "lfence", X86_FEATURE_LFENCE_RDTSC) #define dma_rmb() barrier() #define dma_wmb() barrier() diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index ba15d53c1ca7..062cdecb2f24 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -45,14 +45,13 @@ * We do the locked ops that don't return the old value as * a mask operation on a byte. */ -#define IS_IMMEDIATE(nr) (__builtin_constant_p(nr)) #define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) static __always_inline void arch_set_bit(long nr, volatile unsigned long *addr) { - if (IS_IMMEDIATE(nr)) { + if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "orb %1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)CONST_MASK(nr)) @@ -72,7 +71,7 @@ arch___set_bit(long nr, volatile unsigned long *addr) static __always_inline void arch_clear_bit(long nr, volatile unsigned long *addr) { - if (IS_IMMEDIATE(nr)) { + if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "andb %1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)~CONST_MASK(nr))); @@ -123,7 +122,7 @@ arch___change_bit(long nr, volatile unsigned long *addr) static __always_inline void arch_change_bit(long nr, volatile unsigned long *addr) { - if (IS_IMMEDIATE(nr)) { + if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "xorb %1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)CONST_MASK(nr))); @@ -389,7 +388,9 @@ static __always_inline int fls64(__u64 x) #include <asm-generic/bitops/const_hweight.h> -#include <asm-generic/bitops-instrumented.h> +#include <asm-generic/bitops/instrumented-atomic.h> +#include <asm-generic/bitops/instrumented-non-atomic.h> +#include <asm-generic/bitops/instrumented-lock.h> #include <asm-generic/bitops/le.h> diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index f5e90a849bca..981fe923a59f 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -59,7 +59,6 @@ static void sanitize_boot_params(struct boot_params *boot_params) BOOT_PARAM_PRESERVE(apm_bios_info), BOOT_PARAM_PRESERVE(tboot_addr), BOOT_PARAM_PRESERVE(ist_info), - BOOT_PARAM_PRESERVE(acpi_rsdp_addr), BOOT_PARAM_PRESERVE(hd0_info), BOOT_PARAM_PRESERVE(hd1_info), BOOT_PARAM_PRESERVE(sys_desc_table), @@ -71,6 +70,8 @@ static void sanitize_boot_params(struct boot_params *boot_params) BOOT_PARAM_PRESERVE(eddbuf_entries), BOOT_PARAM_PRESERVE(edd_mbr_sig_buf_entries), BOOT_PARAM_PRESERVE(edd_mbr_sig_buffer), + BOOT_PARAM_PRESERVE(secure_boot), + BOOT_PARAM_PRESERVE(hdr), BOOT_PARAM_PRESERVE(e820_table), BOOT_PARAM_PRESERVE(eddbuf), }; diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 6804d6642767..facba9bc30ca 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -32,7 +32,7 @@ #define _BUG_FLAGS(ins, flags) \ do { \ - asm volatile("1:\t" ins "\n" \ + asm_inline volatile("1:\t" ins "\n" \ ".pushsection __bug_table,\"aw\"\n" \ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \ @@ -49,7 +49,7 @@ do { \ #define _BUG_FLAGS(ins, flags) \ do { \ - asm volatile("1:\t" ins "\n" \ + asm_inline volatile("1:\t" ins "\n" \ ".pushsection __bug_table,\"aw\"\n" \ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ "\t.word %c0" "\t# bug_entry::flags\n" \ diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h index 542509b53e0f..92ae28389940 100644 --- a/arch/x86/include/asm/bugs.h +++ b/arch/x86/include/asm/bugs.h @@ -6,16 +6,12 @@ extern void check_bugs(void); -#if defined(CONFIG_CPU_SUP_INTEL) -void check_mpx_erratum(struct cpuinfo_x86 *c); -#else -static inline void check_mpx_erratum(struct cpuinfo_x86 *c) {} -#endif - #if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32) int ppro_with_ram_bug(void); #else static inline int ppro_with_ram_bug(void) { return 0; } #endif +extern void cpu_bugs_smt_update(void); + #endif /* _ASM_X86_BUGS_H */ diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h deleted file mode 100644 index facd374a1bf7..000000000000 --- a/arch/x86/include/asm/calgary.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Derived from include/asm-powerpc/iommu.h - * - * Copyright IBM Corporation, 2006-2007 - * - * Author: Jon Mason <jdmason@us.ibm.com> - * Author: Muli Ben-Yehuda <muli@il.ibm.com> - */ - -#ifndef _ASM_X86_CALGARY_H -#define _ASM_X86_CALGARY_H - -#include <linux/spinlock.h> -#include <linux/device.h> -#include <linux/dma-mapping.h> -#include <linux/timer.h> -#include <asm/types.h> - -struct iommu_table { - const struct cal_chipset_ops *chip_ops; /* chipset specific funcs */ - unsigned long it_base; /* mapped address of tce table */ - unsigned long it_hint; /* Hint for next alloc */ - unsigned long *it_map; /* A simple allocation bitmap for now */ - void __iomem *bbar; /* Bridge BAR */ - u64 tar_val; /* Table Address Register */ - struct timer_list watchdog_timer; - spinlock_t it_lock; /* Protects it_map */ - unsigned int it_size; /* Size of iommu table in entries */ - unsigned char it_busno; /* Bus number this table belongs to */ -}; - -struct cal_chipset_ops { - void (*handle_quirks)(struct iommu_table *tbl, struct pci_dev *dev); - void (*tce_cache_blast)(struct iommu_table *tbl); - void (*dump_error_regs)(struct iommu_table *tbl); -}; - -#define TCE_TABLE_SIZE_UNSPECIFIED ~0 -#define TCE_TABLE_SIZE_64K 0 -#define TCE_TABLE_SIZE_128K 1 -#define TCE_TABLE_SIZE_256K 2 -#define TCE_TABLE_SIZE_512K 3 -#define TCE_TABLE_SIZE_1M 4 -#define TCE_TABLE_SIZE_2M 5 -#define TCE_TABLE_SIZE_4M 6 -#define TCE_TABLE_SIZE_8M 7 - -extern int use_calgary; - -#ifdef CONFIG_CALGARY_IOMMU -extern int detect_calgary(void); -#else -static inline int detect_calgary(void) { return -ENODEV; } -#endif - -#endif /* _ASM_X86_CALGARY_H */ diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 22c4dfe65992..52e9f3480f69 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -177,23 +177,6 @@ typedef struct user_regs_struct compat_elf_gregset_t; (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) #endif -/* - * A pointer passed in from user mode. This should not - * be used for syscall parameters, just declare them - * as pointers because the syscall entry code will have - * appropriately converted them already. - */ - -static inline void __user *compat_ptr(compat_uptr_t uptr) -{ - return (void __user *)(unsigned long)uptr; -} - -static inline compat_uptr_t ptr_to_compat(void __user *uptr) -{ - return (u32)(unsigned long)uptr; -} - static inline void __user *arch_compat_alloc_user_space(long len) { compat_uptr_t sp; diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index cff3f3f3bfe0..02c0078d3787 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPU_ENTRY_AREA_H #define _ASM_X86_CPU_ENTRY_AREA_H @@ -6,6 +6,7 @@ #include <linux/percpu-defs.h> #include <asm/processor.h> #include <asm/intel_ds.h> +#include <asm/pgtable_areas.h> #ifdef CONFIG_X86_64 @@ -65,6 +66,13 @@ enum exception_stack_ordering { #endif +#ifdef CONFIG_X86_32 +struct doublefault_stack { + unsigned long stack[(PAGE_SIZE - sizeof(struct x86_hw_tss)) / sizeof(unsigned long)]; + struct x86_hw_tss tss; +} __aligned(PAGE_SIZE); +#endif + /* * cpu_entry_area is a percpu region that contains things needed by the CPU * and early entry/exit code. Real types aren't used for all fields here @@ -78,10 +86,19 @@ struct cpu_entry_area { /* * The GDT is just below entry_stack and thus serves (on x86_64) as - * a a read-only guard page. + * a read-only guard page. On 32-bit the GDT must be writeable, so + * it needs an extra guard page. */ +#ifdef CONFIG_X86_32 + char guard_entry_stack[PAGE_SIZE]; +#endif struct entry_stack_page entry_stack_page; +#ifdef CONFIG_X86_32 + char guard_doublefault_stack[PAGE_SIZE]; + struct doublefault_stack doublefault_stack; +#endif + /* * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because * we need task switches to work, and task switches write to the TSS. @@ -94,7 +111,6 @@ struct cpu_entry_area { */ struct cea_exception_stacks estacks; #endif -#ifdef CONFIG_CPU_SUP_INTEL /* * Per CPU debug store for Intel performance monitoring. Wastes a * full page at the moment. @@ -105,11 +121,13 @@ struct cpu_entry_area { * Reserve enough fixmap PTEs. */ struct debug_store_buffers cpu_debug_buffers; -#endif }; -#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) -#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) +#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) +#define CPU_ENTRY_AREA_ARRAY_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) + +/* Total size includes the readonly IDT mapping page as well: */ +#define CPU_ENTRY_AREA_TOTAL_SIZE (CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE) DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks); @@ -117,14 +135,6 @@ DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks); extern void setup_cpu_entry_areas(void); extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); -#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE -#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) - -#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) - -#define CPU_ENTRY_AREA_MAP_SIZE \ - (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE) - extern struct cpu_entry_area *get_cpu_entry_area(int cpu); static inline struct entry_stack *cpu_entry_stack(int cpu) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 58acda503817..59bf91c57aa8 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -61,6 +61,13 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define CHECK_BIT_IN_MASK_WORD(maskname, word, bit) \ (((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word )) +/* + * {REQUIRED,DISABLED}_MASK_CHECK below may seem duplicated with the + * following BUILD_BUG_ON_ZERO() check but when NCAPINTS gets changed, all + * header macros which use NCAPINTS need to be changed. The duplicated macro + * use causes the compiler to issue errors for all headers so that all usage + * sites can be corrected. + */ #define REQUIRED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 0, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 1, feature_bit) || \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index e880f2408e29..f3327cb56edf 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -96,7 +96,6 @@ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" MFENCE synchronizes RDTSC */ #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ @@ -221,6 +220,7 @@ #define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ #define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ +#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -232,6 +232,8 @@ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ +#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ +#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -291,6 +293,7 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ +#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */ #define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ #define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ #define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ @@ -355,6 +358,8 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */ +#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ @@ -397,5 +402,7 @@ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/cpuidle_haltpoll.h b/arch/x86/include/asm/cpuidle_haltpoll.h new file mode 100644 index 000000000000..c8b39c6716ff --- /dev/null +++ b/arch/x86/include/asm/cpuidle_haltpoll.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARCH_HALTPOLL_H +#define _ARCH_HALTPOLL_H + +void arch_haltpoll_enable(unsigned int cpu); +void arch_haltpoll_disable(unsigned int cpu); + +#endif diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h index 0acf5ee45a21..f58de66091e5 100644 --- a/arch/x86/include/asm/crash.h +++ b/arch/x86/include/asm/crash.h @@ -2,10 +2,17 @@ #ifndef _ASM_X86_CRASH_H #define _ASM_X86_CRASH_H +struct kimage; + int crash_load_segments(struct kimage *image); -int crash_copy_backup_region(struct kimage *image); int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params); void crash_smp_send_stop(void); +#ifdef CONFIG_KEXEC_CORE +void __init crash_reserve_low_1M(void); +#else +static inline void __init crash_reserve_low_1M(void) { } +#endif + #endif /* _ASM_X86_CRASH_H */ diff --git a/arch/x86/include/asm/crypto/aes.h b/arch/x86/include/asm/crypto/aes.h deleted file mode 100644 index c508521dd190..000000000000 --- a/arch/x86/include/asm/crypto/aes.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ASM_X86_AES_H -#define ASM_X86_AES_H - -#include <linux/crypto.h> -#include <crypto/aes.h> - -void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, - const u8 *src); -void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, - const u8 *src); -#endif diff --git a/arch/x86/include/asm/crypto/camellia.h b/arch/x86/include/asm/crypto/camellia.h index a5d86fc0593f..f6d91861cb14 100644 --- a/arch/x86/include/asm/crypto/camellia.h +++ b/arch/x86/include/asm/crypto/camellia.h @@ -26,71 +26,66 @@ struct camellia_xts_ctx { extern int __camellia_setkey(struct camellia_ctx *cctx, const unsigned char *key, - unsigned int key_len, u32 *flags); + unsigned int key_len); extern int xts_camellia_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen); /* regular block cipher functions */ -asmlinkage void __camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, bool xor); -asmlinkage void camellia_dec_blk(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void __camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src, + bool xor); +asmlinkage void camellia_dec_blk(const void *ctx, u8 *dst, const u8 *src); /* 2-way parallel cipher functions */ -asmlinkage void __camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, bool xor); -asmlinkage void camellia_dec_blk_2way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void __camellia_enc_blk_2way(const void *ctx, u8 *dst, const u8 *src, + bool xor); +asmlinkage void camellia_dec_blk_2way(const void *ctx, u8 *dst, const u8 *src); /* 16-way parallel cipher functions (avx/aes-ni) */ -asmlinkage void camellia_ecb_enc_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void camellia_ecb_dec_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); - -asmlinkage void camellia_cbc_dec_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void camellia_ctr_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); - -asmlinkage void camellia_xts_enc_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); -asmlinkage void camellia_xts_dec_16way(struct camellia_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); - -static inline void camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst, - const u8 *src) +asmlinkage void camellia_ecb_enc_16way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void camellia_ecb_dec_16way(const void *ctx, u8 *dst, const u8 *src); + +asmlinkage void camellia_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void camellia_ctr_16way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); + +asmlinkage void camellia_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); +asmlinkage void camellia_xts_dec_16way(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); + +static inline void camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src) { __camellia_enc_blk(ctx, dst, src, false); } -static inline void camellia_enc_blk_xor(struct camellia_ctx *ctx, u8 *dst, - const u8 *src) +static inline void camellia_enc_blk_xor(const void *ctx, u8 *dst, const u8 *src) { __camellia_enc_blk(ctx, dst, src, true); } -static inline void camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst, +static inline void camellia_enc_blk_2way(const void *ctx, u8 *dst, const u8 *src) { __camellia_enc_blk_2way(ctx, dst, src, false); } -static inline void camellia_enc_blk_xor_2way(struct camellia_ctx *ctx, u8 *dst, +static inline void camellia_enc_blk_xor_2way(const void *ctx, u8 *dst, const u8 *src) { __camellia_enc_blk_2way(ctx, dst, src, true); } /* glue helpers */ -extern void camellia_decrypt_cbc_2way(void *ctx, u128 *dst, const u128 *src); -extern void camellia_crypt_ctr(void *ctx, u128 *dst, const u128 *src, +extern void camellia_decrypt_cbc_2way(const void *ctx, u8 *dst, const u8 *src); +extern void camellia_crypt_ctr(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -extern void camellia_crypt_ctr_2way(void *ctx, u128 *dst, const u128 *src, +extern void camellia_crypt_ctr_2way(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -extern void camellia_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv); -extern void camellia_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv); +extern void camellia_xts_enc(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); +extern void camellia_xts_dec(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); #endif /* ASM_X86_CAMELLIA_H */ diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h index d1818634ae7e..777c0f63418c 100644 --- a/arch/x86/include/asm/crypto/glue_helper.h +++ b/arch/x86/include/asm/crypto/glue_helper.h @@ -11,18 +11,13 @@ #include <asm/fpu/api.h> #include <crypto/b128ops.h> -typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src); -typedef void (*common_glue_cbc_func_t)(void *ctx, u128 *dst, const u128 *src); -typedef void (*common_glue_ctr_func_t)(void *ctx, u128 *dst, const u128 *src, +typedef void (*common_glue_func_t)(const void *ctx, u8 *dst, const u8 *src); +typedef void (*common_glue_cbc_func_t)(const void *ctx, u8 *dst, const u8 *src); +typedef void (*common_glue_ctr_func_t)(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -typedef void (*common_glue_xts_func_t)(void *ctx, u128 *dst, const u128 *src, +typedef void (*common_glue_xts_func_t)(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -#define GLUE_FUNC_CAST(fn) ((common_glue_func_t)(fn)) -#define GLUE_CBC_FUNC_CAST(fn) ((common_glue_cbc_func_t)(fn)) -#define GLUE_CTR_FUNC_CAST(fn) ((common_glue_ctr_func_t)(fn)) -#define GLUE_XTS_FUNC_CAST(fn) ((common_glue_xts_func_t)(fn)) - struct common_glue_func_entry { unsigned int num_blocks; /* number of blocks that @fn will process */ union { @@ -114,9 +109,10 @@ extern int glue_ctr_req_128bit(const struct common_glue_ctx *gctx, extern int glue_xts_req_128bit(const struct common_glue_ctx *gctx, struct skcipher_request *req, common_glue_func_t tweak_fn, void *tweak_ctx, - void *crypt_ctx); + void *crypt_ctx, bool decrypt); -extern void glue_xts_crypt_128bit_one(void *ctx, u128 *dst, const u128 *src, - le128 *iv, common_glue_func_t fn); +extern void glue_xts_crypt_128bit_one(const void *ctx, u8 *dst, + const u8 *src, le128 *iv, + common_glue_func_t fn); #endif /* _CRYPTO_GLUE_HELPER_H */ diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h index db7c9cc32234..251c2c89d7cf 100644 --- a/arch/x86/include/asm/crypto/serpent-avx.h +++ b/arch/x86/include/asm/crypto/serpent-avx.h @@ -15,26 +15,26 @@ struct serpent_xts_ctx { struct serpent_ctx crypt_ctx; }; -asmlinkage void serpent_ecb_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_ecb_enc_8way_avx(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void serpent_ecb_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_ecb_dec_8way_avx(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void serpent_cbc_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_cbc_dec_8way_avx(const void *ctx, u8 *dst, const u8 *src); -asmlinkage void serpent_ctr_8way_avx(struct serpent_ctx *ctx, u8 *dst, - const u8 *src, le128 *iv); +asmlinkage void serpent_ctr_8way_avx(const void *ctx, u8 *dst, const u8 *src, + le128 *iv); -asmlinkage void serpent_xts_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_xts_enc_8way_avx(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -asmlinkage void serpent_xts_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_xts_dec_8way_avx(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -extern void __serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src, +extern void __serpent_crypt_ctr(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -extern void serpent_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv); -extern void serpent_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv); +extern void serpent_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv); +extern void serpent_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv); extern int xts_serpent_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen); diff --git a/arch/x86/include/asm/crypto/serpent-sse2.h b/arch/x86/include/asm/crypto/serpent-sse2.h index 1a345e8a7496..860ca248914b 100644 --- a/arch/x86/include/asm/crypto/serpent-sse2.h +++ b/arch/x86/include/asm/crypto/serpent-sse2.h @@ -9,25 +9,23 @@ #define SERPENT_PARALLEL_BLOCKS 4 -asmlinkage void __serpent_enc_blk_4way(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void __serpent_enc_blk_4way(const struct serpent_ctx *ctx, u8 *dst, const u8 *src, bool xor); -asmlinkage void serpent_dec_blk_4way(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_dec_blk_4way(const struct serpent_ctx *ctx, u8 *dst, const u8 *src); -static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst, - const u8 *src) +static inline void serpent_enc_blk_xway(const void *ctx, u8 *dst, const u8 *src) { __serpent_enc_blk_4way(ctx, dst, src, false); } -static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst, - const u8 *src) +static inline void serpent_enc_blk_xway_xor(const struct serpent_ctx *ctx, + u8 *dst, const u8 *src) { __serpent_enc_blk_4way(ctx, dst, src, true); } -static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst, - const u8 *src) +static inline void serpent_dec_blk_xway(const void *ctx, u8 *dst, const u8 *src) { serpent_dec_blk_4way(ctx, dst, src); } @@ -36,25 +34,23 @@ static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst, #define SERPENT_PARALLEL_BLOCKS 8 -asmlinkage void __serpent_enc_blk_8way(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void __serpent_enc_blk_8way(const struct serpent_ctx *ctx, u8 *dst, const u8 *src, bool xor); -asmlinkage void serpent_dec_blk_8way(struct serpent_ctx *ctx, u8 *dst, +asmlinkage void serpent_dec_blk_8way(const struct serpent_ctx *ctx, u8 *dst, const u8 *src); -static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst, - const u8 *src) +static inline void serpent_enc_blk_xway(const void *ctx, u8 *dst, const u8 *src) { __serpent_enc_blk_8way(ctx, dst, src, false); } -static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst, - const u8 *src) +static inline void serpent_enc_blk_xway_xor(const struct serpent_ctx *ctx, + u8 *dst, const u8 *src) { __serpent_enc_blk_8way(ctx, dst, src, true); } -static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst, - const u8 *src) +static inline void serpent_dec_blk_xway(const void *ctx, u8 *dst, const u8 *src) { serpent_dec_blk_8way(ctx, dst, src); } diff --git a/arch/x86/include/asm/crypto/twofish.h b/arch/x86/include/asm/crypto/twofish.h index f618bf272b90..2c377a8042e1 100644 --- a/arch/x86/include/asm/crypto/twofish.h +++ b/arch/x86/include/asm/crypto/twofish.h @@ -7,22 +7,19 @@ #include <crypto/b128ops.h> /* regular block cipher functions from twofish_x86_64 module */ -asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst, - const u8 *src); -asmlinkage void twofish_dec_blk(struct twofish_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void twofish_enc_blk(const void *ctx, u8 *dst, const u8 *src); +asmlinkage void twofish_dec_blk(const void *ctx, u8 *dst, const u8 *src); /* 3-way parallel cipher functions */ -asmlinkage void __twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src, bool xor); -asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst, - const u8 *src); +asmlinkage void __twofish_enc_blk_3way(const void *ctx, u8 *dst, const u8 *src, + bool xor); +asmlinkage void twofish_dec_blk_3way(const void *ctx, u8 *dst, const u8 *src); /* helpers from twofish_x86_64-3way module */ -extern void twofish_dec_blk_cbc_3way(void *ctx, u128 *dst, const u128 *src); -extern void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src, +extern void twofish_dec_blk_cbc_3way(const void *ctx, u8 *dst, const u8 *src); +extern void twofish_enc_blk_ctr(const void *ctx, u8 *dst, const u8 *src, le128 *iv); -extern void twofish_enc_blk_ctr_3way(void *ctx, u128 *dst, const u128 *src, +extern void twofish_enc_blk_ctr_3way(const void *ctx, u8 *dst, const u8 *src, le128 *iv); #endif /* ASM_X86_TWOFISH_H */ diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index a8f6c809d9b1..7e31f7f1bb06 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -6,20 +6,7 @@ struct dev_archdata { #if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU) void *iommu; /* hook for IOMMU specific extension */ #endif -#ifdef CONFIG_STA2X11 - bool is_sta2x11; -#endif -}; - -#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS) -struct dma_domain { - struct list_head node; - const struct dma_map_ops *dma_ops; - int domain_nr; }; -void add_dma_domain(struct dma_domain *domain); -void del_dma_domain(struct dma_domain *domain); -#endif struct pdev_archdata { }; diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index a5ea841cc6d2..4ea8584682f9 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -10,19 +10,13 @@ * cpu_feature_enabled(). */ -#ifdef CONFIG_X86_INTEL_MPX -# define DISABLE_MPX 0 -#else -# define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31)) -#endif - #ifdef CONFIG_X86_SMAP # define DISABLE_SMAP 0 #else # define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31)) #endif -#ifdef CONFIG_X86_INTEL_UMIP +#ifdef CONFIG_X86_UMIP # define DISABLE_UMIP 0 #else # define DISABLE_UMIP (1<<(X86_FEATURE_UMIP & 31)) @@ -74,7 +68,7 @@ #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_MPX|DISABLE_SMAP) +#define DISABLED_MASK9 (DISABLE_SMAP) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index 20a46150e0a8..9b8cb50768c2 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -73,6 +73,19 @@ static inline u64 mul_u32_u32(u32 a, u32 b) #else # include <asm-generic/div64.h> + +static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div) +{ + u64 q; + + asm ("mulq %2; divq %3" : "=a" (q) + : "a" (a), "rm" ((u64)mul), "rm" ((u64)div) + : "rdx"); + + return q; +} +#define mul_u64_u32_div mul_u64_u32_div + #endif /* CONFIG_X86_32 */ #endif /* _ASM_X86_DIV64_H */ diff --git a/arch/x86/include/asm/dma-direct.h b/arch/x86/include/asm/dma-direct.h deleted file mode 100644 index 1a19251eaac9..000000000000 --- a/arch/x86/include/asm/dma-direct.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ASM_X86_DMA_DIRECT_H -#define ASM_X86_DMA_DIRECT_H 1 - -bool dma_capable(struct device *dev, dma_addr_t addr, size_t size); -dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr); -phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr); - -#endif /* ASM_X86_DMA_DIRECT_H */ diff --git a/arch/x86/include/asm/doublefault.h b/arch/x86/include/asm/doublefault.h new file mode 100644 index 000000000000..af9a14ac8962 --- /dev/null +++ b/arch/x86/include/asm/doublefault.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_DOUBLEFAULT_H +#define _ASM_X86_DOUBLEFAULT_H + +#if defined(CONFIG_X86_32) && defined(CONFIG_DOUBLEFAULT) +extern void doublefault_init_cpu_tss(void); +#else +static inline void doublefault_init_cpu_tss(void) +{ +} +#endif + +#endif /* _ASM_X86_DOUBLEFAULT_H */ diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h index c3aa4b5e49e2..314f75d886d0 100644 --- a/arch/x86/include/asm/e820/types.h +++ b/arch/x86/include/asm/e820/types.h @@ -29,6 +29,14 @@ enum e820_type { E820_TYPE_PRAM = 12, /* + * Special-purpose memory is indicated to the system via the + * EFI_MEMORY_SP attribute. Define an e820 translation of this + * memory type for the purpose of reserving this range and + * marking it with the IORES_DESC_SOFT_RESERVED designation. + */ + E820_TYPE_SOFT_RESERVED = 0xefffffff, + + /* * Reserved RAM used by the kernel itself if * CONFIG_INTEL_TXT=y is enabled, memory of this type * will be included in the S3 integrity calculation diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 606a4b6a9812..86169a24b0d8 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -8,6 +8,7 @@ #include <asm/tlb.h> #include <asm/nospec-branch.h> #include <asm/mmu_context.h> +#include <linux/build_bug.h> /* * We map the EFI regions needed for runtime services non-contiguously, @@ -19,13 +20,16 @@ * This is the main reason why we're doing stable VA mappings for RT * services. * - * This flag is used in conjunction with a chicken bit called - * "efi=old_map" which can be used as a fallback to the old runtime - * services mapping method in case there's some b0rkage with a - * particular EFI implementation (haha, it is hard to hold up the - * sarcasm here...). + * SGI UV1 machines are known to be incompatible with this scheme, so we + * provide an opt-out for these machines via a DMI quirk that sets the + * attribute below. */ -#define EFI_OLD_MEMMAP EFI_ARCH_1 +#define EFI_UV1_MEMMAP EFI_ARCH_1 + +static inline bool efi_have_uv1_memmap(void) +{ + return IS_ENABLED(CONFIG_X86_UV) && efi_enabled(EFI_UV1_MEMMAP); +} #define EFI32_LOADER_SIGNATURE "EL32" #define EFI64_LOADER_SIGNATURE "EL64" @@ -34,10 +38,46 @@ #define ARCH_EFI_IRQ_FLAGS_MASK X86_EFLAGS_IF -#ifdef CONFIG_X86_32 +/* + * The EFI services are called through variadic functions in many cases. These + * functions are implemented in assembler and support only a fixed number of + * arguments. The macros below allows us to check at build time that we don't + * try to call them with too many arguments. + * + * __efi_nargs() will return the number of arguments if it is 7 or less, and + * cause a BUILD_BUG otherwise. The limitations of the C preprocessor make it + * impossible to calculate the exact number of arguments beyond some + * pre-defined limit. The maximum number of arguments currently supported by + * any of the thunks is 7, so this is good enough for now and can be extended + * in the obvious way if we ever need more. + */ + +#define __efi_nargs(...) __efi_nargs_(__VA_ARGS__) +#define __efi_nargs_(...) __efi_nargs__(0, ##__VA_ARGS__, \ + __efi_arg_sentinel(7), __efi_arg_sentinel(6), \ + __efi_arg_sentinel(5), __efi_arg_sentinel(4), \ + __efi_arg_sentinel(3), __efi_arg_sentinel(2), \ + __efi_arg_sentinel(1), __efi_arg_sentinel(0)) +#define __efi_nargs__(_0, _1, _2, _3, _4, _5, _6, _7, n, ...) \ + __take_second_arg(n, \ + ({ BUILD_BUG_ON_MSG(1, "__efi_nargs limit exceeded"); 8; })) +#define __efi_arg_sentinel(n) , n + +/* + * __efi_nargs_check(f, n, ...) will cause a BUILD_BUG if the ellipsis + * represents more than n arguments. + */ -extern asmlinkage unsigned long efi_call_phys(void *, ...); +#define __efi_nargs_check(f, n, ...) \ + __efi_nargs_check_(f, __efi_nargs(__VA_ARGS__), n) +#define __efi_nargs_check_(f, p, n) __efi_nargs_check__(f, p, n) +#define __efi_nargs_check__(f, p, n) ({ \ + BUILD_BUG_ON_MSG( \ + (p) > (n), \ + #f " called with too many arguments (" #p ">" #n ")"); \ +}) +#ifdef CONFIG_X86_32 #define arch_efi_call_virt_setup() \ ({ \ kernel_fpu_begin(); \ @@ -51,13 +91,7 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...); }) -/* - * Wrap all the virtual calls in a way that forces the parameters on the stack. - */ -#define arch_efi_call_virt(p, f, args...) \ -({ \ - ((efi_##f##_t __attribute__((regparm(0)))*) p->f)(args); \ -}) +#define arch_efi_call_virt(p, f, args...) p->f(args) #define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) @@ -65,9 +99,12 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...); #define EFI_LOADER_SIGNATURE "EL64" -extern asmlinkage u64 efi_call(void *fp, ...); +extern asmlinkage u64 __efi_call(void *fp, ...); -#define efi_call_phys(f, args...) efi_call((f), args) +#define efi_call(...) ({ \ + __efi_nargs_check(efi_call, 7, __VA_ARGS__); \ + __efi_call(__VA_ARGS__); \ +}) /* * struct efi_scratch - Scratch space used while switching to/from efi_mm @@ -85,7 +122,7 @@ struct efi_scratch { kernel_fpu_begin(); \ firmware_restrict_branch_speculation_start(); \ \ - if (!efi_enabled(EFI_OLD_MEMMAP)) \ + if (!efi_have_uv1_memmap()) \ efi_switch_mm(&efi_mm); \ }) @@ -94,7 +131,7 @@ struct efi_scratch { #define arch_efi_call_virt_teardown() \ ({ \ - if (!efi_enabled(EFI_OLD_MEMMAP)) \ + if (!efi_have_uv1_memmap()) \ efi_switch_mm(efi_scratch.prev_mm); \ \ firmware_restrict_branch_speculation_end(); \ @@ -121,8 +158,6 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, extern struct efi_scratch efi_scratch; extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); -extern pgd_t * __init efi_call_phys_prolog(void); -extern void __init efi_call_phys_epilog(pgd_t *save_pgd); extern void __init efi_print_memmap(void); extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); @@ -140,7 +175,8 @@ extern void efi_delete_dummy_variable(void); extern void efi_switch_mm(struct mm_struct *mm); extern void efi_recover_from_page_fault(unsigned long phys_addr); extern void efi_free_boot_services(void); -extern void efi_reserve_boot_services(void); +extern pgd_t * __init efi_uv1_memmap_phys_prolog(void); +extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd); struct efi_setup_data { u64 fw_vendor; @@ -153,102 +189,174 @@ struct efi_setup_data { extern u64 efi_setup; #ifdef CONFIG_EFI +extern efi_status_t __efi64_thunk(u32, ...); -static inline bool efi_is_native(void) +#define efi64_thunk(...) ({ \ + __efi_nargs_check(efi64_thunk, 6, __VA_ARGS__); \ + __efi64_thunk(__VA_ARGS__); \ +}) + +static inline bool efi_is_mixed(void) { - return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT); + if (!IS_ENABLED(CONFIG_EFI_MIXED)) + return false; + return IS_ENABLED(CONFIG_X86_64) && !efi_enabled(EFI_64BIT); } static inline bool efi_runtime_supported(void) { - if (efi_is_native()) - return true; - - if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_enabled(EFI_OLD_MEMMAP)) + if (IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT)) return true; - return false; + return IS_ENABLED(CONFIG_EFI_MIXED); } extern void parse_efi_setup(u64 phys_addr, u32 data_len); extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); -#ifdef CONFIG_EFI_MIXED extern void efi_thunk_runtime_setup(void); -extern efi_status_t efi_thunk_set_virtual_address_map( - void *phys_set_virtual_address_map, - unsigned long memory_map_size, - unsigned long descriptor_size, - u32 descriptor_version, - efi_memory_desc_t *virtual_map); -#else -static inline void efi_thunk_runtime_setup(void) {} -static inline efi_status_t efi_thunk_set_virtual_address_map( - void *phys_set_virtual_address_map, - unsigned long memory_map_size, - unsigned long descriptor_size, - u32 descriptor_version, - efi_memory_desc_t *virtual_map) -{ - return EFI_SUCCESS; -} -#endif /* CONFIG_EFI_MIXED */ - +efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map); /* arch specific definitions used by the stub code */ -struct efi_config { - u64 image_handle; - u64 table; - u64 runtime_services; - u64 boot_services; - u64 text_output; - efi_status_t (*call)(unsigned long, ...); - bool is64; -} __packed; - -__pure const struct efi_config *__efi_early(void); +__attribute_const__ bool efi_is_64bit(void); -static inline bool efi_is_64bit(void) +static inline bool efi_is_native(void) { if (!IS_ENABLED(CONFIG_X86_64)) - return false; - + return true; if (!IS_ENABLED(CONFIG_EFI_MIXED)) return true; + return efi_is_64bit(); +} + +#define efi_mixed_mode_cast(attr) \ + __builtin_choose_expr( \ + __builtin_types_compatible_p(u32, __typeof__(attr)), \ + (unsigned long)(attr), (attr)) + +#define efi_table_attr(inst, attr) \ + (efi_is_native() \ + ? inst->attr \ + : (__typeof__(inst->attr)) \ + efi_mixed_mode_cast(inst->mixed_mode.attr)) + +/* + * The following macros allow translating arguments if necessary from native to + * mixed mode. The use case for this is to initialize the upper 32 bits of + * output parameters, and where the 32-bit method requires a 64-bit argument, + * which must be split up into two arguments to be thunked properly. + * + * As examples, the AllocatePool boot service returns the address of the + * allocation, but it will not set the high 32 bits of the address. To ensure + * that the full 64-bit address is initialized, we zero-init the address before + * calling the thunk. + * + * The FreePages boot service takes a 64-bit physical address even in 32-bit + * mode. For the thunk to work correctly, a native 64-bit call of + * free_pages(addr, size) + * must be translated to + * efi64_thunk(free_pages, addr & U32_MAX, addr >> 32, size) + * so that the two 32-bit halves of addr get pushed onto the stack separately. + */ - return __efi_early()->is64; +static inline void *efi64_zero_upper(void *p) +{ + ((u32 *)p)[1] = 0; + return p; } -#define efi_table_attr(table, attr, instance) \ - (efi_is_64bit() ? \ - ((table##_64_t *)(unsigned long)instance)->attr : \ - ((table##_32_t *)(unsigned long)instance)->attr) +#define __efi64_argmap_free_pages(addr, size) \ + ((addr), 0, (size)) + +#define __efi64_argmap_get_memory_map(mm_size, mm, key, size, ver) \ + ((mm_size), (mm), efi64_zero_upper(key), efi64_zero_upper(size), (ver)) + +#define __efi64_argmap_allocate_pool(type, size, buffer) \ + ((type), (size), efi64_zero_upper(buffer)) + +#define __efi64_argmap_handle_protocol(handle, protocol, interface) \ + ((handle), (protocol), efi64_zero_upper(interface)) -#define efi_call_proto(protocol, f, instance, ...) \ - __efi_early()->call(efi_table_attr(protocol, f, instance), \ - instance, ##__VA_ARGS__) +#define __efi64_argmap_locate_protocol(protocol, reg, interface) \ + ((protocol), (reg), efi64_zero_upper(interface)) + +/* PCI I/O */ +#define __efi64_argmap_get_location(protocol, seg, bus, dev, func) \ + ((protocol), efi64_zero_upper(seg), efi64_zero_upper(bus), \ + efi64_zero_upper(dev), efi64_zero_upper(func)) + +/* + * The macros below handle the plumbing for the argument mapping. To add a + * mapping for a specific EFI method, simply define a macro + * __efi64_argmap_<method name>, following the examples above. + */ -#define efi_call_early(f, ...) \ - __efi_early()->call(efi_table_attr(efi_boot_services, f, \ - __efi_early()->boot_services), __VA_ARGS__) +#define __efi64_thunk_map(inst, func, ...) \ + efi64_thunk(inst->mixed_mode.func, \ + __efi64_argmap(__efi64_argmap_ ## func(__VA_ARGS__), \ + (__VA_ARGS__))) -#define __efi_call_early(f, ...) \ - __efi_early()->call((unsigned long)f, __VA_ARGS__); +#define __efi64_argmap(mapped, args) \ + __PASTE(__efi64_argmap__, __efi_nargs(__efi_eat mapped))(mapped, args) +#define __efi64_argmap__0(mapped, args) __efi_eval mapped +#define __efi64_argmap__1(mapped, args) __efi_eval args -#define efi_call_runtime(f, ...) \ - __efi_early()->call(efi_table_attr(efi_runtime_services, f, \ - __efi_early()->runtime_services), __VA_ARGS__) +#define __efi_eat(...) +#define __efi_eval(...) __VA_ARGS__ + +/* The three macros below handle dispatching via the thunk if needed */ + +#define efi_call_proto(inst, func, ...) \ + (efi_is_native() \ + ? inst->func(inst, ##__VA_ARGS__) \ + : __efi64_thunk_map(inst, func, inst, ##__VA_ARGS__)) + +#define efi_bs_call(func, ...) \ + (efi_is_native() \ + ? efi_system_table()->boottime->func(__VA_ARGS__) \ + : __efi64_thunk_map(efi_table_attr(efi_system_table(), \ + boottime), func, __VA_ARGS__)) + +#define efi_rt_call(func, ...) \ + (efi_is_native() \ + ? efi_system_table()->runtime->func(__VA_ARGS__) \ + : __efi64_thunk_map(efi_table_attr(efi_system_table(), \ + runtime), func, __VA_ARGS__)) extern bool efi_reboot_required(void); +extern bool efi_is_table_address(unsigned long phys_addr); +extern void efi_find_mirror(void); +extern void efi_reserve_boot_services(void); #else static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {} static inline bool efi_reboot_required(void) { return false; } +static inline bool efi_is_table_address(unsigned long phys_addr) +{ + return false; +} +static inline void efi_find_mirror(void) +{ +} +static inline void efi_reserve_boot_services(void) +{ +} #endif /* CONFIG_EFI */ +#ifdef CONFIG_EFI_FAKE_MEMMAP +extern void __init efi_fake_memmap_early(void); +#else +static inline void efi_fake_memmap_early(void) +{ +} +#endif + #endif /* _ASM_X86_EFI_H */ diff --git a/arch/x86/include/asm/emulate_prefix.h b/arch/x86/include/asm/emulate_prefix.h new file mode 100644 index 000000000000..70f5b98a5286 --- /dev/null +++ b/arch/x86/include/asm/emulate_prefix.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_EMULATE_PREFIX_H +#define _ASM_X86_EMULATE_PREFIX_H + +/* + * Virt escape sequences to trigger instruction emulation; + * ideally these would decode to 'whole' instruction and not destroy + * the instruction stream; sadly this is not true for the 'kvm' one :/ + */ + +#define __XEN_EMULATE_PREFIX 0x0f,0x0b,0x78,0x65,0x6e /* ud2 ; .ascii "xen" */ +#define __KVM_EMULATE_PREFIX 0x0f,0x0b,0x6b,0x76,0x6d /* ud2 ; .ascii "kvm" */ + +#endif diff --git a/arch/x86/include/asm/error-injection.h b/arch/x86/include/asm/error-injection.h deleted file mode 100644 index 47b7a1296245..000000000000 --- a/arch/x86/include/asm/error-injection.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_ERROR_INJECTION_H -#define _ASM_ERROR_INJECTION_H - -#include <linux/compiler.h> -#include <linux/linkage.h> -#include <asm/ptrace.h> -#include <asm-generic/error-injection.h> - -asmlinkage void just_return_func(void); -void override_function_with_return(struct pt_regs *regs); - -#endif /* _ASM_ERROR_INJECTION_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 9da8cccdf3fb..28183ee3cc42 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -42,8 +42,7 @@ * Because of this, FIXADDR_TOP x86 integration was left as later work. */ #ifdef CONFIG_X86_32 -/* used by vmalloc.c, vsyscall.lds.S. - * +/* * Leave one empty page between vmalloc'ed areas and * the start of the fixmap. */ @@ -120,7 +119,7 @@ enum fixed_addresses { * before ioremap() is functional. * * If necessary we round it up to the next 512 pages boundary so - * that we can have a single pgd entry and a single pte table: + * that we can have a single pmd entry and a single pte table: */ #define NR_FIX_BTMAPS 64 #define FIX_BTMAPS_SLOTS 8 @@ -157,7 +156,7 @@ extern pte_t *kmap_pte; extern pte_t *pkmap_page_table; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte); -void native_set_fixmap(enum fixed_addresses idx, +void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags); #ifndef CONFIG_PARAVIRT_XXL diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 4c95c365058a..44c48e34d799 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -509,7 +509,7 @@ static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { - return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; + return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } /* diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 287f1f7b2e52..85be2f506272 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -16,7 +16,6 @@ #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR #ifndef __ASSEMBLY__ -extern void mcount(void); extern atomic_t modifying_ftrace_code; extern void __fentry__(void); @@ -29,14 +28,25 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +/* + * When a ftrace registered caller is tracing a function that is + * also set by a register_ftrace_direct() call, it needs to be + * differentiated in the ftrace_caller trampoline. To do this, we + * place the direct caller in the ORIG_AX part of pt_regs. This + * tells the ftrace_caller that there's a direct caller. + */ +static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) +{ + /* Emulate a call */ + regs->orig_ax = addr; +} + #ifdef CONFIG_DYNAMIC_FTRACE struct dyn_arch_ftrace { /* No extra data needed for x86 */ }; -int ftrace_int3_handler(struct pt_regs *regs); - #define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR #endif /* CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index cbd97e22d2f3..4154bc5f6a4e 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -153,8 +153,8 @@ extern char irq_entries_start[]; extern char spurious_entries_start[]; #define VECTOR_UNUSED NULL -#define VECTOR_SHUTDOWN ((void *)~0UL) -#define VECTOR_RETRIGGERED ((void *)~1UL) +#define VECTOR_SHUTDOWN ((void *)-1L) +#define VECTOR_RETRIGGERED ((void *)-2L) typedef struct irq_desc* vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index af78cd72b8f3..92abc1e42bfc 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -13,6 +13,16 @@ #include <asm/page.h> /* + * While not explicitly listed in the TLFS, Hyper-V always runs with a page size + * of 4096. These definitions are used when communicating with Hyper-V using + * guest physical pages and guest physical page addresses, since the guest page + * size may not be 4096 on all architectures. + */ +#define HV_HYP_PAGE_SHIFT 12 +#define HV_HYP_PAGE_SIZE BIT(HV_HYP_PAGE_SHIFT) +#define HV_HYP_PAGE_MASK (~(HV_HYP_PAGE_SIZE - 1)) + +/* * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent * is set by CPUID(HvCpuIdFunctionVersionAndFeatures). */ @@ -76,6 +86,8 @@ #define HV_X64_ACCESS_FREQUENCY_MSRS BIT(11) /* AccessReenlightenmentControls privilege */ #define HV_X64_ACCESS_REENLIGHTENMENT BIT(13) +/* AccessTscInvariantControls privilege */ +#define HV_X64_ACCESS_TSC_INVARIANT BIT(15) /* * Feature identification: indicates which flags were specified at partition @@ -170,7 +182,15 @@ /* Recommend using enlightened VMCS */ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) +/* + * Virtual processor will never share a physical core with another virtual + * processor, except for virtual processors that are reported as sibling SMT + * threads. + */ +#define HV_X64_NO_NONARCH_CORESHARING BIT(18) + /* Nested features. These are HYPERV_CPUID_NESTED_FEATURES.EAX bits. */ +#define HV_X64_NESTED_DIRECT_FLUSH BIT(17) #define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) #define HV_X64_NESTED_MSR_BITMAP BIT(19) @@ -260,6 +280,9 @@ #define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 #define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 +/* TSC invariant control */ +#define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118 + /* * Declare the MSR used to setup pages used to communicate with the hypervisor. */ @@ -514,14 +537,24 @@ struct hv_timer_message_payload { __u64 delivery_time; /* When the message was delivered */ } __packed; +struct hv_nested_enlightenments_control { + struct { + __u32 directhypercall:1; + __u32 reserved:31; + } features; + struct { + __u32 reserved; + } hypercallControls; +} __packed; + /* Define virtual processor assist page structure. */ struct hv_vp_assist_page { __u32 apic_assist; - __u32 reserved; - __u64 vtl_control[2]; - __u64 nested_enlightenments_control[2]; - __u32 enlighten_vmentry; - __u32 padding; + __u32 reserved1; + __u64 vtl_control[3]; + struct hv_nested_enlightenments_control nested_control; + __u8 enlighten_vmentry; + __u8 reserved2[7]; __u64 current_nested_vmcs; } __packed; @@ -776,7 +809,8 @@ union hv_synic_sint { u64 reserved1:8; u64 masked:1; u64 auto_eoi:1; - u64 reserved2:46; + u64 polling:1; + u64 reserved2:45; } __packed; }; @@ -847,7 +881,7 @@ union hv_gpa_page_range { * count is equal with how many entries of union hv_gpa_page_range can * be populated into the input parameter page. */ -#define HV_MAX_FLUSH_REP_COUNT ((PAGE_SIZE - 2 * sizeof(u64)) / \ +#define HV_MAX_FLUSH_REP_COUNT ((HV_HYP_PAGE_SIZE - 2 * sizeof(u64)) / \ sizeof(union hv_gpa_page_range)) struct hv_guest_mapping_flush_list { @@ -872,4 +906,7 @@ struct hv_tlb_flush_ex { u64 gva_list[]; } __packed; +struct hv_partition_assist_pg { + u32 tlb_lock_count; +}; #endif diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 154f27be8bfc..5c1ae3eff9d4 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -45,6 +45,7 @@ struct insn { struct insn_field immediate2; /* for 64bit imm or seg16 */ }; + int emulate_prefix_size; insn_attr_t attr; unsigned char opnd_bytes; unsigned char addr_bytes; @@ -128,6 +129,11 @@ static inline int insn_is_evex(struct insn *insn) return (insn->vex_prefix.nbytes == 4); } +static inline int insn_has_emulate_prefix(struct insn *insn) +{ + return !!insn->emulate_prefix_size; +} + /* Ensure this instruction is decoded completely */ static inline int insn_complete(struct insn *insn) { diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 0278aa66ef62..4981c293f926 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -5,12 +5,34 @@ /* * "Big Core" Processors (Branded as Core, Xeon, etc...) * - * The "_X" parts are generally the EP and EX Xeons, or the - * "Extreme" ones, like Broadwell-E, or Atom microserver. - * * While adding a new CPUID for a new microarchitecture, add a new * group to keep logically sorted out in chronological order. Within * that group keep the CPUID for the variants sorted by model number. + * + * The defined symbol names have the following form: + * INTEL_FAM6{OPTFAMILY}_{MICROARCH}{OPTDIFF} + * where: + * OPTFAMILY Describes the family of CPUs that this belongs to. Default + * is assumed to be "_CORE" (and should be omitted). Other values + * currently in use are _ATOM and _XEON_PHI + * MICROARCH Is the code name for the micro-architecture for this core. + * N.B. Not the platform name. + * OPTDIFF If needed, a short string to differentiate by market segment. + * + * Common OPTDIFFs: + * + * - regular client parts + * _L - regular mobile parts + * _G - parts with extra graphics on + * _X - regular server parts + * _D - micro server parts + * + * Historical OPTDIFFs: + * + * _EP - 2 socket server parts + * _EX - 4+ socket server parts + * + * The #define line may optionally include a comment including platform names. */ #define INTEL_FAM6_CORE_YONAH 0x0E @@ -34,30 +56,36 @@ #define INTEL_FAM6_IVYBRIDGE 0x3A #define INTEL_FAM6_IVYBRIDGE_X 0x3E -#define INTEL_FAM6_HASWELL_CORE 0x3C +#define INTEL_FAM6_HASWELL 0x3C #define INTEL_FAM6_HASWELL_X 0x3F -#define INTEL_FAM6_HASWELL_ULT 0x45 -#define INTEL_FAM6_HASWELL_GT3E 0x46 +#define INTEL_FAM6_HASWELL_L 0x45 +#define INTEL_FAM6_HASWELL_G 0x46 -#define INTEL_FAM6_BROADWELL_CORE 0x3D -#define INTEL_FAM6_BROADWELL_GT3E 0x47 +#define INTEL_FAM6_BROADWELL 0x3D +#define INTEL_FAM6_BROADWELL_G 0x47 #define INTEL_FAM6_BROADWELL_X 0x4F -#define INTEL_FAM6_BROADWELL_XEON_D 0x56 +#define INTEL_FAM6_BROADWELL_D 0x56 -#define INTEL_FAM6_SKYLAKE_MOBILE 0x4E -#define INTEL_FAM6_SKYLAKE_DESKTOP 0x5E +#define INTEL_FAM6_SKYLAKE_L 0x4E +#define INTEL_FAM6_SKYLAKE 0x5E #define INTEL_FAM6_SKYLAKE_X 0x55 -#define INTEL_FAM6_KABYLAKE_MOBILE 0x8E -#define INTEL_FAM6_KABYLAKE_DESKTOP 0x9E +#define INTEL_FAM6_KABYLAKE_L 0x8E +#define INTEL_FAM6_KABYLAKE 0x9E -#define INTEL_FAM6_CANNONLAKE_MOBILE 0x66 +#define INTEL_FAM6_CANNONLAKE_L 0x66 #define INTEL_FAM6_ICELAKE_X 0x6A -#define INTEL_FAM6_ICELAKE_XEON_D 0x6C -#define INTEL_FAM6_ICELAKE_DESKTOP 0x7D -#define INTEL_FAM6_ICELAKE_MOBILE 0x7E +#define INTEL_FAM6_ICELAKE_D 0x6C +#define INTEL_FAM6_ICELAKE 0x7D +#define INTEL_FAM6_ICELAKE_L 0x7E #define INTEL_FAM6_ICELAKE_NNPI 0x9D +#define INTEL_FAM6_TIGERLAKE_L 0x8C +#define INTEL_FAM6_TIGERLAKE 0x8D + +#define INTEL_FAM6_COMETLAKE 0xA5 +#define INTEL_FAM6_COMETLAKE_L 0xA6 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ @@ -68,17 +96,22 @@ #define INTEL_FAM6_ATOM_SALTWELL_TABLET 0x35 /* Cloverview */ #define INTEL_FAM6_ATOM_SILVERMONT 0x37 /* Bay Trail, Valleyview */ -#define INTEL_FAM6_ATOM_SILVERMONT_X 0x4D /* Avaton, Rangely */ +#define INTEL_FAM6_ATOM_SILVERMONT_D 0x4D /* Avaton, Rangely */ #define INTEL_FAM6_ATOM_SILVERMONT_MID 0x4A /* Merriefield */ #define INTEL_FAM6_ATOM_AIRMONT 0x4C /* Cherry Trail, Braswell */ #define INTEL_FAM6_ATOM_AIRMONT_MID 0x5A /* Moorefield */ +#define INTEL_FAM6_ATOM_AIRMONT_NP 0x75 /* Lightning Mountain */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */ -#define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */ +#define INTEL_FAM6_ATOM_GOLDMONT_D 0x5F /* Denverton */ + +/* Note: the micro-architecture is "Goldmont Plus" */ #define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */ -#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */ +#define INTEL_FAM6_ATOM_TREMONT_D 0x86 /* Jacobsville */ +#define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */ +#define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */ /* Xeon Phi */ diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h index 9e7adcdbe031..e6da1ce26256 100644 --- a/arch/x86/include/asm/intel_pmc_ipc.h +++ b/arch/x86/include/asm/intel_pmc_ipc.h @@ -31,30 +31,13 @@ #if IS_ENABLED(CONFIG_INTEL_PMC_IPC) -int intel_pmc_ipc_simple_command(int cmd, int sub); -int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, - u32 *out, u32 outlen, u32 dptr, u32 sptr); int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out, u32 outlen); int intel_pmc_s0ix_counter_read(u64 *data); -int intel_pmc_gcr_read(u32 offset, u32 *data); int intel_pmc_gcr_read64(u32 offset, u64 *data); -int intel_pmc_gcr_write(u32 offset, u32 data); -int intel_pmc_gcr_update(u32 offset, u32 mask, u32 val); #else -static inline int intel_pmc_ipc_simple_command(int cmd, int sub) -{ - return -EINVAL; -} - -static inline int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, - u32 *out, u32 outlen, u32 dptr, u32 sptr) -{ - return -EINVAL; -} - static inline int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out, u32 outlen) { @@ -66,26 +49,11 @@ static inline int intel_pmc_s0ix_counter_read(u64 *data) return -EINVAL; } -static inline int intel_pmc_gcr_read(u32 offset, u32 *data) -{ - return -EINVAL; -} - static inline int intel_pmc_gcr_read64(u32 offset, u64 *data) { return -EINVAL; } -static inline int intel_pmc_gcr_write(u32 offset, u32 data) -{ - return -EINVAL; -} - -static inline int intel_pmc_gcr_update(u32 offset, u32 mask, u32 val) -{ - return -EINVAL; -} - #endif /*CONFIG_INTEL_PMC_IPC*/ #endif diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h index 634f99b1dc22..423b788f495e 100644 --- a/arch/x86/include/asm/intel_pt.h +++ b/arch/x86/include/asm/intel_pt.h @@ -28,10 +28,12 @@ enum pt_capabilities { void cpu_emergency_stop_pt(void); extern u32 intel_pt_validate_hw_cap(enum pt_capabilities cap); extern u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities cap); +extern int is_intel_pt_event(struct perf_event *event); #else static inline void cpu_emergency_stop_pt(void) {} static inline u32 intel_pt_validate_hw_cap(enum pt_capabilities cap) { return 0; } static inline u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities capability) { return 0; } +static inline int is_intel_pt_event(struct perf_event *event) { return 0; } #endif #endif /* _ASM_X86_INTEL_PT_H */ diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h index 4a8c6e817398..2a1442ba6e78 100644 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ b/arch/x86/include/asm/intel_scu_ipc.h @@ -22,24 +22,12 @@ /* Read single register */ int intel_scu_ipc_ioread8(u16 addr, u8 *data); -/* Read two sequential registers */ -int intel_scu_ipc_ioread16(u16 addr, u16 *data); - -/* Read four sequential registers */ -int intel_scu_ipc_ioread32(u16 addr, u32 *data); - /* Read a vector */ int intel_scu_ipc_readv(u16 *addr, u8 *data, int len); /* Write single register */ int intel_scu_ipc_iowrite8(u16 addr, u8 data); -/* Write two sequential registers */ -int intel_scu_ipc_iowrite16(u16 addr, u16 data); - -/* Write four sequential registers */ -int intel_scu_ipc_iowrite32(u16 addr, u32 data); - /* Write a vector */ int intel_scu_ipc_writev(u16 *addr, u8 *data, int len); @@ -50,14 +38,6 @@ int intel_scu_ipc_update_register(u16 addr, u8 data, u8 mask); int intel_scu_ipc_simple_command(int cmd, int sub); int intel_scu_ipc_command(int cmd, int sub, u32 *in, int inlen, u32 *out, int outlen); -int intel_scu_ipc_raw_command(int cmd, int sub, u8 *in, int inlen, - u32 *out, int outlen, u32 dptr, u32 sptr); - -/* I2C control api */ -int intel_scu_ipc_i2c_cntrl(u32 addr, u32 *data); - -/* Update FW version */ -int intel_scu_ipc_fw_update(u8 *buffer, u32 length); extern struct blocking_notifier_head intel_scu_notifier; diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h index 214394860632..2f77e31a1283 100644 --- a/arch/x86/include/asm/intel_telemetry.h +++ b/arch/x86/include/asm/intel_telemetry.h @@ -40,13 +40,10 @@ struct telemetry_evtmap { struct telemetry_unit_config { struct telemetry_evtmap *telem_evts; void __iomem *regmap; - u32 ssram_base_addr; u8 ssram_evts_used; u8 curr_period; u8 max_period; u8 min_period; - u32 ssram_size; - }; struct telemetry_plt_config { diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 6bed97ff6db2..e1aa17a468a8 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -180,8 +180,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) * The default ioremap() behavior is non-cached; if you need something * else, you probably want one of the following. */ -extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); -#define ioremap_nocache ioremap_nocache extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); #define ioremap_uc ioremap_uc extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); @@ -205,10 +203,7 @@ extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long * If the area you are trying to map is a PCI BAR you should have a * look at pci_iomap(). */ -static inline void __iomem *ioremap(resource_size_t offset, unsigned long size) -{ - return ioremap_nocache(offset, size); -} +void __iomem *ioremap(resource_size_t offset, unsigned long size); #define ioremap ioremap extern void iounmap(volatile void __iomem *addr); @@ -404,4 +399,40 @@ extern bool arch_memremap_can_ram_remap(resource_size_t offset, extern bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size); +/** + * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units + * @__dst: destination, in MMIO space (must be 512-bit aligned) + * @src: source + * @count: number of 512 bits quantities to submit + * + * Submit data from kernel space to MMIO space, in units of 512 bits at a + * time. Order of access is not guaranteed, nor is a memory barrier + * performed afterwards. + * + * Warning: Do not use this helper unless your driver has checked that the CPU + * instruction is supported on the platform. + */ +static inline void iosubmit_cmds512(void __iomem *__dst, const void *src, + size_t count) +{ + /* + * Note that this isn't an "on-stack copy", just definition of "dst" + * as a pointer to 64-bytes of stuff that is going to be overwritten. + * In the MOVDIR64B case that may be needed as you can use the + * MOVDIR64B instruction to copy arbitrary memory around. This trick + * lets the compiler know how much gets clobbered. + */ + volatile struct { char _[64]; } *dst = __dst; + const u8 *from = src; + const u8 *end = from + count * 64; + + while (from < end) { + /* MOVDIR64B [rdx], rax */ + asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" + : "=m" (dst) + : "d" (from), "a" (dst)); + from += 64; + } +} + #endif /* _ASM_X86_IO_H */ diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h new file mode 100644 index 000000000000..02c6ef8f7667 --- /dev/null +++ b/arch/x86/include/asm/io_bitmap.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IOBITMAP_H +#define _ASM_X86_IOBITMAP_H + +#include <linux/refcount.h> +#include <asm/processor.h> + +struct io_bitmap { + u64 sequence; + refcount_t refcnt; + /* The maximum number of bytes to copy so all zero bits are covered */ + unsigned int max; + unsigned long bitmap[IO_BITMAP_LONGS]; +}; + +struct task_struct; + +#ifdef CONFIG_X86_IOPL_IOPERM +void io_bitmap_share(struct task_struct *tsk); +void io_bitmap_exit(void); + +void tss_update_io_bitmap(void); +#else +static inline void io_bitmap_share(struct task_struct *tsk) { } +static inline void io_bitmap_exit(void) { } +static inline void tss_update_io_bitmap(void) { } +#endif + +#endif diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index baedab8ac538..bf1ed2ddc74b 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -2,11 +2,28 @@ #ifndef _ASM_X86_IOMMU_H #define _ASM_X86_IOMMU_H +#include <linux/acpi.h> + +#include <asm/e820/api.h> + extern int force_iommu, no_iommu; extern int iommu_detected; -extern int iommu_pass_through; /* 10 seconds */ #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) +static inline int __init +arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr) +{ + u64 start = rmrr->base_address; + u64 end = rmrr->end_address + 1; + + if (e820__mapped_all(start, end, E820_TYPE_RESERVED)) + return 0; + + pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n", + start, end - 1); + return -EINVAL; +} + #endif /* _ASM_X86_IOMMU_H */ diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h deleted file mode 100644 index f73076be546a..000000000000 --- a/arch/x86/include/asm/ipi.h +++ /dev/null @@ -1,109 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _ASM_X86_IPI_H -#define _ASM_X86_IPI_H - -#ifdef CONFIG_X86_LOCAL_APIC - -/* - * Copyright 2004 James Cleverdon, IBM. - * - * Generic APIC InterProcessor Interrupt code. - * - * Moved to include file by James Cleverdon from - * arch/x86-64/kernel/smp.c - * - * Copyrights from kernel/smp.c: - * - * (c) 1995 Alan Cox, Building #3 <alan@redhat.com> - * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com> - * (c) 2002,2003 Andi Kleen, SuSE Labs. - */ - -#include <asm/hw_irq.h> -#include <asm/apic.h> -#include <asm/smp.h> - -/* - * the following functions deal with sending IPIs between CPUs. - * - * We use 'broadcast', CPU->CPU IPIs and self-IPIs too. - */ - -static inline unsigned int __prepare_ICR(unsigned int shortcut, int vector, - unsigned int dest) -{ - unsigned int icr = shortcut | dest; - - switch (vector) { - default: - icr |= APIC_DM_FIXED | vector; - break; - case NMI_VECTOR: - icr |= APIC_DM_NMI; - break; - } - return icr; -} - -static inline int __prepare_ICR2(unsigned int mask) -{ - return SET_APIC_DEST_FIELD(mask); -} - -static inline void __xapic_wait_icr_idle(void) -{ - while (native_apic_mem_read(APIC_ICR) & APIC_ICR_BUSY) - cpu_relax(); -} - -void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest); - -/* - * This is used to send an IPI with no shorthand notation (the destination is - * specified in bits 56 to 63 of the ICR). - */ -void __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest); - -extern void default_send_IPI_single(int cpu, int vector); -extern void default_send_IPI_single_phys(int cpu, int vector); -extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, - int vector); -extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, - int vector); - -/* Avoid include hell */ -#define NMI_VECTOR 0x02 - -extern int no_broadcast; - -static inline void __default_local_send_IPI_allbutself(int vector) -{ - if (no_broadcast || vector == NMI_VECTOR) - apic->send_IPI_mask_allbutself(cpu_online_mask, vector); - else - __default_send_IPI_shortcut(APIC_DEST_ALLBUT, vector, apic->dest_logical); -} - -static inline void __default_local_send_IPI_all(int vector) -{ - if (no_broadcast || vector == NMI_VECTOR) - apic->send_IPI_mask(cpu_online_mask, vector); - else - __default_send_IPI_shortcut(APIC_DEST_ALLINC, vector, apic->dest_logical); -} - -#ifdef CONFIG_X86_32 -extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, - int vector); -extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, - int vector); -extern void default_send_IPI_mask_logical(const struct cpumask *mask, - int vector); -extern void default_send_IPI_allbutself(int vector); -extern void default_send_IPI_all(int vector); -extern void default_send_IPI_self(int vector); -#endif - -#endif - -#endif /* _ASM_X86_IPI_H */ diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 8f95686ec27e..a176f6165d85 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -34,7 +34,7 @@ extern __visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs); extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); -extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); +extern void handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 75f1e35e7c15..247ab14c6309 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -33,6 +33,7 @@ enum show_regs_mode { }; extern void die(const char *, struct pt_regs *,long); +void die_addr(const char *str, struct pt_regs *regs, long err, long gp_addr); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); extern void __show_regs(struct pt_regs *regs, enum show_regs_mode); diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 5e7d6b46de97..6802c59e8252 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -66,10 +66,6 @@ struct kimage; # define KEXEC_ARCH KEXEC_ARCH_X86_64 #endif -/* Memory to backup during crash kdump */ -#define KEXEC_BACKUP_SRC_START (0UL) -#define KEXEC_BACKUP_SRC_END (640 * 1024UL - 1) /* 640K */ - /* * This function is responsible for capturing register states if coming * via panic otherwise just fix up the ss and sp if coming via kernel @@ -154,12 +150,6 @@ struct kimage_arch { pud_t *pud; pmd_t *pmd; pte_t *pte; - /* Details of backup region */ - unsigned long backup_src_start; - unsigned long backup_src_sz; - - /* Physical address of backup segment */ - unsigned long backup_load_addr; /* Core ELF header buffer */ void *elf_headers; diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 5dc909d9ad81..95b1f053bd96 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -11,12 +11,11 @@ #include <asm-generic/kprobes.h> -#define BREAKPOINT_INSTRUCTION 0xcc - #ifdef CONFIG_KPROBES #include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> +#include <asm/text-patching.h> #include <asm/insn.h> #define __ARCH_WANT_KPROBES_INSN_SLOT @@ -25,10 +24,7 @@ struct pt_regs; struct kprobe; typedef u8 kprobe_opcode_t; -#define RELATIVEJUMP_OPCODE 0xe9 -#define RELATIVEJUMP_SIZE 5 -#define RELATIVECALL_OPCODE 0xe8 -#define RELATIVE_ADDR_SIZE 4 + #define MAX_STACK_SIZE 64 #define CUR_STACK_SIZE(ADDR) \ (current_top_of_stack() - (unsigned long)(ADDR)) @@ -43,11 +39,11 @@ extern __visible kprobe_opcode_t optprobe_template_entry[]; extern __visible kprobe_opcode_t optprobe_template_val[]; extern __visible kprobe_opcode_t optprobe_template_call[]; extern __visible kprobe_opcode_t optprobe_template_end[]; -#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE) +#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + DISP32_SIZE) #define MAX_OPTINSN_SIZE \ (((unsigned long)optprobe_template_end - \ (unsigned long)optprobe_template_entry) + \ - MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE) + MAX_OPTIMIZED_LENGTH + JMP32_INSN_SIZE) extern const int kretprobe_blacklist_size; @@ -73,7 +69,7 @@ struct arch_specific_insn { struct arch_optimized_insn { /* copy of the original instructions */ - kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE]; + kprobe_opcode_t copied_insn[DISP32_SIZE]; /* detour code buffer */ kprobe_opcode_t *insn; /* the size of instructions copied to detour code buffer */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index feab24cac610..03946eb3e2b9 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -222,6 +222,10 @@ struct x86_emulate_ops { bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit); + bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt); + bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt); + bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt); + void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); @@ -229,7 +233,7 @@ struct x86_emulate_ops { int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate); void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt); - + int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); }; typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -429,6 +433,7 @@ enum x86_intercept { x86_intercept_ins, x86_intercept_out, x86_intercept_outs, + x86_intercept_xsetbv, nr_x86_intercepts }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 74e88e5edd9c..40a0c0fd95ca 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -78,6 +78,8 @@ #define KVM_REQ_HV_STIMER KVM_ARCH_REQ(22) #define KVM_REQ_LOAD_EOI_EXITMAP KVM_ARCH_REQ(23) #define KVM_REQ_GET_VMCS12_PAGES KVM_ARCH_REQ(24) +#define KVM_REQ_APICV_UPDATE \ + KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -156,10 +158,8 @@ enum kvm_reg { VCPU_REGS_R15 = __VCPU_REGS_R15, #endif VCPU_REGS_RIP, - NR_VCPU_REGS -}; + NR_VCPU_REGS, -enum kvm_reg_ex { VCPU_EXREG_PDPTR = NR_VCPU_REGS, VCPU_EXREG_CR3, VCPU_EXREG_RFLAGS, @@ -177,6 +177,11 @@ enum { VCPU_SREG_LDTR, }; +enum exit_fastpath_completion { + EXIT_FASTPATH_NONE, + EXIT_FASTPATH_SKIP_EMUL_INS, +}; + #include <asm/kvm_emulate.h> #define KVM_NR_MEM_OBJS 40 @@ -219,13 +224,6 @@ enum { PFERR_WRITE_MASK | \ PFERR_PRESENT_MASK) -/* - * The mask used to denote special SPTEs, which can be either MMIO SPTEs or - * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting - * with the SVE bit in EPT PTEs. - */ -#define SPTE_SPECIAL_MASK (1ULL << 62) - /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* @@ -319,8 +317,12 @@ struct kvm_rmap_head { struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; + struct list_head lpage_disallowed_link; + bool unsync; + u8 mmu_valid_gen; bool mmio_cached; + bool lpage_disallowed; /* Can't be replaced by an equiv large page */ /* * The following two entries are used to key the shadow page in the @@ -383,12 +385,12 @@ struct kvm_mmu { void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); - int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err, + int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err, bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access, - struct x86_exception *exception); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa, + u32 access, struct x86_exception *exception); gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, @@ -457,6 +459,11 @@ struct kvm_pmc { u64 eventsel; struct perf_event *perf_event; struct kvm_vcpu *vcpu; + /* + * eventsel value for general purpose counters, + * ctrl value for fixed counters. + */ + u64 current_config; }; struct kvm_pmu { @@ -475,7 +482,21 @@ struct kvm_pmu { struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED]; struct irq_work irq_work; - u64 reprogram_pmi; + DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); + DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX); + DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX); + + /* + * The gate to release perf_events not marked in + * pmc_in_use only once in a vcpu time slice. + */ + bool need_cleanup; + + /* + * The total number of programmed perf_events and it helps to avoid + * redundant check before cleanup if guest don't use vPMU at all. + */ + u8 event_count; }; struct kvm_pmu_ops; @@ -568,6 +589,7 @@ struct kvm_vcpu_arch { u64 smbase; u64 smi_count; bool tpr_access_reporting; + bool xsaves_enabled; u64 ia32_xss; u64 microcode_version; u64 arch_capabilities; @@ -591,7 +613,7 @@ struct kvm_vcpu_arch { * Paging state of an L2 guest (used for nested npt) * * This context will save all necessary information to walk page tables - * of the an L2 guest. This context is only initialized for page table + * of an L2 guest. This context is only initialized for page table * walking and not for faulting since we never handle l2 page faults on * the host. */ @@ -670,10 +692,10 @@ struct kvm_vcpu_arch { bool pvclock_set_guest_stopped_request; struct { + u8 preempted; u64 msr_val; u64 last_steal; - struct gfn_to_hva_cache stime; - struct kvm_steal_time steal; + struct gfn_to_pfn_cache cache; } st; u64 tsc_offset; @@ -717,7 +739,7 @@ struct kvm_vcpu_arch { /* Cache MMIO info */ u64 mmio_gva; - unsigned access; + unsigned mmio_access; gfn_t mmio_gfn; u64 mmio_gen; @@ -759,9 +781,19 @@ struct kvm_vcpu_arch { u64 msr_kvm_poll_control; /* - * Indicate whether the access faults on its page table in guest - * which is set when fix page fault and used to detect unhandeable - * instruction. + * Indicates the guest is trying to write a gfn that contains one or + * more of the PTEs used to translate the write itself, i.e. the access + * is changing its own translation in the guest page tables. KVM exits + * to userspace if emulation of the faulting instruction fails and this + * flag is set, as KVM cannot make forward progress. + * + * If emulation fails for a write to guest page tables, KVM unprotects + * (zaps) the shadow page for the target gfn and resumes the guest to + * retry the non-emulatable instruction (on hardware). Unprotecting the + * gfn doesn't allow forward progress for a self-changing access because + * doing so also zaps the translation for the gfn, i.e. retrying the + * instruction will hit a !PRESENT fault, which results in a new shadow + * page and sends KVM back to square one. */ bool write_fault_to_shadow_pgtable; @@ -843,6 +875,8 @@ struct kvm_hv { /* How many vCPUs have VP index != vCPU index */ atomic_t num_mismatched_vp_indexes; + + struct hv_partition_assist_pg *hv_pa_pg; }; enum kvm_irqchip_mode { @@ -851,16 +885,25 @@ enum kvm_irqchip_mode { KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; +#define APICV_INHIBIT_REASON_DISABLE 0 +#define APICV_INHIBIT_REASON_HYPERV 1 +#define APICV_INHIBIT_REASON_NESTED 2 +#define APICV_INHIBIT_REASON_IRQWIN 3 +#define APICV_INHIBIT_REASON_PIT_REINJ 4 + struct kvm_arch { unsigned long n_used_mmu_pages; unsigned long n_requested_mmu_pages; unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; + u8 mmu_valid_gen; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* * Hash table of struct kvm_mmu_page. */ struct list_head active_mmu_pages; + struct list_head zapped_obsolete_pages; + struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; @@ -879,6 +922,7 @@ struct kvm_arch { struct kvm_apic_map *apic_map; bool apic_access_page_done; + unsigned long apicv_inhibit_reasons; gpa_t wall_clock; @@ -935,6 +979,7 @@ struct kvm_arch { bool exception_payload_enabled; struct kvm_pmu_event_filter *pmu_event_filter; + struct task_struct *nx_lpage_recovery_thread; }; struct kvm_vm_stat { @@ -948,6 +993,7 @@ struct kvm_vm_stat { ulong mmu_unsync; ulong remote_tlb_flush; ulong lpages; + ulong nx_lpage_splits; ulong max_mmu_page_hash_collisions; }; @@ -1000,6 +1046,11 @@ struct kvm_lapic_irq { bool msi_redir_hint; }; +static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) +{ + return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; +} + struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ @@ -1018,7 +1069,7 @@ struct kvm_x86_ops { void (*vm_destroy)(struct kvm *kvm); /* Create, but do not attach this VCPU */ - struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id); + int (*vcpu_create)(struct kvm_vcpu *vcpu); void (*vcpu_free)(struct kvm_vcpu *vcpu); void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); @@ -1037,7 +1088,6 @@ struct kvm_x86_ops { struct kvm_segment *var, int seg); void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu); - void (*decache_cr3)(struct kvm_vcpu *vcpu); void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu); void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -1069,8 +1119,9 @@ struct kvm_x86_ops { void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr); void (*run)(struct kvm_vcpu *vcpu); - int (*handle_exit)(struct kvm_vcpu *vcpu); - void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + int (*handle_exit)(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath); + int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, @@ -1086,7 +1137,8 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); - bool (*get_enable_apicv)(struct kvm_vcpu *vcpu); + bool (*check_apicv_inhibit_reasons)(ulong bit); + void (*pre_update_apicv_exec_ctrl)(struct kvm *kvm, bool activate); void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); @@ -1119,11 +1171,13 @@ struct kvm_x86_ops { int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage); - void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu); + void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion *exit_fastpath); bool (*mpx_supported)(void); bool (*xsaves_supported)(void); bool (*umip_emulated)(void); bool (*pt_supported)(void); + bool (*pku_supported)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); @@ -1191,7 +1245,7 @@ struct kvm_x86_ops { int (*set_nested_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, struct kvm_nested_state *kvm_state); - void (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); + bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); int (*smi_allowed)(struct kvm_vcpu *vcpu); int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); @@ -1209,6 +1263,9 @@ struct kvm_x86_ops { uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu); bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu); + + bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); + int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { @@ -1308,26 +1365,53 @@ extern u64 kvm_default_tsc_scaling_ratio; extern u64 kvm_mce_cap_supported; -enum emulation_result { - EMULATE_DONE, /* no further processing */ - EMULATE_USER_EXIT, /* kvm_run ready for userspace exit */ - EMULATE_FAIL, /* can't emulate this instruction */ -}; - +/* + * EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing + * userspace I/O) to indicate that the emulation context + * should be resued as is, i.e. skip initialization of + * emulation context, instruction fetch and decode. + * + * EMULTYPE_TRAP_UD - Set when emulating an intercepted #UD from hardware. + * Indicates that only select instructions (tagged with + * EmulateOnUD) should be emulated (to minimize the emulator + * attack surface). See also EMULTYPE_TRAP_UD_FORCED. + * + * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to + * decode the instruction length. For use *only* by + * kvm_x86_ops->skip_emulated_instruction() implementations. + * + * EMULTYPE_ALLOW_RETRY - Set when the emulator should resume the guest to + * retry native execution under certain conditions. + * + * EMULTYPE_TRAP_UD_FORCED - Set when emulating an intercepted #UD that was + * triggered by KVM's magic "force emulation" prefix, + * which is opt in via module param (off by default). + * Bypasses EmulateOnUD restriction despite emulating + * due to an intercepted #UD (see EMULTYPE_TRAP_UD). + * Used to test the full emulator from userspace. + * + * EMULTYPE_VMWARE_GP - Set when emulating an intercepted #GP for VMware + * backdoor emulation, which is opt in via module param. + * VMware backoor emulation handles select instructions + * and reinjects the #GP for all other cases. + */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) #define EMULTYPE_ALLOW_RETRY (1 << 3) -#define EMULTYPE_NO_UD_ON_FAIL (1 << 4) -#define EMULTYPE_VMWARE (1 << 5) +#define EMULTYPE_TRAP_UD_FORCED (1 << 4) +#define EMULTYPE_VMWARE_GP (1 << 5) int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); -int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); -int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); +int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated); +int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data); +int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data); +int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu); +int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu); struct x86_emulate_ctxt; @@ -1413,11 +1497,15 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); -void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu); +bool kvm_apicv_activated(struct kvm *kvm); +void kvm_apicv_init(struct kvm *kvm, bool enable); +void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); +void kvm_request_apicv_update(struct kvm *kvm, bool activate, + unsigned long bit); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); @@ -1500,7 +1588,7 @@ enum { #define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) #define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) -asmlinkage void __noreturn kvm_spurious_fault(void); +asmlinkage void kvm_spurious_fault(void); /* * Hardware virtualization extension instructions may fault if a @@ -1508,24 +1596,14 @@ asmlinkage void __noreturn kvm_spurious_fault(void); * Usually after catching the fault we just panic; during reboot * instead the instruction is ignored. */ -#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn) \ +#define __kvm_handle_fault_on_reboot(insn) \ "666: \n\t" \ insn "\n\t" \ "jmp 668f \n\t" \ "667: \n\t" \ "call kvm_spurious_fault \n\t" \ "668: \n\t" \ - ".pushsection .fixup, \"ax\" \n\t" \ - "700: \n\t" \ - cleanup_insn "\n\t" \ - "cmpb $0, kvm_rebooting\n\t" \ - "je 667b \n\t" \ - "jmp 668b \n\t" \ - ".popsection \n\t" \ - _ASM_EXTABLE(666b, 700b) - -#define __kvm_handle_fault_on_reboot(insn) \ - ____kvm_handle_fault_on_reboot(insn, "") + _ASM_EXTABLE(666b, 667b) #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); @@ -1554,6 +1632,8 @@ bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); void kvm_make_mclock_inprogress_request(struct kvm *kvm); void kvm_make_scan_ioapic_request(struct kvm *kvm); +void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, + unsigned long *vcpu_bitmap); void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); @@ -1571,7 +1651,6 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu); int kvm_is_in_guest(void); int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); -int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); @@ -1581,6 +1660,13 @@ bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, struct kvm_lapic_irq *irq); +static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) +{ + /* We can only post Fixed and LowPrio IRQs */ + return (irq->delivery_mode == dest_Fixed || + irq->delivery_mode == dest_LowestPrio); +} + static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { if (kvm_x86_ops->vcpu_blocking) diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 14caa9d9fb7f..365111789cc6 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -13,10 +13,6 @@ #ifdef __ASSEMBLY__ -#define GLOBAL(name) \ - .globl name; \ - name: - #if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16) #define __ALIGN .p2align 4, 0x90 #define __ALIGN_STR __stringify(__ALIGN) diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index dc2d4b206ab7..4359b955e0b7 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -144,7 +144,7 @@ struct mce_log_buffer { enum mce_notifier_prios { MCE_PRIO_FIRST = INT_MAX, - MCE_PRIO_SRAO = INT_MAX - 1, + MCE_PRIO_UC = INT_MAX - 1, MCE_PRIO_EXTLOG = INT_MAX - 2, MCE_PRIO_NFIT = INT_MAX - 3, MCE_PRIO_EDAC = INT_MAX - 4, @@ -290,6 +290,7 @@ extern void apei_mce_report_mem_error(int corrected, /* These may be used by multiple smca_hwid_mcatypes */ enum smca_bank_types { SMCA_LS = 0, /* Load Store */ + SMCA_LS_V2, /* Load Store */ SMCA_IF, /* Instruction Fetch */ SMCA_L2_CACHE, /* L2 Cache */ SMCA_DE, /* Decoder Unit */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 0c196c47d621..848ce43b9040 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -92,6 +92,16 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; +static inline bool mem_encrypt_active(void) +{ + return sme_me_mask; +} + +static inline u64 sme_get_me_mask(void) +{ + return sme_me_mask; +} + #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/memtype.h b/arch/x86/include/asm/memtype.h new file mode 100644 index 000000000000..9c2447b3555d --- /dev/null +++ b/arch/x86/include/asm/memtype.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MEMTYPE_H +#define _ASM_X86_MEMTYPE_H + +#include <linux/types.h> +#include <asm/pgtable_types.h> + +extern bool pat_enabled(void); +extern void pat_disable(const char *reason); +extern void pat_init(void); +extern void init_cache_modes(void); + +extern int memtype_reserve(u64 start, u64 end, + enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); +extern int memtype_free(u64 start, u64 end); + +extern int memtype_kernel_map_sync(u64 base, unsigned long size, + enum page_cache_mode pcm); + +extern int memtype_reserve_io(resource_size_t start, resource_size_t end, + enum page_cache_mode *pcm); + +extern void memtype_free_io(resource_size_t start, resource_size_t end); + +extern bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn); + +#endif /* _ASM_X86_MEMTYPE_H */ diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 209492849566..6685e1218959 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -53,6 +53,6 @@ static inline void __init load_ucode_amd_bsp(unsigned int family) {} static inline void load_ucode_amd_ap(unsigned int family) {} static inline int __init save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } -void reload_ucode_amd(void) {} +static inline void reload_ucode_amd(void) {} #endif #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index e78c7db87801..bdeae9291e5c 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -50,10 +50,6 @@ typedef struct { u16 pkey_allocation_map; s16 execute_only_pkey; #endif -#ifdef CONFIG_X86_INTEL_MPX - /* address of the bounds directory */ - void __user *bd_addr; -#endif } mm_context_t; #define INIT_MM_CONTEXT(mm) \ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 9024236693d2..b538d9ddee9c 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -12,7 +12,6 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/paravirt.h> -#include <asm/mpx.h> #include <asm/debugreg.h> extern atomic64_t last_mm_ctx_id; @@ -26,18 +25,20 @@ static inline void paravirt_activate_mm(struct mm_struct *prev, #ifdef CONFIG_PERF_EVENTS +DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key); DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key); -static inline void load_mm_cr4(struct mm_struct *mm) +static inline void load_mm_cr4_irqsoff(struct mm_struct *mm) { if (static_branch_unlikely(&rdpmc_always_available_key) || - atomic_read(&mm->context.perf_rdpmc_allowed)) - cr4_set_bits(X86_CR4_PCE); + (!static_branch_unlikely(&rdpmc_never_available_key) && + atomic_read(&mm->context.perf_rdpmc_allowed))) + cr4_set_bits_irqsoff(X86_CR4_PCE); else - cr4_clear_bits(X86_CR4_PCE); + cr4_clear_bits_irqsoff(X86_CR4_PCE); } #else -static inline void load_mm_cr4(struct mm_struct *mm) {} +static inline void load_mm_cr4_irqsoff(struct mm_struct *mm) {} #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL @@ -67,14 +68,6 @@ struct ldt_struct { int slot; }; -/* This is a multiple of PAGE_SIZE. */ -#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) - -static inline void *ldt_slot_va(int slot) -{ - return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); -} - /* * Used for LDT copy/destruction. */ @@ -97,87 +90,21 @@ static inline void destroy_context_ldt(struct mm_struct *mm) { } static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif -static inline void load_mm_ldt(struct mm_struct *mm) -{ #ifdef CONFIG_MODIFY_LDT_SYSCALL - struct ldt_struct *ldt; - - /* READ_ONCE synchronizes with smp_store_release */ - ldt = READ_ONCE(mm->context.ldt); - - /* - * Any change to mm->context.ldt is followed by an IPI to all - * CPUs with the mm active. The LDT will not be freed until - * after the IPI is handled by all such CPUs. This means that, - * if the ldt_struct changes before we return, the values we see - * will be safe, and the new values will be loaded before we run - * any user code. - * - * NB: don't try to convert this to use RCU without extreme care. - * We would still need IRQs off, because we don't want to change - * the local LDT after an IPI loaded a newer value than the one - * that we can see. - */ - - if (unlikely(ldt)) { - if (static_cpu_has(X86_FEATURE_PTI)) { - if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { - /* - * Whoops -- either the new LDT isn't mapped - * (if slot == -1) or is mapped into a bogus - * slot (if slot > 1). - */ - clear_LDT(); - return; - } - - /* - * If page table isolation is enabled, ldt->entries - * will not be mapped in the userspace pagetables. - * Tell the CPU to access the LDT through the alias - * at ldt_slot_va(ldt->slot). - */ - set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); - } else { - set_ldt(ldt->entries, ldt->nr_entries); - } - } else { - clear_LDT(); - } +extern void load_mm_ldt(struct mm_struct *mm); +extern void switch_ldt(struct mm_struct *prev, struct mm_struct *next); #else +static inline void load_mm_ldt(struct mm_struct *mm) +{ clear_LDT(); -#endif } - static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) { -#ifdef CONFIG_MODIFY_LDT_SYSCALL - /* - * Load the LDT if either the old or new mm had an LDT. - * - * An mm will never go from having an LDT to not having an LDT. Two - * mms never share an LDT, so we don't gain anything by checking to - * see whether the LDT changed. There's also no guarantee that - * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, - * then prev->context.ldt will also be non-NULL. - * - * If we really cared, we could optimize the case where prev == next - * and we're exiting lazy mode. Most of the time, if this happens, - * we don't actually need to reload LDTR, but modify_ldt() is mostly - * used by legacy code and emulators where we don't need this level of - * performance. - * - * This uses | instead of || because it generates better code. - */ - if (unlikely((unsigned long)prev->context.ldt | - (unsigned long)next->context.ldt)) - load_mm_ldt(next); -#endif - DEBUG_LOCKS_WARN_ON(preemptible()); } +#endif -void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); +extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); /* * Init a new mm. Used on mm copies, like at fork() @@ -272,34 +199,9 @@ static inline bool is_64bit_mm(struct mm_struct *mm) } #endif -static inline void arch_bprm_mm_init(struct mm_struct *mm, - struct vm_area_struct *vma) -{ - mpx_mm_init(mm); -} - static inline void arch_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { - /* - * mpx_notify_unmap() goes and reads a rarely-hot - * cacheline in the mm_struct. That can be expensive - * enough to be seen in profiles. - * - * The mpx_notify_unmap() call and its contents have been - * observed to affect munmap() performance on hardware - * where MPX is not present. - * - * The unlikely() optimizes for the fast case: no MPX - * in the CPU, or no MPX use in the process. Even if - * we get this wrong (in the unlikely event that MPX - * is widely enabled on some system) the overhead of - * MPX itself (reading bounds tables) is expected to - * overwhelm the overhead of getting this unlikely() - * consistently wrong. - */ - if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX))) - mpx_notify_unmap(mm, start, end); } /* diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index 7948a17febb4..c215d2762488 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -15,6 +15,8 @@ struct mod_arch_specific { #ifdef CONFIG_X86_64 /* X86_64 does not define MODULE_PROC_FAMILY */ +#elif defined CONFIG_M486SX +#define MODULE_PROC_FAMILY "486SX " #elif defined CONFIG_M486 #define MODULE_PROC_FAMILY "486 " #elif defined CONFIG_M586 diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h deleted file mode 100644 index 143a5c193ed3..000000000000 --- a/arch/x86/include/asm/mpx.h +++ /dev/null @@ -1,116 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_MPX_H -#define _ASM_X86_MPX_H - -#include <linux/types.h> -#include <linux/mm_types.h> - -#include <asm/ptrace.h> -#include <asm/insn.h> - -/* - * NULL is theoretically a valid place to put the bounds - * directory, so point this at an invalid address. - */ -#define MPX_INVALID_BOUNDS_DIR ((void __user *)-1) -#define MPX_BNDCFG_ENABLE_FLAG 0x1 -#define MPX_BD_ENTRY_VALID_FLAG 0x1 - -/* - * The upper 28 bits [47:20] of the virtual address in 64-bit - * are used to index into bounds directory (BD). - * - * The directory is 2G (2^31) in size, and with 8-byte entries - * it has 2^28 entries. - */ -#define MPX_BD_SIZE_BYTES_64 (1UL<<31) -#define MPX_BD_ENTRY_BYTES_64 8 -#define MPX_BD_NR_ENTRIES_64 (MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64) - -/* - * The 32-bit directory is 4MB (2^22) in size, and with 4-byte - * entries it has 2^20 entries. - */ -#define MPX_BD_SIZE_BYTES_32 (1UL<<22) -#define MPX_BD_ENTRY_BYTES_32 4 -#define MPX_BD_NR_ENTRIES_32 (MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32) - -/* - * A 64-bit table is 4MB total in size, and an entry is - * 4 64-bit pointers in size. - */ -#define MPX_BT_SIZE_BYTES_64 (1UL<<22) -#define MPX_BT_ENTRY_BYTES_64 32 -#define MPX_BT_NR_ENTRIES_64 (MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64) - -/* - * A 32-bit table is 16kB total in size, and an entry is - * 4 32-bit pointers in size. - */ -#define MPX_BT_SIZE_BYTES_32 (1UL<<14) -#define MPX_BT_ENTRY_BYTES_32 16 -#define MPX_BT_NR_ENTRIES_32 (MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32) - -#define MPX_BNDSTA_TAIL 2 -#define MPX_BNDCFG_TAIL 12 -#define MPX_BNDSTA_ADDR_MASK (~((1UL<<MPX_BNDSTA_TAIL)-1)) -#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1)) -#define MPX_BNDSTA_ERROR_CODE 0x3 - -struct mpx_fault_info { - void __user *addr; - void __user *lower; - void __user *upper; -}; - -#ifdef CONFIG_X86_INTEL_MPX - -extern int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs); -extern int mpx_handle_bd_fault(void); - -static inline int kernel_managing_mpx_tables(struct mm_struct *mm) -{ - return (mm->context.bd_addr != MPX_INVALID_BOUNDS_DIR); -} - -static inline void mpx_mm_init(struct mm_struct *mm) -{ - /* - * NULL is theoretically a valid place to put the bounds - * directory, so point this at an invalid address. - */ - mm->context.bd_addr = MPX_INVALID_BOUNDS_DIR; -} - -extern void mpx_notify_unmap(struct mm_struct *mm, unsigned long start, unsigned long end); -extern unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, unsigned long flags); - -#else -static inline int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs) -{ - return -EINVAL; -} -static inline int mpx_handle_bd_fault(void) -{ - return -EINVAL; -} -static inline int kernel_managing_mpx_tables(struct mm_struct *mm) -{ - return 0; -} -static inline void mpx_mm_init(struct mm_struct *mm) -{ -} -static inline void mpx_notify_unmap(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ -} - -static inline unsigned long mpx_unmapped_area_check(unsigned long addr, - unsigned long len, unsigned long flags) -{ - return addr; -} -#endif /* CONFIG_X86_INTEL_MPX */ - -#endif /* _ASM_X86_MPX_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 2ef31cc8c529..6b79515abb82 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -218,7 +218,9 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) void __init hyperv_init(void); void hyperv_setup_mmu_ops(void); - +void *hv_alloc_hyperv_page(void); +void *hv_alloc_hyperv_zeroed_page(void); +void hv_free_hyperv_page(unsigned long addr); void hyperv_reenlightenment_intr(struct pt_regs *regs); void set_hv_tscchange_cb(void (*cb)(void)); void clear_hv_tscchange_cb(void); @@ -241,6 +243,8 @@ static inline void hv_apic_init(void) {} #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} static inline void hyperv_setup_mmu_ops(void) {} +static inline void *hv_alloc_hyperv_page(void) { return NULL; } +static inline void hv_free_hyperv_page(unsigned long addr) {} static inline void set_hv_tscchange_cb(void (*cb)(void)) {} static inline void clear_hv_tscchange_cb(void) {} static inline void hyperv_stop_tsc_emulation(void) {}; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 6b4fc2788078..ebe1685e92dd 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -93,6 +93,18 @@ * Microarchitectural Data * Sampling (MDS) vulnerabilities. */ +#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /* + * The processor is not susceptible to a + * machine check error due to modifying the + * code page size along with either the + * physical address or cache type + * without TLB invalidation. + */ +#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */ +#define ARCH_CAP_TAA_NO BIT(8) /* + * Not susceptible to + * TSX Async Abort (TAA) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -103,6 +115,10 @@ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e +#define MSR_IA32_TSX_CTRL 0x00000122 +#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ +#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 @@ -375,15 +391,26 @@ /* Alternative perfctr range with full access. */ #define MSR_IA32_PMC0 0x000004c1 -/* AMD64 MSRs. Not complete. See the architecture manual for a more - complete list. */ +/* Auto-reload via MSR instead of DS area */ +#define MSR_RELOAD_PMC0 0x000014c1 +#define MSR_RELOAD_FIXED_CTR0 0x00001309 +/* + * AMD64 MSRs. Not complete. See the architecture manual for a more + * complete list. + */ #define MSR_AMD64_PATCH_LEVEL 0x0000008b #define MSR_AMD64_TSC_RATIO 0xc0000104 #define MSR_AMD64_NB_CFG 0xc001001f +#define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_PATCH_LOADER 0xc0010020 +#define MSR_AMD_PERF_CTL 0xc0010062 +#define MSR_AMD_PERF_STATUS 0xc0010063 +#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 +#define MSR_AMD_PPIN_CTL 0xc00102f0 +#define MSR_AMD_PPIN 0xc00102f1 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 #define MSR_AMD64_BU_CFG2 0xc001102a @@ -531,7 +558,14 @@ #define MSR_IA32_EBL_CR_POWERON 0x0000002a #define MSR_EBC_FREQUENCY_ID 0x0000002c #define MSR_SMI_COUNT 0x00000034 -#define MSR_IA32_FEATURE_CONTROL 0x0000003a + +/* Referred to as IA32_FEATURE_CONTROL in Intel's SDM. */ +#define MSR_IA32_FEAT_CTL 0x0000003a +#define FEAT_CTL_LOCKED BIT(0) +#define FEAT_CTL_VMX_ENABLED_INSIDE_SMX BIT(1) +#define FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX BIT(2) +#define FEAT_CTL_LMCE_ENABLED BIT(20) + #define MSR_IA32_TSC_ADJUST 0x0000003b #define MSR_IA32_BNDCFGS 0x00000d90 @@ -539,11 +573,6 @@ #define MSR_IA32_XSS 0x00000da0 -#define FEATURE_CONTROL_LOCKED (1<<0) -#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1) -#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2) -#define FEATURE_CONTROL_LMCE (1<<20) - #define MSR_IA32_APICBASE 0x0000001b #define MSR_IA32_APICBASE_BSP (1<<8) #define MSR_IA32_APICBASE_ENABLE (1<<11) @@ -560,9 +589,6 @@ #define MSR_IA32_PERF_STATUS 0x00000198 #define MSR_IA32_PERF_CTL 0x00000199 #define INTEL_PERF_CTL_MASK 0xffff -#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 -#define MSR_AMD_PERF_STATUS 0xc0010063 -#define MSR_AMD_PERF_CTL 0xc0010062 #define MSR_IA32_MPERF 0x000000e7 #define MSR_IA32_APERF 0x000000e8 diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 5cc3930cb465..86f20d520a07 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -233,8 +233,7 @@ static __always_inline unsigned long long rdtsc_ordered(void) * Thus, use the preferred barrier on the respective CPU, aiming for * RDTSCP as the default. */ - asm volatile(ALTERNATIVE_3("rdtsc", - "mfence; rdtsc", X86_FEATURE_MFENCE_RDTSC, + asm volatile(ALTERNATIVE_2("rdtsc", "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC, "rdtscp", X86_FEATURE_RDTSCP) : EAX_EDX_RET(val, low, high) diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index dbff1456d215..829df26fd7a3 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -24,7 +24,7 @@ #define _ASM_X86_MTRR_H #include <uapi/asm/mtrr.h> -#include <asm/pat.h> +#include <asm/memtype.h> /* @@ -86,7 +86,7 @@ static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) } static inline void mtrr_bp_init(void) { - pat_disable("MTRRs disabled, skipping PAT initialization too."); + pat_disable("PAT support disabled because CONFIG_MTRR is disabled in the kernel."); } #define mtrr_ap_init() do {} while (0) diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index e28f8b723b5c..9d5252c9685c 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -21,7 +21,7 @@ #define MWAIT_ECX_INTERRUPT_BREAK 0x1 #define MWAITX_ECX_TIMER_ENABLE BIT(1) #define MWAITX_MAX_LOOPS ((u32)-1) -#define MWAITX_DISABLE_CSTATES 0xf +#define MWAITX_DISABLE_CSTATES 0xf0 static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 75ded1d13d98..9d5d949e662e 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -41,7 +41,6 @@ struct nmiaction { struct list_head list; nmi_handler_t handler; u64 max_duration; - struct irq_work irq_work; unsigned long flags; const char *name; }; diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 109f974f9835..07e95dcb40ad 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -37,7 +37,6 @@ */ #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ /* * Google experimented with loop-unrolling and this turned out to be @@ -192,7 +191,7 @@ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ - "903: addl $4, %%esp;\n" \ + "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \ @@ -314,7 +313,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); #include <asm/segment.h> /** - * mds_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the @@ -337,7 +336,7 @@ static inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index dce26f1d13e1..86e7317eb31f 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -139,18 +139,6 @@ static inline void __write_cr4(unsigned long x) PVOP_VCALL1(cpu.write_cr4, x); } -#ifdef CONFIG_X86_64 -static inline unsigned long read_cr8(void) -{ - return PVOP_CALL0(unsigned long, cpu.read_cr8); -} - -static inline void write_cr8(unsigned long x) -{ - PVOP_VCALL1(cpu.write_cr8, x); -} -#endif - static inline void arch_safe_halt(void) { PVOP_VCALL0(irq.safe_halt); @@ -306,10 +294,6 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) { PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g); } -static inline void set_iopl_mask(unsigned mask) -{ - PVOP_VCALL1(cpu.set_iopl_mask, mask); -} static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 639b2df445ee..84812964d3dd 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -119,11 +119,6 @@ struct pv_cpu_ops { void (*write_cr4)(unsigned long); -#ifdef CONFIG_X86_64 - unsigned long (*read_cr8)(void); - void (*write_cr8)(unsigned long); -#endif - /* Segment descriptor handling */ void (*load_tr_desc)(void); void (*load_gdt)(const struct desc_ptr *); @@ -145,8 +140,6 @@ struct pv_cpu_ops { void (*load_sp0)(unsigned long sp0); - void (*set_iopl_mask)(unsigned mask); - void (*wbinvd)(void); /* cpuid emulation, mostly so that caps bits can be disabled */ diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h deleted file mode 100644 index 92015c65fa2a..000000000000 --- a/arch/x86/include/asm/pat.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_PAT_H -#define _ASM_X86_PAT_H - -#include <linux/types.h> -#include <asm/pgtable_types.h> - -bool pat_enabled(void); -void pat_disable(const char *reason); -extern void pat_init(void); -extern void init_cache_modes(void); - -extern int reserve_memtype(u64 start, u64 end, - enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); -extern int free_memtype(u64 start, u64 end); - -extern int kernel_map_sync_memtype(u64 base, unsigned long size, - enum page_cache_mode pcm); - -int io_reserve_memtype(resource_size_t start, resource_size_t end, - enum page_cache_mode *pcm); - -void io_free_memtype(resource_size_t start, resource_size_t end); - -bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn); - -#endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index e662f987dfa2..7ccb338507e3 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -9,11 +9,9 @@ #include <linux/scatterlist.h> #include <linux/numa.h> #include <asm/io.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/x86_init.h> -#ifdef __KERNEL__ - struct pci_sysdata { int domain; /* PCI domain */ int node; /* NUMA node */ @@ -27,7 +25,7 @@ struct pci_sysdata { void *fwnode; /* IRQ domain for MSI assignment */ #endif #if IS_ENABLED(CONFIG_VMD) - bool vmd_domain; /* True if in Intel VMD domain */ + struct pci_dev *vmd_dev; /* VMD Device if in Intel VMD domain */ #endif }; @@ -35,14 +33,17 @@ extern int pci_routeirq; extern int noioapicquirk; extern int noioapicreroute; +static inline struct pci_sysdata *to_pci_sysdata(const struct pci_bus *bus) +{ + return bus->sysdata; +} + #ifdef CONFIG_PCI #ifdef CONFIG_PCI_DOMAINS static inline int pci_domain_nr(struct pci_bus *bus) { - struct pci_sysdata *sd = bus->sysdata; - - return sd->domain; + return to_pci_sysdata(bus)->domain; } static inline int pci_proc_domain(struct pci_bus *bus) @@ -54,24 +55,20 @@ static inline int pci_proc_domain(struct pci_bus *bus) #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN static inline void *_pci_root_bus_fwnode(struct pci_bus *bus) { - struct pci_sysdata *sd = bus->sysdata; - - return sd->fwnode; + return to_pci_sysdata(bus)->fwnode; } #define pci_root_bus_fwnode _pci_root_bus_fwnode #endif +#if IS_ENABLED(CONFIG_VMD) static inline bool is_vmd(struct pci_bus *bus) { -#if IS_ENABLED(CONFIG_VMD) - struct pci_sysdata *sd = bus->sysdata; - - return sd->vmd_domain; -#else - return false; -#endif + return to_pci_sysdata(bus)->vmd_dev != NULL; } +#else +#define is_vmd(bus) false +#endif /* CONFIG_VMD */ /* Can be used to override the logic in pci_scan_bus for skipping already-configured bus numbers - to be used for buggy BIOSes @@ -118,11 +115,6 @@ void native_restore_msi_irqs(struct pci_dev *dev); #define native_setup_msi_irqs NULL #define native_teardown_msi_irq NULL #endif -#endif /* __KERNEL__ */ - -#ifdef CONFIG_X86_64 -#include <asm/pci_64.h> -#endif /* generic pci stuff */ #include <asm-generic/pci.h> @@ -131,9 +123,7 @@ void native_restore_msi_irqs(struct pci_dev *dev); /* Returns the node based on pci bus */ static inline int __pcibus_to_node(const struct pci_bus *bus) { - const struct pci_sysdata *sd = bus->sysdata; - - return sd->node; + return to_pci_sysdata(bus)->node; } static inline const struct cpumask * diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h deleted file mode 100644 index f5411de0ae11..000000000000 --- a/arch/x86/include/asm/pci_64.h +++ /dev/null @@ -1,28 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_PCI_64_H -#define _ASM_X86_PCI_64_H - -#ifdef __KERNEL__ - -#ifdef CONFIG_CALGARY_IOMMU -static inline void *pci_iommu(struct pci_bus *bus) -{ - struct pci_sysdata *sd = bus->sysdata; - return sd->iommu; -} - -static inline void set_pci_iommu(struct pci_bus *bus, void *val) -{ - struct pci_sysdata *sd = bus->sysdata; - sd->iommu = val; -} -#endif /* CONFIG_CALGARY_IOMMU */ - -extern int (*pci_config_read)(int seg, int bus, int dev, int fn, - int reg, int len, u32 *value); -extern int (*pci_config_write)(int seg, int bus, int dev, int fn, - int reg, int len, u32 value); - -#endif /* __KERNEL__ */ - -#endif /* _ASM_X86_PCI_64_H */ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 1392d5e6e8d6..29964b0e1075 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -252,16 +252,20 @@ struct pebs_lbr { #define IBSCTL_LVT_OFFSET_VALID (1ULL<<8) #define IBSCTL_LVT_OFFSET_MASK 0x0F -/* ibs fetch bits/masks */ +/* IBS fetch bits/masks */ #define IBS_FETCH_RAND_EN (1ULL<<57) #define IBS_FETCH_VAL (1ULL<<49) #define IBS_FETCH_ENABLE (1ULL<<48) #define IBS_FETCH_CNT 0xFFFF0000ULL #define IBS_FETCH_MAX_CNT 0x0000FFFFULL -/* ibs op bits/masks */ -/* lower 4 bits of the current count are ignored: */ -#define IBS_OP_CUR_CNT (0xFFFF0ULL<<32) +/* + * IBS op bits/masks + * The lower 7 bits of the current count are random bits + * preloaded by hardware and ignored in software + */ +#define IBS_OP_CUR_CNT (0xFFF80ULL<<32) +#define IBS_OP_CUR_CNT_RAND (0x0007FULL<<32) #define IBS_OP_CNT_CTL (1ULL<<19) #define IBS_OP_VAL (1ULL<<18) #define IBS_OP_ENABLE (1ULL<<17) @@ -318,17 +322,10 @@ struct perf_guest_switch_msr { u64 host, guest; }; -extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); extern void perf_check_microcode(void); extern int x86_perf_rdpmc_index(struct perf_event *event); #else -static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) -{ - *nr = 0; - return NULL; -} - static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) { memset(cap, 0, sizeof(*cap)); @@ -338,8 +335,23 @@ static inline void perf_events_lapic_init(void) { } static inline void perf_check_microcode(void) { } #endif +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) +extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); +#else +static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) +{ + *nr = 0; + return NULL; +} +#endif + #ifdef CONFIG_CPU_SUP_INTEL extern void intel_pt_handle_vmx(int on); +#else +static inline void intel_pt_handle_vmx(int on) +{ + +} #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index e3633795fb22..5afb5e0fe903 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -36,39 +36,41 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte) #define pmd_read_atomic pmd_read_atomic /* - * pte_offset_map_lock on 32bit PAE kernels was reading the pmd_t with - * a "*pmdp" dereference done by gcc. Problem is, in certain places - * where pte_offset_map_lock is called, concurrent page faults are + * pte_offset_map_lock() on 32-bit PAE kernels was reading the pmd_t with + * a "*pmdp" dereference done by GCC. Problem is, in certain places + * where pte_offset_map_lock() is called, concurrent page faults are * allowed, if the mmap_sem is hold for reading. An example is mincore * vs page faults vs MADV_DONTNEED. On the page fault side - * pmd_populate rightfully does a set_64bit, but if we're reading the + * pmd_populate() rightfully does a set_64bit(), but if we're reading the * pmd_t with a "*pmdp" on the mincore side, a SMP race can happen - * because gcc will not read the 64bit of the pmd atomically. To fix - * this all places running pmd_offset_map_lock() while holding the + * because GCC will not read the 64-bit value of the pmd atomically. + * + * To fix this all places running pte_offset_map_lock() while holding the * mmap_sem in read mode, shall read the pmdp pointer using this - * function to know if the pmd is null nor not, and in turn to know if - * they can run pmd_offset_map_lock or pmd_trans_huge or other pmd + * function to know if the pmd is null or not, and in turn to know if + * they can run pte_offset_map_lock() or pmd_trans_huge() or other pmd * operations. * - * Without THP if the mmap_sem is hold for reading, the pmd can only - * transition from null to not null while pmd_read_atomic runs. So + * Without THP if the mmap_sem is held for reading, the pmd can only + * transition from null to not null while pmd_read_atomic() runs. So * we can always return atomic pmd values with this function. * - * With THP if the mmap_sem is hold for reading, the pmd can become + * With THP if the mmap_sem is held for reading, the pmd can become * trans_huge or none or point to a pte (and in turn become "stable") - * at any time under pmd_read_atomic. We could read it really - * atomically here with a atomic64_read for the THP enabled case (and + * at any time under pmd_read_atomic(). We could read it truly + * atomically here with an atomic64_read() for the THP enabled case (and * it would be a whole lot simpler), but to avoid using cmpxchg8b we * only return an atomic pmdval if the low part of the pmdval is later - * found stable (i.e. pointing to a pte). And we're returning a none - * pmdval if the low part of the pmd is none. In some cases the high - * and low part of the pmdval returned may not be consistent if THP is - * enabled (the low part may point to previously mapped hugepage, - * while the high part may point to a more recently mapped hugepage), - * but pmd_none_or_trans_huge_or_clear_bad() only needs the low part - * of the pmd to be read atomically to decide if the pmd is unstable - * or not, with the only exception of when the low part of the pmd is - * zero in which case we return a none pmd. + * found to be stable (i.e. pointing to a pte). We are also returning a + * 'none' (zero) pmdval if the low part of the pmd is zero. + * + * In some cases the high and low part of the pmdval returned may not be + * consistent if THP is enabled (the low part may point to previously + * mapped hugepage, while the high part may point to a more recently + * mapped hugepage), but pmd_none_or_trans_huge_or_clear_bad() only + * needs the low part of the pmd to be read atomically to decide if the + * pmd is unstable or not, with the only exception when the low part + * of the pmd is zero, in which case we return a 'none' pmd. */ static inline pmd_t pmd_read_atomic(pmd_t *pmdp) { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 0bc530c4eb13..7e118660bbd9 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -29,8 +29,9 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD]; int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); -void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); -void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user); +void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); +void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, + bool user); void ptdump_walk_pgd_level_checkwx(void); void ptdump_walk_user_pgd_level_checkwx(void); @@ -239,6 +240,7 @@ static inline unsigned long pgd_pfn(pgd_t pgd) return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; } +#define p4d_leaf p4d_large static inline int p4d_large(p4d_t p4d) { /* No 512 GiB pages yet */ @@ -247,6 +249,7 @@ static inline int p4d_large(p4d_t p4d) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) +#define pmd_leaf pmd_large static inline int pmd_large(pmd_t pte) { return pmd_flags(pte) & _PAGE_PSE; @@ -874,6 +877,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); } +#define pud_leaf pud_large static inline int pud_large(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) == @@ -885,6 +889,7 @@ static inline int pud_bad(pud_t pud) return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; } #else +#define pud_leaf pud_large static inline int pud_large(pud_t pud) { return 0; @@ -1233,6 +1238,7 @@ static inline bool pgdp_maps_userspace(void *__ptr) return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); } +#define pgd_leaf pgd_large static inline int pgd_large(pgd_t pgd) { return 0; } #ifdef CONFIG_PAGE_TABLE_ISOLATION @@ -1463,6 +1469,12 @@ static inline bool arch_has_pfn_modify_check(void) return boot_cpu_has_bug(X86_BUG_L1TF); } +#define arch_faults_on_old_pte arch_faults_on_old_pte +static inline bool arch_faults_on_old_pte(void) +{ + return false; +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index c78da8eda8f2..0dca7f7aeff2 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -29,8 +29,6 @@ extern pgd_t swapper_pg_dir[1024]; extern pgd_t initial_page_table[1024]; extern pmd_t initial_pg_pmd[]; -static inline void pgtable_cache_init(void) { } -static inline void check_pgt_cache(void) { } void paging_init(void); void sync_initial_page_table(void); diff --git a/arch/x86/include/asm/pgtable_32_areas.h b/arch/x86/include/asm/pgtable_32_areas.h new file mode 100644 index 000000000000..b6355416a15a --- /dev/null +++ b/arch/x86/include/asm/pgtable_32_areas.h @@ -0,0 +1,53 @@ +#ifndef _ASM_X86_PGTABLE_32_AREAS_H +#define _ASM_X86_PGTABLE_32_AREAS_H + +#include <asm/cpu_entry_area.h> + +/* + * Just any arbitrary offset to the start of the vmalloc VM area: the + * current 8MB value just means that there will be a 8MB "hole" after the + * physical memory until the kernel virtual memory starts. That means that + * any out-of-bounds memory accesses will hopefully be caught. + * The vmalloc() routines leaves a hole of 4kB between each vmalloced + * area for the same reason. ;) + */ +#define VMALLOC_OFFSET (8 * 1024 * 1024) + +#ifndef __ASSEMBLY__ +extern bool __vmalloc_start_set; /* set once high_memory is set */ +#endif + +#define VMALLOC_START ((unsigned long)high_memory + VMALLOC_OFFSET) +#ifdef CONFIG_X86_PAE +#define LAST_PKMAP 512 +#else +#define LAST_PKMAP 1024 +#endif + +#define CPU_ENTRY_AREA_PAGES (NR_CPUS * DIV_ROUND_UP(sizeof(struct cpu_entry_area), PAGE_SIZE)) + +/* The +1 is for the readonly IDT page: */ +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK) + +#define LDT_BASE_ADDR \ + ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) + +#define LDT_END_ADDR (LDT_BASE_ADDR + PMD_SIZE) + +#define PKMAP_BASE \ + ((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK) + +#ifdef CONFIG_HIGHMEM +# define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) +#else +# define VMALLOC_END (LDT_BASE_ADDR - 2 * PAGE_SIZE) +#endif + +#define MODULES_VADDR VMALLOC_START +#define MODULES_END VMALLOC_END +#define MODULES_LEN (MODULES_VADDR - MODULES_END) + +#define MAXMEM (VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE) + +#endif /* _ASM_X86_PGTABLE_32_AREAS_H */ diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index b0bc0fff5f1f..5356a46b0373 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_PGTABLE_32_DEFS_H -#define _ASM_X86_PGTABLE_32_DEFS_H +#ifndef _ASM_X86_PGTABLE_32_TYPES_H +#define _ASM_X86_PGTABLE_32_TYPES_H /* * The Linux x86 paging architecture is 'compile-time dual-mode', it @@ -20,54 +20,4 @@ #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE - 1)) -/* Just any arbitrary offset to the start of the vmalloc VM area: the - * current 8MB value just means that there will be a 8MB "hole" after the - * physical memory until the kernel virtual memory starts. That means that - * any out-of-bounds memory accesses will hopefully be caught. - * The vmalloc() routines leaves a hole of 4kB between each vmalloced - * area for the same reason. ;) - */ -#define VMALLOC_OFFSET (8 * 1024 * 1024) - -#ifndef __ASSEMBLY__ -extern bool __vmalloc_start_set; /* set once high_memory is set */ -#endif - -#define VMALLOC_START ((unsigned long)high_memory + VMALLOC_OFFSET) -#ifdef CONFIG_X86_PAE -#define LAST_PKMAP 512 -#else -#define LAST_PKMAP 1024 -#endif - -/* - * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c - * to avoid include recursion hell - */ -#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) - -#define CPU_ENTRY_AREA_BASE \ - ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \ - & PMD_MASK) - -#define LDT_BASE_ADDR \ - ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) - -#define LDT_END_ADDR (LDT_BASE_ADDR + PMD_SIZE) - -#define PKMAP_BASE \ - ((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK) - -#ifdef CONFIG_HIGHMEM -# define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) -#else -# define VMALLOC_END (LDT_BASE_ADDR - 2 * PAGE_SIZE) -#endif - -#define MODULES_VADDR VMALLOC_START -#define MODULES_END VMALLOC_END -#define MODULES_LEN (MODULES_VADDR - MODULES_END) - -#define MAXMEM (VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE) - -#endif /* _ASM_X86_PGTABLE_32_DEFS_H */ +#endif /* _ASM_X86_PGTABLE_32_TYPES_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 4990d26dfc73..0b6c4042942a 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -241,9 +241,6 @@ extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -#define pgtable_cache_init() do { } while (0) -#define check_pgt_cache() do { } while (0) - #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 diff --git a/arch/x86/include/asm/pgtable_areas.h b/arch/x86/include/asm/pgtable_areas.h new file mode 100644 index 000000000000..d34cce1b995c --- /dev/null +++ b/arch/x86/include/asm/pgtable_areas.h @@ -0,0 +1,16 @@ +#ifndef _ASM_X86_PGTABLE_AREAS_H +#define _ASM_X86_PGTABLE_AREAS_H + +#ifdef CONFIG_X86_32 +# include <asm/pgtable_32_areas.h> +#endif + +/* Single page reserved for the readonly IDT mapping: */ +#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE +#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) + +#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) + +#define CPU_ENTRY_AREA_MAP_SIZE (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE) + +#endif /* _ASM_X86_PGTABLE_AREAS_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index b5e49e6bac63..0239998d8cdc 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -110,11 +110,6 @@ #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -#define _PAGE_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |\ - _PAGE_ACCESSED | _PAGE_DIRTY) -#define _KERNPG_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | \ - _PAGE_ACCESSED | _PAGE_DIRTY) - /* * Set of bits not changed in pte_modify. The pte's * protection key is treated like _PAGE_RW, for @@ -136,80 +131,93 @@ */ #ifndef __ASSEMBLY__ enum page_cache_mode { - _PAGE_CACHE_MODE_WB = 0, - _PAGE_CACHE_MODE_WC = 1, + _PAGE_CACHE_MODE_WB = 0, + _PAGE_CACHE_MODE_WC = 1, _PAGE_CACHE_MODE_UC_MINUS = 2, - _PAGE_CACHE_MODE_UC = 3, - _PAGE_CACHE_MODE_WT = 4, - _PAGE_CACHE_MODE_WP = 5, - _PAGE_CACHE_MODE_NUM = 8 + _PAGE_CACHE_MODE_UC = 3, + _PAGE_CACHE_MODE_WT = 4, + _PAGE_CACHE_MODE_WP = 5, + + _PAGE_CACHE_MODE_NUM = 8 }; #endif -#define _PAGE_CACHE_MASK (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT) -#define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) -#define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) +#define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) -#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) -#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_NX) - -#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT | _PAGE_RW | \ - _PAGE_USER | _PAGE_ACCESSED) -#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_NX) -#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_ACCESSED) -#define PAGE_COPY PAGE_COPY_NOEXEC -#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_NX) -#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_ACCESSED) - -#define __PAGE_KERNEL_EXEC \ - (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL) -#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC | _PAGE_NX) - -#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) -#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) -#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE) -#define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) -#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) -#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) -#define __PAGE_KERNEL_WP (__PAGE_KERNEL | _PAGE_CACHE_WP) - -#define __PAGE_KERNEL_IO (__PAGE_KERNEL) -#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE) +#define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) -#ifndef __ASSEMBLY__ +#define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) +#define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) -#define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) +#define __PP _PAGE_PRESENT +#define __RW _PAGE_RW +#define _USR _PAGE_USER +#define ___A _PAGE_ACCESSED +#define ___D _PAGE_DIRTY +#define ___G _PAGE_GLOBAL +#define __NX _PAGE_NX + +#define _ENC _PAGE_ENC +#define __WP _PAGE_CACHE_WP +#define __NC _PAGE_NOCACHE +#define _PSE _PAGE_PSE + +#define pgprot_val(x) ((x).pgprot) +#define __pgprot(x) ((pgprot_t) { (x) } ) +#define __pg(x) __pgprot(x) + +#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) + +#define PAGE_NONE __pg( 0| 0| 0|___A| 0| 0| 0|___G) +#define PAGE_SHARED __pg(__PP|__RW|_USR|___A|__NX| 0| 0| 0) +#define PAGE_SHARED_EXEC __pg(__PP|__RW|_USR|___A| 0| 0| 0| 0) +#define PAGE_COPY_NOEXEC __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) +#define PAGE_COPY_EXEC __pg(__PP| 0|_USR|___A| 0| 0| 0| 0) +#define PAGE_COPY __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) +#define PAGE_READONLY __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) +#define PAGE_READONLY_EXEC __pg(__PP| 0|_USR|___A| 0| 0| 0| 0) + +#define __PAGE_KERNEL (__PP|__RW| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_EXEC (__PP|__RW| 0|___A| 0|___D| 0|___G) +#define _KERNPG_TABLE_NOENC (__PP|__RW| 0|___A| 0|___D| 0| 0) +#define _KERNPG_TABLE (__PP|__RW| 0|___A| 0|___D| 0| 0| _ENC) +#define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) +#define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) +#define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_RX (__PP| 0| 0|___A| 0|___D| 0|___G) +#define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) +#define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) +#define __PAGE_KERNEL_LARGE_EXEC (__PP|__RW| 0|___A| 0|___D|_PSE|___G) +#define __PAGE_KERNEL_WP (__PP|__RW| 0|___A|__NX|___D| 0|___G| __WP) + + +#define __PAGE_KERNEL_IO __PAGE_KERNEL +#define __PAGE_KERNEL_IO_NOCACHE __PAGE_KERNEL_NOCACHE -#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ - _PAGE_DIRTY | _PAGE_ENC) -#define _PAGE_TABLE (_KERNPG_TABLE | _PAGE_USER) -#define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _PAGE_ENC) -#define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _PAGE_ENC) +#ifndef __ASSEMBLY__ -#define __PAGE_KERNEL_NOENC (__PAGE_KERNEL) -#define __PAGE_KERNEL_NOENC_WP (__PAGE_KERNEL_WP) +#define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _ENC) +#define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _ENC) +#define __PAGE_KERNEL_NOENC (__PAGE_KERNEL | 0) +#define __PAGE_KERNEL_NOENC_WP (__PAGE_KERNEL_WP | 0) -#define default_pgprot(x) __pgprot((x) & __default_kernel_pte_mask) +#define __pgprot_mask(x) __pgprot((x) & __default_kernel_pte_mask) -#define PAGE_KERNEL default_pgprot(__PAGE_KERNEL | _PAGE_ENC) -#define PAGE_KERNEL_NOENC default_pgprot(__PAGE_KERNEL) -#define PAGE_KERNEL_RO default_pgprot(__PAGE_KERNEL_RO | _PAGE_ENC) -#define PAGE_KERNEL_EXEC default_pgprot(__PAGE_KERNEL_EXEC | _PAGE_ENC) -#define PAGE_KERNEL_EXEC_NOENC default_pgprot(__PAGE_KERNEL_EXEC) -#define PAGE_KERNEL_RX default_pgprot(__PAGE_KERNEL_RX | _PAGE_ENC) -#define PAGE_KERNEL_NOCACHE default_pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC) -#define PAGE_KERNEL_LARGE default_pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC) -#define PAGE_KERNEL_LARGE_EXEC default_pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC) -#define PAGE_KERNEL_VVAR default_pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC) +#define PAGE_KERNEL __pgprot_mask(__PAGE_KERNEL | _ENC) +#define PAGE_KERNEL_NOENC __pgprot_mask(__PAGE_KERNEL | 0) +#define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC) +#define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC) +#define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) +#define PAGE_KERNEL_RX __pgprot_mask(__PAGE_KERNEL_RX | _ENC) +#define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC) +#define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC) +#define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC) +#define PAGE_KERNEL_VVAR __pgprot_mask(__PAGE_KERNEL_VVAR | _ENC) -#define PAGE_KERNEL_IO default_pgprot(__PAGE_KERNEL_IO) -#define PAGE_KERNEL_IO_NOCACHE default_pgprot(__PAGE_KERNEL_IO_NOCACHE) +#define PAGE_KERNEL_IO __pgprot_mask(__PAGE_KERNEL_IO) +#define PAGE_KERNEL_IO_NOCACHE __pgprot_mask(__PAGE_KERNEL_IO_NOCACHE) #endif /* __ASSEMBLY__ */ @@ -449,9 +457,6 @@ static inline pteval_t pte_flags(pte_t pte) return native_pte_val(pte) & PTE_FLAGS_MASK; } -#define pgprot_val(x) ((x).pgprot) -#define __pgprot(x) ((pgprot_t) { (x) } ) - extern uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM]; extern uint8_t __pte2cachemode_tbl[8]; @@ -561,6 +566,10 @@ static inline void update_page_count(int level, unsigned long pages) { } extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); + +struct mm_struct; +extern pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, + unsigned int *level); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 99a7fa9ab0a3..3d4cb83a8828 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -102,7 +102,7 @@ static __always_inline bool should_resched(int preempt_offset) return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); } -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION extern asmlinkage void ___preempt_schedule(void); # define __preempt_schedule() \ asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6e0a3b43d027..09705ccc393c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -7,6 +7,7 @@ /* Forward declaration, a strange C thing */ struct task_struct; struct mm_struct; +struct io_bitmap; struct vm86; #include <asm/math_emu.h> @@ -24,6 +25,7 @@ struct vm86; #include <asm/special_insns.h> #include <asm/fpu/types.h> #include <asm/unwind_hints.h> +#include <asm/vmxfeatures.h> #include <linux/personality.h> #include <linux/cache.h> @@ -84,6 +86,9 @@ struct cpuinfo_x86 { /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; #endif +#ifdef CONFIG_X86_VMX_FEATURE_NAMES + __u32 vmx_capability[NVMXINTS]; +#endif __u8 x86_virt_bits; __u8 x86_phys_bits; /* CPUID returned core id bits: */ @@ -93,7 +98,15 @@ struct cpuinfo_x86 { __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ int cpuid_level; - __u32 x86_capability[NCAPINTS + NBUGINTS]; + /* + * Align to size of unsigned long because the x86_capability array + * is passed to bitops which require the alignment. Use unnamed + * union to enforce the array is aligned to size of unsigned long. + */ + union { + __u32 x86_capability[NCAPINTS + NBUGINTS]; + unsigned long x86_capability_alignment; + }; char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ @@ -157,7 +170,6 @@ enum cpuid_regs_idx { extern struct cpuinfo_x86 boot_cpu_data; extern struct cpuinfo_x86 new_cpu_data; -extern struct x86_hw_tss doublefault_tss; extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; @@ -328,10 +340,32 @@ struct x86_hw_tss { * IO-bitmap sizes: */ #define IO_BITMAP_BITS 65536 -#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8) -#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) -#define IO_BITMAP_OFFSET (offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss)) -#define INVALID_IO_BITMAP_OFFSET 0x8000 +#define IO_BITMAP_BYTES (IO_BITMAP_BITS / BITS_PER_BYTE) +#define IO_BITMAP_LONGS (IO_BITMAP_BYTES / sizeof(long)) + +#define IO_BITMAP_OFFSET_VALID_MAP \ + (offsetof(struct tss_struct, io_bitmap.bitmap) - \ + offsetof(struct tss_struct, x86_tss)) + +#define IO_BITMAP_OFFSET_VALID_ALL \ + (offsetof(struct tss_struct, io_bitmap.mapall) - \ + offsetof(struct tss_struct, x86_tss)) + +#ifdef CONFIG_X86_IOPL_IOPERM +/* + * sizeof(unsigned long) coming from an extra "long" at the end of the + * iobitmap. The limit is inclusive, i.e. the last valid byte. + */ +# define __KERNEL_TSS_LIMIT \ + (IO_BITMAP_OFFSET_VALID_ALL + IO_BITMAP_BYTES + \ + sizeof(unsigned long) - 1) +#else +# define __KERNEL_TSS_LIMIT \ + (offsetof(struct tss_struct, x86_tss) + sizeof(struct x86_hw_tss) - 1) +#endif + +/* Base offset outside of TSS_LIMIT so unpriviledged IO causes #GP */ +#define IO_BITMAP_OFFSET_INVALID (__KERNEL_TSS_LIMIT + 1) struct entry_stack { unsigned long words[64]; @@ -341,13 +375,21 @@ struct entry_stack_page { struct entry_stack stack; } __aligned(PAGE_SIZE); -struct tss_struct { +/* + * All IO bitmap related data stored in the TSS: + */ +struct x86_io_bitmap { + /* The sequence number of the last active bitmap. */ + u64 prev_sequence; + /* - * The fixed hardware portion. This must not cross a page boundary - * at risk of violating the SDM's advice and potentially triggering - * errata. + * Store the dirty size of the last io bitmap offender. The next + * one will have to do the cleanup as the switch out to a non io + * bitmap user will just set x86_tss.io_bitmap_base to a value + * outside of the TSS limit. So for sane tasks there is no need to + * actually touch the io_bitmap at all. */ - struct x86_hw_tss x86_tss; + unsigned int prev_max; /* * The extra 1 is there because the CPU will access an @@ -355,21 +397,28 @@ struct tss_struct { * bitmap. The extra byte must be all 1 bits, and must * be within the limit. */ - unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; + unsigned long bitmap[IO_BITMAP_LONGS + 1]; + + /* + * Special I/O bitmap to emulate IOPL(3). All bytes zero, + * except the additional byte at the end. + */ + unsigned long mapall[IO_BITMAP_LONGS + 1]; +}; + +struct tss_struct { + /* + * The fixed hardware portion. This must not cross a page boundary + * at risk of violating the SDM's advice and potentially triggering + * errata. + */ + struct x86_hw_tss x86_tss; + + struct x86_io_bitmap io_bitmap; } __aligned(PAGE_SIZE); DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw); -/* - * sizeof(unsigned long) coming from an extra "long" at the end - * of the iobitmap. - * - * -1? seg base+limit should be pointing to the address of the - * last valid byte - */ -#define __KERNEL_TSS_LIMIT \ - (IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1) - /* Per CPU interrupt stacks */ struct irq_stack { char stack[IRQ_STACK_SIZE]; @@ -480,10 +529,14 @@ struct thread_struct { struct vm86 *vm86; #endif /* IO permissions: */ - unsigned long *io_bitmap_ptr; - unsigned long iopl; - /* Max allowed port in the bitmap, in bytes: */ - unsigned io_bitmap_max; + struct io_bitmap *io_bitmap; + + /* + * IOPL. Priviledge level dependent I/O permission which is + * emulated via the I/O bitmap to prevent user space from disabling + * interrupts. + */ + unsigned long iopl_emul; mm_segment_t addr_limit; @@ -515,25 +568,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ -/* - * Set IOPL bits in EFLAGS from given mask - */ -static inline void native_set_iopl_mask(unsigned mask) -{ -#ifdef CONFIG_X86_32 - unsigned int reg; - - asm volatile ("pushfl;" - "popl %0;" - "andl %1, %0;" - "orl %2, %0;" - "pushl %0;" - "popfl" - : "=&r" (reg) - : "i" (~X86_EFLAGS_IOPL), "r" (mask)); -#endif -} - static inline void native_load_sp0(unsigned long sp0) { @@ -573,7 +607,6 @@ static inline void load_sp0(unsigned long sp0) native_load_sp0(sp0); } -#define set_iopl_mask native_set_iopl_mask #endif /* CONFIG_PARAVIRT_XXL */ /* Free all resources held by a thread. */ @@ -841,7 +874,6 @@ static inline void spin_lock_prefetch(const void *x) #define INIT_THREAD { \ .sp0 = TOP_OF_INIT_STACK, \ .sysenter_cs = __KERNEL_CS, \ - .io_bitmap_ptr = NULL, \ .addr_limit = KERNEL_DS, \ } @@ -915,24 +947,6 @@ extern int set_tsc_mode(unsigned int val); DECLARE_PER_CPU(u64, msr_misc_features_shadow); -/* Register/unregister a process' MPX related resource */ -#define MPX_ENABLE_MANAGEMENT() mpx_enable_management() -#define MPX_DISABLE_MANAGEMENT() mpx_disable_management() - -#ifdef CONFIG_X86_INTEL_MPX -extern int mpx_enable_management(void); -extern int mpx_disable_management(void); -#else -static inline int mpx_enable_management(void) -{ - return -EINVAL; -} -static inline int mpx_disable_management(void) -{ - return -EINVAL; -} -#endif /* CONFIG_X86_INTEL_MPX */ - #ifdef CONFIG_CPU_SUP_AMD extern u16 amd_get_nb_id(int cpu); extern u32 amd_get_nodes_per_socket(void); @@ -958,7 +972,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) extern unsigned long arch_align_stack(unsigned long sp); void free_init_pages(const char *what, unsigned long begin, unsigned long end); -extern void free_kernel_image_pages(void *begin, void *end); +extern void free_kernel_image_pages(const char *what, void *begin, void *end); void default_idle(void); #ifdef CONFIG_XEN @@ -968,7 +982,6 @@ bool xen_set_default_idle(void); #endif void stop_this_cpu(void *dummy); -void df_debug(struct pt_regs *regs, long error_code); void microcode_check(void); enum l1tf_mitigations { diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h index 5df09a0b80b8..07375b476c4f 100644 --- a/arch/x86/include/asm/pti.h +++ b/arch/x86/include/asm/pti.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PTI_H #define _ASM_X86_PTI_H #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 332eb3525867..6d6475fdd327 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -159,6 +159,19 @@ static inline bool user_64bit_mode(struct pt_regs *regs) #endif } +/* + * Determine whether the register set came from any context that is running in + * 64-bit mode. + */ +static inline bool any_64bit_mode(struct pt_regs *regs) +{ +#ifdef CONFIG_X86_64 + return !user_mode(regs) || user_64bit_mode(regs); +#else + return false; +#endif +} + #ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp @@ -339,27 +352,17 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, #define ARCH_HAS_USER_SINGLE_STEP_REPORT -/* - * When hitting ptrace_stop(), we cannot return using SYSRET because - * that does not restore the full CPU state, only a minimal set. The - * ptracer can change arbitrary register values, which is usually okay - * because the usual ptrace stops run off the signal delivery path which - * forces IRET; however, ptrace_event() stops happen in arbitrary places - * in the kernel and don't force IRET path. - * - * So force IRET path after a ptrace stop. - */ -#define arch_ptrace_stop_needed(code, info) \ -({ \ - force_iret(); \ - false; \ -}) - struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); +#ifdef CONFIG_X86_64 +# define do_set_thread_area_64(p, s, t) do_arch_prctl_64(p, s, t) +#else +# define do_set_thread_area_64(p, s, t) (0) +#endif + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PTRACE_H */ diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h index 92c34e517da1..5528e9325049 100644 --- a/arch/x86/include/asm/purgatory.h +++ b/arch/x86/include/asm/purgatory.h @@ -6,16 +6,6 @@ #include <linux/purgatory.h> extern void purgatory(void); -/* - * These forward declarations serve two purposes: - * - * 1) Make sparse happy when checking arch/purgatory - * 2) Document that these are required to be global so the symbol - * lookup in kexec works - */ -extern unsigned long purgatory_backup_dest; -extern unsigned long purgatory_backup_src; -extern unsigned long purgatory_backup_sz; #endif /* __ASSEMBLY__ */ #endif /* _ASM_PURGATORY_H */ diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index bd5ac6cc37db..444d6fd9a6d8 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -63,10 +63,25 @@ static inline bool vcpu_is_preempted(long cpu) #endif #ifdef CONFIG_PARAVIRT +/* + * virt_spin_lock_key - enables (by default) the virt_spin_lock() hijack. + * + * Native (and PV wanting native due to vCPU pinning) should disable this key. + * It is done in this backwards fashion to only have a single direction change, + * which removes ordering between native_pv_spin_init() and HV setup. + */ DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key); void native_pv_lock_init(void) __init; +/* + * Shortcut for the queued_spin_lock_slowpath() function that allows + * virt to hijack it. + * + * Returns: + * true - lock has been negotiated, all done; + * false - queued_spin_lock_slowpath() will do its thing. + */ #define virt_spin_lock virt_spin_lock static inline bool virt_spin_lock(struct qspinlock *lock) { diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index c53682303c9c..b35030eeec36 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -14,13 +14,12 @@ #include <linux/types.h> #include <asm/io.h> -/* This must match data at realmode.S */ +/* This must match data at realmode/rm/header.S */ struct real_mode_header { u32 text_start; u32 ro_end; /* SMP trampoline */ u32 trampoline_start; - u32 trampoline_status; u32 trampoline_header; #ifdef CONFIG_X86_64 u32 trampoline_pgd; @@ -37,7 +36,7 @@ struct real_mode_header { #endif }; -/* This must match data at trampoline_32/64.S */ +/* This must match data at realmode/rm/trampoline_{32,64}.S */ struct trampoline_header { #ifdef CONFIG_X86_32 u32 start; diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h deleted file mode 100644 index 232f856e0db0..000000000000 --- a/arch/x86/include/asm/refcount.h +++ /dev/null @@ -1,126 +0,0 @@ -#ifndef __ASM_X86_REFCOUNT_H -#define __ASM_X86_REFCOUNT_H -/* - * x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from - * PaX/grsecurity. - */ -#include <linux/refcount.h> -#include <asm/bug.h> - -/* - * This is the first portion of the refcount error handling, which lives in - * .text.unlikely, and is jumped to from the CPU flag check (in the - * following macros). This saves the refcount value location into CX for - * the exception handler to use (in mm/extable.c), and then triggers the - * central refcount exception. The fixup address for the exception points - * back to the regular execution flow in .text. - */ -#define _REFCOUNT_EXCEPTION \ - ".pushsection .text..refcount\n" \ - "111:\tlea %[var], %%" _ASM_CX "\n" \ - "112:\t" ASM_UD2 "\n" \ - ASM_UNREACHABLE \ - ".popsection\n" \ - "113:\n" \ - _ASM_EXTABLE_REFCOUNT(112b, 113b) - -/* Trigger refcount exception if refcount result is negative. */ -#define REFCOUNT_CHECK_LT_ZERO \ - "js 111f\n\t" \ - _REFCOUNT_EXCEPTION - -/* Trigger refcount exception if refcount result is zero or negative. */ -#define REFCOUNT_CHECK_LE_ZERO \ - "jz 111f\n\t" \ - REFCOUNT_CHECK_LT_ZERO - -/* Trigger refcount exception unconditionally. */ -#define REFCOUNT_ERROR \ - "jmp 111f\n\t" \ - _REFCOUNT_EXCEPTION - -static __always_inline void refcount_add(unsigned int i, refcount_t *r) -{ - asm volatile(LOCK_PREFIX "addl %1,%0\n\t" - REFCOUNT_CHECK_LT_ZERO - : [var] "+m" (r->refs.counter) - : "ir" (i) - : "cc", "cx"); -} - -static __always_inline void refcount_inc(refcount_t *r) -{ - asm volatile(LOCK_PREFIX "incl %0\n\t" - REFCOUNT_CHECK_LT_ZERO - : [var] "+m" (r->refs.counter) - : : "cc", "cx"); -} - -static __always_inline void refcount_dec(refcount_t *r) -{ - asm volatile(LOCK_PREFIX "decl %0\n\t" - REFCOUNT_CHECK_LE_ZERO - : [var] "+m" (r->refs.counter) - : : "cc", "cx"); -} - -static __always_inline __must_check -bool refcount_sub_and_test(unsigned int i, refcount_t *r) -{ - bool ret = GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", - REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, e, "er", i, "cx"); - - if (ret) { - smp_acquire__after_ctrl_dep(); - return true; - } - - return false; -} - -static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) -{ - bool ret = GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", - REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, e, "cx"); - - if (ret) { - smp_acquire__after_ctrl_dep(); - return true; - } - - return false; -} - -static __always_inline __must_check -bool refcount_add_not_zero(unsigned int i, refcount_t *r) -{ - int c, result; - - c = atomic_read(&(r->refs)); - do { - if (unlikely(c == 0)) - return false; - - result = c + i; - - /* Did we try to increment from/to an undesirable state? */ - if (unlikely(c < 0 || c == INT_MAX || result < c)) { - asm volatile(REFCOUNT_ERROR - : : [var] "m" (r->refs.counter) - : "cc", "cx"); - break; - } - - } while (!atomic_try_cmpxchg(&(r->refs), &c, result)); - - return c != 0; -} - -static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r) -{ - return refcount_add_not_zero(1, r); -} - -#endif diff --git a/arch/x86/include/asm/rio.h b/arch/x86/include/asm/rio.h deleted file mode 100644 index 0a21986d2238..000000000000 --- a/arch/x86/include/asm/rio.h +++ /dev/null @@ -1,64 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Derived from include/asm-x86/mach-summit/mach_mpparse.h - * and include/asm-x86/mach-default/bios_ebda.h - * - * Author: Laurent Vivier <Laurent.Vivier@bull.net> - */ - -#ifndef _ASM_X86_RIO_H -#define _ASM_X86_RIO_H - -#define RIO_TABLE_VERSION 3 - -struct rio_table_hdr { - u8 version; /* Version number of this data structure */ - u8 num_scal_dev; /* # of Scalability devices */ - u8 num_rio_dev; /* # of RIO I/O devices */ -} __attribute__((packed)); - -struct scal_detail { - u8 node_id; /* Scalability Node ID */ - u32 CBAR; /* Address of 1MB register space */ - u8 port0node; /* Node ID port connected to: 0xFF=None */ - u8 port0port; /* Port num port connected to: 0,1,2, or */ - /* 0xFF=None */ - u8 port1node; /* Node ID port connected to: 0xFF = None */ - u8 port1port; /* Port num port connected to: 0,1,2, or */ - /* 0xFF=None */ - u8 port2node; /* Node ID port connected to: 0xFF = None */ - u8 port2port; /* Port num port connected to: 0,1,2, or */ - /* 0xFF=None */ - u8 chassis_num; /* 1 based Chassis number (1 = boot node) */ -} __attribute__((packed)); - -struct rio_detail { - u8 node_id; /* RIO Node ID */ - u32 BBAR; /* Address of 1MB register space */ - u8 type; /* Type of device */ - u8 owner_id; /* Node ID of Hurricane that owns this */ - /* node */ - u8 port0node; /* Node ID port connected to: 0xFF=None */ - u8 port0port; /* Port num port connected to: 0,1,2, or */ - /* 0xFF=None */ - u8 port1node; /* Node ID port connected to: 0xFF=None */ - u8 port1port; /* Port num port connected to: 0,1,2, or */ - /* 0xFF=None */ - u8 first_slot; /* Lowest slot number below this Calgary */ - u8 status; /* Bit 0 = 1 : the XAPIC is used */ - /* = 0 : the XAPIC is not used, ie: */ - /* ints fwded to another XAPIC */ - /* Bits1:7 Reserved */ - u8 WP_index; /* instance index - lower ones have */ - /* lower slot numbers/PCI bus numbers */ - u8 chassis_num; /* 1 based Chassis number */ -} __attribute__((packed)); - -enum { - HURR_SCALABILTY = 0, /* Hurricane Scalability info */ - HURR_RIOIB = 2, /* Hurricane RIOIB info */ - COMPAT_CALGARY = 4, /* Compatibility Calgary */ - ALT_CALGARY = 5, /* Second Planar Calgary */ -}; - -#endif /* _ASM_X86_RIO_H */ diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 71b32f2570ab..036c360910c5 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -6,7 +6,6 @@ #include <asm/extable.h> extern char __brk_base[], __brk_limit[]; -extern struct exception_table_entry __stop___ex_table[]; extern char __end_rodata_aligned[]; #if defined(CONFIG_X86_64) diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index ac3892920419..6669164abadc 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -31,6 +31,18 @@ */ #define SEGMENT_RPL_MASK 0x3 +/* + * When running on Xen PV, the actual privilege level of the kernel is 1, + * not 0. Testing the Requested Privilege Level in a segment selector to + * determine whether the context is user mode or kernel mode with + * SEGMENT_RPL_MASK is wrong because the PV kernel's privilege level + * matches the 0x3 mask. + * + * Testing with USER_SEGMENT_RPL_MASK is valid for both native and Xen PV + * kernels because privilege level 2 is never used. + */ +#define USER_SEGMENT_RPL_MASK 0x2 + /* User mode is privilege level 3: */ #define USER_RPL 0x3 diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index ae7b909dc242..64c3dce374e5 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -40,7 +40,6 @@ int _set_memory_wt(unsigned long addr, int numpages); int _set_memory_wb(unsigned long addr, int numpages); int set_memory_uc(unsigned long addr, int numpages); int set_memory_wc(unsigned long addr, int numpages); -int set_memory_wt(unsigned long addr, int numpages); int set_memory_wb(unsigned long addr, int numpages); int set_memory_np(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); @@ -48,11 +47,6 @@ int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); int set_memory_np_noalias(unsigned long addr, int numpages); -int set_memory_array_uc(unsigned long *addr, int addrinarray); -int set_memory_array_wc(unsigned long *addr, int addrinarray); -int set_memory_array_wt(unsigned long *addr, int addrinarray); -int set_memory_array_wb(unsigned long *addr, int addrinarray); - int set_pages_array_uc(struct page **pages, int addrinarray); int set_pages_array_wc(struct page **pages, int addrinarray); int set_pages_array_wt(struct page **pages, int addrinarray); @@ -80,8 +74,6 @@ int set_pages_array_wb(struct page **pages, int addrinarray); int set_pages_uc(struct page *page, int numpages); int set_pages_wb(struct page *page, int numpages); -int set_pages_x(struct page *page, int numpages); -int set_pages_nx(struct page *page, int numpages); int set_pages_ro(struct page *page, int numpages); int set_pages_rw(struct page *page, int numpages); @@ -89,8 +81,6 @@ int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); extern int kernel_set_to_readonly; -void set_kernel_text_rw(void); -void set_kernel_text_ro(void); #ifdef CONFIG_X86_64 static inline int set_mce_nospec(unsigned long pfn) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index e1356a3b8223..e15f364efbcc 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -143,6 +143,7 @@ void play_dead_common(void); void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); +void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 219be88a59d2..6d37b8fcfc77 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -73,20 +73,6 @@ static inline unsigned long native_read_cr4(void) void native_write_cr4(unsigned long val); -#ifdef CONFIG_X86_64 -static inline unsigned long native_read_cr8(void) -{ - unsigned long cr8; - asm volatile("movq %%cr8,%0" : "=r" (cr8)); - return cr8; -} - -static inline void native_write_cr8(unsigned long val) -{ - asm volatile("movq %0,%%cr8" :: "r" (val) : "memory"); -} -#endif - #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS static inline u32 rdpkru(void) { @@ -200,16 +186,6 @@ static inline void wbinvd(void) #ifdef CONFIG_X86_64 -static inline unsigned long read_cr8(void) -{ - return native_read_cr8(); -} - -static inline void write_cr8(unsigned long x) -{ - native_write_cr8(x); -} - static inline void load_gs_index(unsigned selector) { native_load_gs_index(selector); diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index a7af9f53c0cb..35bb35d28733 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -34,7 +34,7 @@ struct saved_context { */ unsigned long kernelmode_gs_base, usermode_gs_base, fs_base; - unsigned long cr0, cr2, cr3, cr4, cr8; + unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; bool misc_enable_saved; struct saved_msrs saved_msrs; diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index dec9c1e84c78..6ece8561ba66 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -52,6 +52,7 @@ enum { INTERCEPT_MWAIT, INTERCEPT_MWAIT_COND, INTERCEPT_XSETBV, + INTERCEPT_RDPRU, }; diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 18a4b6890fa8..0e059b73437b 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -103,7 +103,17 @@ static inline void update_task_stack(struct task_struct *task) if (static_cpu_has(X86_FEATURE_XENPV)) load_sp0(task_top_of_stack(task)); #endif +} +static inline void kthread_frame_init(struct inactive_task_frame *frame, + unsigned long fun, unsigned long arg) +{ + frame->bx = fun; +#ifdef CONFIG_X86_32 + frame->di = arg; +#else + frame->r12 = arg; +#endif } #endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 2dc4a021beea..8db3fdb6102e 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -36,6 +36,10 @@ extern const sys_call_ptr_t sys_call_table[]; extern const sys_call_ptr_t ia32_sys_call_table[]; #endif +#ifdef CONFIG_X86_X32_ABI +extern const sys_call_ptr_t x32_sys_call_table[]; +#endif + /* * Only the low 32 bits of orig_ax are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index e046a405743d..e2389ce9bf58 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -6,6 +6,8 @@ #ifndef _ASM_X86_SYSCALL_WRAPPER_H #define _ASM_X86_SYSCALL_WRAPPER_H +struct pt_regs; + /* Mapping of registers to parameters for syscalls on x86-64 and x32 */ #define SC_X86_64_REGS_TO_ARGS(x, ...) \ __MAP(x,__SC_ARGS \ @@ -28,13 +30,21 @@ * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this * case as well. */ +#define __IA32_COMPAT_SYS_STUB0(x, name) \ + asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs);\ + ALLOW_ERROR_INJECTION(__ia32_compat_sys_##name, ERRNO); \ + asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs)\ + { \ + return __se_compat_sys_##name(); \ + } + #define __IA32_COMPAT_SYS_STUBx(x, name, ...) \ asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\ ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO); \ asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\ { \ return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + } #define __IA32_SYS_STUBx(x, name, ...) \ asmlinkage long __ia32_sys##name(const struct pt_regs *regs); \ @@ -48,16 +58,23 @@ * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias * named __ia32_sys_*() */ -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(void); \ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ - asmlinkage long __x64_sys_##sname(void) -#define COND_SYSCALL(name) \ - cond_syscall(__x64_sys_##name); \ - cond_syscall(__ia32_sys_##name) +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ + ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ + SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ + { \ + return sys_ni_syscall(); \ + } \ + asmlinkage __weak long __ia32_sys_##name(const struct pt_regs *__unused)\ + { \ + return sys_ni_syscall(); \ + } #define SYS_NI(name) \ SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); \ @@ -75,15 +92,24 @@ * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common * with x86_64 obviously do not need such care. */ +#define __X32_COMPAT_SYS_STUB0(x, name, ...) \ + asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs);\ + ALLOW_ERROR_INJECTION(__x32_compat_sys_##name, ERRNO); \ + asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs)\ + { \ + return __se_compat_sys_##name();\ + } + #define __X32_COMPAT_SYS_STUBx(x, name, ...) \ asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\ ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO); \ asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\ { \ return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + } #else /* CONFIG_X86_X32 */ +#define __X32_COMPAT_SYS_STUB0(x, name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) #endif /* CONFIG_X86_X32 */ @@ -94,6 +120,17 @@ * mapping of registers to parameters, we need to generate stubs for each * of them. */ +#define COMPAT_SYSCALL_DEFINE0(name) \ + static long __se_compat_sys_##name(void); \ + static inline long __do_compat_sys_##name(void); \ + __IA32_COMPAT_SYS_STUB0(x, name) \ + __X32_COMPAT_SYS_STUB0(x, name) \ + static long __se_compat_sys_##name(void) \ + { \ + return __do_compat_sys_##name(); \ + } \ + static inline long __do_compat_sys_##name(void) + #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ @@ -181,15 +218,19 @@ * macros to work correctly. */ #ifndef SYSCALL_DEFINE0 -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(void); \ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - asmlinkage long __x64_sys_##sname(void) +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ + ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ + asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) #endif #ifndef COND_SYSCALL -#define COND_SYSCALL(name) cond_syscall(__x64_sys_##name) +#define COND_SYSCALL(name) \ + asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ + { \ + return sys_ni_syscall(); \ + } #endif #ifndef SYS_NI @@ -201,7 +242,6 @@ * For VSYSCALLS, we need to declare these three syscalls with the new * pt_regs-based calling convention for in-kernel use. */ -struct pt_regs; asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs); asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs); asmlinkage long __x64_sys_time(const struct pt_regs *regs); diff --git a/arch/x86/include/asm/tce.h b/arch/x86/include/asm/tce.h deleted file mode 100644 index 6ed2deacf1d0..000000000000 --- a/arch/x86/include/asm/tce.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * This file is derived from asm-powerpc/tce.h. - * - * Copyright (C) IBM Corporation, 2006 - * - * Author: Muli Ben-Yehuda <muli@il.ibm.com> - * Author: Jon Mason <jdmason@us.ibm.com> - */ - -#ifndef _ASM_X86_TCE_H -#define _ASM_X86_TCE_H - -extern unsigned int specified_table_size; -struct iommu_table; - -#define TCE_ENTRY_SIZE 8 /* in bytes */ - -#define TCE_READ_SHIFT 0 -#define TCE_WRITE_SHIFT 1 -#define TCE_HUBID_SHIFT 2 /* unused */ -#define TCE_RSVD_SHIFT 8 /* unused */ -#define TCE_RPN_SHIFT 12 -#define TCE_UNUSED_SHIFT 48 /* unused */ - -#define TCE_RPN_MASK 0x0000fffffffff000ULL - -extern void tce_build(struct iommu_table *tbl, unsigned long index, - unsigned int npages, unsigned long uaddr, int direction); -extern void tce_free(struct iommu_table *tbl, long index, unsigned int npages); -extern void * __init alloc_tce_table(void); -extern void __init free_tce_table(void *tbl); -extern int __init build_tce_table(struct pci_dev *dev, void __iomem *bbar); - -#endif /* _ASM_X86_TCE_H */ diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 70c09967a999..67315fa3956a 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -25,13 +25,6 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, */ #define POKE_MAX_OPCODE_SIZE 5 -struct text_poke_loc { - void *detour; - void *addr; - size_t len; - const char opcode[POKE_MAX_OPCODE_SIZE]; -}; - extern void text_poke_early(void *addr, const void *opcode, size_t len); /* @@ -45,14 +38,81 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len); * no thread can be preempted in the instructions being modified (no iret to an * invalid instruction possible) or if the instructions are changed from a * consistent state to another consistent state atomically. - * On the local CPU you need to be protected again NMI or MCE handlers seeing an - * inconsistent instruction while you patch. + * On the local CPU you need to be protected against NMI or MCE handlers seeing + * an inconsistent instruction while you patch. */ extern void *text_poke(void *addr, const void *opcode, size_t len); +extern void text_poke_sync(void); extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len); extern int poke_int3_handler(struct pt_regs *regs); -extern void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); -extern void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries); +extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate); + +extern void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate); +extern void text_poke_finish(void); + +#define INT3_INSN_SIZE 1 +#define INT3_INSN_OPCODE 0xCC + +#define CALL_INSN_SIZE 5 +#define CALL_INSN_OPCODE 0xE8 + +#define JMP32_INSN_SIZE 5 +#define JMP32_INSN_OPCODE 0xE9 + +#define JMP8_INSN_SIZE 2 +#define JMP8_INSN_OPCODE 0xEB + +#define DISP32_SIZE 4 + +static inline int text_opcode_size(u8 opcode) +{ + int size = 0; + +#define __CASE(insn) \ + case insn##_INSN_OPCODE: size = insn##_INSN_SIZE; break + + switch(opcode) { + __CASE(INT3); + __CASE(CALL); + __CASE(JMP32); + __CASE(JMP8); + } + +#undef __CASE + + return size; +} + +union text_poke_insn { + u8 text[POKE_MAX_OPCODE_SIZE]; + struct { + u8 opcode; + s32 disp; + } __attribute__((packed)); +}; + +static __always_inline +void *text_gen_insn(u8 opcode, const void *addr, const void *dest) +{ + static union text_poke_insn insn; /* per instance */ + int size = text_opcode_size(opcode); + + insn.opcode = opcode; + + if (size > 1) { + insn.disp = (long)dest - (long)(addr + size); + if (size == 2) { + /* + * Ensure that for JMP9 the displacement + * actually fits the signed byte. + */ + BUG_ON((insn.disp >> 31) != (insn.disp >> 7)); + } + } + + return &insn.text; +} + extern int after_bootmem; extern __ro_after_init struct mm_struct *poking_mm; extern __ro_after_init unsigned long poking_addr; @@ -63,9 +123,6 @@ static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } -#define INT3_INSN_SIZE 1 -#define CALL_INSN_SIZE 5 - static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) { /* @@ -73,6 +130,9 @@ static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) * stack where the break point happened, and the saving of * pt_regs. We can extend the original stack because of * this gap. See the idtentry macro's create_gap option. + * + * Similarly entry_32.S will have a gap on the stack for (any) hardware + * exception and pt_regs; see FIXUP_FRAME. */ regs->sp -= sizeof(unsigned long); *(unsigned long *)regs->sp = val; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index f9453536f9bb..cf4327986e98 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -143,8 +143,8 @@ struct thread_info { _TIF_NOHZ) /* flags to check in __switch_to() */ -#define _TIF_WORK_CTXSW_BASE \ - (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP| \ +#define _TIF_WORK_CTXSW_BASE \ + (_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP | \ _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE) /* @@ -156,8 +156,14 @@ struct thread_info { # define _TIF_WORK_CTXSW (_TIF_WORK_CTXSW_BASE) #endif -#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) -#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) +#ifdef CONFIG_X86_IOPL_IOPERM +# define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW| _TIF_USER_RETURN_NOTIFY | \ + _TIF_IO_BITMAP) +#else +# define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW| _TIF_USER_RETURN_NOTIFY) +#endif + +#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) #define STACK_WARN (THREAD_SIZE/8) @@ -233,15 +239,6 @@ static inline int arch_within_stack_frames(const void * const stack, current_thread_info()->status & TS_COMPAT) #endif -/* - * Force syscall return via IRET by making it look as if there was - * some work pending. IRET is our most capable (but slowest) syscall - * return path, which is able to restore modified SS, CS and certain - * EFLAGS values that other (fast) syscall return instructions - * are not able to restore properly. - */ -#define force_iret() set_thread_flag(TIF_NOTIFY_RESUME) - extern void arch_task_cache_init(void); extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); extern void arch_release_task_struct(struct task_struct *tsk); diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index f23e7aaff4cd..820082bd6880 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -29,8 +29,8 @@ static inline void tlb_flush(struct mmu_gather *tlb) * shootdown, enablement code for several hypervisors overrides * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing * a hypercall. To keep software pagetable walkers safe in this case we - * switch to RCU based table free (HAVE_RCU_TABLE_FREE). See the comment - * below 'ifdef CONFIG_HAVE_RCU_TABLE_FREE' in include/asm-generic/tlb.h + * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment + * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h * for more details. */ static inline void __tlb_remove_table(void *table) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index dee375831962..6f66d841262d 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -290,26 +290,42 @@ static inline void __cr4_set(unsigned long cr4) } /* Set in this cpu's CR4. */ -static inline void cr4_set_bits(unsigned long mask) +static inline void cr4_set_bits_irqsoff(unsigned long mask) { - unsigned long cr4, flags; + unsigned long cr4; - local_irq_save(flags); cr4 = this_cpu_read(cpu_tlbstate.cr4); if ((cr4 | mask) != cr4) __cr4_set(cr4 | mask); - local_irq_restore(flags); } /* Clear in this cpu's CR4. */ -static inline void cr4_clear_bits(unsigned long mask) +static inline void cr4_clear_bits_irqsoff(unsigned long mask) { - unsigned long cr4, flags; + unsigned long cr4; - local_irq_save(flags); cr4 = this_cpu_read(cpu_tlbstate.cr4); if ((cr4 & ~mask) != cr4) __cr4_set(cr4 & ~mask); +} + +/* Set in this cpu's CR4. */ +static inline void cr4_set_bits(unsigned long mask) +{ + unsigned long flags; + + local_irq_save(flags); + cr4_set_bits_irqsoff(mask); + local_irq_restore(flags); +} + +/* Clear in this cpu's CR4. */ +static inline void cr4_clear_bits(unsigned long mask) +{ + unsigned long flags; + + local_irq_save(flags); + cr4_clear_bits_irqsoff(mask); local_irq_restore(flags); } diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h index ace464f09681..4d705cb4d63b 100644 --- a/arch/x86/include/asm/trace/hyperv.h +++ b/arch/x86/include/asm/trace/hyperv.h @@ -71,6 +71,21 @@ TRACE_EVENT(hyperv_send_ipi_mask, __entry->ncpus, __entry->vector) ); +TRACE_EVENT(hyperv_send_ipi_one, + TP_PROTO(int cpu, + int vector), + TP_ARGS(cpu, vector), + TP_STRUCT__entry( + __field(int, cpu) + __field(int, vector) + ), + TP_fast_assign(__entry->cpu = cpu; + __entry->vector = vector; + ), + TP_printk("cpu %d vector %x", + __entry->cpu, __entry->vector) + ); + #endif /* CONFIG_HYPERV */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h deleted file mode 100644 index 54133017267c..000000000000 --- a/arch/x86/include/asm/trace/mpx.h +++ /dev/null @@ -1,134 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM mpx - -#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_MPX_H - -#include <linux/tracepoint.h> - -#ifdef CONFIG_X86_INTEL_MPX - -TRACE_EVENT(mpx_bounds_register_exception, - - TP_PROTO(void __user *addr_referenced, - const struct mpx_bndreg *bndreg), - TP_ARGS(addr_referenced, bndreg), - - TP_STRUCT__entry( - __field(void __user *, addr_referenced) - __field(u64, lower_bound) - __field(u64, upper_bound) - ), - - TP_fast_assign( - __entry->addr_referenced = addr_referenced; - __entry->lower_bound = bndreg->lower_bound; - __entry->upper_bound = bndreg->upper_bound; - ), - /* - * Note that we are printing out the '~' of the upper - * bounds register here. It is actually stored in its - * one's complement form so that its 'init' state - * corresponds to all 0's. But, that looks like - * gibberish when printed out, so print out the 1's - * complement instead of the actual value here. Note - * though that you still need to specify filters for the - * actual value, not the displayed one. - */ - TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx", - __entry->addr_referenced, - __entry->lower_bound, - ~__entry->upper_bound - ) -); - -TRACE_EVENT(bounds_exception_mpx, - - TP_PROTO(const struct mpx_bndcsr *bndcsr), - TP_ARGS(bndcsr), - - TP_STRUCT__entry( - __field(u64, bndcfgu) - __field(u64, bndstatus) - ), - - TP_fast_assign( - /* need to get rid of the 'const' on bndcsr */ - __entry->bndcfgu = (u64)bndcsr->bndcfgu; - __entry->bndstatus = (u64)bndcsr->bndstatus; - ), - - TP_printk("bndcfgu:0x%llx bndstatus:0x%llx", - __entry->bndcfgu, - __entry->bndstatus) -); - -DECLARE_EVENT_CLASS(mpx_range_trace, - - TP_PROTO(unsigned long start, - unsigned long end), - TP_ARGS(start, end), - - TP_STRUCT__entry( - __field(unsigned long, start) - __field(unsigned long, end) - ), - - TP_fast_assign( - __entry->start = start; - __entry->end = end; - ), - - TP_printk("[0x%p:0x%p]", - (void *)__entry->start, - (void *)__entry->end - ) -); - -DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap, - TP_PROTO(unsigned long start, unsigned long end), - TP_ARGS(start, end) -); - -DEFINE_EVENT(mpx_range_trace, mpx_unmap_search, - TP_PROTO(unsigned long start, unsigned long end), - TP_ARGS(start, end) -); - -TRACE_EVENT(mpx_new_bounds_table, - - TP_PROTO(unsigned long table_vaddr), - TP_ARGS(table_vaddr), - - TP_STRUCT__entry( - __field(unsigned long, table_vaddr) - ), - - TP_fast_assign( - __entry->table_vaddr = table_vaddr; - ), - - TP_printk("table vaddr:%p", (void *)__entry->table_vaddr) -); - -#else - -/* - * This gets used outside of MPX-specific code, so we need a stub. - */ -static inline -void trace_bounds_exception_mpx(const struct mpx_bndcsr *bndcsr) -{ -} - -#endif /* CONFIG_X86_INTEL_MPX */ - -#undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH asm/trace/ -#undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE mpx -#endif /* _TRACE_MPX_H */ - -/* This part must be outside protection */ -#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index b25e633033c3..ffa0dc8a535e 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -69,6 +69,9 @@ dotraplinkage void do_overflow(struct pt_regs *regs, long error_code); dotraplinkage void do_bounds(struct pt_regs *regs, long error_code); dotraplinkage void do_invalid_op(struct pt_regs *regs, long error_code); dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code); +#if defined(CONFIG_X86_64) || defined(CONFIG_DOUBLEFAULT) +dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long cr2); +#endif dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *regs, long error_code); dotraplinkage void do_invalid_TSS(struct pt_regs *regs, long error_code); dotraplinkage void do_segment_not_present(struct pt_regs *regs, long error_code); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 9c4435307ff8..61d93f062a36 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -444,8 +444,10 @@ __pu_label: \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ + __typeof__(ptr) __gu_ptr = (ptr); \ + __typeof__(size) __gu_size = (size); \ __uaccess_begin_nospec(); \ - __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ + __get_user_size(__gu_val, __gu_ptr, __gu_size, __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ __builtin_expect(__gu_err, 0); \ @@ -732,5 +734,28 @@ do { \ if (unlikely(__gu_err)) goto err_label; \ } while (0) +/* + * We want the unsafe accessors to always be inlined and use + * the error labels - thus the macro games. + */ +#define unsafe_copy_loop(dst, src, len, type, label) \ + while (len >= sizeof(type)) { \ + unsafe_put_user(*(type *)src,(type __user *)dst,label); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } + +#define unsafe_copy_to_user(_dst,_src,_len,label) \ +do { \ + char __user *__ucu_dst = (_dst); \ + const char *__ucu_src = (_src); \ + size_t __ucu_len = (_len); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ +} while (0) + #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/umip.h b/arch/x86/include/asm/umip.h index db43f2a0d92c..aeed98c3c9e1 100644 --- a/arch/x86/include/asm/umip.h +++ b/arch/x86/include/asm/umip.h @@ -4,9 +4,9 @@ #include <linux/types.h> #include <asm/ptrace.h> -#ifdef CONFIG_X86_INTEL_UMIP +#ifdef CONFIG_X86_UMIP bool fixup_umip_exception(struct pt_regs *regs); #else static inline bool fixup_umip_exception(struct pt_regs *regs) { return false; } -#endif /* CONFIG_X86_INTEL_UMIP */ +#endif /* CONFIG_X86_UMIP */ #endif /* _ASM_X86_UMIP_H */ diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 097589753fec..a7dd080749ce 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -5,12 +5,6 @@ #include <uapi/asm/unistd.h> -# ifdef CONFIG_X86_X32_ABI -# define __SYSCALL_MASK (~(__X32_SYSCALL_BIT)) -# else -# define __SYSCALL_MASK (~0) -# endif - # ifdef CONFIG_X86_32 # include <asm/unistd_32.h> diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 0bcdb1279361..f5e2eb12cb71 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -86,6 +86,14 @@ UNWIND_HINT sp_offset=\sp_offset .endm +.macro UNWIND_HINT_SAVE + UNWIND_HINT type=UNWIND_HINT_TYPE_SAVE +.endm + +.macro UNWIND_HINT_RESTORE + UNWIND_HINT type=UNWIND_HINT_TYPE_RESTORE +.endm + #else /* !__ASSEMBLY__ */ #define UNWIND_HINT(sp_reg, sp_offset, type, end) \ diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index 6e7caf65fa40..389174eaec79 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -138,7 +138,7 @@ extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect); extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *); extern int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus); -extern void uv_bios_init(void); +extern int uv_bios_init(void); extern unsigned long sn_rtc_cycles_per_second; extern int uv_type; diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index e60c45fd3679..45ea95ce79b4 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -12,13 +12,26 @@ struct mm_struct; #ifdef CONFIG_X86_UV #include <linux/efi.h> +#define UV_PROC_NODE "sgi_uv" + +static inline int uv(int uvtype) +{ + /* uv(0) is "any" */ + if (uvtype >= 0 && uvtype <= 30) + return 1 << uvtype; + return 1; +} + +extern unsigned long uv_systab_phys; + extern enum uv_system_type get_uv_system_type(void); static inline bool is_early_uv_system(void) { - return !((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab); + return uv_systab_phys && uv_systab_phys != EFI_INVALID_TABLE_ADDR; } extern int is_uv_system(void); -extern int is_uv_hubless(void); +extern int is_uv_hubbed(int uvtype); +extern int is_uv_hubless(int uvtype); extern void uv_cpu_init(void); extern void uv_nmi_init(void); extern void uv_system_init(void); @@ -30,7 +43,8 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } static inline bool is_early_uv_system(void) { return 0; } static inline int is_uv_system(void) { return 0; } -static inline int is_uv_hubless(void) { return 0; } +static inline int is_uv_hubbed(int uv) { return 0; } +static inline int is_uv_hubless(int uv) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } static inline const struct cpumask * diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 44cf6d6deb7a..950cd1395d5d 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -19,6 +19,7 @@ #include <linux/topology.h> #include <asm/types.h> #include <asm/percpu.h> +#include <asm/uv/uv.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/bios.h> #include <asm/irq_vectors.h> @@ -243,83 +244,61 @@ static inline int uv_hub_info_check(int version) #define UV4_HUB_REVISION_BASE 7 #define UV4A_HUB_REVISION_BASE 8 /* UV4 (fixed) rev 2 */ -#ifdef UV1_HUB_IS_SUPPORTED +/* WARNING: UVx_HUB_IS_SUPPORTED defines are deprecated and will be removed */ static inline int is_uv1_hub(void) { - return uv_hub_info->hub_revision < UV2_HUB_REVISION_BASE; -} +#ifdef UV1_HUB_IS_SUPPORTED + return is_uv_hubbed(uv(1)); #else -static inline int is_uv1_hub(void) -{ return 0; -} #endif +} -#ifdef UV2_HUB_IS_SUPPORTED static inline int is_uv2_hub(void) { - return ((uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE) && - (uv_hub_info->hub_revision < UV3_HUB_REVISION_BASE)); -} +#ifdef UV2_HUB_IS_SUPPORTED + return is_uv_hubbed(uv(2)); #else -static inline int is_uv2_hub(void) -{ return 0; -} #endif +} -#ifdef UV3_HUB_IS_SUPPORTED static inline int is_uv3_hub(void) { - return ((uv_hub_info->hub_revision >= UV3_HUB_REVISION_BASE) && - (uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE)); -} +#ifdef UV3_HUB_IS_SUPPORTED + return is_uv_hubbed(uv(3)); #else -static inline int is_uv3_hub(void) -{ return 0; -} #endif +} /* First test "is UV4A", then "is UV4" */ -#ifdef UV4A_HUB_IS_SUPPORTED -static inline int is_uv4a_hub(void) -{ - return (uv_hub_info->hub_revision >= UV4A_HUB_REVISION_BASE); -} -#else static inline int is_uv4a_hub(void) { +#ifdef UV4A_HUB_IS_SUPPORTED + if (is_uv_hubbed(uv(4))) + return (uv_hub_info->hub_revision == UV4A_HUB_REVISION_BASE); +#endif return 0; } -#endif -#ifdef UV4_HUB_IS_SUPPORTED static inline int is_uv4_hub(void) { - return uv_hub_info->hub_revision >= UV4_HUB_REVISION_BASE; -} +#ifdef UV4_HUB_IS_SUPPORTED + return is_uv_hubbed(uv(4)); #else -static inline int is_uv4_hub(void) -{ return 0; -} #endif +} static inline int is_uvx_hub(void) { - if (uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE) - return uv_hub_info->hub_revision; - - return 0; + return (is_uv_hubbed(-2) >= uv(2)); } static inline int is_uv_hub(void) { -#ifdef UV1_HUB_IS_SUPPORTED - return uv_hub_info->hub_revision; -#endif - return is_uvx_hub(); + return is_uv1_hub() || is_uvx_hub(); } union uvh_apicid { diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 230474e2ddb5..bbcdc7b8f963 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -21,6 +21,7 @@ struct vdso_image { long sym_vvar_page; long sym_pvclock_page; long sym_hvclock_page; + long sym_timens_page; long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index ba71a63cdac4..6ee1f7dba34b 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -21,6 +21,7 @@ #include <clocksource/hyperv_timer.h> #define __vdso_data (VVAR(_vdso_data)) +#define __timens_vdso_data (TIMENS(_vdso_data)) #define VDSO_HAS_TIME 1 @@ -51,11 +52,18 @@ extern struct pvclock_vsyscall_time_info pvclock_page __attribute__((visibility("hidden"))); #endif -#ifdef CONFIG_HYPERV_TSCPAGE +#ifdef CONFIG_HYPERV_TIMER extern struct ms_hyperv_tsc_page hvclock_page __attribute__((visibility("hidden"))); #endif +#ifdef CONFIG_TIME_NS +static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void) +{ + return __timens_vdso_data; +} +#endif + #ifndef BUILD_VDSO32 static __always_inline @@ -96,8 +104,6 @@ long clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) #else -#define VDSO_HAS_32BIT_FALLBACK 1 - static __always_inline long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -228,7 +234,7 @@ static u64 vread_pvclock(void) } #endif -#ifdef CONFIG_HYPERV_TSCPAGE +#ifdef CONFIG_HYPERV_TIMER static u64 vread_hvclock(void) { return hv_read_tsc_page(&hvclock_page); @@ -251,7 +257,7 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode) return vread_pvclock(); } #endif -#ifdef CONFIG_HYPERV_TSCPAGE +#ifdef CONFIG_HYPERV_TIMER if (clock_mode == VCLOCK_HVCLOCK) { barrier(); return vread_hvclock(); diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h new file mode 100644 index 000000000000..29837740b520 --- /dev/null +++ b/arch/x86/include/asm/vmalloc.h @@ -0,0 +1,6 @@ +#ifndef _ASM_X86_VMALLOC_H +#define _ASM_X86_VMALLOC_H + +#include <asm/pgtable_areas.h> + +#endif /* _ASM_X86_VMALLOC_H */ diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h new file mode 100644 index 000000000000..ac9fc51e2b18 --- /dev/null +++ b/arch/x86/include/asm/vmware.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 or MIT */ +#ifndef _ASM_X86_VMWARE_H +#define _ASM_X86_VMWARE_H + +#include <asm/cpufeatures.h> +#include <asm/alternative.h> +#include <linux/stringify.h> + +/* + * The hypercall definitions differ in the low word of the %edx argument + * in the following way: the old port base interface uses the port + * number to distinguish between high- and low bandwidth versions. + * + * The new vmcall interface instead uses a set of flags to select + * bandwidth mode and transfer direction. The flags should be loaded + * into %dx by any user and are automatically replaced by the port + * number if the VMWARE_HYPERVISOR_PORT method is used. + * + * In short, new driver code should strictly use the new definition of + * %dx content. + */ + +/* Old port-based version */ +#define VMWARE_HYPERVISOR_PORT 0x5658 +#define VMWARE_HYPERVISOR_PORT_HB 0x5659 + +/* Current vmcall / vmmcall version */ +#define VMWARE_HYPERVISOR_HB BIT(0) +#define VMWARE_HYPERVISOR_OUT BIT(1) + +/* The low bandwidth call. The low word of edx is presumed clear. */ +#define VMWARE_HYPERCALL \ + ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \ + "inl (%%dx), %%eax", \ + "vmcall", X86_FEATURE_VMCALL, \ + "vmmcall", X86_FEATURE_VMW_VMMCALL) + +/* + * The high bandwidth out call. The low word of edx is presumed to have the + * HB and OUT bits set. + */ +#define VMWARE_HYPERCALL_HB_OUT \ + ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \ + "rep outsb", \ + "vmcall", X86_FEATURE_VMCALL, \ + "vmmcall", X86_FEATURE_VMW_VMMCALL) + +/* + * The high bandwidth in call. The low word of edx is presumed to have the + * HB bit set. + */ +#define VMWARE_HYPERCALL_HB_IN \ + ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \ + "rep insb", \ + "vmcall", X86_FEATURE_VMCALL, \ + "vmmcall", X86_FEATURE_VMW_VMMCALL) +#endif diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index a39136b0d509..2a85287b3685 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -15,66 +15,70 @@ #include <linux/bitops.h> #include <linux/types.h> #include <uapi/asm/vmx.h> +#include <asm/vmxfeatures.h> + +#define VMCS_CONTROL_BIT(x) BIT(VMX_FEATURE_##x & 0x1f) /* * Definitions of Primary Processor-Based VM-Execution Controls. */ -#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004 -#define CPU_BASED_USE_TSC_OFFSETING 0x00000008 -#define CPU_BASED_HLT_EXITING 0x00000080 -#define CPU_BASED_INVLPG_EXITING 0x00000200 -#define CPU_BASED_MWAIT_EXITING 0x00000400 -#define CPU_BASED_RDPMC_EXITING 0x00000800 -#define CPU_BASED_RDTSC_EXITING 0x00001000 -#define CPU_BASED_CR3_LOAD_EXITING 0x00008000 -#define CPU_BASED_CR3_STORE_EXITING 0x00010000 -#define CPU_BASED_CR8_LOAD_EXITING 0x00080000 -#define CPU_BASED_CR8_STORE_EXITING 0x00100000 -#define CPU_BASED_TPR_SHADOW 0x00200000 -#define CPU_BASED_VIRTUAL_NMI_PENDING 0x00400000 -#define CPU_BASED_MOV_DR_EXITING 0x00800000 -#define CPU_BASED_UNCOND_IO_EXITING 0x01000000 -#define CPU_BASED_USE_IO_BITMAPS 0x02000000 -#define CPU_BASED_MONITOR_TRAP_FLAG 0x08000000 -#define CPU_BASED_USE_MSR_BITMAPS 0x10000000 -#define CPU_BASED_MONITOR_EXITING 0x20000000 -#define CPU_BASED_PAUSE_EXITING 0x40000000 -#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS 0x80000000 +#define CPU_BASED_INTR_WINDOW_EXITING VMCS_CONTROL_BIT(INTR_WINDOW_EXITING) +#define CPU_BASED_USE_TSC_OFFSETTING VMCS_CONTROL_BIT(USE_TSC_OFFSETTING) +#define CPU_BASED_HLT_EXITING VMCS_CONTROL_BIT(HLT_EXITING) +#define CPU_BASED_INVLPG_EXITING VMCS_CONTROL_BIT(INVLPG_EXITING) +#define CPU_BASED_MWAIT_EXITING VMCS_CONTROL_BIT(MWAIT_EXITING) +#define CPU_BASED_RDPMC_EXITING VMCS_CONTROL_BIT(RDPMC_EXITING) +#define CPU_BASED_RDTSC_EXITING VMCS_CONTROL_BIT(RDTSC_EXITING) +#define CPU_BASED_CR3_LOAD_EXITING VMCS_CONTROL_BIT(CR3_LOAD_EXITING) +#define CPU_BASED_CR3_STORE_EXITING VMCS_CONTROL_BIT(CR3_STORE_EXITING) +#define CPU_BASED_CR8_LOAD_EXITING VMCS_CONTROL_BIT(CR8_LOAD_EXITING) +#define CPU_BASED_CR8_STORE_EXITING VMCS_CONTROL_BIT(CR8_STORE_EXITING) +#define CPU_BASED_TPR_SHADOW VMCS_CONTROL_BIT(VIRTUAL_TPR) +#define CPU_BASED_NMI_WINDOW_EXITING VMCS_CONTROL_BIT(NMI_WINDOW_EXITING) +#define CPU_BASED_MOV_DR_EXITING VMCS_CONTROL_BIT(MOV_DR_EXITING) +#define CPU_BASED_UNCOND_IO_EXITING VMCS_CONTROL_BIT(UNCOND_IO_EXITING) +#define CPU_BASED_USE_IO_BITMAPS VMCS_CONTROL_BIT(USE_IO_BITMAPS) +#define CPU_BASED_MONITOR_TRAP_FLAG VMCS_CONTROL_BIT(MONITOR_TRAP_FLAG) +#define CPU_BASED_USE_MSR_BITMAPS VMCS_CONTROL_BIT(USE_MSR_BITMAPS) +#define CPU_BASED_MONITOR_EXITING VMCS_CONTROL_BIT(MONITOR_EXITING) +#define CPU_BASED_PAUSE_EXITING VMCS_CONTROL_BIT(PAUSE_EXITING) +#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS VMCS_CONTROL_BIT(SEC_CONTROLS) #define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x0401e172 /* * Definitions of Secondary Processor-Based VM-Execution Controls. */ -#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001 -#define SECONDARY_EXEC_ENABLE_EPT 0x00000002 -#define SECONDARY_EXEC_DESC 0x00000004 -#define SECONDARY_EXEC_RDTSCP 0x00000008 -#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE 0x00000010 -#define SECONDARY_EXEC_ENABLE_VPID 0x00000020 -#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 -#define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080 -#define SECONDARY_EXEC_APIC_REGISTER_VIRT 0x00000100 -#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY 0x00000200 -#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400 -#define SECONDARY_EXEC_RDRAND_EXITING 0x00000800 -#define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000 -#define SECONDARY_EXEC_ENABLE_VMFUNC 0x00002000 -#define SECONDARY_EXEC_SHADOW_VMCS 0x00004000 -#define SECONDARY_EXEC_ENCLS_EXITING 0x00008000 -#define SECONDARY_EXEC_RDSEED_EXITING 0x00010000 -#define SECONDARY_EXEC_ENABLE_PML 0x00020000 -#define SECONDARY_EXEC_PT_CONCEAL_VMX 0x00080000 -#define SECONDARY_EXEC_XSAVES 0x00100000 -#define SECONDARY_EXEC_PT_USE_GPA 0x01000000 -#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC 0x00400000 -#define SECONDARY_EXEC_TSC_SCALING 0x02000000 - -#define PIN_BASED_EXT_INTR_MASK 0x00000001 -#define PIN_BASED_NMI_EXITING 0x00000008 -#define PIN_BASED_VIRTUAL_NMIS 0x00000020 -#define PIN_BASED_VMX_PREEMPTION_TIMER 0x00000040 -#define PIN_BASED_POSTED_INTR 0x00000080 +#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES VMCS_CONTROL_BIT(VIRT_APIC_ACCESSES) +#define SECONDARY_EXEC_ENABLE_EPT VMCS_CONTROL_BIT(EPT) +#define SECONDARY_EXEC_DESC VMCS_CONTROL_BIT(DESC_EXITING) +#define SECONDARY_EXEC_RDTSCP VMCS_CONTROL_BIT(RDTSCP) +#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE VMCS_CONTROL_BIT(VIRTUAL_X2APIC) +#define SECONDARY_EXEC_ENABLE_VPID VMCS_CONTROL_BIT(VPID) +#define SECONDARY_EXEC_WBINVD_EXITING VMCS_CONTROL_BIT(WBINVD_EXITING) +#define SECONDARY_EXEC_UNRESTRICTED_GUEST VMCS_CONTROL_BIT(UNRESTRICTED_GUEST) +#define SECONDARY_EXEC_APIC_REGISTER_VIRT VMCS_CONTROL_BIT(APIC_REGISTER_VIRT) +#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY VMCS_CONTROL_BIT(VIRT_INTR_DELIVERY) +#define SECONDARY_EXEC_PAUSE_LOOP_EXITING VMCS_CONTROL_BIT(PAUSE_LOOP_EXITING) +#define SECONDARY_EXEC_RDRAND_EXITING VMCS_CONTROL_BIT(RDRAND_EXITING) +#define SECONDARY_EXEC_ENABLE_INVPCID VMCS_CONTROL_BIT(INVPCID) +#define SECONDARY_EXEC_ENABLE_VMFUNC VMCS_CONTROL_BIT(VMFUNC) +#define SECONDARY_EXEC_SHADOW_VMCS VMCS_CONTROL_BIT(SHADOW_VMCS) +#define SECONDARY_EXEC_ENCLS_EXITING VMCS_CONTROL_BIT(ENCLS_EXITING) +#define SECONDARY_EXEC_RDSEED_EXITING VMCS_CONTROL_BIT(RDSEED_EXITING) +#define SECONDARY_EXEC_ENABLE_PML VMCS_CONTROL_BIT(PAGE_MOD_LOGGING) +#define SECONDARY_EXEC_PT_CONCEAL_VMX VMCS_CONTROL_BIT(PT_CONCEAL_VMX) +#define SECONDARY_EXEC_XSAVES VMCS_CONTROL_BIT(XSAVES) +#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC) +#define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA) +#define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) +#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE 0x04000000 + +#define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING) +#define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING) +#define PIN_BASED_VIRTUAL_NMIS VMCS_CONTROL_BIT(VIRTUAL_NMIS) +#define PIN_BASED_VMX_PREEMPTION_TIMER VMCS_CONTROL_BIT(PREEMPTION_TIMER) +#define PIN_BASED_POSTED_INTR VMCS_CONTROL_BIT(POSTED_INTR) #define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x00000016 @@ -110,9 +114,12 @@ #define VMX_MISC_SAVE_EFER_LMA 0x00000020 #define VMX_MISC_ACTIVITY_HLT 0x00000040 #define VMX_MISC_ZERO_LEN_INS 0x40000000 +#define VMX_MISC_MSR_LIST_MULTIPLIER 512 /* VMFUNC functions */ -#define VMX_VMFUNC_EPTP_SWITCHING 0x00000001 +#define VMFUNC_CONTROL_BIT(x) BIT((VMX_FEATURE_##x & 0x1f) - 28) + +#define VMX_VMFUNC_EPTP_SWITCHING VMFUNC_CONTROL_BIT(EPTP_SWITCHING) #define VMFUNC_EPTP_ENTRIES 512 static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic) @@ -562,6 +569,20 @@ enum vm_instruction_error_number { VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID = 28, }; +/* + * VM-instruction errors that can be encountered on VM-Enter, used to trace + * nested VM-Enter failures reported by hardware. Errors unique to VM-Enter + * from a SMI Transfer Monitor are not included as things have gone seriously + * sideways if we get one of those... + */ +#define VMX_VMENTER_INSTRUCTION_ERRORS \ + { VMXERR_VMLAUNCH_NONCLEAR_VMCS, "VMLAUNCH_NONCLEAR_VMCS" }, \ + { VMXERR_VMRESUME_NONLAUNCHED_VMCS, "VMRESUME_NONLAUNCHED_VMCS" }, \ + { VMXERR_VMRESUME_AFTER_VMXOFF, "VMRESUME_AFTER_VMXOFF" }, \ + { VMXERR_ENTRY_INVALID_CONTROL_FIELD, "VMENTRY_INVALID_CONTROL_FIELD" }, \ + { VMXERR_ENTRY_INVALID_HOST_STATE_FIELD, "VMENTRY_INVALID_HOST_STATE_FIELD" }, \ + { VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS, "VMENTRY_EVENTS_BLOCKED_BY_MOV_SS" } + enum vmx_l1d_flush_state { VMENTER_L1D_FLUSH_AUTO, VMENTER_L1D_FLUSH_NEVER, diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h new file mode 100644 index 000000000000..a50e4a0de315 --- /dev/null +++ b/arch/x86/include/asm/vmxfeatures.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_VMXFEATURES_H +#define _ASM_X86_VMXFEATURES_H + +/* + * Defines VMX CPU feature bits + */ +#define NVMXINTS 3 /* N 32-bit words worth of info */ + +/* + * Note: If the comment begins with a quoted string, that string is used + * in /proc/cpuinfo instead of the macro name. If the string is "", + * this feature bit is not displayed in /proc/cpuinfo at all. + */ + +/* Pin-Based VM-Execution Controls, EPT/VPID, APIC and VM-Functions, word 0 */ +#define VMX_FEATURE_INTR_EXITING ( 0*32+ 0) /* "" VM-Exit on vectored interrupts */ +#define VMX_FEATURE_NMI_EXITING ( 0*32+ 3) /* "" VM-Exit on NMIs */ +#define VMX_FEATURE_VIRTUAL_NMIS ( 0*32+ 5) /* "vnmi" NMI virtualization */ +#define VMX_FEATURE_PREEMPTION_TIMER ( 0*32+ 6) /* VMX Preemption Timer */ +#define VMX_FEATURE_POSTED_INTR ( 0*32+ 7) /* Posted Interrupts */ + +/* EPT/VPID features, scattered to bits 16-23 */ +#define VMX_FEATURE_INVVPID ( 0*32+ 16) /* INVVPID is supported */ +#define VMX_FEATURE_EPT_EXECUTE_ONLY ( 0*32+ 17) /* "ept_x_only" EPT entries can be execute only */ +#define VMX_FEATURE_EPT_AD ( 0*32+ 18) /* EPT Accessed/Dirty bits */ +#define VMX_FEATURE_EPT_1GB ( 0*32+ 19) /* 1GB EPT pages */ + +/* Aggregated APIC features 24-27 */ +#define VMX_FEATURE_FLEXPRIORITY ( 0*32+ 24) /* TPR shadow + virt APIC */ +#define VMX_FEATURE_APICV ( 0*32+ 25) /* TPR shadow + APIC reg virt + virt intr delivery + posted interrupts */ + +/* VM-Functions, shifted to bits 28-31 */ +#define VMX_FEATURE_EPTP_SWITCHING ( 0*32+ 28) /* EPTP switching (in guest) */ + +/* Primary Processor-Based VM-Execution Controls, word 1 */ +#define VMX_FEATURE_INTR_WINDOW_EXITING ( 1*32+ 2) /* "" VM-Exit if INTRs are unblocked in guest */ +#define VMX_FEATURE_USE_TSC_OFFSETTING ( 1*32+ 3) /* "tsc_offset" Offset hardware TSC when read in guest */ +#define VMX_FEATURE_HLT_EXITING ( 1*32+ 7) /* "" VM-Exit on HLT */ +#define VMX_FEATURE_INVLPG_EXITING ( 1*32+ 9) /* "" VM-Exit on INVLPG */ +#define VMX_FEATURE_MWAIT_EXITING ( 1*32+ 10) /* "" VM-Exit on MWAIT */ +#define VMX_FEATURE_RDPMC_EXITING ( 1*32+ 11) /* "" VM-Exit on RDPMC */ +#define VMX_FEATURE_RDTSC_EXITING ( 1*32+ 12) /* "" VM-Exit on RDTSC */ +#define VMX_FEATURE_CR3_LOAD_EXITING ( 1*32+ 15) /* "" VM-Exit on writes to CR3 */ +#define VMX_FEATURE_CR3_STORE_EXITING ( 1*32+ 16) /* "" VM-Exit on reads from CR3 */ +#define VMX_FEATURE_CR8_LOAD_EXITING ( 1*32+ 19) /* "" VM-Exit on writes to CR8 */ +#define VMX_FEATURE_CR8_STORE_EXITING ( 1*32+ 20) /* "" VM-Exit on reads from CR8 */ +#define VMX_FEATURE_VIRTUAL_TPR ( 1*32+ 21) /* "vtpr" TPR virtualization, a.k.a. TPR shadow */ +#define VMX_FEATURE_NMI_WINDOW_EXITING ( 1*32+ 22) /* "" VM-Exit if NMIs are unblocked in guest */ +#define VMX_FEATURE_MOV_DR_EXITING ( 1*32+ 23) /* "" VM-Exit on accesses to debug registers */ +#define VMX_FEATURE_UNCOND_IO_EXITING ( 1*32+ 24) /* "" VM-Exit on *all* IN{S} and OUT{S}*/ +#define VMX_FEATURE_USE_IO_BITMAPS ( 1*32+ 25) /* "" VM-Exit based on I/O port */ +#define VMX_FEATURE_MONITOR_TRAP_FLAG ( 1*32+ 27) /* "mtf" VMX single-step VM-Exits */ +#define VMX_FEATURE_USE_MSR_BITMAPS ( 1*32+ 28) /* "" VM-Exit based on MSR index */ +#define VMX_FEATURE_MONITOR_EXITING ( 1*32+ 29) /* "" VM-Exit on MONITOR (MWAIT's accomplice) */ +#define VMX_FEATURE_PAUSE_EXITING ( 1*32+ 30) /* "" VM-Exit on PAUSE (unconditionally) */ +#define VMX_FEATURE_SEC_CONTROLS ( 1*32+ 31) /* "" Enable Secondary VM-Execution Controls */ + +/* Secondary Processor-Based VM-Execution Controls, word 2 */ +#define VMX_FEATURE_VIRT_APIC_ACCESSES ( 2*32+ 0) /* "vapic" Virtualize memory mapped APIC accesses */ +#define VMX_FEATURE_EPT ( 2*32+ 1) /* Extended Page Tables, a.k.a. Two-Dimensional Paging */ +#define VMX_FEATURE_DESC_EXITING ( 2*32+ 2) /* "" VM-Exit on {S,L}*DT instructions */ +#define VMX_FEATURE_RDTSCP ( 2*32+ 3) /* "" Enable RDTSCP in guest */ +#define VMX_FEATURE_VIRTUAL_X2APIC ( 2*32+ 4) /* "" Virtualize X2APIC for the guest */ +#define VMX_FEATURE_VPID ( 2*32+ 5) /* Virtual Processor ID (TLB ASID modifier) */ +#define VMX_FEATURE_WBINVD_EXITING ( 2*32+ 6) /* "" VM-Exit on WBINVD */ +#define VMX_FEATURE_UNRESTRICTED_GUEST ( 2*32+ 7) /* Allow Big Real Mode and other "invalid" states */ +#define VMX_FEATURE_APIC_REGISTER_VIRT ( 2*32+ 8) /* "vapic_reg" Hardware emulation of reads to the virtual-APIC */ +#define VMX_FEATURE_VIRT_INTR_DELIVERY ( 2*32+ 9) /* "vid" Evaluation and delivery of pending virtual interrupts */ +#define VMX_FEATURE_PAUSE_LOOP_EXITING ( 2*32+ 10) /* "ple" Conditionally VM-Exit on PAUSE at CPL0 */ +#define VMX_FEATURE_RDRAND_EXITING ( 2*32+ 11) /* "" VM-Exit on RDRAND*/ +#define VMX_FEATURE_INVPCID ( 2*32+ 12) /* "" Enable INVPCID in guest */ +#define VMX_FEATURE_VMFUNC ( 2*32+ 13) /* "" Enable VM-Functions (leaf dependent) */ +#define VMX_FEATURE_SHADOW_VMCS ( 2*32+ 14) /* VMREAD/VMWRITE in guest can access shadow VMCS */ +#define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */ +#define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* "" VM-Exit on RDSEED */ +#define VMX_FEATURE_PAGE_MOD_LOGGING ( 2*32+ 17) /* "pml" Log dirty pages into buffer */ +#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* "" Conditionally reflect EPT violations as #VE exceptions */ +#define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */ +#define VMX_FEATURE_XSAVES ( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */ +#define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */ +#define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* "" Processor Trace logs GPAs */ +#define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */ +#define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ + +#endif /* _ASM_X86_VMXFEATURES_H */ diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index 32f5d9a0b90e..183e98e49ab9 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -19,10 +19,10 @@ #ifndef _ASM_X86_VVAR_H #define _ASM_X86_VVAR_H -#if defined(__VVAR_KERNEL_LDS) - -/* The kernel linker script defines its own magic to put vvars in the - * right place. +#ifdef EMIT_VVAR +/* + * EMIT_VVAR() is used by the kernel linker script to put vvars in the + * right place. Also, it's used by kernel code to import offsets values. */ #define DECLARE_VVAR(offset, type, name) \ EMIT_VVAR(name, offset) @@ -33,9 +33,12 @@ extern char __vvar_page; #define DECLARE_VVAR(offset, type, name) \ extern type vvar_ ## name[CS_BASES] \ - __attribute__((visibility("hidden"))); + __attribute__((visibility("hidden"))); \ + extern type timens_ ## name[CS_BASES] \ + __attribute__((visibility("hidden"))); \ #define VVAR(name) (vvar_ ## name) +#define TIMENS(name) (timens_ ## name) #define DEFINE_VVAR(type, name) \ type name[CS_BASES] \ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index ac0934189017..96d9cd208610 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -51,12 +51,14 @@ struct x86_init_resources { * are set up. * @intr_init: interrupt init code * @trap_init: platform specific trap setup + * @intr_mode_select: interrupt delivery mode selection * @intr_mode_init: interrupt delivery mode setup */ struct x86_init_irqs { void (*pre_vector_init)(void); void (*intr_init)(void); void (*trap_init)(void); + void (*intr_mode_select)(void); void (*intr_mode_init)(void); }; @@ -134,10 +136,12 @@ struct x86_hyper_init { /** * struct x86_init_acpi - x86 ACPI init functions + * @set_root_poitner: set RSDP address * @get_root_pointer: get RSDP address * @reduced_hw_early_init: hardware reduced platform early init */ struct x86_init_acpi { + void (*set_root_pointer)(u64 addr); u64 (*get_root_pointer)(void); void (*reduced_hw_early_init)(void); }; diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 42e1245af0d8..ff4b52e37e60 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -62,6 +62,4 @@ void xen_arch_register_cpu(int num); void xen_arch_unregister_cpu(int num); #endif -extern void xen_set_iopl_mask(unsigned mask); - #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index 62ca03ef5c65..9139b3e86316 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -379,12 +379,9 @@ struct xen_pmu_arch { * Prefix forces emulation of some non-trapping instructions. * Currently only CPUID. */ -#ifdef __ASSEMBLY__ -#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ; -#define XEN_CPUID XEN_EMULATE_PREFIX cpuid -#else -#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; " -#define XEN_CPUID XEN_EMULATE_PREFIX "cpuid" -#endif +#include <asm/emulate_prefix.h> + +#define XEN_EMULATE_PREFIX __ASM_FORM(.byte __XEN_EMULATE_PREFIX ;) +#define XEN_CPUID XEN_EMULATE_PREFIX __ASM_FORM(cpuid) #endif /* _ASM_X86_XEN_INTERFACE_H */ diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h index 116777e7f387..63cd41b2e17a 100644 --- a/arch/x86/include/asm/xen/page-coherent.h +++ b/arch/x86/include/asm/xen/page-coherent.h @@ -21,18 +21,4 @@ static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, free_pages((unsigned long) cpu_addr, get_order(size)); } -static inline void xen_dma_map_page(struct device *hwdev, struct page *page, - dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, unsigned long attrs) { } - -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, - unsigned long attrs) { } - -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) { } - -static inline void xen_dma_sync_single_for_device(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) { } - #endif /* _ASM_X86_XEN_PAGE_COHERENT_H */ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index c895df5482c5..8669c6bdbb84 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_BOOTPARAM_H #define _ASM_X86_BOOTPARAM_H -/* setup_data types */ +/* setup_data/setup_indirect types */ #define SETUP_NONE 0 #define SETUP_E820_EXT 1 #define SETUP_DTB 2 @@ -11,6 +11,11 @@ #define SETUP_APPLE_PROPERTIES 5 #define SETUP_JAILHOUSE 6 +#define SETUP_INDIRECT (1<<31) + +/* SETUP_INDIRECT | max(SETUP_*) */ +#define SETUP_TYPE_MAX (SETUP_INDIRECT | SETUP_JAILHOUSE) + /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF #define RAMDISK_PROMPT_FLAG 0x8000 @@ -49,6 +54,14 @@ struct setup_data { __u8 data[0]; }; +/* extensible setup indirect data node */ +struct setup_indirect { + __u32 type; + __u32 reserved; /* Reserved, must be set to zero. */ + __u64 len; + __u64 addr; +}; + struct setup_header { __u8 setup_sects; __u16 root_flags; @@ -88,6 +101,7 @@ struct setup_header { __u64 pref_address; __u32 init_size; __u32 handover_offset; + __u32 kernel_info_offset; } __attribute__((packed)); struct sys_desc_table { @@ -139,15 +153,22 @@ struct boot_e820_entry { * setup data structure. */ struct jailhouse_setup_data { - __u16 version; - __u16 compatible_version; - __u16 pm_timer_address; - __u16 num_cpus; - __u64 pci_mmconfig_base; - __u32 tsc_khz; - __u32 apic_khz; - __u8 standard_ioapic; - __u8 cpu_ids[255]; + struct { + __u16 version; + __u16 compatible_version; + } __attribute__((packed)) hdr; + struct { + __u16 pm_timer_address; + __u16 num_cpus; + __u64 pci_mmconfig_base; + __u32 tsc_khz; + __u32 apic_khz; + __u8 standard_ioapic; + __u8 cpu_ids[255]; + } __attribute__((packed)) v1; + struct { + __u32 flags; + } __attribute__((packed)) v2; } __attribute__((packed)); /* The so-called "zeropage" */ diff --git a/arch/x86/include/uapi/asm/errno.h b/arch/x86/include/uapi/asm/errno.h deleted file mode 100644 index 4c82b503d92f..000000000000 --- a/arch/x86/include/uapi/asm/errno.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/errno.h> diff --git a/arch/x86/include/uapi/asm/fcntl.h b/arch/x86/include/uapi/asm/fcntl.h deleted file mode 100644 index 46ab12db5739..000000000000 --- a/arch/x86/include/uapi/asm/fcntl.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/fcntl.h> diff --git a/arch/x86/include/uapi/asm/ioctl.h b/arch/x86/include/uapi/asm/ioctl.h deleted file mode 100644 index b279fe06dfe5..000000000000 --- a/arch/x86/include/uapi/asm/ioctl.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ioctl.h> diff --git a/arch/x86/include/uapi/asm/ioctls.h b/arch/x86/include/uapi/asm/ioctls.h deleted file mode 100644 index ec34c760665e..000000000000 --- a/arch/x86/include/uapi/asm/ioctls.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ioctls.h> diff --git a/arch/x86/include/uapi/asm/ipcbuf.h b/arch/x86/include/uapi/asm/ipcbuf.h deleted file mode 100644 index 84c7e51cb6d0..000000000000 --- a/arch/x86/include/uapi/asm/ipcbuf.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ipcbuf.h> diff --git a/arch/x86/include/uapi/asm/msgbuf.h b/arch/x86/include/uapi/asm/msgbuf.h index 90ab9a795b49..b3d0664fadc9 100644 --- a/arch/x86/include/uapi/asm/msgbuf.h +++ b/arch/x86/include/uapi/asm/msgbuf.h @@ -5,6 +5,9 @@ #if !defined(__x86_64__) || !defined(__ILP32__) #include <asm-generic/msgbuf.h> #else + +#include <asm/ipcbuf.h> + /* * The msqid64_ds structure for x86 architecture with x32 ABI. * @@ -15,9 +18,9 @@ struct msqid64_ds { struct ipc64_perm msg_perm; - __kernel_time_t msg_stime; /* last msgsnd time */ - __kernel_time_t msg_rtime; /* last msgrcv time */ - __kernel_time_t msg_ctime; /* last change time */ + __kernel_long_t msg_stime; /* last msgsnd time */ + __kernel_long_t msg_rtime; /* last msgrcv time */ + __kernel_long_t msg_ctime; /* last change time */ __kernel_ulong_t msg_cbytes; /* current number of bytes on queue */ __kernel_ulong_t msg_qnum; /* number of messages in queue */ __kernel_ulong_t msg_qbytes; /* max number of bytes on queue */ diff --git a/arch/x86/include/uapi/asm/param.h b/arch/x86/include/uapi/asm/param.h deleted file mode 100644 index 965d45427975..000000000000 --- a/arch/x86/include/uapi/asm/param.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/param.h> diff --git a/arch/x86/include/uapi/asm/resource.h b/arch/x86/include/uapi/asm/resource.h deleted file mode 100644 index 04bc4db8921b..000000000000 --- a/arch/x86/include/uapi/asm/resource.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/resource.h> diff --git a/arch/x86/include/uapi/asm/sembuf.h b/arch/x86/include/uapi/asm/sembuf.h index 89de6cd9f0a7..71205b02a191 100644 --- a/arch/x86/include/uapi/asm/sembuf.h +++ b/arch/x86/include/uapi/asm/sembuf.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_SEMBUF_H #define _ASM_X86_SEMBUF_H +#include <asm/ipcbuf.h> + /* * The semid64_ds structure for x86 architecture. * Note extra padding because this structure is passed back and forth @@ -21,9 +23,9 @@ struct semid64_ds { unsigned long sem_ctime; /* last change time */ unsigned long sem_ctime_high; #else - __kernel_time_t sem_otime; /* last semop time */ + __kernel_long_t sem_otime; /* last semop time */ __kernel_ulong_t __unused1; - __kernel_time_t sem_ctime; /* last change time */ + __kernel_long_t sem_ctime; /* last change time */ __kernel_ulong_t __unused2; #endif __kernel_ulong_t sem_nsems; /* no. of semaphores in array */ diff --git a/arch/x86/include/uapi/asm/shmbuf.h b/arch/x86/include/uapi/asm/shmbuf.h index 644421f3823b..f0305dc660c9 100644 --- a/arch/x86/include/uapi/asm/shmbuf.h +++ b/arch/x86/include/uapi/asm/shmbuf.h @@ -16,9 +16,9 @@ struct shmid64_ds { struct ipc64_perm shm_perm; /* operation perms */ size_t shm_segsz; /* size of segment (bytes) */ - __kernel_time_t shm_atime; /* last attach time */ - __kernel_time_t shm_dtime; /* last detach time */ - __kernel_time_t shm_ctime; /* last change time */ + __kernel_long_t shm_atime; /* last attach time */ + __kernel_long_t shm_dtime; /* last detach time */ + __kernel_long_t shm_ctime; /* last change time */ __kernel_pid_t shm_cpid; /* pid of creator */ __kernel_pid_t shm_lpid; /* pid of last operator */ __kernel_ulong_t shm_nattch; /* no. of current attaches */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index a9731f8a480f..2e8a30f06c74 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -75,6 +75,7 @@ #define SVM_EXIT_MWAIT 0x08b #define SVM_EXIT_MWAIT_COND 0x08c #define SVM_EXIT_XSETBV 0x08d +#define SVM_EXIT_RDPRU 0x08e #define SVM_EXIT_NPF 0x400 #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402 diff --git a/arch/x86/include/uapi/asm/termbits.h b/arch/x86/include/uapi/asm/termbits.h deleted file mode 100644 index 3935b106de79..000000000000 --- a/arch/x86/include/uapi/asm/termbits.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/termbits.h> diff --git a/arch/x86/include/uapi/asm/termios.h b/arch/x86/include/uapi/asm/termios.h deleted file mode 100644 index 280d78a9d966..000000000000 --- a/arch/x86/include/uapi/asm/termios.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/termios.h> diff --git a/arch/x86/include/uapi/asm/types.h b/arch/x86/include/uapi/asm/types.h deleted file mode 100644 index 9d5c11a24279..000000000000 --- a/arch/x86/include/uapi/asm/types.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _ASM_X86_TYPES_H -#define _ASM_X86_TYPES_H - -#include <asm-generic/types.h> - -#endif /* _ASM_X86_TYPES_H */ diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h index 30d7d04d72d6..196fdd02b8b1 100644 --- a/arch/x86/include/uapi/asm/unistd.h +++ b/arch/x86/include/uapi/asm/unistd.h @@ -3,7 +3,7 @@ #define _UAPI_ASM_X86_UNISTD_H /* x32 syscall flag bit */ -#define __X32_SYSCALL_BIT 0x40000000 +#define __X32_SYSCALL_BIT 0x40000000UL #ifndef __KERNEL__ # ifdef __i386__ diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index f0b0c90dd398..e95b72ec19bc 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -31,8 +31,9 @@ #define EXIT_REASON_EXCEPTION_NMI 0 #define EXIT_REASON_EXTERNAL_INTERRUPT 1 #define EXIT_REASON_TRIPLE_FAULT 2 +#define EXIT_REASON_INIT_SIGNAL 3 -#define EXIT_REASON_PENDING_INTERRUPT 7 +#define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 #define EXIT_REASON_TASK_SWITCH 9 #define EXIT_REASON_CPUID 10 @@ -85,12 +86,15 @@ #define EXIT_REASON_PML_FULL 62 #define EXIT_REASON_XSAVES 63 #define EXIT_REASON_XRSTORS 64 +#define EXIT_REASON_UMWAIT 67 +#define EXIT_REASON_TPAUSE 68 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ - { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_INIT_SIGNAL, "INIT_SIGNAL" }, \ + { EXIT_REASON_INTERRUPT_WINDOW, "INTERRUPT_WINDOW" }, \ { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ { EXIT_REASON_CPUID, "CPUID" }, \ @@ -142,7 +146,9 @@ { EXIT_REASON_RDSEED, "RDSEED" }, \ { EXIT_REASON_PML_FULL, "PML_FULL" }, \ { EXIT_REASON_XSAVES, "XSAVES" }, \ - { EXIT_REASON_XRSTORS, "XRSTORS" } + { EXIT_REASON_XRSTORS, "XRSTORS" }, \ + { EXIT_REASON_UMWAIT, "UMWAIT" }, \ + { EXIT_REASON_TPAUSE, "TPAUSE" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 3578ad248bc9..9b294c13809a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -94,13 +94,16 @@ obj-$(CONFIG_FUNCTION_TRACER) += ftrace_$(BITS).o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o +obj-$(CONFIG_CRASH_CORE) += crash_core_$(BITS).o obj-$(CONFIG_KEXEC_CORE) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-y += kprobes/ obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_DOUBLEFAULT) += doublefault.o +ifeq ($(CONFIG_X86_32),y) +obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o +endif obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_VM86) += vm86_32.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o @@ -134,7 +137,7 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o -obj-$(CONFIG_X86_INTEL_UMIP) += umip.o +obj-$(CONFIG_X86_UMIP) += umip.o obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o @@ -146,7 +149,6 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_AUDIT) += audit_64.o obj-$(CONFIG_GART_IOMMU) += amd_gart_64.o aperture_64.o - obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o obj-$(CONFIG_MMCONF_FAM10H) += mmconf-fam10h_64.o obj-y += vsmp_64.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 17b33ef604f3..04205ce127a1 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1760,6 +1760,11 @@ void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) e820__update_table_print(); } +void x86_default_set_root_pointer(u64 addr) +{ + boot_params.acpi_rsdp_addr = addr; +} + u64 x86_default_get_root_pointer(void) { return boot_params.acpi_rsdp_addr; diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index ca13851f0570..26b7256f590f 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -27,6 +27,17 @@ static char temp_stack[4096]; #endif /** + * acpi_get_wakeup_address - provide physical address for S3 wakeup + * + * Returns the physical address where the kernel should be resumed after the + * system awakes from S3, e.g. for programming into the firmware waking vector. + */ +unsigned long acpi_get_wakeup_address(void) +{ + return ((unsigned long)(real_mode_header->wakeup_start)); +} + +/** * x86_acpi_enter_sleep_state - enter sleep state * @state: Sleep state to enter. * diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index fbb60ca4255c..d06c2079b6c1 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -3,7 +3,7 @@ * Variables and functions used by the code in sleep.c */ -#include <asm/realmode.h> +#include <linux/linkage.h> extern unsigned long saved_video_mode; extern long saved_magic; diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index e95e95960156..daf88f8143c5 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -9,8 +9,7 @@ .code32 ALIGN -ENTRY(wakeup_pmode_return) -wakeup_pmode_return: +SYM_CODE_START(wakeup_pmode_return) movw $__KERNEL_DS, %ax movw %ax, %ss movw %ax, %fs @@ -39,6 +38,7 @@ wakeup_pmode_return: # jump to place where we left off movl saved_eip, %eax jmp *%eax +SYM_CODE_END(wakeup_pmode_return) bogus_magic: jmp bogus_magic @@ -72,7 +72,7 @@ restore_registers: popfl ret -ENTRY(do_suspend_lowlevel) +SYM_CODE_START(do_suspend_lowlevel) call save_processor_state call save_registers pushl $3 @@ -87,10 +87,11 @@ ret_point: call restore_registers call restore_processor_state ret +SYM_CODE_END(do_suspend_lowlevel) .data ALIGN -ENTRY(saved_magic) .long 0 +SYM_DATA(saved_magic, .long 0) saved_eip: .long 0 # saved registers diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index b0715c3ac18d..c8daa92f38dc 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -14,12 +14,17 @@ /* * Hooray, we are in Long 64-bit mode (but still running in low memory) */ -ENTRY(wakeup_long64) +SYM_FUNC_START(wakeup_long64) movq saved_magic, %rax movq $0x123456789abcdef0, %rdx cmpq %rdx, %rax - jne bogus_64_magic + je 2f + /* stop here on a saved_magic mismatch */ + movq $0xbad6d61676963, %rcx +1: + jmp 1b +2: movw $__KERNEL_DS, %ax movw %ax, %ss movw %ax, %ds @@ -35,12 +40,9 @@ ENTRY(wakeup_long64) movq saved_rip, %rax jmp *%rax -ENDPROC(wakeup_long64) +SYM_FUNC_END(wakeup_long64) -bogus_64_magic: - jmp bogus_64_magic - -ENTRY(do_suspend_lowlevel) +SYM_FUNC_START(do_suspend_lowlevel) FRAME_BEGIN subq $8, %rsp xorl %eax, %eax @@ -123,7 +125,7 @@ ENTRY(do_suspend_lowlevel) addq $8, %rsp FRAME_END jmp restore_processor_state -ENDPROC(do_suspend_lowlevel) +SYM_FUNC_END(do_suspend_lowlevel) .data saved_rbp: .quad 0 @@ -134,4 +136,4 @@ saved_rbx: .quad 0 saved_rip: .quad 0 saved_rsp: .quad 0 -ENTRY(saved_magic) .quad 0 +SYM_DATA(saved_magic, .quad 0) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ccd32013c47a..15ac0d5f4b40 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -23,6 +23,7 @@ #include <asm/nmi.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> +#include <asm/insn.h> #include <asm/io.h> #include <asm/fixmap.h> @@ -713,7 +714,7 @@ void __init alternative_instructions(void) * Don't stop machine check exceptions while patching. * MCEs only happen when something got corrupted and in this * case we must do something about the corruption. - * Ignoring it is worse than a unlikely patching race. + * Ignoring it is worse than an unlikely patching race. * Also machine checks tend to be broadcast and if one CPU * goes into machine check the others follow quickly, so we don't * expect a machine check to cause undue problems during to code @@ -753,8 +754,8 @@ void __init alternative_instructions(void) * When you use this code to patch more than one byte of an instruction * you need to make sure that other CPUs cannot execute this code in parallel. * Also no thread must be currently preempted in the middle of these - * instructions. And on the local CPU you need to be protected again NMI or MCE - * handlers seeing an inconsistent instruction while you patch. + * instructions. And on the local CPU you need to be protected against NMI or + * MCE handlers seeing an inconsistent instruction while you patch. */ void __init_or_module text_poke_early(void *addr, const void *opcode, size_t len) @@ -936,74 +937,139 @@ static void do_sync_core(void *info) sync_core(); } -static struct bp_patching_desc { +void text_poke_sync(void) +{ + on_each_cpu(do_sync_core, NULL, 1); +} + +struct text_poke_loc { + s32 rel_addr; /* addr := _stext + rel_addr */ + s32 rel32; + u8 opcode; + const u8 text[POKE_MAX_OPCODE_SIZE]; +}; + +struct bp_patching_desc { struct text_poke_loc *vec; int nr_entries; -} bp_patching; + atomic_t refs; +}; + +static struct bp_patching_desc *bp_desc; -static int patch_cmp(const void *key, const void *elt) +static inline struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) +{ + struct bp_patching_desc *desc = READ_ONCE(*descp); /* rcu_dereference */ + + if (!desc || !atomic_inc_not_zero(&desc->refs)) + return NULL; + + return desc; +} + +static inline void put_desc(struct bp_patching_desc *desc) +{ + smp_mb__before_atomic(); + atomic_dec(&desc->refs); +} + +static inline void *text_poke_addr(struct text_poke_loc *tp) +{ + return _stext + tp->rel_addr; +} + +static int notrace patch_cmp(const void *key, const void *elt) { struct text_poke_loc *tp = (struct text_poke_loc *) elt; - if (key < tp->addr) + if (key < text_poke_addr(tp)) return -1; - if (key > tp->addr) + if (key > text_poke_addr(tp)) return 1; return 0; } NOKPROBE_SYMBOL(patch_cmp); -int poke_int3_handler(struct pt_regs *regs) +int notrace poke_int3_handler(struct pt_regs *regs) { + struct bp_patching_desc *desc; struct text_poke_loc *tp; - unsigned char int3 = 0xcc; + int len, ret = 0; void *ip; + if (user_mode(regs)) + return 0; + /* * Having observed our INT3 instruction, we now must observe - * bp_patching.nr_entries. - * - * nr_entries != 0 INT3 - * WMB RMB - * write INT3 if (nr_entries) + * bp_desc: * - * Idem for other elements in bp_patching. + * bp_desc = desc INT3 + * WMB RMB + * write INT3 if (desc) */ smp_rmb(); - if (likely(!bp_patching.nr_entries)) - return 0; - - if (user_mode(regs)) + desc = try_get_desc(&bp_desc); + if (!desc) return 0; /* - * Discount the sizeof(int3). See text_poke_bp_batch(). + * Discount the INT3. See text_poke_bp_batch(). */ - ip = (void *) regs->ip - sizeof(int3); + ip = (void *) regs->ip - INT3_INSN_SIZE; /* * Skip the binary search if there is a single member in the vector. */ - if (unlikely(bp_patching.nr_entries > 1)) { - tp = bsearch(ip, bp_patching.vec, bp_patching.nr_entries, + if (unlikely(desc->nr_entries > 1)) { + tp = bsearch(ip, desc->vec, desc->nr_entries, sizeof(struct text_poke_loc), patch_cmp); if (!tp) - return 0; + goto out_put; } else { - tp = bp_patching.vec; - if (tp->addr != ip) - return 0; + tp = desc->vec; + if (text_poke_addr(tp) != ip) + goto out_put; } - /* set up the specified breakpoint detour */ - regs->ip = (unsigned long) tp->detour; + len = text_opcode_size(tp->opcode); + ip += len; - return 1; + switch (tp->opcode) { + case INT3_INSN_OPCODE: + /* + * Someone poked an explicit INT3, they'll want to handle it, + * do not consume. + */ + goto out_put; + + case CALL_INSN_OPCODE: + int3_emulate_call(regs, (long)ip + tp->rel32); + break; + + case JMP32_INSN_OPCODE: + case JMP8_INSN_OPCODE: + int3_emulate_jmp(regs, (long)ip + tp->rel32); + break; + + default: + BUG(); + } + + ret = 1; + +out_put: + put_desc(desc); + return ret; } NOKPROBE_SYMBOL(poke_int3_handler); +#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc)) +static struct text_poke_loc tp_vec[TP_VEC_MAX]; +static int tp_vec_nr; + /** * text_poke_bp_batch() -- update instructions on live kernel on SMP * @tp: vector of instructions to patch @@ -1014,7 +1080,7 @@ NOKPROBE_SYMBOL(poke_int3_handler); * synchronization using int3 breakpoint. * * The way it is done: - * - For each entry in the vector: + * - For each entry in the vector: * - add a int3 trap to the address that will be patched * - sync cores * - For each entry in the vector: @@ -1025,16 +1091,20 @@ NOKPROBE_SYMBOL(poke_int3_handler); * replacing opcode * - sync cores */ -void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) +static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) { - int patched_all_but_first = 0; - unsigned char int3 = 0xcc; + struct bp_patching_desc desc = { + .vec = tp, + .nr_entries = nr_entries, + .refs = ATOMIC_INIT(1), + }; + unsigned char int3 = INT3_INSN_OPCODE; unsigned int i; + int do_sync; lockdep_assert_held(&text_mutex); - bp_patching.vec = tp; - bp_patching.nr_entries = nr_entries; + smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */ /* * Corresponding read barrier in int3 notifier for making sure the @@ -1046,45 +1116,153 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) * First step: add a int3 trap to the address that will be patched. */ for (i = 0; i < nr_entries; i++) - text_poke(tp[i].addr, &int3, sizeof(int3)); + text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE); - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); /* * Second step: update all but the first byte of the patched range. */ - for (i = 0; i < nr_entries; i++) { - if (tp[i].len - sizeof(int3) > 0) { - text_poke((char *)tp[i].addr + sizeof(int3), - (const char *)tp[i].opcode + sizeof(int3), - tp[i].len - sizeof(int3)); - patched_all_but_first++; + for (do_sync = 0, i = 0; i < nr_entries; i++) { + int len = text_opcode_size(tp[i].opcode); + + if (len - INT3_INSN_SIZE > 0) { + text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE, + (const char *)tp[i].text + INT3_INSN_SIZE, + len - INT3_INSN_SIZE); + do_sync++; } } - if (patched_all_but_first) { + if (do_sync) { /* * According to Intel, this core syncing is very likely * not necessary and we'd be safe even without it. But * better safe than sorry (plus there's not only Intel). */ - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); } /* * Third step: replace the first byte (int3) by the first byte of * replacing opcode. */ - for (i = 0; i < nr_entries; i++) - text_poke(tp[i].addr, tp[i].opcode, sizeof(int3)); + for (do_sync = 0, i = 0; i < nr_entries; i++) { + if (tp[i].text[0] == INT3_INSN_OPCODE) + continue; + + text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE); + do_sync++; + } + + if (do_sync) + text_poke_sync(); - on_each_cpu(do_sync_core, NULL, 1); /* - * sync_core() implies an smp_mb() and orders this store against - * the writing of the new instruction. + * Remove and synchronize_rcu(), except we have a very primitive + * refcount based completion. */ - bp_patching.vec = NULL; - bp_patching.nr_entries = 0; + WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */ + if (!atomic_dec_and_test(&desc.refs)) + atomic_cond_read_acquire(&desc.refs, !VAL); +} + +void text_poke_loc_init(struct text_poke_loc *tp, void *addr, + const void *opcode, size_t len, const void *emulate) +{ + struct insn insn; + + memcpy((void *)tp->text, opcode, len); + if (!emulate) + emulate = opcode; + + kernel_insn_init(&insn, emulate, MAX_INSN_SIZE); + insn_get_length(&insn); + + BUG_ON(!insn_complete(&insn)); + BUG_ON(len != insn.length); + + tp->rel_addr = addr - (void *)_stext; + tp->opcode = insn.opcode.bytes[0]; + + switch (tp->opcode) { + case INT3_INSN_OPCODE: + break; + + case CALL_INSN_OPCODE: + case JMP32_INSN_OPCODE: + case JMP8_INSN_OPCODE: + tp->rel32 = insn.immediate.value; + break; + + default: /* assume NOP */ + switch (len) { + case 2: /* NOP2 -- emulate as JMP8+0 */ + BUG_ON(memcmp(emulate, ideal_nops[len], len)); + tp->opcode = JMP8_INSN_OPCODE; + tp->rel32 = 0; + break; + + case 5: /* NOP5 -- emulate as JMP32+0 */ + BUG_ON(memcmp(emulate, ideal_nops[NOP_ATOMIC5], len)); + tp->opcode = JMP32_INSN_OPCODE; + tp->rel32 = 0; + break; + + default: /* unknown instruction */ + BUG(); + } + break; + } +} + +/* + * We hard rely on the tp_vec being ordered; ensure this is so by flushing + * early if needed. + */ +static bool tp_order_fail(void *addr) +{ + struct text_poke_loc *tp; + + if (!tp_vec_nr) + return false; + + if (!addr) /* force */ + return true; + + tp = &tp_vec[tp_vec_nr - 1]; + if ((unsigned long)text_poke_addr(tp) > (unsigned long)addr) + return true; + + return false; +} + +static void text_poke_flush(void *addr) +{ + if (tp_vec_nr == TP_VEC_MAX || tp_order_fail(addr)) { + text_poke_bp_batch(tp_vec, tp_vec_nr); + tp_vec_nr = 0; + } +} + +void text_poke_finish(void) +{ + text_poke_flush(NULL); +} + +void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate) +{ + struct text_poke_loc *tp; + + if (unlikely(system_state == SYSTEM_BOOTING)) { + text_poke_early(addr, opcode, len); + return; + } + + text_poke_flush(addr); + + tp = &tp_vec[tp_vec_nr++]; + text_poke_loc_init(tp, addr, opcode, len, emulate); } /** @@ -1098,20 +1276,15 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) * dynamically allocated memory. This function should be used when it is * not possible to allocate memory. */ -void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) +void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate) { - struct text_poke_loc tp = { - .detour = handler, - .addr = addr, - .len = len, - }; + struct text_poke_loc tp; - if (len > POKE_MAX_OPCODE_SIZE) { - WARN_ONCE(1, "len is larger than %d\n", POKE_MAX_OPCODE_SIZE); + if (unlikely(system_state == SYSTEM_BOOTING)) { + text_poke_early(addr, opcode, len); return; } - memcpy((void *)tp.opcode, opcode, len); - + text_poke_loc_init(&tp, addr, opcode, len, emulate); text_poke_bp_batch(&tp, 1); } diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index a585ea6f686a..4e5f50236048 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -185,13 +185,13 @@ static void iommu_full(struct device *dev, size_t size, int dir) static inline int need_iommu(struct device *dev, unsigned long addr, size_t size) { - return force_iommu || !dma_capable(dev, addr, size); + return force_iommu || !dma_capable(dev, addr, size, true); } static inline int nonforced_iommu(struct device *dev, unsigned long addr, size_t size) { - return !dma_capable(dev, addr, size); + return !dma_capable(dev, addr, size, true); } /* Map a single continuous physical area into the IOMMU. @@ -510,10 +510,9 @@ static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size) iommu_size -= round_up(a, PMD_PAGE_SIZE) - a; if (iommu_size < 64*1024*1024) { - pr_warning( - "PCI-DMA: Warning: Small IOMMU %luMB." + pr_warn("PCI-DMA: Warning: Small IOMMU %luMB." " Consider increasing the AGP aperture in BIOS\n", - iommu_size >> 20); + iommu_size >> 20); } return iommu_size; @@ -665,8 +664,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info) nommu: /* Should not happen anymore */ - pr_warning("PCI-DMA: More than 4GB of RAM and no IOMMU\n" - "falling back to iommu=soft.\n"); + pr_warn("PCI-DMA: More than 4GB of RAM and no IOMMU - falling back to iommu=soft.\n"); return -1; } @@ -677,7 +675,10 @@ static const struct dma_map_ops gart_dma_ops = { .unmap_page = gart_unmap_page, .alloc = gart_alloc_coherent, .free = gart_free_coherent, + .mmap = dma_common_mmap, + .get_sgtable = dma_common_get_sgtable, .dma_supported = dma_direct_supported, + .get_required_mask = dma_direct_get_required_mask, }; static void gart_iommu_shutdown(void) @@ -730,8 +731,8 @@ int __init gart_iommu_init(void) !gart_iommu_aperture || (no_agp && init_amd_gatt(&info) < 0)) { if (max_pfn > MAX_DMA32_PFN) { - pr_warning("More than 4GB of memory but GART IOMMU not available.\n"); - pr_warning("falling back to iommu=soft.\n"); + pr_warn("More than 4GB of memory but GART IOMMU not available.\n"); + pr_warn("falling back to iommu=soft.\n"); } return 0; } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index d63e63b7d1d9..69aed0ebbdfc 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -21,6 +21,8 @@ #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 +#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 +#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -50,6 +52,8 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -63,6 +67,8 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 5da106f84e84..fe698f96617c 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -95,7 +95,7 @@ static inline void apbt_set_mapping(void) printk(KERN_WARNING "No timer base from SFI, use default\n"); apbt_address = APBT_DEFAULT_BASE; } - apbt_virt_address = ioremap_nocache(apbt_address, APBT_MMAP_SIZE); + apbt_virt_address = ioremap(apbt_address, APBT_MMAP_SIZE); if (!apbt_virt_address) { pr_debug("Failed mapping APBT phy address at %lu\n",\ (unsigned long)apbt_address); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index f5291362da1a..5f973fed3c9f 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -65,10 +65,10 @@ unsigned int num_processors; unsigned disabled_cpus; /* Processor that is doing the boot up */ -unsigned int boot_cpu_physical_apicid = -1U; +unsigned int boot_cpu_physical_apicid __ro_after_init = -1U; EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid); -u8 boot_cpu_apic_version; +u8 boot_cpu_apic_version __ro_after_init; /* * The highest APIC ID seen during enumeration. @@ -85,13 +85,13 @@ physid_mask_t phys_cpu_present_map; * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to * avoid undefined behaviour caused by sending INIT from AP to BSP. */ -static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID; +static unsigned int disabled_cpu_apicid __ro_after_init = BAD_APICID; /* * This variable controls which CPUs receive external NMIs. By default, * external NMIs are delivered only to the BSP. */ -static int apic_extnmi = APIC_EXTNMI_BSP; +static int apic_extnmi __ro_after_init = APIC_EXTNMI_BSP; /* * Map cpu index to physical APIC ID @@ -114,7 +114,7 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid); DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID); /* Local APIC was disabled by the BIOS and enabled by the kernel */ -static int enabled_via_apicbase; +static int enabled_via_apicbase __ro_after_init; /* * Handle interrupt mode configuration register (IMCR). @@ -172,23 +172,23 @@ static __init int setup_apicpmtimer(char *s) __setup("apicpmtimer", setup_apicpmtimer); #endif -unsigned long mp_lapic_addr; -int disable_apic; +unsigned long mp_lapic_addr __ro_after_init; +int disable_apic __ro_after_init; /* Disable local APIC timer from the kernel commandline or via dmi quirk */ static int disable_apic_timer __initdata; /* Local APIC timer works in C2 */ -int local_apic_timer_c2_ok; +int local_apic_timer_c2_ok __ro_after_init; EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); /* * Debug level, exported for io_apic.c */ -int apic_verbosity; +int apic_verbosity __ro_after_init; -int pic_mode; +int pic_mode __ro_after_init; /* Have we found an MP table */ -int smp_found_config; +int smp_found_config __ro_after_init; static struct resource lapic_resource = { .name = "Local APIC", @@ -199,7 +199,7 @@ unsigned int lapic_timer_period = 0; static void apic_pm_activate(void); -static unsigned long apic_phys; +static unsigned long apic_phys __ro_after_init; /* * Get the LAPIC version @@ -590,21 +590,21 @@ static u32 skx_deadline_rev(void) static const struct x86_cpu_id deadline_match[] = { DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), - DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_D, bdx_deadline_rev), DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_GT3E, 0x17), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL, 0x22), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_L, 0x20), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_G, 0x17), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_CORE, 0x25), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_GT3E, 0x17), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL, 0x25), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_G, 0x17), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_MOBILE, 0xb2), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_DESKTOP, 0xb2), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_L, 0xb2), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE, 0xb2), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_MOBILE, 0x52), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_DESKTOP, 0x52), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_L, 0x52), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE, 0x52), {}, }; @@ -722,7 +722,7 @@ static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2; static __initdata unsigned long lapic_cal_j1, lapic_cal_j2; /* - * Temporary interrupt handler. + * Temporary interrupt handler and polled calibration function. */ static void __init lapic_cal_handler(struct clock_event_device *dev) { @@ -780,8 +780,8 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) res = (((u64)deltapm) * mult) >> 22; do_div(res, 1000000); - pr_warning("APIC calibration not consistent " - "with PM-Timer: %ldms instead of 100ms\n",(long)res); + pr_warn("APIC calibration not consistent " + "with PM-Timer: %ldms instead of 100ms\n", (long)res); /* Correct the lapic counter value */ res = (((u64)(*delta)) * pm_100ms); @@ -830,8 +830,21 @@ bool __init apic_needs_pit(void) if (!tsc_khz || !cpu_khz) return true; - /* Is there an APIC at all? */ - if (!boot_cpu_has(X86_FEATURE_APIC)) + /* Is there an APIC at all or is it disabled? */ + if (!boot_cpu_has(X86_FEATURE_APIC) || disable_apic) + return true; + + /* + * If interrupt delivery mode is legacy PIC or virtual wire without + * configuration, the local APIC timer wont be set up. Make sure + * that the PIT is initialized. + */ + if (apic_intr_mode == APIC_PIC || + apic_intr_mode == APIC_VIRTUAL_WIRE_NO_CONFIG) + return true; + + /* Virt guests may lack ARAT, but still have DEADLINE */ + if (!boot_cpu_has(X86_FEATURE_ARAT)) return true; /* Deadline timer is based on TSC so no further PIT action required */ @@ -851,7 +864,8 @@ bool __init apic_needs_pit(void) static int __init calibrate_APIC_clock(void) { struct clock_event_device *levt = this_cpu_ptr(&lapic_events); - void (*real_handler)(struct clock_event_device *dev); + u64 tsc_perj = 0, tsc_start = 0; + unsigned long jif_start; unsigned long deltaj; long delta, deltatsc; int pm_referenced = 0; @@ -878,28 +892,64 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" "calibrating APIC timer ...\n"); + /* + * There are platforms w/o global clockevent devices. Instead of + * making the calibration conditional on that, use a polling based + * approach everywhere. + */ local_irq_disable(); - /* Replace the global interrupt handler */ - real_handler = global_clock_event->event_handler; - global_clock_event->event_handler = lapic_cal_handler; - /* * Setup the APIC counter to maximum. There is no way the lapic * can underflow in the 100ms detection time frame */ __setup_APIC_LVTT(0xffffffff, 0, 0); - /* Let the interrupts run */ + /* + * Methods to terminate the calibration loop: + * 1) Global clockevent if available (jiffies) + * 2) TSC if available and frequency is known + */ + jif_start = READ_ONCE(jiffies); + + if (tsc_khz) { + tsc_start = rdtsc(); + tsc_perj = div_u64((u64)tsc_khz * 1000, HZ); + } + + /* + * Enable interrupts so the tick can fire, if a global + * clockevent device is available + */ local_irq_enable(); - while (lapic_cal_loops <= LAPIC_CAL_LOOPS) - cpu_relax(); + while (lapic_cal_loops <= LAPIC_CAL_LOOPS) { + /* Wait for a tick to elapse */ + while (1) { + if (tsc_khz) { + u64 tsc_now = rdtsc(); + if ((tsc_now - tsc_start) >= tsc_perj) { + tsc_start += tsc_perj; + break; + } + } else { + unsigned long jif_now = READ_ONCE(jiffies); - local_irq_disable(); + if (time_after(jif_now, jif_start)) { + jif_start = jif_now; + break; + } + } + cpu_relax(); + } - /* Restore the real event handler */ - global_clock_event->event_handler = real_handler; + /* Invoke the calibration routine */ + local_irq_disable(); + lapic_cal_handler(NULL); + local_irq_enable(); + } + + local_irq_disable(); /* Build delta t1-t2 as apic timer counts down */ delta = lapic_cal_t1 - lapic_cal_t2; @@ -936,17 +986,18 @@ static int __init calibrate_APIC_clock(void) */ if (lapic_timer_period < (1000000 / HZ)) { local_irq_enable(); - pr_warning("APIC frequency too slow, disabling apic timer\n"); + pr_warn("APIC frequency too slow, disabling apic timer\n"); return -1; } levt->features &= ~CLOCK_EVT_FEAT_DUMMY; /* - * PM timer calibration failed or not turned on - * so lets try APIC timer based calibration + * PM timer calibration failed or not turned on so lets try APIC + * timer based calibration, if a global clockevent device is + * available. */ - if (!pm_referenced) { + if (!pm_referenced && global_clock_event) { apic_printk(APIC_VERBOSE, "... verify APIC timer\n"); /* @@ -979,7 +1030,7 @@ static int __init calibrate_APIC_clock(void) local_irq_enable(); if (levt->features & CLOCK_EVT_FEAT_DUMMY) { - pr_warning("APIC timer disabled due to verification failure\n"); + pr_warn("APIC timer disabled due to verification failure\n"); return -1; } @@ -1053,8 +1104,8 @@ static void local_apic_timer_interrupt(void) * spurious. */ if (!evt->event_handler) { - pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", - smp_processor_id()); + pr_warn("Spurious LAPIC timer interrupt on cpu %d\n", + smp_processor_id()); /* Switch it off */ lapic_timer_shutdown(evt); return; @@ -1182,25 +1233,38 @@ void clear_local_APIC(void) } /** - * disable_local_APIC - clear and disable the local APIC + * apic_soft_disable - Clears and software disables the local APIC on hotplug + * + * Contrary to disable_local_APIC() this does not touch the enable bit in + * MSR_IA32_APICBASE. Clearing that bit on systems based on the 3 wire APIC + * bus would require a hardware reset as the APIC would lose track of bus + * arbitration. On systems with FSB delivery APICBASE could be disabled, + * but it has to be guaranteed that no interrupt is sent to the APIC while + * in that state and it's not clear from the SDM whether it still responds + * to INIT/SIPI messages. Stay on the safe side and use software disable. */ -void disable_local_APIC(void) +void apic_soft_disable(void) { - unsigned int value; - - /* APIC hasn't been mapped yet */ - if (!x2apic_mode && !apic_phys) - return; + u32 value; clear_local_APIC(); - /* - * Disable APIC (implies clearing of registers - * for 82489DX!). - */ + /* Soft disable APIC (implies clearing of registers for 82489DX!). */ value = apic_read(APIC_SPIV); value &= ~APIC_SPIV_APIC_ENABLED; apic_write(APIC_SPIV, value); +} + +/** + * disable_local_APIC - clear and disable the local APIC + */ +void disable_local_APIC(void) +{ + /* APIC hasn't been mapped yet */ + if (!x2apic_mode && !apic_phys) + return; + + apic_soft_disable(); #ifdef CONFIG_X86_32 /* @@ -1265,9 +1329,9 @@ void __init sync_Arb_IDs(void) APIC_INT_LEVELTRIG | APIC_DM_INIT); } -enum apic_intr_mode_id apic_intr_mode; +enum apic_intr_mode_id apic_intr_mode __ro_after_init; -static int __init apic_intr_mode_select(void) +static int __init __apic_intr_mode_select(void) { /* Check kernel option */ if (disable_apic) { @@ -1329,6 +1393,12 @@ static int __init apic_intr_mode_select(void) return APIC_SYMMETRIC_IO; } +/* Select the interrupt delivery mode for the BSP */ +void __init apic_intr_mode_select(void) +{ + apic_intr_mode = __apic_intr_mode_select(); +} + /* * An initial setup of the virtual wire mode. */ @@ -1385,8 +1455,6 @@ void __init apic_intr_mode_init(void) { bool upmode = IS_ENABLED(CONFIG_UP_LATE_INIT); - apic_intr_mode = apic_intr_mode_select(); - switch (apic_intr_mode) { case APIC_PIC: pr_info("APIC: Keep in PIC mode(8259)\n"); @@ -1453,54 +1521,72 @@ static void lapic_setup_esr(void) oldvalue, value); } -static void apic_pending_intr_clear(void) +#define APIC_IR_REGS APIC_ISR_NR +#define APIC_IR_BITS (APIC_IR_REGS * 32) +#define APIC_IR_MAPSIZE (APIC_IR_BITS / BITS_PER_LONG) + +union apic_ir { + unsigned long map[APIC_IR_MAPSIZE]; + u32 regs[APIC_IR_REGS]; +}; + +static bool apic_check_and_ack(union apic_ir *irr, union apic_ir *isr) { - long long max_loops = cpu_khz ? cpu_khz : 1000000; - unsigned long long tsc = 0, ntsc; - unsigned int queued; - unsigned long value; - int i, j, acked = 0; + int i, bit; + + /* Read the IRRs */ + for (i = 0; i < APIC_IR_REGS; i++) + irr->regs[i] = apic_read(APIC_IRR + i * 0x10); + + /* Read the ISRs */ + for (i = 0; i < APIC_IR_REGS; i++) + isr->regs[i] = apic_read(APIC_ISR + i * 0x10); - if (boot_cpu_has(X86_FEATURE_TSC)) - tsc = rdtsc(); /* - * After a crash, we no longer service the interrupts and a pending - * interrupt from previous kernel might still have ISR bit set. - * - * Most probably by now CPU has serviced that pending interrupt and - * it might not have done the ack_APIC_irq() because it thought, - * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it - * does not clear the ISR bit and cpu thinks it has already serivced - * the interrupt. Hence a vector might get locked. It was noticed - * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. + * If the ISR map is not empty. ACK the APIC and run another round + * to verify whether a pending IRR has been unblocked and turned + * into a ISR. */ - do { - queued = 0; - for (i = APIC_ISR_NR - 1; i >= 0; i--) - queued |= apic_read(APIC_IRR + i*0x10); - - for (i = APIC_ISR_NR - 1; i >= 0; i--) { - value = apic_read(APIC_ISR + i*0x10); - for_each_set_bit(j, &value, 32) { - ack_APIC_irq(); - acked++; - } - } - if (acked > 256) { - pr_err("LAPIC pending interrupts after %d EOI\n", acked); - break; - } - if (queued) { - if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { - ntsc = rdtsc(); - max_loops = (long long)cpu_khz << 10; - max_loops -= ntsc - tsc; - } else { - max_loops--; - } - } - } while (queued && max_loops > 0); - WARN_ON(max_loops <= 0); + if (!bitmap_empty(isr->map, APIC_IR_BITS)) { + /* + * There can be multiple ISR bits set when a high priority + * interrupt preempted a lower priority one. Issue an ACK + * per set bit. + */ + for_each_set_bit(bit, isr->map, APIC_IR_BITS) + ack_APIC_irq(); + return true; + } + + return !bitmap_empty(irr->map, APIC_IR_BITS); +} + +/* + * After a crash, we no longer service the interrupts and a pending + * interrupt from previous kernel might still have ISR bit set. + * + * Most probably by now the CPU has serviced that pending interrupt and it + * might not have done the ack_APIC_irq() because it thought, interrupt + * came from i8259 as ExtInt. LAPIC did not get EOI so it does not clear + * the ISR bit and cpu thinks it has already serivced the interrupt. Hence + * a vector might get locked. It was noticed for timer irq (vector + * 0x31). Issue an extra EOI to clear ISR. + * + * If there are pending IRR bits they turn into ISR bits after a higher + * priority ISR bit has been acked. + */ +static void apic_pending_intr_clear(void) +{ + union apic_ir irr, isr; + unsigned int i; + + /* 512 loops are way oversized and give the APIC a chance to obey. */ + for (i = 0; i < 512; i++) { + if (!apic_check_and_ack(&irr, &isr)) + return; + } + /* Dump the IRR/ISR content if that failed */ + pr_warn("APIC: Stale IRR: %256pb ISR: %256pb\n", irr.map, isr.map); } /** @@ -1513,16 +1599,20 @@ static void setup_local_APIC(void) { int cpu = smp_processor_id(); unsigned int value; -#ifdef CONFIG_X86_32 - int logical_apicid, ldr_apicid; -#endif - if (disable_apic) { disable_ioapic_support(); return; } + /* + * If this comes from kexec/kcrash the APIC might be enabled in + * SPIV. Soft disable it before doing further initialization. + */ + value = apic_read(APIC_SPIV); + value &= ~APIC_SPIV_APIC_ENABLED; + apic_write(APIC_SPIV, value); + #ifdef CONFIG_X86_32 /* Pound the ESR really hard over the head with a big hammer - mbligh */ if (lapic_is_integrated() && apic->disable_esr) { @@ -1532,8 +1622,6 @@ static void setup_local_APIC(void) apic_write(APIC_ESR, 0); } #endif - perf_events_lapic_init(); - /* * Double-check whether this APIC is really registered. * This is meaningless in clustered apic mode, so we skip it. @@ -1548,26 +1636,35 @@ static void setup_local_APIC(void) apic->init_apic_ldr(); #ifdef CONFIG_X86_32 - /* - * APIC LDR is initialized. If logical_apicid mapping was - * initialized during get_smp_config(), make sure it matches the - * actual value. - */ - logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); - WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid); - /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + if (apic->dest_logical) { + int logical_apicid, ldr_apicid; + + /* + * APIC LDR is initialized. If logical_apicid mapping was + * initialized during get_smp_config(), make sure it matches + * the actual value. + */ + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + if (logical_apicid != BAD_APICID) + WARN_ON(logical_apicid != ldr_apicid); + /* Always use the value from LDR. */ + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + } #endif /* - * Set Task Priority to 'accept all'. We never change this - * later on. + * Set Task Priority to 'accept all except vectors 0-31'. An APIC + * vector in the 16-31 range could be delivered if TPR == 0, but we + * would think it's an exception and terrible things will happen. We + * never change this later on. */ value = apic_read(APIC_TASKPRI); value &= ~APIC_TPRI_MASK; + value |= 0x10; apic_write(APIC_TASKPRI, value); + /* Clear eventually stale ISR/IRR bits */ apic_pending_intr_clear(); /* @@ -1614,6 +1711,8 @@ static void setup_local_APIC(void) value |= SPURIOUS_APIC_VECTOR; apic_write(APIC_SPIV, value); + perf_events_lapic_init(); + /* * Set up LVT0, LVT1: * @@ -1725,11 +1824,11 @@ static int __init setup_nox2apic(char *str) int apicid = native_apic_msr_read(APIC_ID); if (apicid >= 255) { - pr_warning("Apicid: %08x, cannot enforce nox2apic\n", - apicid); + pr_warn("Apicid: %08x, cannot enforce nox2apic\n", + apicid); return 0; } - pr_warning("x2apic already enabled.\n"); + pr_warn("x2apic already enabled.\n"); __x2apic_disable(); } setup_clear_cpu_cap(X86_FEATURE_X2APIC); @@ -1897,7 +1996,7 @@ static int __init apic_verify(void) */ features = cpuid_edx(1); if (!(features & (1 << X86_FEATURE_APIC))) { - pr_warning("Could not enable APIC!\n"); + pr_warn("Could not enable APIC!\n"); return -1; } set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC); @@ -2251,7 +2350,7 @@ static int cpuid_to_apicid[] = { #ifdef CONFIG_SMP /** * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread - * @id: APIC ID to check + * @apicid: APIC ID to check */ bool apic_id_is_primary_thread(unsigned int apicid) { @@ -2324,9 +2423,8 @@ int generic_processor_info(int apicid, int version) disabled_cpu_apicid == apicid) { int thiscpu = num_processors + disabled_cpus; - pr_warning("APIC: Disabling requested cpu." - " Processor %d/0x%x ignored.\n", - thiscpu, apicid); + pr_warn("APIC: Disabling requested cpu." + " Processor %d/0x%x ignored.\n", thiscpu, apicid); disabled_cpus++; return -ENODEV; @@ -2340,8 +2438,7 @@ int generic_processor_info(int apicid, int version) apicid != boot_cpu_physical_apicid) { int thiscpu = max + disabled_cpus - 1; - pr_warning( - "APIC: NR_CPUS/possible_cpus limit of %i almost" + pr_warn("APIC: NR_CPUS/possible_cpus limit of %i almost" " reached. Keeping one slot for boot cpu." " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); @@ -2352,9 +2449,8 @@ int generic_processor_info(int apicid, int version) if (num_processors >= nr_cpu_ids) { int thiscpu = max + disabled_cpus; - pr_warning("APIC: NR_CPUS/possible_cpus limit of %i " - "reached. Processor %d/0x%x ignored.\n", - max, thiscpu, apicid); + pr_warn("APIC: NR_CPUS/possible_cpus limit of %i reached. " + "Processor %d/0x%x ignored.\n", max, thiscpu, apicid); disabled_cpus++; return -EINVAL; @@ -2384,13 +2480,13 @@ int generic_processor_info(int apicid, int version) * Validate version */ if (version == 0x0) { - pr_warning("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n", - cpu, apicid); + pr_warn("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n", + cpu, apicid); version = 0x10; } if (version != boot_cpu_apic_version) { - pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n", + pr_warn("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n", boot_cpu_apic_version, cpu, version); } @@ -2543,6 +2639,13 @@ static int lapic_suspend(void) #endif local_irq_save(flags); + + /* + * Mask IOAPIC before disabling the local APIC to prevent stale IRR + * entries on some implementations. + */ + mask_ioapic_entries(); + disable_local_APIC(); irq_remapping_disable(); @@ -2759,7 +2862,7 @@ static int __init apic_set_verbosity(char *arg) apic_verbosity = APIC_VERBOSE; #ifdef CONFIG_X86_64 else { - pr_warning("APIC Verbosity level %s not recognised" + pr_warn("APIC Verbosity level %s not recognised" " use apic=verbose or apic=debug\n", arg); return -EINVAL; } diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index bbdca603f94a..7862b152a052 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -8,21 +8,14 @@ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and * James Cleverdon. */ -#include <linux/acpi.h> -#include <linux/errno.h> -#include <linux/threads.h> #include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/ctype.h> -#include <linux/hardirq.h> #include <linux/export.h> +#include <linux/acpi.h> -#include <asm/smp.h> -#include <asm/ipi.h> -#include <asm/apic.h> -#include <asm/apic_flat_64.h> #include <asm/jailhouse_para.h> +#include <asm/apic.h> + +#include "local.h" static struct apic apic_physflat; static struct apic apic_flat; @@ -83,35 +76,6 @@ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) _flat_send_IPI_mask(mask, vector); } -static void flat_send_IPI_allbutself(int vector) -{ - int cpu = smp_processor_id(); - - if (IS_ENABLED(CONFIG_HOTPLUG_CPU) || vector == NMI_VECTOR) { - if (!cpumask_equal(cpu_online_mask, cpumask_of(cpu))) { - unsigned long mask = cpumask_bits(cpu_online_mask)[0]; - - if (cpu < BITS_PER_LONG) - __clear_bit(cpu, &mask); - - _flat_send_IPI_mask(mask, vector); - } - } else if (num_online_cpus() > 1) { - __default_send_IPI_shortcut(APIC_DEST_ALLBUT, - vector, apic->dest_logical); - } -} - -static void flat_send_IPI_all(int vector) -{ - if (vector == NMI_VECTOR) { - flat_send_IPI_mask(cpu_online_mask, vector); - } else { - __default_send_IPI_shortcut(APIC_DEST_ALLINC, - vector, apic->dest_logical); - } -} - static unsigned int flat_get_apic_id(unsigned long x) { return (x >> 24) & 0xFF; @@ -173,9 +137,9 @@ static struct apic apic_flat __ro_after_init = { .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, - .send_IPI_allbutself = flat_send_IPI_allbutself, - .send_IPI_all = flat_send_IPI_all, - .send_IPI_self = apic_send_IPI_self, + .send_IPI_allbutself = default_send_IPI_allbutself, + .send_IPI_all = default_send_IPI_all, + .send_IPI_self = default_send_IPI_self, .inquire_remote_apic = default_inquire_remote_apic, @@ -225,16 +189,6 @@ static void physflat_init_apic_ldr(void) */ } -static void physflat_send_IPI_allbutself(int vector) -{ - default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); -} - -static void physflat_send_IPI_all(int vector) -{ - default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); -} - static int physflat_probe(void) { if (apic == &apic_physflat || num_possible_cpus() > 8 || @@ -276,9 +230,9 @@ static struct apic apic_physflat __ro_after_init = { .send_IPI = default_send_IPI_single_phys, .send_IPI_mask = default_send_IPI_mask_sequence_phys, .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_phys, - .send_IPI_allbutself = physflat_send_IPI_allbutself, - .send_IPI_all = physflat_send_IPI_all, - .send_IPI_self = apic_send_IPI_self, + .send_IPI_allbutself = default_send_IPI_allbutself, + .send_IPI_all = default_send_IPI_all, + .send_IPI_self = default_send_IPI_self, .inquire_remote_apic = default_inquire_remote_apic, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 5078b5ce63a7..98c9bb75d185 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -9,25 +9,9 @@ * to not uglify the caller's code and allow to call (some) apic routines * like self-ipi, etc... */ - -#include <linux/threads.h> #include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/ctype.h> -#include <linux/errno.h> -#include <asm/fixmap.h> -#include <asm/mpspec.h> -#include <asm/apicdef.h> -#include <asm/apic.h> -#include <asm/setup.h> -#include <linux/smp.h> -#include <asm/ipi.h> - -#include <linux/interrupt.h> -#include <asm/acpi.h> -#include <asm/e820/api.h> +#include <asm/apic.h> static void noop_init_apic_ldr(void) { } static void noop_send_IPI(int cpu, int vector) { } diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index a5464b8b6c46..cdf45b4700f2 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -10,15 +10,15 @@ * Send feedback to <support@numascale.com> * */ - +#include <linux/types.h> #include <linux/init.h> #include <asm/numachip/numachip.h> #include <asm/numachip/numachip_csr.h> -#include <asm/ipi.h> -#include <asm/apic_flat_64.h> + #include <asm/pgtable.h> -#include <asm/pci_x86.h> + +#include "local.h" u8 numachip_system __read_mostly; static const struct apic apic_numachip1; diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index afee386ff711..38b5b51d42f6 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -4,18 +4,13 @@ * * Drives the local APIC in "clustered mode". */ -#include <linux/threads.h> #include <linux/cpumask.h> -#include <linux/kernel.h> -#include <linux/init.h> #include <linux/dmi.h> #include <linux/smp.h> -#include <asm/apicdef.h> -#include <asm/fixmap.h> -#include <asm/mpspec.h> #include <asm/apic.h> -#include <asm/ipi.h> + +#include "local.h" static unsigned bigsmp_get_apic_id(unsigned long x) { @@ -38,32 +33,12 @@ static int bigsmp_early_logical_apicid(int cpu) return early_per_cpu(x86_cpu_to_apicid, cpu); } -static inline unsigned long calculate_ldr(int cpu) -{ - unsigned long val, id; - - val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; - id = per_cpu(x86_bios_cpu_apicid, cpu); - val |= SET_APIC_LOGICAL_ID(id); - - return val; -} - /* - * Set up the logical destination ID. - * - * Intel recommends to set DFR, LDR and TPR before enabling - * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel - * document number 292116). So here it goes... + * bigsmp enables physical destination mode + * and doesn't use LDR and DFR */ static void bigsmp_init_apic_ldr(void) { - unsigned long val; - int cpu = smp_processor_id(); - - apic_write(APIC_DFR, APIC_DFR_FLAT); - val = calculate_ldr(cpu); - apic_write(APIC_LDR, val); } static void bigsmp_setup_apic_routing(void) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c7bb6c69f21c..913c88617848 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1725,19 +1725,20 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data) return false; } -static inline bool ioapic_irqd_mask(struct irq_data *data) +static inline bool ioapic_prepare_move(struct irq_data *data) { - /* If we are moving the irq we need to mask it */ + /* If we are moving the IRQ we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data))) { - mask_ioapic_irq(data); + if (!irqd_irq_masked(data)) + mask_ioapic_irq(data); return true; } return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) +static inline void ioapic_finish_move(struct irq_data *data, bool moveit) { - if (unlikely(masked)) { + if (unlikely(moveit)) { /* Only migrate the irq if the ack has been received. * * On rare occasions the broadcast level triggered ack gets @@ -1766,15 +1767,17 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) */ if (!io_apic_level_ack_pending(data->chip_data)) irq_move_masked_irq(data); - unmask_ioapic_irq(data); + /* If the IRQ is masked in the core, leave it: */ + if (!irqd_irq_masked(data)) + unmask_ioapic_irq(data); } } #else -static inline bool ioapic_irqd_mask(struct irq_data *data) +static inline bool ioapic_prepare_move(struct irq_data *data) { return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) +static inline void ioapic_finish_move(struct irq_data *data, bool moveit) { } #endif @@ -1783,11 +1786,11 @@ static void ioapic_ack_level(struct irq_data *irq_data) { struct irq_cfg *cfg = irqd_cfg(irq_data); unsigned long v; - bool masked; + bool moveit; int i; irq_complete_move(cfg); - masked = ioapic_irqd_mask(irq_data); + moveit = ioapic_prepare_move(irq_data); /* * It appears there is an erratum which affects at least version 0x11 @@ -1842,7 +1845,7 @@ static void ioapic_ack_level(struct irq_data *irq_data) eoi_ioapic_pin(cfg->vector, irq_data->chip_data); } - ioapic_irqd_unmask(irq_data, masked); + ioapic_finish_move(irq_data, moveit); } static void ioapic_ir_ack_level(struct irq_data *irq_data) @@ -2438,7 +2441,13 @@ unsigned int arch_dynirq_lower_bound(unsigned int from) * dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use * gsi_top if ioapic_dynirq_base hasn't been initialized yet. */ - return ioapic_initialized ? ioapic_dynirq_base : gsi_top; + if (!ioapic_initialized) + return gsi_top; + /* + * For DT enabled machines ioapic_dynirq_base is irrelevant and not + * updated. So simply return @from if ioapic_dynirq_base == 0. + */ + return ioapic_dynirq_base ? : from; } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 82f9244fe61f..6ca0f91372fd 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -1,24 +1,113 @@ // SPDX-License-Identifier: GPL-2.0 + #include <linux/cpumask.h> -#include <linux/interrupt.h> - -#include <linux/mm.h> -#include <linux/delay.h> -#include <linux/spinlock.h> -#include <linux/kernel_stat.h> -#include <linux/mc146818rtc.h> -#include <linux/cache.h> -#include <linux/cpu.h> - -#include <asm/smp.h> -#include <asm/mtrr.h> -#include <asm/tlbflush.h> -#include <asm/mmu_context.h> -#include <asm/apic.h> -#include <asm/proto.h> -#include <asm/ipi.h> - -void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest) +#include <linux/smp.h> + +#include "local.h" + +DEFINE_STATIC_KEY_FALSE(apic_use_ipi_shorthand); + +#ifdef CONFIG_SMP +static int apic_ipi_shorthand_off __ro_after_init; + +static __init int apic_ipi_shorthand(char *str) +{ + get_option(&str, &apic_ipi_shorthand_off); + return 1; +} +__setup("no_ipi_broadcast=", apic_ipi_shorthand); + +static int __init print_ipi_mode(void) +{ + pr_info("IPI shorthand broadcast: %s\n", + apic_ipi_shorthand_off ? "disabled" : "enabled"); + return 0; +} +late_initcall(print_ipi_mode); + +void apic_smt_update(void) +{ + /* + * Do not switch to broadcast mode if: + * - Disabled on the command line + * - Only a single CPU is online + * - Not all present CPUs have been at least booted once + * + * The latter is important as the local APIC might be in some + * random state and a broadcast might cause havoc. That's + * especially true for NMI broadcasting. + */ + if (apic_ipi_shorthand_off || num_online_cpus() == 1 || + !cpumask_equal(cpu_present_mask, &cpus_booted_once_mask)) { + static_branch_disable(&apic_use_ipi_shorthand); + } else { + static_branch_enable(&apic_use_ipi_shorthand); + } +} + +void apic_send_IPI_allbutself(unsigned int vector) +{ + if (num_online_cpus() < 2) + return; + + if (static_branch_likely(&apic_use_ipi_shorthand)) + apic->send_IPI_allbutself(vector); + else + apic->send_IPI_mask_allbutself(cpu_online_mask, vector); +} + +/* + * Send a 'reschedule' IPI to another CPU. It goes straight through and + * wastes no time serializing anything. Worst case is that we lose a + * reschedule ... + */ +void native_smp_send_reschedule(int cpu) +{ + if (unlikely(cpu_is_offline(cpu))) { + WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu); + return; + } + apic->send_IPI(cpu, RESCHEDULE_VECTOR); +} + +void native_send_call_func_single_ipi(int cpu) +{ + apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR); +} + +void native_send_call_func_ipi(const struct cpumask *mask) +{ + if (static_branch_likely(&apic_use_ipi_shorthand)) { + unsigned int cpu = smp_processor_id(); + + if (!cpumask_or_equal(mask, cpumask_of(cpu), cpu_online_mask)) + goto sendmask; + + if (cpumask_test_cpu(cpu, mask)) + apic->send_IPI_all(CALL_FUNCTION_VECTOR); + else if (num_online_cpus() > 1) + apic->send_IPI_allbutself(CALL_FUNCTION_VECTOR); + return; + } + +sendmask: + apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR); +} + +#endif /* CONFIG_SMP */ + +static inline int __prepare_ICR2(unsigned int mask) +{ + return SET_APIC_DEST_FIELD(mask); +} + +static inline void __xapic_wait_icr_idle(void) +{ + while (native_apic_mem_read(APIC_ICR) & APIC_ICR_BUSY) + cpu_relax(); +} + +void __default_send_IPI_shortcut(unsigned int shortcut, int vector) { /* * Subtle. In the case of the 'never do double writes' workaround @@ -32,12 +121,16 @@ void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int /* * Wait for idle. */ - __xapic_wait_icr_idle(); + if (unlikely(vector == NMI_VECTOR)) + safe_apic_wait_icr_idle(); + else + __xapic_wait_icr_idle(); /* - * No need to touch the target chip field + * No need to touch the target chip field. Also the destination + * mode is ignored when a shorthand is used. */ - cfg = __prepare_ICR(shortcut, vector, dest); + cfg = __prepare_ICR(shortcut, vector, 0); /* * Send the IPI. The write to APIC_ICR fires this off. @@ -133,6 +226,21 @@ void default_send_IPI_single(int cpu, int vector) apic->send_IPI_mask(cpumask_of(cpu), vector); } +void default_send_IPI_allbutself(int vector) +{ + __default_send_IPI_shortcut(APIC_DEST_ALLBUT, vector); +} + +void default_send_IPI_all(int vector) +{ + __default_send_IPI_shortcut(APIC_DEST_ALLINC, vector); +} + +void default_send_IPI_self(int vector) +{ + __default_send_IPI_shortcut(APIC_DEST_SELF, vector); +} + #ifdef CONFIG_X86_32 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, @@ -192,28 +300,6 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector) local_irq_restore(flags); } -void default_send_IPI_allbutself(int vector) -{ - /* - * if there are no other CPUs in the system then we get an APIC send - * error if we try to broadcast, thus avoid sending IPIs in this case. - */ - if (!(num_online_cpus() > 1)) - return; - - __default_local_send_IPI_allbutself(vector); -} - -void default_send_IPI_all(int vector) -{ - __default_local_send_IPI_all(vector); -} - -void default_send_IPI_self(int vector) -{ - __default_send_IPI_shortcut(APIC_DEST_SELF, vector, apic->dest_logical); -} - /* must come after the send_IPI functions above for inlining */ static int convert_apicid_to_cpu(int apic_id) { diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h new file mode 100644 index 000000000000..04797f05ce94 --- /dev/null +++ b/arch/x86/kernel/apic/local.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Historical copyright notices: + * + * Copyright 2004 James Cleverdon, IBM. + * (c) 1995 Alan Cox, Building #3 <alan@redhat.com> + * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com> + * (c) 2002,2003 Andi Kleen, SuSE Labs. + */ + +#include <linux/jump_label.h> + +#include <asm/apic.h> + +/* APIC flat 64 */ +void flat_init_apic_ldr(void); + +/* X2APIC */ +int x2apic_apic_id_valid(u32 apicid); +int x2apic_apic_id_registered(void); +void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest); +unsigned int x2apic_get_apic_id(unsigned long id); +u32 x2apic_set_apic_id(unsigned int id); +int x2apic_phys_pkg_id(int initial_apicid, int index_msb); +void x2apic_send_IPI_self(int vector); +void __x2apic_send_IPI_shorthand(int vector, u32 which); + +/* IPI */ + +DECLARE_STATIC_KEY_FALSE(apic_use_ipi_shorthand); + +static inline unsigned int __prepare_ICR(unsigned int shortcut, int vector, + unsigned int dest) +{ + unsigned int icr = shortcut | dest; + + switch (vector) { + default: + icr |= APIC_DM_FIXED | vector; + break; + case NMI_VECTOR: + icr |= APIC_DM_NMI; + break; + } + return icr; +} + +void __default_send_IPI_shortcut(unsigned int shortcut, int vector); + +/* + * This is used to send an IPI with no shorthand notation (the destination is + * specified in bits 56 to 63 of the ICR). + */ +void __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest); + +void default_send_IPI_single(int cpu, int vector); +void default_send_IPI_single_phys(int cpu, int vector); +void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector); +void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, int vector); +void default_send_IPI_allbutself(int vector); +void default_send_IPI_all(int vector); +void default_send_IPI_self(int vector); + +#ifdef CONFIG_X86_32 +void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector); +void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector); +void default_send_IPI_mask_logical(const struct cpumask *mask, int vector); +#endif diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 7f7533462474..159bd0cb8548 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -23,10 +23,8 @@ static struct irq_domain *msi_default_domain; -static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg) { - struct irq_cfg *cfg = irqd_cfg(data); - msg->address_hi = MSI_ADDR_BASE_HI; if (x2apic_enabled()) @@ -47,6 +45,127 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) MSI_DATA_VECTOR(cfg->vector); } +static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +{ + __irq_msi_compose_msg(irqd_cfg(data), msg); +} + +static void irq_msi_update_msg(struct irq_data *irqd, struct irq_cfg *cfg) +{ + struct msi_msg msg[2] = { [1] = { }, }; + + __irq_msi_compose_msg(cfg, msg); + irq_data_get_irq_chip(irqd)->irq_write_msi_msg(irqd, msg); +} + +static int +msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) +{ + struct irq_cfg old_cfg, *cfg = irqd_cfg(irqd); + struct irq_data *parent = irqd->parent_data; + unsigned int cpu; + int ret; + + /* Save the current configuration */ + cpu = cpumask_first(irq_data_get_effective_affinity_mask(irqd)); + old_cfg = *cfg; + + /* Allocate a new target vector */ + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE) + return ret; + + /* + * For non-maskable and non-remapped MSI interrupts the migration + * to a different destination CPU and a different vector has to be + * done careful to handle the possible stray interrupt which can be + * caused by the non-atomic update of the address/data pair. + * + * Direct update is possible when: + * - The MSI is maskable (remapped MSI does not use this code path)). + * The quirk bit is not set in this case. + * - The new vector is the same as the old vector + * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) + * - The new destination CPU is the same as the old destination CPU + */ + if (!irqd_msi_nomask_quirk(irqd) || + cfg->vector == old_cfg.vector || + old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || + cfg->dest_apicid == old_cfg.dest_apicid) { + irq_msi_update_msg(irqd, cfg); + return ret; + } + + /* + * Paranoia: Validate that the interrupt target is the local + * CPU. + */ + if (WARN_ON_ONCE(cpu != smp_processor_id())) { + irq_msi_update_msg(irqd, cfg); + return ret; + } + + /* + * Redirect the interrupt to the new vector on the current CPU + * first. This might cause a spurious interrupt on this vector if + * the device raises an interrupt right between this update and the + * update to the final destination CPU. + * + * If the vector is in use then the installed device handler will + * denote it as spurious which is no harm as this is a rare event + * and interrupt handlers have to cope with spurious interrupts + * anyway. If the vector is unused, then it is marked so it won't + * trigger the 'No irq handler for vector' warning in do_IRQ(). + * + * This requires to hold vector lock to prevent concurrent updates to + * the affected vector. + */ + lock_vector_lock(); + + /* + * Mark the new target vector on the local CPU if it is currently + * unused. Reuse the VECTOR_RETRIGGERED state which is also used in + * the CPU hotplug path for a similar purpose. This cannot be + * undone here as the current CPU has interrupts disabled and + * cannot handle the interrupt before the whole set_affinity() + * section is done. In the CPU unplug case, the current CPU is + * about to vanish and will not handle any interrupts anymore. The + * vector is cleaned up when the CPU comes online again. + */ + if (IS_ERR_OR_NULL(this_cpu_read(vector_irq[cfg->vector]))) + this_cpu_write(vector_irq[cfg->vector], VECTOR_RETRIGGERED); + + /* Redirect it to the new vector on the local CPU temporarily */ + old_cfg.vector = cfg->vector; + irq_msi_update_msg(irqd, &old_cfg); + + /* Now transition it to the target CPU */ + irq_msi_update_msg(irqd, cfg); + + /* + * All interrupts after this point are now targeted at the new + * vector/CPU. + * + * Drop vector lock before testing whether the temporary assignment + * to the local CPU was hit by an interrupt raised in the device, + * because the retrigger function acquires vector lock again. + */ + unlock_vector_lock(); + + /* + * Check whether the transition raced with a device interrupt and + * is pending in the local APICs IRR. It is safe to do this outside + * of vector lock as the irq_desc::lock of this interrupt is still + * held and interrupts are disabled: The check is not accessing the + * underlying vector store. It's just checking the local APIC's + * IRR. + */ + if (lapic_vector_set_in_irr(cfg->vector)) + irq_data_get_irq_chip(irqd)->irq_retrigger(irqd); + + return ret; +} + /* * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, * which implement the MSI or MSI-X Capability Structure. @@ -58,6 +177,7 @@ static struct irq_chip pci_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_set_affinity = msi_set_affinity, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -146,6 +266,8 @@ void __init arch_init_msi_domain(struct irq_domain *parent) } if (!msi_default_domain) pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); + else + msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; } #ifdef CONFIG_IRQ_REMAP diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index ee2d91e382f1..67b33d67002f 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -6,51 +6,14 @@ * * Generic x86 APIC driver probe layer. */ -#include <linux/threads.h> -#include <linux/cpumask.h> #include <linux/export.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/ctype.h> -#include <linux/init.h> #include <linux/errno.h> -#include <asm/fixmap.h> -#include <asm/mpspec.h> -#include <asm/apicdef.h> -#include <asm/apic.h> -#include <asm/setup.h> - #include <linux/smp.h> -#include <asm/ipi.h> -#include <linux/interrupt.h> +#include <asm/apic.h> #include <asm/acpi.h> -#include <asm/e820/api.h> -#ifdef CONFIG_HOTPLUG_CPU -#define DEFAULT_SEND_IPI (1) -#else -#define DEFAULT_SEND_IPI (0) -#endif - -int no_broadcast = DEFAULT_SEND_IPI; - -static __init int no_ipi_broadcast(char *str) -{ - get_option(&str, &no_broadcast); - pr_info("Using %s mode\n", - no_broadcast ? "No IPI Broadcast" : "IPI Broadcast"); - return 1; -} -__setup("no_ipi_broadcast=", no_ipi_broadcast); - -static int __init print_ipi_mode(void) -{ - pr_info("Using IPI %s mode\n", - no_broadcast ? "No-Shortcut" : "Shortcut"); - return 0; -} -late_initcall(print_ipi_mode); +#include "local.h" static int default_x86_32_early_logical_apicid(int cpu) { diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index e6560a02eb46..29f0e0984557 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -8,19 +8,9 @@ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and * James Cleverdon. */ -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/ctype.h> -#include <linux/hardirq.h> -#include <linux/dmar.h> - -#include <asm/smp.h> #include <asm/apic.h> -#include <asm/ipi.h> -#include <asm/setup.h> + +#include "local.h" /* * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode. @@ -46,13 +36,6 @@ void __init default_setup_apic_routing(void) x86_platform.apic_post_init(); } -/* Same for both flat and physical. */ - -void apic_send_IPI_self(int vector) -{ - __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); -} - int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { struct apic **drv; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index fdacb864c3dd..2c5676b0a6e7 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -398,6 +398,17 @@ static int activate_reserved(struct irq_data *irqd) if (!irqd_can_reserve(irqd)) apicd->can_reserve = false; } + + /* + * Check to ensure that the effective affinity mask is a subset + * the user supplied affinity mask, and warn the user if it is not + */ + if (!cpumask_subset(irq_data_get_effective_affinity_mask(irqd), + irq_data_get_affinity_mask(irqd))) { + pr_warn("irq %u: Affinity broken due to vector space exhaustion.\n", + irqd->irq); + } + return ret; } diff --git a/arch/x86/kernel/apic/x2apic.h b/arch/x86/kernel/apic/x2apic.h deleted file mode 100644 index a49b3604027f..000000000000 --- a/arch/x86/kernel/apic/x2apic.h +++ /dev/null @@ -1,9 +0,0 @@ -/* Common bits for X2APIC cluster/physical modes. */ - -int x2apic_apic_id_valid(u32 apicid); -int x2apic_apic_id_registered(void); -void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest); -unsigned int x2apic_get_apic_id(unsigned long id); -u32 x2apic_set_apic_id(unsigned int id); -int x2apic_phys_pkg_id(int initial_apicid, int index_msb); -void x2apic_send_IPI_self(int vector); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 609e499387a1..b0889c48a2ac 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -1,15 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/threads.h> + +#include <linux/cpuhotplug.h> #include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/ctype.h> -#include <linux/dmar.h> -#include <linux/irq.h> -#include <linux/cpu.h> +#include <linux/slab.h> +#include <linux/mm.h> + +#include <asm/apic.h> -#include <asm/smp.h> -#include "x2apic.h" +#include "local.h" struct cluster_mask { unsigned int clusterid; @@ -84,12 +82,12 @@ x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector) static void x2apic_send_IPI_allbutself(int vector) { - __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLBUT); + __x2apic_send_IPI_shorthand(vector, APIC_DEST_ALLBUT); } static void x2apic_send_IPI_all(int vector) { - __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC); + __x2apic_send_IPI_shorthand(vector, APIC_DEST_ALLINC); } static u32 x2apic_calc_apicid(unsigned int cpu) @@ -158,7 +156,8 @@ static int x2apic_dead_cpu(unsigned int dead_cpu) { struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu); - cpumask_clear_cpu(dead_cpu, &cmsk->mask); + if (cmsk) + cpumask_clear_cpu(dead_cpu, &cmsk->mask); free_cpumask_var(per_cpu(ipi_mask, dead_cpu)); return 0; } diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index b5cf9e7b3830..bc9693841353 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -1,14 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/threads.h> + #include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/ctype.h> -#include <linux/dmar.h> +#include <linux/acpi.h> -#include <asm/smp.h> -#include <asm/ipi.h> -#include "x2apic.h" +#include "local.h" int x2apic_phys; @@ -80,12 +75,12 @@ static void static void x2apic_send_IPI_allbutself(int vector) { - __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLBUT); + __x2apic_send_IPI_shorthand(vector, APIC_DEST_ALLBUT); } static void x2apic_send_IPI_all(int vector) { - __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC); + __x2apic_send_IPI_shorthand(vector, APIC_DEST_ALLINC); } static void init_x2apic_ldr(void) @@ -117,6 +112,14 @@ void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest) native_x2apic_icr_write(cfg, apicid); } +void __x2apic_send_IPI_shorthand(int vector, u32 which) +{ + unsigned long cfg = __prepare_ICR(which, vector, 0); + + x2apic_wrmsr_fence(); + native_x2apic_icr_write(cfg, 0); +} + unsigned int x2apic_get_apic_id(unsigned long id) { return id; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1e225528f0d7..ad53b2abc859 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -7,50 +7,37 @@ * * Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved. */ +#include <linux/crash_dump.h> +#include <linux/cpuhotplug.h> #include <linux/cpumask.h> -#include <linux/hardirq.h> #include <linux/proc_fs.h> -#include <linux/threads.h> -#include <linux/kernel.h> +#include <linux/memory.h> #include <linux/export.h> -#include <linux/string.h> -#include <linux/ctype.h> -#include <linux/sched.h> -#include <linux/timer.h> -#include <linux/slab.h> -#include <linux/cpu.h> -#include <linux/init.h> -#include <linux/io.h> #include <linux/pci.h> -#include <linux/kdebug.h> -#include <linux/delay.h> -#include <linux/crash_dump.h> -#include <linux/reboot.h> -#include <linux/memory.h> -#include <linux/numa.h> +#include <linux/acpi.h> +#include <linux/efi.h> +#include <asm/e820/api.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> -#include <asm/current.h> -#include <asm/pgtable.h> #include <asm/uv/bios.h> #include <asm/uv/uv.h> #include <asm/apic.h> -#include <asm/e820/api.h> -#include <asm/ipi.h> -#include <asm/smp.h> -#include <asm/x86_init.h> -#include <asm/nmi.h> -DEFINE_PER_CPU(int, x2apic_extra_bits); +static DEFINE_PER_CPU(int, x2apic_extra_bits); static enum uv_system_type uv_system_type; -static bool uv_hubless_system; +static int uv_hubbed_system; +static int uv_hubless_system; static u64 gru_start_paddr, gru_end_paddr; static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr; static u64 gru_dist_lmask, gru_dist_umask; static union uvh_apicid uvh_apicid; +/* Unpack OEM/TABLE ID's to be NULL terminated strings */ +static u8 oem_id[ACPI_OEM_ID_SIZE + 1]; +static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; + /* Information derived from CPUID: */ static struct { unsigned int apicid_shift; @@ -268,17 +255,35 @@ static void __init uv_set_apicid_hibit(void) } } -static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static void __init uv_stringify(int len, char *to, char *from) +{ + /* Relies on 'to' being NULL chars so result will be NULL terminated */ + strncpy(to, from, len-1); +} + +static int __init uv_acpi_madt_oem_check(char *_oem_id, char *_oem_table_id) { int pnodeid; int uv_apic; + uv_stringify(sizeof(oem_id), oem_id, _oem_id); + uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id); + if (strncmp(oem_id, "SGI", 3) != 0) { - if (strncmp(oem_id, "NSGI", 4) == 0) { - uv_hubless_system = true; - pr_info("UV: OEM IDs %s/%s, HUBLESS\n", - oem_id, oem_table_id); - } + if (strncmp(oem_id, "NSGI", 4) != 0) + return 0; + + /* UV4 Hubless, CH, (0x11:UV4+Any) */ + if (strncmp(oem_id, "NSGI4", 5) == 0) + uv_hubless_system = 0x11; + + /* UV3 Hubless, UV300/MC990X w/o hub (0x9:UV3+Any) */ + else + uv_hubless_system = 0x9; + + pr_info("UV: OEM IDs %s/%s, HUBLESS(0x%x)\n", + oem_id, oem_table_id, uv_hubless_system); + return 0; } @@ -306,6 +311,24 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) if (uv_hub_info->hub_revision == 0) goto badbios; + switch (uv_hub_info->hub_revision) { + case UV4_HUB_REVISION_BASE: + uv_hubbed_system = 0x11; + break; + + case UV3_HUB_REVISION_BASE: + uv_hubbed_system = 0x9; + break; + + case UV2_HUB_REVISION_BASE: + uv_hubbed_system = 0x5; + break; + + case UV1_HUB_REVISION_BASE: + uv_hubbed_system = 0x3; + break; + } + pnodeid = early_get_pnodeid(); early_get_apic_socketid_shift(); @@ -356,9 +379,15 @@ int is_uv_system(void) } EXPORT_SYMBOL_GPL(is_uv_system); -int is_uv_hubless(void) +int is_uv_hubbed(int uvtype) +{ + return (uv_hubbed_system & uvtype); +} +EXPORT_SYMBOL_GPL(is_uv_hubbed); + +int is_uv_hubless(int uvtype) { - return uv_hubless_system; + return (uv_hubless_system & uvtype); } EXPORT_SYMBOL_GPL(is_uv_hubless); @@ -1275,7 +1304,8 @@ static int __init decode_uv_systab(void) struct uv_systab *st; int i; - if (uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE) + /* If system is uv3 or lower, there is no extended UVsystab */ + if (is_uv_hubbed(0xfffffe) < uv(4) && is_uv_hubless(0xfffffe) < uv(4)) return 0; /* No extended UVsystab required */ st = uv_systab; @@ -1454,6 +1484,72 @@ static void __init build_socket_tables(void) } } +/* Check which reboot to use */ +static void check_efi_reboot(void) +{ + /* If EFI reboot not available, use ACPI reboot */ + if (!efi_enabled(EFI_BOOT)) + reboot_type = BOOT_ACPI; +} + +/* Setup user proc fs files */ +static int __maybe_unused proc_hubbed_show(struct seq_file *file, void *data) +{ + seq_printf(file, "0x%x\n", uv_hubbed_system); + return 0; +} + +static int __maybe_unused proc_hubless_show(struct seq_file *file, void *data) +{ + seq_printf(file, "0x%x\n", uv_hubless_system); + return 0; +} + +static int __maybe_unused proc_oemid_show(struct seq_file *file, void *data) +{ + seq_printf(file, "%s/%s\n", oem_id, oem_table_id); + return 0; +} + +static __init void uv_setup_proc_files(int hubless) +{ + struct proc_dir_entry *pde; + + pde = proc_mkdir(UV_PROC_NODE, NULL); + proc_create_single("oemid", 0, pde, proc_oemid_show); + if (hubless) + proc_create_single("hubless", 0, pde, proc_hubless_show); + else + proc_create_single("hubbed", 0, pde, proc_hubbed_show); +} + +/* Initialize UV hubless systems */ +static __init int uv_system_init_hubless(void) +{ + int rc; + + /* Setup PCH NMI handler */ + uv_nmi_setup_hubless(); + + /* Init kernel/BIOS interface */ + rc = uv_bios_init(); + if (rc < 0) + return rc; + + /* Process UVsystab */ + rc = decode_uv_systab(); + if (rc < 0) + return rc; + + /* Create user access node */ + if (rc >= 0) + uv_setup_proc_files(1); + + check_efi_reboot(); + + return rc; +} + static void __init uv_system_init_hub(void) { struct uv_hub_info_s hub_info = {0}; @@ -1579,32 +1675,27 @@ static void __init uv_system_init_hub(void) uv_nmi_setup(); uv_cpu_init(); uv_scir_register_cpu_notifier(); - proc_mkdir("sgi_uv", NULL); + uv_setup_proc_files(0); /* Register Legacy VGA I/O redirection handler: */ pci_register_set_vga_state(uv_set_vga_state); - /* - * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as - * EFI is not enabled in the kdump kernel: - */ - if (is_kdump_kernel()) - reboot_type = BOOT_ACPI; + check_efi_reboot(); } /* - * There is a small amount of UV specific code needed to initialize a - * UV system that does not have a "UV HUB" (referred to as "hubless"). + * There is a different code path needed to initialize a UV system that does + * not have a "UV HUB" (referred to as "hubless"). */ void __init uv_system_init(void) { - if (likely(!is_uv_system() && !is_uv_hubless())) + if (likely(!is_uv_system() && !is_uv_hubless(1))) return; if (is_uv_system()) uv_system_init_hub(); else - uv_nmi_setup_hubless(); + uv_system_init_hubless(); } apic_driver(apic_x2apic_uv_x); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index d3d075226c0a..24d2fde30d00 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -6,13 +6,28 @@ #include <asm/ia32.h> #define __SYSCALL_64(nr, sym, qual) [nr] = 1, +#define __SYSCALL_X32(nr, sym, qual) static char syscalls_64[] = { #include <asm/syscalls_64.h> }; +#undef __SYSCALL_64 +#undef __SYSCALL_X32 + +#ifdef CONFIG_X86_X32_ABI +#define __SYSCALL_64(nr, sym, qual) +#define __SYSCALL_X32(nr, sym, qual) [nr] = 1, +static char syscalls_x32[] = { +#include <asm/syscalls_64.h> +}; +#undef __SYSCALL_64 +#undef __SYSCALL_X32 +#endif + #define __SYSCALL_I386(nr, sym, qual) [nr] = 1, static char syscalls_ia32[] = { #include <asm/syscalls_32.h> }; +#undef __SYSCALL_I386 #if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) #include <asm/kvm_para.h> @@ -62,7 +77,6 @@ int main(void) ENTRY(cr2); ENTRY(cr3); ENTRY(cr4); - ENTRY(cr8); ENTRY(gdt_desc); BLANK(); #undef ENTRY @@ -80,6 +94,11 @@ int main(void) DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); DEFINE(NR_syscalls, sizeof(syscalls_64)); +#ifdef CONFIG_X86_X32_ABI + DEFINE(__NR_syscall_x32_max, sizeof(syscalls_x32) - 1); + DEFINE(X32_NR_syscalls, sizeof(syscalls_x32)); +#endif + DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1); DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32)); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index d7a1e5a9331c..7dc4ad68eb41 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -29,8 +29,9 @@ obj-y += umwait.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o +obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o ifdef CONFIG_CPU_SUP_INTEL -obj-y += intel.o intel_pconfig.o +obj-y += intel.o intel_pconfig.o tsx.o obj-$(CONFIG_PM) += intel_epb.o endif obj-$(CONFIG_CPU_SUP_AMD) += amd.o @@ -53,11 +54,12 @@ obj-$(CONFIG_ACRN_GUEST) += acrn.o ifdef CONFIG_X86_FEATURE_NAMES quiet_cmd_mkcapflags = MKCAP $@ - cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@ + cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^ cpufeature = $(src)/../../include/asm/cpufeatures.h +vmxfeature = $(src)/../../include/asm/vmxfeatures.h -$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE +$(obj)/capflags.c: $(cpufeature) $(vmxfeature) $(src)/mkcapflags.sh FORCE $(call if_changed,mkcapflags) endif targets += capflags.c diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 8d4e50428b68..ac83a0fef628 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/random.h> +#include <linux/topology.h> #include <asm/processor.h> #include <asm/apic.h> #include <asm/cacheinfo.h> @@ -318,13 +319,6 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c) c->cpu_core_id %= cus_per_node; } - -static void amd_get_topology_early(struct cpuinfo_x86 *c) -{ - if (cpu_has(c, X86_FEATURE_TOPOEXT)) - smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; -} - /* * Fixup core topology information for * (1) AMD multi-node processors @@ -614,9 +608,9 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) return; clear_all: - clear_cpu_cap(c, X86_FEATURE_SME); + setup_clear_cpu_cap(X86_FEATURE_SME); clear_sev: - clear_cpu_cap(c, X86_FEATURE_SEV); + setup_clear_cpu_cap(X86_FEATURE_SEV); } } @@ -716,7 +710,8 @@ static void early_init_amd(struct cpuinfo_x86 *c) } } - amd_get_topology_early(c); + if (cpu_has(c, X86_FEATURE_TOPOEXT)) + smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; } static void init_amd_k8(struct cpuinfo_x86 *c) @@ -804,6 +799,64 @@ static void init_amd_ln(struct cpuinfo_x86 *c) msr_set_bit(MSR_AMD64_DE_CFG, 31); } +static bool rdrand_force; + +static int __init rdrand_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "force")) + rdrand_force = true; + else + return -EINVAL; + + return 0; +} +early_param("rdrand", rdrand_cmdline); + +static void clear_rdrand_cpuid_bit(struct cpuinfo_x86 *c) +{ + /* + * Saving of the MSR used to hide the RDRAND support during + * suspend/resume is done by arch/x86/power/cpu.c, which is + * dependent on CONFIG_PM_SLEEP. + */ + if (!IS_ENABLED(CONFIG_PM_SLEEP)) + return; + + /* + * The nordrand option can clear X86_FEATURE_RDRAND, so check for + * RDRAND support using the CPUID function directly. + */ + if (!(cpuid_ecx(1) & BIT(30)) || rdrand_force) + return; + + msr_clear_bit(MSR_AMD64_CPUID_FN_1, 62); + + /* + * Verify that the CPUID change has occurred in case the kernel is + * running virtualized and the hypervisor doesn't support the MSR. + */ + if (cpuid_ecx(1) & BIT(30)) { + pr_info_once("BIOS may not properly restore RDRAND after suspend, but hypervisor does not support hiding RDRAND via CPUID.\n"); + return; + } + + clear_cpu_cap(c, X86_FEATURE_RDRAND); + pr_info_once("BIOS may not properly restore RDRAND after suspend, hiding RDRAND via CPUID. Use rdrand=force to reenable.\n"); +} + +static void init_amd_jg(struct cpuinfo_x86 *c) +{ + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); +} + static void init_amd_bd(struct cpuinfo_x86 *c) { u64 value; @@ -818,12 +871,23 @@ static void init_amd_bd(struct cpuinfo_x86 *c) wrmsrl_safe(MSR_F15H_IC_CFG, value); } } + + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); } static void init_amd_zn(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_ZEN); +#ifdef CONFIG_NUMA + node_reclaim_distance = 32; +#endif + /* * Fix erratum 1076: CPB feature bit not being set in CPUID. * Always set it, except when running under a hypervisor. @@ -860,6 +924,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x10: init_amd_gh(c); break; case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; + case 0x16: init_amd_jg(c); break; case 0x17: init_amd_zn(c); break; } @@ -879,12 +944,8 @@ static void init_amd(struct cpuinfo_x86 *c) init_amd_cacheinfo(c); if (cpu_has(c, X86_FEATURE_XMM2)) { - unsigned long long val; - int ret; - /* - * A serializing LFENCE has less overhead than MFENCE, so - * use it for execution serialization. On families which + * Use LFENCE for execution serialization. On families which * don't have that MSR, LFENCE is already serializing. * msr_set_bit() uses the safe accessors, too, even if the MSR * is not present. @@ -892,19 +953,8 @@ static void init_amd(struct cpuinfo_x86 *c) msr_set_bit(MSR_F10H_DECFG, MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); - /* - * Verify that the MSR write was successful (could be running - * under a hypervisor) and only then assume that LFENCE is - * serializing. - */ - ret = rdmsrl_safe(MSR_F10H_DECFG, &val); - if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { - /* A serializing LFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); - } else { - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); - } + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); } /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c6fa3ef10b4e..ed54b3b21c39 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -39,6 +39,8 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init mds_print_mitigation(void); +static void __init taa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -105,6 +107,13 @@ void __init check_bugs(void) ssb_select_mitigation(); l1tf_select_mitigation(); mds_select_mitigation(); + taa_select_mitigation(); + + /* + * As MDS and TAA mitigations are inter-related, print MDS + * mitigation until after TAA mitigation selection is done. + */ + mds_print_mitigation(); arch_smt_update(); @@ -243,6 +252,12 @@ static void __init mds_select_mitigation(void) (mds_nosmt || cpu_mitigations_auto_nosmt())) cpu_smt_disable(false); } +} + +static void __init mds_print_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) + return; pr_info("%s\n", mds_strings[mds_mitigation]); } @@ -269,6 +284,120 @@ static int __init mds_cmdline(char *str) early_param("mds", mds_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "TAA: " fmt + +enum taa_mitigations { + TAA_MITIGATION_OFF, + TAA_MITIGATION_UCODE_NEEDED, + TAA_MITIGATION_VERW, + TAA_MITIGATION_TSX_DISABLED, +}; + +/* Default mitigation for TAA-affected CPUs */ +static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; +static bool taa_nosmt __ro_after_init; + +static const char * const taa_strings[] = { + [TAA_MITIGATION_OFF] = "Vulnerable", + [TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", + [TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled", +}; + +static void __init taa_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TSX previously disabled by tsx=off */ + if (!boot_cpu_has(X86_FEATURE_RTM)) { + taa_mitigation = TAA_MITIGATION_TSX_DISABLED; + goto out; + } + + if (cpu_mitigations_off()) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* + * TAA mitigation via VERW is turned off if both + * tsx_async_abort=off and mds=off are specified. + */ + if (taa_mitigation == TAA_MITIGATION_OFF && + mds_mitigation == MDS_MITIGATION_OFF) + goto out; + + if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) + taa_mitigation = TAA_MITIGATION_VERW; + else + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1. + * A microcode update fixes this behavior to clear CPU buffers. It also + * adds support for MSR_IA32_TSX_CTRL which is enumerated by the + * ARCH_CAP_TSX_CTRL_MSR bit. + * + * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode + * update is required. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ( (ia32_cap & ARCH_CAP_MDS_NO) && + !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * TSX is enabled, select alternate mitigation for TAA which is + * the same as MDS. Enable MDS static branch to clear CPU buffers. + * + * For guests that can't determine whether the correct microcode is + * present on host, enable the mitigation for UCODE_NEEDED as well. + */ + static_branch_enable(&mds_user_clear); + + if (taa_nosmt || cpu_mitigations_auto_nosmt()) + cpu_smt_disable(false); + + /* + * Update MDS mitigation, if necessary, as the mds_user_clear is + * now enabled for TAA mitigation. + */ + if (mds_mitigation == MDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_MDS)) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_select_mitigation(); + } +out: + pr_info("%s\n", taa_strings[taa_mitigation]); +} + +static int __init tsx_async_abort_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_TAA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + taa_mitigation = TAA_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + taa_mitigation = TAA_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_nosmt = true; + } + + return 0; +} +early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -786,13 +915,10 @@ static void update_mds_branch_idle(void) } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" -void arch_smt_update(void) +void cpu_bugs_smt_update(void) { - /* Enhanced IBRS implies STIBP. No update required. */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) - return; - mutex_lock(&spec_ctrl_mutex); switch (spectre_v2_user) { @@ -819,6 +945,17 @@ void arch_smt_update(void) break; } + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -1149,6 +1286,9 @@ void x86_spec_ctrl_setup_ap(void) x86_amd_ssb_disable(); } +bool itlb_multihit_kvm_mitigation; +EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); + #undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt @@ -1184,15 +1324,15 @@ static void override_cache_bits(struct cpuinfo_x86 *c) case INTEL_FAM6_WESTMERE: case INTEL_FAM6_SANDYBRIDGE: case INTEL_FAM6_IVYBRIDGE: - case INTEL_FAM6_HASWELL_CORE: - case INTEL_FAM6_HASWELL_ULT: - case INTEL_FAM6_HASWELL_GT3E: - case INTEL_FAM6_BROADWELL_CORE: - case INTEL_FAM6_BROADWELL_GT3E: - case INTEL_FAM6_SKYLAKE_MOBILE: - case INTEL_FAM6_SKYLAKE_DESKTOP: - case INTEL_FAM6_KABYLAKE_MOBILE: - case INTEL_FAM6_KABYLAKE_DESKTOP: + case INTEL_FAM6_HASWELL: + case INTEL_FAM6_HASWELL_L: + case INTEL_FAM6_HASWELL_G: + case INTEL_FAM6_BROADWELL: + case INTEL_FAM6_BROADWELL_G: + case INTEL_FAM6_SKYLAKE_L: + case INTEL_FAM6_SKYLAKE: + case INTEL_FAM6_KABYLAKE_L: + case INTEL_FAM6_KABYLAKE: if (c->x86_cache_bits < 44) c->x86_cache_bits = 44; break; @@ -1304,11 +1444,24 @@ static ssize_t l1tf_show_state(char *buf) l1tf_vmx_states[l1tf_vmx_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + if (itlb_multihit_kvm_mitigation) + return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + else + return sprintf(buf, "KVM: Vulnerable\n"); +} #else static ssize_t l1tf_show_state(char *buf) { return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + return sprintf(buf, "Processor vulnerable\n"); +} #endif static ssize_t mds_show_state(char *buf) @@ -1328,6 +1481,21 @@ static ssize_t mds_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t tsx_async_abort_show_state(char *buf) +{ + if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || + (taa_mitigation == TAA_MITIGATION_OFF)) + return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); + } + + return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) @@ -1398,6 +1566,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MDS: return mds_show_state(buf); + case X86_BUG_TAA: + return tsx_async_abort_show_state(buf); + + case X86_BUG_ITLB_MULTIHIT: + return itlb_multihit_show_state(buf); + default: break; } @@ -1434,4 +1608,14 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_MDS); } + +ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TAA); +} + +ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); +} #endif diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 14433ff5b828..426792565d86 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -18,13 +18,6 @@ #define RNG_ENABLED (1 << 3) #define RNG_ENABLE (1 << 6) /* MSR_VIA_RNG */ -#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000 -#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000 -#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000 -#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 -#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 -#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 - static void init_c3(struct cpuinfo_x86 *c) { u32 lo, hi; @@ -71,8 +64,6 @@ static void init_c3(struct cpuinfo_x86 *c) c->x86_cache_alignment = c->x86_clflush_size * 2; set_cpu_cap(c, X86_FEATURE_REP_GOOD); } - - cpu_detect_cache_sizes(c); } enum { @@ -119,31 +110,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c) } } -static void centaur_detect_vmx_virtcap(struct cpuinfo_x86 *c) -{ - u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; - - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); - msr_ctl = vmx_msr_high | vmx_msr_low; - - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW) - set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI) - set_cpu_cap(c, X86_FEATURE_VNMI); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) { - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - vmx_msr_low, vmx_msr_high); - msr_ctl2 = vmx_msr_high | vmx_msr_low; - if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && - (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) - set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) - set_cpu_cap(c, X86_FEATURE_EPT); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) - set_cpu_cap(c, X86_FEATURE_VPID); - } -} - static void init_centaur(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 @@ -250,8 +216,7 @@ static void init_centaur(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); #endif - if (cpu_has(c, X86_FEATURE_VMX)) - centaur_detect_vmx_virtcap(c); + init_ia32_feat_ctl(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f125bf7ecb6f..52c9bfbbdb2a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -14,6 +14,7 @@ #include <linux/sched/mm.h> #include <linux/sched/clock.h> #include <linux/sched/task.h> +#include <linux/sched/smt.h> #include <linux/init.h> #include <linux/kprobes.h> #include <linux/kgdb.h> @@ -24,6 +25,7 @@ #include <asm/stackprotector.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> +#include <asm/doublefault.h> #include <asm/archrandom.h> #include <asm/hypervisor.h> #include <asm/processor.h> @@ -48,15 +50,12 @@ #include <asm/cpu.h> #include <asm/mce.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> #include <asm/intel-family.h> #include <asm/cpu_device_id.h> - -#ifdef CONFIG_X86_LOCAL_APIC #include <asm/uv/uv.h> -#endif #include "cpu.h" @@ -165,22 +164,6 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); -static int __init x86_mpx_setup(char *s) -{ - /* require an exact match without trailing characters */ - if (strlen(s)) - return 0; - - /* do not emit a message if the feature is not present */ - if (!boot_cpu_has(X86_FEATURE_MPX)) - return 1; - - setup_clear_cpu_cap(X86_FEATURE_MPX); - pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n"); - return 1; -} -__setup("nompx", x86_mpx_setup); - #ifdef CONFIG_X86_64 static int __init x86_nopcid_setup(char *s) { @@ -307,8 +290,6 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) static __init int setup_disable_smep(char *arg) { setup_clear_cpu_cap(X86_FEATURE_SMEP); - /* Check for things that depend on SMEP being enabled: */ - check_mpx_erratum(&boot_cpu_data); return 1; } __setup("nosmep", setup_disable_smep); @@ -565,8 +546,9 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c) return NULL; /* Not found */ } -__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; -__u32 cpu_caps_set[NCAPINTS + NBUGINTS]; +/* Aligned to unsigned long to avoid split lock in atomic bitmap ops */ +__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long)); +__u32 cpu_caps_set[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long)); void load_percpu_segment(int cpu) { @@ -1016,13 +998,15 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } -#define NO_SPECULATION BIT(0) -#define NO_MELTDOWN BIT(1) -#define NO_SSB BIT(2) -#define NO_L1TF BIT(3) -#define NO_MDS BIT(4) -#define MSBDS_ONLY BIT(5) -#define NO_SWAPGS BIT(6) +#define NO_SPECULATION BIT(0) +#define NO_MELTDOWN BIT(1) +#define NO_SSB BIT(2) +#define NO_L1TF BIT(3) +#define NO_MDS BIT(4) +#define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6) +#define NO_ITLB_MULTIHIT BIT(7) +#define NO_SPECTRE_V2 BIT(8) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -1043,26 +1027,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ - VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), - - VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(CORE_YONAH, NO_SSB), - VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -1072,15 +1057,21 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { * good enough for our purposes. */ + VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT), + /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + + /* Zhaoxin Family 7 */ + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), {} }; @@ -1091,18 +1082,31 @@ static bool __init cpu_matches(unsigned long which) return m && !!(m->driver_data & which); } -static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +u64 x86_read_arch_cap_msr(void) { u64 ia32_cap = 0; + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + return ia32_cap; +} + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ + if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); + if (cpu_matches(NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + if (!cpu_matches(NO_SPECTRE_V2)) + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) @@ -1120,6 +1124,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (!cpu_matches(NO_SWAPGS)) setup_force_cpu_bug(X86_BUG_SWAPGS); + /* + * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when: + * - TSX is supported or + * - TSX_CTRL is present + * + * TSX_CTRL check is needed for cases when TSX could be disabled before + * the kernel boot e.g. kexec. + * TSX_CTRL check alone is not sufficient for cases when the microcode + * update is not present or running as guest that don't get TSX_CTRL. + */ + if (!(ia32_cap & ARCH_CAP_TAA_NO) && + (cpu_has(c, X86_FEATURE_RTM) || + (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + setup_force_cpu_bug(X86_BUG_TAA); + if (cpu_matches(NO_MELTDOWN)) return; @@ -1420,6 +1439,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) #endif c->x86_cache_alignment = c->x86_clflush_size; memset(&c->x86_capability, 0, sizeof(c->x86_capability)); +#ifdef CONFIG_X86_VMX_FEATURE_NAMES + memset(&c->vmx_capability, 0, sizeof(c->vmx_capability)); +#endif generic_identify(c); @@ -1553,6 +1575,8 @@ void __init identify_boot_cpu(void) #endif cpu_detect_tlb(&boot_cpu_data); setup_cr_pinning(); + + tsx_init(); } void identify_secondary_cpu(struct cpuinfo_x86 *c) @@ -1748,7 +1772,7 @@ static void wait_for_master_cpu(int cpu) } #ifdef CONFIG_X86_64 -static void setup_getcpu(int cpu) +static inline void setup_getcpu(int cpu) { unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu)); struct desc_struct d = { }; @@ -1768,7 +1792,50 @@ static void setup_getcpu(int cpu) write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S); } + +static inline void ucode_cpu_init(int cpu) +{ + if (cpu) + load_ucode_ap(); +} + +static inline void tss_setup_ist(struct tss_struct *tss) +{ + /* Set up the per-CPU TSS IST stacks */ + tss->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF); + tss->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI); + tss->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB); + tss->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE); +} + +#else /* CONFIG_X86_64 */ + +static inline void setup_getcpu(int cpu) { } + +static inline void ucode_cpu_init(int cpu) +{ + show_ucode_info_early(); +} + +static inline void tss_setup_ist(struct tss_struct *tss) { } + +#endif /* !CONFIG_X86_64 */ + +static inline void tss_setup_io_bitmap(struct tss_struct *tss) +{ + tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID; + +#ifdef CONFIG_X86_IOPL_IOPERM + tss->io_bitmap.prev_max = 0; + tss->io_bitmap.prev_sequence = 0; + memset(tss->io_bitmap.bitmap, 0xff, sizeof(tss->io_bitmap.bitmap)); + /* + * Invalidate the extra array entry past the end of the all + * permission bitmap as required by the hardware. + */ + tss->io_bitmap.mapall[IO_BITMAP_LONGS] = ~0UL; #endif +} /* * cpu_init() initializes state that is per-CPU. Some data is already @@ -1776,21 +1843,15 @@ static void setup_getcpu(int cpu) * and IDT. We reload them nevertheless, this function acts as a * 'CPU state barrier', nothing should get across. */ -#ifdef CONFIG_X86_64 - void cpu_init(void) { + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + struct task_struct *cur = current; int cpu = raw_smp_processor_id(); - struct task_struct *me; - struct tss_struct *t; - int i; wait_for_master_cpu(cpu); - if (cpu) - load_ucode_ap(); - - t = &per_cpu(cpu_tss_rw, cpu); + ucode_cpu_init(cpu); #ifdef CONFIG_NUMA if (this_cpu_read(numa_node) == 0 && @@ -1799,63 +1860,47 @@ void cpu_init(void) #endif setup_getcpu(cpu); - me = current; - pr_debug("Initializing CPU#%d\n", cpu); - cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); + if (IS_ENABLED(CONFIG_X86_64) || cpu_feature_enabled(X86_FEATURE_VME) || + boot_cpu_has(X86_FEATURE_TSC) || boot_cpu_has(X86_FEATURE_DE)) + cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); /* * Initialize the per-CPU GDT with the boot GDT, * and set up the GDT descriptor: */ - switch_to_new_gdt(cpu); - loadsegment(fs, 0); - load_current_idt(); - memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8); - syscall_init(); - - wrmsrl(MSR_FS_BASE, 0); - wrmsrl(MSR_KERNEL_GS_BASE, 0); - barrier(); + if (IS_ENABLED(CONFIG_X86_64)) { + loadsegment(fs, 0); + memset(cur->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8); + syscall_init(); - x86_configure_nx(); - x2apic_setup(); + wrmsrl(MSR_FS_BASE, 0); + wrmsrl(MSR_KERNEL_GS_BASE, 0); + barrier(); - /* - * set up and load the per-CPU TSS - */ - if (!t->x86_tss.ist[0]) { - t->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF); - t->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI); - t->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB); - t->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE); + x2apic_setup(); } - t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; - - /* - * <= is required because the CPU will access up to - * 8 bits beyond the end of the IO permission bitmap. - */ - for (i = 0; i <= IO_BITMAP_LONGS; i++) - t->io_bitmap[i] = ~0UL; - mmgrab(&init_mm); - me->active_mm = &init_mm; - BUG_ON(me->mm); + cur->active_mm = &init_mm; + BUG_ON(cur->mm); initialize_tlbstate_and_flush(); - enter_lazy_tlb(&init_mm, me); + enter_lazy_tlb(&init_mm, cur); - /* - * Initialize the TSS. sp0 points to the entry trampoline stack - * regardless of what task is running. - */ + /* Initialize the TSS. */ + tss_setup_ist(tss); + tss_setup_io_bitmap(tss); set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); + load_TR_desc(); + /* + * sp0 points to the entry trampoline stack regardless of what task + * is running. + */ load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1)); load_mm_ldt(&init_mm); @@ -1863,6 +1908,8 @@ void cpu_init(void) clear_all_debug_regs(); dbg_restore_debug_regs(); + doublefault_init_cpu_tss(); + fpu__init_cpu(); if (is_uv_system()) @@ -1871,63 +1918,6 @@ void cpu_init(void) load_fixmap_gdt(cpu); } -#else - -void cpu_init(void) -{ - int cpu = smp_processor_id(); - struct task_struct *curr = current; - struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu); - - wait_for_master_cpu(cpu); - - show_ucode_info_early(); - - pr_info("Initializing CPU#%d\n", cpu); - - if (cpu_feature_enabled(X86_FEATURE_VME) || - boot_cpu_has(X86_FEATURE_TSC) || - boot_cpu_has(X86_FEATURE_DE)) - cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); - - load_current_idt(); - switch_to_new_gdt(cpu); - - /* - * Set up and load the per-CPU TSS and LDT - */ - mmgrab(&init_mm); - curr->active_mm = &init_mm; - BUG_ON(curr->mm); - initialize_tlbstate_and_flush(); - enter_lazy_tlb(&init_mm, curr); - - /* - * Initialize the TSS. sp0 points to the entry trampoline stack - * regardless of what task is running. - */ - set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); - load_TR_desc(); - load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1)); - - load_mm_ldt(&init_mm); - - t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; - -#ifdef CONFIG_DOUBLEFAULT - /* Set up doublefault TSS pointer in the GDT */ - __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss); -#endif - - clear_all_debug_regs(); - dbg_restore_debug_regs(); - - fpu__init_cpu(); - - load_fixmap_gdt(cpu); -} -#endif - /* * The microcode loader calls this upon late microcode load to recheck features, * only when microcode has been updated. Caller holds microcode_mutex and CPU @@ -1957,3 +1947,14 @@ void microcode_check(void) pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n"); pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); } + +/* + * Invoked from core CPU hotplug code after hotplug operations + */ +void arch_smt_update(void) +{ + /* Handle the speculative execution misfeatures */ + cpu_bugs_smt_update(); + /* Check whether IPI broadcasting can be enabled */ + apic_smt_update(); +} diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index c0e2407abdd6..37fdefd14f28 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -44,6 +44,22 @@ struct _tlb_table { extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; +#ifdef CONFIG_CPU_SUP_INTEL +enum tsx_ctrl_states { + TSX_CTRL_ENABLE, + TSX_CTRL_DISABLE, + TSX_CTRL_NOT_SUPPORTED, +}; + +extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; + +extern void __init tsx_init(void); +extern void tsx_enable(void); +extern void tsx_disable(void); +#else +static inline void tsx_init(void) { } +#endif /* CONFIG_CPU_SUP_INTEL */ + extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void get_cpu_address_sizes(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); @@ -62,4 +78,10 @@ unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern u64 x86_read_arch_cap_msr(void); + +#ifdef CONFIG_IA32_FEAT_CTL +void init_ia32_feat_ctl(struct cpuinfo_x86 *c); +#endif + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index b5353244749b..3cbe24ca80ab 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -20,54 +20,55 @@ struct cpuid_dep { * but it's difficult to tell that to the init reference checker. */ static const struct cpuid_dep cpuid_deps[] = { - { X86_FEATURE_FXSR, X86_FEATURE_FPU }, - { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE }, - { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE }, - { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE }, - { X86_FEATURE_AVX, X86_FEATURE_XSAVE }, - { X86_FEATURE_PKU, X86_FEATURE_XSAVE }, - { X86_FEATURE_MPX, X86_FEATURE_XSAVE }, - { X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE }, - { X86_FEATURE_CMOV, X86_FEATURE_FXSR }, - { X86_FEATURE_MMX, X86_FEATURE_FXSR }, - { X86_FEATURE_MMXEXT, X86_FEATURE_MMX }, - { X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR }, - { X86_FEATURE_XSAVE, X86_FEATURE_FXSR }, - { X86_FEATURE_XMM, X86_FEATURE_FXSR }, - { X86_FEATURE_XMM2, X86_FEATURE_XMM }, - { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, - { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 }, - { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 }, - { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, - { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 }, - { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, }, - { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, - { X86_FEATURE_AES, X86_FEATURE_XMM2 }, - { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, - { X86_FEATURE_FMA, X86_FEATURE_AVX }, - { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, - { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, - { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, - { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, - { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, - { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F }, - { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F }, - { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC }, - { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC }, - { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC }, - { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL }, + { X86_FEATURE_FXSR, X86_FEATURE_FPU }, + { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE }, + { X86_FEATURE_AVX, X86_FEATURE_XSAVE }, + { X86_FEATURE_PKU, X86_FEATURE_XSAVE }, + { X86_FEATURE_MPX, X86_FEATURE_XSAVE }, + { X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE }, + { X86_FEATURE_CMOV, X86_FEATURE_FXSR }, + { X86_FEATURE_MMX, X86_FEATURE_FXSR }, + { X86_FEATURE_MMXEXT, X86_FEATURE_MMX }, + { X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR }, + { X86_FEATURE_XSAVE, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM2, X86_FEATURE_XMM }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 }, + { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, }, + { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, + { X86_FEATURE_AES, X86_FEATURE_XMM2 }, + { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, + { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VP2INTERSECT, X86_FEATURE_AVX512VL }, + { X86_FEATURE_CQM_OCCUP_LLC, X86_FEATURE_CQM_LLC }, + { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC }, + { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC }, + { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL }, {} }; diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c new file mode 100644 index 000000000000..0268185bef94 --- /dev/null +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/tboot.h> + +#include <asm/cpufeature.h> +#include <asm/msr-index.h> +#include <asm/processor.h> +#include <asm/vmx.h> + +#undef pr_fmt +#define pr_fmt(fmt) "x86/cpu: " fmt + +#ifdef CONFIG_X86_VMX_FEATURE_NAMES +enum vmx_feature_leafs { + MISC_FEATURES = 0, + PRIMARY_CTLS, + SECONDARY_CTLS, + NR_VMX_FEATURE_WORDS, +}; + +#define VMX_F(x) BIT(VMX_FEATURE_##x & 0x1f) + +static void init_vmx_capabilities(struct cpuinfo_x86 *c) +{ + u32 supported, funcs, ept, vpid, ign; + + BUILD_BUG_ON(NVMXINTS != NR_VMX_FEATURE_WORDS); + + /* + * The high bits contain the allowed-1 settings, i.e. features that can + * be turned on. The low bits contain the allowed-0 settings, i.e. + * features that can be turned off. Ignore the allowed-0 settings, + * if a feature can be turned on then it's supported. + * + * Use raw rdmsr() for primary processor controls and pin controls MSRs + * as they exist on any CPU that supports VMX, i.e. we want the WARN if + * the RDMSR faults. + */ + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, ign, supported); + c->vmx_capability[PRIMARY_CTLS] = supported; + + rdmsr_safe(MSR_IA32_VMX_PROCBASED_CTLS2, &ign, &supported); + c->vmx_capability[SECONDARY_CTLS] = supported; + + rdmsr(MSR_IA32_VMX_PINBASED_CTLS, ign, supported); + rdmsr_safe(MSR_IA32_VMX_VMFUNC, &ign, &funcs); + + /* + * Except for EPT+VPID, which enumerates support for both in a single + * MSR, low for EPT, high for VPID. + */ + rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, &ept, &vpid); + + /* Pin, EPT, VPID and VM-Func are merged into a single word. */ + WARN_ON_ONCE(supported >> 16); + WARN_ON_ONCE(funcs >> 4); + c->vmx_capability[MISC_FEATURES] = (supported & 0xffff) | + ((vpid & 0x1) << 16) | + ((funcs & 0xf) << 28); + + /* EPT bits are full on scattered and must be manually handled. */ + if (ept & VMX_EPT_EXECUTE_ONLY_BIT) + c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_EXECUTE_ONLY); + if (ept & VMX_EPT_AD_BIT) + c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_AD); + if (ept & VMX_EPT_1GB_PAGE_BIT) + c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_1GB); + + /* Synthetic APIC features that are aggregates of multiple features. */ + if ((c->vmx_capability[PRIMARY_CTLS] & VMX_F(VIRTUAL_TPR)) && + (c->vmx_capability[SECONDARY_CTLS] & VMX_F(VIRT_APIC_ACCESSES))) + c->vmx_capability[MISC_FEATURES] |= VMX_F(FLEXPRIORITY); + + if ((c->vmx_capability[PRIMARY_CTLS] & VMX_F(VIRTUAL_TPR)) && + (c->vmx_capability[SECONDARY_CTLS] & VMX_F(APIC_REGISTER_VIRT)) && + (c->vmx_capability[SECONDARY_CTLS] & VMX_F(VIRT_INTR_DELIVERY)) && + (c->vmx_capability[MISC_FEATURES] & VMX_F(POSTED_INTR))) + c->vmx_capability[MISC_FEATURES] |= VMX_F(APICV); + + /* Set the synthetic cpufeatures to preserve /proc/cpuinfo's ABI. */ + if (c->vmx_capability[PRIMARY_CTLS] & VMX_F(VIRTUAL_TPR)) + set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); + if (c->vmx_capability[MISC_FEATURES] & VMX_F(FLEXPRIORITY)) + set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); + if (c->vmx_capability[MISC_FEATURES] & VMX_F(VIRTUAL_NMIS)) + set_cpu_cap(c, X86_FEATURE_VNMI); + if (c->vmx_capability[SECONDARY_CTLS] & VMX_F(EPT)) + set_cpu_cap(c, X86_FEATURE_EPT); + if (c->vmx_capability[MISC_FEATURES] & VMX_F(EPT_AD)) + set_cpu_cap(c, X86_FEATURE_EPT_AD); + if (c->vmx_capability[MISC_FEATURES] & VMX_F(VPID)) + set_cpu_cap(c, X86_FEATURE_VPID); +} +#endif /* CONFIG_X86_VMX_FEATURE_NAMES */ + +void init_ia32_feat_ctl(struct cpuinfo_x86 *c) +{ + bool tboot = tboot_enabled(); + u64 msr; + + if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) { + clear_cpu_cap(c, X86_FEATURE_VMX); + return; + } + + if (msr & FEAT_CTL_LOCKED) + goto update_caps; + + /* + * Ignore whatever value BIOS left in the MSR to avoid enabling random + * features or faulting on the WRMSR. + */ + msr = FEAT_CTL_LOCKED; + + /* + * Enable VMX if and only if the kernel may do VMXON at some point, + * i.e. KVM is enabled, to avoid unnecessarily adding an attack vector + * for the kernel, e.g. using VMX to hide malicious code. + */ + if (cpu_has(c, X86_FEATURE_VMX) && IS_ENABLED(CONFIG_KVM_INTEL)) { + msr |= FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; + + if (tboot) + msr |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX; + } + + wrmsrl(MSR_IA32_FEAT_CTL, msr); + +update_caps: + set_cpu_cap(c, X86_FEATURE_MSR_IA32_FEAT_CTL); + + if (!cpu_has(c, X86_FEATURE_VMX)) + return; + + if ( (tboot && !(msr & FEAT_CTL_VMX_ENABLED_INSIDE_SMX)) || + (!tboot && !(msr & FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX))) { + if (IS_ENABLED(CONFIG_KVM_INTEL)) + pr_err_once("VMX (%s TXT) disabled by BIOS\n", + tboot ? "inside" : "outside"); + clear_cpu_cap(c, X86_FEATURE_VMX); + } else { +#ifdef CONFIG_X86_VMX_FEATURE_NAMES + init_vmx_capabilities(c); +#endif + } +} diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 415621ddb8a2..4e28c1fc8749 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -330,12 +330,8 @@ static void init_hygon(struct cpuinfo_x86 *c) init_hygon_cacheinfo(c); if (cpu_has(c, X86_FEATURE_XMM2)) { - unsigned long long val; - int ret; - /* - * A serializing LFENCE has less overhead than MFENCE, so - * use it for execution serialization. On families which + * Use LFENCE for execution serialization. On families which * don't have that MSR, LFENCE is already serializing. * msr_set_bit() uses the safe accessors, too, even if the MSR * is not present. @@ -343,19 +339,8 @@ static void init_hygon(struct cpuinfo_x86 *c) msr_set_bit(MSR_F10H_DECFG, MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); - /* - * Verify that the MSR write was successful (could be running - * under a hypervisor) and only then assume that LFENCE is - * serializing. - */ - ret = rdmsrl_safe(MSR_F10H_DECFG, &val); - if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { - /* A serializing LFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); - } else { - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); - } + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); } /* diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 8d6d92ebeb54..be82cd5841c3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -32,41 +32,6 @@ #endif /* - * Just in case our CPU detection goes bad, or you have a weird system, - * allow a way to override the automatic disabling of MPX. - */ -static int forcempx; - -static int __init forcempx_setup(char *__unused) -{ - forcempx = 1; - - return 1; -} -__setup("intel-skd-046-workaround=disable", forcempx_setup); - -void check_mpx_erratum(struct cpuinfo_x86 *c) -{ - if (forcempx) - return; - /* - * Turn off the MPX feature on CPUs where SMEP is not - * available or disabled. - * - * Works around Intel Erratum SKD046: "Branch Instructions - * May Initialize MPX Bound Registers Incorrectly". - * - * This might falsely disable MPX on systems without - * SMEP, like Atom processors without SMEP. But there - * is no such hardware known at the moment. - */ - if (cpu_has(c, X86_FEATURE_MPX) && !cpu_has(c, X86_FEATURE_SMEP)) { - setup_clear_cpu_cap(X86_FEATURE_MPX); - pr_warn("x86/mpx: Disabling MPX since SMEP not present\n"); - } -} - -/* * Processors which have self-snooping capability can handle conflicting * memory type across CPUs by snooping its own cache. However, there exists * CPU models in which having conflicting memory types still leads to @@ -142,21 +107,21 @@ struct sku_microcode { u32 microcode; }; static const struct sku_microcode spectre_bad_microcodes[] = { - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x80 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x80 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x80 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x80 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 }, + { INTEL_FAM6_KABYLAKE, 0x0B, 0x80 }, + { INTEL_FAM6_KABYLAKE, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE, 0x09, 0x80 }, + { INTEL_FAM6_KABYLAKE_L, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_L, 0x09, 0x80 }, { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, - { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, - { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, - { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 }, + { INTEL_FAM6_BROADWELL, 0x04, 0x28 }, + { INTEL_FAM6_BROADWELL_G, 0x01, 0x1b }, + { INTEL_FAM6_BROADWELL_D, 0x02, 0x14 }, + { INTEL_FAM6_BROADWELL_D, 0x03, 0x07000011 }, { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 }, - { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 }, - { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 }, - { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 }, + { INTEL_FAM6_HASWELL_L, 0x01, 0x21 }, + { INTEL_FAM6_HASWELL_G, 0x01, 0x18 }, + { INTEL_FAM6_HASWELL, 0x03, 0x23 }, { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, @@ -265,9 +230,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ if (c->x86 == 6) { switch (c->x86_model) { - case 0x27: /* Penwell */ - case 0x35: /* Cloverview */ - case 0x4a: /* Merrifield */ + case INTEL_FAM6_ATOM_SALTWELL_MID: + case INTEL_FAM6_ATOM_SALTWELL_TABLET: + case INTEL_FAM6_ATOM_SILVERMONT_MID: + case INTEL_FAM6_ATOM_AIRMONT_NP: set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); break; default: @@ -329,7 +295,6 @@ static void early_init_intel(struct cpuinfo_x86 *c) c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); } - check_mpx_erratum(c); check_memory_type_self_snoop_errata(c); /* @@ -493,52 +458,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -static void detect_vmx_virtcap(struct cpuinfo_x86 *c) -{ - /* Intel VMX MSR indicated features */ -#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000 -#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000 -#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000 -#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 -#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 -#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 -#define x86_VMX_FEATURE_EPT_CAP_AD 0x00200000 - - u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; - u32 msr_vpid_cap, msr_ept_cap; - - clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW); - clear_cpu_cap(c, X86_FEATURE_VNMI); - clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - clear_cpu_cap(c, X86_FEATURE_EPT); - clear_cpu_cap(c, X86_FEATURE_VPID); - clear_cpu_cap(c, X86_FEATURE_EPT_AD); - - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); - msr_ctl = vmx_msr_high | vmx_msr_low; - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW) - set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI) - set_cpu_cap(c, X86_FEATURE_VNMI); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) { - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - vmx_msr_low, vmx_msr_high); - msr_ctl2 = vmx_msr_high | vmx_msr_low; - if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && - (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) - set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) { - set_cpu_cap(c, X86_FEATURE_EPT); - rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, - msr_ept_cap, msr_vpid_cap); - if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD) - set_cpu_cap(c, X86_FEATURE_EPT_AD); - } - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) - set_cpu_cap(c, X86_FEATURE_VPID); - } -} - #define MSR_IA32_TME_ACTIVATE 0x982 /* Helpers to access TME_ACTIVATE MSR */ @@ -754,13 +673,17 @@ static void init_intel(struct cpuinfo_x86 *c) /* Work around errata */ srat_detect_node(c); - if (cpu_has(c, X86_FEATURE_VMX)) - detect_vmx_virtcap(c); + init_ia32_feat_ctl(c); if (cpu_has(c, X86_FEATURE_TME)) detect_tme(c); init_intel_misc_features(c); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); } #ifdef CONFIG_X86_32 @@ -813,7 +736,7 @@ static const struct _tlb_table intel_tlb_table[] = { { 0x04, TLB_DATA_4M, 8, " TLB_DATA 4 MByte pages, 4-way set associative" }, { 0x05, TLB_DATA_4M, 32, " TLB_DATA 4 MByte pages, 4-way set associative" }, { 0x0b, TLB_INST_4M, 4, " TLB_INST 4 MByte pages, 4-way set associative" }, - { 0x4f, TLB_INST_4K, 32, " TLB_INST 4 KByte pages */" }, + { 0x4f, TLB_INST_4K, 32, " TLB_INST 4 KByte pages" }, { 0x50, TLB_INST_ALL, 64, " TLB_INST 4 KByte and 2-MByte or 4-MByte pages" }, { 0x51, TLB_INST_ALL, 128, " TLB_INST 4 KByte and 2-MByte or 4-MByte pages" }, { 0x52, TLB_INST_ALL, 256, " TLB_INST 4 KByte and 2-MByte or 4-MByte pages" }, @@ -841,7 +764,7 @@ static const struct _tlb_table intel_tlb_table[] = { { 0xba, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way associative" }, { 0xc0, TLB_DATA_4K_4M, 8, " TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" }, { 0xc1, STLB_4K_2M, 1024, " STLB 4 KByte and 2 MByte pages, 8-way associative" }, - { 0xc2, TLB_DATA_2M_4M, 16, " DTLB 2 MByte/4MByte pages, 4-way associative" }, + { 0xc2, TLB_DATA_2M_4M, 16, " TLB_DATA 2 MByte/4MByte pages, 4-way associative" }, { 0xca, STLB_4K, 512, " STLB 4 KByte pages, 4-way associative" }, { 0x00, 0, 0 } }; @@ -853,8 +776,8 @@ static void intel_tlb_lookup(const unsigned char desc) return; /* look up this descriptor in the table */ - for (k = 0; intel_tlb_table[k].descriptor != desc && \ - intel_tlb_table[k].descriptor != 0; k++) + for (k = 0; intel_tlb_table[k].descriptor != desc && + intel_tlb_table[k].descriptor != 0; k++) ; if (intel_tlb_table[k].tlb_type == 0) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 6ea7fdc82f3c..b3a50d962851 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -78,6 +78,7 @@ struct smca_bank_name { static struct smca_bank_name smca_names[] = { [SMCA_LS] = { "load_store", "Load Store Unit" }, + [SMCA_LS_V2] = { "load_store", "Load Store Unit" }, [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, [SMCA_DE] = { "decode_unit", "Decode Unit" }, @@ -138,6 +139,7 @@ static struct smca_hwid smca_hwid_mcatypes[] = { /* ZN Core (HWID=0xB0) MCA types */ { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF }, + { SMCA_LS_V2, HWID_MCATYPE(0xB0, 0x10), 0xFFFFFF }, { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF }, { SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF }, { SMCA_DE, HWID_MCATYPE(0xB0, 0x3), 0x1FF }, @@ -266,10 +268,10 @@ static void smca_configure(unsigned int bank, unsigned int cpu) smca_set_misc_banks_map(bank, cpu); /* Return early if this bank was already initialized. */ - if (smca_banks[bank].hwid) + if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } @@ -583,7 +585,7 @@ bool amd_filter_mce(struct mce *m) * - Prevent possible spurious interrupts from the IF bank on Family 0x17 * Models 0x10-0x2F due to Erratum #1114. */ -void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank) +static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank) { int i, num_msrs; u64 hwcr; diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 743370ee4983..2c4f949611e4 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -53,8 +53,6 @@ #include "internal.h" -static DEFINE_MUTEX(mce_log_mutex); - /* sysfs synchronization */ static DEFINE_MUTEX(mce_sysfs_mutex); @@ -156,19 +154,10 @@ void mce_log(struct mce *m) if (!mce_gen_pool_add(m)) irq_work_queue(&mce_irq_work); } - -void mce_inject_log(struct mce *m) -{ - mutex_lock(&mce_log_mutex); - mce_log(m); - mutex_unlock(&mce_log_mutex); -} -EXPORT_SYMBOL_GPL(mce_inject_log); - -static struct notifier_block mce_srao_nb; +EXPORT_SYMBOL_GPL(mce_log); /* - * We run the default notifier if we have only the SRAO, the first and the + * We run the default notifier if we have only the UC, the first and the * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS * notifiers registered on the chain. */ @@ -488,8 +477,9 @@ int mce_usable_address(struct mce *m) if (!(m->status & MCI_STATUS_ADDRV)) return 0; - /* Checks after this one are Intel-specific: */ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + /* Checks after this one are Intel/Zhaoxin-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) return 1; if (!(m->status & MCI_STATUS_MISCV)) @@ -507,10 +497,13 @@ EXPORT_SYMBOL_GPL(mce_usable_address); bool mce_is_memory_error(struct mce *m) { - if (m->cpuvendor == X86_VENDOR_AMD || - m->cpuvendor == X86_VENDOR_HYGON) { + switch (m->cpuvendor) { + case X86_VENDOR_AMD: + case X86_VENDOR_HYGON: return amd_mce_is_memory_error(m); - } else if (m->cpuvendor == X86_VENDOR_INTEL) { + + case X86_VENDOR_INTEL: + case X86_VENDOR_ZHAOXIN: /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes * @@ -527,9 +520,10 @@ bool mce_is_memory_error(struct mce *m) return (m->status & 0xef80) == BIT(7) || (m->status & 0xef00) == BIT(8) || (m->status & 0xeffc) == 0xc; - } - return false; + default: + return false; + } } EXPORT_SYMBOL_GPL(mce_is_memory_error); @@ -589,26 +583,29 @@ static struct notifier_block first_nb = { .priority = MCE_PRIO_FIRST, }; -static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, - void *data) +static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, + void *data) { struct mce *mce = (struct mce *)data; unsigned long pfn; - if (!mce) + if (!mce || !mce_usable_address(mce)) return NOTIFY_DONE; - if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { - pfn = mce->addr >> PAGE_SHIFT; - if (!memory_failure(pfn, 0)) - set_mce_nospec(pfn); - } + if (mce->severity != MCE_AO_SEVERITY && + mce->severity != MCE_DEFERRED_SEVERITY) + return NOTIFY_DONE; + + pfn = mce->addr >> PAGE_SHIFT; + if (!memory_failure(pfn, 0)) + set_mce_nospec(pfn); return NOTIFY_OK; } -static struct notifier_block mce_srao_nb = { - .notifier_call = srao_decode_notifier, - .priority = MCE_PRIO_SRAO, + +static struct notifier_block mce_uc_nb = { + .notifier_call = uc_decode_notifier, + .priority = MCE_PRIO_UC, }; static int mce_default_notifier(struct notifier_block *nb, unsigned long val, @@ -758,26 +755,22 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) log_it: error_seen = true; - mce_read_aux(&m, i); + if (flags & MCP_DONTLOG) + goto clear_it; + mce_read_aux(&m, i); m.severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) - mce_log(&m); - else if (mce_usable_address(&m)) { - /* - * Although we skipped logging this, we still want - * to take action. Add to the pool so the registered - * notifiers will see it. - */ - if (!mce_gen_pool_add(&m)) - mce_schedule_work(); - } + if (mca_cfg.dont_log_ce && !mce_usable_address(&m)) + goto clear_it; + + mce_log(&m); + +clear_it: /* * Clear state for this bank. */ @@ -802,7 +795,7 @@ EXPORT_SYMBOL_GPL(machine_check_poll); static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { - char *tmp; + char *tmp = *msg; int i; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { @@ -814,8 +807,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); + m->bank = i; if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { - m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; @@ -1127,6 +1120,12 @@ static bool __mc_check_crashing_cpu(int cpu) u64 mcgstatus; mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + + if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) { + if (mcgstatus & MCG_STATUS_LMCES) + return false; + } + if (mcgstatus & MCG_STATUS_RIPV) { mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); return true; @@ -1221,8 +1220,8 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; int cpu = smp_processor_id(); - char *msg = "Unknown"; struct mce m, *final; + char *msg = NULL; int worst = 0; /* @@ -1277,9 +1276,10 @@ void do_machine_check(struct pt_regs *regs, long error_code) /* * Check if this MCE is signaled to only this logical processor, - * on Intel only. + * on Intel, Zhaoxin only. */ - if (m.cpuvendor == X86_VENDOR_INTEL) + if (m.cpuvendor == X86_VENDOR_INTEL || + m.cpuvendor == X86_VENDOR_ZHAOXIN) lmce = m.mcgstatus & MCG_STATUS_LMCES; /* @@ -1353,7 +1353,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) ist_end_non_atomic(); } else { if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0)) - mce_panic("Failed kernel mode recovery", &m, NULL); + mce_panic("Failed kernel mode recovery", &m, msg); } out_ist: @@ -1697,6 +1697,18 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 6 && c->x86_model == 45) quirk_no_way_out = quirk_sandybridge_ifu; } + + if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { + /* + * All newer Zhaoxin CPUs support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; + } + } + if (cfg->monarch_timeout < 0) cfg->monarch_timeout = 0; if (cfg->bootlog != 0) @@ -1760,6 +1772,35 @@ static void mce_centaur_feature_init(struct cpuinfo_x86 *c) } } +static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + + /* + * These CPUs have MCA bank 8 which reports only one error type called + * SVAD (System View Address Decoder). The reporting of that error is + * controlled by IA32_MC8.CTL.0. + * + * If enabled, prefetching on these CPUs will cause SVAD MCE when + * virtual machines start and result in a system panic. Always disable + * bank 8 SVAD error by default. + */ + if ((c->x86 == 7 && c->x86_model == 0x1b) || + (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (this_cpu_read(mce_num_banks) > 8) + mce_banks[8].ctl = 0; + } + + intel_init_cmci(); + intel_init_lmce(); + mce_adjust_timer = cmci_intel_adjust_timer; +} + +static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c) +{ + intel_clear_lmce(); +} + static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) { switch (c->x86_vendor) { @@ -1781,6 +1822,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_centaur_feature_init(c); break; + case X86_VENDOR_ZHAOXIN: + mce_zhaoxin_feature_init(c); + break; + default: break; } @@ -1792,6 +1837,11 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) case X86_VENDOR_INTEL: mce_intel_feature_clear(c); break; + + case X86_VENDOR_ZHAOXIN: + mce_zhaoxin_feature_clear(c); + break; + default: break; } @@ -1979,7 +2029,7 @@ int __init mcheck_init(void) { mcheck_intel_therm_init(); mce_register_decode_chain(&first_nb); - mce_register_decode_chain(&mce_srao_nb); + mce_register_decode_chain(&mce_uc_nb); mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); @@ -2014,15 +2064,16 @@ static void mce_disable_error_reporting(void) static void vendor_disable_error_reporting(void) { /* - * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs - * are socket-wide. - * Disabling them for just a single offlined CPU is bad, since it will - * inhibit reporting for all shared resources on the socket like the - * last level cache (LLC), the integrated memory controller (iMC), etc. + * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these + * MSRs are socket-wide. Disabling them for just a single offlined CPU + * is bad, since it will inhibit reporting for all shared resources on + * the socket like the last level cache (LLC), the integrated memory + * controller (iMC), etc. */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || - boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) return; mce_disable_error_reporting(); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 1f30117b24ba..3413b41b8d55 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -494,7 +494,7 @@ static void do_inject(void) i_mce.status |= MCI_STATUS_SYNDV; if (inj_type == SW_INJ) { - mce_inject_log(&i_mce); + mce_log(&i_mce); return; } diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index e43eb6732630..5627b1091b85 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -85,8 +85,10 @@ static int cmci_supported(int *banks) * initialization is vendor keyed and this * makes sure none of the backdoors are entered otherwise. */ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) return 0; + if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) return 0; rdmsrl(MSR_IA32_MCG_CAP, cap); @@ -113,15 +115,16 @@ static bool lmce_supported(void) /* * BIOS should indicate support for LMCE by setting bit 20 in - * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will - * generate a #GP fault. + * IA32_FEAT_CTL without which touching MCG_EXT_CTL will generate a #GP + * fault. The MSR must also be locked for LMCE_ENABLED to take effect. + * WARN if the MSR isn't locked as init_ia32_feat_ctl() unconditionally + * locks the MSR in the event that it wasn't already locked by BIOS. */ - rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp); - if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) == - (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) - return true; + rdmsrl(MSR_IA32_FEAT_CTL, tmp); + if (WARN_ON_ONCE(!(tmp & FEAT_CTL_LOCKED))) + return false; - return false; + return tmp & FEAT_CTL_LMCE_ENABLED; } bool mce_intel_cmci_poll(void) @@ -423,7 +426,7 @@ void cmci_disable_bank(int bank) raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } -static void intel_init_cmci(void) +void intel_init_cmci(void) { int banks; @@ -442,7 +445,7 @@ static void intel_init_cmci(void) cmci_recheck(); } -static void intel_init_lmce(void) +void intel_init_lmce(void) { u64 val; @@ -455,7 +458,7 @@ static void intel_init_lmce(void) wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN); } -static void intel_clear_lmce(void) +void intel_clear_lmce(void) { u64 val; @@ -479,9 +482,10 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) switch (c->x86_model) { case INTEL_FAM6_IVYBRIDGE_X: case INTEL_FAM6_HASWELL_X: - case INTEL_FAM6_BROADWELL_XEON_D: + case INTEL_FAM6_BROADWELL_D: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 43031db429d2..b785c0d0b590 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -45,11 +45,17 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval); bool mce_intel_cmci_poll(void); void mce_intel_hcpu_update(unsigned long cpu); void cmci_disable_bank(int bank); +void intel_init_cmci(void); +void intel_init_lmce(void); +void intel_clear_lmce(void); #else # define cmci_intel_adjust_timer mce_adjust_timer_default static inline bool mce_intel_cmci_poll(void) { return false; } static inline void mce_intel_hcpu_update(unsigned long cpu) { } static inline void cmci_disable_bank(int bank) { } +static inline void intel_init_cmci(void) { } +static inline void intel_init_lmce(void) { } +static inline void intel_clear_lmce(void) { } #endif void mce_timer_kick(unsigned long interval); @@ -78,8 +84,6 @@ static inline int apei_clear_mce(u64 record_id) } #endif -void mce_inject_log(struct mce *m); - /* * We consider records to be equivalent if bank+status+addr+misc all match. * This is only used when the system is going down because of a fatal error diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 210f1f5db5f7..87bcdc6dc2f0 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -107,11 +107,11 @@ static struct severity { */ MCESEV( AO, "Action optional: memory scrubbing error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB) + SER, MASK(MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB) ), MCESEV( AO, "Action optional: last level cache writeback error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB) + SER, MASK(MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB) ), /* ignore OVER for UCNA */ diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 6e2becf547c5..58b4ee3cda77 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -40,15 +40,58 @@ #define THERMAL_THROTTLING_EVENT 0 #define POWER_LIMIT_EVENT 1 -/* - * Current thermal event state: +/** + * struct _thermal_state - Represent the current thermal event state + * @next_check: Stores the next timestamp, when it is allowed + * to log the next warning message. + * @last_interrupt_time: Stores the timestamp for the last threshold + * high event. + * @therm_work: Delayed workqueue structure + * @count: Stores the current running count for thermal + * or power threshold interrupts. + * @last_count: Stores the previous running count for thermal + * or power threshold interrupts. + * @max_time_ms: This shows the maximum amount of time CPU was + * in throttled state for a single thermal + * threshold high to low state. + * @total_time_ms: This is a cumulative time during which CPU was + * in the throttled state. + * @rate_control_active: Set when a throttling message is logged. + * This is used for the purpose of rate-control. + * @new_event: Stores the last high/low status of the + * THERM_STATUS_PROCHOT or + * THERM_STATUS_POWER_LIMIT. + * @level: Stores whether this _thermal_state instance is + * for a CORE level or for PACKAGE level. + * @sample_index: Index for storing the next sample in the buffer + * temp_samples[]. + * @sample_count: Total number of samples collected in the buffer + * temp_samples[]. + * @average: The last moving average of temperature samples + * @baseline_temp: Temperature at which thermal threshold high + * interrupt was generated. + * @temp_samples: Storage for temperature samples to calculate + * moving average. + * + * This structure is used to represent data related to thermal state for a CPU. + * There is a separate storage for core and package level for each CPU. */ struct _thermal_state { - bool new_event; - int event; u64 next_check; + u64 last_interrupt_time; + struct delayed_work therm_work; unsigned long count; unsigned long last_count; + unsigned long max_time_ms; + unsigned long total_time_ms; + bool rate_control_active; + bool new_event; + u8 level; + u8 sample_index; + u8 sample_count; + u8 average; + u8 baseline_temp; + u8 temp_samples[3]; }; struct thermal_state { @@ -121,8 +164,22 @@ define_therm_throt_device_one_ro(package_throttle_count); define_therm_throt_device_show_func(package_power_limit, count); define_therm_throt_device_one_ro(package_power_limit_count); +define_therm_throt_device_show_func(core_throttle, max_time_ms); +define_therm_throt_device_one_ro(core_throttle_max_time_ms); + +define_therm_throt_device_show_func(package_throttle, max_time_ms); +define_therm_throt_device_one_ro(package_throttle_max_time_ms); + +define_therm_throt_device_show_func(core_throttle, total_time_ms); +define_therm_throt_device_one_ro(core_throttle_total_time_ms); + +define_therm_throt_device_show_func(package_throttle, total_time_ms); +define_therm_throt_device_one_ro(package_throttle_total_time_ms); + static struct attribute *thermal_throttle_attrs[] = { &dev_attr_core_throttle_count.attr, + &dev_attr_core_throttle_max_time_ms.attr, + &dev_attr_core_throttle_total_time_ms.attr, NULL }; @@ -135,6 +192,112 @@ static const struct attribute_group thermal_attr_group = { #define CORE_LEVEL 0 #define PACKAGE_LEVEL 1 +#define THERM_THROT_POLL_INTERVAL HZ +#define THERM_STATUS_PROCHOT_LOG BIT(1) + +#define THERM_STATUS_CLEAR_CORE_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11) | BIT(13) | BIT(15)) +#define THERM_STATUS_CLEAR_PKG_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11)) + +static void clear_therm_status_log(int level) +{ + int msr; + u64 mask, msr_val; + + if (level == CORE_LEVEL) { + msr = MSR_IA32_THERM_STATUS; + mask = THERM_STATUS_CLEAR_CORE_MASK; + } else { + msr = MSR_IA32_PACKAGE_THERM_STATUS; + mask = THERM_STATUS_CLEAR_PKG_MASK; + } + + rdmsrl(msr, msr_val); + msr_val &= mask; + wrmsrl(msr, msr_val & ~THERM_STATUS_PROCHOT_LOG); +} + +static void get_therm_status(int level, bool *proc_hot, u8 *temp) +{ + int msr; + u64 msr_val; + + if (level == CORE_LEVEL) + msr = MSR_IA32_THERM_STATUS; + else + msr = MSR_IA32_PACKAGE_THERM_STATUS; + + rdmsrl(msr, msr_val); + if (msr_val & THERM_STATUS_PROCHOT_LOG) + *proc_hot = true; + else + *proc_hot = false; + + *temp = (msr_val >> 16) & 0x7F; +} + +static void __maybe_unused throttle_active_work(struct work_struct *work) +{ + struct _thermal_state *state = container_of(to_delayed_work(work), + struct _thermal_state, therm_work); + unsigned int i, avg, this_cpu = smp_processor_id(); + u64 now = get_jiffies_64(); + bool hot; + u8 temp; + + get_therm_status(state->level, &hot, &temp); + /* temperature value is offset from the max so lesser means hotter */ + if (!hot && temp > state->baseline_temp) { + if (state->rate_control_active) + pr_info("CPU%d: %s temperature/speed normal (total events = %lu)\n", + this_cpu, + state->level == CORE_LEVEL ? "Core" : "Package", + state->count); + + state->rate_control_active = false; + return; + } + + if (time_before64(now, state->next_check) && + state->rate_control_active) + goto re_arm; + + state->next_check = now + CHECK_INTERVAL; + + if (state->count != state->last_count) { + /* There was one new thermal interrupt */ + state->last_count = state->count; + state->average = 0; + state->sample_count = 0; + state->sample_index = 0; + } + + state->temp_samples[state->sample_index] = temp; + state->sample_count++; + state->sample_index = (state->sample_index + 1) % ARRAY_SIZE(state->temp_samples); + if (state->sample_count < ARRAY_SIZE(state->temp_samples)) + goto re_arm; + + avg = 0; + for (i = 0; i < ARRAY_SIZE(state->temp_samples); ++i) + avg += state->temp_samples[i]; + + avg /= ARRAY_SIZE(state->temp_samples); + + if (state->average > avg) { + pr_warn("CPU%d: %s temperature is above threshold, cpu clock is throttled (total events = %lu)\n", + this_cpu, + state->level == CORE_LEVEL ? "Core" : "Package", + state->count); + state->rate_control_active = true; + } + + state->average = avg; + +re_arm: + clear_therm_status_log(state->level); + schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL); +} + /*** * therm_throt_process - Process thermal throttling event from interrupt * @curr: Whether the condition is current or not (boolean), since the @@ -178,27 +341,33 @@ static void therm_throt_process(bool new_event, int event, int level) if (new_event) state->count++; - if (time_before64(now, state->next_check) && - state->count != state->last_count) + if (event != THERMAL_THROTTLING_EVENT) return; - state->next_check = now + CHECK_INTERVAL; - state->last_count = state->count; + if (new_event && !state->last_interrupt_time) { + bool hot; + u8 temp; + + get_therm_status(state->level, &hot, &temp); + /* + * Ignore short temperature spike as the system is not close + * to PROCHOT. 10C offset is large enough to ignore. It is + * already dropped from the high threshold temperature. + */ + if (temp > 10) + return; - /* if we just entered the thermal event */ - if (new_event) { - if (event == THERMAL_THROTTLING_EVENT) - pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", - this_cpu, - level == CORE_LEVEL ? "Core" : "Package", - state->count); - return; - } - if (old_event) { - if (event == THERMAL_THROTTLING_EVENT) - pr_info("CPU%d: %s temperature/speed normal\n", this_cpu, - level == CORE_LEVEL ? "Core" : "Package"); - return; + state->baseline_temp = temp; + state->last_interrupt_time = now; + schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL); + } else if (old_event && state->last_interrupt_time) { + unsigned long throttle_time; + + throttle_time = jiffies_delta_to_msecs(now - state->last_interrupt_time); + if (throttle_time > state->max_time_ms) + state->max_time_ms = throttle_time; + state->total_time_ms += throttle_time; + state->last_interrupt_time = 0; } } @@ -244,20 +413,47 @@ static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu) if (err) return err; - if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) + if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) { err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_core_power_limit_count.attr, thermal_attr_group.name); + if (err) + goto del_group; + } + if (cpu_has(c, X86_FEATURE_PTS)) { err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_package_throttle_count.attr, thermal_attr_group.name); - if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) + if (err) + goto del_group; + + err = sysfs_add_file_to_group(&dev->kobj, + &dev_attr_package_throttle_max_time_ms.attr, + thermal_attr_group.name); + if (err) + goto del_group; + + err = sysfs_add_file_to_group(&dev->kobj, + &dev_attr_package_throttle_total_time_ms.attr, + thermal_attr_group.name); + if (err) + goto del_group; + + if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) { err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_package_power_limit_count.attr, thermal_attr_group.name); + if (err) + goto del_group; + } } + return 0; + +del_group: + sysfs_remove_group(&dev->kobj, &thermal_attr_group); + return err; } @@ -269,15 +465,34 @@ static void thermal_throttle_remove_dev(struct device *dev) /* Get notified when a cpu comes on/off. Be hotplug friendly. */ static int thermal_throttle_online(unsigned int cpu) { + struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + u32 l; + + state->package_throttle.level = PACKAGE_LEVEL; + state->core_throttle.level = CORE_LEVEL; + + INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work); + INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work); + + /* Unmask the thermal vector after the above workqueues are initialized. */ + l = apic_read(APIC_LVTTHMR); + apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); return thermal_throttle_add_dev(dev, cpu); } static int thermal_throttle_offline(unsigned int cpu) { + struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + cancel_delayed_work(&state->package_throttle.therm_work); + cancel_delayed_work(&state->core_throttle.therm_work); + + state->package_throttle.rate_control_active = false; + state->core_throttle.rate_control_active = false; + thermal_throttle_remove_dev(dev); return 0; } @@ -512,10 +727,6 @@ void intel_init_thermal(struct cpuinfo_x86 *c) rdmsr(MSR_IA32_MISC_ENABLE, l, h); wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h); - /* Unmask the thermal vector: */ - l = apic_read(APIC_LVTTHMR); - apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - pr_info_once("CPU0: Thermal monitoring enabled (%s)\n", tm2 ? "TM2" : "TM1"); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index a0e52bd00ecc..3f6b137ef4e6 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -567,7 +567,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) void reload_ucode_amd(void) { struct microcode_amd *mc; - u32 rev, dummy; + u32 rev, dummy __always_unused; mc = (struct microcode_amd *)amd_ucode_patch; @@ -673,7 +673,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct ucode_cpu_info *uci; struct ucode_patch *p; enum ucode_state ret; - u32 rev, dummy; + u32 rev, dummy __always_unused; BUG_ON(raw_smp_processor_id() != cpu); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index cb0fdcaf1415..7019d4b2df0c 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -63,11 +63,6 @@ LIST_HEAD(microcode_cache); */ static DEFINE_MUTEX(microcode_mutex); -/* - * Serialize late loading so that CPUs get updated one-by-one. - */ -static DEFINE_RAW_SPINLOCK(update_lock); - struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; struct cpu_info_ctx { @@ -566,11 +561,18 @@ static int __reload_late(void *info) if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC)) return -1; - raw_spin_lock(&update_lock); - apply_microcode_local(&err); - raw_spin_unlock(&update_lock); + /* + * On an SMT system, it suffices to load the microcode on one sibling of + * the core because the microcode engine is shared between the threads. + * Synchronization still needs to take place so that no concurrent + * loading attempts happen on multiple threads of an SMT core. See + * below. + */ + if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu) + apply_microcode_local(&err); + else + goto wait_for_siblings; - /* siblings return UCODE_OK because their engine got updated already */ if (err > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); ret = -1; @@ -578,14 +580,18 @@ static int __reload_late(void *info) ret = 1; } +wait_for_siblings: + if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC)) + panic("Timeout during microcode update!\n"); + /* - * Increase the wait timeout to a safe value here since we're - * serializing the microcode update and that could take a while on a - * large number of CPUs. And that is fine as the *actual* timeout will - * be determined by the last CPU finished updating and thus cut short. + * At least one thread has completed update on each core. + * For others, simply call the update to make sure the + * per-cpu cpuinfo can be updated with right microcode + * revision. */ - if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus())) - panic("Timeout during microcode update!\n"); + if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu) + apply_microcode_local(&err); return ret; } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ce799cfe9434..6a99535d7f37 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -791,6 +791,7 @@ static enum ucode_state apply_microcode_intel(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); + bool bsp = c->cpu_index == boot_cpu_data.cpu_index; struct microcode_intel *mc; enum ucode_state ret; static int prev_rev; @@ -836,7 +837,7 @@ static enum ucode_state apply_microcode_intel(int cpu) return UCODE_ERROR; } - if (rev != prev_rev) { + if (bsp && rev != prev_rev) { pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", rev, mc->hdr.date & 0xffff, @@ -852,7 +853,7 @@ out: c->microcode = rev; /* Update boot_cpu_data's revision too, if we're on the BSP: */ - if (c->cpu_index == boot_cpu_data.cpu_index) + if (bsp) boot_cpu_data.microcode = rev; return ret; diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index aed45b8895d5..1db560ed2ca3 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -6,8 +6,7 @@ set -e -IN=$1 -OUT=$2 +OUT=$1 dump_array() { @@ -15,6 +14,7 @@ dump_array() SIZE=$2 PFX=$3 POSTFIX=$4 + IN=$5 PFX_SZ=$(echo $PFX | wc -c) TABS="$(printf '\t\t\t\t\t')" @@ -57,11 +57,18 @@ trap 'rm "$OUT"' EXIT echo "#endif" echo "" - dump_array "x86_cap_flags" "NCAPINTS*32" "X86_FEATURE_" "" + dump_array "x86_cap_flags" "NCAPINTS*32" "X86_FEATURE_" "" $2 echo "" - dump_array "x86_bug_flags" "NBUGINTS*32" "X86_BUG_" "NCAPINTS*32" + dump_array "x86_bug_flags" "NBUGINTS*32" "X86_BUG_" "NCAPINTS*32" $2 + echo "" + echo "#ifdef CONFIG_X86_VMX_FEATURE_NAMES" + echo "#ifndef _ASM_X86_VMXFEATURES_H" + echo "#include <asm/vmxfeatures.h>" + echo "#endif" + dump_array "x86_vmx_flags" "NVMXINTS*32" "VMX_FEATURE_" "" $3 + echo "#endif /* CONFIG_X86_VMX_FEATURE_NAMES */" ) > $OUT trap - EXIT diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 062f77279ce3..caa032ce3fe3 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -29,6 +29,7 @@ #include <asm/timer.h> #include <asm/reboot.h> #include <asm/nmi.h> +#include <clocksource/hyperv_timer.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -215,6 +216,10 @@ static void __init ms_hyperv_init_platform(void) int hv_host_info_ecx; int hv_host_info_edx; +#ifdef CONFIG_PARAVIRT + pv_info.name = "Hyper-V"; +#endif + /* * Extract the features and hints */ @@ -285,7 +290,12 @@ static void __init ms_hyperv_init_platform(void) machine_ops.shutdown = hv_machine_shutdown; machine_ops.crash_shutdown = hv_machine_crash_shutdown; #endif - mark_tsc_unstable("running on Hyper-V"); + if (ms_hyperv.features & HV_X64_ACCESS_TSC_INVARIANT) { + wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1); + setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); + } else { + mark_tsc_unstable("running on Hyper-V"); + } /* * Generation 2 instances don't support reading the NMI status from @@ -338,6 +348,15 @@ static void __init ms_hyperv_init_platform(void) x2apic_phys = 1; # endif + /* Register Hyper-V specific clocksource */ + hv_init_clocksource(); +#endif +} + +void hv_setup_sched_clock(void *sched_clock) +{ +#ifdef CONFIG_PARAVIRT + pv_ops.time.sched_clock = sched_clock; #endif } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index aa5c064a6a22..51b9190c628b 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -15,7 +15,7 @@ #include <asm/tlbflush.h> #include <asm/mtrr.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include "mtrr.h" diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 4d36dcc1cf87..a5c506f6da7f 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -101,9 +101,6 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) int length; size_t linelen; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - memset(line, 0, LINE_SIZE); len = min_t(size_t, len, LINE_SIZE - 1); @@ -226,8 +223,6 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_ADD_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_file_add(sentry.base, sentry.size, sentry.type, true, file, 0); @@ -236,24 +231,18 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_SET_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_add(sentry.base, sentry.size, sentry.type, false); break; case MTRRIOC_DEL_ENTRY: #ifdef CONFIG_COMPAT case MTRRIOC32_DEL_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_file_del(sentry.base, sentry.size, file, 0); break; case MTRRIOC_KILL_ENTRY: #ifdef CONFIG_COMPAT case MTRRIOC32_KILL_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_del(-1, sentry.base, sentry.size); break; case MTRRIOC_GET_ENTRY: @@ -279,8 +268,6 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_ADD_PAGE_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_file_add(sentry.base, sentry.size, sentry.type, true, file, 1); @@ -289,8 +276,6 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_SET_PAGE_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_add_page(sentry.base, sentry.size, sentry.type, false); break; @@ -298,16 +283,12 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_DEL_PAGE_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_file_del(sentry.base, sentry.size, file, 1); break; case MTRRIOC_KILL_PAGE_ENTRY: #ifdef CONFIG_COMPAT case MTRRIOC32_KILL_PAGE_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_del_page(-1, sentry.base, sentry.size); break; case MTRRIOC_GET_PAGE_ENTRY: @@ -373,28 +354,6 @@ static int mtrr_close(struct inode *ino, struct file *file) return single_release(ino, file); } -static int mtrr_seq_show(struct seq_file *seq, void *offset); - -static int mtrr_open(struct inode *inode, struct file *file) -{ - if (!mtrr_if) - return -EIO; - if (!mtrr_if->get) - return -ENXIO; - return single_open(file, mtrr_seq_show, NULL); -} - -static const struct file_operations mtrr_fops = { - .owner = THIS_MODULE, - .open = mtrr_open, - .read = seq_read, - .llseek = seq_lseek, - .write = mtrr_write, - .unlocked_ioctl = mtrr_ioctl, - .compat_ioctl = mtrr_ioctl, - .release = mtrr_close, -}; - static int mtrr_seq_show(struct seq_file *seq, void *offset) { char factor; @@ -426,6 +385,29 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset) return 0; } +static int mtrr_open(struct inode *inode, struct file *file) +{ + if (!mtrr_if) + return -EIO; + if (!mtrr_if->get) + return -ENXIO; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + return single_open(file, mtrr_seq_show, NULL); +} + +static const struct proc_ops mtrr_proc_ops = { + .proc_open = mtrr_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = mtrr_write, + .proc_ioctl = mtrr_ioctl, +#ifdef CONFIG_COMPAT + .proc_compat_ioctl = mtrr_ioctl, +#endif + .proc_release = mtrr_close, +}; + static int __init mtrr_if_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -436,7 +418,7 @@ static int __init mtrr_if_init(void) (!cpu_has(c, X86_FEATURE_CENTAUR_MCR))) return -ENODEV; - proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops); + proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_proc_ops); return 0; } arch_initcall(mtrr_if_init); diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 507039c20128..6a80f36b5d59 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -52,7 +52,7 @@ #include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include "mtrr.h" diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index cb2e49810d68..4eec8889b0ff 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -7,6 +7,10 @@ #include "cpu.h" +#ifdef CONFIG_X86_VMX_FEATURE_NAMES +extern const char * const x86_vmx_flags[NVMXINTS*32]; +#endif + /* * Get CPU information for use by the procfs. */ @@ -102,6 +106,17 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has(c, i) && x86_cap_flags[i] != NULL) seq_printf(m, " %s", x86_cap_flags[i]); +#ifdef CONFIG_X86_VMX_FEATURE_NAMES + if (cpu_has(c, X86_FEATURE_VMX) && c->vmx_capability[0]) { + seq_puts(m, "\nvmx flags\t:"); + for (i = 0; i < 32*NVMXINTS; i++) { + if (test_bit(i, (unsigned long *)c->vmx_capability) && + x86_vmx_flags[i] != NULL) + seq_printf(m, " %s", x86_vmx_flags[i]); + } + } +#endif + seq_puts(m, "\nbugs\t\t:"); for (i = 0; i < 32*NBUGINTS; i++) { unsigned int bug_bit = 32*NCAPINTS + i; diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 5c900f9527ff..c4be62058dd9 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -29,7 +29,8 @@ __setup("nordrand", x86_rdrand_setup); #ifdef CONFIG_ARCH_RANDOM void x86_init_rdrand(struct cpuinfo_x86 *c) { - unsigned long tmp; + unsigned int changed = 0; + unsigned long tmp, prev; int i; if (!cpu_has(c, X86_FEATURE_RDRAND)) @@ -42,5 +43,24 @@ void x86_init_rdrand(struct cpuinfo_x86 *c) return; } } + + /* + * Stupid sanity-check whether RDRAND does *actually* generate + * some at least random-looking data. + */ + prev = tmp; + for (i = 0; i < SANITY_CHECK_LOOPS; i++) { + if (rdrand_long(&tmp)) { + if (prev != tmp) + changed++; + + prev = tmp; + } + } + + if (WARN_ON_ONCE(!changed)) + pr_emerg( +"RDRAND gives funky smelling output, might consider not using it by booting with \"nordrand\""); + } #endif diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 03eb90d00af0..89049b343c7a 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -618,7 +618,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) if (static_branch_unlikely(&rdt_mon_enable_key)) rmdir_mondata_subdir_allrdtgrp(r, d->id); list_del(&d->list); - if (is_mbm_enabled()) + if (r->mon_capable && is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { /* diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index efbd54cc4e69..055c8613b531 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -522,6 +522,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto out; + } md.priv = of->kn->priv; resid = md.u.rid; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index e49b77283924..181c992f448c 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -57,6 +57,7 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) } DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); /** * struct mon_evt - Entry in the event list of a resource diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 397206f23d14..773124b0e18a 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -514,7 +514,7 @@ void mbm_handle_overflow(struct work_struct *work) mutex_lock(&rdtgroup_mutex); - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); @@ -543,7 +543,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) return; cpu = cpumask_any(&dom->cpu_mask); dom->mbm_work_cpu = cpu; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index a46dee8e78db..064e9ef44cd6 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -461,10 +461,8 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, } rdtgrp = rdtgroup_kn_lock_live(of->kn); - rdt_last_cmd_clear(); if (!rdtgrp) { ret = -ENOENT; - rdt_last_cmd_puts("Directory was removed\n"); goto unlock; } @@ -534,11 +532,15 @@ static void move_myself(struct callback_head *head) kfree(rdtgrp); } + if (unlikely(current->flags & PF_EXITING)) + goto out; + preempt_disable(); /* update PQR_ASSOC MSR to make resource group go into effect */ resctrl_sched_in(); preempt_enable(); +out: kfree(callback); } @@ -727,6 +729,92 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, return ret; } +#ifdef CONFIG_PROC_CPU_RESCTRL + +/* + * A task can only be part of one resctrl control group and of one monitor + * group which is associated to that control group. + * + * 1) res: + * mon: + * + * resctrl is not available. + * + * 2) res:/ + * mon: + * + * Task is part of the root resctrl control group, and it is not associated + * to any monitor group. + * + * 3) res:/ + * mon:mon0 + * + * Task is part of the root resctrl control group and monitor group mon0. + * + * 4) res:group0 + * mon: + * + * Task is part of resctrl control group group0, and it is not associated + * to any monitor group. + * + * 5) res:group0 + * mon:mon1 + * + * Task is part of resctrl control group group0 and monitor group mon1. + */ +int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) +{ + struct rdtgroup *rdtg; + int ret = 0; + + mutex_lock(&rdtgroup_mutex); + + /* Return empty if resctrl has not been mounted. */ + if (!static_branch_unlikely(&rdt_enable_key)) { + seq_puts(s, "res:\nmon:\n"); + goto unlock; + } + + list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) { + struct rdtgroup *crg; + + /* + * Task information is only relevant for shareable + * and exclusive groups. + */ + if (rdtg->mode != RDT_MODE_SHAREABLE && + rdtg->mode != RDT_MODE_EXCLUSIVE) + continue; + + if (rdtg->closid != tsk->closid) + continue; + + seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "", + rdtg->kn->name); + seq_puts(s, "mon:"); + list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, + mon.crdtgrp_list) { + if (tsk->rmid != crg->mon.rmid) + continue; + seq_printf(s, "%s", crg->kn->name); + break; + } + seq_putc(s, '\n'); + goto unlock; + } + /* + * The above search should succeed. Otherwise return + * with an error. + */ + ret = -ENOENT; +unlock: + mutex_unlock(&rdtgroup_mutex); + + return ret; +} +#endif + static int rdt_last_cmd_status_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -1743,9 +1831,6 @@ static int set_cache_qos_cfg(int level, bool enable) struct rdt_domain *d; int cpu; - if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) - return -ENOMEM; - if (level == RDT_RESOURCE_L3) update = l3_qos_cfg_update; else if (level == RDT_RESOURCE_L2) @@ -1753,6 +1838,9 @@ static int set_cache_qos_cfg(int level, bool enable) else return -EINVAL; + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + r_l = &rdt_resources_all[level]; list_for_each_entry(d, &r_l->domains, list) { /* Pick one CPU from each domain instance to update MSR */ @@ -1972,7 +2060,7 @@ static int rdt_get_tree(struct fs_context *fc) if (rdt_mon_capable) { ret = mongroup_create_dir(rdtgroup_default.kn, - NULL, "mon_groups", + &rdtgroup_default, "mon_groups", &kn_mongrp); if (ret < 0) goto out_info; @@ -2039,25 +2127,20 @@ enum rdt_param { nr__rdt_params }; -static const struct fs_parameter_spec rdt_param_specs[] = { +static const struct fs_parameter_spec rdt_fs_parameters[] = { fsparam_flag("cdp", Opt_cdp), fsparam_flag("cdpl2", Opt_cdpl2), fsparam_flag("mba_MBps", Opt_mba_mbps), {} }; -static const struct fs_parameter_description rdt_fs_parameters = { - .name = "rdt", - .specs = rdt_param_specs, -}; - static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct rdt_fs_context *ctx = rdt_fc2context(fc); struct fs_parse_result result; int opt; - opt = fs_parse(fc, &rdt_fs_parameters, param, &result); + opt = fs_parse(fc, rdt_fs_parameters, param, &result); if (opt < 0) return opt; @@ -2207,7 +2290,11 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { free_rmid(sentry->mon.rmid); list_del(&sentry->mon.crdtgrp_list); - kfree(sentry); + + if (atomic_read(&sentry->waitcount) != 0) + sentry->flags = RDT_DELETED; + else + kfree(sentry); } } @@ -2245,7 +2332,11 @@ static void rmdir_all_sub(void) kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); - kfree(rdtgrp); + + if (atomic_read(&rdtgrp->waitcount) != 0) + rdtgrp->flags = RDT_DELETED; + else + kfree(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); @@ -2282,7 +2373,7 @@ static void rdt_kill_sb(struct super_block *sb) static struct file_system_type rdt_fs_type = { .name = "resctrl", .init_fs_context = rdt_init_fs_context, - .parameters = &rdt_fs_parameters, + .parameters = rdt_fs_parameters, .kill_sb = rdt_kill_sb, }; @@ -2448,7 +2539,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, /* * Create the mon_data directory first. */ - ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn); + ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn); if (ret) return ret; @@ -2638,7 +2729,6 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) } static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, - struct kernfs_node *prgrp_kn, const char *name, umode_t mode, enum rdt_group_type rtype, struct rdtgroup **r) { @@ -2647,11 +2737,9 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, uint files = 0; int ret; - prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); - rdt_last_cmd_clear(); + prdtgrp = rdtgroup_kn_lock_live(parent_kn); if (!prdtgrp) { ret = -ENODEV; - rdt_last_cmd_puts("Directory was removed\n"); goto out_unlock; } @@ -2722,7 +2810,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, kernfs_activate(kn); /* - * The caller unlocks the prgrp_kn upon success. + * The caller unlocks the parent_kn upon success. */ return 0; @@ -2733,7 +2821,7 @@ out_destroy: out_free_rgrp: kfree(rdtgrp); out_unlock: - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2750,15 +2838,12 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) * to monitor a subset of tasks and cpus in its parent ctrl_mon group. */ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, - struct kernfs_node *prgrp_kn, - const char *name, - umode_t mode) + const char *name, umode_t mode) { struct rdtgroup *rdtgrp, *prgrp; int ret; - ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTMON_GROUP, - &rdtgrp); + ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTMON_GROUP, &rdtgrp); if (ret) return ret; @@ -2771,7 +2856,7 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, */ list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2780,7 +2865,6 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, * to allocate and monitor resources. */ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, - struct kernfs_node *prgrp_kn, const char *name, umode_t mode) { struct rdtgroup *rdtgrp; @@ -2788,8 +2872,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, u32 closid; int ret; - ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTCTRL_GROUP, - &rdtgrp); + ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTCTRL_GROUP, &rdtgrp); if (ret) return ret; @@ -2814,7 +2897,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, * Create an empty mon_groups directory to hold the subset * of tasks and cpus to monitor. */ - ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); + ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL); if (ret) { rdt_last_cmd_puts("kernfs subdir error\n"); goto out_del_list; @@ -2830,7 +2913,7 @@ out_id_free: out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); out_unlock: - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2863,14 +2946,14 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, * subdirectory */ if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn) - return rdtgroup_mkdir_ctrl_mon(parent_kn, parent_kn, name, mode); + return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode); /* * If RDT monitoring is supported and the parent directory is a valid * "mon_groups" directory, add a monitoring subdirectory. */ if (rdt_mon_capable && is_mon_groups(parent_kn, name)) - return rdtgroup_mkdir_mon(parent_kn, parent_kn->parent, name, mode); + return rdtgroup_mkdir_mon(parent_kn, name, mode); return -EPERM; } @@ -2956,13 +3039,13 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, closid_free(rdtgrp->closid); free_rmid(rdtgrp->mon.rmid); + rdtgroup_ctrl_remove(kn, rdtgrp); + /* * Free all the child monitor group rmids. */ free_all_child_rdtgrp(rdtgrp); - rdtgroup_ctrl_remove(kn, rdtgrp); - return 0; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index adf9b71386ef..62b137c3c97a 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -4,7 +4,7 @@ */ #include <linux/cpu.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/apic.h> #include <asm/processor.h> diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index ee48c3fc8a65..d3a0791bc052 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -7,7 +7,7 @@ #include <linux/cpu.h> #include <asm/apic.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/processor.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c new file mode 100644 index 000000000000..e2ad30e474f8 --- /dev/null +++ b/arch/x86/kernel/cpu/tsx.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Transactional Synchronization Extensions (TSX) control. + * + * Copyright (C) 2019 Intel Corporation + * + * Author: + * Pawan Gupta <pawan.kumar.gupta@linux.intel.com> + */ + +#include <linux/cpufeature.h> + +#include <asm/cmdline.h> + +#include "cpu.h" + +#undef pr_fmt +#define pr_fmt(fmt) "tsx: " fmt + +enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; + +void tsx_disable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Force all transactions to immediately abort */ + tsx |= TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is not enumerated in CPUID. + * This is visible to userspace and will ensure they + * do not waste resources trying TSX transactions that + * will always abort. + */ + tsx |= TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +void tsx_enable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Enable the RTM feature in the cpu */ + tsx &= ~TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is enumerated in CPUID. + * This is visible to userspace and will ensure they + * can enumerate and use the TSX feature. + */ + tsx &= ~TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +static bool __init tsx_ctrl_is_supported(void) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); +} + +static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) +{ + if (boot_cpu_has_bug(X86_BUG_TAA)) + return TSX_CTRL_DISABLE; + + return TSX_CTRL_ENABLE; +} + +void __init tsx_init(void) +{ + char arg[5] = {}; + int ret; + + if (!tsx_ctrl_is_supported()) + return; + + ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg)); + if (ret >= 0) { + if (!strcmp(arg, "on")) { + tsx_ctrl_state = TSX_CTRL_ENABLE; + } else if (!strcmp(arg, "off")) { + tsx_ctrl_state = TSX_CTRL_DISABLE; + } else if (!strcmp(arg, "auto")) { + tsx_ctrl_state = x86_get_tsx_auto_mode(); + } else { + tsx_ctrl_state = TSX_CTRL_DISABLE; + pr_err("invalid option, defaulting to off\n"); + } + } else { + /* tsx= not provided */ + if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO)) + tsx_ctrl_state = x86_get_tsx_auto_mode(); + else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF)) + tsx_ctrl_state = TSX_CTRL_DISABLE; + else + tsx_ctrl_state = TSX_CTRL_ENABLE; + } + + if (tsx_ctrl_state == TSX_CTRL_DISABLE) { + tsx_disable(); + + /* + * tsx_disable() will change the state of the RTM and HLE CPUID + * bits. Clear them here since they are now expected to be not + * set. + */ + setup_clear_cpu_cap(X86_FEATURE_RTM); + setup_clear_cpu_cap(X86_FEATURE_HLE); + } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { + + /* + * HW defaults TSX to be enabled at bootup. + * We may still need the TSX enable support + * during init for special cases like + * kexec after TSX is disabled. + */ + tsx_enable(); + + /* + * tsx_enable() will change the state of the RTM and HLE CPUID + * bits. Force them here since they are now expected to be set. + */ + setup_force_cpu_cap(X86_FEATURE_RTM); + setup_force_cpu_cap(X86_FEATURE_HLE); + } +} diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c index 32b4dc9030aa..c222f283b456 100644 --- a/arch/x86/kernel/cpu/umwait.c +++ b/arch/x86/kernel/cpu/umwait.c @@ -17,6 +17,12 @@ */ static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE); +u32 get_umwait_control_msr(void) +{ + return umwait_control_cached; +} +EXPORT_SYMBOL_GPL(get_umwait_control_msr); + /* * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by * hardware or BIOS before kernel boot. diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 3c648476d4fb..46d732696c1c 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -30,34 +30,69 @@ #include <asm/hypervisor.h> #include <asm/timer.h> #include <asm/apic.h> +#include <asm/vmware.h> #undef pr_fmt #define pr_fmt(fmt) "vmware: " fmt -#define CPUID_VMWARE_INFO_LEAF 0x40000000 +#define CPUID_VMWARE_INFO_LEAF 0x40000000 +#define CPUID_VMWARE_FEATURES_LEAF 0x40000010 +#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0) +#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1) + #define VMWARE_HYPERVISOR_MAGIC 0x564D5868 -#define VMWARE_HYPERVISOR_PORT 0x5658 -#define VMWARE_PORT_CMD_GETVERSION 10 -#define VMWARE_PORT_CMD_GETHZ 45 -#define VMWARE_PORT_CMD_GETVCPU_INFO 68 -#define VMWARE_PORT_CMD_LEGACY_X2APIC 3 -#define VMWARE_PORT_CMD_VCPU_RESERVED 31 +#define VMWARE_CMD_GETVERSION 10 +#define VMWARE_CMD_GETHZ 45 +#define VMWARE_CMD_GETVCPU_INFO 68 +#define VMWARE_CMD_LEGACY_X2APIC 3 +#define VMWARE_CMD_VCPU_RESERVED 31 #define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \ - __asm__("inl (%%dx)" : \ - "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ - "0"(VMWARE_HYPERVISOR_MAGIC), \ - "1"(VMWARE_PORT_CMD_##cmd), \ - "2"(VMWARE_HYPERVISOR_PORT), "3"(UINT_MAX) : \ - "memory"); + __asm__("inl (%%dx), %%eax" : \ + "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ + "a"(VMWARE_HYPERVISOR_MAGIC), \ + "c"(VMWARE_CMD_##cmd), \ + "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) : \ + "memory") + +#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \ + __asm__("vmcall" : \ + "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ + "a"(VMWARE_HYPERVISOR_MAGIC), \ + "c"(VMWARE_CMD_##cmd), \ + "d"(0), "b"(UINT_MAX) : \ + "memory") + +#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx) \ + __asm__("vmmcall" : \ + "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ + "a"(VMWARE_HYPERVISOR_MAGIC), \ + "c"(VMWARE_CMD_##cmd), \ + "d"(0), "b"(UINT_MAX) : \ + "memory") + +#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do { \ + switch (vmware_hypercall_mode) { \ + case CPUID_VMWARE_FEATURES_ECX_VMCALL: \ + VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \ + break; \ + case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \ + VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx); \ + break; \ + default: \ + VMWARE_PORT(cmd, eax, ebx, ecx, edx); \ + break; \ + } \ + } while (0) static unsigned long vmware_tsc_khz __ro_after_init; +static u8 vmware_hypercall_mode __ro_after_init; static inline int __vmware_platform(void) { uint32_t eax, ebx, ecx, edx; - VMWARE_PORT(GETVERSION, eax, ebx, ecx, edx); + VMWARE_CMD(GETVERSION, eax, ebx, ecx, edx); return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC; } @@ -129,6 +164,10 @@ static void __init vmware_set_capabilities(void) { setup_force_cpu_cap(X86_FEATURE_CONSTANT_TSC); setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); + if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMCALL) + setup_force_cpu_cap(X86_FEATURE_VMCALL); + else if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMMCALL) + setup_force_cpu_cap(X86_FEATURE_VMW_VMMCALL); } static void __init vmware_platform_setup(void) @@ -136,7 +175,7 @@ static void __init vmware_platform_setup(void) uint32_t eax, ebx, ecx, edx; uint64_t lpj, tsc_khz; - VMWARE_PORT(GETHZ, eax, ebx, ecx, edx); + VMWARE_CMD(GETHZ, eax, ebx, ecx, edx); if (ebx != UINT_MAX) { lpj = tsc_khz = eax | (((uint64_t)ebx) << 32); @@ -174,10 +213,21 @@ static void __init vmware_platform_setup(void) vmware_set_capabilities(); } +static u8 vmware_select_hypercall(void) +{ + int eax, ebx, ecx, edx; + + cpuid(CPUID_VMWARE_FEATURES_LEAF, &eax, &ebx, &ecx, &edx); + return (ecx & (CPUID_VMWARE_FEATURES_ECX_VMMCALL | + CPUID_VMWARE_FEATURES_ECX_VMCALL)); +} + /* * While checking the dmi string information, just checking the product * serial key should be enough, as this will always have a VMware * specific string when running under VMware hypervisor. + * If !boot_cpu_has(X86_FEATURE_HYPERVISOR), vmware_hypercall_mode + * intentionally defaults to 0. */ static uint32_t __init vmware_platform(void) { @@ -187,8 +237,16 @@ static uint32_t __init vmware_platform(void) cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &hyper_vendor_id[0], &hyper_vendor_id[1], &hyper_vendor_id[2]); - if (!memcmp(hyper_vendor_id, "VMwareVMware", 12)) + if (!memcmp(hyper_vendor_id, "VMwareVMware", 12)) { + if (eax >= CPUID_VMWARE_FEATURES_LEAF) + vmware_hypercall_mode = + vmware_select_hypercall(); + + pr_info("hypercall mode: 0x%02x\n", + (unsigned int) vmware_hypercall_mode); + return CPUID_VMWARE_INFO_LEAF; + } } else if (dmi_available && dmi_name_in_serial("VMware") && __vmware_platform()) return 1; @@ -200,9 +258,9 @@ static uint32_t __init vmware_platform(void) static bool __init vmware_legacy_x2apic_available(void) { uint32_t eax, ebx, ecx, edx; - VMWARE_PORT(GETVCPU_INFO, eax, ebx, ecx, edx); - return (eax & (1 << VMWARE_PORT_CMD_VCPU_RESERVED)) == 0 && - (eax & (1 << VMWARE_PORT_CMD_LEGACY_X2APIC)) != 0; + VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx); + return (eax & (1 << VMWARE_CMD_VCPU_RESERVED)) == 0 && + (eax & (1 << VMWARE_CMD_LEGACY_X2APIC)) != 0; } const __initconst struct hypervisor_x86 x86_hyper_vmware = { diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index 8e6f2f4b4afe..df1358ba622b 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -16,13 +16,6 @@ #define RNG_ENABLED (1 << 3) #define RNG_ENABLE (1 << 8) /* MSR_ZHAOXIN_RNG */ -#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000 -#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000 -#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000 -#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 -#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 -#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 - static void init_zhaoxin_cap(struct cpuinfo_x86 *c) { u32 lo, hi; @@ -58,8 +51,6 @@ static void init_zhaoxin_cap(struct cpuinfo_x86 *c) if (c->x86 >= 0x6) set_cpu_cap(c, X86_FEATURE_REP_GOOD); - - cpu_detect_cache_sizes(c); } static void early_init_zhaoxin(struct cpuinfo_x86 *c) @@ -89,31 +80,6 @@ static void early_init_zhaoxin(struct cpuinfo_x86 *c) } -static void zhaoxin_detect_vmx_virtcap(struct cpuinfo_x86 *c) -{ - u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; - - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); - msr_ctl = vmx_msr_high | vmx_msr_low; - - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW) - set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI) - set_cpu_cap(c, X86_FEATURE_VNMI); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) { - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - vmx_msr_low, vmx_msr_high); - msr_ctl2 = vmx_msr_high | vmx_msr_low; - if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && - (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) - set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) - set_cpu_cap(c, X86_FEATURE_EPT); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) - set_cpu_cap(c, X86_FEATURE_VPID); - } -} - static void init_zhaoxin(struct cpuinfo_x86 *c) { early_init_zhaoxin(c); @@ -141,8 +107,7 @@ static void init_zhaoxin(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); #endif - if (cpu_has(c, X86_FEATURE_VMX)) - zhaoxin_detect_vmx_virtcap(c); + init_ia32_feat_ctl(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 2bf70a2fed90..fd87b59452a3 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -24,6 +24,7 @@ #include <linux/export.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/memblock.h> #include <asm/processor.h> #include <asm/hardirq.h> @@ -39,6 +40,7 @@ #include <asm/virtext.h> #include <asm/intel_pt.h> #include <asm/crash.h> +#include <asm/cmdline.h> /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { @@ -68,6 +70,19 @@ static inline void cpu_crash_vmclear_loaded_vmcss(void) rcu_read_unlock(); } +/* + * When the crashkernel option is specified, only use the low + * 1M for the real mode trampoline. + */ +void __init crash_reserve_low_1M(void) +{ + if (cmdline_find_option(boot_command_line, "crashkernel", NULL, 0) < 0) + return; + + memblock_reserve(0, 1<<20); + pr_info("Reserving the low 1M of memory for crashkernel\n"); +} + #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) @@ -173,8 +188,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_KEXEC_FILE -static unsigned long crash_zero_bytes; - static int get_nr_ram_ranges_callback(struct resource *res, void *arg) { unsigned int *nr_ranges = arg; @@ -189,8 +202,7 @@ static struct crash_mem *fill_up_crash_elf_data(void) unsigned int nr_ranges = 0; struct crash_mem *cmem; - walk_system_ram_res(0, -1, &nr_ranges, - get_nr_ram_ranges_callback); + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); if (!nr_ranges) return NULL; @@ -217,17 +229,19 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem) { int ret = 0; + /* Exclude the low 1M because it is always reserved */ + ret = crash_exclude_mem_range(cmem, 0, 1<<20); + if (ret) + return ret; + /* Exclude crashkernel region */ ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); if (ret) return ret; - if (crashk_low_res.end) { + if (crashk_low_res.end) ret = crash_exclude_mem_range(cmem, crashk_low_res.start, - crashk_low_res.end); - if (ret) - return ret; - } + crashk_low_res.end); return ret; } @@ -248,16 +262,13 @@ static int prepare_elf_headers(struct kimage *image, void **addr, unsigned long *sz) { struct crash_mem *cmem; - Elf64_Ehdr *ehdr; - Elf64_Phdr *phdr; - int ret, i; + int ret; cmem = fill_up_crash_elf_data(); if (!cmem) return -ENOMEM; - ret = walk_system_ram_res(0, -1, cmem, - prepare_elf64_ram_headers_callback); + ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); if (ret) goto out; @@ -267,24 +278,8 @@ static int prepare_elf_headers(struct kimage *image, void **addr, goto out; /* By default prepare 64bit headers */ - ret = crash_prepare_elf64_headers(cmem, - IS_ENABLED(CONFIG_X86_64), addr, sz); - if (ret) - goto out; + ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); - /* - * If a range matches backup region, adjust offset to backup - * segment. - */ - ehdr = (Elf64_Ehdr *)*addr; - phdr = (Elf64_Phdr *)(ehdr + 1); - for (i = 0; i < ehdr->e_phnum; phdr++, i++) - if (phdr->p_type == PT_LOAD && - phdr->p_paddr == image->arch.backup_src_start && - phdr->p_memsz == image->arch.backup_src_sz) { - phdr->p_offset = image->arch.backup_load_addr; - break; - } out: vfree(cmem); return ret; @@ -298,8 +293,7 @@ static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE) return 1; - memcpy(¶ms->e820_table[nr_e820_entries], entry, - sizeof(struct e820_entry)); + memcpy(¶ms->e820_table[nr_e820_entries], entry, sizeof(struct e820_entry)); params->e820_entries++; return 0; } @@ -323,19 +317,11 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, unsigned long long mend) { unsigned long start, end; - int ret = 0; cmem->ranges[0].start = mstart; cmem->ranges[0].end = mend; cmem->nr_ranges = 1; - /* Exclude Backup region */ - start = image->arch.backup_load_addr; - end = start + image->arch.backup_src_sz - 1; - ret = crash_exclude_mem_range(cmem, start, end); - if (ret) - return ret; - /* Exclude elf header region */ start = image->arch.elf_load_addr; end = start + image->arch.elf_headers_sz - 1; @@ -358,40 +344,39 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) memset(&cmd, 0, sizeof(struct crash_memmap_data)); cmd.params = params; - /* Add first 640K segment */ - ei.addr = image->arch.backup_src_start; - ei.size = image->arch.backup_src_sz; - ei.type = E820_TYPE_RAM; - add_e820_entry(params, &ei); + /* Add the low 1M */ + cmd.type = E820_TYPE_RAM; + flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + walk_iomem_res_desc(IORES_DESC_NONE, flags, 0, (1<<20)-1, &cmd, + memmap_entry_callback); /* Add ACPI tables */ cmd.type = E820_TYPE_ACPI; flags = IORESOURCE_MEM | IORESOURCE_BUSY; walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd, - memmap_entry_callback); + memmap_entry_callback); /* Add ACPI Non-volatile Storage */ cmd.type = E820_TYPE_NVS; walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd, - memmap_entry_callback); + memmap_entry_callback); /* Add e820 reserved ranges */ cmd.type = E820_TYPE_RESERVED; flags = IORESOURCE_MEM; walk_iomem_res_desc(IORES_DESC_RESERVED, flags, 0, -1, &cmd, - memmap_entry_callback); + memmap_entry_callback); /* Add crashk_low_res region */ if (crashk_low_res.end) { ei.addr = crashk_low_res.start; - ei.size = crashk_low_res.end - crashk_low_res.start + 1; + ei.size = resource_size(&crashk_low_res); ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } /* Exclude some ranges from crashk_res and add rest to memmap */ - ret = memmap_exclude_ranges(image, cmem, crashk_res.start, - crashk_res.end); + ret = memmap_exclude_ranges(image, cmem, crashk_res.start, crashk_res.end); if (ret) goto out; @@ -411,55 +396,12 @@ out: return ret; } -static int determine_backup_region(struct resource *res, void *arg) -{ - struct kimage *image = arg; - - image->arch.backup_src_start = res->start; - image->arch.backup_src_sz = resource_size(res); - - /* Expecting only one range for backup region */ - return 1; -} - int crash_load_segments(struct kimage *image) { int ret; struct kexec_buf kbuf = { .image = image, .buf_min = 0, .buf_max = ULONG_MAX, .top_down = false }; - /* - * Determine and load a segment for backup area. First 640K RAM - * region is backup source - */ - - ret = walk_system_ram_res(KEXEC_BACKUP_SRC_START, KEXEC_BACKUP_SRC_END, - image, determine_backup_region); - - /* Zero or postive return values are ok */ - if (ret < 0) - return ret; - - /* Add backup segment. */ - if (image->arch.backup_src_sz) { - kbuf.buffer = &crash_zero_bytes; - kbuf.bufsz = sizeof(crash_zero_bytes); - kbuf.memsz = image->arch.backup_src_sz; - kbuf.buf_align = PAGE_SIZE; - /* - * Ideally there is no source for backup segment. This is - * copied in purgatory after crash. Just add a zero filled - * segment for now to make sure checksum logic works fine. - */ - ret = kexec_add_buffer(&kbuf); - if (ret) - return ret; - image->arch.backup_load_addr = kbuf.mem; - pr_debug("Loaded backup region at 0x%lx backup_start=0x%lx memsz=0x%lx\n", - image->arch.backup_load_addr, - image->arch.backup_src_start, kbuf.memsz); - } - /* Prepare elf headers and add a segment */ ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz); if (ret) diff --git a/arch/x86/kernel/crash_core_32.c b/arch/x86/kernel/crash_core_32.c new file mode 100644 index 000000000000..c0159a7bca6d --- /dev/null +++ b/arch/x86/kernel/crash_core_32.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/crash_core.h> + +#include <asm/pgtable.h> +#include <asm/setup.h> + +void arch_crash_save_vmcoreinfo(void) +{ +#ifdef CONFIG_NUMA + VMCOREINFO_SYMBOL(node_data); + VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); +#endif +#ifdef CONFIG_X86_PAE + VMCOREINFO_CONFIG(X86_PAE); +#endif +} diff --git a/arch/x86/kernel/crash_core_64.c b/arch/x86/kernel/crash_core_64.c new file mode 100644 index 000000000000..845a57eb4eb7 --- /dev/null +++ b/arch/x86/kernel/crash_core_64.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/crash_core.h> + +#include <asm/pgtable.h> +#include <asm/setup.h> + +void arch_crash_save_vmcoreinfo(void) +{ + u64 sme_mask = sme_me_mask; + + VMCOREINFO_NUMBER(phys_base); + VMCOREINFO_SYMBOL(init_top_pgt); + vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n", + pgtable_l5_enabled()); + +#ifdef CONFIG_NUMA + VMCOREINFO_SYMBOL(node_data); + VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); +#endif + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); + VMCOREINFO_NUMBER(sme_mask); +} diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index 22369dd5de3b..045e82e8945b 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -70,3 +70,8 @@ ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize, { return __copy_oldmem_page(pfn, buf, csize, offset, userbuf, true); } + +ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) +{ + return read_from_oldmem(buf, count, ppos, 0, sev_active()); +} diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c deleted file mode 100644 index 0b8cedb20d6d..000000000000 --- a/arch/x86/kernel/doublefault.c +++ /dev/null @@ -1,83 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/mm.h> -#include <linux/sched.h> -#include <linux/sched/debug.h> -#include <linux/init_task.h> -#include <linux/fs.h> - -#include <linux/uaccess.h> -#include <asm/pgtable.h> -#include <asm/processor.h> -#include <asm/desc.h> - -#ifdef CONFIG_X86_32 - -#define DOUBLEFAULT_STACKSIZE (1024) -static unsigned long doublefault_stack[DOUBLEFAULT_STACKSIZE]; -#define STACK_START (unsigned long)(doublefault_stack+DOUBLEFAULT_STACKSIZE) - -#define ptr_ok(x) ((x) > PAGE_OFFSET && (x) < PAGE_OFFSET + MAXMEM) - -static void doublefault_fn(void) -{ - struct desc_ptr gdt_desc = {0, 0}; - unsigned long gdt, tss; - - native_store_gdt(&gdt_desc); - gdt = gdt_desc.address; - - printk(KERN_EMERG "PANIC: double fault, gdt at %08lx [%d bytes]\n", gdt, gdt_desc.size); - - if (ptr_ok(gdt)) { - gdt += GDT_ENTRY_TSS << 3; - tss = get_desc_base((struct desc_struct *)gdt); - printk(KERN_EMERG "double fault, tss at %08lx\n", tss); - - if (ptr_ok(tss)) { - struct x86_hw_tss *t = (struct x86_hw_tss *)tss; - - printk(KERN_EMERG "eip = %08lx, esp = %08lx\n", - t->ip, t->sp); - - printk(KERN_EMERG "eax = %08lx, ebx = %08lx, ecx = %08lx, edx = %08lx\n", - t->ax, t->bx, t->cx, t->dx); - printk(KERN_EMERG "esi = %08lx, edi = %08lx\n", - t->si, t->di); - } - } - - for (;;) - cpu_relax(); -} - -struct x86_hw_tss doublefault_tss __cacheline_aligned = { - .sp0 = STACK_START, - .ss0 = __KERNEL_DS, - .ldt = 0, - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, - - .ip = (unsigned long) doublefault_fn, - /* 0x2 bit is always set */ - .flags = X86_EFLAGS_SF | 0x2, - .sp = STACK_START, - .es = __USER_DS, - .cs = __KERNEL_CS, - .ss = __KERNEL_DS, - .ds = __USER_DS, - .fs = __KERNEL_PERCPU, - - .__cr3 = __pa_nodebug(swapper_pg_dir), -}; - -/* dummy for do_double_fault() call */ -void df_debug(struct pt_regs *regs, long error_code) {} - -#else /* !CONFIG_X86_32 */ - -void df_debug(struct pt_regs *regs, long error_code) -{ - pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code); - show_regs(regs); - panic("Machine halted."); -} -#endif diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c new file mode 100644 index 000000000000..3793646f0fb5 --- /dev/null +++ b/arch/x86/kernel/doublefault_32.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/init_task.h> +#include <linux/fs.h> + +#include <linux/uaccess.h> +#include <asm/pgtable.h> +#include <asm/processor.h> +#include <asm/desc.h> +#include <asm/traps.h> + +extern void double_fault(void); +#define ptr_ok(x) ((x) > PAGE_OFFSET && (x) < PAGE_OFFSET + MAXMEM) + +#define TSS(x) this_cpu_read(cpu_tss_rw.x86_tss.x) + +static void set_df_gdt_entry(unsigned int cpu); + +/* + * Called by double_fault with CR0.TS and EFLAGS.NT cleared. The CPU thinks + * we're running the doublefault task. Cannot return. + */ +asmlinkage notrace void __noreturn doublefault_shim(void) +{ + unsigned long cr2; + struct pt_regs regs; + + BUILD_BUG_ON(sizeof(struct doublefault_stack) != PAGE_SIZE); + + cr2 = native_read_cr2(); + + /* Reset back to the normal kernel task. */ + force_reload_TR(); + set_df_gdt_entry(smp_processor_id()); + + trace_hardirqs_off(); + + /* + * Fill in pt_regs. A downside of doing this in C is that the unwinder + * won't see it (no ENCODE_FRAME_POINTER), so a nested stack dump + * won't successfully unwind to the source of the double fault. + * The main dump from do_double_fault() is fine, though, since it + * uses these regs directly. + * + * If anyone ever cares, this could be moved to asm. + */ + regs.ss = TSS(ss); + regs.__ssh = 0; + regs.sp = TSS(sp); + regs.flags = TSS(flags); + regs.cs = TSS(cs); + /* We won't go through the entry asm, so we can leave __csh as 0. */ + regs.__csh = 0; + regs.ip = TSS(ip); + regs.orig_ax = 0; + regs.gs = TSS(gs); + regs.__gsh = 0; + regs.fs = TSS(fs); + regs.__fsh = 0; + regs.es = TSS(es); + regs.__esh = 0; + regs.ds = TSS(ds); + regs.__dsh = 0; + regs.ax = TSS(ax); + regs.bp = TSS(bp); + regs.di = TSS(di); + regs.si = TSS(si); + regs.dx = TSS(dx); + regs.cx = TSS(cx); + regs.bx = TSS(bx); + + do_double_fault(®s, 0, cr2); + + /* + * x86_32 does not save the original CR3 anywhere on a task switch. + * This means that, even if we wanted to return, we would need to find + * some way to reconstruct CR3. We could make a credible guess based + * on cpu_tlbstate, but that would be racy and would not account for + * PTI. + * + * Instead, don't bother. We can return through + * rewind_stack_do_exit() instead. + */ + panic("cannot return from double fault\n"); +} +NOKPROBE_SYMBOL(doublefault_shim); + +DEFINE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack) = { + .tss = { + /* + * No sp0 or ss0 -- we never run CPL != 0 with this TSS + * active. sp is filled in later. + */ + .ldt = 0, + .io_bitmap_base = IO_BITMAP_OFFSET_INVALID, + + .ip = (unsigned long) double_fault, + .flags = X86_EFLAGS_FIXED, + .es = __USER_DS, + .cs = __KERNEL_CS, + .ss = __KERNEL_DS, + .ds = __USER_DS, + .fs = __KERNEL_PERCPU, +#ifndef CONFIG_X86_32_LAZY_GS + .gs = __KERNEL_STACK_CANARY, +#endif + + .__cr3 = __pa_nodebug(swapper_pg_dir), + }, +}; + +static void set_df_gdt_entry(unsigned int cpu) +{ + /* Set up doublefault TSS pointer in the GDT */ + __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, + &get_cpu_entry_area(cpu)->doublefault_stack.tss); + +} + +void doublefault_init_cpu_tss(void) +{ + unsigned int cpu = smp_processor_id(); + struct cpu_entry_area *cea = get_cpu_entry_area(cpu); + + /* + * The linker isn't smart enough to initialize percpu variables that + * point to other places in percpu space. + */ + this_cpu_write(doublefault_stack.tss.sp, + (unsigned long)&cea->doublefault_stack.stack + + sizeof(doublefault_stack.stack)); + + set_df_gdt_entry(cpu); +} diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 2b5886401e5f..ae64ec7f752f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -365,21 +365,30 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) } NOKPROBE_SYMBOL(oops_end); -int __die(const char *str, struct pt_regs *regs, long err) +static void __die_header(const char *str, struct pt_regs *regs, long err) { + const char *pr = ""; + /* Save the regs of the first oops for the executive summary later. */ if (!die_counter) exec_summary_regs = *regs; + if (IS_ENABLED(CONFIG_PREEMPTION)) + pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT"; + printk(KERN_DEFAULT "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter, - IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", + pr, IS_ENABLED(CONFIG_SMP) ? " SMP" : "", debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "", IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ? (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : ""); +} +NOKPROBE_SYMBOL(__die_header); +static int __die_body(const char *str, struct pt_regs *regs, long err) +{ show_regs(regs); print_modules(); @@ -389,6 +398,13 @@ int __die(const char *str, struct pt_regs *regs, long err) return 0; } +NOKPROBE_SYMBOL(__die_body); + +int __die(const char *str, struct pt_regs *regs, long err) +{ + __die_header(str, regs, err); + return __die_body(str, regs, err); +} NOKPROBE_SYMBOL(__die); /* @@ -405,6 +421,19 @@ void die(const char *str, struct pt_regs *regs, long err) oops_end(flags, regs, sig); } +void die_addr(const char *str, struct pt_regs *regs, long err, long gp_addr) +{ + unsigned long flags = oops_begin(); + int sig = SIGSEGV; + + __die_header(str, regs, err); + if (gp_addr) + kasan_non_canonical_hook(gp_addr); + if (__die_body(str, regs, err)) + sig = 0; + oops_end(flags, regs, sig); +} + void show_regs(struct pt_regs *regs) { show_regs_print_info(KERN_DEFAULT); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 64a59d726639..8e3a8fedfa4d 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -29,6 +29,9 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_ENTRY) return "ENTRY_TRAMPOLINE"; + if (type == STACK_TYPE_EXCEPTION) + return "#DF"; + return NULL; } @@ -82,6 +85,30 @@ static bool in_softirq_stack(unsigned long *stack, struct stack_info *info) return true; } +static bool in_doublefault_stack(unsigned long *stack, struct stack_info *info) +{ +#ifdef CONFIG_DOUBLEFAULT + struct cpu_entry_area *cea = get_cpu_entry_area(raw_smp_processor_id()); + struct doublefault_stack *ss = &cea->doublefault_stack; + + void *begin = ss->stack; + void *end = begin + sizeof(ss->stack); + + if ((void *)stack < begin || (void *)stack >= end) + return false; + + info->type = STACK_TYPE_EXCEPTION; + info->begin = begin; + info->end = end; + info->next_sp = (unsigned long *)this_cpu_read(cpu_tss_rw.x86_tss.sp); + + return true; +#else + return false; +#endif +} + + int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask) { @@ -105,6 +132,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (in_softirq_stack(stack, info)) goto recursion_check; + if (in_doublefault_stack(stack, info)) + goto recursion_check; + goto unknown; recursion_check: diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 753b8cfe8b8a..87b97897a881 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -94,6 +94,13 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); begin = (unsigned long)__this_cpu_read(cea_exception_stacks); + /* + * Handle the case where stack trace is collected _before_ + * cea_exception_stacks had been initialized. + */ + if (!begin) + return false; + end = begin + sizeof(struct cea_exception_stacks); /* Bail if @stack is outside the exception stack area. */ if (stk < begin || stk >= end) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 7da2bcd2b8eb..c5399e80c59c 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -190,6 +190,7 @@ static void __init e820_print_type(enum e820_type type) case E820_TYPE_RAM: /* Fall through: */ case E820_TYPE_RESERVED_KERN: pr_cont("usable"); break; case E820_TYPE_RESERVED: pr_cont("reserved"); break; + case E820_TYPE_SOFT_RESERVED: pr_cont("soft reserved"); break; case E820_TYPE_ACPI: pr_cont("ACPI data"); break; case E820_TYPE_NVS: pr_cont("ACPI NVS"); break; case E820_TYPE_UNUSABLE: pr_cont("unusable"); break; @@ -999,6 +1000,17 @@ void __init e820__reserve_setup_data(void) data = early_memremap(pa_data, sizeof(*data)); e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); e820__range_update_kexec(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + + if (data->type == SETUP_INDIRECT && + ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { + e820__range_update(((struct setup_indirect *)data->data)->addr, + ((struct setup_indirect *)data->data)->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + e820__range_update_kexec(((struct setup_indirect *)data->data)->addr, + ((struct setup_indirect *)data->data)->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + } + pa_data = data->next; early_memunmap(data, sizeof(*data)); } @@ -1037,6 +1049,7 @@ static const char *__init e820_type_to_string(struct e820_entry *entry) case E820_TYPE_PRAM: return "Persistent Memory (legacy)"; case E820_TYPE_PMEM: return "Persistent Memory"; case E820_TYPE_RESERVED: return "Reserved"; + case E820_TYPE_SOFT_RESERVED: return "Soft Reserved"; default: return "Unknown E820 type"; } } @@ -1052,6 +1065,7 @@ static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry) case E820_TYPE_PRAM: /* Fall-through: */ case E820_TYPE_PMEM: /* Fall-through: */ case E820_TYPE_RESERVED: /* Fall-through: */ + case E820_TYPE_SOFT_RESERVED: /* Fall-through: */ default: return IORESOURCE_MEM; } } @@ -1064,6 +1078,7 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry) case E820_TYPE_PMEM: return IORES_DESC_PERSISTENT_MEMORY; case E820_TYPE_PRAM: return IORES_DESC_PERSISTENT_MEMORY_LEGACY; case E820_TYPE_RESERVED: return IORES_DESC_RESERVED; + case E820_TYPE_SOFT_RESERVED: return IORES_DESC_SOFT_RESERVED; case E820_TYPE_RESERVED_KERN: /* Fall-through: */ case E820_TYPE_RAM: /* Fall-through: */ case E820_TYPE_UNUSABLE: /* Fall-through: */ @@ -1078,11 +1093,12 @@ static bool __init do_mark_busy(enum e820_type type, struct resource *res) return true; /* - * Treat persistent memory like device memory, i.e. reserve it - * for exclusive use of a driver + * Treat persistent memory and other special memory ranges like + * device memory, i.e. reserve it for exclusive use of a driver */ switch (type) { case E820_TYPE_RESERVED: + case E820_TYPE_SOFT_RESERVED: case E820_TYPE_PRAM: case E820_TYPE_PMEM: return false; @@ -1285,6 +1301,9 @@ void __init e820__memblock_setup(void) if (end != (resource_size_t)end) continue; + if (entry->type == E820_TYPE_SOFT_RESERVED) + memblock_reserve(entry->addr, entry->size); + if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN) continue; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6c4f01540833..2f9ec14be3b1 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -549,6 +549,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_CNL_IDS(&gen9_early_ops), INTEL_ICL_11_IDS(&gen11_early_ops), INTEL_EHL_IDS(&gen11_early_ops), + INTEL_TGL_12_IDS(&gen11_early_ops), }; struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0); @@ -709,6 +710,12 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3e20, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3ec4, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x8a12, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 0071b794ed19..400a05e1c1c5 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -352,6 +352,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_unlock(); return 0; } + fpregs_deactivate(fpu); fpregs_unlock(); } @@ -403,6 +404,8 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } if (!ret) fpregs_mark_activate(); + else + fpregs_deactivate(fpu); fpregs_unlock(); err_out: diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index e5cb67d67c03..a1806598aaa4 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -60,7 +60,7 @@ u64 xfeatures_mask __read_mostly; static unsigned int xstate_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_sizes[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; -static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8]; +static unsigned int xstate_comp_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; /* * The XSAVE area of kernel can be in standard or compacted format; @@ -107,23 +107,20 @@ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) } EXPORT_SYMBOL_GPL(cpu_has_xfeatures); -static int xfeature_is_supervisor(int xfeature_nr) +static bool xfeature_is_supervisor(int xfeature_nr) { /* - * We currently do not support supervisor states, but if - * we did, we could find out like this. - * - * SDM says: If state component 'i' is a user state component, - * ECX[0] return 0; if state component i is a supervisor - * state component, ECX[0] returns 1. + * Extended State Enumeration Sub-leaves (EAX = 0DH, ECX = n, n > 1) + * returns ECX[0] set to (1) for a supervisor state, and cleared (0) + * for a user state. */ u32 eax, ebx, ecx, edx; cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); - return !!(ecx & 1); + return ecx & 1; } -static int xfeature_is_user(int xfeature_nr) +static bool xfeature_is_user(int xfeature_nr) { return !xfeature_is_supervisor(xfeature_nr); } @@ -254,10 +251,13 @@ static void __init setup_xstate_features(void) * in the fixed offsets in the xsave area in either compacted form * or standard form. */ - xstate_offsets[0] = 0; - xstate_sizes[0] = offsetof(struct fxregs_state, xmm_space); - xstate_offsets[1] = xstate_sizes[0]; - xstate_sizes[1] = FIELD_SIZEOF(struct fxregs_state, xmm_space); + xstate_offsets[XFEATURE_FP] = 0; + xstate_sizes[XFEATURE_FP] = offsetof(struct fxregs_state, + xmm_space); + + xstate_offsets[XFEATURE_SSE] = xstate_sizes[XFEATURE_FP]; + xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state, + xmm_space); for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { if (!xfeature_enabled(i)) @@ -342,7 +342,7 @@ static int xfeature_is_aligned(int xfeature_nr) */ static void __init setup_xstate_comp(void) { - unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8]; + unsigned int xstate_comp_sizes[XFEATURE_MAX]; int i; /* @@ -350,8 +350,9 @@ static void __init setup_xstate_comp(void) * in the fixed offsets in the xsave area in either compacted form * or standard form. */ - xstate_comp_offsets[0] = 0; - xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space); + xstate_comp_offsets[XFEATURE_FP] = 0; + xstate_comp_offsets[XFEATURE_SSE] = offsetof(struct fxregs_state, + xmm_space); if (!boot_cpu_has(X86_FEATURE_XSAVES)) { for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { @@ -415,7 +416,8 @@ static void __init setup_init_fpu_buf(void) print_xstate_features(); if (boot_cpu_has(X86_FEATURE_XSAVES)) - init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask; + init_fpstate.xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | + xfeatures_mask; /* * Init all the features state with header.xfeatures being 0x0 @@ -840,7 +842,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) /* * We should not ever be requesting features that we - * have not enabled. Remember that pcntxt_mask is + * have not enabled. Remember that xfeatures_mask is * what we write to the XCR0 register. */ WARN_ONCE(!(xfeatures_mask & BIT_ULL(xfeature_nr)), diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 024c3053dbba..37a0aeaf89e7 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -23,6 +23,7 @@ #include <linux/list.h> #include <linux/module.h> #include <linux/memory.h> +#include <linux/vmalloc.h> #include <trace/syscall.h> @@ -34,6 +35,8 @@ #ifdef CONFIG_DYNAMIC_FTRACE +static int ftrace_poke_late = 0; + int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) { @@ -43,84 +46,37 @@ int ftrace_arch_code_modify_prepare(void) * ftrace has it set to "read/write". */ mutex_lock(&text_mutex); - set_kernel_text_rw(); - set_all_modules_text_rw(); + ftrace_poke_late = 1; return 0; } int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) { - set_all_modules_text_ro(); - set_kernel_text_ro(); + /* + * ftrace_make_{call,nop}() may be called during + * module load, and we need to finish the text_poke_queue() + * that they do, here. + */ + text_poke_finish(); + ftrace_poke_late = 0; mutex_unlock(&text_mutex); return 0; } -union ftrace_code_union { - char code[MCOUNT_INSN_SIZE]; - struct { - unsigned char op; - int offset; - } __attribute__((packed)); -}; - -static int ftrace_calc_offset(long ip, long addr) -{ - return (int)(addr - ip); -} - -static unsigned char * -ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr) +static const char *ftrace_nop_replace(void) { - static union ftrace_code_union calc; - - calc.op = op; - calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - - return calc.code; -} - -static unsigned char * -ftrace_call_replace(unsigned long ip, unsigned long addr) -{ - return ftrace_text_replace(0xe8, ip, addr); -} - -static inline int -within(unsigned long addr, unsigned long start, unsigned long end) -{ - return addr >= start && addr < end; + return ideal_nops[NOP_ATOMIC5]; } -static unsigned long text_ip_addr(unsigned long ip) +static const char *ftrace_call_replace(unsigned long ip, unsigned long addr) { - /* - * On x86_64, kernel text mappings are mapped read-only, so we use - * the kernel identity mapping instead of the kernel text mapping - * to modify the kernel text. - * - * For 32bit kernels, these mappings are same and we can use - * kernel identity mapping to modify code. - */ - if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa_symbol(ip)); - - return ip; + return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr); } -static const unsigned char *ftrace_nop_replace(void) +static int ftrace_verify_code(unsigned long ip, const char *old_code) { - return ideal_nops[NOP_ATOMIC5]; -} - -static int -ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code) -{ - unsigned char replaced[MCOUNT_INSN_SIZE]; - - ftrace_expected = old_code; + char cur_code[MCOUNT_INSN_SIZE]; /* * Note: @@ -129,31 +85,46 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, * Carefully read and modify the code with probe_kernel_*(), and make * sure what we read is what we expected it to be before modifying it. */ - /* read the text we want to modify */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { + WARN_ON(1); return -EFAULT; + } /* Make sure it is what we expect it to be */ - if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + if (memcmp(cur_code, old_code, MCOUNT_INSN_SIZE) != 0) { + WARN_ON(1); return -EINVAL; + } - ip = text_ip_addr(ip); - - /* replace the text with the new text */ - if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) - return -EPERM; + return 0; +} - sync_core(); +/* + * Marked __ref because it calls text_poke_early() which is .init.text. That is + * ok because that call will happen early, during boot, when .init sections are + * still present. + */ +static int __ref +ftrace_modify_code_direct(unsigned long ip, const char *old_code, + const char *new_code) +{ + int ret = ftrace_verify_code(ip, old_code); + if (ret) + return ret; + /* replace the text with the new text */ + if (ftrace_poke_late) + text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL); + else + text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE); return 0; } -int ftrace_make_nop(struct module *mod, - struct dyn_ftrace *rec, unsigned long addr) +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned const char *new, *old; unsigned long ip = rec->ip; + const char *new, *old; old = ftrace_call_replace(ip, addr); new = ftrace_nop_replace(); @@ -167,19 +138,20 @@ int ftrace_make_nop(struct module *mod, * just modify the code directly. */ if (addr == MCOUNT_ADDR) - return ftrace_modify_code_direct(rec->ip, old, new); + return ftrace_modify_code_direct(ip, old, new); - ftrace_expected = NULL; - - /* Normal cases use add_brk_on_nop */ + /* + * x86 overrides ftrace_replace_code -- this function will never be used + * in this case. + */ WARN_ONCE(1, "invalid use of ftrace_make_nop"); return -EINVAL; } int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned const char *new, *old; unsigned long ip = rec->ip; + const char *new, *old; old = ftrace_nop_replace(); new = ftrace_call_replace(ip, addr); @@ -189,43 +161,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) } /* - * The modifying_ftrace_code is used to tell the breakpoint - * handler to call ftrace_int3_handler(). If it fails to - * call this handler for a breakpoint added by ftrace, then - * the kernel may crash. - * - * As atomic_writes on x86 do not need a barrier, we do not - * need to add smp_mb()s for this to work. It is also considered - * that we can not read the modifying_ftrace_code before - * executing the breakpoint. That would be quite remarkable if - * it could do that. Here's the flow that is required: - * - * CPU-0 CPU-1 - * - * atomic_inc(mfc); - * write int3s - * <trap-int3> // implicit (r)mb - * if (atomic_read(mfc)) - * call ftrace_int3_handler() - * - * Then when we are finished: - * - * atomic_dec(mfc); - * - * If we hit a breakpoint that was not set by ftrace, it does not - * matter if ftrace_int3_handler() is called or not. It will - * simply be ignored. But it is crucial that a ftrace nop/caller - * breakpoint is handled. No other user should ever place a - * breakpoint on an ftrace nop/caller location. It must only - * be done by this code. - */ -atomic_t modifying_ftrace_code __read_mostly; - -static int -ftrace_modify_code(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code); - -/* * Should never be called: * As it is only called by __ftrace_replace_code() which is called by * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() @@ -237,452 +172,84 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { WARN_ON(1); - ftrace_expected = NULL; return -EINVAL; } -static unsigned long ftrace_update_func; -static unsigned long ftrace_update_func_call; - -static int update_ftrace_func(unsigned long ip, void *new) -{ - unsigned char old[MCOUNT_INSN_SIZE]; - int ret; - - memcpy(old, (void *)ip, MCOUNT_INSN_SIZE); - - ftrace_update_func = ip; - /* Make sure the breakpoints see the ftrace_update_func update */ - smp_wmb(); - - /* See comment above by declaration of modifying_ftrace_code */ - atomic_inc(&modifying_ftrace_code); - - ret = ftrace_modify_code(ip, old, new); - - atomic_dec(&modifying_ftrace_code); - - return ret; -} - int ftrace_update_ftrace_func(ftrace_func_t func) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char *new; - int ret; - - ftrace_update_func_call = (unsigned long)func; - - new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - - /* Also update the regs callback function */ - if (!ret) { - ip = (unsigned long)(&ftrace_regs_call); - new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - } - - return ret; -} - -static nokprobe_inline int is_ftrace_caller(unsigned long ip) -{ - if (ip == ftrace_update_func) - return 1; - - return 0; -} - -/* - * A breakpoint was added to the code address we are about to - * modify, and this is the handle that will just skip over it. - * We are either changing a nop into a trace call, or a trace - * call to a nop. While the change is taking place, we treat - * it just like it was a nop. - */ -int ftrace_int3_handler(struct pt_regs *regs) -{ unsigned long ip; + const char *new; - if (WARN_ON_ONCE(!regs)) - return 0; - - ip = regs->ip - INT3_INSN_SIZE; - - if (ftrace_location(ip)) { - int3_emulate_call(regs, (unsigned long)ftrace_regs_caller); - return 1; - } else if (is_ftrace_caller(ip)) { - if (!ftrace_update_func_call) { - int3_emulate_jmp(regs, ip + CALL_INSN_SIZE); - return 1; - } - int3_emulate_call(regs, ftrace_update_func_call); - return 1; - } - - return 0; -} -NOKPROBE_SYMBOL(ftrace_int3_handler); - -static int ftrace_write(unsigned long ip, const char *val, int size) -{ - ip = text_ip_addr(ip); - - if (probe_kernel_write((void *)ip, val, size)) - return -EPERM; - - return 0; -} - -static int add_break(unsigned long ip, const char *old) -{ - unsigned char replaced[MCOUNT_INSN_SIZE]; - unsigned char brk = BREAKPOINT_INSTRUCTION; - - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; - - ftrace_expected = old; - - /* Make sure it is what we expect it to be */ - if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0) - return -EINVAL; - - return ftrace_write(ip, &brk, 1); -} - -static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned const char *old; - unsigned long ip = rec->ip; - - old = ftrace_call_replace(ip, addr); - - return add_break(rec->ip, old); -} - - -static int add_brk_on_nop(struct dyn_ftrace *rec) -{ - unsigned const char *old; - - old = ftrace_nop_replace(); - - return add_break(rec->ip, old); -} - -static int add_breakpoints(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ftrace_addr = ftrace_get_addr_curr(rec); - - ret = ftrace_test_record(rec, enable); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return add_brk_on_nop(rec); - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return add_brk_on_call(rec, ftrace_addr); - } - return 0; -} - -/* - * On error, we need to remove breakpoints. This needs to - * be done caefully. If the address does not currently have a - * breakpoint, we know we are done. Otherwise, we look at the - * remaining 4 bytes of the instruction. If it matches a nop - * we replace the breakpoint with the nop. Otherwise we replace - * it with the call instruction. - */ -static int remove_breakpoint(struct dyn_ftrace *rec) -{ - unsigned char ins[MCOUNT_INSN_SIZE]; - unsigned char brk = BREAKPOINT_INSTRUCTION; - const unsigned char *nop; - unsigned long ftrace_addr; - unsigned long ip = rec->ip; - - /* If we fail the read, just give up */ - if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; - - /* If this does not have a breakpoint, we are done */ - if (ins[0] != brk) - return 0; - - nop = ftrace_nop_replace(); - - /* - * If the last 4 bytes of the instruction do not match - * a nop, then we assume that this is a call to ftrace_addr. - */ - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) { - /* - * For extra paranoidism, we check if the breakpoint is on - * a call that would actually jump to the ftrace_addr. - * If not, don't touch the breakpoint, we make just create - * a disaster. - */ - ftrace_addr = ftrace_get_addr_new(rec); - nop = ftrace_call_replace(ip, ftrace_addr); - - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) - goto update; - - /* Check both ftrace_addr and ftrace_old_addr */ - ftrace_addr = ftrace_get_addr_curr(rec); - nop = ftrace_call_replace(ip, ftrace_addr); - - ftrace_expected = nop; - - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) - return -EINVAL; - } - - update: - return ftrace_write(ip, nop, 1); -} - -static int add_update_code(unsigned long ip, unsigned const char *new) -{ - /* skip breakpoint */ - ip++; - new++; - return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1); -} - -static int add_update_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_call_replace(ip, addr); - return add_update_code(ip, new); -} - -static int add_update_nop(struct dyn_ftrace *rec) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_nop_replace(); - return add_update_code(ip, new); -} - -static int add_update(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ret = ftrace_test_record(rec, enable); - - ftrace_addr = ftrace_get_addr_new(rec); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return add_update_call(rec, ftrace_addr); - - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return add_update_nop(rec); - } - - return 0; -} - -static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_call_replace(ip, addr); - - return ftrace_write(ip, new, 1); -} - -static int finish_update_nop(struct dyn_ftrace *rec) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_nop_replace(); - - return ftrace_write(ip, new, 1); -} - -static int finish_update(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ret = ftrace_update_record(rec, enable); - - ftrace_addr = ftrace_get_addr_new(rec); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return finish_update_call(rec, ftrace_addr); + ip = (unsigned long)(&ftrace_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return finish_update_nop(rec); - } + ip = (unsigned long)(&ftrace_regs_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); return 0; } -static void do_sync_core(void *data) -{ - sync_core(); -} - -static void run_sync(void) -{ - int enable_irqs; - - /* No need to sync if there's only one CPU */ - if (num_online_cpus() == 1) - return; - - enable_irqs = irqs_disabled(); - - /* We may be called with interrupts disabled (on bootup). */ - if (enable_irqs) - local_irq_enable(); - on_each_cpu(do_sync_core, NULL, 1); - if (enable_irqs) - local_irq_disable(); -} - void ftrace_replace_code(int enable) { struct ftrace_rec_iter *iter; struct dyn_ftrace *rec; - const char *report = "adding breakpoints"; - int count = 0; + const char *new, *old; int ret; for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); - ret = add_breakpoints(rec, enable); - if (ret) - goto remove_breakpoints; - count++; - } - - run_sync(); + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; - report = "updating code"; - count = 0; + case FTRACE_UPDATE_MAKE_CALL: + old = ftrace_nop_replace(); + break; - for_ftrace_rec_iter(iter) { - rec = ftrace_rec_iter_record(iter); + case FTRACE_UPDATE_MODIFY_CALL: + case FTRACE_UPDATE_MAKE_NOP: + old = ftrace_call_replace(rec->ip, ftrace_get_addr_curr(rec)); + break; + } - ret = add_update(rec, enable); - if (ret) - goto remove_breakpoints; - count++; + ret = ftrace_verify_code(rec->ip, old); + if (ret) { + ftrace_bug(ret, rec); + return; + } } - run_sync(); - - report = "removing breakpoints"; - count = 0; - for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); - ret = finish_update(rec, enable); - if (ret) - goto remove_breakpoints; - count++; - } + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; - run_sync(); + case FTRACE_UPDATE_MAKE_CALL: + case FTRACE_UPDATE_MODIFY_CALL: + new = ftrace_call_replace(rec->ip, ftrace_get_addr_new(rec)); + break; - return; + case FTRACE_UPDATE_MAKE_NOP: + new = ftrace_nop_replace(); + break; + } - remove_breakpoints: - pr_warn("Failed on %s (%d):\n", report, count); - ftrace_bug(ret, rec); - for_ftrace_rec_iter(iter) { - rec = ftrace_rec_iter_record(iter); - /* - * Breakpoints are handled only when this function is in - * progress. The system could not work with them. - */ - if (remove_breakpoint(rec)) - BUG(); + text_poke_queue((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL); + ftrace_update_record(rec, enable); } - run_sync(); -} - -static int -ftrace_modify_code(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code) -{ - int ret; - - ret = add_break(ip, old_code); - if (ret) - goto out; - - run_sync(); - - ret = add_update_code(ip, new_code); - if (ret) - goto fail_update; - - run_sync(); - - ret = ftrace_write(ip, new_code, 1); - /* - * The breakpoint is handled only when this function is in progress. - * The system could not work if we could not remove it. - */ - BUG_ON(ret); - out: - run_sync(); - return ret; - - fail_update: - /* Also here the system could not work with the breakpoint */ - if (ftrace_write(ip, old_code, 1)) - BUG(); - goto out; + text_poke_finish(); } void arch_ftrace_update_code(int command) { - /* See comment above by declaration of modifying_ftrace_code */ - atomic_inc(&modifying_ftrace_code); - ftrace_modify_all_code(command); - - atomic_dec(&modifying_ftrace_code); } int __init ftrace_dyn_arch_init(void) @@ -747,6 +314,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) unsigned long start_offset; unsigned long end_offset; unsigned long op_offset; + unsigned long call_offset; unsigned long offset; unsigned long npages; unsigned long size; @@ -763,10 +331,12 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) start_offset = (unsigned long)ftrace_regs_caller; end_offset = (unsigned long)ftrace_regs_caller_end; op_offset = (unsigned long)ftrace_regs_caller_op_ptr; + call_offset = (unsigned long)ftrace_regs_call; } else { start_offset = (unsigned long)ftrace_caller; end_offset = (unsigned long)ftrace_epilogue; op_offset = (unsigned long)ftrace_caller_op_ptr; + call_offset = (unsigned long)ftrace_call; } size = end_offset - start_offset; @@ -823,16 +393,21 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* put in the new offset to the ftrace_ops */ memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE); + /* put in the call to the function */ + mutex_lock(&text_mutex); + call_offset -= start_offset; + memcpy(trampoline + call_offset, + text_gen_insn(CALL_INSN_OPCODE, + trampoline + call_offset, + ftrace_ops_get_func(ops)), CALL_INSN_SIZE); + mutex_unlock(&text_mutex); + /* ALLOC_TRAMP flags lets us know we created it */ ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP; set_vm_flush_reset_perms(trampoline); - /* - * Module allocation needs to be completed by making the page - * executable. The page is still writable, which is a security hazard, - * but anyhow ftrace breaks W^X completely. - */ + set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); return (unsigned long)trampoline; fail: @@ -859,62 +434,54 @@ static unsigned long calc_trampoline_call_offset(bool save_regs) void arch_ftrace_update_trampoline(struct ftrace_ops *ops) { ftrace_func_t func; - unsigned char *new; unsigned long offset; unsigned long ip; unsigned int size; - int ret, npages; + const char *new; - if (ops->trampoline) { - /* - * The ftrace_ops caller may set up its own trampoline. - * In such a case, this code must not modify it. - */ - if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) - return; - npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT; - set_memory_rw(ops->trampoline, npages); - } else { + if (!ops->trampoline) { ops->trampoline = create_trampoline(ops, &size); if (!ops->trampoline) return; ops->trampoline_size = size; - npages = PAGE_ALIGN(size) >> PAGE_SHIFT; + return; } + /* + * The ftrace_ops caller may set up its own trampoline. + * In such a case, this code must not modify it. + */ + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return; + offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); ip = ops->trampoline + offset; - func = ftrace_ops_get_func(ops); - ftrace_update_func_call = (unsigned long)func; - + mutex_lock(&text_mutex); /* Do a safe modify in case the trampoline is executing */ new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - set_memory_ro(ops->trampoline, npages); - - /* The update should never fail */ - WARN_ON(ret); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + mutex_unlock(&text_mutex); } /* Return the address of the function the trampoline calls */ static void *addr_from_call(void *ptr) { - union ftrace_code_union calc; + union text_poke_insn call; int ret; - ret = probe_kernel_read(&calc, ptr, MCOUNT_INSN_SIZE); + ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE); if (WARN_ON_ONCE(ret < 0)) return NULL; /* Make sure this is a call */ - if (WARN_ON_ONCE(calc.op != 0xe8)) { - pr_warn("Expected e8, got %x\n", calc.op); + if (WARN_ON_ONCE(call.opcode != CALL_INSN_OPCODE)) { + pr_warn("Expected E8, got %x\n", call.opcode); return NULL; } - return ptr + MCOUNT_INSN_SIZE + calc.offset; + return ptr + CALL_INSN_SIZE + call.disp; } void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, @@ -981,19 +548,18 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); -static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) +static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { - return ftrace_text_replace(0xe9, ip, addr); + return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr); } static int ftrace_mod_jmp(unsigned long ip, void *func) { - unsigned char *new; + const char *new; - ftrace_update_func_call = 0UL; new = ftrace_jmp_replace(ip, (unsigned long)func); - - return update_ftrace_func(ip, new); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + return 0; } int ftrace_enable_ftrace_graph_caller(void) @@ -1019,10 +585,9 @@ int ftrace_disable_ftrace_graph_caller(void) void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer) { + unsigned long return_hooker = (unsigned long)&return_to_handler; unsigned long old; int faulted; - unsigned long return_hooker = (unsigned long) - &return_to_handler; /* * When resuming from suspend-to-ram, this function can be indirectly diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index 073aab525d80..e8a9f8370112 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -12,20 +12,18 @@ #include <asm/frame.h> #include <asm/asm-offsets.h> -# define function_hook __fentry__ -EXPORT_SYMBOL(__fentry__) - #ifdef CONFIG_FRAME_POINTER # define MCOUNT_FRAME 1 /* using frame = true */ #else # define MCOUNT_FRAME 0 /* using frame = false */ #endif -ENTRY(function_hook) +SYM_FUNC_START(__fentry__) ret -END(function_hook) +SYM_FUNC_END(__fentry__) +EXPORT_SYMBOL(__fentry__) -ENTRY(ftrace_caller) +SYM_CODE_START(ftrace_caller) #ifdef CONFIG_FRAME_POINTER /* @@ -85,11 +83,11 @@ ftrace_graph_call: #endif /* This is weak to keep gas from relaxing the jumps */ -WEAK(ftrace_stub) +SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) ret -END(ftrace_caller) +SYM_CODE_END(ftrace_caller) -ENTRY(ftrace_regs_caller) +SYM_CODE_START(ftrace_regs_caller) /* * We're here from an mcount/fentry CALL, and the stack frame looks like: * @@ -138,7 +136,7 @@ ENTRY(ftrace_regs_caller) movl function_trace_op, %ecx # 3rd argument: ftrace_pos pushl %esp # 4th argument: pt_regs -GLOBAL(ftrace_regs_call) +SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) call ftrace_stub addl $4, %esp # skip 4th argument @@ -163,9 +161,10 @@ GLOBAL(ftrace_regs_call) popl %eax jmp .Lftrace_ret +SYM_CODE_END(ftrace_regs_caller) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) +SYM_CODE_START(ftrace_graph_caller) pushl %eax pushl %ecx pushl %edx @@ -179,7 +178,7 @@ ENTRY(ftrace_graph_caller) popl %ecx popl %eax ret -END(ftrace_graph_caller) +SYM_CODE_END(ftrace_graph_caller) .globl return_to_handler return_to_handler: diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 809d54397dba..369e61faacfe 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -14,9 +14,6 @@ .code64 .section .entry.text, "ax" -# define function_hook __fentry__ -EXPORT_SYMBOL(__fentry__) - #ifdef CONFIG_FRAME_POINTER /* Save parent and function stack frames (rip and rbp) */ # define MCOUNT_FRAME_SIZE (8+16*2) @@ -88,6 +85,7 @@ EXPORT_SYMBOL(__fentry__) movq %rdi, RDI(%rsp) movq %r8, R8(%rsp) movq %r9, R9(%rsp) + movq $0, ORIG_RAX(%rsp) /* * Save the original RBP. Even though the mcount ABI does not * require this, it helps out callers. @@ -114,7 +112,11 @@ EXPORT_SYMBOL(__fentry__) subq $MCOUNT_INSN_SIZE, %rdi .endm -.macro restore_mcount_regs +.macro restore_mcount_regs save=0 + + /* ftrace_regs_caller or frame pointers require this */ + movq RBP(%rsp), %rbp + movq R9(%rsp), %r9 movq R8(%rsp), %r8 movq RDI(%rsp), %rdi @@ -123,31 +125,29 @@ EXPORT_SYMBOL(__fentry__) movq RCX(%rsp), %rcx movq RAX(%rsp), %rax - /* ftrace_regs_caller can modify %rbp */ - movq RBP(%rsp), %rbp - - addq $MCOUNT_REG_SIZE, %rsp + addq $MCOUNT_REG_SIZE-\save, %rsp .endm #ifdef CONFIG_DYNAMIC_FTRACE -ENTRY(function_hook) +SYM_FUNC_START(__fentry__) retq -ENDPROC(function_hook) +SYM_FUNC_END(__fentry__) +EXPORT_SYMBOL(__fentry__) -ENTRY(ftrace_caller) +SYM_FUNC_START(ftrace_caller) /* save_mcount_regs fills in first two parameters */ save_mcount_regs -GLOBAL(ftrace_caller_op_ptr) +SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL) /* Load the ftrace_ops into the 3rd parameter */ movq function_trace_op(%rip), %rdx /* regs go into 4th parameter (but make it NULL) */ movq $0, %rcx -GLOBAL(ftrace_call) +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) call ftrace_stub restore_mcount_regs @@ -157,10 +157,10 @@ GLOBAL(ftrace_call) * think twice before adding any new code or changing the * layout here. */ -GLOBAL(ftrace_epilogue) +SYM_INNER_LABEL(ftrace_epilogue, SYM_L_GLOBAL) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -GLOBAL(ftrace_graph_call) +SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) jmp ftrace_stub #endif @@ -168,19 +168,21 @@ GLOBAL(ftrace_graph_call) * This is weak to keep gas from relaxing the jumps. * It is also used to copy the retq for trampolines. */ -WEAK(ftrace_stub) +SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) retq -ENDPROC(ftrace_caller) +SYM_FUNC_END(ftrace_caller) -ENTRY(ftrace_regs_caller) +SYM_FUNC_START(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ pushfq + UNWIND_HINT_SAVE + /* added 8 bytes to save flags */ save_mcount_regs 8 /* save_mcount_regs fills in first two parameters */ -GLOBAL(ftrace_regs_caller_op_ptr) +SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL) /* Load the ftrace_ops into the 3rd parameter */ movq function_trace_op(%rip), %rdx @@ -209,7 +211,7 @@ GLOBAL(ftrace_regs_caller_op_ptr) /* regs go into 4th parameter */ leaq (%rsp), %rcx -GLOBAL(ftrace_regs_call) +SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) call ftrace_stub /* Copy flags back to SS, to restore them */ @@ -228,7 +230,33 @@ GLOBAL(ftrace_regs_call) movq R10(%rsp), %r10 movq RBX(%rsp), %rbx - restore_mcount_regs + movq ORIG_RAX(%rsp), %rax + movq %rax, MCOUNT_REG_SIZE-8(%rsp) + + /* If ORIG_RAX is anything but zero, make this a call to that */ + movq ORIG_RAX(%rsp), %rax + cmpq $0, %rax + je 1f + + /* Swap the flags with orig_rax */ + movq MCOUNT_REG_SIZE(%rsp), %rdi + movq %rdi, MCOUNT_REG_SIZE-8(%rsp) + movq %rax, MCOUNT_REG_SIZE(%rsp) + + restore_mcount_regs 8 + + jmp 2f + +1: restore_mcount_regs + + +2: + /* + * The stack layout is nondetermistic here, depending on which path was + * taken. This confuses objtool and ORC, rightfully so. For now, + * pretend the stack always looks like the non-direct case. + */ + UNWIND_HINT_RESTORE /* Restore flags */ popfq @@ -239,16 +267,16 @@ GLOBAL(ftrace_regs_call) * The trampoline will add the code to jump * to the return. */ -GLOBAL(ftrace_regs_caller_end) +SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) jmp ftrace_epilogue -ENDPROC(ftrace_regs_caller) +SYM_FUNC_END(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ -ENTRY(function_hook) +SYM_FUNC_START(__fentry__) cmpq $ftrace_stub, ftrace_trace_function jnz trace @@ -261,7 +289,7 @@ fgraph_trace: jnz ftrace_graph_caller #endif -GLOBAL(ftrace_stub) +SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) retq trace: @@ -279,11 +307,12 @@ trace: restore_mcount_regs jmp fgraph_trace -ENDPROC(function_hook) +SYM_FUNC_END(__fentry__) +EXPORT_SYMBOL(__fentry__) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) +SYM_FUNC_START(ftrace_graph_caller) /* Saves rbp into %rdx and fills first parameter */ save_mcount_regs @@ -294,9 +323,9 @@ ENTRY(ftrace_graph_caller) restore_mcount_regs retq -ENDPROC(ftrace_graph_caller) +SYM_FUNC_END(ftrace_graph_caller) -ENTRY(return_to_handler) +SYM_CODE_START(return_to_handler) UNWIND_HINT_EMPTY subq $24, %rsp @@ -312,5 +341,5 @@ ENTRY(return_to_handler) movq (%rsp), %rax addq $24, %rsp JMP_NOSPEC %rdi -END(return_to_handler) +SYM_CODE_END(return_to_handler) #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 29ffa495bd1c..206a4b6144c2 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -222,13 +222,31 @@ unsigned long __head __startup_64(unsigned long physaddr, * we might write invalid pmds, when the kernel is relocated * cleanup_highmap() fixes this up along with the mappings * beyond _end. + * + * Only the region occupied by the kernel image has so far + * been checked against the table of usable memory regions + * provided by the firmware, so invalidate pages outside that + * region. A page table entry that maps to a reserved area of + * memory would allow processor speculation into that area, + * and on some hardware (particularly the UV platform) even + * speculative access to some reserved areas is caught as an + * error, causing the BIOS to halt the system. */ pmd = fixup_pointer(level2_kernel_pgt, physaddr); - for (i = 0; i < PTRS_PER_PMD; i++) { + + /* invalidate pages before the kernel image */ + for (i = 0; i < pmd_index((unsigned long)_text); i++) + pmd[i] &= ~_PAGE_PRESENT; + + /* fixup pages that are part of the kernel image */ + for (; i <= pmd_index((unsigned long)_end); i++) if (pmd[i] & _PAGE_PRESENT) pmd[i] += load_delta; - } + + /* invalidate pages after the kernel image */ + for (; i < PTRS_PER_PMD; i++) + pmd[i] &= ~_PAGE_PRESENT; /* * Fixup phys_base - remove the memory encryption mask to obtain diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 30f9cb2c0b55..3923ab4630d7 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -64,7 +64,7 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE) * can. */ __HEAD -ENTRY(startup_32) +SYM_CODE_START(startup_32) movl pa(initial_stack),%ecx /* test KEEP_SEGMENTS flag to see if the bootloader is asking @@ -156,7 +156,7 @@ ENTRY(startup_32) jmp *%eax .Lbad_subarch: -WEAK(xen_entry) +SYM_INNER_LABEL_ALIGN(xen_entry, SYM_L_WEAK) /* Unknown implementation; there's really nothing we can do at this point. */ ud2a @@ -172,6 +172,7 @@ num_subarch_entries = (. - subarch_entries) / 4 #else jmp .Ldefault_entry #endif /* CONFIG_PARAVIRT */ +SYM_CODE_END(startup_32) #ifdef CONFIG_HOTPLUG_CPU /* @@ -179,12 +180,12 @@ num_subarch_entries = (. - subarch_entries) / 4 * up already except stack. We just set up stack here. Then call * start_secondary(). */ -ENTRY(start_cpu0) +SYM_FUNC_START(start_cpu0) movl initial_stack, %ecx movl %ecx, %esp call *(initial_code) 1: jmp 1b -ENDPROC(start_cpu0) +SYM_FUNC_END(start_cpu0) #endif /* @@ -195,7 +196,7 @@ ENDPROC(start_cpu0) * If cpu hotplug is not supported then this code can go in init section * which will be freed later */ -ENTRY(startup_32_smp) +SYM_FUNC_START(startup_32_smp) cld movl $(__BOOT_DS),%eax movl %eax,%ds @@ -362,7 +363,7 @@ ENTRY(startup_32_smp) call *(initial_code) 1: jmp 1b -ENDPROC(startup_32_smp) +SYM_FUNC_END(startup_32_smp) #include "verify_cpu.S" @@ -392,7 +393,7 @@ setup_once: andl $0,setup_once_ref /* Once is enough, thanks */ ret -ENTRY(early_idt_handler_array) +SYM_FUNC_START(early_idt_handler_array) # 36(%esp) %eflags # 32(%esp) %cs # 28(%esp) %eip @@ -407,9 +408,9 @@ ENTRY(early_idt_handler_array) i = i + 1 .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handler_array) +SYM_FUNC_END(early_idt_handler_array) -early_idt_handler_common: +SYM_CODE_START_LOCAL(early_idt_handler_common) /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -460,10 +461,10 @@ early_idt_handler_common: decl %ss:early_recursion_flag addl $4, %esp /* pop pt_regs->orig_ax */ iret -ENDPROC(early_idt_handler_common) +SYM_CODE_END(early_idt_handler_common) /* This is the default interrupt "handler" :-) */ -ENTRY(early_ignore_irq) +SYM_FUNC_START(early_ignore_irq) cld #ifdef CONFIG_PRINTK pushl %eax @@ -498,19 +499,16 @@ ENTRY(early_ignore_irq) hlt_loop: hlt jmp hlt_loop -ENDPROC(early_ignore_irq) +SYM_FUNC_END(early_ignore_irq) __INITDATA .align 4 -GLOBAL(early_recursion_flag) - .long 0 +SYM_DATA(early_recursion_flag, .long 0) __REFDATA .align 4 -ENTRY(initial_code) - .long i386_start_kernel -ENTRY(setup_once_ref) - .long setup_once +SYM_DATA(initial_code, .long i386_start_kernel) +SYM_DATA(setup_once_ref, .long setup_once) #ifdef CONFIG_PAGE_TABLE_ISOLATION #define PGD_ALIGN (2 * PAGE_SIZE) @@ -553,7 +551,7 @@ EXPORT_SYMBOL(empty_zero_page) __PAGE_ALIGNED_DATA /* Page-aligned for the benefit of paravirt? */ .align PGD_ALIGN -ENTRY(initial_page_table) +SYM_DATA_START(initial_page_table) .long pa(initial_pg_pmd+PGD_IDENT_ATTR),0 /* low identity map */ # if KPMDS == 3 .long pa(initial_pg_pmd+PGD_IDENT_ATTR),0 @@ -571,17 +569,28 @@ ENTRY(initial_page_table) # error "Kernel PMDs should be 1, 2 or 3" # endif .align PAGE_SIZE /* needs to be page-sized too */ + +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* + * PTI needs another page so sync_initial_pagetable() works correctly + * and does not scribble over the data which is placed behind the + * actual initial_page_table. See clone_pgd_range(). + */ + .fill 1024, 4, 0 +#endif + +SYM_DATA_END(initial_page_table) #endif .data .balign 4 -ENTRY(initial_stack) - /* - * The SIZEOF_PTREGS gap is a convention which helps the in-kernel - * unwinder reliably detect the end of the stack. - */ - .long init_thread_union + THREAD_SIZE - SIZEOF_PTREGS - \ - TOP_OF_KERNEL_STACK_PADDING; +/* + * The SIZEOF_PTREGS gap is a convention which helps the in-kernel unwinder + * reliably detect the end of the stack. + */ +SYM_DATA(initial_stack, + .long init_thread_union + THREAD_SIZE - + SIZEOF_PTREGS - TOP_OF_KERNEL_STACK_PADDING) __INITRODATA int_msg: @@ -597,27 +606,28 @@ int_msg: */ .data -.globl boot_gdt_descr - ALIGN # early boot GDT descriptor (must use 1:1 address mapping) .word 0 # 32 bit align gdt_desc.address -boot_gdt_descr: +SYM_DATA_START_LOCAL(boot_gdt_descr) .word __BOOT_DS+7 .long boot_gdt - __PAGE_OFFSET +SYM_DATA_END(boot_gdt_descr) # boot GDT descriptor (later on used by CPU#0): .word 0 # 32 bit align gdt_desc.address -ENTRY(early_gdt_descr) +SYM_DATA_START(early_gdt_descr) .word GDT_ENTRIES*8-1 .long gdt_page /* Overwritten for secondary CPUs */ +SYM_DATA_END(early_gdt_descr) /* * The boot_gdt must mirror the equivalent in setup.S and is * used only for booting. */ .align L1_CACHE_BYTES -ENTRY(boot_gdt) +SYM_DATA_START(boot_gdt) .fill GDT_ENTRY_BOOT_CS,8,0 .quad 0x00cf9a000000ffff /* kernel 4GB code at 0x00000000 */ .quad 0x00cf92000000ffff /* kernel 4GB data at 0x00000000 */ +SYM_DATA_END(boot_gdt) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index f3d3e9646a99..4bbc770af632 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -49,8 +49,7 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map) .text __HEAD .code64 - .globl startup_64 -startup_64: +SYM_CODE_START_NOALIGN(startup_64) UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, @@ -90,7 +89,9 @@ startup_64: /* Form the CR3 value being sure to include the CR3 modifier */ addq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f -ENTRY(secondary_startup_64) +SYM_CODE_END(startup_64) + +SYM_CODE_START(secondary_startup_64) UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, @@ -240,7 +241,7 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq .Lafter_lret: -END(secondary_startup_64) +SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" @@ -250,30 +251,28 @@ END(secondary_startup_64) * up already except stack. We just set up stack here. Then call * start_secondary() via .Ljump_to_C_code. */ -ENTRY(start_cpu0) +SYM_CODE_START(start_cpu0) UNWIND_HINT_EMPTY movq initial_stack(%rip), %rsp jmp .Ljump_to_C_code -END(start_cpu0) +SYM_CODE_END(start_cpu0) #endif /* Both SMP bootup and ACPI suspend change these variables */ __REFDATA .balign 8 - GLOBAL(initial_code) - .quad x86_64_start_kernel - GLOBAL(initial_gs) - .quad INIT_PER_CPU_VAR(fixed_percpu_data) - GLOBAL(initial_stack) - /* - * The SIZEOF_PTREGS gap is a convention which helps the in-kernel - * unwinder reliably detect the end of the stack. - */ - .quad init_thread_union + THREAD_SIZE - SIZEOF_PTREGS +SYM_DATA(initial_code, .quad x86_64_start_kernel) +SYM_DATA(initial_gs, .quad INIT_PER_CPU_VAR(fixed_percpu_data)) + +/* + * The SIZEOF_PTREGS gap is a convention which helps the in-kernel unwinder + * reliably detect the end of the stack. + */ +SYM_DATA(initial_stack, .quad init_thread_union + THREAD_SIZE - SIZEOF_PTREGS) __FINITDATA __INIT -ENTRY(early_idt_handler_array) +SYM_CODE_START(early_idt_handler_array) i = 0 .rept NUM_EXCEPTION_VECTORS .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 @@ -289,9 +288,9 @@ ENTRY(early_idt_handler_array) .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr UNWIND_HINT_IRET_REGS offset=16 -END(early_idt_handler_array) +SYM_CODE_END(early_idt_handler_array) -early_idt_handler_common: +SYM_CODE_START_LOCAL(early_idt_handler_common) /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -333,17 +332,11 @@ early_idt_handler_common: 20: decl early_recursion_flag(%rip) jmp restore_regs_and_return_to_kernel -END(early_idt_handler_common) +SYM_CODE_END(early_idt_handler_common) - __INITDATA - .balign 4 -GLOBAL(early_recursion_flag) - .long 0 - -#define NEXT_PAGE(name) \ - .balign PAGE_SIZE; \ -GLOBAL(name) +#define SYM_DATA_START_PAGE_ALIGNED(name) \ + SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) #ifdef CONFIG_PAGE_TABLE_ISOLATION /* @@ -358,11 +351,11 @@ GLOBAL(name) */ #define PTI_USER_PGD_FILL 512 /* This ensures they are 8k-aligned: */ -#define NEXT_PGD_PAGE(name) \ - .balign 2 * PAGE_SIZE; \ -GLOBAL(name) +#define SYM_DATA_START_PTI_ALIGNED(name) \ + SYM_START(name, SYM_L_GLOBAL, .balign 2 * PAGE_SIZE) #else -#define NEXT_PGD_PAGE(name) NEXT_PAGE(name) +#define SYM_DATA_START_PTI_ALIGNED(name) \ + SYM_DATA_START_PAGE_ALIGNED(name) #define PTI_USER_PGD_FILL 0 #endif @@ -375,17 +368,23 @@ GLOBAL(name) .endr __INITDATA -NEXT_PGD_PAGE(early_top_pgt) + .balign 4 + +SYM_DATA_START_PTI_ALIGNED(early_top_pgt) .fill 512,8,0 .fill PTI_USER_PGD_FILL,8,0 +SYM_DATA_END(early_top_pgt) -NEXT_PAGE(early_dynamic_pgts) +SYM_DATA_START_PAGE_ALIGNED(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 +SYM_DATA_END(early_dynamic_pgts) + +SYM_DATA(early_recursion_flag, .long 0) .data #if defined(CONFIG_XEN_PV) || defined(CONFIG_PVH) -NEXT_PGD_PAGE(init_top_pgt) +SYM_DATA_START_PTI_ALIGNED(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + L4_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC @@ -393,11 +392,13 @@ NEXT_PGD_PAGE(init_top_pgt) /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC .fill PTI_USER_PGD_FILL,8,0 +SYM_DATA_END(init_top_pgt) -NEXT_PAGE(level3_ident_pgt) +SYM_DATA_START_PAGE_ALIGNED(level3_ident_pgt) .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .fill 511, 8, 0 -NEXT_PAGE(level2_ident_pgt) +SYM_DATA_END(level3_ident_pgt) +SYM_DATA_START_PAGE_ALIGNED(level2_ident_pgt) /* * Since I easily can, map the first 1G. * Don't set NX because code runs from these pages. @@ -407,25 +408,29 @@ NEXT_PAGE(level2_ident_pgt) * the CPU should ignore the bit. */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) +SYM_DATA_END(level2_ident_pgt) #else -NEXT_PGD_PAGE(init_top_pgt) +SYM_DATA_START_PTI_ALIGNED(init_top_pgt) .fill 512,8,0 .fill PTI_USER_PGD_FILL,8,0 +SYM_DATA_END(init_top_pgt) #endif #ifdef CONFIG_X86_5LEVEL -NEXT_PAGE(level4_kernel_pgt) +SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt) .fill 511,8,0 .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC +SYM_DATA_END(level4_kernel_pgt) #endif -NEXT_PAGE(level3_kernel_pgt) +SYM_DATA_START_PAGE_ALIGNED(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC +SYM_DATA_END(level3_kernel_pgt) -NEXT_PAGE(level2_kernel_pgt) +SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt) /* * 512 MB kernel mapping. We spend a full page on this pagetable * anyway. @@ -442,8 +447,9 @@ NEXT_PAGE(level2_kernel_pgt) */ PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE) +SYM_DATA_END(level2_kernel_pgt) -NEXT_PAGE(level2_fixmap_pgt) +SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt) .fill (512 - 4 - FIXMAP_PMD_NUM),8,0 pgtno = 0 .rept (FIXMAP_PMD_NUM) @@ -453,31 +459,32 @@ NEXT_PAGE(level2_fixmap_pgt) .endr /* 6 MB reserved space + a 2MB hole */ .fill 4,8,0 +SYM_DATA_END(level2_fixmap_pgt) -NEXT_PAGE(level1_fixmap_pgt) +SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt) .rept (FIXMAP_PMD_NUM) .fill 512,8,0 .endr +SYM_DATA_END(level1_fixmap_pgt) #undef PMDS .data .align 16 - .globl early_gdt_descr -early_gdt_descr: - .word GDT_ENTRIES*8-1 -early_gdt_descr_base: - .quad INIT_PER_CPU_VAR(gdt_page) - -ENTRY(phys_base) - /* This must match the first entry in level2_kernel_pgt */ - .quad 0x0000000000000000 + +SYM_DATA(early_gdt_descr, .word GDT_ENTRIES*8-1) +SYM_DATA_LOCAL(early_gdt_descr_base, .quad INIT_PER_CPU_VAR(gdt_page)) + + .align 16 +/* This must match the first entry in level2_kernel_pgt */ +SYM_DATA(phys_base, .quad 0x0) EXPORT_SYMBOL(phys_base) #include "../../x86/xen/xen-head.S" __PAGE_ALIGNED_BSS -NEXT_PAGE(empty_zero_page) +SYM_DATA_START_PAGE_ALIGNED(empty_zero_page) .skip PAGE_SIZE +SYM_DATA_END(empty_zero_page) EXPORT_SYMBOL(empty_zero_page) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c6f791bc481e..7a50f0b62a70 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -84,7 +84,7 @@ static inline void hpet_writel(unsigned int d, unsigned int a) static inline void hpet_set_mapping(void) { - hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); + hpet_virt_address = ioremap(hpet_address, HPET_MMAP_SIZE); } static inline void hpet_clear_mapping(void) diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c index 4c407833faca..4d4f5d9faac3 100644 --- a/arch/x86/kernel/ima_arch.c +++ b/arch/x86/kernel/ima_arch.c @@ -74,9 +74,9 @@ bool arch_ima_get_secureboot(void) /* secureboot arch rules */ static const char * const sb_arch_rules[] = { -#if !IS_ENABLED(CONFIG_KEXEC_VERIFY_SIG) +#if !IS_ENABLED(CONFIG_KEXEC_SIG) "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig", -#endif /* CONFIG_KEXEC_VERIFY_SIG */ +#endif /* CONFIG_KEXEC_SIG */ "measure func=KEXEC_KERNEL_CHECK", #if !IS_ENABLED(CONFIG_MODULE_SIG) "appraise func=MODULE_CHECK appraise_type=imasig", diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 0fe1c8782208..8abeee0dd7bf 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -3,35 +3,74 @@ * This contains the io-permission bitmap code - written by obz, with changes * by Linus. 32/64 bits code unification by Miguel Botón. */ - -#include <linux/sched.h> -#include <linux/sched/task_stack.h> -#include <linux/kernel.h> #include <linux/capability.h> -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/ioport.h> -#include <linux/smp.h> -#include <linux/stddef.h> -#include <linux/slab.h> -#include <linux/thread_info.h> +#include <linux/security.h> #include <linux/syscalls.h> #include <linux/bitmap.h> -#include <asm/syscalls.h> +#include <linux/ioport.h> +#include <linux/sched.h> +#include <linux/slab.h> + +#include <asm/io_bitmap.h> #include <asm/desc.h> +#ifdef CONFIG_X86_IOPL_IOPERM + +static atomic64_t io_bitmap_sequence; + +void io_bitmap_share(struct task_struct *tsk) +{ + /* Can be NULL when current->thread.iopl_emul == 3 */ + if (current->thread.io_bitmap) { + /* + * Take a refcount on current's bitmap. It can be used by + * both tasks as long as none of them changes the bitmap. + */ + refcount_inc(¤t->thread.io_bitmap->refcnt); + tsk->thread.io_bitmap = current->thread.io_bitmap; + } + set_tsk_thread_flag(tsk, TIF_IO_BITMAP); +} + +static void task_update_io_bitmap(void) +{ + struct thread_struct *t = ¤t->thread; + + if (t->iopl_emul == 3 || t->io_bitmap) { + /* TSS update is handled on exit to user space */ + set_thread_flag(TIF_IO_BITMAP); + } else { + clear_thread_flag(TIF_IO_BITMAP); + /* Invalidate TSS */ + preempt_disable(); + tss_update_io_bitmap(); + preempt_enable(); + } +} + +void io_bitmap_exit(void) +{ + struct io_bitmap *iobm = current->thread.io_bitmap; + + current->thread.io_bitmap = NULL; + task_update_io_bitmap(); + if (iobm && refcount_dec_and_test(&iobm->refcnt)) + kfree(iobm); +} + /* - * this changes the io permissions bitmap in the current task. + * This changes the io permissions bitmap in the current task. */ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on) { struct thread_struct *t = ¤t->thread; - struct tss_struct *tss; - unsigned int i, max_long, bytes, bytes_updated; + unsigned int i, max_long; + struct io_bitmap *iobm; if ((from + num <= from) || (from + num > IO_BITMAP_BITS)) return -EINVAL; - if (turn_on && !capable(CAP_SYS_RAWIO)) + if (turn_on && (!capable(CAP_SYS_RAWIO) || + security_locked_down(LOCKDOWN_IOPORT))) return -EPERM; /* @@ -39,59 +78,72 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on) * IO bitmap up. ioperm() is much less timing critical than clone(), * this is why we delay this operation until now: */ - if (!t->io_bitmap_ptr) { - unsigned long *bitmap = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); - - if (!bitmap) + iobm = t->io_bitmap; + if (!iobm) { + /* No point to allocate a bitmap just to clear permissions */ + if (!turn_on) + return 0; + iobm = kmalloc(sizeof(*iobm), GFP_KERNEL); + if (!iobm) return -ENOMEM; - memset(bitmap, 0xff, IO_BITMAP_BYTES); - t->io_bitmap_ptr = bitmap; - set_thread_flag(TIF_IO_BITMAP); + memset(iobm->bitmap, 0xff, sizeof(iobm->bitmap)); + refcount_set(&iobm->refcnt, 1); + } - /* - * Now that we have an IO bitmap, we need our TSS limit to be - * correct. It's fine if we are preempted after doing this: - * with TIF_IO_BITMAP set, context switches will keep our TSS - * limit correct. - */ - preempt_disable(); - refresh_tss_limit(); - preempt_enable(); + /* + * If the bitmap is not shared, then nothing can take a refcount as + * current can obviously not fork at the same time. If it's shared + * duplicate it and drop the refcount on the original one. + */ + if (refcount_read(&iobm->refcnt) > 1) { + iobm = kmemdup(iobm, sizeof(*iobm), GFP_KERNEL); + if (!iobm) + return -ENOMEM; + refcount_set(&iobm->refcnt, 1); + io_bitmap_exit(); } /* - * do it in the per-thread copy and in the TSS ... - * - * Disable preemption via get_cpu() - we must not switch away - * because the ->io_bitmap_max value must match the bitmap - * contents: + * Store the bitmap pointer (might be the same if the task already + * head one). Must be done here so freeing the bitmap when all + * permissions are dropped has the pointer set up. */ - tss = &per_cpu(cpu_tss_rw, get_cpu()); + t->io_bitmap = iobm; + /* Mark it active for context switching and exit to user mode */ + set_thread_flag(TIF_IO_BITMAP); + /* + * Update the tasks bitmap. The update of the TSS bitmap happens on + * exit to user mode. So this needs no protection. + */ if (turn_on) - bitmap_clear(t->io_bitmap_ptr, from, num); + bitmap_clear(iobm->bitmap, from, num); else - bitmap_set(t->io_bitmap_ptr, from, num); + bitmap_set(iobm->bitmap, from, num); /* * Search for a (possibly new) maximum. This is simple and stupid, * to keep it obviously correct: */ - max_long = 0; - for (i = 0; i < IO_BITMAP_LONGS; i++) - if (t->io_bitmap_ptr[i] != ~0UL) + max_long = UINT_MAX; + for (i = 0; i < IO_BITMAP_LONGS; i++) { + if (iobm->bitmap[i] != ~0UL) max_long = i; + } + /* All permissions dropped? */ + if (max_long == UINT_MAX) { + io_bitmap_exit(); + return 0; + } - bytes = (max_long + 1) * sizeof(unsigned long); - bytes_updated = max(bytes, t->io_bitmap_max); - - t->io_bitmap_max = bytes; - - /* Update the TSS: */ - memcpy(tss->io_bitmap, t->io_bitmap_ptr, bytes_updated); + iobm->max = (max_long + 1) * sizeof(unsigned long); - put_cpu(); + /* + * Update the sequence number to force a TSS update on return to + * user mode. + */ + iobm->sequence = atomic64_add_return(1, &io_bitmap_sequence); return 0; } @@ -102,37 +154,61 @@ SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on) } /* - * sys_iopl has to be used when you want to access the IO ports - * beyond the 0x3ff range: to get the full 65536 ports bitmapped - * you'd need 8kB of bitmaps/process, which is a bit excessive. + * The sys_iopl functionality depends on the level argument, which if + * granted for the task is used to enable access to all 65536 I/O ports. + * + * This does not use the IOPL mechanism provided by the CPU as that would + * also allow the user space task to use the CLI/STI instructions. * - * Here we just change the flags value on the stack: we allow - * only the super-user to do it. This depends on the stack-layout - * on system-call entry - see also fork() and the signal handling - * code. + * Disabling interrupts in a user space task is dangerous as it might lock + * up the machine and the semantics vs. syscalls and exceptions is + * undefined. + * + * Setting IOPL to level 0-2 is disabling I/O permissions. Level 3 + * 3 enables them. + * + * IOPL is strictly per thread and inherited on fork. */ SYSCALL_DEFINE1(iopl, unsigned int, level) { - struct pt_regs *regs = current_pt_regs(); struct thread_struct *t = ¤t->thread; - - /* - * Careful: the IOPL bits in regs->flags are undefined under Xen PV - * and changing them has no effect. - */ - unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT; + unsigned int old; if (level > 3) return -EINVAL; + + old = t->iopl_emul; + + /* No point in going further if nothing changes */ + if (level == old) + return 0; + /* Trying to gain more privileges? */ if (level > old) { - if (!capable(CAP_SYS_RAWIO)) + if (!capable(CAP_SYS_RAWIO) || + security_locked_down(LOCKDOWN_IOPORT)) return -EPERM; } - regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | - (level << X86_EFLAGS_IOPL_BIT); - t->iopl = level << X86_EFLAGS_IOPL_BIT; - set_iopl_mask(t->iopl); + + t->iopl_emul = level; + task_update_io_bitmap(); return 0; } + +#else /* CONFIG_X86_IOPL_IOPERM */ + +long ksys_ioperm(unsigned long from, unsigned long num, int turn_on) +{ + return -ENOSYS; +} +SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on) +{ + return -ENOSYS; +} + +SYSCALL_DEFINE1(iopl, unsigned int, level) +{ + return -ENOSYS; +} +#endif diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 4215653f8a8e..21efee32e2b1 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -243,11 +243,15 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU"); desc = __this_cpu_read(vector_irq[vector]); - - if (!handle_irq(desc, regs)) { + if (likely(!IS_ERR_OR_NULL(desc))) { + if (IS_ENABLED(CONFIG_X86_32)) + handle_irq(desc, regs); + else + generic_handle_irq_desc(desc); + } else { ack_APIC_irq(); - if (desc != VECTOR_RETRIGGERED && desc != VECTOR_SHUTDOWN) { + if (desc == VECTOR_UNUSED) { pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n", __func__, smp_processor_id(), vector); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index fc34816c6f04..a759ca97cd01 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -148,18 +148,13 @@ void do_softirq_own_stack(void) call_on_stack(__do_softirq, isp); } -bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) +void handle_irq(struct irq_desc *desc, struct pt_regs *regs) { int overflow = check_stack_overflow(); - if (IS_ERR_OR_NULL(desc)) - return false; - if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) { if (unlikely(overflow)) print_stack_overflow(); generic_handle_irq_desc(desc); } - - return true; } diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 6bf6517a05bb..12df3a4abfdd 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -26,15 +26,6 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible; DECLARE_INIT_PER_CPU(irq_stack_backing_store); -bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) -{ - if (IS_ERR_OR_NULL(desc)) - return false; - - generic_handle_irq_desc(desc); - return true; -} - #ifdef CONFIG_VMAP_STACK /* * VMAP the backing store with guard pages diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S index ddeeaac8adda..0db0375235b4 100644 --- a/arch/x86/kernel/irqflags.S +++ b/arch/x86/kernel/irqflags.S @@ -7,20 +7,20 @@ /* * unsigned long native_save_fl(void) */ -ENTRY(native_save_fl) +SYM_FUNC_START(native_save_fl) pushf pop %_ASM_AX ret -ENDPROC(native_save_fl) +SYM_FUNC_END(native_save_fl) EXPORT_SYMBOL(native_save_fl) /* * void native_restore_fl(unsigned long flags) * %eax/%rdi: flags */ -ENTRY(native_restore_fl) +SYM_FUNC_START(native_restore_fl) push %_ASM_ARG1 popf ret -ENDPROC(native_restore_fl) +SYM_FUNC_END(native_restore_fl) EXPORT_SYMBOL(native_restore_fl) diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index 3ad34f01de2a..6eb8b50ea07e 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -11,6 +11,7 @@ #include <linux/acpi_pmtmr.h> #include <linux/kernel.h> #include <linux/reboot.h> +#include <linux/serial_8250.h> #include <asm/apic.h> #include <asm/cpu.h> #include <asm/hypervisor.h> @@ -21,9 +22,24 @@ #include <asm/setup.h> #include <asm/jailhouse_para.h> -static __initdata struct jailhouse_setup_data setup_data; +static struct jailhouse_setup_data setup_data; +#define SETUP_DATA_V1_LEN (sizeof(setup_data.hdr) + sizeof(setup_data.v1)) +#define SETUP_DATA_V2_LEN (SETUP_DATA_V1_LEN + sizeof(setup_data.v2)) + static unsigned int precalibrated_tsc_khz; +static void jailhouse_setup_irq(unsigned int irq) +{ + struct mpc_intsrc mp_irq = { + .type = MP_INTSRC, + .irqtype = mp_INT, + .irqflag = MP_IRQPOL_ACTIVE_HIGH | MP_IRQTRIG_EDGE, + .srcbusirq = irq, + .dstirq = irq, + }; + mp_save_irq(&mp_irq); +} + static uint32_t jailhouse_cpuid_base(void) { if (boot_cpu_data.cpuid_level < 0 || @@ -45,7 +61,7 @@ static void jailhouse_get_wallclock(struct timespec64 *now) static void __init jailhouse_timer_init(void) { - lapic_timer_period = setup_data.apic_khz * (1000 / HZ); + lapic_timer_period = setup_data.v1.apic_khz * (1000 / HZ); } static unsigned long jailhouse_get_tsc(void) @@ -77,33 +93,28 @@ static void __init jailhouse_get_smp_config(unsigned int early) .type = IOAPIC_DOMAIN_STRICT, .ops = &mp_ioapic_irqdomain_ops, }; - struct mpc_intsrc mp_irq = { - .type = MP_INTSRC, - .irqtype = mp_INT, - .irqflag = MP_IRQPOL_ACTIVE_HIGH | MP_IRQTRIG_EDGE, - }; unsigned int cpu; jailhouse_x2apic_init(); register_lapic_address(0xfee00000); - for (cpu = 0; cpu < setup_data.num_cpus; cpu++) { - generic_processor_info(setup_data.cpu_ids[cpu], + for (cpu = 0; cpu < setup_data.v1.num_cpus; cpu++) { + generic_processor_info(setup_data.v1.cpu_ids[cpu], boot_cpu_apic_version); } smp_found_config = 1; - if (setup_data.standard_ioapic) { + if (setup_data.v1.standard_ioapic) { mp_register_ioapic(0, 0xfec00000, gsi_top, &ioapic_cfg); - /* Register 1:1 mapping for legacy UART IRQs 3 and 4 */ - mp_irq.srcbusirq = mp_irq.dstirq = 3; - mp_save_irq(&mp_irq); - - mp_irq.srcbusirq = mp_irq.dstirq = 4; - mp_save_irq(&mp_irq); + if (IS_ENABLED(CONFIG_SERIAL_8250) && + setup_data.hdr.version < 2) { + /* Register 1:1 mapping for legacy UART IRQs 3 and 4 */ + jailhouse_setup_irq(3); + jailhouse_setup_irq(4); + } } } @@ -126,9 +137,9 @@ static int __init jailhouse_pci_arch_init(void) pcibios_last_bus = 0xff; #ifdef CONFIG_PCI_MMCONFIG - if (setup_data.pci_mmconfig_base) { + if (setup_data.v1.pci_mmconfig_base) { pci_mmconfig_add(0, 0, pcibios_last_bus, - setup_data.pci_mmconfig_base); + setup_data.v1.pci_mmconfig_base); pci_mmcfg_arch_init(); } #endif @@ -136,9 +147,57 @@ static int __init jailhouse_pci_arch_init(void) return 0; } +#ifdef CONFIG_SERIAL_8250 +static inline bool jailhouse_uart_enabled(unsigned int uart_nr) +{ + return setup_data.v2.flags & BIT(uart_nr); +} + +static void jailhouse_serial_fixup(int port, struct uart_port *up, + u32 *capabilities) +{ + static const u16 pcuart_base[] = {0x3f8, 0x2f8, 0x3e8, 0x2e8}; + unsigned int n; + + for (n = 0; n < ARRAY_SIZE(pcuart_base); n++) { + if (pcuart_base[n] != up->iobase) + continue; + + if (jailhouse_uart_enabled(n)) { + pr_info("Enabling UART%u (port 0x%lx)\n", n, + up->iobase); + jailhouse_setup_irq(up->irq); + } else { + /* Deactivate UART if access isn't allowed */ + up->iobase = 0; + } + break; + } +} + +static void __init jailhouse_serial_workaround(void) +{ + /* + * There are flags inside setup_data that indicate availability of + * platform UARTs since setup data version 2. + * + * In case of version 1, we don't know which UARTs belong Linux. In + * this case, unconditionally register 1:1 mapping for legacy UART IRQs + * 3 and 4. + */ + if (setup_data.hdr.version > 1) + serial8250_set_isa_configurator(jailhouse_serial_fixup); +} +#else /* !CONFIG_SERIAL_8250 */ +static inline void jailhouse_serial_workaround(void) +{ +} +#endif /* CONFIG_SERIAL_8250 */ + static void __init jailhouse_init_platform(void) { u64 pa_data = boot_params.hdr.setup_data; + unsigned long setup_data_len; struct setup_data header; void *mapping; @@ -163,16 +222,8 @@ static void __init jailhouse_init_platform(void) memcpy(&header, mapping, sizeof(header)); early_memunmap(mapping, sizeof(header)); - if (header.type == SETUP_JAILHOUSE && - header.len >= sizeof(setup_data)) { - pa_data += offsetof(struct setup_data, data); - - mapping = early_memremap(pa_data, sizeof(setup_data)); - memcpy(&setup_data, mapping, sizeof(setup_data)); - early_memunmap(mapping, sizeof(setup_data)); - + if (header.type == SETUP_JAILHOUSE) break; - } pa_data = header.next; } @@ -180,13 +231,28 @@ static void __init jailhouse_init_platform(void) if (!pa_data) panic("Jailhouse: No valid setup data found"); - if (setup_data.compatible_version > JAILHOUSE_SETUP_REQUIRED_VERSION) - panic("Jailhouse: Unsupported setup data structure"); - - pmtmr_ioport = setup_data.pm_timer_address; + /* setup data must at least contain the header */ + if (header.len < sizeof(setup_data.hdr)) + goto unsupported; + + pa_data += offsetof(struct setup_data, data); + setup_data_len = min_t(unsigned long, sizeof(setup_data), + (unsigned long)header.len); + mapping = early_memremap(pa_data, setup_data_len); + memcpy(&setup_data, mapping, setup_data_len); + early_memunmap(mapping, setup_data_len); + + if (setup_data.hdr.version == 0 || + setup_data.hdr.compatible_version != + JAILHOUSE_SETUP_REQUIRED_VERSION || + (setup_data.hdr.version == 1 && header.len < SETUP_DATA_V1_LEN) || + (setup_data.hdr.version >= 2 && header.len < SETUP_DATA_V2_LEN)) + goto unsupported; + + pmtmr_ioport = setup_data.v1.pm_timer_address; pr_debug("Jailhouse: PM-Timer IO Port: %#x\n", pmtmr_ioport); - precalibrated_tsc_khz = setup_data.tsc_khz; + precalibrated_tsc_khz = setup_data.v1.tsc_khz; setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); pci_probe = 0; @@ -196,6 +262,12 @@ static void __init jailhouse_init_platform(void) * are none in a non-root cell. */ disable_acpi(); + + jailhouse_serial_workaround(); + return; + +unsupported: + panic("Jailhouse: Unsupported setup data structure"); } bool jailhouse_paravirt(void) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 044053235302..9c4498ea0b3c 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -16,15 +16,7 @@ #include <asm/alternative.h> #include <asm/text-patching.h> -union jump_code_union { - char code[JUMP_LABEL_NOP_SIZE]; - struct { - char jump; - int offset; - } __attribute__((packed)); -}; - -static void bug_at(unsigned char *ip, int line) +static void bug_at(const void *ip, int line) { /* * The location is not an op that we were expecting. @@ -35,42 +27,42 @@ static void bug_at(unsigned char *ip, int line) BUG(); } -static void __jump_label_set_jump_code(struct jump_entry *entry, - enum jump_label_type type, - union jump_code_union *code, - int init) +static const void * +__jump_label_set_jump_code(struct jump_entry *entry, enum jump_label_type type, int init) { const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; - const void *expect; + const void *expect, *code; + const void *addr, *dest; int line; - code->jump = 0xe9; - code->offset = jump_entry_target(entry) - - (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE); + addr = (void *)jump_entry_code(entry); + dest = (void *)jump_entry_target(entry); + + code = text_gen_insn(JMP32_INSN_OPCODE, addr, dest); if (init) { expect = default_nop; line = __LINE__; } else if (type == JUMP_LABEL_JMP) { expect = ideal_nop; line = __LINE__; } else { - expect = code->code; line = __LINE__; + expect = code; line = __LINE__; } - if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE)) - bug_at((void *)jump_entry_code(entry), line); + if (memcmp(addr, expect, JUMP_LABEL_NOP_SIZE)) + bug_at(addr, line); if (type == JUMP_LABEL_NOP) - memcpy(code, ideal_nop, JUMP_LABEL_NOP_SIZE); + code = ideal_nop; + + return code; } -static void __ref __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type, - int init) +static void inline __jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { - union jump_code_union code; - - __jump_label_set_jump_code(entry, type, &code, init); + const void *opcode = __jump_label_set_jump_code(entry, type, init); /* * As long as only a single processor is running and the code is still @@ -84,32 +76,33 @@ static void __ref __jump_label_transform(struct jump_entry *entry, * always nop being the 'currently valid' instruction */ if (init || system_state == SYSTEM_BOOTING) { - text_poke_early((void *)jump_entry_code(entry), &code, + text_poke_early((void *)jump_entry_code(entry), opcode, JUMP_LABEL_NOP_SIZE); return; } - text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE, - (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE); + text_poke_bp((void *)jump_entry_code(entry), opcode, JUMP_LABEL_NOP_SIZE, NULL); } -void arch_jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) +static void __ref jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { mutex_lock(&text_mutex); - __jump_label_transform(entry, type, 0); + __jump_label_transform(entry, type, init); mutex_unlock(&text_mutex); } -#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc)) -static struct text_poke_loc tp_vec[TP_VEC_MAX]; -static int tp_vec_nr; +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + jump_label_transform(entry, type, 0); +} bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { - struct text_poke_loc *tp; - void *entry_code; + const void *opcode; if (system_state == SYSTEM_BOOTING) { /* @@ -119,55 +112,19 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry, return true; } - /* - * No more space in the vector, tell upper layer to apply - * the queue before continuing. - */ - if (tp_vec_nr == TP_VEC_MAX) - return false; - - tp = &tp_vec[tp_vec_nr]; - - entry_code = (void *)jump_entry_code(entry); - - /* - * The INT3 handler will do a bsearch in the queue, so we need entries - * to be sorted. We can survive an unsorted list by rejecting the entry, - * forcing the generic jump_label code to apply the queue. Warning once, - * to raise the attention to the case of an unsorted entry that is - * better not happen, because, in the worst case we will perform in the - * same way as we do without batching - with some more overhead. - */ - if (tp_vec_nr > 0) { - int prev = tp_vec_nr - 1; - struct text_poke_loc *prev_tp = &tp_vec[prev]; - - if (WARN_ON_ONCE(prev_tp->addr > entry_code)) - return false; - } - - __jump_label_set_jump_code(entry, type, - (union jump_code_union *) &tp->opcode, 0); - - tp->addr = entry_code; - tp->detour = entry_code + JUMP_LABEL_NOP_SIZE; - tp->len = JUMP_LABEL_NOP_SIZE; - - tp_vec_nr++; - + mutex_lock(&text_mutex); + opcode = __jump_label_set_jump_code(entry, type, 0); + text_poke_queue((void *)jump_entry_code(entry), + opcode, JUMP_LABEL_NOP_SIZE, NULL); + mutex_unlock(&text_mutex); return true; } void arch_jump_label_transform_apply(void) { - if (!tp_vec_nr) - return; - mutex_lock(&text_mutex); - text_poke_bp_batch(tp_vec, tp_vec_nr); + text_poke_finish(); mutex_unlock(&text_mutex); - - tp_vec_nr = 0; } static enum { @@ -196,5 +153,5 @@ __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, jlstate = JL_STATE_NO_UPDATE; } if (jlstate == JL_STATE_UPDATE) - __jump_label_transform(entry, type, 1); + jump_label_transform(entry, type, 1); } diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index edaa30b20841..64b6da95af98 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -44,7 +44,12 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf, if (count > node->len - pos) count = node->len - pos; - pa = node->paddr + sizeof(struct setup_data) + pos; + pa = node->paddr + pos; + + /* Is it direct data or invalid indirect one? */ + if (!(node->type & SETUP_INDIRECT) || node->type == SETUP_INDIRECT) + pa += sizeof(struct setup_data); + p = memremap(pa, count, MEMREMAP_WB); if (!p) return -ENOMEM; @@ -108,9 +113,17 @@ static int __init create_setup_data_nodes(struct dentry *parent) goto err_dir; } - node->paddr = pa_data; - node->type = data->type; - node->len = data->len; + if (data->type == SETUP_INDIRECT && + ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { + node->paddr = ((struct setup_indirect *)data->data)->addr; + node->type = ((struct setup_indirect *)data->data)->type; + node->len = ((struct setup_indirect *)data->data)->len; + } else { + node->paddr = pa_data; + node->type = data->type; + node->len = data->len; + } + create_setup_data_node(d, no, node); pa_data = data->next; diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 5ebcd02cbca7..f293d872602a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -177,9 +177,10 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr, * acpi_rsdp=<addr> on kernel command line to make second kernel boot * without efi. */ - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return 0; + params->secure_boot = boot_params.secure_boot; ei->efi_loader_signature = current_ei->efi_loader_signature; ei->efi_systab = current_ei->efi_systab; ei->efi_systab_hi = current_ei->efi_systab_hi; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 23297ea64f5f..c44fe7d8d9a4 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -416,7 +416,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs) */ void kgdb_roundup_cpus(void) { - apic->send_IPI_allbutself(APIC_DM_NMI); + apic_send_IPI_allbutself(NMI_VECTOR); } #endif diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 0e0b08008b5a..4d7022a740ab 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -40,6 +40,7 @@ #include <linux/frame.h> #include <linux/kasan.h> #include <linux/moduleloader.h> +#include <linux/vmalloc.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -119,14 +120,14 @@ __synthesize_relative_insn(void *dest, void *from, void *to, u8 op) /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ void synthesize_reljump(void *dest, void *from, void *to) { - __synthesize_relative_insn(dest, from, to, RELATIVEJUMP_OPCODE); + __synthesize_relative_insn(dest, from, to, JMP32_INSN_OPCODE); } NOKPROBE_SYMBOL(synthesize_reljump); /* Insert a call instruction at address 'from', which calls address 'to'.*/ void synthesize_relcall(void *dest, void *from, void *to) { - __synthesize_relative_insn(dest, from, to, RELATIVECALL_OPCODE); + __synthesize_relative_insn(dest, from, to, CALL_INSN_OPCODE); } NOKPROBE_SYMBOL(synthesize_relcall); @@ -301,7 +302,7 @@ static int can_probe(unsigned long paddr) * Another debugging subsystem might insert this breakpoint. * In that case, we can't recover it. */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) return 0; addr += insn.length; } @@ -351,8 +352,12 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) kernel_insn_init(insn, dest, MAX_INSN_SIZE); insn_get_length(insn); + /* We can not probe force emulate prefixed instruction */ + if (insn_has_emulate_prefix(insn)) + return 0; + /* Another subsystem puts a breakpoint, failed to recover */ - if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn->opcode.bytes[0] == INT3_INSN_OPCODE) return 0; /* We should not singlestep on the exception masking instructions */ @@ -396,14 +401,14 @@ static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p, int len = insn->length; if (can_boost(insn, p->addr) && - MAX_INSN_SIZE - len >= RELATIVEJUMP_SIZE) { + MAX_INSN_SIZE - len >= JMP32_INSN_SIZE) { /* * These instructions can be executed directly if it * jumps back to correct address. */ synthesize_reljump(buf + len, p->ainsn.insn + len, p->addr + insn->length); - len += RELATIVEJUMP_SIZE; + len += JMP32_INSN_SIZE; p->ainsn.boostable = true; } else { p->ainsn.boostable = false; @@ -497,12 +502,14 @@ int arch_prepare_kprobe(struct kprobe *p) void arch_arm_kprobe(struct kprobe *p) { - text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1); + text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1); + text_poke_sync(); } void arch_disarm_kprobe(struct kprobe *p) { text_poke(p->addr, &p->opcode, 1); + text_poke_sync(); } void arch_remove_kprobe(struct kprobe *p) @@ -580,7 +587,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, if (setup_detour_execution(p, regs, reenter)) return; -#if !defined(CONFIG_PREEMPT) +#if !defined(CONFIG_PREEMPTION) if (p->ainsn.boostable && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ if (!reenter) @@ -605,7 +612,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, regs->flags |= X86_EFLAGS_TF; regs->flags &= ~X86_EFLAGS_IF; /* single step inline if the instruction is an int3 */ - if (p->opcode == BREAKPOINT_INSTRUCTION) + if (p->opcode == INT3_INSN_OPCODE) regs->ip = (unsigned long)p->addr; else regs->ip = (unsigned long)p->ainsn.insn; @@ -691,7 +698,7 @@ int kprobe_int3_handler(struct pt_regs *regs) reset_current_kprobe(); return 1; } - } else if (*addr != BREAKPOINT_INSTRUCTION) { + } else if (*addr != INT3_INSN_OPCODE) { /* * The breakpoint instruction was removed right * after we hit it. Another cpu has removed diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 9d4aedece363..3f45b5c43a71 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -38,7 +38,7 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) long offs; int i; - for (i = 0; i < RELATIVEJUMP_SIZE; i++) { + for (i = 0; i < JMP32_INSN_SIZE; i++) { kp = get_kprobe((void *)addr - i); /* This function only handles jump-optimized kprobe */ if (kp && kprobe_optimized(kp)) { @@ -62,10 +62,10 @@ found: if (addr == (unsigned long)kp->addr) { buf[0] = kp->opcode; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + memcpy(buf + 1, op->optinsn.copied_insn, DISP32_SIZE); } else { offs = addr - (unsigned long)kp->addr - 1; - memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs); + memcpy(buf, op->optinsn.copied_insn + offs, DISP32_SIZE - offs); } return (unsigned long)buf; @@ -141,8 +141,6 @@ STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_END_IDX \ ((long)optprobe_template_end - (long)optprobe_template_entry) -#define INT3_SIZE sizeof(kprobe_opcode_t) - /* Optimized kprobe call back function: called from optinsn */ static void optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) @@ -162,7 +160,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) regs->cs |= get_kernel_rpl(); regs->gs = 0; #endif - regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; + regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE; regs->orig_ax = ~0UL; __this_cpu_write(current_kprobe, &op->kp); @@ -179,7 +177,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) struct insn insn; int len = 0, ret; - while (len < RELATIVEJUMP_SIZE) { + while (len < JMP32_INSN_SIZE) { ret = __copy_instruction(dest + len, src + len, real + len, &insn); if (!ret || !can_boost(&insn, src + len)) return -EINVAL; @@ -271,7 +269,7 @@ static int can_optimize(unsigned long paddr) return 0; /* Check there is enough space for a relative jump. */ - if (size - offset < RELATIVEJUMP_SIZE) + if (size - offset < JMP32_INSN_SIZE) return 0; /* Decode instructions */ @@ -290,15 +288,15 @@ static int can_optimize(unsigned long paddr) kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); /* Another subsystem puts a breakpoint */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) return 0; /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); /* Check any instructions don't jump into target */ if (insn_is_indirect_jump(&insn) || - insn_jump_into_range(&insn, paddr + INT3_SIZE, - RELATIVE_ADDR_SIZE)) + insn_jump_into_range(&insn, paddr + INT3_INSN_SIZE, + DISP32_SIZE)) return 0; addr += insn.length; } @@ -374,7 +372,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, * Verify if the address gap is in 2GB range, because this uses * a relative jump. */ - rel = (long)slot - (long)op->kp.addr + RELATIVEJUMP_SIZE; + rel = (long)slot - (long)op->kp.addr + JMP32_INSN_SIZE; if (abs(rel) > 0x7fffffff) { ret = -ERANGE; goto err; @@ -401,9 +399,9 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, /* Set returning jmp instruction at the tail of out-of-line buffer */ synthesize_reljump(buf + len, slot + len, (u8 *)op->kp.addr + op->optinsn.size); - len += RELATIVEJUMP_SIZE; + len += JMP32_INSN_SIZE; - /* We have to use text_poke for instuction buffer because it is RO */ + /* We have to use text_poke() for instruction buffer because it is RO */ text_poke(slot, buf, len); ret = 0; out: @@ -416,44 +414,50 @@ err: } /* - * Replace breakpoints (int3) with relative jumps. + * Replace breakpoints (INT3) with relative jumps (JMP.d32). * Caller must call with locking kprobe_mutex and text_mutex. + * + * The caller will have installed a regular kprobe and after that issued + * syncrhonize_rcu_tasks(), this ensures that the instruction(s) that live in + * the 4 bytes after the INT3 are unused and can now be overwritten. */ void arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; - u8 insn_buff[RELATIVEJUMP_SIZE]; + u8 insn_buff[JMP32_INSN_SIZE]; list_for_each_entry_safe(op, tmp, oplist, list) { s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + ((long)op->kp.addr + JMP32_INSN_SIZE)); WARN_ON(kprobe_disabled(&op->kp)); /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_INSN_SIZE, + DISP32_SIZE); - insn_buff[0] = RELATIVEJUMP_OPCODE; + insn_buff[0] = JMP32_INSN_OPCODE; *(s32 *)(&insn_buff[1]) = rel; - text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, - op->optinsn.insn); + text_poke_bp(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL); list_del_init(&op->list); } } -/* Replace a relative jump with a breakpoint (int3). */ +/* + * Replace a relative jump (JMP.d32) with a breakpoint (INT3). + * + * After that, we can restore the 4 bytes after the INT3 to undo what + * arch_optimize_kprobes() scribbled. This is safe since those bytes will be + * unused once the INT3 lands. + */ void arch_unoptimize_kprobe(struct optimized_kprobe *op) { - u8 insn_buff[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - insn_buff[0] = BREAKPOINT_INSTRUCTION; - memcpy(insn_buff + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, - op->optinsn.insn); + arch_arm_kprobe(&op->kp); + text_poke(op->kp.addr + INT3_INSN_SIZE, + op->optinsn.copied_insn, DISP32_SIZE); + text_poke_sync(); } /* diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 7969da939213..d0a19121c6a4 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -100,7 +100,12 @@ static int __init get_setup_data_size(int nr, size_t *size) if (!data) return -ENOMEM; if (nr == i) { - *size = data->len; + if (data->type == SETUP_INDIRECT && + ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) + *size = ((struct setup_indirect *)data->data)->len; + else + *size = data->len; + memunmap(data); return 0; } @@ -130,7 +135,10 @@ static ssize_t type_show(struct kobject *kobj, if (!data) return -ENOMEM; - ret = sprintf(buf, "0x%x\n", data->type); + if (data->type == SETUP_INDIRECT) + ret = sprintf(buf, "0x%x\n", ((struct setup_indirect *)data->data)->type); + else + ret = sprintf(buf, "0x%x\n", data->type); memunmap(data); return ret; } @@ -142,7 +150,7 @@ static ssize_t setup_data_data_read(struct file *fp, loff_t off, size_t count) { int nr, ret = 0; - u64 paddr; + u64 paddr, len; struct setup_data *data; void *p; @@ -157,19 +165,28 @@ static ssize_t setup_data_data_read(struct file *fp, if (!data) return -ENOMEM; - if (off > data->len) { + if (data->type == SETUP_INDIRECT && + ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { + paddr = ((struct setup_indirect *)data->data)->addr; + len = ((struct setup_indirect *)data->data)->len; + } else { + paddr += sizeof(*data); + len = data->len; + } + + if (off > len) { ret = -EINVAL; goto out; } - if (count > data->len - off) - count = data->len - off; + if (count > len - off) + count = len - off; if (!count) goto out; ret = count; - p = memremap(paddr + sizeof(*data), data->len, MEMREMAP_WB); + p = memremap(paddr, len, MEMREMAP_WB); if (!p) { ret = -ENOMEM; goto out; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4ab377c9fffe..d817f255aed8 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -33,6 +33,7 @@ #include <asm/apicdef.h> #include <asm/hypervisor.h> #include <asm/tlb.h> +#include <asm/cpuidle_haltpoll.h> static int kvmapf = 1; @@ -244,17 +245,13 @@ NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason); dotraplinkage void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { - enum ctx_state prev_state; - switch (kvm_read_and_reset_pf_reason()) { default: do_page_fault(regs, error_code, address); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - prev_state = exception_enter(); kvm_async_pf_task_wait((u32)address, !user_mode(regs)); - exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); @@ -311,7 +308,7 @@ static void kvm_guest_cpu_init(void) if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) { u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION pa |= KVM_ASYNC_PF_SEND_ALWAYS; #endif pa |= KVM_ASYNC_PF_ENABLED; @@ -502,16 +499,6 @@ static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) __send_ipi_mask(local_mask, vector); } -static void kvm_send_ipi_allbutself(int vector) -{ - kvm_send_ipi_mask_allbutself(cpu_online_mask, vector); -} - -static void kvm_send_ipi_all(int vector) -{ - __send_ipi_mask(cpu_online_mask, vector); -} - /* * Set the IPI entry points */ @@ -519,8 +506,6 @@ static void kvm_setup_pv_ipi(void) { apic->send_IPI_mask = kvm_send_ipi_mask; apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself; - apic->send_IPI_allbutself = kvm_send_ipi_allbutself; - apic->send_IPI_all = kvm_send_ipi_all; pr_info("KVM setup pv IPIs\n"); } @@ -705,6 +690,7 @@ unsigned int kvm_arch_para_hints(void) { return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES); } +EXPORT_SYMBOL_GPL(kvm_arch_para_hints); static uint32_t __init kvm_detect(void) { @@ -750,6 +736,9 @@ static __init int kvm_setup_pv_tlb_flush(void) { int cpu; + if (!kvm_para_available() || nopv) + return 0; + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { @@ -867,3 +856,39 @@ void __init kvm_spinlock_init(void) } #endif /* CONFIG_PARAVIRT_SPINLOCKS */ + +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + +static void kvm_disable_host_haltpoll(void *i) +{ + wrmsrl(MSR_KVM_POLL_CONTROL, 0); +} + +static void kvm_enable_host_haltpoll(void *i) +{ + wrmsrl(MSR_KVM_POLL_CONTROL, 1); +} + +void arch_haltpoll_enable(unsigned int cpu) +{ + if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) { + pr_err_once("kvm: host does not support poll control\n"); + pr_err_once("kvm: host upgrade recommended\n"); + return; + } + + /* Enable guest halt poll disables host halt poll */ + smp_call_function_single(cpu, kvm_disable_host_haltpoll, NULL, 1); +} +EXPORT_SYMBOL_GPL(arch_haltpoll_enable); + +void arch_haltpoll_disable(unsigned int cpu) +{ + if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) + return; + + /* Enable guest halt poll disables host halt poll */ + smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1); +} +EXPORT_SYMBOL_GPL(arch_haltpoll_disable); +#endif diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index b2463fcb20a8..c57e1ca70fd1 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -28,6 +28,89 @@ #include <asm/desc.h> #include <asm/mmu_context.h> #include <asm/syscalls.h> +#include <asm/pgtable_areas.h> + +/* This is a multiple of PAGE_SIZE. */ +#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) + +static inline void *ldt_slot_va(int slot) +{ + return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); +} + +void load_mm_ldt(struct mm_struct *mm) +{ + struct ldt_struct *ldt; + + /* READ_ONCE synchronizes with smp_store_release */ + ldt = READ_ONCE(mm->context.ldt); + + /* + * Any change to mm->context.ldt is followed by an IPI to all + * CPUs with the mm active. The LDT will not be freed until + * after the IPI is handled by all such CPUs. This means that, + * if the ldt_struct changes before we return, the values we see + * will be safe, and the new values will be loaded before we run + * any user code. + * + * NB: don't try to convert this to use RCU without extreme care. + * We would still need IRQs off, because we don't want to change + * the local LDT after an IPI loaded a newer value than the one + * that we can see. + */ + + if (unlikely(ldt)) { + if (static_cpu_has(X86_FEATURE_PTI)) { + if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { + /* + * Whoops -- either the new LDT isn't mapped + * (if slot == -1) or is mapped into a bogus + * slot (if slot > 1). + */ + clear_LDT(); + return; + } + + /* + * If page table isolation is enabled, ldt->entries + * will not be mapped in the userspace pagetables. + * Tell the CPU to access the LDT through the alias + * at ldt_slot_va(ldt->slot). + */ + set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); + } else { + set_ldt(ldt->entries, ldt->nr_entries); + } + } else { + clear_LDT(); + } +} + +void switch_ldt(struct mm_struct *prev, struct mm_struct *next) +{ + /* + * Load the LDT if either the old or new mm had an LDT. + * + * An mm will never go from having an LDT to not having an LDT. Two + * mms never share an LDT, so we don't gain anything by checking to + * see whether the LDT changed. There's also no guarantee that + * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, + * then prev->context.ldt will also be non-NULL. + * + * If we really cared, we could optimize the case where prev == next + * and we're exiting lazy mode. Most of the time, if this happens, + * we don't actually need to reload LDTR, but modify_ldt() is mostly + * used by legacy code and emulators where we don't need this level of + * performance. + * + * This uses | instead of || because it generates better code. + */ + if (unlikely((unsigned long)prev->context.ldt | + (unsigned long)next->context.ldt)) + load_mm_ldt(next); + + DEBUG_LOCKS_WARN_ON(preemptible()); +} static void refresh_ldt_segments(void) { diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 77854b192fef..02bddfc122a4 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -148,7 +148,7 @@ int machine_kexec_prepare(struct kimage *image) { int error; - set_pages_x(image->control_code_page, 1); + set_memory_x((unsigned long)page_address(image->control_code_page), 1); error = machine_kexec_alloc_page_tables(image); if (error) return error; @@ -162,7 +162,7 @@ int machine_kexec_prepare(struct kimage *image) */ void machine_kexec_cleanup(struct kimage *image) { - set_pages_nx(image->control_code_page, 1); + set_memory_nx((unsigned long)page_address(image->control_code_page), 1); machine_kexec_free_page_tables(image); } @@ -250,15 +250,3 @@ void machine_kexec(struct kimage *image) __ftrace_enabled_restore(save_ftrace_enabled); } - -void arch_crash_save_vmcoreinfo(void) -{ -#ifdef CONFIG_NUMA - VMCOREINFO_SYMBOL(node_data); - VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); -#endif -#ifdef CONFIG_X86_PAE - VMCOREINFO_CONFIG(X86_PAE); -#endif -} - diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 5dcd438ad8f2..ad5cdd6a5f23 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -298,48 +298,6 @@ static void load_segments(void) ); } -#ifdef CONFIG_KEXEC_FILE -/* Update purgatory as needed after various image segments have been prepared */ -static int arch_update_purgatory(struct kimage *image) -{ - int ret = 0; - - if (!image->file_mode) - return 0; - - /* Setup copying of backup region */ - if (image->type == KEXEC_TYPE_CRASH) { - ret = kexec_purgatory_get_set_symbol(image, - "purgatory_backup_dest", - &image->arch.backup_load_addr, - sizeof(image->arch.backup_load_addr), 0); - if (ret) - return ret; - - ret = kexec_purgatory_get_set_symbol(image, - "purgatory_backup_src", - &image->arch.backup_src_start, - sizeof(image->arch.backup_src_start), 0); - if (ret) - return ret; - - ret = kexec_purgatory_get_set_symbol(image, - "purgatory_backup_sz", - &image->arch.backup_src_sz, - sizeof(image->arch.backup_src_sz), 0); - if (ret) - return ret; - } - - return ret; -} -#else /* !CONFIG_KEXEC_FILE */ -static inline int arch_update_purgatory(struct kimage *image) -{ - return 0; -} -#endif /* CONFIG_KEXEC_FILE */ - int machine_kexec_prepare(struct kimage *image) { unsigned long start_pgtable; @@ -353,11 +311,6 @@ int machine_kexec_prepare(struct kimage *image) if (result) return result; - /* update purgatory as needed */ - result = arch_update_purgatory(image); - if (result) - return result; - return 0; } @@ -445,25 +398,6 @@ void machine_kexec(struct kimage *image) __ftrace_enabled_restore(save_ftrace_enabled); } -void arch_crash_save_vmcoreinfo(void) -{ - u64 sme_mask = sme_me_mask; - - VMCOREINFO_NUMBER(phys_base); - VMCOREINFO_SYMBOL(init_top_pgt); - vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n", - pgtable_l5_enabled()); - -#ifdef CONFIG_NUMA - VMCOREINFO_SYMBOL(node_data); - VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); -#endif - vmcoreinfo_append_str("KERNELOFFSET=%lx\n", - kaslr_offset()); - VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); - VMCOREINFO_NUMBER(sme_mask); -} - /* arch-dependent functionality related to kexec file-based syscall */ #ifdef CONFIG_KEXEC_FILE diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 3db2252b958d..1547be359d7f 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -34,6 +34,7 @@ #include <linux/notifier.h> #include <linux/uaccess.h> #include <linux/gfp.h> +#include <linux/security.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -79,6 +80,10 @@ static ssize_t msr_write(struct file *file, const char __user *buf, int err = 0; ssize_t bytes = 0; + err = security_locked_down(LOCKDOWN_MSR); + if (err) + return err; + if (count % 8) return -EINVAL; /* Invalid chunk size */ @@ -130,6 +135,9 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) err = -EFAULT; break; } + err = security_locked_down(LOCKDOWN_MSR); + if (err) + break; err = wrmsr_safe_regs_on_cpu(cpu, regs); if (err) break; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4df7705022b9..54c21d6abd5a 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -104,18 +104,22 @@ static int __init nmi_warning_debugfs(void) } fs_initcall(nmi_warning_debugfs); -static void nmi_max_handler(struct irq_work *w) +static void nmi_check_duration(struct nmiaction *action, u64 duration) { - struct nmiaction *a = container_of(w, struct nmiaction, irq_work); + u64 whole_msecs = READ_ONCE(action->max_duration); int remainder_ns, decimal_msecs; - u64 whole_msecs = READ_ONCE(a->max_duration); + + if (duration < nmi_longest_ns || duration < action->max_duration) + return; + + action->max_duration = duration; remainder_ns = do_div(whole_msecs, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; printk_ratelimited(KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", - a->handler, whole_msecs, decimal_msecs); + action->handler, whole_msecs, decimal_msecs); } static int nmi_handle(unsigned int type, struct pt_regs *regs) @@ -142,11 +146,7 @@ static int nmi_handle(unsigned int type, struct pt_regs *regs) delta = sched_clock() - delta; trace_nmi_handler(a->handler, (int)delta, thishandled); - if (delta < nmi_longest_ns || delta < a->max_duration) - continue; - - a->max_duration = delta; - irq_work_queue(&a->irq_work); + nmi_check_duration(a, delta); } rcu_read_unlock(); @@ -164,8 +164,6 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) if (!action->handler) return -EINVAL; - init_irq_work(&action->irq_work, nmi_max_handler); - raw_spin_lock_irqsave(&desc->lock, flags); /* @@ -512,6 +510,9 @@ NOKPROBE_SYMBOL(is_debug_stack); dotraplinkage notrace void do_nmi(struct pt_regs *regs, long error_code) { + if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id())) + return; + if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { this_cpu_write(nmi_state, NMI_LATCHED); return; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 0aa6256eedd8..789f5e4f89de 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -311,10 +311,6 @@ struct paravirt_patch_template pv_ops = { .cpu.read_cr0 = native_read_cr0, .cpu.write_cr0 = native_write_cr0, .cpu.write_cr4 = native_write_cr4, -#ifdef CONFIG_X86_64 - .cpu.read_cr8 = native_read_cr8, - .cpu.write_cr8 = native_write_cr8, -#endif .cpu.wbinvd = native_wbinvd, .cpu.read_msr = native_read_msr, .cpu.write_msr = native_write_msr, @@ -345,8 +341,6 @@ struct paravirt_patch_template pv_ops = { .cpu.iret = native_iret, .cpu.swapgs = native_swapgs, - .cpu.set_iopl_mask = native_set_iopl_mask, - .cpu.start_context_switch = paravirt_nop, .cpu.end_context_switch = paravirt_nop, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c deleted file mode 100644 index 9d4343aa481b..000000000000 --- a/arch/x86/kernel/pci-calgary_64.c +++ /dev/null @@ -1,1584 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Derived from arch/powerpc/kernel/iommu.c - * - * Copyright IBM Corporation, 2006-2007 - * Copyright (C) 2006 Jon Mason <jdmason@kudzu.us> - * - * Author: Jon Mason <jdmason@kudzu.us> - * Author: Muli Ben-Yehuda <muli@il.ibm.com> - - */ - -#define pr_fmt(fmt) "Calgary: " fmt - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/slab.h> -#include <linux/mm.h> -#include <linux/spinlock.h> -#include <linux/string.h> -#include <linux/crash_dump.h> -#include <linux/dma-mapping.h> -#include <linux/dma-direct.h> -#include <linux/bitmap.h> -#include <linux/pci_ids.h> -#include <linux/pci.h> -#include <linux/delay.h> -#include <linux/scatterlist.h> -#include <linux/iommu-helper.h> - -#include <asm/iommu.h> -#include <asm/calgary.h> -#include <asm/tce.h> -#include <asm/pci-direct.h> -#include <asm/dma.h> -#include <asm/rio.h> -#include <asm/bios_ebda.h> -#include <asm/x86_init.h> -#include <asm/iommu_table.h> - -#ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT -int use_calgary __read_mostly = 1; -#else -int use_calgary __read_mostly = 0; -#endif /* CONFIG_CALGARY_DEFAULT_ENABLED */ - -#define PCI_DEVICE_ID_IBM_CALGARY 0x02a1 -#define PCI_DEVICE_ID_IBM_CALIOC2 0x0308 - -/* register offsets inside the host bridge space */ -#define CALGARY_CONFIG_REG 0x0108 -#define PHB_CSR_OFFSET 0x0110 /* Channel Status */ -#define PHB_PLSSR_OFFSET 0x0120 -#define PHB_CONFIG_RW_OFFSET 0x0160 -#define PHB_IOBASE_BAR_LOW 0x0170 -#define PHB_IOBASE_BAR_HIGH 0x0180 -#define PHB_MEM_1_LOW 0x0190 -#define PHB_MEM_1_HIGH 0x01A0 -#define PHB_IO_ADDR_SIZE 0x01B0 -#define PHB_MEM_1_SIZE 0x01C0 -#define PHB_MEM_ST_OFFSET 0x01D0 -#define PHB_AER_OFFSET 0x0200 -#define PHB_CONFIG_0_HIGH 0x0220 -#define PHB_CONFIG_0_LOW 0x0230 -#define PHB_CONFIG_0_END 0x0240 -#define PHB_MEM_2_LOW 0x02B0 -#define PHB_MEM_2_HIGH 0x02C0 -#define PHB_MEM_2_SIZE_HIGH 0x02D0 -#define PHB_MEM_2_SIZE_LOW 0x02E0 -#define PHB_DOSHOLE_OFFSET 0x08E0 - -/* CalIOC2 specific */ -#define PHB_SAVIOR_L2 0x0DB0 -#define PHB_PAGE_MIG_CTRL 0x0DA8 -#define PHB_PAGE_MIG_DEBUG 0x0DA0 -#define PHB_ROOT_COMPLEX_STATUS 0x0CB0 - -/* PHB_CONFIG_RW */ -#define PHB_TCE_ENABLE 0x20000000 -#define PHB_SLOT_DISABLE 0x1C000000 -#define PHB_DAC_DISABLE 0x01000000 -#define PHB_MEM2_ENABLE 0x00400000 -#define PHB_MCSR_ENABLE 0x00100000 -/* TAR (Table Address Register) */ -#define TAR_SW_BITS 0x0000ffffffff800fUL -#define TAR_VALID 0x0000000000000008UL -/* CSR (Channel/DMA Status Register) */ -#define CSR_AGENT_MASK 0xffe0ffff -/* CCR (Calgary Configuration Register) */ -#define CCR_2SEC_TIMEOUT 0x000000000000000EUL -/* PMCR/PMDR (Page Migration Control/Debug Registers */ -#define PMR_SOFTSTOP 0x80000000 -#define PMR_SOFTSTOPFAULT 0x40000000 -#define PMR_HARDSTOP 0x20000000 - -/* - * The maximum PHB bus number. - * x3950M2 (rare): 8 chassis, 48 PHBs per chassis = 384 - * x3950M2: 4 chassis, 48 PHBs per chassis = 192 - * x3950 (PCIE): 8 chassis, 32 PHBs per chassis = 256 - * x3950 (PCIX): 8 chassis, 16 PHBs per chassis = 128 - */ -#define MAX_PHB_BUS_NUM 256 - -#define PHBS_PER_CALGARY 4 - -/* register offsets in Calgary's internal register space */ -static const unsigned long tar_offsets[] = { - 0x0580 /* TAR0 */, - 0x0588 /* TAR1 */, - 0x0590 /* TAR2 */, - 0x0598 /* TAR3 */ -}; - -static const unsigned long split_queue_offsets[] = { - 0x4870 /* SPLIT QUEUE 0 */, - 0x5870 /* SPLIT QUEUE 1 */, - 0x6870 /* SPLIT QUEUE 2 */, - 0x7870 /* SPLIT QUEUE 3 */ -}; - -static const unsigned long phb_offsets[] = { - 0x8000 /* PHB0 */, - 0x9000 /* PHB1 */, - 0xA000 /* PHB2 */, - 0xB000 /* PHB3 */ -}; - -/* PHB debug registers */ - -static const unsigned long phb_debug_offsets[] = { - 0x4000 /* PHB 0 DEBUG */, - 0x5000 /* PHB 1 DEBUG */, - 0x6000 /* PHB 2 DEBUG */, - 0x7000 /* PHB 3 DEBUG */ -}; - -/* - * STUFF register for each debug PHB, - * byte 1 = start bus number, byte 2 = end bus number - */ - -#define PHB_DEBUG_STUFF_OFFSET 0x0020 - -unsigned int specified_table_size = TCE_TABLE_SIZE_UNSPECIFIED; -static int translate_empty_slots __read_mostly = 0; -static int calgary_detected __read_mostly = 0; - -static struct rio_table_hdr *rio_table_hdr __initdata; -static struct scal_detail *scal_devs[MAX_NUMNODES] __initdata; -static struct rio_detail *rio_devs[MAX_NUMNODES * 4] __initdata; - -struct calgary_bus_info { - void *tce_space; - unsigned char translation_disabled; - signed char phbid; - void __iomem *bbar; -}; - -static void calgary_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev); -static void calgary_tce_cache_blast(struct iommu_table *tbl); -static void calgary_dump_error_regs(struct iommu_table *tbl); -static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev); -static void calioc2_tce_cache_blast(struct iommu_table *tbl); -static void calioc2_dump_error_regs(struct iommu_table *tbl); -static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl); -static void get_tce_space_from_tar(void); - -static const struct cal_chipset_ops calgary_chip_ops = { - .handle_quirks = calgary_handle_quirks, - .tce_cache_blast = calgary_tce_cache_blast, - .dump_error_regs = calgary_dump_error_regs -}; - -static const struct cal_chipset_ops calioc2_chip_ops = { - .handle_quirks = calioc2_handle_quirks, - .tce_cache_blast = calioc2_tce_cache_blast, - .dump_error_regs = calioc2_dump_error_regs -}; - -static struct calgary_bus_info bus_info[MAX_PHB_BUS_NUM] = { { NULL, 0, 0 }, }; - -static inline int translation_enabled(struct iommu_table *tbl) -{ - /* only PHBs with translation enabled have an IOMMU table */ - return (tbl != NULL); -} - -static void iommu_range_reserve(struct iommu_table *tbl, - unsigned long start_addr, unsigned int npages) -{ - unsigned long index; - unsigned long end; - unsigned long flags; - - index = start_addr >> PAGE_SHIFT; - - /* bail out if we're asked to reserve a region we don't cover */ - if (index >= tbl->it_size) - return; - - end = index + npages; - if (end > tbl->it_size) /* don't go off the table */ - end = tbl->it_size; - - spin_lock_irqsave(&tbl->it_lock, flags); - - bitmap_set(tbl->it_map, index, npages); - - spin_unlock_irqrestore(&tbl->it_lock, flags); -} - -static unsigned long iommu_range_alloc(struct device *dev, - struct iommu_table *tbl, - unsigned int npages) -{ - unsigned long flags; - unsigned long offset; - unsigned long boundary_size; - - boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, - PAGE_SIZE) >> PAGE_SHIFT; - - BUG_ON(npages == 0); - - spin_lock_irqsave(&tbl->it_lock, flags); - - offset = iommu_area_alloc(tbl->it_map, tbl->it_size, tbl->it_hint, - npages, 0, boundary_size, 0); - if (offset == ~0UL) { - tbl->chip_ops->tce_cache_blast(tbl); - - offset = iommu_area_alloc(tbl->it_map, tbl->it_size, 0, - npages, 0, boundary_size, 0); - if (offset == ~0UL) { - pr_warn("IOMMU full\n"); - spin_unlock_irqrestore(&tbl->it_lock, flags); - if (panic_on_overflow) - panic("Calgary: fix the allocator.\n"); - else - return DMA_MAPPING_ERROR; - } - } - - tbl->it_hint = offset + npages; - BUG_ON(tbl->it_hint > tbl->it_size); - - spin_unlock_irqrestore(&tbl->it_lock, flags); - - return offset; -} - -static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, - void *vaddr, unsigned int npages, int direction) -{ - unsigned long entry; - dma_addr_t ret; - - entry = iommu_range_alloc(dev, tbl, npages); - if (unlikely(entry == DMA_MAPPING_ERROR)) { - pr_warn("failed to allocate %u pages in iommu %p\n", - npages, tbl); - return DMA_MAPPING_ERROR; - } - - /* set the return dma address */ - ret = (entry << PAGE_SHIFT) | ((unsigned long)vaddr & ~PAGE_MASK); - - /* put the TCEs in the HW table */ - tce_build(tbl, entry, npages, (unsigned long)vaddr & PAGE_MASK, - direction); - return ret; -} - -static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, - unsigned int npages) -{ - unsigned long entry; - unsigned long flags; - - /* were we called with bad_dma_address? */ - if (unlikely(dma_addr == DMA_MAPPING_ERROR)) { - WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA " - "address 0x%Lx\n", dma_addr); - return; - } - - entry = dma_addr >> PAGE_SHIFT; - - BUG_ON(entry + npages > tbl->it_size); - - tce_free(tbl, entry, npages); - - spin_lock_irqsave(&tbl->it_lock, flags); - - bitmap_clear(tbl->it_map, entry, npages); - - spin_unlock_irqrestore(&tbl->it_lock, flags); -} - -static inline struct iommu_table *find_iommu_table(struct device *dev) -{ - struct pci_dev *pdev; - struct pci_bus *pbus; - struct iommu_table *tbl; - - pdev = to_pci_dev(dev); - - /* search up the device tree for an iommu */ - pbus = pdev->bus; - do { - tbl = pci_iommu(pbus); - if (tbl && tbl->it_busno == pbus->number) - break; - tbl = NULL; - pbus = pbus->parent; - } while (pbus); - - BUG_ON(tbl && (tbl->it_busno != pbus->number)); - - return tbl; -} - -static void calgary_unmap_sg(struct device *dev, struct scatterlist *sglist, - int nelems,enum dma_data_direction dir, - unsigned long attrs) -{ - struct iommu_table *tbl = find_iommu_table(dev); - struct scatterlist *s; - int i; - - if (!translation_enabled(tbl)) - return; - - for_each_sg(sglist, s, nelems, i) { - unsigned int npages; - dma_addr_t dma = s->dma_address; - unsigned int dmalen = s->dma_length; - - if (dmalen == 0) - break; - - npages = iommu_num_pages(dma, dmalen, PAGE_SIZE); - iommu_free(tbl, dma, npages); - } -} - -static int calgary_map_sg(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir, - unsigned long attrs) -{ - struct iommu_table *tbl = find_iommu_table(dev); - struct scatterlist *s; - unsigned long vaddr; - unsigned int npages; - unsigned long entry; - int i; - - for_each_sg(sg, s, nelems, i) { - BUG_ON(!sg_page(s)); - - vaddr = (unsigned long) sg_virt(s); - npages = iommu_num_pages(vaddr, s->length, PAGE_SIZE); - - entry = iommu_range_alloc(dev, tbl, npages); - if (entry == DMA_MAPPING_ERROR) { - /* makes sure unmap knows to stop */ - s->dma_length = 0; - goto error; - } - - s->dma_address = (entry << PAGE_SHIFT) | s->offset; - - /* insert into HW table */ - tce_build(tbl, entry, npages, vaddr & PAGE_MASK, dir); - - s->dma_length = s->length; - } - - return nelems; -error: - calgary_unmap_sg(dev, sg, nelems, dir, 0); - for_each_sg(sg, s, nelems, i) { - sg->dma_address = DMA_MAPPING_ERROR; - sg->dma_length = 0; - } - return 0; -} - -static dma_addr_t calgary_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - void *vaddr = page_address(page) + offset; - unsigned long uaddr; - unsigned int npages; - struct iommu_table *tbl = find_iommu_table(dev); - - uaddr = (unsigned long)vaddr; - npages = iommu_num_pages(uaddr, size, PAGE_SIZE); - - return iommu_alloc(dev, tbl, vaddr, npages, dir); -} - -static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - struct iommu_table *tbl = find_iommu_table(dev); - unsigned int npages; - - npages = iommu_num_pages(dma_addr, size, PAGE_SIZE); - iommu_free(tbl, dma_addr, npages); -} - -static void* calgary_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) -{ - void *ret = NULL; - dma_addr_t mapping; - unsigned int npages, order; - struct iommu_table *tbl = find_iommu_table(dev); - - size = PAGE_ALIGN(size); /* size rounded up to full pages */ - npages = size >> PAGE_SHIFT; - order = get_order(size); - - /* alloc enough pages (and possibly more) */ - ret = (void *)__get_free_pages(flag, order); - if (!ret) - goto error; - memset(ret, 0, size); - - /* set up tces to cover the allocated range */ - mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL); - if (mapping == DMA_MAPPING_ERROR) - goto free; - *dma_handle = mapping; - return ret; -free: - free_pages((unsigned long)ret, get_order(size)); - ret = NULL; -error: - return ret; -} - -static void calgary_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ - unsigned int npages; - struct iommu_table *tbl = find_iommu_table(dev); - - size = PAGE_ALIGN(size); - npages = size >> PAGE_SHIFT; - - iommu_free(tbl, dma_handle, npages); - free_pages((unsigned long)vaddr, get_order(size)); -} - -static const struct dma_map_ops calgary_dma_ops = { - .alloc = calgary_alloc_coherent, - .free = calgary_free_coherent, - .map_sg = calgary_map_sg, - .unmap_sg = calgary_unmap_sg, - .map_page = calgary_map_page, - .unmap_page = calgary_unmap_page, - .dma_supported = dma_direct_supported, -}; - -static inline void __iomem * busno_to_bbar(unsigned char num) -{ - return bus_info[num].bbar; -} - -static inline int busno_to_phbid(unsigned char num) -{ - return bus_info[num].phbid; -} - -static inline unsigned long split_queue_offset(unsigned char num) -{ - size_t idx = busno_to_phbid(num); - - return split_queue_offsets[idx]; -} - -static inline unsigned long tar_offset(unsigned char num) -{ - size_t idx = busno_to_phbid(num); - - return tar_offsets[idx]; -} - -static inline unsigned long phb_offset(unsigned char num) -{ - size_t idx = busno_to_phbid(num); - - return phb_offsets[idx]; -} - -static inline void __iomem* calgary_reg(void __iomem *bar, unsigned long offset) -{ - unsigned long target = ((unsigned long)bar) | offset; - return (void __iomem*)target; -} - -static inline int is_calioc2(unsigned short device) -{ - return (device == PCI_DEVICE_ID_IBM_CALIOC2); -} - -static inline int is_calgary(unsigned short device) -{ - return (device == PCI_DEVICE_ID_IBM_CALGARY); -} - -static inline int is_cal_pci_dev(unsigned short device) -{ - return (is_calgary(device) || is_calioc2(device)); -} - -static void calgary_tce_cache_blast(struct iommu_table *tbl) -{ - u64 val; - u32 aer; - int i = 0; - void __iomem *bbar = tbl->bbar; - void __iomem *target; - - /* disable arbitration on the bus */ - target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_AER_OFFSET); - aer = readl(target); - writel(0, target); - - /* read plssr to ensure it got there */ - target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_PLSSR_OFFSET); - val = readl(target); - - /* poll split queues until all DMA activity is done */ - target = calgary_reg(bbar, split_queue_offset(tbl->it_busno)); - do { - val = readq(target); - i++; - } while ((val & 0xff) != 0xff && i < 100); - if (i == 100) - pr_warn("PCI bus not quiesced, continuing anyway\n"); - - /* invalidate TCE cache */ - target = calgary_reg(bbar, tar_offset(tbl->it_busno)); - writeq(tbl->tar_val, target); - - /* enable arbitration */ - target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_AER_OFFSET); - writel(aer, target); - (void)readl(target); /* flush */ -} - -static void calioc2_tce_cache_blast(struct iommu_table *tbl) -{ - void __iomem *bbar = tbl->bbar; - void __iomem *target; - u64 val64; - u32 val; - int i = 0; - int count = 1; - unsigned char bus = tbl->it_busno; - -begin: - printk(KERN_DEBUG "Calgary: CalIOC2 bus 0x%x entering tce cache blast " - "sequence - count %d\n", bus, count); - - /* 1. using the Page Migration Control reg set SoftStop */ - target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL); - val = be32_to_cpu(readl(target)); - printk(KERN_DEBUG "1a. read 0x%x [LE] from %p\n", val, target); - val |= PMR_SOFTSTOP; - printk(KERN_DEBUG "1b. writing 0x%x [LE] to %p\n", val, target); - writel(cpu_to_be32(val), target); - - /* 2. poll split queues until all DMA activity is done */ - printk(KERN_DEBUG "2a. starting to poll split queues\n"); - target = calgary_reg(bbar, split_queue_offset(bus)); - do { - val64 = readq(target); - i++; - } while ((val64 & 0xff) != 0xff && i < 100); - if (i == 100) - pr_warn("CalIOC2: PCI bus not quiesced, continuing anyway\n"); - - /* 3. poll Page Migration DEBUG for SoftStopFault */ - target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_DEBUG); - val = be32_to_cpu(readl(target)); - printk(KERN_DEBUG "3. read 0x%x [LE] from %p\n", val, target); - - /* 4. if SoftStopFault - goto (1) */ - if (val & PMR_SOFTSTOPFAULT) { - if (++count < 100) - goto begin; - else { - pr_warn("CalIOC2: too many SoftStopFaults, aborting TCE cache flush sequence!\n"); - return; /* pray for the best */ - } - } - - /* 5. Slam into HardStop by reading PHB_PAGE_MIG_CTRL */ - target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL); - printk(KERN_DEBUG "5a. slamming into HardStop by reading %p\n", target); - val = be32_to_cpu(readl(target)); - printk(KERN_DEBUG "5b. read 0x%x [LE] from %p\n", val, target); - target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_DEBUG); - val = be32_to_cpu(readl(target)); - printk(KERN_DEBUG "5c. read 0x%x [LE] from %p (debug)\n", val, target); - - /* 6. invalidate TCE cache */ - printk(KERN_DEBUG "6. invalidating TCE cache\n"); - target = calgary_reg(bbar, tar_offset(bus)); - writeq(tbl->tar_val, target); - - /* 7. Re-read PMCR */ - printk(KERN_DEBUG "7a. Re-reading PMCR\n"); - target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL); - val = be32_to_cpu(readl(target)); - printk(KERN_DEBUG "7b. read 0x%x [LE] from %p\n", val, target); - - /* 8. Remove HardStop */ - printk(KERN_DEBUG "8a. removing HardStop from PMCR\n"); - target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL); - val = 0; - printk(KERN_DEBUG "8b. writing 0x%x [LE] to %p\n", val, target); - writel(cpu_to_be32(val), target); - val = be32_to_cpu(readl(target)); - printk(KERN_DEBUG "8c. read 0x%x [LE] from %p\n", val, target); -} - -static void __init calgary_reserve_mem_region(struct pci_dev *dev, u64 start, - u64 limit) -{ - unsigned int numpages; - - limit = limit | 0xfffff; - limit++; - - numpages = ((limit - start) >> PAGE_SHIFT); - iommu_range_reserve(pci_iommu(dev->bus), start, numpages); -} - -static void __init calgary_reserve_peripheral_mem_1(struct pci_dev *dev) -{ - void __iomem *target; - u64 low, high, sizelow; - u64 start, limit; - struct iommu_table *tbl = pci_iommu(dev->bus); - unsigned char busnum = dev->bus->number; - void __iomem *bbar = tbl->bbar; - - /* peripheral MEM_1 region */ - target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_1_LOW); - low = be32_to_cpu(readl(target)); - target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_1_HIGH); - high = be32_to_cpu(readl(target)); - target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_1_SIZE); - sizelow = be32_to_cpu(readl(target)); - - start = (high << 32) | low; - limit = sizelow; - - calgary_reserve_mem_region(dev, start, limit); -} - -static void __init calgary_reserve_peripheral_mem_2(struct pci_dev *dev) -{ - void __iomem *target; - u32 val32; - u64 low, high, sizelow, sizehigh; - u64 start, limit; - struct iommu_table *tbl = pci_iommu(dev->bus); - unsigned char busnum = dev->bus->number; - void __iomem *bbar = tbl->bbar; - - /* is it enabled? */ - target = calgary_reg(bbar, phb_offset(busnum) | PHB_CONFIG_RW_OFFSET); - val32 = be32_to_cpu(readl(target)); - if (!(val32 & PHB_MEM2_ENABLE)) - return; - - target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_2_LOW); - low = be32_to_cpu(readl(target)); - target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_2_HIGH); - high = be32_to_cpu(readl(target)); - target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_2_SIZE_LOW); - sizelow = be32_to_cpu(readl(target)); - target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_2_SIZE_HIGH); - sizehigh = be32_to_cpu(readl(target)); - - start = (high << 32) | low; - limit = (sizehigh << 32) | sizelow; - - calgary_reserve_mem_region(dev, start, limit); -} - -/* - * some regions of the IO address space do not get translated, so we - * must not give devices IO addresses in those regions. The regions - * are the 640KB-1MB region and the two PCI peripheral memory holes. - * Reserve all of them in the IOMMU bitmap to avoid giving them out - * later. - */ -static void __init calgary_reserve_regions(struct pci_dev *dev) -{ - unsigned int npages; - u64 start; - struct iommu_table *tbl = pci_iommu(dev->bus); - - /* avoid the BIOS/VGA first 640KB-1MB region */ - /* for CalIOC2 - avoid the entire first MB */ - if (is_calgary(dev->device)) { - start = (640 * 1024); - npages = ((1024 - 640) * 1024) >> PAGE_SHIFT; - } else { /* calioc2 */ - start = 0; - npages = (1 * 1024 * 1024) >> PAGE_SHIFT; - } - iommu_range_reserve(tbl, start, npages); - - /* reserve the two PCI peripheral memory regions in IO space */ - calgary_reserve_peripheral_mem_1(dev); - calgary_reserve_peripheral_mem_2(dev); -} - -static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar) -{ - u64 val64; - u64 table_phys; - void __iomem *target; - int ret; - struct iommu_table *tbl; - - /* build TCE tables for each PHB */ - ret = build_tce_table(dev, bbar); - if (ret) - return ret; - - tbl = pci_iommu(dev->bus); - tbl->it_base = (unsigned long)bus_info[dev->bus->number].tce_space; - - if (is_kdump_kernel()) - calgary_init_bitmap_from_tce_table(tbl); - else - tce_free(tbl, 0, tbl->it_size); - - if (is_calgary(dev->device)) - tbl->chip_ops = &calgary_chip_ops; - else if (is_calioc2(dev->device)) - tbl->chip_ops = &calioc2_chip_ops; - else - BUG(); - - calgary_reserve_regions(dev); - - /* set TARs for each PHB */ - target = calgary_reg(bbar, tar_offset(dev->bus->number)); - val64 = be64_to_cpu(readq(target)); - - /* zero out all TAR bits under sw control */ - val64 &= ~TAR_SW_BITS; - table_phys = (u64)__pa(tbl->it_base); - - val64 |= table_phys; - - BUG_ON(specified_table_size > TCE_TABLE_SIZE_8M); - val64 |= (u64) specified_table_size; - - tbl->tar_val = cpu_to_be64(val64); - - writeq(tbl->tar_val, target); - readq(target); /* flush */ - - return 0; -} - -static void __init calgary_free_bus(struct pci_dev *dev) -{ - u64 val64; - struct iommu_table *tbl = pci_iommu(dev->bus); - void __iomem *target; - unsigned int bitmapsz; - - target = calgary_reg(tbl->bbar, tar_offset(dev->bus->number)); - val64 = be64_to_cpu(readq(target)); - val64 &= ~TAR_SW_BITS; - writeq(cpu_to_be64(val64), target); - readq(target); /* flush */ - - bitmapsz = tbl->it_size / BITS_PER_BYTE; - free_pages((unsigned long)tbl->it_map, get_order(bitmapsz)); - tbl->it_map = NULL; - - kfree(tbl); - - set_pci_iommu(dev->bus, NULL); - - /* Can't free bootmem allocated memory after system is up :-( */ - bus_info[dev->bus->number].tce_space = NULL; -} - -static void calgary_dump_error_regs(struct iommu_table *tbl) -{ - void __iomem *bbar = tbl->bbar; - void __iomem *target; - u32 csr, plssr; - - target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_CSR_OFFSET); - csr = be32_to_cpu(readl(target)); - - target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_PLSSR_OFFSET); - plssr = be32_to_cpu(readl(target)); - - /* If no error, the agent ID in the CSR is not valid */ - pr_emerg("DMA error on Calgary PHB 0x%x, 0x%08x@CSR 0x%08x@PLSSR\n", - tbl->it_busno, csr, plssr); -} - -static void calioc2_dump_error_regs(struct iommu_table *tbl) -{ - void __iomem *bbar = tbl->bbar; - u32 csr, csmr, plssr, mck, rcstat; - void __iomem *target; - unsigned long phboff = phb_offset(tbl->it_busno); - unsigned long erroff; - u32 errregs[7]; - int i; - - /* dump CSR */ - target = calgary_reg(bbar, phboff | PHB_CSR_OFFSET); - csr = be32_to_cpu(readl(target)); - /* dump PLSSR */ - target = calgary_reg(bbar, phboff | PHB_PLSSR_OFFSET); - plssr = be32_to_cpu(readl(target)); - /* dump CSMR */ - target = calgary_reg(bbar, phboff | 0x290); - csmr = be32_to_cpu(readl(target)); - /* dump mck */ - target = calgary_reg(bbar, phboff | 0x800); - mck = be32_to_cpu(readl(target)); - - pr_emerg("DMA error on CalIOC2 PHB 0x%x\n", tbl->it_busno); - - pr_emerg("0x%08x@CSR 0x%08x@PLSSR 0x%08x@CSMR 0x%08x@MCK\n", - csr, plssr, csmr, mck); - - /* dump rest of error regs */ - pr_emerg(""); - for (i = 0; i < ARRAY_SIZE(errregs); i++) { - /* err regs are at 0x810 - 0x870 */ - erroff = (0x810 + (i * 0x10)); - target = calgary_reg(bbar, phboff | erroff); - errregs[i] = be32_to_cpu(readl(target)); - pr_cont("0x%08x@0x%lx ", errregs[i], erroff); - } - pr_cont("\n"); - - /* root complex status */ - target = calgary_reg(bbar, phboff | PHB_ROOT_COMPLEX_STATUS); - rcstat = be32_to_cpu(readl(target)); - printk(KERN_EMERG "Calgary: 0x%08x@0x%x\n", rcstat, - PHB_ROOT_COMPLEX_STATUS); -} - -static void calgary_watchdog(struct timer_list *t) -{ - struct iommu_table *tbl = from_timer(tbl, t, watchdog_timer); - void __iomem *bbar = tbl->bbar; - u32 val32; - void __iomem *target; - - target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_CSR_OFFSET); - val32 = be32_to_cpu(readl(target)); - - /* If no error, the agent ID in the CSR is not valid */ - if (val32 & CSR_AGENT_MASK) { - tbl->chip_ops->dump_error_regs(tbl); - - /* reset error */ - writel(0, target); - - /* Disable bus that caused the error */ - target = calgary_reg(bbar, phb_offset(tbl->it_busno) | - PHB_CONFIG_RW_OFFSET); - val32 = be32_to_cpu(readl(target)); - val32 |= PHB_SLOT_DISABLE; - writel(cpu_to_be32(val32), target); - readl(target); /* flush */ - } else { - /* Reset the timer */ - mod_timer(&tbl->watchdog_timer, jiffies + 2 * HZ); - } -} - -static void __init calgary_set_split_completion_timeout(void __iomem *bbar, - unsigned char busnum, unsigned long timeout) -{ - u64 val64; - void __iomem *target; - unsigned int phb_shift = ~0; /* silence gcc */ - u64 mask; - - switch (busno_to_phbid(busnum)) { - case 0: phb_shift = (63 - 19); - break; - case 1: phb_shift = (63 - 23); - break; - case 2: phb_shift = (63 - 27); - break; - case 3: phb_shift = (63 - 35); - break; - default: - BUG_ON(busno_to_phbid(busnum)); - } - - target = calgary_reg(bbar, CALGARY_CONFIG_REG); - val64 = be64_to_cpu(readq(target)); - - /* zero out this PHB's timer bits */ - mask = ~(0xFUL << phb_shift); - val64 &= mask; - val64 |= (timeout << phb_shift); - writeq(cpu_to_be64(val64), target); - readq(target); /* flush */ -} - -static void __init calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev) -{ - unsigned char busnum = dev->bus->number; - void __iomem *bbar = tbl->bbar; - void __iomem *target; - u32 val; - - /* - * CalIOC2 designers recommend setting bit 8 in 0xnDB0 to 1 - */ - target = calgary_reg(bbar, phb_offset(busnum) | PHB_SAVIOR_L2); - val = cpu_to_be32(readl(target)); - val |= 0x00800000; - writel(cpu_to_be32(val), target); -} - -static void __init calgary_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev) -{ - unsigned char busnum = dev->bus->number; - - /* - * Give split completion a longer timeout on bus 1 for aic94xx - * http://bugzilla.kernel.org/show_bug.cgi?id=7180 - */ - if (is_calgary(dev->device) && (busnum == 1)) - calgary_set_split_completion_timeout(tbl->bbar, busnum, - CCR_2SEC_TIMEOUT); -} - -static void __init calgary_enable_translation(struct pci_dev *dev) -{ - u32 val32; - unsigned char busnum; - void __iomem *target; - void __iomem *bbar; - struct iommu_table *tbl; - - busnum = dev->bus->number; - tbl = pci_iommu(dev->bus); - bbar = tbl->bbar; - - /* enable TCE in PHB Config Register */ - target = calgary_reg(bbar, phb_offset(busnum) | PHB_CONFIG_RW_OFFSET); - val32 = be32_to_cpu(readl(target)); - val32 |= PHB_TCE_ENABLE | PHB_DAC_DISABLE | PHB_MCSR_ENABLE; - - printk(KERN_INFO "Calgary: enabling translation on %s PHB %#x\n", - (dev->device == PCI_DEVICE_ID_IBM_CALGARY) ? - "Calgary" : "CalIOC2", busnum); - printk(KERN_INFO "Calgary: errant DMAs will now be prevented on this " - "bus.\n"); - - writel(cpu_to_be32(val32), target); - readl(target); /* flush */ - - timer_setup(&tbl->watchdog_timer, calgary_watchdog, 0); - mod_timer(&tbl->watchdog_timer, jiffies); -} - -static void __init calgary_disable_translation(struct pci_dev *dev) -{ - u32 val32; - unsigned char busnum; - void __iomem *target; - void __iomem *bbar; - struct iommu_table *tbl; - - busnum = dev->bus->number; - tbl = pci_iommu(dev->bus); - bbar = tbl->bbar; - - /* disable TCE in PHB Config Register */ - target = calgary_reg(bbar, phb_offset(busnum) | PHB_CONFIG_RW_OFFSET); - val32 = be32_to_cpu(readl(target)); - val32 &= ~(PHB_TCE_ENABLE | PHB_DAC_DISABLE | PHB_MCSR_ENABLE); - - printk(KERN_INFO "Calgary: disabling translation on PHB %#x!\n", busnum); - writel(cpu_to_be32(val32), target); - readl(target); /* flush */ - - del_timer_sync(&tbl->watchdog_timer); -} - -static void __init calgary_init_one_nontraslated(struct pci_dev *dev) -{ - pci_dev_get(dev); - set_pci_iommu(dev->bus, NULL); - - /* is the device behind a bridge? */ - if (dev->bus->parent) - dev->bus->parent->self = dev; - else - dev->bus->self = dev; -} - -static int __init calgary_init_one(struct pci_dev *dev) -{ - void __iomem *bbar; - struct iommu_table *tbl; - int ret; - - bbar = busno_to_bbar(dev->bus->number); - ret = calgary_setup_tar(dev, bbar); - if (ret) - goto done; - - pci_dev_get(dev); - - if (dev->bus->parent) { - if (dev->bus->parent->self) - printk(KERN_WARNING "Calgary: IEEEE, dev %p has " - "bus->parent->self!\n", dev); - dev->bus->parent->self = dev; - } else - dev->bus->self = dev; - - tbl = pci_iommu(dev->bus); - tbl->chip_ops->handle_quirks(tbl, dev); - - calgary_enable_translation(dev); - - return 0; - -done: - return ret; -} - -static int __init calgary_locate_bbars(void) -{ - int ret; - int rioidx, phb, bus; - void __iomem *bbar; - void __iomem *target; - unsigned long offset; - u8 start_bus, end_bus; - u32 val; - - ret = -ENODATA; - for (rioidx = 0; rioidx < rio_table_hdr->num_rio_dev; rioidx++) { - struct rio_detail *rio = rio_devs[rioidx]; - - if ((rio->type != COMPAT_CALGARY) && (rio->type != ALT_CALGARY)) - continue; - - /* map entire 1MB of Calgary config space */ - bbar = ioremap_nocache(rio->BBAR, 1024 * 1024); - if (!bbar) - goto error; - - for (phb = 0; phb < PHBS_PER_CALGARY; phb++) { - offset = phb_debug_offsets[phb] | PHB_DEBUG_STUFF_OFFSET; - target = calgary_reg(bbar, offset); - - val = be32_to_cpu(readl(target)); - - start_bus = (u8)((val & 0x00FF0000) >> 16); - end_bus = (u8)((val & 0x0000FF00) >> 8); - - if (end_bus) { - for (bus = start_bus; bus <= end_bus; bus++) { - bus_info[bus].bbar = bbar; - bus_info[bus].phbid = phb; - } - } else { - bus_info[start_bus].bbar = bbar; - bus_info[start_bus].phbid = phb; - } - } - } - - return 0; - -error: - /* scan bus_info and iounmap any bbars we previously ioremap'd */ - for (bus = 0; bus < ARRAY_SIZE(bus_info); bus++) - if (bus_info[bus].bbar) - iounmap(bus_info[bus].bbar); - - return ret; -} - -static int __init calgary_init(void) -{ - int ret; - struct pci_dev *dev = NULL; - struct calgary_bus_info *info; - - ret = calgary_locate_bbars(); - if (ret) - return ret; - - /* Purely for kdump kernel case */ - if (is_kdump_kernel()) - get_tce_space_from_tar(); - - do { - dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev); - if (!dev) - break; - if (!is_cal_pci_dev(dev->device)) - continue; - - info = &bus_info[dev->bus->number]; - if (info->translation_disabled) { - calgary_init_one_nontraslated(dev); - continue; - } - - if (!info->tce_space && !translate_empty_slots) - continue; - - ret = calgary_init_one(dev); - if (ret) - goto error; - } while (1); - - dev = NULL; - for_each_pci_dev(dev) { - struct iommu_table *tbl; - - tbl = find_iommu_table(&dev->dev); - - if (translation_enabled(tbl)) - dev->dev.dma_ops = &calgary_dma_ops; - } - - return ret; - -error: - do { - dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev); - if (!dev) - break; - if (!is_cal_pci_dev(dev->device)) - continue; - - info = &bus_info[dev->bus->number]; - if (info->translation_disabled) { - pci_dev_put(dev); - continue; - } - if (!info->tce_space && !translate_empty_slots) - continue; - - calgary_disable_translation(dev); - calgary_free_bus(dev); - pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */ - dev->dev.dma_ops = NULL; - } while (1); - - return ret; -} - -static inline int __init determine_tce_table_size(void) -{ - int ret; - - if (specified_table_size != TCE_TABLE_SIZE_UNSPECIFIED) - return specified_table_size; - - if (is_kdump_kernel() && saved_max_pfn) { - /* - * Table sizes are from 0 to 7 (TCE_TABLE_SIZE_64K to - * TCE_TABLE_SIZE_8M). Table size 0 has 8K entries and each - * larger table size has twice as many entries, so shift the - * max ram address by 13 to divide by 8K and then look at the - * order of the result to choose between 0-7. - */ - ret = get_order((saved_max_pfn * PAGE_SIZE) >> 13); - if (ret > TCE_TABLE_SIZE_8M) - ret = TCE_TABLE_SIZE_8M; - } else { - /* - * Use 8M by default (suggested by Muli) if it's not - * kdump kernel and saved_max_pfn isn't set. - */ - ret = TCE_TABLE_SIZE_8M; - } - - return ret; -} - -static int __init build_detail_arrays(void) -{ - unsigned long ptr; - unsigned numnodes, i; - int scal_detail_size, rio_detail_size; - - numnodes = rio_table_hdr->num_scal_dev; - if (numnodes > MAX_NUMNODES){ - printk(KERN_WARNING - "Calgary: MAX_NUMNODES too low! Defined as %d, " - "but system has %d nodes.\n", - MAX_NUMNODES, numnodes); - return -ENODEV; - } - - switch (rio_table_hdr->version){ - case 2: - scal_detail_size = 11; - rio_detail_size = 13; - break; - case 3: - scal_detail_size = 12; - rio_detail_size = 15; - break; - default: - printk(KERN_WARNING - "Calgary: Invalid Rio Grande Table Version: %d\n", - rio_table_hdr->version); - return -EPROTO; - } - - ptr = ((unsigned long)rio_table_hdr) + 3; - for (i = 0; i < numnodes; i++, ptr += scal_detail_size) - scal_devs[i] = (struct scal_detail *)ptr; - - for (i = 0; i < rio_table_hdr->num_rio_dev; - i++, ptr += rio_detail_size) - rio_devs[i] = (struct rio_detail *)ptr; - - return 0; -} - -static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev) -{ - int dev; - u32 val; - - if (pci_dev == PCI_DEVICE_ID_IBM_CALIOC2) { - /* - * FIXME: properly scan for devices across the - * PCI-to-PCI bridge on every CalIOC2 port. - */ - return 1; - } - - for (dev = 1; dev < 8; dev++) { - val = read_pci_config(bus, dev, 0, 0); - if (val != 0xffffffff) - break; - } - return (val != 0xffffffff); -} - -/* - * calgary_init_bitmap_from_tce_table(): - * Function for kdump case. In the second/kdump kernel initialize - * the bitmap based on the tce table entries obtained from first kernel - */ -static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl) -{ - u64 *tp; - unsigned int index; - tp = ((u64 *)tbl->it_base); - for (index = 0 ; index < tbl->it_size; index++) { - if (*tp != 0x0) - set_bit(index, tbl->it_map); - tp++; - } -} - -/* - * get_tce_space_from_tar(): - * Function for kdump case. Get the tce tables from first kernel - * by reading the contents of the base address register of calgary iommu - */ -static void __init get_tce_space_from_tar(void) -{ - int bus; - void __iomem *target; - unsigned long tce_space; - - for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) { - struct calgary_bus_info *info = &bus_info[bus]; - unsigned short pci_device; - u32 val; - - val = read_pci_config(bus, 0, 0, 0); - pci_device = (val & 0xFFFF0000) >> 16; - - if (!is_cal_pci_dev(pci_device)) - continue; - if (info->translation_disabled) - continue; - - if (calgary_bus_has_devices(bus, pci_device) || - translate_empty_slots) { - target = calgary_reg(bus_info[bus].bbar, - tar_offset(bus)); - tce_space = be64_to_cpu(readq(target)); - tce_space = tce_space & TAR_SW_BITS; - - tce_space = tce_space & (~specified_table_size); - info->tce_space = (u64 *)__va(tce_space); - } - } - return; -} - -static int __init calgary_iommu_init(void) -{ - int ret; - - /* ok, we're trying to use Calgary - let's roll */ - printk(KERN_INFO "PCI-DMA: Using Calgary IOMMU\n"); - - ret = calgary_init(); - if (ret) { - printk(KERN_ERR "PCI-DMA: Calgary init failed %d, " - "falling back to no_iommu\n", ret); - return ret; - } - - return 0; -} - -int __init detect_calgary(void) -{ - int bus; - void *tbl; - int calgary_found = 0; - unsigned long ptr; - unsigned int offset, prev_offset; - int ret; - - /* - * if the user specified iommu=off or iommu=soft or we found - * another HW IOMMU already, bail out. - */ - if (no_iommu || iommu_detected) - return -ENODEV; - - if (!use_calgary) - return -ENODEV; - - if (!early_pci_allowed()) - return -ENODEV; - - printk(KERN_DEBUG "Calgary: detecting Calgary via BIOS EBDA area\n"); - - ptr = (unsigned long)phys_to_virt(get_bios_ebda()); - - rio_table_hdr = NULL; - prev_offset = 0; - offset = 0x180; - /* - * The next offset is stored in the 1st word. - * Only parse up until the offset increases: - */ - while (offset > prev_offset) { - /* The block id is stored in the 2nd word */ - if (*((unsigned short *)(ptr + offset + 2)) == 0x4752){ - /* set the pointer past the offset & block id */ - rio_table_hdr = (struct rio_table_hdr *)(ptr + offset + 4); - break; - } - prev_offset = offset; - offset = *((unsigned short *)(ptr + offset)); - } - if (!rio_table_hdr) { - printk(KERN_DEBUG "Calgary: Unable to locate Rio Grande table " - "in EBDA - bailing!\n"); - return -ENODEV; - } - - ret = build_detail_arrays(); - if (ret) { - printk(KERN_DEBUG "Calgary: build_detail_arrays ret %d\n", ret); - return -ENOMEM; - } - - specified_table_size = determine_tce_table_size(); - - for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) { - struct calgary_bus_info *info = &bus_info[bus]; - unsigned short pci_device; - u32 val; - - val = read_pci_config(bus, 0, 0, 0); - pci_device = (val & 0xFFFF0000) >> 16; - - if (!is_cal_pci_dev(pci_device)) - continue; - - if (info->translation_disabled) - continue; - - if (calgary_bus_has_devices(bus, pci_device) || - translate_empty_slots) { - /* - * If it is kdump kernel, find and use tce tables - * from first kernel, else allocate tce tables here - */ - if (!is_kdump_kernel()) { - tbl = alloc_tce_table(); - if (!tbl) - goto cleanup; - info->tce_space = tbl; - } - calgary_found = 1; - } - } - - printk(KERN_DEBUG "Calgary: finished detection, Calgary %s\n", - calgary_found ? "found" : "not found"); - - if (calgary_found) { - iommu_detected = 1; - calgary_detected = 1; - printk(KERN_INFO "PCI-DMA: Calgary IOMMU detected.\n"); - printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d\n", - specified_table_size); - - x86_init.iommu.iommu_init = calgary_iommu_init; - } - return calgary_found; - -cleanup: - for (--bus; bus >= 0; --bus) { - struct calgary_bus_info *info = &bus_info[bus]; - - if (info->tce_space) - free_tce_table(info->tce_space); - } - return -ENOMEM; -} - -static int __init calgary_parse_options(char *p) -{ - unsigned int bridge; - unsigned long val; - size_t len; - ssize_t ret; - - while (*p) { - if (!strncmp(p, "64k", 3)) - specified_table_size = TCE_TABLE_SIZE_64K; - else if (!strncmp(p, "128k", 4)) - specified_table_size = TCE_TABLE_SIZE_128K; - else if (!strncmp(p, "256k", 4)) - specified_table_size = TCE_TABLE_SIZE_256K; - else if (!strncmp(p, "512k", 4)) - specified_table_size = TCE_TABLE_SIZE_512K; - else if (!strncmp(p, "1M", 2)) - specified_table_size = TCE_TABLE_SIZE_1M; - else if (!strncmp(p, "2M", 2)) - specified_table_size = TCE_TABLE_SIZE_2M; - else if (!strncmp(p, "4M", 2)) - specified_table_size = TCE_TABLE_SIZE_4M; - else if (!strncmp(p, "8M", 2)) - specified_table_size = TCE_TABLE_SIZE_8M; - - len = strlen("translate_empty_slots"); - if (!strncmp(p, "translate_empty_slots", len)) - translate_empty_slots = 1; - - len = strlen("disable"); - if (!strncmp(p, "disable", len)) { - p += len; - if (*p == '=') - ++p; - if (*p == '\0') - break; - ret = kstrtoul(p, 0, &val); - if (ret) - break; - - bridge = val; - if (bridge < MAX_PHB_BUS_NUM) { - printk(KERN_INFO "Calgary: disabling " - "translation for PHB %#x\n", bridge); - bus_info[bridge].translation_disabled = 1; - } - } - - p = strpbrk(p, ","); - if (!p) - break; - - p++; /* skip ',' */ - } - return 1; -} -__setup("calgary=", calgary_parse_options); - -static void __init calgary_fixup_one_tce_space(struct pci_dev *dev) -{ - struct iommu_table *tbl; - unsigned int npages; - int i; - - tbl = pci_iommu(dev->bus); - - for (i = 0; i < 4; i++) { - struct resource *r = &dev->resource[PCI_BRIDGE_RESOURCES + i]; - - /* Don't give out TCEs that map MEM resources */ - if (!(r->flags & IORESOURCE_MEM)) - continue; - - /* 0-based? we reserve the whole 1st MB anyway */ - if (!r->start) - continue; - - /* cover the whole region */ - npages = resource_size(r) >> PAGE_SHIFT; - npages++; - - iommu_range_reserve(tbl, r->start, npages); - } -} - -static int __init calgary_fixup_tce_spaces(void) -{ - struct pci_dev *dev = NULL; - struct calgary_bus_info *info; - - if (no_iommu || swiotlb || !calgary_detected) - return -ENODEV; - - printk(KERN_DEBUG "Calgary: fixing up tce spaces\n"); - - do { - dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev); - if (!dev) - break; - if (!is_cal_pci_dev(dev->device)) - continue; - - info = &bus_info[dev->bus->number]; - if (info->translation_disabled) - continue; - - if (!info->tce_space) - continue; - - calgary_fixup_one_tce_space(dev); - - } while (1); - - return 0; -} - -/* - * We need to be call after pcibios_assign_resources (fs_initcall level) - * and before device_initcall. - */ -rootfs_initcall(calgary_fixup_tce_spaces); - -IOMMU_INIT_POST(detect_calgary); diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index f62b498b18fb..5dcedad21dff 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/dma-direct.h> #include <linux/dma-debug.h> +#include <linux/iommu.h> #include <linux/dmar.h> #include <linux/export.h> #include <linux/memblock.h> @@ -11,7 +12,6 @@ #include <asm/dma.h> #include <asm/iommu.h> #include <asm/gart.h> -#include <asm/calgary.h> #include <asm/x86_init.h> #include <asm/iommu_table.h> @@ -34,21 +34,6 @@ int no_iommu __read_mostly; /* Set this to 1 if there is a HW IOMMU in the system */ int iommu_detected __read_mostly = 0; -/* - * This variable becomes 1 if iommu=pt is passed on the kernel command line. - * If this variable is 1, IOMMU implementations do no DMA translation for - * devices and allow every device to access to whole physical memory. This is - * useful if a user wants to use an IOMMU only for KVM device assignment to - * guests and not for driver dma translation. - * It is also possible to disable by default in kernel config, and enable with - * iommu=nopt at boot time. - */ -#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH -int iommu_pass_through __read_mostly = 1; -#else -int iommu_pass_through __read_mostly; -#endif - extern struct iommu_table_entry __iommu_table[], __iommu_table_end[]; void __init pci_iommu_alloc(void) @@ -120,17 +105,12 @@ static __init int iommu_setup(char *p) swiotlb = 1; #endif if (!strncmp(p, "pt", 2)) - iommu_pass_through = 1; + iommu_set_default_passthrough(true); if (!strncmp(p, "nopt", 4)) - iommu_pass_through = 0; + iommu_set_default_translated(true); gart_parse_options(p); -#ifdef CONFIG_CALGARY_IOMMU - if (!strncmp(p, "calgary", 7)) - use_calgary = 1; -#endif /* CONFIG_CALGARY_IOMMU */ - p += strcspn(p, ","); if (*p == ',') ++p; @@ -160,7 +140,7 @@ rootfs_initcall(pci_iommu_init); static int via_no_dac_cb(struct pci_dev *pdev, void *data) { - pdev->dev.bus_dma_mask = DMA_BIT_MASK(32); + pdev->dev.bus_dma_limit = DMA_BIT_MASK(32); return 0; } diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 5f5302028a9a..c2cfa5e7c152 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -/* Glue code to lib/swiotlb.c */ #include <linux/pci.h> #include <linux/cache.h> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 75fea0d48c0e..839b5244e3b7 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -41,6 +41,7 @@ #include <asm/desc.h> #include <asm/prctl.h> #include <asm/spec-ctrl.h> +#include <asm/io_bitmap.h> #include <asm/proto.h> #include "process.h" @@ -72,18 +73,9 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = { #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, #endif + .io_bitmap_base = IO_BITMAP_OFFSET_INVALID, }, -#ifdef CONFIG_X86_32 - /* - * Note that the .io_bitmap member must be extra-big. This is because - * the CPU will access an additional byte beyond the end of the IO - * permission bitmap. The extra byte must be all 1 bits, and must - * be within the limit. - */ - .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, -#endif }; EXPORT_PER_CPU_SYMBOL(cpu_tss_rw); @@ -110,28 +102,89 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) void exit_thread(struct task_struct *tsk) { struct thread_struct *t = &tsk->thread; - unsigned long *bp = t->io_bitmap_ptr; struct fpu *fpu = &t->fpu; - if (bp) { - struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu()); - - t->io_bitmap_ptr = NULL; - clear_thread_flag(TIF_IO_BITMAP); - /* - * Careful, clear this in the TSS too: - */ - memset(tss->io_bitmap, 0xff, t->io_bitmap_max); - t->io_bitmap_max = 0; - put_cpu(); - kfree(bp); - } + if (test_thread_flag(TIF_IO_BITMAP)) + io_bitmap_exit(); free_vm86(t); fpu__drop(fpu); } +static int set_new_tls(struct task_struct *p, unsigned long tls) +{ + struct user_desc __user *utls = (struct user_desc __user *)tls; + + if (in_ia32_syscall()) + return do_set_thread_area(p, -1, utls, 0); + else + return do_set_thread_area_64(p, ARCH_SET_FS, tls); +} + +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct *p, unsigned long tls) +{ + struct inactive_task_frame *frame; + struct fork_frame *fork_frame; + struct pt_regs *childregs; + int ret = 0; + + childregs = task_pt_regs(p); + fork_frame = container_of(childregs, struct fork_frame, regs); + frame = &fork_frame->frame; + + frame->bp = 0; + frame->ret_addr = (unsigned long) ret_from_fork; + p->thread.sp = (unsigned long) fork_frame; + p->thread.io_bitmap = NULL; + memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); + +#ifdef CONFIG_X86_64 + savesegment(gs, p->thread.gsindex); + p->thread.gsbase = p->thread.gsindex ? 0 : current->thread.gsbase; + savesegment(fs, p->thread.fsindex); + p->thread.fsbase = p->thread.fsindex ? 0 : current->thread.fsbase; + savesegment(es, p->thread.es); + savesegment(ds, p->thread.ds); +#else + p->thread.sp0 = (unsigned long) (childregs + 1); + /* + * Clear all status flags including IF and set fixed bit. 64bit + * does not have this initialization as the frame does not contain + * flags. The flags consistency (especially vs. AC) is there + * ensured via objtool, which lacks 32bit support. + */ + frame->flags = X86_EFLAGS_FIXED; +#endif + + /* Kernel thread ? */ + if (unlikely(p->flags & PF_KTHREAD)) { + memset(childregs, 0, sizeof(struct pt_regs)); + kthread_frame_init(frame, sp, arg); + return 0; + } + + frame->bx = 0; + *childregs = *current_pt_regs(); + childregs->ax = 0; + if (sp) + childregs->sp = sp; + +#ifdef CONFIG_X86_32 + task_user_gs(p) = get_user_gs(current_pt_regs()); +#endif + + /* Set a new TLS for the child thread? */ + if (clone_flags & CLONE_SETTLS) + ret = set_new_tls(p, tls); + + if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP))) + io_bitmap_share(p); + + return ret; +} + void flush_thread(void) { struct task_struct *tsk = current; @@ -269,31 +322,96 @@ void arch_setup_new_exec(void) } } -static inline void switch_to_bitmap(struct thread_struct *prev, - struct thread_struct *next, - unsigned long tifp, unsigned long tifn) +#ifdef CONFIG_X86_IOPL_IOPERM +static inline void tss_invalidate_io_bitmap(struct tss_struct *tss) +{ + /* + * Invalidate the I/O bitmap by moving io_bitmap_base outside the + * TSS limit so any subsequent I/O access from user space will + * trigger a #GP. + * + * This is correct even when VMEXIT rewrites the TSS limit + * to 0x67 as the only requirement is that the base points + * outside the limit. + */ + tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID; +} + +static inline void switch_to_bitmap(unsigned long tifp) +{ + /* + * Invalidate I/O bitmap if the previous task used it. This prevents + * any possible leakage of an active I/O bitmap. + * + * If the next task has an I/O bitmap it will handle it on exit to + * user mode. + */ + if (tifp & _TIF_IO_BITMAP) + tss_invalidate_io_bitmap(this_cpu_ptr(&cpu_tss_rw)); +} + +static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) +{ + /* + * Copy at least the byte range of the incoming tasks bitmap which + * covers the permitted I/O ports. + * + * If the previous task which used an I/O bitmap had more bits + * permitted, then the copy needs to cover those as well so they + * get turned off. + */ + memcpy(tss->io_bitmap.bitmap, iobm->bitmap, + max(tss->io_bitmap.prev_max, iobm->max)); + + /* + * Store the new max and the sequence number of this bitmap + * and a pointer to the bitmap itself. + */ + tss->io_bitmap.prev_max = iobm->max; + tss->io_bitmap.prev_sequence = iobm->sequence; +} + +/** + * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode + */ +void tss_update_io_bitmap(void) { struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + struct thread_struct *t = ¤t->thread; + u16 *base = &tss->x86_tss.io_bitmap_base; + + if (!test_thread_flag(TIF_IO_BITMAP)) { + tss_invalidate_io_bitmap(tss); + return; + } + + if (IS_ENABLED(CONFIG_X86_IOPL_IOPERM) && t->iopl_emul == 3) { + *base = IO_BITMAP_OFFSET_VALID_ALL; + } else { + struct io_bitmap *iobm = t->io_bitmap; - if (tifn & _TIF_IO_BITMAP) { - /* - * Copy the relevant range of the IO bitmap. - * Normally this is 128 bytes or less: - */ - memcpy(tss->io_bitmap, next->io_bitmap_ptr, - max(prev->io_bitmap_max, next->io_bitmap_max)); - /* - * Make sure that the TSS limit is correct for the CPU - * to notice the IO bitmap. - */ - refresh_tss_limit(); - } else if (tifp & _TIF_IO_BITMAP) { /* - * Clear any possible leftover bits: + * Only copy bitmap data when the sequence number differs. The + * update time is accounted to the incoming task. */ - memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); + if (tss->io_bitmap.prev_sequence != iobm->sequence) + tss_copy_io_bitmap(tss, iobm); + + /* Enable the bitmap */ + *base = IO_BITMAP_OFFSET_VALID_MAP; } + + /* + * Make sure that the TSS limit is covering the IO bitmap. It might have + * been cut down by a VMEXIT to 0x67 which would cause a subsequent I/O + * access from user space to trigger a #GP because tbe bitmap is outside + * the TSS limit. + */ + refresh_tss_limit(); } +#else /* CONFIG_X86_IOPL_IOPERM */ +static inline void switch_to_bitmap(unsigned long tifp) { } +#endif #ifdef CONFIG_SMP @@ -497,15 +615,12 @@ void speculation_ctrl_update_current(void) void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) { - struct thread_struct *prev, *next; unsigned long tifp, tifn; - prev = &prev_p->thread; - next = &next_p->thread; - tifn = READ_ONCE(task_thread_info(next_p)->flags); tifp = READ_ONCE(task_thread_info(prev_p)->flags); - switch_to_bitmap(prev, next, tifp, tifn); + + switch_to_bitmap(tifp); propagate_user_return_notify(prev_p, next_p); @@ -580,7 +695,7 @@ void __cpuidle default_idle(void) safe_halt(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } -#ifdef CONFIG_APM_MODULE +#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); #endif diff --git a/arch/x86/kernel/process.h b/arch/x86/kernel/process.h index 320ab978fb1f..1d0797b2338a 100644 --- a/arch/x86/kernel/process.h +++ b/arch/x86/kernel/process.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ // // Code shared between 32 and 64 bit diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index b8ceec4974fe..5052ced43373 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -112,74 +112,6 @@ void release_thread(struct task_struct *dead_task) release_vm86_irqs(dead_task); } -int copy_thread_tls(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p, unsigned long tls) -{ - struct pt_regs *childregs = task_pt_regs(p); - struct fork_frame *fork_frame = container_of(childregs, struct fork_frame, regs); - struct inactive_task_frame *frame = &fork_frame->frame; - struct task_struct *tsk; - int err; - - /* - * For a new task use the RESET flags value since there is no before. - * All the status flags are zero; DF and all the system flags must also - * be 0, specifically IF must be 0 because we context switch to the new - * task with interrupts disabled. - */ - frame->flags = X86_EFLAGS_FIXED; - frame->bp = 0; - frame->ret_addr = (unsigned long) ret_from_fork; - p->thread.sp = (unsigned long) fork_frame; - p->thread.sp0 = (unsigned long) (childregs+1); - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - - if (unlikely(p->flags & PF_KTHREAD)) { - /* kernel thread */ - memset(childregs, 0, sizeof(struct pt_regs)); - frame->bx = sp; /* function */ - frame->di = arg; - p->thread.io_bitmap_ptr = NULL; - return 0; - } - frame->bx = 0; - *childregs = *current_pt_regs(); - childregs->ax = 0; - if (sp) - childregs->sp = sp; - - task_user_gs(p) = get_user_gs(current_pt_regs()); - - p->thread.io_bitmap_ptr = NULL; - tsk = current; - err = -ENOMEM; - - if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { - p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr, - IO_BITMAP_BYTES, GFP_KERNEL); - if (!p->thread.io_bitmap_ptr) { - p->thread.io_bitmap_max = 0; - return -ENOMEM; - } - set_tsk_thread_flag(p, TIF_IO_BITMAP); - } - - err = 0; - - /* - * Set a new TLS for the child thread? - */ - if (clone_flags & CLONE_SETTLS) - err = do_set_thread_area(p, -1, - (struct user_desc __user *)tls, 0); - - if (err && p->thread.io_bitmap_ptr) { - kfree(p->thread.io_bitmap_ptr); - p->thread.io_bitmap_max = 0; - } - return err; -} - void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { @@ -192,7 +124,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) regs->ip = new_ip; regs->sp = new_sp; regs->flags = X86_EFLAGS_IF; - force_iret(); } EXPORT_SYMBOL_GPL(start_thread); @@ -255,15 +186,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ load_TLS(next, cpu); - /* - * Restore IOPL if needed. In normal use, the flags restore - * in the switch assembly will handle this. But if the kernel - * is running virtualized at a non-zero CPL, the popf will - * not restore flags, so it must be done in a separate step. - */ - if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl)) - set_iopl_mask(next->iopl); - switch_to_extra(prev_p, next_p); /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index af64519b2695..ffd497804dbc 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -371,81 +371,6 @@ void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase) task->thread.gsbase = gsbase; } -int copy_thread_tls(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p, unsigned long tls) -{ - int err; - struct pt_regs *childregs; - struct fork_frame *fork_frame; - struct inactive_task_frame *frame; - struct task_struct *me = current; - - childregs = task_pt_regs(p); - fork_frame = container_of(childregs, struct fork_frame, regs); - frame = &fork_frame->frame; - - frame->bp = 0; - frame->ret_addr = (unsigned long) ret_from_fork; - p->thread.sp = (unsigned long) fork_frame; - p->thread.io_bitmap_ptr = NULL; - - savesegment(gs, p->thread.gsindex); - p->thread.gsbase = p->thread.gsindex ? 0 : me->thread.gsbase; - savesegment(fs, p->thread.fsindex); - p->thread.fsbase = p->thread.fsindex ? 0 : me->thread.fsbase; - savesegment(es, p->thread.es); - savesegment(ds, p->thread.ds); - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - - if (unlikely(p->flags & PF_KTHREAD)) { - /* kernel thread */ - memset(childregs, 0, sizeof(struct pt_regs)); - frame->bx = sp; /* function */ - frame->r12 = arg; - return 0; - } - frame->bx = 0; - *childregs = *current_pt_regs(); - - childregs->ax = 0; - if (sp) - childregs->sp = sp; - - err = -ENOMEM; - if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) { - p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr, - IO_BITMAP_BYTES, GFP_KERNEL); - if (!p->thread.io_bitmap_ptr) { - p->thread.io_bitmap_max = 0; - return -ENOMEM; - } - set_tsk_thread_flag(p, TIF_IO_BITMAP); - } - - /* - * Set a new TLS for the child thread? - */ - if (clone_flags & CLONE_SETTLS) { -#ifdef CONFIG_IA32_EMULATION - if (in_ia32_syscall()) - err = do_set_thread_area(p, -1, - (struct user_desc __user *)tls, 0); - else -#endif - err = do_arch_prctl_64(p, ARCH_SET_FS, tls); - if (err) - goto out; - } - err = 0; -out: - if (err && p->thread.io_bitmap_ptr) { - kfree(p->thread.io_bitmap_ptr); - p->thread.io_bitmap_max = 0; - } - - return err; -} - static void start_thread_common(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp, @@ -469,7 +394,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; - force_iret(); } void @@ -572,17 +496,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) switch_to_extra(prev_p, next_p); -#ifdef CONFIG_XEN_PV - /* - * On Xen PV, IOPL bits in pt_regs->flags have no effect, and - * current_pt_regs()->flags may not match the current task's - * intended IOPL. We need to switch it manually. - */ - if (unlikely(static_cpu_has(X86_FEATURE_XENPV) && - prev->iopl != next->iopl)) - xen_set_iopl_mask(next->iopl); -#endif - if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) { /* * AMD CPUs have a misfeature: SYSRET sets the SS selector but diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 3c5bbe8e4120..f0e1ddbc2fd7 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -42,6 +42,7 @@ #include <asm/traps.h> #include <asm/syscall.h> #include <asm/fsgsbase.h> +#include <asm/io_bitmap.h> #include "tls.h" @@ -181,6 +182,9 @@ static u16 get_segment_reg(struct task_struct *task, unsigned long offset) static int set_segment_reg(struct task_struct *task, unsigned long offset, u16 value) { + if (WARN_ON_ONCE(task == current)) + return -EIO; + /* * The value argument was already truncated to 16 bits. */ @@ -208,10 +212,7 @@ static int set_segment_reg(struct task_struct *task, break; case offsetof(struct user_regs_struct, gs): - if (task == current) - set_user_gs(task_pt_regs(task), value); - else - task_user_gs(task) = value; + task_user_gs(task) = value; } return 0; @@ -271,32 +272,41 @@ static u16 get_segment_reg(struct task_struct *task, unsigned long offset) static int set_segment_reg(struct task_struct *task, unsigned long offset, u16 value) { + if (WARN_ON_ONCE(task == current)) + return -EIO; + /* * The value argument was already truncated to 16 bits. */ if (invalid_selector(value)) return -EIO; + /* + * This function has some ABI oddities. + * + * A 32-bit ptracer probably expects that writing FS or GS will change + * FSBASE or GSBASE respectively. In the absence of FSGSBASE support, + * this code indeed has that effect. When FSGSBASE is added, this + * will require a special case. + * + * For existing 64-bit ptracers, writing FS or GS *also* currently + * changes the base if the selector is nonzero the next time the task + * is run. This behavior may not be needed, and trying to preserve it + * when FSGSBASE is added would be complicated at best. + */ + switch (offset) { case offsetof(struct user_regs_struct,fs): task->thread.fsindex = value; - if (task == current) - loadsegment(fs, task->thread.fsindex); break; case offsetof(struct user_regs_struct,gs): task->thread.gsindex = value; - if (task == current) - load_gs_index(task->thread.gsindex); break; case offsetof(struct user_regs_struct,ds): task->thread.ds = value; - if (task == current) - loadsegment(ds, task->thread.ds); break; case offsetof(struct user_regs_struct,es): task->thread.es = value; - if (task == current) - loadsegment(es, task->thread.es); break; /* @@ -374,6 +384,9 @@ static int putreg(struct task_struct *child, * When changing the FS base, use do_arch_prctl_64() * to set the index to zero and to set the base * as requested. + * + * NB: This behavior is nonsensical and likely needs to + * change when FSGSBASE support is added. */ if (child->thread.fsbase != value) return do_arch_prctl_64(child, ARCH_SET_FS, value); @@ -697,7 +710,9 @@ static int ptrace_set_debugreg(struct task_struct *tsk, int n, static int ioperm_active(struct task_struct *target, const struct user_regset *regset) { - return target->thread.io_bitmap_max / regset->size; + struct io_bitmap *iobm = target->thread.io_bitmap; + + return iobm ? DIV_ROUND_UP(iobm->max, regset->size) : 0; } static int ioperm_get(struct task_struct *target, @@ -705,12 +720,13 @@ static int ioperm_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - if (!target->thread.io_bitmap_ptr) + struct io_bitmap *iobm = target->thread.io_bitmap; + + if (!iobm) return -ENXIO; return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - target->thread.io_bitmap_ptr, - 0, IO_BITMAP_BYTES); + iobm->bitmap, 0, IO_BITMAP_BYTES); } /* diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 8451f38ad399..896d74cb5081 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -90,8 +90,6 @@ static void ich_force_hpet_resume(void) BUG(); else printk(KERN_DEBUG "Force enabled HPET at resume\n"); - - return; } static void ich_force_enable_hpet(struct pci_dev *dev) @@ -112,7 +110,7 @@ static void ich_force_enable_hpet(struct pci_dev *dev) } /* use bits 31:14, 16 kB aligned */ - rcba_base = ioremap_nocache(rcba, 0x4000); + rcba_base = ioremap(rcba, 0x4000); if (rcba_base == NULL) { dev_printk(KERN_DEBUG, &dev->dev, "ioremap failed; " "cannot force enable HPET\n"); @@ -448,7 +446,6 @@ static void nvidia_force_enable_hpet(struct pci_dev *dev) dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n", force_hpet_address); cached_dev = dev; - return; } /* ISA Bridges */ @@ -513,7 +510,6 @@ static void e6xx_force_enable_hpet(struct pci_dev *dev) force_hpet_resume_type = NONE_FORCE_HPET_RESUME; dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at " "0x%lx\n", force_hpet_address); - return; } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU, e6xx_force_enable_hpet); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 09d6bded3c1e..0cc7c0b106bb 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -828,11 +828,6 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) return NMI_HANDLED; } -static void smp_send_nmi_allbutself(void) -{ - apic->send_IPI_allbutself(NMI_VECTOR); -} - /* * Halt all other CPUs, calling the specified function on each of them * @@ -861,7 +856,7 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) */ wmb(); - smp_send_nmi_allbutself(); + apic_send_IPI_allbutself(NMI_VECTOR); /* Kick CPUs looping in NMI context. */ WRITE_ONCE(crash_ipi_issued, 1); diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index ee26df08002e..94b33885f8d2 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -35,8 +35,7 @@ #define CP_PA_BACKUP_PAGES_MAP DATA(0x1c) .text - .globl relocate_kernel -relocate_kernel: +SYM_CODE_START_NOALIGN(relocate_kernel) /* Save the CPU context, used for jumping back */ pushl %ebx @@ -93,8 +92,9 @@ relocate_kernel: addl $(identity_mapped - relocate_kernel), %eax pushl %eax ret +SYM_CODE_END(relocate_kernel) -identity_mapped: +SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) /* set return address to 0 if not preserving context */ pushl $0 /* store the start address on the stack */ @@ -191,8 +191,9 @@ identity_mapped: addl $(virtual_mapped - relocate_kernel), %eax pushl %eax ret +SYM_CODE_END(identity_mapped) -virtual_mapped: +SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) movl CR4(%edi), %eax movl %eax, %cr4 movl CR3(%edi), %eax @@ -208,9 +209,10 @@ virtual_mapped: popl %esi popl %ebx ret +SYM_CODE_END(virtual_mapped) /* Do the copies */ -swap_pages: +SYM_CODE_START_LOCAL_NOALIGN(swap_pages) movl 8(%esp), %edx movl 4(%esp), %ecx pushl %ebp @@ -270,6 +272,7 @@ swap_pages: popl %ebx popl %ebp ret +SYM_CODE_END(swap_pages) .globl kexec_control_code_size .set kexec_control_code_size, . - relocate_kernel diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index c51ccff5cd01..ef3ba99068d3 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -38,8 +38,7 @@ .text .align PAGE_SIZE .code64 - .globl relocate_kernel -relocate_kernel: +SYM_CODE_START_NOALIGN(relocate_kernel) /* * %rdi indirection_page * %rsi page_list @@ -103,8 +102,9 @@ relocate_kernel: addq $(identity_mapped - relocate_kernel), %r8 pushq %r8 ret +SYM_CODE_END(relocate_kernel) -identity_mapped: +SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) /* set return address to 0 if not preserving context */ pushq $0 /* store the start address on the stack */ @@ -209,8 +209,9 @@ identity_mapped: movq $virtual_mapped, %rax pushq %rax ret +SYM_CODE_END(identity_mapped) -virtual_mapped: +SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) movq RSP(%r8), %rsp movq CR4(%r8), %rax movq %rax, %cr4 @@ -228,9 +229,10 @@ virtual_mapped: popq %rbp popq %rbx ret +SYM_CODE_END(virtual_mapped) /* Do the copies */ -swap_pages: +SYM_CODE_START_LOCAL_NOALIGN(swap_pages) movq %rdi, %rcx /* Put the page_list in %rcx */ xorl %edi, %edi xorl %esi, %esi @@ -283,6 +285,7 @@ swap_pages: jmp 0b 3: ret +SYM_CODE_END(swap_pages) .globl kexec_control_code_size .set kexec_control_code_size, . - relocate_kernel diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bbe35bf879f5..a74262c71484 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -2,130 +2,54 @@ /* * Copyright (C) 1995 Linus Torvalds * - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 - * - * Memory region support - * David Parsons <orc@pell.chi.il.us>, July-August 1999 - * - * Added E820 sanitization routine (removes overlapping memory regions); - * Brian Moyle <bmoyle@mvista.com>, February 2001 - * - * Moved CPU detection code to cpu/${cpu}.c - * Patrick Mochel <mochel@osdl.org>, March 2002 - * - * Provisions for empty E820 memory regions (reported by certain BIOSes). - * Alex Achenbach <xela@slit.de>, December 2002. - * + * This file contains the setup_arch() code, which handles the architecture-dependent + * parts of early kernel initialization. */ - -/* - * This file handles the architecture-dependent parts of initialization - */ - -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/mmzone.h> -#include <linux/screen_info.h> -#include <linux/ioport.h> -#include <linux/acpi.h> -#include <linux/sfi.h> -#include <linux/apm_bios.h> -#include <linux/initrd.h> -#include <linux/memblock.h> -#include <linux/seq_file.h> #include <linux/console.h> -#include <linux/root_dev.h> -#include <linux/highmem.h> -#include <linux/export.h> +#include <linux/crash_dump.h> +#include <linux/dmi.h> #include <linux/efi.h> -#include <linux/init.h> -#include <linux/edd.h> +#include <linux/init_ohci1394_dma.h> +#include <linux/initrd.h> #include <linux/iscsi_ibft.h> -#include <linux/nodemask.h> -#include <linux/kexec.h> -#include <linux/dmi.h> -#include <linux/pfn.h> +#include <linux/memblock.h> #include <linux/pci.h> -#include <asm/pci-direct.h> -#include <linux/init_ohci1394_dma.h> -#include <linux/kvm_para.h> -#include <linux/dma-contiguous.h> -#include <xen/xen.h> -#include <uapi/linux/mount.h> - -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/stddef.h> -#include <linux/unistd.h> -#include <linux/ptrace.h> -#include <linux/user.h> -#include <linux/delay.h> - -#include <linux/kallsyms.h> -#include <linux/cpufreq.h> -#include <linux/dma-mapping.h> -#include <linux/ctype.h> -#include <linux/uaccess.h> - -#include <linux/percpu.h> -#include <linux/crash_dump.h> +#include <linux/root_dev.h> +#include <linux/sfi.h> #include <linux/tboot.h> -#include <linux/jiffies.h> -#include <linux/mem_encrypt.h> -#include <linux/sizes.h> - #include <linux/usb/xhci-dbgp.h> -#include <video/edid.h> -#include <asm/mtrr.h> +#include <uapi/linux/mount.h> + +#include <xen/xen.h> + #include <asm/apic.h> -#include <asm/realmode.h> -#include <asm/e820/api.h> -#include <asm/mpspec.h> -#include <asm/setup.h> -#include <asm/efi.h> -#include <asm/timer.h> -#include <asm/i8259.h> -#include <asm/sections.h> -#include <asm/io_apic.h> -#include <asm/ist.h> -#include <asm/setup_arch.h> #include <asm/bios_ebda.h> -#include <asm/cacheflush.h> -#include <asm/processor.h> #include <asm/bugs.h> -#include <asm/kasan.h> - -#include <asm/vsyscall.h> #include <asm/cpu.h> -#include <asm/desc.h> -#include <asm/dma.h> -#include <asm/iommu.h> +#include <asm/efi.h> #include <asm/gart.h> -#include <asm/mmu_context.h> -#include <asm/proto.h> - -#include <asm/paravirt.h> #include <asm/hypervisor.h> -#include <asm/olpc_ofw.h> - -#include <asm/percpu.h> -#include <asm/topology.h> -#include <asm/apicdef.h> -#include <asm/amd_nb.h> +#include <asm/io_apic.h> +#include <asm/kasan.h> +#include <asm/kaslr.h> #include <asm/mce.h> -#include <asm/alternative.h> +#include <asm/mtrr.h> +#include <asm/realmode.h> +#include <asm/olpc_ofw.h> +#include <asm/pci-direct.h> #include <asm/prom.h> -#include <asm/microcode.h> -#include <asm/kaslr.h> +#include <asm/proto.h> #include <asm/unwind.h> +#include <asm/vsyscall.h> +#include <linux/vmalloc.h> /* - * max_low_pfn_mapped: highest direct mapped pfn under 4GB - * max_pfn_mapped: highest direct mapped pfn over 4GB + * max_low_pfn_mapped: highest directly mapped pfn < 4 GB + * max_pfn_mapped: highest directly mapped pfn > 4 GB * * The direct mapping only covers E820_TYPE_RAM regions, so the ranges and gaps are - * represented by pfn_mapped + * represented by pfn_mapped[]. */ unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; @@ -135,14 +59,30 @@ RESERVE_BRK(dmi_alloc, 65536); #endif -static __initdata unsigned long _brk_start = (unsigned long)__brk_base; -unsigned long _brk_end = (unsigned long)__brk_base; +/* + * Range of the BSS area. The size of the BSS area is determined + * at link time, with RESERVE_BRK*() facility reserving additional + * chunks. + */ +static __initdata +unsigned long _brk_start = (unsigned long)__brk_base; +unsigned long _brk_end = (unsigned long)__brk_base; struct boot_params boot_params; /* - * Machine setup.. + * These are the four main kernel memory regions, we put them into + * the resource tree so that kdump tools and other debugging tools + * recover it: */ + +static struct resource rodata_resource = { + .name = "Kernel rodata", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM +}; + static struct resource data_resource = { .name = "Kernel data", .start = 0, @@ -166,16 +106,16 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 -/* cpu data as detected by the assembly code in head_32.S */ +/* CPU data as detected by the assembly code in head_32.S */ struct cpuinfo_x86 new_cpu_data; -/* common cpu data for all cpus */ +/* Common CPU data for all CPUs */ struct cpuinfo_x86 boot_cpu_data __read_mostly; EXPORT_SYMBOL(boot_cpu_data); unsigned int def_to_bigsmp; -/* for MCA, but anyone else can use it if they want */ +/* For MCA, but anyone else can use it if they want */ unsigned int machine_id; unsigned int machine_submodel_id; unsigned int BIOS_revision; @@ -438,6 +378,12 @@ static void __init memblock_x86_reserve_range_setup_data(void) while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); memblock_reserve(pa_data, sizeof(*data) + data->len); + + if (data->type == SETUP_INDIRECT && + ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) + memblock_reserve(((struct setup_indirect *)data->data)->addr, + ((struct setup_indirect *)data->data)->len); + pa_data = data->next; early_memunmap(data, sizeof(*data)); } @@ -455,15 +401,15 @@ static void __init memblock_x86_reserve_range_setup_data(void) /* * Keep the crash kernel below this limit. * - * On 32 bits earlier kernels would limit the kernel to the low 512 MiB + * Earlier 32-bits kernels would limit the kernel to the low 512 MB range * due to mapping restrictions. * - * On 64bit, kdump kernel need be restricted to be under 64TB, which is - * the upper limit of system RAM in 4-level paing mode. Since the kdump - * jumping could be from 5-level to 4-level, the jumping will fail if - * kernel is put above 64TB, and there's no way to detect the paging mode - * of the kernel which will be loaded for dumping during the 1st kernel - * bootup. + * 64-bit kdump kernels need to be restricted to be under 64 TB, which is + * the upper limit of system RAM in 4-level paging mode. Since the kdump + * jump could be from 5-level paging to 4-level paging, the jump will fail if + * the kernel is put above 64 TB, and during the 1st kernel bootup there's + * no good way to detect the paging mode of the target kernel which will be + * loaded for dumping. */ #ifdef CONFIG_X86_32 # define CRASH_ADDR_LOW_MAX SZ_512M @@ -486,7 +432,7 @@ static int __init reserve_crashkernel_low(void) ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); if (ret) { /* - * two parts from lib/swiotlb.c: + * two parts from kernel/dma/swiotlb.c: * -swiotlb size: user-specified with swiotlb= or default. * * -swiotlb overflow buffer: now hardcoded to 32k. We round it @@ -743,8 +689,8 @@ static void __init trim_bios_range(void) e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); /* - * special case: Some BIOSen report the PC BIOS - * area (640->1Mb) as ram even though it is not. + * special case: Some BIOSes report the PC BIOS + * area (640Kb -> 1Mb) as RAM even though it is not. * take them out. */ e820__range_remove(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_TYPE_RAM, 1); @@ -874,7 +820,7 @@ void __init setup_arch(char **cmdline_p) /* * Note: Quark X1000 CPUs advertise PGE incorrectly and require * a cr3 based tlb flush, so the following __flush_tlb_all() - * will not flush anything because the cpu quirk which clears + * will not flush anything because the CPU quirk which clears * X86_FEATURE_PGE has not been invoked yet. Though due to the * load_cr3() above the TLB has been flushed already. The * quirk is invoked before subsequent calls to __flush_tlb_all() @@ -947,11 +893,11 @@ void __init setup_arch(char **cmdline_p) init_mm.end_data = (unsigned long) _edata; init_mm.brk = _brk_end; - mpx_mm_init(&init_mm); - code_resource.start = __pa_symbol(_text); code_resource.end = __pa_symbol(_etext)-1; - data_resource.start = __pa_symbol(_etext); + rodata_resource.start = __pa_symbol(__start_rodata); + rodata_resource.end = __pa_symbol(__end_rodata)-1; + data_resource.start = __pa_symbol(_sdata); data_resource.end = __pa_symbol(_edata)-1; bss_resource.start = __pa_symbol(__bss_start); bss_resource.end = __pa_symbol(__bss_stop)-1; @@ -1040,6 +986,7 @@ void __init setup_arch(char **cmdline_p) /* after parse_early_param, so could debug it */ insert_resource(&iomem_resource, &code_resource); + insert_resource(&iomem_resource, &rodata_resource); insert_resource(&iomem_resource, &data_resource); insert_resource(&iomem_resource, &bss_resource); @@ -1122,17 +1069,15 @@ void __init setup_arch(char **cmdline_p) reserve_bios_regions(); - if (efi_enabled(EFI_MEMMAP)) { - efi_fake_memmap(); - efi_find_mirror(); - efi_esrt_init(); + efi_fake_memmap(); + efi_find_mirror(); + efi_esrt_init(); - /* - * The EFI specification says that boot service code won't be - * called after ExitBootServices(). This is, in fact, a lie. - */ - efi_reserve_boot_services(); - } + /* + * The EFI specification says that boot service code won't be + * called after ExitBootServices(). This is, in fact, a lie. + */ + efi_reserve_boot_services(); /* preallocate 4k for mptable mpc */ e820__memblock_alloc_reserved_mpc_new(); @@ -1281,8 +1226,6 @@ void __init setup_arch(char **cmdline_p) #if defined(CONFIG_VGA_CONSOLE) if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) conswitchp = &vga_con; -#elif defined(CONFIG_DUMMY_CONSOLE) - conswitchp = &dummy_con; #endif #endif x86_init.oem.banner(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 86663874ef04..e6d7894ad127 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -207,8 +207,8 @@ void __init setup_per_cpu_areas(void) pcpu_cpu_distance, pcpu_fc_alloc, pcpu_fc_free); if (rc < 0) - pr_warning("%s allocator failed (%d), falling back to page size\n", - pcpu_fc_names[pcpu_chosen_fc], rc); + pr_warn("%s allocator failed (%d), falling back to page size\n", + pcpu_fc_names[pcpu_chosen_fc], rc); } if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 8eb7193e158d..8a29573851a3 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -151,8 +151,6 @@ static int restore_sigcontext(struct pt_regs *regs, err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32)); - force_iret(); - return err; } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 96421f97e75c..b8d4e9c3c070 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -115,46 +115,6 @@ static atomic_t stopping_cpu = ATOMIC_INIT(-1); static bool smp_no_nmi_ipi = false; -/* - * this function sends a 'reschedule' IPI to another CPU. - * it goes straight through and wastes no time serializing - * anything. Worst case is that we lose a reschedule ... - */ -static void native_smp_send_reschedule(int cpu) -{ - if (unlikely(cpu_is_offline(cpu))) { - WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu); - return; - } - apic->send_IPI(cpu, RESCHEDULE_VECTOR); -} - -void native_send_call_func_single_ipi(int cpu) -{ - apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR); -} - -void native_send_call_func_ipi(const struct cpumask *mask) -{ - cpumask_var_t allbutself; - - if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) { - apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR); - return; - } - - cpumask_copy(allbutself, cpu_online_mask); - __cpumask_clear_cpu(smp_processor_id(), allbutself); - - if (cpumask_equal(mask, allbutself) && - cpumask_equal(cpu_online_mask, cpu_callout_mask)) - apic->send_IPI_allbutself(CALL_FUNCTION_VECTOR); - else - apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR); - - free_cpumask_var(allbutself); -} - static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) { /* We are registered on stopping cpu too, avoid spurious NMI */ @@ -179,6 +139,12 @@ asmlinkage __visible void smp_reboot_interrupt(void) irq_exit(); } +static int register_stop_handler(void) +{ + return register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback, + NMI_FLAG_FIRST, "smp_stop"); +} + static void native_stop_other_cpus(int wait) { unsigned long flags; @@ -209,42 +175,44 @@ static void native_stop_other_cpus(int wait) /* sync above data before sending IRQ */ wmb(); - apic->send_IPI_allbutself(REBOOT_VECTOR); + apic_send_IPI_allbutself(REBOOT_VECTOR); /* - * Don't wait longer than a second if the caller - * didn't ask us to wait. + * Don't wait longer than a second for IPI completion. The + * wait request is not checked here because that would + * prevent an NMI shutdown attempt in case that not all + * CPUs reach shutdown state. */ timeout = USEC_PER_SEC; - while (num_online_cpus() > 1 && (wait || timeout--)) + while (num_online_cpus() > 1 && timeout--) udelay(1); } - - /* if the REBOOT_VECTOR didn't work, try with the NMI */ - if ((num_online_cpus() > 1) && (!smp_no_nmi_ipi)) { - if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback, - NMI_FLAG_FIRST, "smp_stop")) - /* Note: we ignore failures here */ - /* Hope the REBOOT_IRQ is good enough */ - goto finish; - /* sync above data before sending IRQ */ - wmb(); - - pr_emerg("Shutting down cpus with NMI\n"); + /* if the REBOOT_VECTOR didn't work, try with the NMI */ + if (num_online_cpus() > 1) { + /* + * If NMI IPI is enabled, try to register the stop handler + * and send the IPI. In any case try to wait for the other + * CPUs to stop. + */ + if (!smp_no_nmi_ipi && !register_stop_handler()) { + /* Sync above data before sending IRQ */ + wmb(); - apic->send_IPI_allbutself(NMI_VECTOR); + pr_emerg("Shutting down cpus with NMI\n"); + apic_send_IPI_allbutself(NMI_VECTOR); + } /* - * Don't wait longer than a 10 ms if the caller - * didn't ask us to wait. + * Don't wait longer than 10 ms if the caller didn't + * reqeust it. If wait is true, the machine hangs here if + * one or more CPUs do not reach shutdown state. */ timeout = USEC_PER_MSEC * 10; while (num_online_cpus() > 1 && (wait || timeout--)) udelay(1); } -finish: local_irq_save(flags); disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fdbd47ceb84d..69881b2d446c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1023,8 +1023,6 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle) static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, int *cpu0_nmi_registered) { - volatile u32 *trampoline_status = - (volatile u32 *) __va(real_mode_header->trampoline_status); /* start_ip had better be page-aligned! */ unsigned long start_ip = real_mode_header->trampoline_start; @@ -1116,9 +1114,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, } } - /* mark "stuck" area as not stuck */ - *trampoline_status = 0; - if (x86_platform.legacy.warm_reset) { /* * Cleanup possible dangling ends... @@ -1596,7 +1591,12 @@ int native_cpu_disable(void) if (ret) return ret; - clear_local_APIC(); + /* + * Disable the local APIC. Otherwise IPI broadcasts will reach + * it. It still responds normally to INIT, NMI, SMI, and SIPI + * messages. + */ + apic_soft_disable(); cpu_disable_common(); return 0; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index f7476ce23b6e..ca3c11a17b5a 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -22,7 +22,6 @@ #include <asm/elf.h> #include <asm/ia32.h> #include <asm/syscalls.h> -#include <asm/mpx.h> /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. @@ -137,10 +136,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct vm_unmapped_area_info info; unsigned long begin, end; - addr = mpx_unmapped_area_check(addr, len, flags); - if (IS_ERR_VALUE(addr)) - return addr; - if (flags & MAP_FIXED) return addr; @@ -180,10 +175,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long addr = addr0; struct vm_unmapped_area_info info; - addr = mpx_unmapped_area_check(addr, len, flags); - if (IS_ERR_VALUE(addr)) - return addr; - /* requested length too big for entire address space */ if (len > TASK_SIZE) return -ENOMEM; diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 01f0e2263b86..298fc1edd9c9 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -90,11 +90,11 @@ __init int create_simplefb(const struct screen_info *si, if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) size <<= 16; length = mode->height * mode->stride; - length = PAGE_ALIGN(length); if (length > size) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } + length = PAGE_ALIGN(length); /* setup IORESOURCE_MEM as framebuffer memory */ memset(&res, 0, sizeof(res)); diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index a49fe1dcb47e..b89f6ac6a0c0 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -57,7 +57,7 @@ void __init tboot_probe(void) */ if (!e820__mapped_any(boot_params.tboot_addr, boot_params.tboot_addr, E820_TYPE_RESERVED)) { - pr_warning("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n"); + pr_warn("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n"); return; } @@ -65,13 +65,12 @@ void __init tboot_probe(void) set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr); tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE); if (memcmp(&tboot_uuid, &tboot->uuid, sizeof(tboot->uuid))) { - pr_warning("tboot at 0x%llx is invalid\n", - boot_params.tboot_addr); + pr_warn("tboot at 0x%llx is invalid\n", boot_params.tboot_addr); tboot = NULL; return; } if (tboot->version < 5) { - pr_warning("tboot version is invalid: %u\n", tboot->version); + pr_warn("tboot version is invalid: %u\n", tboot->version); tboot = NULL; return; } @@ -289,7 +288,7 @@ static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control) if (sleep_state >= ACPI_S_STATE_COUNT || acpi_shutdown_map[sleep_state] == -1) { - pr_warning("unsupported sleep state 0x%x\n", sleep_state); + pr_warn("unsupported sleep state 0x%x\n", sleep_state); return -1; } @@ -302,7 +301,7 @@ static int tboot_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b) if (!tboot_enabled()) return 0; - pr_warning("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)"); + pr_warn("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)"); return -ENODEV; } @@ -320,7 +319,7 @@ static int tboot_wait_for_aps(int num_aps) } if (timeout) - pr_warning("tboot wait for APs timeout\n"); + pr_warn("tboot wait for APs timeout\n"); return !(atomic_read((atomic_t *)&tboot->num_in_wfs) == num_aps); } @@ -355,7 +354,7 @@ static ssize_t tboot_log_read(struct file *file, char __user *user_buf, size_t c void *kbuf; int ret = -EFAULT; - log_base = ioremap_nocache(TBOOT_SERIAL_LOG_ADDR, TBOOT_SERIAL_LOG_SIZE); + log_base = ioremap(TBOOT_SERIAL_LOG_ADDR, TBOOT_SERIAL_LOG_SIZE); if (!log_base) return ret; @@ -516,7 +515,7 @@ int tboot_force_iommu(void) return 1; if (no_iommu || swiotlb || dmar_disabled) - pr_warning("Forcing Intel-IOMMU to enabled\n"); + pr_warn("Forcing Intel-IOMMU to enabled\n"); dmar_disabled = 0; #ifdef CONFIG_SWIOTLB diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c deleted file mode 100644 index 6384be751eff..000000000000 --- a/arch/x86/kernel/tce_64.c +++ /dev/null @@ -1,177 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * This file manages the translation entries for the IBM Calgary IOMMU. - * - * Derived from arch/powerpc/platforms/pseries/iommu.c - * - * Copyright (C) IBM Corporation, 2006 - * - * Author: Jon Mason <jdmason@us.ibm.com> - * Author: Muli Ben-Yehuda <muli@il.ibm.com> - */ - -#include <linux/types.h> -#include <linux/slab.h> -#include <linux/mm.h> -#include <linux/spinlock.h> -#include <linux/string.h> -#include <linux/pci.h> -#include <linux/dma-mapping.h> -#include <linux/memblock.h> -#include <asm/tce.h> -#include <asm/calgary.h> -#include <asm/proto.h> -#include <asm/cacheflush.h> - -/* flush a tce at 'tceaddr' to main memory */ -static inline void flush_tce(void* tceaddr) -{ - /* a single tce can't cross a cache line */ - if (boot_cpu_has(X86_FEATURE_CLFLUSH)) - clflush(tceaddr); - else - wbinvd(); -} - -void tce_build(struct iommu_table *tbl, unsigned long index, - unsigned int npages, unsigned long uaddr, int direction) -{ - u64* tp; - u64 t; - u64 rpn; - - t = (1 << TCE_READ_SHIFT); - if (direction != DMA_TO_DEVICE) - t |= (1 << TCE_WRITE_SHIFT); - - tp = ((u64*)tbl->it_base) + index; - - while (npages--) { - rpn = (virt_to_bus((void*)uaddr)) >> PAGE_SHIFT; - t &= ~TCE_RPN_MASK; - t |= (rpn << TCE_RPN_SHIFT); - - *tp = cpu_to_be64(t); - flush_tce(tp); - - uaddr += PAGE_SIZE; - tp++; - } -} - -void tce_free(struct iommu_table *tbl, long index, unsigned int npages) -{ - u64* tp; - - tp = ((u64*)tbl->it_base) + index; - - while (npages--) { - *tp = cpu_to_be64(0); - flush_tce(tp); - tp++; - } -} - -static inline unsigned int table_size_to_number_of_entries(unsigned char size) -{ - /* - * size is the order of the table, 0-7 - * smallest table is 8K entries, so shift result by 13 to - * multiply by 8K - */ - return (1 << size) << 13; -} - -static int tce_table_setparms(struct pci_dev *dev, struct iommu_table *tbl) -{ - unsigned int bitmapsz; - unsigned long bmppages; - int ret; - - tbl->it_busno = dev->bus->number; - - /* set the tce table size - measured in entries */ - tbl->it_size = table_size_to_number_of_entries(specified_table_size); - - /* - * number of bytes needed for the bitmap size in number of - * entries; we need one bit per entry - */ - bitmapsz = tbl->it_size / BITS_PER_BYTE; - bmppages = __get_free_pages(GFP_KERNEL, get_order(bitmapsz)); - if (!bmppages) { - printk(KERN_ERR "Calgary: cannot allocate bitmap\n"); - ret = -ENOMEM; - goto done; - } - - tbl->it_map = (unsigned long*)bmppages; - - memset(tbl->it_map, 0, bitmapsz); - - tbl->it_hint = 0; - - spin_lock_init(&tbl->it_lock); - - return 0; - -done: - return ret; -} - -int __init build_tce_table(struct pci_dev *dev, void __iomem *bbar) -{ - struct iommu_table *tbl; - int ret; - - if (pci_iommu(dev->bus)) { - printk(KERN_ERR "Calgary: dev %p has sysdata->iommu %p\n", - dev, pci_iommu(dev->bus)); - BUG(); - } - - tbl = kzalloc(sizeof(struct iommu_table), GFP_KERNEL); - if (!tbl) { - printk(KERN_ERR "Calgary: error allocating iommu_table\n"); - ret = -ENOMEM; - goto done; - } - - ret = tce_table_setparms(dev, tbl); - if (ret) - goto free_tbl; - - tbl->bbar = bbar; - - set_pci_iommu(dev->bus, tbl); - - return 0; - -free_tbl: - kfree(tbl); -done: - return ret; -} - -void * __init alloc_tce_table(void) -{ - unsigned int size; - - size = table_size_to_number_of_entries(specified_table_size); - size *= TCE_ENTRY_SIZE; - - return memblock_alloc_low(size, size); -} - -void __init free_tce_table(void *tbl) -{ - unsigned int size; - - if (!tbl) - return; - - size = table_size_to_number_of_entries(specified_table_size); - size *= TCE_ENTRY_SIZE; - - memblock_free(__pa(tbl), size); -} diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 7ce29cee9f9e..d8673d8a779b 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -91,10 +91,18 @@ void __init hpet_time_init(void) static __init void x86_late_time_init(void) { + /* + * Before PIT/HPET init, select the interrupt mode. This is required + * to make the decision whether PIT should be initialized correct. + */ + x86_init.irqs.intr_mode_select(); + + /* Setup the legacy timers */ x86_init.timers.timer_init(); + /* - * After PIT/HPET timers init, select and setup - * the final interrupt mode for delivering IRQs. + * After PIT/HPET timers init, set up the final interrupt mode for + * delivering IRQs. */ x86_init.irqs.intr_mode_init(); tsc_init(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 4bb0f8447112..6ef00eb6fbb9 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -37,11 +37,6 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/io.h> - -#if defined(CONFIG_EDAC) -#include <linux/edac.h> -#endif - #include <asm/stacktrace.h> #include <asm/processor.h> #include <asm/debugreg.h> @@ -57,10 +52,10 @@ #include <asm/mach_traps.h> #include <asm/alternative.h> #include <asm/fpu/xstate.h> -#include <asm/trace/mpx.h> -#include <asm/mpx.h> #include <asm/vm86.h> #include <asm/umip.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -311,8 +306,23 @@ __visible void __noreturn handle_stack_overflow(const char *message, } #endif -#ifdef CONFIG_X86_64 -/* Runs on IST stack */ +#if defined(CONFIG_X86_64) || defined(CONFIG_DOUBLEFAULT) +/* + * Runs on an IST stack for x86_64 and on a special task stack for x86_32. + * + * On x86_64, this is more or less a normal kernel entry. Notwithstanding the + * SDM's warnings about double faults being unrecoverable, returning works as + * expected. Presumably what the SDM actually means is that the CPU may get + * the register state wrong on entry, so returning could be a bad idea. + * + * Various CPU engineers have promised that double faults due to an IRET fault + * while the stack is read-only are, in fact, recoverable. + * + * On x86_32, this is entered through a task gate, and regs are synthesized + * from the TSS. Returning is, in principle, okay, but changes to regs will + * be lost. If, for some reason, we need to return to a context with modified + * regs, the shim code could be adjusted to synchronize the registers. + */ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long cr2) { static const char str[] = "double fault"; @@ -416,22 +426,14 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2); #endif -#ifdef CONFIG_DOUBLEFAULT - df_debug(regs, error_code); -#endif - /* - * This is always a kernel trap and never fixable (and thus must - * never return). - */ - for (;;) - die(str, regs, error_code); + pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code); + die("double fault", regs, error_code); + panic("Machine halted."); } #endif dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) { - const struct mpx_bndcsr *bndcsr; - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); if (notify_die(DIE_TRAP, "bounds", regs, error_code, X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP) @@ -441,84 +443,60 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) if (!user_mode(regs)) die("bounds", regs, error_code); - if (!cpu_feature_enabled(X86_FEATURE_MPX)) { - /* The exception is not from Intel MPX */ - goto exit_trap; - } + do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL); +} - /* - * We need to look at BNDSTATUS to resolve this exception. - * A NULL here might mean that it is in its 'init state', - * which is all zeros which indicates MPX was not - * responsible for the exception. - */ - bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR); - if (!bndcsr) - goto exit_trap; +enum kernel_gp_hint { + GP_NO_HINT, + GP_NON_CANONICAL, + GP_CANONICAL +}; - trace_bounds_exception_mpx(bndcsr); - /* - * The error code field of the BNDSTATUS register communicates status - * information of a bound range exception #BR or operation involving - * bound directory. - */ - switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) { - case 2: /* Bound directory has invalid entry. */ - if (mpx_handle_bd_fault()) - goto exit_trap; - break; /* Success, it was handled */ - case 1: /* Bound violation. */ - { - struct task_struct *tsk = current; - struct mpx_fault_info mpx; - - if (mpx_fault_info(&mpx, regs)) { - /* - * We failed to decode the MPX instruction. Act as if - * the exception was not caused by MPX. - */ - goto exit_trap; - } - /* - * Success, we decoded the instruction and retrieved - * an 'mpx' containing the address being accessed - * which caused the exception. This information - * allows and application to possibly handle the - * #BR exception itself. - */ - if (!do_trap_no_signal(tsk, X86_TRAP_BR, "bounds", regs, - error_code)) - break; +/* + * When an uncaught #GP occurs, try to determine the memory address accessed by + * the instruction and return that address to the caller. Also, try to figure + * out whether any part of the access to that address was non-canonical. + */ +static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, + unsigned long *addr) +{ + u8 insn_buf[MAX_INSN_SIZE]; + struct insn insn; - show_signal(tsk, SIGSEGV, "trap ", "bounds", regs, error_code); + if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE)) + return GP_NO_HINT; - force_sig_bnderr(mpx.addr, mpx.lower, mpx.upper); - break; - } - case 0: /* No exception caused by Intel MPX operations. */ - goto exit_trap; - default: - die("bounds", regs, error_code); - } + kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE); + insn_get_modrm(&insn); + insn_get_sib(&insn); - return; + *addr = (unsigned long)insn_get_addr_ref(&insn, regs); + if (*addr == -1UL) + return GP_NO_HINT; -exit_trap: +#ifdef CONFIG_X86_64 /* - * This path out is for all the cases where we could not - * handle the exception in some way (like allocating a - * table or telling userspace about it. We will also end - * up here if the kernel has MPX turned off at compile - * time.. + * Check that: + * - the operand is not in the kernel half + * - the last byte of the operand is not in the user canonical half */ - do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL); + if (*addr < ~__VIRTUAL_MASK && + *addr + insn.opnd_bytes - 1 > __VIRTUAL_MASK) + return GP_NON_CANONICAL; +#endif + + return GP_CANONICAL; } -dotraplinkage void -do_general_protection(struct pt_regs *regs, long error_code) +#define GPFSTR "general protection fault" + +dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) { - const char *desc = "general protection fault"; + char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR; + enum kernel_gp_hint hint = GP_NO_HINT; struct task_struct *tsk; + unsigned long gp_addr; + int ret; RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); cond_local_irq_enable(regs); @@ -535,48 +513,61 @@ do_general_protection(struct pt_regs *regs, long error_code) } tsk = current; - if (!user_mode(regs)) { - if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) - return; + if (user_mode(regs)) { tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; - /* - * To be potentially processing a kprobe fault and to - * trust the result from kprobe_running(), we have to - * be non-preemptible. - */ - if (!preemptible() && kprobe_running() && - kprobe_fault_handler(regs, X86_TRAP_GP)) - return; + show_signal(tsk, SIGSEGV, "", desc, regs, error_code); + force_sig(SIGSEGV); - if (notify_die(DIE_GPF, desc, regs, error_code, - X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) - die(desc, regs, error_code); return; } + if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) + return; + tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; - show_signal(tsk, SIGSEGV, "", desc, regs, error_code); + /* + * To be potentially processing a kprobe fault and to trust the result + * from kprobe_running(), we have to be non-preemptible. + */ + if (!preemptible() && + kprobe_running() && + kprobe_fault_handler(regs, X86_TRAP_GP)) + return; + + ret = notify_die(DIE_GPF, desc, regs, error_code, X86_TRAP_GP, SIGSEGV); + if (ret == NOTIFY_STOP) + return; + + if (error_code) + snprintf(desc, sizeof(desc), "segment-related " GPFSTR); + else + hint = get_kernel_gp_address(regs, &gp_addr); + + if (hint != GP_NO_HINT) + snprintf(desc, sizeof(desc), GPFSTR ", %s 0x%lx", + (hint == GP_NON_CANONICAL) ? "probably for non-canonical address" + : "maybe for address", + gp_addr); + + /* + * KASAN is interested only in the non-canonical case, clear it + * otherwise. + */ + if (hint != GP_NON_CANONICAL) + gp_addr = 0; + + die_addr(desc, regs, error_code, gp_addr); - force_sig(SIGSEGV); } NOKPROBE_SYMBOL(do_general_protection); dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * ftrace must be first, everything else may cause a recursive crash. - * See note by declaration of modifying_ftrace_code in ftrace.c - */ - if (unlikely(atomic_read(&modifying_ftrace_code)) && - ftrace_int3_handler(regs)) - return; -#endif if (poke_int3_handler(regs)) return; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 57d87f79558f..7e322e2daaf5 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -638,7 +638,7 @@ unsigned long native_calibrate_tsc(void) * clock. */ if (crystal_khz == 0 && - boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_X) + boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_D) crystal_khz = 25000; /* @@ -1505,6 +1505,9 @@ void __init tsc_init(void) return; } + if (tsc_clocksource_reliable || no_tsc_watchdog) + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 067858fe4db8..e0cbe4f2af49 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -58,6 +58,10 @@ static const struct freq_desc freq_desc_ann = { 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } }; +static const struct freq_desc freq_desc_lgm = { + 1, { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 } +}; + static const struct x86_cpu_id tsc_msr_cpu_ids[] = { INTEL_CPU_FAM6(ATOM_SALTWELL_MID, freq_desc_pnw), INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET, freq_desc_clv), @@ -65,6 +69,7 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = { INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, freq_desc_tng), INTEL_CPU_FAM6(ATOM_AIRMONT, freq_desc_cht), INTEL_CPU_FAM6(ATOM_AIRMONT_MID, freq_desc_ann), + INTEL_CPU_FAM6(ATOM_AIRMONT_NP, freq_desc_lgm), {} }; diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index ec534f978867..32a818764e03 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -233,7 +233,6 @@ static cycles_t check_tsc_warp(unsigned int timeout) * The measurement runs for 'timeout' msecs: */ end = start + (cycles_t) tsc_khz * timeout; - now = start; for (i = 0; ; i++) { /* @@ -364,12 +363,12 @@ retry: /* Force it to 0 if random warps brought us here */ atomic_set(&test_runs, 0); - pr_warning("TSC synchronization [CPU#%d -> CPU#%d]:\n", + pr_warn("TSC synchronization [CPU#%d -> CPU#%d]:\n", smp_processor_id(), cpu); - pr_warning("Measured %Ld cycles TSC warp between CPUs, " - "turning off TSC clock.\n", max_warp); + pr_warn("Measured %Ld cycles TSC warp between CPUs, " + "turning off TSC clock.\n", max_warp); if (random_warps) - pr_warning("TSC warped randomly between CPUs\n"); + pr_warn("TSC warped randomly between CPUs\n"); mark_tsc_unstable("check_tsc_sync_source failed"); } diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index 5b345add550f..4d732a444711 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -1,6 +1,6 @@ /* - * umip.c Emulation for instruction protected by the Intel User-Mode - * Instruction Prevention feature + * umip.c Emulation for instruction protected by the User-Mode Instruction + * Prevention feature * * Copyright (c) 2017, Intel Corporation. * Ricardo Neri <ricardo.neri-calderon@linux.intel.com> @@ -18,10 +18,10 @@ /** DOC: Emulation for User-Mode Instruction Prevention (UMIP) * - * The feature User-Mode Instruction Prevention present in recent Intel - * processor prevents a group of instructions (sgdt, sidt, sldt, smsw, and str) - * from being executed with CPL > 0. Otherwise, a general protection fault is - * issued. + * User-Mode Instruction Prevention is a security feature present in recent + * x86 processors that, when enabled, prevents a group of instructions (SGDT, + * SIDT, SLDT, SMSW and STR) from being run in user mode by issuing a general + * protection fault if the instruction is executed with CPL > 0. * * Rather than relaying to the user space the general protection fault caused by * the UMIP-protected instructions (in the form of a SIGSEGV signal), it can be @@ -36,8 +36,8 @@ * DOSEMU2) rely on this subset of instructions to function. * * The instructions protected by UMIP can be split in two groups. Those which - * return a kernel memory address (sgdt and sidt) and those which return a - * value (sldt, str and smsw). + * return a kernel memory address (SGDT and SIDT) and those which return a + * value (SLDT, STR and SMSW). * * For the instructions that return a kernel memory address, applications * such as WineHQ rely on the result being located in the kernel memory space, @@ -45,15 +45,13 @@ * value that, lies close to the top of the kernel memory. The limit for the GDT * and the IDT are set to zero. * - * Given that sldt and str are not commonly used in programs that run on WineHQ + * Given that SLDT and STR are not commonly used in programs that run on WineHQ * or DOSEMU2, they are not emulated. * * The instruction smsw is emulated to return the value that the register CR0 * has at boot time as set in the head_32. * - * Also, emulation is provided only for 32-bit processes; 64-bit processes - * that attempt to use the instructions that UMIP protects will receive the - * SIGSEGV signal issued as a consequence of the general protection fault. + * Emulation is provided for both 32-bit and 64-bit processes. * * Care is taken to appropriately emulate the results when segmentation is * used. That is, rather than relying on USER_DS and USER_CS, the function @@ -63,17 +61,18 @@ * application uses a local descriptor table. */ -#define UMIP_DUMMY_GDT_BASE 0xfffe0000 -#define UMIP_DUMMY_IDT_BASE 0xffff0000 +#define UMIP_DUMMY_GDT_BASE 0xfffffffffffe0000ULL +#define UMIP_DUMMY_IDT_BASE 0xffffffffffff0000ULL /* * The SGDT and SIDT instructions store the contents of the global descriptor * table and interrupt table registers, respectively. The destination is a * memory operand of X+2 bytes. X bytes are used to store the base address of - * the table and 2 bytes are used to store the limit. In 32-bit processes, the - * only processes for which emulation is provided, X has a value of 4. + * the table and 2 bytes are used to store the limit. In 32-bit processes X + * has a value of 4, in 64-bit processes X has a value of 8. */ -#define UMIP_GDT_IDT_BASE_SIZE 4 +#define UMIP_GDT_IDT_BASE_SIZE_64BIT 8 +#define UMIP_GDT_IDT_BASE_SIZE_32BIT 4 #define UMIP_GDT_IDT_LIMIT_SIZE 2 #define UMIP_INST_SGDT 0 /* 0F 01 /0 */ @@ -92,7 +91,7 @@ const char * const umip_insns[5] = { #define umip_pr_err(regs, fmt, ...) \ umip_printk(regs, KERN_ERR, fmt, ##__VA_ARGS__) -#define umip_pr_warning(regs, fmt, ...) \ +#define umip_pr_warn(regs, fmt, ...) \ umip_printk(regs, KERN_WARNING, fmt, ##__VA_ARGS__) /** @@ -189,6 +188,7 @@ static int identify_insn(struct insn *insn) * @umip_inst: A constant indicating the instruction to emulate * @data: Buffer into which the dummy result is stored * @data_size: Size of the emulated result + * @x86_64: true if process is 64-bit, false otherwise * * Emulate an instruction protected by UMIP and provide a dummy result. The * result of the emulation is saved in @data. The size of the results depends @@ -202,11 +202,8 @@ static int identify_insn(struct insn *insn) * 0 on success, -EINVAL on error while emulating. */ static int emulate_umip_insn(struct insn *insn, int umip_inst, - unsigned char *data, int *data_size) + unsigned char *data, int *data_size, bool x86_64) { - unsigned long dummy_base_addr, dummy_value; - unsigned short dummy_limit = 0; - if (!data || !data_size || !insn) return -EINVAL; /* @@ -219,6 +216,9 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst, * is always returned irrespective of the operand size. */ if (umip_inst == UMIP_INST_SGDT || umip_inst == UMIP_INST_SIDT) { + u64 dummy_base_addr; + u16 dummy_limit = 0; + /* SGDT and SIDT do not use registers operands. */ if (X86_MODRM_MOD(insn->modrm.value) == 3) return -EINVAL; @@ -228,13 +228,24 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst, else dummy_base_addr = UMIP_DUMMY_IDT_BASE; - *data_size = UMIP_GDT_IDT_LIMIT_SIZE + UMIP_GDT_IDT_BASE_SIZE; + /* + * 64-bit processes use the entire dummy base address. + * 32-bit processes use the lower 32 bits of the base address. + * dummy_base_addr is always 64 bits, but we memcpy the correct + * number of bytes from it to the destination. + */ + if (x86_64) + *data_size = UMIP_GDT_IDT_BASE_SIZE_64BIT; + else + *data_size = UMIP_GDT_IDT_BASE_SIZE_32BIT; + + memcpy(data + 2, &dummy_base_addr, *data_size); - memcpy(data + 2, &dummy_base_addr, UMIP_GDT_IDT_BASE_SIZE); + *data_size += UMIP_GDT_IDT_LIMIT_SIZE; memcpy(data, &dummy_limit, UMIP_GDT_IDT_LIMIT_SIZE); } else if (umip_inst == UMIP_INST_SMSW) { - dummy_value = CR0_STATE; + unsigned long dummy_value = CR0_STATE; /* * Even though the CR0 register has 4 bytes, the number @@ -290,11 +301,10 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs) * fixup_umip_exception() - Fixup a general protection fault caused by UMIP * @regs: Registers as saved when entering the #GP handler * - * The instructions sgdt, sidt, str, smsw, sldt cause a general protection - * fault if executed with CPL > 0 (i.e., from user space). If the offending - * user-space process is not in long mode, this function fixes the exception - * up and provides dummy results for sgdt, sidt and smsw; str and sldt are not - * fixed up. Also long mode user-space processes are not fixed up. + * The instructions SGDT, SIDT, STR, SMSW and SLDT cause a general protection + * fault if executed with CPL > 0 (i.e., from user space). This function fixes + * the exception up and provides dummy results for SGDT, SIDT and SMSW; STR + * and SLDT are not fixed up. * * If operands are memory addresses, results are copied to user-space memory as * indicated by the instruction pointed by eIP using the registers indicated in @@ -370,16 +380,17 @@ bool fixup_umip_exception(struct pt_regs *regs) if (umip_inst < 0) return false; - umip_pr_warning(regs, "%s instruction cannot be used by applications.\n", + umip_pr_warn(regs, "%s instruction cannot be used by applications.\n", umip_insns[umip_inst]); - /* Do not emulate SLDT, STR or user long mode processes. */ - if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT || user_64bit_mode(regs)) + /* Do not emulate (spoof) SLDT or STR. */ + if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT) return false; - umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n"); + umip_pr_warn(regs, "For now, expensive software emulation returns the result.\n"); - if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size)) + if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size, + user_64bit_mode(regs))) return false; /* diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 332ae6530fa8..e9cc182aa97e 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -187,6 +187,8 @@ static struct orc_entry *orc_find(unsigned long ip) return orc_ftrace_find(ip); } +#ifdef CONFIG_MODULES + static void orc_sort_swap(void *_a, void *_b, int size) { struct orc_entry *orc_a, *orc_b; @@ -229,7 +231,6 @@ static int orc_sort_cmp(const void *_a, const void *_b) return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1; } -#ifdef CONFIG_MODULES void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size, void *_orc, size_t orc_size) { @@ -273,9 +274,11 @@ void __init unwind_init(void) return; } - /* Sort the .orc_unwind and .orc_unwind_ip tables: */ - sort(__start_orc_unwind_ip, num_entries, sizeof(int), orc_sort_cmp, - orc_sort_swap); + /* + * Note, the orc_unwind and orc_unwind_ip tables were already + * sorted at build time via the 'sorttable' tool. + * It's ready for binary search straight away, no need to sort it. + */ /* Initialize the fast lookup table: */ lookup_num_blocks = orc_lookup_end - orc_lookup; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index d8359ebeea70..15e5aad8ac2c 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -508,9 +508,12 @@ struct uprobe_xol_ops { void (*abort)(struct arch_uprobe *, struct pt_regs *); }; -static inline int sizeof_long(void) +static inline int sizeof_long(struct pt_regs *regs) { - return in_ia32_syscall() ? 4 : 8; + /* + * Check registers for mode as in_xxx_syscall() does not apply here. + */ + return user_64bit_mode(regs) ? 8 : 4; } static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) @@ -521,9 +524,9 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) static int emulate_push_stack(struct pt_regs *regs, unsigned long val) { - unsigned long new_sp = regs->sp - sizeof_long(); + unsigned long new_sp = regs->sp - sizeof_long(regs); - if (copy_to_user((void __user *)new_sp, &val, sizeof_long())) + if (copy_to_user((void __user *)new_sp, &val, sizeof_long(regs))) return -EFAULT; regs->sp = new_sp; @@ -556,7 +559,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs long correction = utask->vaddr - utask->xol_vaddr; regs->ip += correction; } else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) { - regs->sp += sizeof_long(); /* Pop incorrect return address */ + regs->sp += sizeof_long(regs); /* Pop incorrect return address */ if (emulate_push_stack(regs, utask->vaddr + auprobe->defparam.ilen)) return -ERESTART; } @@ -675,7 +678,7 @@ static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) * "call" insn was executed out-of-line. Just restore ->sp and restart. * We could also restore ->ip and try to call branch_emulate_op() again. */ - regs->sp += sizeof_long(); + regs->sp += sizeof_long(regs); return -ERESTART; } @@ -839,8 +842,8 @@ static int push_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) /** * arch_uprobe_analyze_insn - instruction analysis including validity and fixups. + * @auprobe: the probepoint information. * @mm: the probed address space. - * @arch_uprobe: the probepoint information. * @addr: virtual address at which to install the probepoint * Return 0 on success or a -ve number on error. */ @@ -1056,7 +1059,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) { - int rasize = sizeof_long(), nleft; + int rasize = sizeof_long(regs), nleft; unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */ if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize)) diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index a024c4f7ba56..641f0fe1e5b4 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -31,7 +31,7 @@ #include <asm/cpufeatures.h> #include <asm/msr-index.h> -ENTRY(verify_cpu) +SYM_FUNC_START_LOCAL(verify_cpu) pushf # Save caller passed flags push $0 # Kill any dangerous flags popf @@ -137,4 +137,4 @@ ENTRY(verify_cpu) popf # Restore caller passed flags xorl %eax, %eax ret -ENDPROC(verify_cpu) +SYM_FUNC_END(verify_cpu) diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index a76c12b38e92..91d55454e702 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -381,7 +381,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) mark_screen_rdonly(tsk->mm); memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs)); - force_iret(); return regs->ax; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index e2feacf921a0..e3296aa028fe 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -21,6 +21,9 @@ #define LOAD_OFFSET __START_KERNEL_map #endif +#define EMITS_PT_NOTE +#define RO_EXCEPTION_TABLE_ALIGN 16 + #include <asm-generic/vmlinux.lds.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> @@ -141,17 +144,12 @@ SECTIONS *(.text.__x86.indirect_thunk) __indirect_thunk_end = .; #endif + } :text =0xcccc - /* End of text section */ - _etext = .; - } :text = 0x9090 - - NOTES :text :note - - EXCEPTION_TABLE(16) :text = 0x9090 - - /* .text should occupy whole number of pages */ + /* End of text section, which should occupy whole number of pages */ + _etext = .; . = ALIGN(PAGE_SIZE); + X86_ALIGN_RODATA_BEGIN RO_DATA(PAGE_SIZE) X86_ALIGN_RODATA_END @@ -195,12 +193,10 @@ SECTIONS __vvar_beginning_hack = .; /* Place all vvars at the offsets in asm/vvar.h. */ -#define EMIT_VVAR(name, offset) \ +#define EMIT_VVAR(name, offset) \ . = __vvar_beginning_hack + offset; \ *(.vvar_ ## name) -#define __VVAR_KERNEL_LDS #include <asm/vvar.h> -#undef __VVAR_KERNEL_LDS #undef EMIT_VVAR /* diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 1bef687faf22..85f1a90c55cd 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -20,7 +20,7 @@ #include <asm/irq.h> #include <asm/io_apic.h> #include <asm/hpet.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/tsc.h> #include <asm/iommu.h> #include <asm/mach_traps.h> @@ -31,6 +31,28 @@ static int __init iommu_init_noop(void) { return 0; } static void iommu_shutdown_noop(void) { } bool __init bool_x86_init_noop(void) { return false; } void x86_op_int_noop(int cpu) { } +static __init int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } +static __init void get_rtc_noop(struct timespec64 *now) { } + +static __initconst const struct of_device_id of_cmos_match[] = { + { .compatible = "motorola,mc146818" }, + {} +}; + +/* + * Allow devicetree configured systems to disable the RTC by setting the + * corresponding DT node's status property to disabled. Code is optimized + * out for CONFIG_OF=n builds. + */ +static __init void x86_wallclock_init(void) +{ + struct device_node *node = of_find_matching_node(NULL, of_cmos_match); + + if (node && !of_device_is_available(node)) { + x86_platform.get_wallclock = get_rtc_noop; + x86_platform.set_wallclock = set_rtc_noop; + } +} /* * The platform setup functions are preset with the default functions @@ -58,6 +80,7 @@ struct x86_init_ops x86_init __initdata = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, .trap_init = x86_init_noop, + .intr_mode_select = apic_intr_mode_select, .intr_mode_init = apic_intr_mode_init }, @@ -73,7 +96,7 @@ struct x86_init_ops x86_init __initdata = { .timers = { .setup_percpu_clockev = setup_boot_APIC_clock, .timer_init = hpet_time_init, - .wallclock_init = x86_init_noop, + .wallclock_init = x86_wallclock_init, }, .iommu = { @@ -95,6 +118,7 @@ struct x86_init_ops x86_init __initdata = { }, .acpi = { + .set_root_pointer = x86_default_set_root_pointer, .get_root_pointer = x86_default_get_root_pointer, .reduced_hw_early_init = acpi_generic_reduced_hw_init, }, diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 840e12583b85..991019d5eee1 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -60,13 +60,11 @@ config KVM If unsure, say N. config KVM_INTEL - tristate "KVM for Intel processors support" - depends on KVM - # for perf_guest_get_msrs(): - depends on CPU_SUP_INTEL + tristate "KVM for Intel (and compatible) processors support" + depends on KVM && IA32_FEAT_CTL ---help--- - Provides support for KVM on Intel processors equipped with the VT - extensions. + Provides support for KVM on processors equipped with Intel's VT + extensions, a.k.a. Virtual Machine Extensions (VMX). To compile this as a module, choose M here: the module will be called kvm-intel. diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 31ecf7a76d5a..b19ef421084d 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -8,9 +8,9 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o -kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ +kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - hyperv.o page_track.o debugfs.o + hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o kvm-amd-y += svm.o pmu_amd.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 22c2720cd948..b1c469446b07 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -62,7 +62,7 @@ u64 kvm_supported_xcr0(void) return xcr0; } -#define F(x) bit(X86_FEATURE_##x) +#define F feature_bit int kvm_update_cpuid(struct kvm_vcpu *vcpu) { @@ -281,8 +281,9 @@ out: return r; } -static void cpuid_mask(u32 *word, int wordnum) +static __always_inline void cpuid_mask(u32 *word, int wordnum) { + reverse_cpuid_check(wordnum); *word &= boot_cpu_data.x86_capability[wordnum]; } @@ -304,7 +305,13 @@ static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function, case 7: case 0xb: case 0xd: + case 0xf: + case 0x10: + case 0x12: case 0x14: + case 0x17: + case 0x18: + case 0x1f: case 0x8000001d: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; break; @@ -346,6 +353,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; unsigned f_la57; + unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0; /* cpuid 7.0.ebx */ const u32 kvm_cpuid_7_0_ebx_x86_features = @@ -357,10 +365,10 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | - F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B); + F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/; /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = @@ -386,12 +394,20 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) /* Set LA57 based on hardware capability. */ entry->ecx |= f_la57; entry->ecx |= f_umip; + entry->ecx |= f_pku; /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even * if the host doesn't support it. @@ -473,6 +489,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON); @@ -491,7 +508,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, r = -E2BIG; - if (*nent >= maxnent) + if (WARN_ON(*nent >= maxnent)) goto out; do_host_cpuid(entry, function, 0); @@ -606,16 +623,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, */ case 0x1f: case 0xb: { - int i, level_type; + int i; - /* read more entries until level_type is zero */ - for (i = 1; ; ++i) { + /* + * We filled in entry[0] for CPUID(EAX=<function>, + * ECX=00H) above. If its level type (ECX[15:8]) is + * zero, then the leaf is unimplemented, and we're + * done. Otherwise, continue to populate entries + * until the level type (ECX[15:8]) of the previously + * added entry is zero. + */ + for (i = 1; entry[i - 1].ecx & 0xff00; ++i) { if (*nent >= maxnent) goto out; - level_type = entry[i - 1].ecx & 0xff00; - if (!level_type) - break; do_host_cpuid(&entry[i], function, i); ++*nent; } @@ -729,18 +750,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); /* - * IBRS, IBPB and VIRT_SSBD aren't necessarily present in - * hardware cpuid + * AMD has separate bits for each SPEC_CTRL bit. + * arch/x86/kernel/cpu/bugs.c is kind enough to + * record that in cpufeatures so use them. */ - if (boot_cpu_has(X86_FEATURE_AMD_IBPB)) + if (boot_cpu_has(X86_FEATURE_IBPB)) entry->ebx |= F(AMD_IBPB); - if (boot_cpu_has(X86_FEATURE_AMD_IBRS)) + if (boot_cpu_has(X86_FEATURE_IBRS)) entry->ebx |= F(AMD_IBRS); - if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) - entry->ebx |= F(VIRT_SSBD); - entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->ebx |= F(AMD_STIBP); + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->ebx |= F(AMD_SSBD); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + entry->ebx |= F(AMD_SSB_NO); /* * The preference is to use SPEC CTRL MSR instead of the * VIRT_SPEC MSR. @@ -756,6 +783,11 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, case 0x8000001a: case 0x8000001e: break; + /* Support memory encryption cpuid if host supports it */ + case 0x8000001F: + if (!boot_cpu_has(X86_FEATURE_SEV)) + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: /*Just support up to 0xC0000004 now*/ @@ -788,14 +820,15 @@ out: static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, int *nent, int maxnent, unsigned int type) { + if (*nent >= maxnent) + return -E2BIG; + if (type == KVM_GET_EMULATED_CPUID) return __do_cpuid_func_emulated(entry, func, nent, maxnent); return __do_cpuid_func(entry, func, nent, maxnent); } -#undef F - struct kvm_cpuid_param { u32 func; bool (*qualifier)(const struct kvm_cpuid_param *param); @@ -952,53 +985,72 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); /* - * If no match is found, check whether we exceed the vCPU's limit - * and return the content of the highest valid _standard_ leaf instead. - * This is to satisfy the CPUID specification. + * If the basic or extended CPUID leaf requested is higher than the + * maximum supported basic or extended leaf, respectively, then it is + * out of range. */ -static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, - u32 function, u32 index) +static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function) { - struct kvm_cpuid_entry2 *maxlevel; - - maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); - if (!maxlevel || maxlevel->eax >= function) - return NULL; - if (function & 0x80000000) { - maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); - if (!maxlevel) - return NULL; - } - return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); + struct kvm_cpuid_entry2 *max; + + max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + return max && function <= max->eax; } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit) { u32 function = *eax, index = *ecx; - struct kvm_cpuid_entry2 *best; - bool entry_found = true; - - best = kvm_find_cpuid_entry(vcpu, function, index); - - if (!best) { - entry_found = false; - if (!check_limit) - goto out; + struct kvm_cpuid_entry2 *entry; + struct kvm_cpuid_entry2 *max; + bool found; - best = check_cpuid_limit(vcpu, function, index); + entry = kvm_find_cpuid_entry(vcpu, function, index); + found = entry; + /* + * Intel CPUID semantics treats any query for an out-of-range + * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were + * requested. AMD CPUID semantics returns all zeroes for any + * undefined leaf, whether or not the leaf is in range. + */ + if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) && + !cpuid_function_in_range(vcpu, function)) { + max = kvm_find_cpuid_entry(vcpu, 0, 0); + if (max) { + function = max->eax; + entry = kvm_find_cpuid_entry(vcpu, function, index); + } } - -out: - if (best) { - *eax = best->eax; - *ebx = best->ebx; - *ecx = best->ecx; - *edx = best->edx; - } else + if (entry) { + *eax = entry->eax; + *ebx = entry->ebx; + *ecx = entry->ecx; + *edx = entry->edx; + if (function == 7 && index == 0) { + u64 data; + if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) && + (data & TSX_CTRL_CPUID_CLEAR)) + *ebx &= ~(F(RTM) | F(HLE)); + } + } else { *eax = *ebx = *ecx = *edx = 0; - trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found); - return entry_found; + /* + * When leaf 0BH or 1FH is defined, CL is pass-through + * and EDX is always the x2APIC ID, even for undefined + * subleaves. Index 1 will exist iff the leaf is + * implemented, so we pass through CL iff leaf 1 + * exists. EDX can be copied from any existing index. + */ + if (function == 0xb || function == 0x1f) { + entry = kvm_find_cpuid_entry(vcpu, function, 1); + if (entry) { + *ecx = index & 0xff; + *edx = entry->edx; + } + } + } + trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found); + return found; } EXPORT_SYMBOL_GPL(kvm_cpuid); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index d78a61408243..7366c618aa04 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -53,15 +53,46 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_7_ECX] = { 7, 0, CPUID_ECX}, [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX}, [CPUID_7_EDX] = { 7, 0, CPUID_EDX}, + [CPUID_7_1_EAX] = { 7, 1, CPUID_EAX}, }; -static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) +/* + * Reverse CPUID and its derivatives can only be used for hardware-defined + * feature words, i.e. words whose bits directly correspond to a CPUID leaf. + * Retrieving a feature bit or masking guest CPUID from a Linux-defined word + * is nonsensical as the bit number/mask is an arbitrary software-defined value + * and can't be used by KVM to query/control guest capabilities. And obviously + * the leaf being queried must have an entry in the lookup table. + */ +static __always_inline void reverse_cpuid_check(unsigned x86_leaf) { - unsigned x86_leaf = x86_feature / 32; - + BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); +} + +/* + * Retrieve the bit mask from an X86_FEATURE_* definition. Features contain + * the hardware defined bit number (stored in bits 4:0) and a software defined + * "word" (stored in bits 31:5). The word is used to index into arrays of + * bit masks that hold the per-cpu feature capabilities, e.g. this_cpu_has(). + */ +static __always_inline u32 __feature_bit(int x86_feature) +{ + reverse_cpuid_check(x86_feature / 32); + return 1 << (x86_feature & 31); +} +#define feature_bit(name) __feature_bit(X86_FEATURE_##name) + +static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) +{ + unsigned x86_leaf = x86_feature / 32; + + reverse_cpuid_check(x86_leaf); return reverse_cpuid[x86_leaf]; } @@ -93,15 +124,11 @@ static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_ { int *reg; - if (x86_feature == X86_FEATURE_XSAVE && - !static_cpu_has(X86_FEATURE_XSAVE)) - return false; - reg = guest_cpuid_get_register(vcpu, x86_feature); if (!reg) return false; - return *reg & bit(x86_feature); + return *reg & __feature_bit(x86_feature); } static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x86_feature) @@ -110,7 +137,7 @@ static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x8 reg = guest_cpuid_get_register(vcpu, x86_feature); if (reg) - *reg &= ~bit(x86_feature); + *reg &= ~__feature_bit(x86_feature); } static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 718f7d9afedc..ddbc61984227 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -22,6 +22,7 @@ #include "kvm_cache_regs.h" #include <asm/kvm_emulate.h> #include <linux/stringify.h> +#include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/nospec-branch.h> @@ -310,7 +311,9 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) #define ON64(x) #endif -static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); +typedef void (*fastop_t)(struct fastop *); + +static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define __FOP_FUNC(name) \ ".align " __stringify(FASTOP_SIZE) " \n\t" \ @@ -1075,8 +1078,23 @@ static void fetch_register_operand(struct operand *op) } } -static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) +static void emulator_get_fpu(void) +{ + fpregs_lock(); + + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); +} + +static void emulator_put_fpu(void) +{ + fpregs_unlock(); +} + +static void read_sse_reg(sse128_t *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; @@ -1098,11 +1116,12 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) #endif default: BUG(); } + emulator_put_fpu(); } -static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, - int reg) +static void write_sse_reg(sse128_t *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; @@ -1124,10 +1143,12 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, #endif default: BUG(); } + emulator_put_fpu(); } -static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) +static void read_mmx_reg(u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; @@ -1139,10 +1160,12 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } -static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) +static void write_mmx_reg(u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; @@ -1154,6 +1177,7 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } static int em_fninit(struct x86_emulate_ctxt *ctxt) @@ -1161,7 +1185,9 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fninit"); + emulator_put_fpu(); return X86EMUL_CONTINUE; } @@ -1172,7 +1198,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstcw %0": "+m"(fcw)); + emulator_put_fpu(); ctxt->dst.val = fcw; @@ -1186,7 +1214,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstsw %0": "+m"(fsw)); + emulator_put_fpu(); ctxt->dst.val = fsw; @@ -1205,7 +1235,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = reg; - read_sse_reg(ctxt, &op->vec_val, reg); + read_sse_reg(&op->vec_val, reg); return; } if (ctxt->d & Mmx) { @@ -1256,7 +1286,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = ctxt->modrm_rm; - read_sse_reg(ctxt, &op->vec_val, ctxt->modrm_rm); + read_sse_reg(&op->vec_val, ctxt->modrm_rm); return rc; } if (ctxt->d & Mmx) { @@ -1833,10 +1863,10 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) op->bytes * op->count); break; case OP_XMM: - write_sse_reg(ctxt, &op->vec_val, op->addr.xmm); + write_sse_reg(&op->vec_val, op->addr.xmm); break; case OP_MM: - write_mmx_reg(ctxt, &op->mm_val, op->addr.mm); + write_mmx_reg(&op->mm_val, op->addr.mm); break; case OP_NONE: /* no writeback */ @@ -2348,12 +2378,7 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) { #ifdef CONFIG_X86_64 - u32 eax, ebx, ecx, edx; - - eax = 0x80000001; - ecx = 0; - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - return edx & bit(X86_FEATURE_LM); + return ctxt->ops->guest_has_long_mode(ctxt); #else return false; #endif @@ -2770,11 +2795,10 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) return emulate_ud(ctxt); ops->get_msr(ctxt, MSR_EFER, &efer); - setup_syscalls_segments(ctxt, &cs, &ss); - if (!(efer & EFER_SCE)) return emulate_ud(ctxt); + setup_syscalls_segments(ctxt, &cs, &ss); ops->get_msr(ctxt, MSR_STAR, &msr_data); msr_data >>= 32; cs_sel = (u16)(msr_data & 0xfffc); @@ -2838,12 +2862,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_PROT64) return X86EMUL_UNHANDLEABLE; - setup_syscalls_segments(ctxt, &cs, &ss); - ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); if ((msr_data & 0xfffc) == 0x0) return emulate_gp(ctxt, 0); + setup_syscalls_segments(ctxt, &cs, &ss); ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK; ss_sel = cs_sel + 8; @@ -3620,18 +3643,11 @@ static int em_mov(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -#define FFL(x) bit(X86_FEATURE_##x) - static int em_movbe(struct x86_emulate_ctxt *ctxt) { - u32 ebx, ecx, edx, eax = 1; u16 tmp; - /* - * Check MOVBE is set in the guest-visible CPUID leaf. - */ - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - if (!(ecx & FFL(MOVBE))) + if (!ctxt->ops->guest_has_movbe(ctxt)) return emulate_ud(ctxt); switch (ctxt->op_bytes) { @@ -4029,10 +4045,7 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt) static int check_fxsr(struct x86_emulate_ctxt *ctxt) { - u32 eax = 1, ebx, ecx = 0, edx; - - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - if (!(edx & FFL(FXSR))) + if (!ctxt->ops->guest_has_fxsr(ctxt)) return emulate_ud(ctxt); if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) @@ -4094,8 +4107,12 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + emulator_put_fpu(); + if (rc != X86EMUL_CONTINUE) return rc; @@ -4138,6 +4155,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + if (size < __fxstate_size(16)) { rc = fxregs_fixup(&fx_state, size); if (rc != X86EMUL_CONTINUE) @@ -4153,9 +4172,25 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); out: + emulator_put_fpu(); + return rc; } +static int em_xsetbv(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ecx, edx; + + eax = reg_read(ctxt, VCPU_REGS_RAX); + edx = reg_read(ctxt, VCPU_REGS_RDX); + ecx = reg_read(ctxt, VCPU_REGS_RCX); + + if (ctxt->ops->set_xcr(ctxt, ecx, ((u64)edx << 32) | eax)) + return emulate_gp(ctxt, 0); + + return X86EMUL_CONTINUE; +} + static bool valid_cr(int nr) { switch (nr) { @@ -4409,6 +4444,12 @@ static const struct opcode group7_rm1[] = { N, N, N, N, N, N, }; +static const struct opcode group7_rm2[] = { + N, + II(ImplicitOps | Priv, em_xsetbv, xsetbv), + N, N, N, N, N, N, +}; + static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), II(SrcNone | Prot | EmulateOnUD, em_hypercall, vmmcall), @@ -4498,7 +4539,8 @@ static const struct group_dual group7 = { { }, { EXT(0, group7_rm0), EXT(0, group7_rm1), - N, EXT(0, group7_rm3), + EXT(0, group7_rm2), + EXT(0, group7_rm3), II(SrcNone | DstMem | Mov, em_smsw, smsw), N, II(SrcMem16 | Mov | Priv, em_lmsw, lmsw), EXT(0, group7_rm7), @@ -5144,7 +5186,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) else { rc = __do_insn_fetch_bytes(ctxt, 1); if (rc != X86EMUL_CONTINUE) - return rc; + goto done; } switch (mode) { @@ -5191,16 +5233,28 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->ad_bytes = def_ad_bytes ^ 6; break; case 0x26: /* ES override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_ES; + break; case 0x2e: /* CS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_CS; + break; case 0x36: /* SS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_SS; + break; case 0x3e: /* DS override */ has_seg_override = true; - ctxt->seg_override = (ctxt->b >> 3) & 3; + ctxt->seg_override = VCPU_SREG_DS; break; case 0x64: /* FS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_FS; + break; case 0x65: /* GS override */ has_seg_override = true; - ctxt->seg_override = ctxt->b & 7; + ctxt->seg_override = VCPU_SREG_GS; break; case 0x40 ... 0x4f: /* REX */ if (mode != X86EMUL_MODE_PROT64) @@ -5284,10 +5338,15 @@ done_prefixes: } break; case Escape: - if (ctxt->modrm > 0xbf) - opcode = opcode.u.esc->high[ctxt->modrm - 0xc0]; - else + if (ctxt->modrm > 0xbf) { + size_t size = ARRAY_SIZE(opcode.u.esc->high); + u32 index = array_index_nospec( + ctxt->modrm - 0xc0, size); + + opcode = opcode.u.esc->high[index]; + } else { opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7]; + } break; case InstrDual: if ((ctxt->modrm >> 6) == 3) @@ -5395,6 +5454,8 @@ done_prefixes: ctxt->memopp->addr.mem.ea + ctxt->_eip); done: + if (rc == X86EMUL_PROPAGATE_FAULT) + ctxt->have_exception = true; return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } @@ -5427,7 +5488,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { int rc; + emulator_get_fpu(); rc = asm_safe("fwait"); + emulator_put_fpu(); if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); @@ -5435,14 +5498,13 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, - struct operand *op) +static void fetch_possible_mmx_operand(struct operand *op) { if (op->type == OP_MM) - read_mmx_reg(ctxt, &op->mm_val, op->addr.mm); + read_mmx_reg(&op->mm_val, op->addr.mm); } -static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) +static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop) { ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; @@ -5518,10 +5580,10 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) * Now that we know the fpu is exception safe, we can fetch * operands from it. */ - fetch_possible_mmx_operand(ctxt, &ctxt->src); - fetch_possible_mmx_operand(ctxt, &ctxt->src2); + fetch_possible_mmx_operand(&ctxt->src); + fetch_possible_mmx_operand(&ctxt->src2); if (!(ctxt->d & Mov)) - fetch_possible_mmx_operand(ctxt, &ctxt->dst); + fetch_possible_mmx_operand(&ctxt->dst); } if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { @@ -5620,14 +5682,10 @@ special_insn: ctxt->eflags &= ~X86_EFLAGS_RF; if (ctxt->execute) { - if (ctxt->d & Fastop) { - void (*fop)(struct fastop *) = (void *)ctxt->execute; - rc = fastop(ctxt, fop); - if (rc != X86EMUL_CONTINUE) - goto done; - goto writeback; - } - rc = ctxt->execute(ctxt); + if (ctxt->d & Fastop) + rc = fastop(ctxt, (fastop_t)ctxt->execute); + else + rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) goto done; goto writeback; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index c10a8b10b203..a86fda7a1d03 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -23,6 +23,7 @@ #include "ioapic.h" #include "hyperv.h" +#include <linux/cpu.h> #include <linux/kvm_host.h> #include <linux/highmem.h> #include <linux/sched/cputime.h> @@ -32,6 +33,7 @@ #include <trace/events/kvm.h> #include "trace.h" +#include "irq.h" #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64) @@ -645,7 +647,9 @@ static int stimer_notify_direct(struct kvm_vcpu_hv_stimer *stimer) .vector = stimer->config.apic_vector }; - return !kvm_apic_set_irq(vcpu, &irq, NULL); + if (lapic_in_kernel(vcpu)) + return !kvm_apic_set_irq(vcpu, &irq, NULL); + return 0; } static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer) @@ -772,9 +776,10 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) /* * Hyper-V SynIC auto EOI SINT's are - * not compatible with APICV, so deactivate APICV + * not compatible with APICV, so request + * to deactivate APICV permanently. */ - kvm_vcpu_deactivate_apicv(vcpu); + kvm_request_apicv_update(vcpu->kvm, false, APICV_INHIBIT_REASON_HYPERV); synic->active = true; synic->dont_zero_synic_pages = dont_zero_synic_pages; return 0; @@ -806,11 +811,12 @@ static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 *pdata) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - *pdata = hv->hv_crash_param[index]; + *pdata = hv->hv_crash_param[array_index_nospec(index, size)]; return 0; } @@ -849,11 +855,12 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 data) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - hv->hv_crash_param[index] = data; + hv->hv_crash_param[array_index_nospec(index, size)] = data; return 0; } @@ -1055,7 +1062,7 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); return 1; } @@ -1118,7 +1125,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; /* - * Clear apic_assist portion of f(struct hv_vp_assist_page + * Clear apic_assist portion of struct hv_vp_assist_page * only, there can be valuable data in the rest which needs * to be preserved e.g. on migration. */ @@ -1175,7 +1182,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); return 1; } @@ -1781,7 +1788,7 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args) int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { - uint16_t evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu); + uint16_t evmcs_ver = 0; struct kvm_cpuid_entry2 cpuid_entries[] = { { .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS }, { .function = HYPERV_CPUID_INTERFACE }, @@ -1793,6 +1800,9 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, }; int i, nent = ARRAY_SIZE(cpuid_entries); + if (kvm_x86_ops->nested_get_evmcs_version) + evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu); + /* Skip NESTED_FEATURES if eVMCS is not supported */ if (!evmcs_ver) --nent; @@ -1849,7 +1859,13 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; - ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + + /* + * Direct Synthetic timers only make sense with in-kernel + * LAPIC + */ + if (lapic_in_kernel(vcpu)) + ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; break; @@ -1861,7 +1877,8 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; if (evmcs_ver) ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED; - + if (!cpu_smt_possible()) + ent->eax |= HV_X64_NO_NONARCH_CORESHARING; /* * Default number of spinlock retry attempts, matches * HyperV 2016. diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 4a6dc54cc12b..b24c606ac04b 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -295,12 +295,24 @@ void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject) if (atomic_read(&ps->reinject) == reinject) return; + /* + * AMD SVM AVIC accelerates EOI write and does not trap. + * This cause in-kernel PIT re-inject mode to fail + * since it checks ps->irq_ack before kvm_set_irq() + * and relies on the ack notifier to timely queue + * the pt->worker work iterm and reinject the missed tick. + * So, deactivate APICv when PIT is in reinject mode. + */ if (reinject) { + kvm_request_apicv_update(kvm, false, + APICV_INHIBIT_REASON_PIT_REINJ); /* The initial state is preserved while ps->reinject == 0. */ kvm_pit_reset_reinject(pit); kvm_register_irq_ack_notifier(kvm, &ps->irq_ack_notifier); kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); } else { + kvm_request_apicv_update(kvm, true, + APICV_INHIBIT_REASON_PIT_REINJ); kvm_unregister_irq_ack_notifier(kvm, &ps->irq_ack_notifier); kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier); } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 8b38bb4868a6..629a09ca9860 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -460,10 +460,14 @@ static int picdev_write(struct kvm_pic *s, switch (addr) { case 0x20: case 0x21: + pic_lock(s); + pic_ioport_write(&s->pics[0], addr, data); + pic_unlock(s); + break; case 0xa0: case 0xa1: pic_lock(s); - pic_ioport_write(&s->pics[addr >> 7], addr, data); + pic_ioport_write(&s->pics[1], addr, data); pic_unlock(s); break; case 0x4d0: diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index d859ae8890d0..7668fed1ce65 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -36,6 +36,7 @@ #include <linux/io.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/nospec.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/current.h> @@ -48,6 +49,11 @@ static int ioapic_service(struct kvm_ioapic *vioapic, int irq, bool line_status); +static void kvm_ioapic_update_eoi_one(struct kvm_vcpu *vcpu, + struct kvm_ioapic *ioapic, + int trigger_mode, + int pin); + static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, unsigned long addr, unsigned long length) @@ -68,13 +74,14 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, default: { u32 redir_index = (ioapic->ioregsel - 0x10) >> 1; - u64 redir_content; + u64 redir_content = ~0ULL; + + if (redir_index < IOAPIC_NUM_PINS) { + u32 index = array_index_nospec( + redir_index, IOAPIC_NUM_PINS); - if (redir_index < IOAPIC_NUM_PINS) - redir_content = - ioapic->redirtbl[redir_index].bits; - else - redir_content = ~0ULL; + redir_content = ioapic->redirtbl[index].bits; + } result = (ioapic->ioregsel & 0x1) ? (redir_content >> 32) & 0xffffffff : @@ -108,8 +115,9 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) union kvm_ioapic_redirect_entry *e; e = &ioapic->redirtbl[RTC_GSI]; - if (!kvm_apic_match_dest(vcpu, NULL, 0, e->fields.dest_id, - e->fields.dest_mode)) + if (!kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + e->fields.dest_id, + kvm_lapic_irq_dest_mode(!!e->fields.dest_mode))) return; new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector); @@ -151,10 +159,16 @@ static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic) __rtc_irq_eoi_tracking_restore_one(vcpu); } -static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu) +static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu, + int vector) { - if (test_and_clear_bit(vcpu->vcpu_id, - ioapic->rtc_status.dest_map.map)) { + struct dest_map *dest_map = &ioapic->rtc_status.dest_map; + + /* RTC special handling */ + if (test_bit(vcpu->vcpu_id, dest_map->map) && + (vector == dest_map->vectors[vcpu->vcpu_id]) && + (test_and_clear_bit(vcpu->vcpu_id, + ioapic->rtc_status.dest_map.map))) { --ioapic->rtc_status.pending_eoi; rtc_status_pending_eoi_check_valid(ioapic); } @@ -168,6 +182,31 @@ static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic) return false; } +static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq) +{ + int i; + struct kvm_vcpu *vcpu; + union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; + + kvm_for_each_vcpu(i, vcpu, ioapic->kvm) { + if (!kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + entry->fields.dest_id, + entry->fields.dest_mode) || + kvm_apic_pending_eoi(vcpu, entry->fields.vector)) + continue; + + /* + * If no longer has pending EOI in LAPICs, update + * EOI for this vetor. + */ + rtc_irq_eoi(ioapic, vcpu, entry->fields.vector); + kvm_ioapic_update_eoi_one(vcpu, ioapic, + entry->fields.trig_mode, + irq); + break; + } +} + static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, int irq_level, bool line_status) { @@ -186,9 +225,18 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, } /* + * AMD SVM AVIC accelerate EOI write and do not trap, + * in-kernel IOAPIC will not be able to receive the EOI. + * In this case, we do lazy update of the pending EOI when + * trying to set IOAPIC irq. + */ + if (kvm_apicv_activated(ioapic->kvm)) + ioapic_lazy_update_eoi(ioapic, irq); + + /* * Return 0 for coalesced interrupts; for edge-triggered interrupts, * this only happens if a previous edge has not been delivered due - * do masking. For level interrupts, the remote_irr field tells + * to masking. For level interrupts, the remote_irr field tells * us if the interrupt is waiting for an EOI. * * RTC is special: it is edge-triggered, but userspace likes to know @@ -250,8 +298,10 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) || index == RTC_GSI) { - if (kvm_apic_match_dest(vcpu, NULL, 0, - e->fields.dest_id, e->fields.dest_mode) || + u16 dm = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); + + if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + e->fields.dest_id, dm) || kvm_apic_pending_eoi(vcpu, e->fields.vector)) __set_bit(e->fields.vector, ioapic_handled_vectors); @@ -271,8 +321,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) { unsigned index; bool mask_before, mask_after; - int old_remote_irr, old_delivery_status; union kvm_ioapic_redirect_entry *e; + unsigned long vcpu_bitmap; + int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode; switch (ioapic->ioregsel) { case IOAPIC_REG_VERSION: @@ -291,11 +342,14 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (index >= IOAPIC_NUM_PINS) return; + index = array_index_nospec(index, IOAPIC_NUM_PINS); e = &ioapic->redirtbl[index]; mask_before = e->fields.mask; /* Preserve read-only fields */ old_remote_irr = e->fields.remote_irr; old_delivery_status = e->fields.delivery_status; + old_dest_id = e->fields.dest_id; + old_dest_mode = e->fields.dest_mode; if (ioapic->ioregsel & 1) { e->bits &= 0xffffffff; e->bits |= (u64) val << 32; @@ -321,7 +375,37 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG && ioapic->irr & (1 << index)) ioapic_service(ioapic, index, false); - kvm_make_scan_ioapic_request(ioapic->kvm); + if (e->fields.delivery_mode == APIC_DM_FIXED) { + struct kvm_lapic_irq irq; + + irq.shorthand = APIC_DEST_NOSHORT; + irq.vector = e->fields.vector; + irq.delivery_mode = e->fields.delivery_mode << 8; + irq.dest_id = e->fields.dest_id; + irq.dest_mode = + kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); + bitmap_zero(&vcpu_bitmap, 16); + kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, + &vcpu_bitmap); + if (old_dest_mode != e->fields.dest_mode || + old_dest_id != e->fields.dest_id) { + /* + * Update vcpu_bitmap with vcpus specified in + * the previous request as well. This is done to + * keep ioapic_handled_vectors synchronized. + */ + irq.dest_id = old_dest_id; + irq.dest_mode = + kvm_lapic_irq_dest_mode( + !!e->fields.dest_mode); + kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, + &vcpu_bitmap); + } + kvm_make_scan_ioapic_request_mask(ioapic->kvm, + &vcpu_bitmap); + } else { + kvm_make_scan_ioapic_request(ioapic->kvm); + } break; } } @@ -339,11 +423,11 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.dest_id = entry->fields.dest_id; irqe.vector = entry->fields.vector; - irqe.dest_mode = entry->fields.dest_mode; + irqe.dest_mode = kvm_lapic_irq_dest_mode(!!entry->fields.dest_mode); irqe.trig_mode = entry->fields.trig_mode; irqe.delivery_mode = entry->fields.delivery_mode << 8; irqe.level = 1; - irqe.shorthand = 0; + irqe.shorthand = APIC_DEST_NOSHORT; irqe.msi_redir_hint = false; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) @@ -415,72 +499,68 @@ static void kvm_ioapic_eoi_inject_work(struct work_struct *work) } #define IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT 10000 - -static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, - struct kvm_ioapic *ioapic, int vector, int trigger_mode) +static void kvm_ioapic_update_eoi_one(struct kvm_vcpu *vcpu, + struct kvm_ioapic *ioapic, + int trigger_mode, + int pin) { - struct dest_map *dest_map = &ioapic->rtc_status.dest_map; struct kvm_lapic *apic = vcpu->arch.apic; - int i; - - /* RTC special handling */ - if (test_bit(vcpu->vcpu_id, dest_map->map) && - vector == dest_map->vectors[vcpu->vcpu_id]) - rtc_irq_eoi(ioapic, vcpu); - - for (i = 0; i < IOAPIC_NUM_PINS; i++) { - union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; + union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[pin]; - if (ent->fields.vector != vector) - continue; - - /* - * We are dropping lock while calling ack notifiers because ack - * notifier callbacks for assigned devices call into IOAPIC - * recursively. Since remote_irr is cleared only after call - * to notifiers if the same vector will be delivered while lock - * is dropped it will be put into irr and will be delivered - * after ack notifier returns. - */ - spin_unlock(&ioapic->lock); - kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i); - spin_lock(&ioapic->lock); + /* + * We are dropping lock while calling ack notifiers because ack + * notifier callbacks for assigned devices call into IOAPIC + * recursively. Since remote_irr is cleared only after call + * to notifiers if the same vector will be delivered while lock + * is dropped it will be put into irr and will be delivered + * after ack notifier returns. + */ + spin_unlock(&ioapic->lock); + kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, pin); + spin_lock(&ioapic->lock); - if (trigger_mode != IOAPIC_LEVEL_TRIG || - kvm_lapic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) - continue; + if (trigger_mode != IOAPIC_LEVEL_TRIG || + kvm_lapic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) + return; - ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); - ent->fields.remote_irr = 0; - if (!ent->fields.mask && (ioapic->irr & (1 << i))) { - ++ioapic->irq_eoi[i]; - if (ioapic->irq_eoi[i] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) { - /* - * Real hardware does not deliver the interrupt - * immediately during eoi broadcast, and this - * lets a buggy guest make slow progress - * even if it does not correctly handle a - * level-triggered interrupt. Emulate this - * behavior if we detect an interrupt storm. - */ - schedule_delayed_work(&ioapic->eoi_inject, HZ / 100); - ioapic->irq_eoi[i] = 0; - trace_kvm_ioapic_delayed_eoi_inj(ent->bits); - } else { - ioapic_service(ioapic, i, false); - } + ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); + ent->fields.remote_irr = 0; + if (!ent->fields.mask && (ioapic->irr & (1 << pin))) { + ++ioapic->irq_eoi[pin]; + if (ioapic->irq_eoi[pin] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) { + /* + * Real hardware does not deliver the interrupt + * immediately during eoi broadcast, and this + * lets a buggy guest make slow progress + * even if it does not correctly handle a + * level-triggered interrupt. Emulate this + * behavior if we detect an interrupt storm. + */ + schedule_delayed_work(&ioapic->eoi_inject, HZ / 100); + ioapic->irq_eoi[pin] = 0; + trace_kvm_ioapic_delayed_eoi_inj(ent->bits); } else { - ioapic->irq_eoi[i] = 0; + ioapic_service(ioapic, pin, false); } + } else { + ioapic->irq_eoi[pin] = 0; } } void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode) { + int i; struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; spin_lock(&ioapic->lock); - __kvm_ioapic_update_eoi(vcpu, ioapic, vector, trigger_mode); + rtc_irq_eoi(ioapic, vcpu, vector); + for (i = 0; i < IOAPIC_NUM_PINS; i++) { + union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; + + if (ent->fields.vector != vector) + continue; + kvm_ioapic_update_eoi_one(vcpu, ioapic, trigger_mode, i); + } spin_unlock(&ioapic->lock); } diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index ea1a4e0297da..2fb2e3c80724 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -116,9 +116,6 @@ static inline int ioapic_in_kernel(struct kvm *kvm) } void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); -bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, unsigned int dest, int dest_mode); -int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); @@ -126,9 +123,6 @@ void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, int level, bool line_status); void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id); -int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, - struct dest_map *dest_map); void kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 7c6233d37c64..f173ab6b407e 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -113,5 +113,8 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu); int kvm_setup_default_irq_routing(struct kvm *kvm); int kvm_setup_empty_irq_routing(struct kvm *kvm); +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq, + struct dest_map *dest_map); #endif diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 8ecd48d31800..79afa0bb5f41 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -52,15 +52,15 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; unsigned int dest_vcpus = 0; - if (irq->dest_mode == 0 && irq->dest_id == 0xff && - kvm_lowest_prio_delivery(irq)) { + if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) + return r; + + if (irq->dest_mode == APIC_DEST_PHYSICAL && + irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) { printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); irq->delivery_mode = APIC_DM_FIXED; } - if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) - return r; - memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap)); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -114,13 +114,14 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, irq->dest_id |= MSI_ADDR_EXT_DEST_ID(e->msi.address_hi); irq->vector = (e->msi.data & MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; - irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; + irq->dest_mode = kvm_lapic_irq_dest_mode( + !!((1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo)); irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; irq->delivery_mode = e->msi.data & 0x700; irq->msi_redir_hint = ((e->msi.address_lo & MSI_ADDR_REDIRECTION_LOWPRI) > 0); irq->level = 1; - irq->shorthand = 0; + irq->shorthand = APIC_DEST_NOSHORT; } EXPORT_SYMBOL_GPL(kvm_set_msi_irq); @@ -416,7 +417,8 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0, + if (irq.level && + kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, irq.dest_id, irq.dest_mode)) __set_bit(irq.vector, ioapic_handled_vectors); } diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 1cc6c47dc77e..58767020de41 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -37,22 +37,50 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif -static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, - enum kvm_reg reg) +static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) { - if (!test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail)) + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) +{ + if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) + return 0; + + if (!kvm_register_is_available(vcpu, reg)) kvm_x86_ops->cache_reg(vcpu, reg); return vcpu->arch.regs[reg]; } -static inline void kvm_register_write(struct kvm_vcpu *vcpu, - enum kvm_reg reg, +static inline void kvm_register_write(struct kvm_vcpu *vcpu, int reg, unsigned long val) { + if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) + return; + vcpu->arch.regs[reg] = val; - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + kvm_register_mark_dirty(vcpu, reg); } static inline unsigned long kvm_rip_read(struct kvm_vcpu *vcpu) @@ -79,9 +107,8 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) { might_sleep(); /* on svm */ - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail)) - kvm_x86_ops->cache_reg(vcpu, (enum kvm_reg)VCPU_EXREG_PDPTR); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) + kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR); return vcpu->arch.walk_mmu->pdptrs[index]; } @@ -109,8 +136,8 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask) static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu) { - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - kvm_x86_ops->decache_cr3(vcpu); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) + kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_CR3); return vcpu->arch.cr3; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 685d17c11461..afcd30d44cbb 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -56,17 +56,17 @@ #define APIC_VERSION (0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16)) #define LAPIC_MMIO_LENGTH (1 << 12) /* followed define is not in apicdef.h */ -#define APIC_SHORT_MASK 0xc0000 -#define APIC_DEST_NOSHORT 0x0 -#define APIC_DEST_MASK 0x800 #define MAX_APIC_VECTOR 256 #define APIC_VECTORS_PER_REG 32 #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul -#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100 -#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000 +static bool lapic_timer_advance_dynamic __read_mostly; +#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_NS_INIT 1000 +#define LAPIC_TIMER_ADVANCE_NS_MAX 5000 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -108,11 +108,6 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -static inline u8 kvm_xapic_id(struct kvm_lapic *apic) -{ - return kvm_lapic_get_reg(apic, APIC_ID) >> 24; -} - static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) { return apic->vcpu->vcpu_id; @@ -216,6 +211,9 @@ static void recalculate_apic_map(struct kvm *kvm) if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) new->phys_map[xapic_id] = apic; + if (!kvm_apic_sw_enabled(apic)) + continue; + ldr = kvm_lapic_get_reg(apic, APIC_LDR); if (apic_x2apic_mode(apic)) { @@ -258,6 +256,8 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) static_key_slow_dec_deferred(&apic_sw_disabled); else static_key_slow_inc(&apic_sw_disabled.key); + + recalculate_apic_map(apic->vcpu->kvm); } } @@ -554,60 +554,53 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, irq->level, irq->trig_mode, dest_map); } +static int __pv_send_ipi(unsigned long *ipi_bitmap, struct kvm_apic_map *map, + struct kvm_lapic_irq *irq, u32 min) +{ + int i, count = 0; + struct kvm_vcpu *vcpu; + + if (min > map->max_apic_id) + return 0; + + for_each_set_bit(i, ipi_bitmap, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, irq, NULL); + } + } + + return count; +} + int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit) { - int i; struct kvm_apic_map *map; - struct kvm_vcpu *vcpu; struct kvm_lapic_irq irq = {0}; int cluster_size = op_64_bit ? 64 : 32; - int count = 0; + int count; + + if (icr & (APIC_DEST_MASK | APIC_SHORT_MASK)) + return -KVM_EINVAL; irq.vector = icr & APIC_VECTOR_MASK; irq.delivery_mode = icr & APIC_MODE_MASK; irq.level = (icr & APIC_INT_ASSERT) != 0; irq.trig_mode = icr & APIC_INT_LEVELTRIG; - if (icr & APIC_DEST_MASK) - return -KVM_EINVAL; - if (icr & APIC_SHORT_MASK) - return -KVM_EINVAL; - rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); - if (unlikely(!map)) { - count = -EOPNOTSUPP; - goto out; + count = -EOPNOTSUPP; + if (likely(map)) { + count = __pv_send_ipi(&ipi_bitmap_low, map, &irq, min); + min += cluster_size; + count += __pv_send_ipi(&ipi_bitmap_high, map, &irq, min); } - if (min > map->max_apic_id) - goto out; - /* Bits above cluster_size are masked in the caller. */ - for_each_set_bit(i, &ipi_bitmap_low, - min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { - if (map->phys_map[min + i]) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); - } - } - - min += cluster_size; - - if (min > map->max_apic_id) - goto out; - - for_each_set_bit(i, &ipi_bitmap_high, - min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { - if (map->phys_map[min + i]) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); - } - } - -out: rcu_read_unlock(); return count; } @@ -796,13 +789,13 @@ static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id, } bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, unsigned int dest, int dest_mode) + int shorthand, unsigned int dest, int dest_mode) { struct kvm_lapic *target = vcpu->arch.apic; u32 mda = kvm_apic_mda(vcpu, dest, source, target); ASSERT(target); - switch (short_hand) { + switch (shorthand) { case APIC_DEST_NOSHORT: if (dest_mode == APIC_DEST_PHYSICAL) return kvm_apic_match_physical_addr(target, mda); @@ -971,12 +964,12 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, } /* - * This routine tries to handler interrupts in posted mode, here is how + * This routine tries to handle interrupts in posted mode, here is how * it deals with different cases: * - For single-destination interrupts, handle it in posted mode * - Else if vector hashing is enabled and it is a lowest-priority * interrupt, handle it in posted mode and use the following mechanism - * to find the destinaiton vCPU. + * to find the destination vCPU. * 1. For lowest-priority interrupts, store all the possible * destination vCPUs in an array. * 2. Use "guest vector % max number of destination vCPUs" to find @@ -1087,9 +1080,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, result = 1; /* assumes that there are only KVM_APIC_INIT/SIPI */ apic->pending_events = (1UL << KVM_APIC_INIT); - /* make sure pending_events is visible before sending - * the request */ - smp_wmb(); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } @@ -1121,6 +1111,50 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, return result; } +/* + * This routine identifies the destination vcpus mask meant to receive the + * IOAPIC interrupts. It either uses kvm_apic_map_get_dest_lapic() to find + * out the destination vcpus array and set the bitmap or it traverses to + * each available vcpu to identify the same. + */ +void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, + unsigned long *vcpu_bitmap) +{ + struct kvm_lapic **dest_vcpu = NULL; + struct kvm_lapic *src = NULL; + struct kvm_apic_map *map; + struct kvm_vcpu *vcpu; + unsigned long bitmap; + int i, vcpu_idx; + bool ret; + + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); + + ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dest_vcpu, + &bitmap); + if (ret) { + for_each_set_bit(i, &bitmap, 16) { + if (!dest_vcpu[i]) + continue; + vcpu_idx = dest_vcpu[i]->vcpu->vcpu_idx; + __set_bit(vcpu_idx, vcpu_bitmap); + } + } else { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!kvm_apic_present(vcpu)) + continue; + if (!kvm_apic_match_dest(vcpu, NULL, + irq->shorthand, + irq->dest_id, + irq->dest_mode)) + continue; + __set_bit(i, vcpu_bitmap); + } + } + rcu_read_unlock(); +} + int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) { return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; @@ -1193,10 +1227,8 @@ void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector) } EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated); -static void apic_send_ipi(struct kvm_lapic *apic) +static void apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high) { - u32 icr_low = kvm_lapic_get_reg(apic, APIC_ICR); - u32 icr_high = kvm_lapic_get_reg(apic, APIC_ICR2); struct kvm_lapic_irq irq; irq.vector = icr_low & APIC_VECTOR_MASK; @@ -1482,26 +1514,25 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu, u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns; u64 ns; + /* Do not adjust for tiny fluctuations or large random spikes. */ + if (abs(advance_expire_delta) > LAPIC_TIMER_ADVANCE_ADJUST_MAX || + abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_MIN) + return; + /* too early */ if (advance_expire_delta < 0) { ns = -advance_expire_delta * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - timer_advance_ns -= min((u32)ns, - timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns -= ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP; } else { /* too late */ ns = advance_expire_delta * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - timer_advance_ns += min((u32)ns, - timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP; } - if (abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) - apic->lapic_timer.timer_advance_adjust_done = true; - if (unlikely(timer_advance_ns > 5000)) { - timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; - apic->lapic_timer.timer_advance_adjust_done = false; - } + if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX)) + timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; apic->lapic_timer.timer_advance_ns = timer_advance_ns; } @@ -1521,7 +1552,7 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) if (guest_tsc < tsc_deadline) __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - if (unlikely(!apic->lapic_timer.timer_advance_adjust_done)) + if (lapic_timer_advance_dynamic) adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); } @@ -1537,9 +1568,9 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic) struct kvm_timer *ktimer = &apic->lapic_timer; kvm_apic_local_deliver(apic, APIC_LVTT); - if (apic_lvtt_tscdeadline(apic)) + if (apic_lvtt_tscdeadline(apic)) { ktimer->tscdeadline = 0; - if (apic_lvtt_oneshot(apic)) { + } else if (apic_lvtt_oneshot(apic)) { ktimer->tscdeadline = 0; ktimer->target_expiration = 0; } @@ -1593,7 +1624,7 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) likely(ns > apic->lapic_timer.timer_advance_ns)) { expire = ktime_add_ns(now, ns); expire = ktime_sub_ns(expire, ktimer->timer_advance_ns); - hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS); + hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_HARD); } else apic_timer_expired(apic); @@ -1909,8 +1940,9 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) } case APIC_ICR: /* No delay here, so we always clear the pending bit */ - kvm_lapic_set_reg(apic, APIC_ICR, val & ~(1 << 12)); - apic_send_ipi(apic); + val &= ~(1 << 12); + apic_send_ipi(apic, val, kvm_lapic_get_reg(apic, APIC_ICR2)); + kvm_lapic_set_reg(apic, APIC_ICR, val); break; case APIC_ICR2: @@ -1925,15 +1957,20 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: - case APIC_LVTERR: + case APIC_LVTERR: { /* TODO: Check vector */ + size_t size; + u32 index; + if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; - - val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4]; + size = ARRAY_SIZE(apic_lvt_mask); + index = array_index_nospec( + (reg - APIC_LVTT) >> 4, size); + val &= apic_lvt_mask[index]; kvm_lapic_set_reg(apic, reg, val); - break; + } case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) @@ -2147,6 +2184,21 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) pr_warn_once("APIC base relocation is unsupported by KVM"); } +void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (vcpu->arch.apicv_active) { + /* irr_pending is always true when apicv is activated. */ + apic->irr_pending = true; + apic->isr_count = 1; + } else { + apic->irr_pending = (apic_search_irr(apic) != -1); + apic->isr_count = count_vectors(apic->regs + APIC_ISR); + } +} +EXPORT_SYMBOL_GPL(kvm_apic_update_apicv); + void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -2189,8 +2241,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_lapic_set_reg(apic, APIC_ISR + 0x10 * i, 0); kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } - apic->irr_pending = vcpu->arch.apicv_active; - apic->isr_count = vcpu->arch.apicv_active ? 1 : 0; + kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -2294,17 +2345,16 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) apic->vcpu = vcpu; hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_HARD); apic->lapic_timer.timer.function = apic_timer_fn; if (timer_advance_ns == -1) { - apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; - apic->lapic_timer.timer_advance_adjust_done = false; + apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; + lapic_timer_advance_dynamic = true; } else { apic->lapic_timer.timer_advance_ns = timer_advance_ns; - apic->lapic_timer.timer_advance_adjust_done = true; + lapic_timer_advance_dynamic = false; } - /* * APIC is created enabled. This will prevent kvm_lapic_set_base from * thinking that APIC state has changed. @@ -2336,14 +2386,13 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) { u32 lvt0 = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LVT0); - int r = 0; if (!kvm_apic_hw_enabled(vcpu->arch.apic)) - r = 1; + return 1; if ((lvt0 & APIC_LVT_MASKED) == 0 && GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) - r = 1; - return r; + return 1; + return 0; } void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) @@ -2449,9 +2498,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); start_apic_timer(apic); - apic->irr_pending = true; - apic->isr_count = vcpu->arch.apicv_active ? - 1 : count_vectors(apic->regs + APIC_ISR); + kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { kvm_x86_ops->apicv_post_state_restore(vcpu); @@ -2479,7 +2526,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) timer = &vcpu->arch.apic->lapic_timer.timer; if (hrtimer_cancel(timer)) - hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_HARD); } /* @@ -2702,11 +2749,14 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) return; /* - * INITs are latched while in SMM. Because an SMM CPU cannot - * be in KVM_MP_STATE_INIT_RECEIVED state, just eat SIPIs - * and delay processing of INIT until the next RSM. + * INITs are latched while CPU is in specific states + * (SMM, VMX non-root mode, SVM with GIF=0). + * Because a CPU cannot be in these states immediately + * after it has processed an INIT signal (and thus in + * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs + * and leave the INIT pending. */ - if (is_smm(vcpu)) { + if (kvm_vcpu_latch_init(vcpu)) { WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); if (test_bit(KVM_APIC_SIPI, &apic->pending_events)) clear_bit(KVM_APIC_SIPI, &apic->pending_events); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 50053d2b8b7b..ec6fbfe325cf 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -10,8 +10,9 @@ #define KVM_APIC_SIPI 1 #define KVM_APIC_LVT_NUM 6 -#define KVM_APIC_SHORT_MASK 0xc0000 -#define KVM_APIC_DEST_MASK 0x800 +#define APIC_SHORT_MASK 0xc0000 +#define APIC_DEST_NOSHORT 0x0 +#define APIC_DEST_MASK 0x800 #define APIC_BUS_CYCLE_NS 1 #define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) @@ -35,7 +36,6 @@ struct kvm_timer { s64 advance_expire_delta; atomic_t pending; /* accumulated triggered timers */ bool hv_timer_in_use; - bool timer_advance_adjust_done; }; struct kvm_lapic { @@ -83,14 +83,15 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val); int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, void *data); bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, unsigned int dest, int dest_mode); - + int shorthand, unsigned int dest, int dest_mode); +int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); +void kvm_apic_update_apicv(struct kvm_vcpu *vcpu); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); @@ -227,6 +228,9 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu); +void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, + unsigned long *vcpu_bitmap); + bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); int kvm_vector_to_index(u32 vector, u32 dest_vcpus, @@ -243,4 +247,9 @@ static inline enum lapic_mode kvm_apic_mode(u64 apic_base) return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); } +static inline u8 kvm_xapic_id(struct kvm_lapic *apic) +{ + return kvm_lapic_get_reg(apic, APIC_ID) >> 24; +} + #endif diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 54c2a377795b..a647601c9e1c 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -51,7 +51,7 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value); +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); @@ -102,6 +102,19 @@ static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu) kvm_get_active_pcid(vcpu)); } +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault); + +static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + u32 err, bool prefault) +{ +#ifdef CONFIG_RETPOLINE + if (likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault)) + return kvm_tdp_page_fault(vcpu, cr2_or_gpa, err, prefault); +#endif + return vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, err, prefault); +} + /* * Currently, we have two sorts of write-protection, a) the first one * write-protects guest page to sync the guest modification, b) another one is @@ -210,4 +223,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); + +int kvm_mmu_post_init_vm(struct kvm *kvm); +void kvm_mmu_pre_destroy_vm(struct kvm *kvm); + #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu/mmu.c index 24843cf49579..87e9ba27ada1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -37,9 +37,10 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kthread.h> #include <asm/page.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/cmpxchg.h> #include <asm/e820/api.h> #include <asm/io.h> @@ -47,6 +48,35 @@ #include <asm/kvm_page_track.h> #include "trace.h" +extern bool itlb_multihit_kvm_mitigation; + +static int __read_mostly nx_huge_pages = -1; +#ifdef CONFIG_PREEMPT_RT +/* Recovery can cause latency spikes, disable it for PREEMPT_RT. */ +static uint __read_mostly nx_huge_pages_recovery_ratio = 0; +#else +static uint __read_mostly nx_huge_pages_recovery_ratio = 60; +#endif + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp); + +static struct kernel_param_ops nx_huge_pages_ops = { + .set = set_nx_huge_pages, + .get = param_get_bool, +}; + +static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = { + .set = set_nx_huge_pages_recovery_ratio, + .get = param_get_uint, +}; + +module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); +__MODULE_PARM_TYPE(nx_huge_pages, "bool"); +module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, + &nx_huge_pages_recovery_ratio, 0644); +__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); + /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: @@ -83,7 +113,17 @@ module_param(dbg, bool, 0644); #define PTE_PREFETCH_NUM 8 #define PT_FIRST_AVAIL_BITS_SHIFT 10 -#define PT64_SECOND_AVAIL_BITS_SHIFT 52 +#define PT64_SECOND_AVAIL_BITS_SHIFT 54 + +/* + * The mask used to denote special SPTEs, which can be either MMIO SPTEs or + * Access Tracking SPTEs. + */ +#define SPTE_SPECIAL_MASK (3ULL << 52) +#define SPTE_AD_ENABLED_MASK (0ULL << 52) +#define SPTE_AD_DISABLED_MASK (1ULL << 52) +#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52) +#define SPTE_MMIO_MASK (3ULL << 52) #define PT64_LEVEL_BITS 9 @@ -214,16 +254,16 @@ static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_mmio_value; +static u64 __read_mostly shadow_mmio_access_mask; static u64 __read_mostly shadow_present_mask; static u64 __read_mostly shadow_me_mask; /* - * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. - * Non-present SPTEs with shadow_acc_track_value set are in place for access - * tracking. + * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK; + * shadow_acc_track_mask is the set of bits to be cleared in non-accessed + * pages. */ static u64 __read_mostly shadow_acc_track_mask; -static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK; /* * The mask/shift to use for saving the original R/X bits when marking the PTE @@ -299,34 +339,63 @@ static void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask) { + BUG_ON((u64)(unsigned)access_mask != access_mask); BUG_ON((mmio_mask & mmio_value) != mmio_value); - shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; + shadow_mmio_value = mmio_value | SPTE_MMIO_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; + shadow_mmio_access_mask = access_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +static bool is_mmio_spte(u64 spte) +{ + return (spte & shadow_mmio_mask) == shadow_mmio_value; +} + static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) { return sp->role.ad_disabled; } +static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) +{ + /* + * When using the EPT page-modification log, the GPAs in the log + * would come from L2 rather than L1. Therefore, we need to rely + * on write protection to record dirty pages. This also bypasses + * PML, since writes now result in a vmexit. + */ + return vcpu->arch.mmu == &vcpu->arch.guest_mmu; +} + static inline bool spte_ad_enabled(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); - return !(spte & shadow_acc_track_value); + MMU_WARN_ON(is_mmio_spte(spte)); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK; +} + +static inline bool spte_ad_need_write_protect(u64 spte) +{ + MMU_WARN_ON(is_mmio_spte(spte)); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK; +} + +static bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); } static inline u64 spte_shadow_accessed_mask(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return spte_ad_enabled(spte) ? shadow_accessed_mask : 0; } static inline u64 spte_shadow_dirty_mask(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return spte_ad_enabled(spte) ? shadow_dirty_mask : 0; } @@ -349,22 +418,24 @@ static inline bool is_access_track_spte(u64 spte) * requires a full MMU zap). The flag is instead explicitly queried when * checking for MMIO spte cache hits. */ -#define MMIO_SPTE_GEN_MASK GENMASK_ULL(18, 0) +#define MMIO_SPTE_GEN_MASK GENMASK_ULL(17, 0) #define MMIO_SPTE_GEN_LOW_START 3 #define MMIO_SPTE_GEN_LOW_END 11 #define MMIO_SPTE_GEN_LOW_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \ MMIO_SPTE_GEN_LOW_START) -#define MMIO_SPTE_GEN_HIGH_START 52 -#define MMIO_SPTE_GEN_HIGH_END 61 +#define MMIO_SPTE_GEN_HIGH_START PT64_SECOND_AVAIL_BITS_SHIFT +#define MMIO_SPTE_GEN_HIGH_END 62 #define MMIO_SPTE_GEN_HIGH_MASK GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \ MMIO_SPTE_GEN_HIGH_START) + static u64 generation_mmio_spte_mask(u64 gen) { u64 mask; WARN_ON(gen & ~MMIO_SPTE_GEN_MASK); + BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK); mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK; mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK; @@ -375,35 +446,37 @@ static u64 get_mmio_spte_generation(u64 spte) { u64 gen; - spte &= ~shadow_mmio_mask; - gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START; gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START; return gen; } -static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, - unsigned access) +static u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access) { + u64 gen = kvm_vcpu_memslots(vcpu)->generation & MMIO_SPTE_GEN_MASK; u64 mask = generation_mmio_spte_mask(gen); u64 gpa = gfn << PAGE_SHIFT; - access &= ACC_WRITE_MASK | ACC_USER_MASK; + access &= shadow_mmio_access_mask; mask |= shadow_mmio_value | access; mask |= gpa | shadow_nonpresent_or_rsvd_mask; mask |= (gpa & shadow_nonpresent_or_rsvd_mask) << shadow_nonpresent_or_rsvd_mask_len; - page_header(__pa(sptep))->mmio_cached = true; - - trace_mark_mmio_spte(sptep, gfn, access, gen); - mmu_spte_set(sptep, mask); + return mask; } -static bool is_mmio_spte(u64 spte) +static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, + unsigned int access) { - return (spte & shadow_mmio_mask) == shadow_mmio_value; + u64 mask = make_mmio_spte(vcpu, gfn, access); + unsigned int gen = get_mmio_spte_generation(mask); + + access = mask & ACC_ALL; + + trace_mark_mmio_spte(sptep, gfn, access, gen); + mmu_spte_set(sptep, mask); } static gfn_t get_mmio_spte_gfn(u64 spte) @@ -418,12 +491,11 @@ static gfn_t get_mmio_spte_gfn(u64 spte) static unsigned get_mmio_spte_access(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_SPTE_GEN_MASK) | shadow_mmio_mask; - return (spte & ~mask) & ~PAGE_MASK; + return spte & shadow_mmio_access_mask; } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - kvm_pfn_t pfn, unsigned access) + kvm_pfn_t pfn, unsigned int access) { if (unlikely(is_noslot_pfn(pfn))) { mark_mmio_spte(vcpu, sptep, gfn, access); @@ -461,7 +533,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, { BUG_ON(!dirty_mask != !accessed_mask); BUG_ON(!accessed_mask && !acc_track_mask); - BUG_ON(acc_track_mask & shadow_acc_track_value); + BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK); shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; @@ -477,16 +549,20 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); static u8 kvm_get_shadow_phys_bits(void) { /* - * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected - * in CPU detection code, but MKTME treats those reduced bits as - * 'keyID' thus they are not reserved bits. Therefore for MKTME - * we should still return physical address bits reported by CPUID. + * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected + * in CPU detection code, but the processor treats those reduced bits as + * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at + * the physical address bits reported by CPUID. */ - if (!boot_cpu_has(X86_FEATURE_TME) || - WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008)) - return boot_cpu_data.x86_phys_bits; + if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008)) + return cpuid_eax(0x80000008) & 0xff; - return cpuid_eax(0x80000008) & 0xff; + /* + * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with + * custom CPUID. Proceed with whatever the kernel found since these features + * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008). + */ + return boot_cpu_data.x86_phys_bits; } static void kvm_mmu_reset_all_pte_masks(void) @@ -1164,6 +1240,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); } +static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + if (sp->lpage_disallowed) + return; + + ++kvm->stat.nx_lpage_splits; + list_add_tail(&sp->lpage_disallowed_link, + &kvm->arch.lpage_disallowed_mmu_pages); + sp->lpage_disallowed = true; +} + static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; @@ -1181,54 +1268,11 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } -static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, - struct kvm_memory_slot *slot) +static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) { - struct kvm_lpage_info *linfo; - - if (slot) { - linfo = lpage_info_slot(gfn, slot, level); - return !!linfo->disallow_lpage; - } - - return true; -} - -static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn, - int level) -{ - struct kvm_memory_slot *slot; - - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - return __mmu_gfn_lpage_is_disallowed(gfn, level, slot); -} - -static int host_mapping_level(struct kvm *kvm, gfn_t gfn) -{ - unsigned long page_size; - int i, ret = 0; - - page_size = kvm_host_page_size(kvm, gfn); - - for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - if (page_size >= KVM_HPAGE_SIZE(i)) - ret = i; - else - break; - } - - return ret; -} - -static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot, - bool no_dirty_log) -{ - if (!slot || slot->flags & KVM_MEMSLOT_INVALID) - return false; - if (no_dirty_log && slot->dirty_bitmap) - return false; - - return true; + --kvm->stat.nx_lpage_splits; + sp->lpage_disallowed = false; + list_del(&sp->lpage_disallowed_link); } static struct kvm_memory_slot * @@ -1238,40 +1282,14 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_memory_slot *slot; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - if (!memslot_valid_for_gpte(slot, no_dirty_log)) - slot = NULL; + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return NULL; + if (no_dirty_log && slot->dirty_bitmap) + return NULL; return slot; } -static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, - bool *force_pt_level) -{ - int host_level, level, max_level; - struct kvm_memory_slot *slot; - - if (unlikely(*force_pt_level)) - return PT_PAGE_TABLE_LEVEL; - - slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn); - *force_pt_level = !memslot_valid_for_gpte(slot, true); - if (unlikely(*force_pt_level)) - return PT_PAGE_TABLE_LEVEL; - - host_level = host_mapping_level(vcpu->kvm, large_gfn); - - if (host_level == PT_PAGE_TABLE_LEVEL) - return host_level; - - max_level = min(kvm_x86_ops->get_lpage_level(), host_level); - - for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level) - if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot)) - break; - - return level - 1; -} - /* * About rmap_head encoding: * @@ -1331,7 +1349,7 @@ pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, if (j != 0) return; if (!prev_desc && !desc->more) - rmap_head->val = (unsigned long)desc->sptes[0]; + rmap_head->val = 0; else if (prev_desc) prev_desc->more = desc->more; @@ -1446,7 +1464,7 @@ struct rmap_iterator { /* * Iteration must be started by this function. This should also be used after * removing/dropping sptes from the rmap link because in such cases the - * information in the itererator may not be valid. + * information in the iterator may not be valid. * * Returns sptep if found, NULL otherwise. */ @@ -1589,16 +1607,16 @@ static bool spte_clear_dirty(u64 *sptep) rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep); + MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; - return mmu_spte_update(sptep, spte); } -static bool wrprot_ad_disabled_spte(u64 *sptep) +static bool spte_wrprot_for_clear_dirty(u64 *sptep) { bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, (unsigned long *)sptep); - if (was_writable) + if (was_writable && !spte_ad_enabled(*sptep)) kvm_set_pfn_dirty(spte_to_pfn(*sptep)); return was_writable; @@ -1617,10 +1635,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - if (spte_ad_enabled(*sptep)) - flush |= spte_clear_dirty(sptep); + if (spte_ad_need_write_protect(*sptep)) + flush |= spte_wrprot_for_clear_dirty(sptep); else - flush |= wrprot_ad_disabled_spte(sptep); + flush |= spte_clear_dirty(sptep); return flush; } @@ -1631,6 +1649,11 @@ static bool spte_set_dirty(u64 *sptep) rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep); + /* + * Similar to the !kvm_x86_ops->slot_disable_log_dirty case, + * do not bother adding back write access to pages marked + * SPTE_AD_WRPROT_ONLY_MASK. + */ spte |= shadow_dirty_mask; return mmu_spte_update(sptep, spte); @@ -2095,6 +2118,13 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct if (!direct) sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); + + /* + * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages() + * depends on valid pages being added to the head of the list. See + * comments in kvm_zap_obsolete_pages(). + */ + sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); kvm_mod_used_mmu_pages(vcpu->kvm, +1); return sp; @@ -2244,7 +2274,7 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, #define for_each_valid_sp(_kvm, _sp, _gfn) \ hlist_for_each_entry(_sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ - if ((_sp)->role.invalid) { \ + if (is_obsolete_sp((_kvm), (_sp))) { \ } else #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \ @@ -2301,6 +2331,12 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } static void mmu_audit_disable(void) { } #endif +static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + return sp->role.invalid || + unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); +} + static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { @@ -2450,7 +2486,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gva_t gaddr, unsigned level, int direct, - unsigned access) + unsigned int access) { union kvm_mmu_page_role role; unsigned quadrant; @@ -2609,7 +2645,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, shadow_user_mask | shadow_x_mask | shadow_me_mask; if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; else spte |= shadow_accessed_mask; @@ -2739,10 +2775,18 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, } else { list_move(&sp->link, &kvm->arch.active_mmu_pages); - if (!sp->role.invalid) + /* + * Obsolete pages cannot be used on any vCPUs, see the comment + * in kvm_mmu_zap_all_fast(). Note, is_obsolete_sp() also + * treats invalid shadow pages as being obsolete. + */ + if (!is_obsolete_sp(kvm, sp)) kvm_reload_remote_mmus(kvm); } + if (sp->lpage_disallowed) + unaccount_huge_nx_page(kvm, sp); + sp->role.invalid = 1; return list_unstable; } @@ -2794,6 +2838,26 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, return kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); } +static int make_mmu_pages_available(struct kvm_vcpu *vcpu) +{ + LIST_HEAD(invalid_list); + + if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES)) + return 0; + + while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) { + if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list)) + break; + + ++vcpu->kvm->stat.mmu_recycled; + } + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + + if (!kvm_mmu_available_pages(vcpu->kvm)) + return -ENOSPC; + return 0; +} + /* * Changing the number of mmu pages allocated to the vm * Note: if goal_nr_mmu_pages is too small, you will get dead lock @@ -2937,7 +3001,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) #define SET_SPTE_NEED_REMOTE_TLB_FLUSH BIT(1) static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned pte_access, int level, + unsigned int pte_access, int level, gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { @@ -2950,7 +3014,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, sp = page_header(__pa(sptep)); if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; + else if (kvm_vcpu_ad_need_write_protect(vcpu)) + spte |= SPTE_AD_WRPROT_ONLY_MASK; /* * For the EPT case, shadow_present_mask is 0 if hardware @@ -2962,6 +3028,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!speculative) spte |= spte_shadow_accessed_mask(spte); + if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) && + is_nx_huge_page_enabled()) { + pte_access &= ~ACC_EXEC_MASK; + } + if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; else @@ -2987,17 +3058,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= (u64)pfn << PAGE_SHIFT; if (pte_access & ACC_WRITE_MASK) { - - /* - * Other vcpu creates new sp in the window between - * mapping_level() and acquiring mmu-lock. We can - * allow guest to retry the access, the mapping can - * be fixed if guest refault. - */ - if (level > PT_PAGE_TABLE_LEVEL && - mmu_gfn_lpage_is_disallowed(vcpu, gfn, level)) - goto done; - spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; /* @@ -3029,13 +3089,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, set_pte: if (mmu_spte_update(sptep, spte)) ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; -done: return ret; } -static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, - int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, - bool speculative, bool host_writable) +static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, + unsigned int pte_access, int write_fault, int level, + gfn_t gfn, kvm_pfn_t pfn, bool speculative, + bool host_writable) { int was_rmapped = 0; int rmap_count; @@ -3117,7 +3177,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, { struct page *pages[PTE_PREFETCH_NUM]; struct kvm_memory_slot *slot; - unsigned access = sp->role.access; + unsigned int access = sp->role.access; int i, ret; gfn_t gfn; @@ -3182,21 +3242,129 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } +static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, + kvm_pfn_t pfn, struct kvm_memory_slot *slot) +{ + unsigned long hva; + pte_t *pte; + int level; + + BUILD_BUG_ON(PT_PAGE_TABLE_LEVEL != (int)PG_LEVEL_4K || + PT_DIRECTORY_LEVEL != (int)PG_LEVEL_2M || + PT_PDPE_LEVEL != (int)PG_LEVEL_1G); + + if (!PageCompound(pfn_to_page(pfn)) && !kvm_is_zone_device_pfn(pfn)) + return PT_PAGE_TABLE_LEVEL; + + /* + * Note, using the already-retrieved memslot and __gfn_to_hva_memslot() + * is not solely for performance, it's also necessary to avoid the + * "writable" check in __gfn_to_hva_many(), which will always fail on + * read-only memslots due to gfn_to_hva() assuming writes. Earlier + * page fault steps have already verified the guest isn't writing a + * read-only memslot. + */ + hva = __gfn_to_hva_memslot(slot, gfn); + + pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level); + if (unlikely(!pte)) + return PT_PAGE_TABLE_LEVEL; + + return level; +} + +static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, + int max_level, kvm_pfn_t *pfnp) +{ + struct kvm_memory_slot *slot; + struct kvm_lpage_info *linfo; + kvm_pfn_t pfn = *pfnp; + kvm_pfn_t mask; + int level; + + if (unlikely(max_level == PT_PAGE_TABLE_LEVEL)) + return PT_PAGE_TABLE_LEVEL; + + if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn)) + return PT_PAGE_TABLE_LEVEL; + + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, true); + if (!slot) + return PT_PAGE_TABLE_LEVEL; + + max_level = min(max_level, kvm_x86_ops->get_lpage_level()); + for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) { + linfo = lpage_info_slot(gfn, slot, max_level); + if (!linfo->disallow_lpage) + break; + } + + if (max_level == PT_PAGE_TABLE_LEVEL) + return PT_PAGE_TABLE_LEVEL; + + level = host_pfn_mapping_level(vcpu, gfn, pfn, slot); + if (level == PT_PAGE_TABLE_LEVEL) + return level; + + level = min(level, max_level); + + /* + * mmu_notifier_retry() was successful and mmu_lock is held, so + * the pmd can't be split from under us. + */ + mask = KVM_PAGES_PER_HPAGE(level) - 1; + VM_BUG_ON((gfn & mask) != (pfn & mask)); + *pfnp = pfn & ~mask; + + return level; +} + +static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) +{ + int level = *levelp; + u64 spte = *it.sptep; + + if (it.level == level && level > PT_PAGE_TABLE_LEVEL && + is_nx_huge_page_enabled() && + is_shadow_present_pte(spte) && + !is_large_pte(spte)) { + /* + * A small SPTE exists for this pfn, but FNAME(fetch) + * and __direct_map would like to create a large PTE + * instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of + * the address. + */ + u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1); + *pfnp |= gfn & page_mask; + (*levelp)--; + } +} + static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, - int map_writable, int level, kvm_pfn_t pfn, - bool prefault) + int map_writable, int max_level, kvm_pfn_t pfn, + bool prefault, bool account_disallowed_nx_lpage) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; - int ret; + int level, ret; gfn_t gfn = gpa >> PAGE_SHIFT; gfn_t base_gfn = gfn; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) + if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) return RET_PF_RETRY; + level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn); + trace_kvm_mmu_spte_requested(gpa, level, pfn); for_each_shadow_entry(vcpu, gpa, it) { + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &level); + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == level) break; @@ -3207,6 +3375,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, it.level - 1, true, ACC_ALL); link_shadow_page(vcpu, it.sptep, sp); + if (account_disallowed_nx_lpage) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -3241,47 +3411,9 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) return -EFAULT; } -static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t gfn, kvm_pfn_t *pfnp, - int *levelp) -{ - kvm_pfn_t pfn = *pfnp; - int level = *levelp; - - /* - * Check if it's a transparent hugepage. If this would be an - * hugetlbfs page, level wouldn't be set to - * PT_PAGE_TABLE_LEVEL and there would be no adjustment done - * here. - */ - if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && - level == PT_PAGE_TABLE_LEVEL && - PageTransCompoundMap(pfn_to_page(pfn)) && - !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { - unsigned long mask; - /* - * mmu_notifier_retry was successful and we hold the - * mmu_lock here, so the pmd can't become splitting - * from under us, and in turn - * __split_huge_page_refcount() can't run from under - * us and we can safely transfer the refcount from - * PG_tail to PG_head as we switch the pfn to tail to - * head. - */ - *levelp = level = PT_DIRECTORY_LEVEL; - mask = KVM_PAGES_PER_HPAGE(level) - 1; - VM_BUG_ON((gfn & mask) != (pfn & mask)); - if (pfn & mask) { - kvm_release_pfn_clean(pfn); - pfn &= ~mask; - kvm_get_pfn(pfn); - *pfnp = pfn; - } - } -} - static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - kvm_pfn_t pfn, unsigned access, int *ret_val) + kvm_pfn_t pfn, unsigned int access, + int *ret_val) { /* The pfn is invalid, report the error! */ if (unlikely(is_error_pfn(pfn))) { @@ -3290,7 +3422,8 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, } if (unlikely(is_noslot_pfn(pfn))) - vcpu_cache_mmio_info(vcpu, gva, gfn, access); + vcpu_cache_mmio_info(vcpu, gva, gfn, + access & shadow_mmio_access_mask); return false; } @@ -3384,7 +3517,7 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte) * - true: let the vcpu to access on the same address again. * - false: let the real page fault path to fix it. */ -static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, +static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code) { struct kvm_shadow_walk_iterator iterator; @@ -3393,9 +3526,6 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, u64 spte = 0ull; uint retry_count = 0; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - return false; - if (!page_fault_can_be_fast(error_code)) return false; @@ -3404,9 +3534,8 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, do { u64 new_spte; - for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) - if (!is_shadow_present_pte(spte) || - iterator.level < level) + for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte) + if (!is_shadow_present_pte(spte)) break; sp = page_header(__pa(iterator.sptep)); @@ -3482,67 +3611,13 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, } while (true); - trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, + trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep, spte, fault_handled); walk_shadow_page_lockless_end(vcpu); return fault_handled; } -static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); -static int make_mmu_pages_available(struct kvm_vcpu *vcpu); - -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, - gfn_t gfn, bool prefault) -{ - int r; - int level; - bool force_pt_level = false; - kvm_pfn_t pfn; - unsigned long mmu_seq; - bool map_writable, write = error_code & PFERR_WRITE_MASK; - - level = mapping_level(vcpu, gfn, &force_pt_level); - if (likely(!force_pt_level)) { - /* - * This path builds a PAE pagetable - so we can map - * 2mb pages at maximum. Therefore check if the level - * is larger than that. - */ - if (level > PT_DIRECTORY_LEVEL) - level = PT_DIRECTORY_LEVEL; - - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); - } - - if (fast_page_fault(vcpu, v, level, error_code)) - return RET_PF_RETRY; - - mmu_seq = vcpu->kvm->mmu_notifier_seq; - smp_rmb(); - - if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable)) - return RET_PF_RETRY; - - if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) - return r; - - r = RET_PF_RETRY; - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) - goto out_unlock; - if (make_mmu_pages_available(vcpu) < 0) - goto out_unlock; - if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault); -out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(pfn); - return r; -} - static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, struct list_head *invalid_list) { @@ -3833,7 +3908,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { if (exception) @@ -3841,7 +3916,7 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, return vaddr; } -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -3853,20 +3928,14 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, static bool __is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level) { - int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f; - - return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) | - ((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0); -} + int bit7 = (pte >> 7) & 1; -static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) -{ - return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level); + return pte & rsvd_check->rsvd_bits_mask[bit7][level-1]; } -static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level) +static bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check, u64 pte) { - return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level); + return rsvd_check->bad_mt_xwr & BIT_ULL(pte & 0x3f); } static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) @@ -3890,11 +3959,11 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { struct kvm_shadow_walk_iterator iterator; u64 sptes[PT64_ROOT_MAX_LEVEL], spte = 0ull; + struct rsvd_bits_validate *rsvd_check; int root, leaf; bool reserved = false; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - goto exit; + rsvd_check = &vcpu->arch.mmu->shadow_zero_check; walk_shadow_page_lockless_begin(vcpu); @@ -3910,8 +3979,13 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) if (!is_shadow_present_pte(spte)) break; - reserved |= is_shadow_zero_bits_set(vcpu->arch.mmu, spte, - iterator.level); + /* + * Use a bitwise-OR instead of a logical-OR to aggregate the + * reserved bit and EPT's invalid memtype/XWR checks to avoid + * adding a Jcc in the loop. + */ + reserved |= __is_bad_mt_xwr(rsvd_check, spte) | + __is_rsvd_bits_set(rsvd_check, spte, iterator.level); } walk_shadow_page_lockless_end(vcpu); @@ -3925,7 +3999,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) root--; } } -exit: + *sptep = spte; return reserved; } @@ -3944,7 +4018,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) if (is_mmio_spte(spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); - unsigned access = get_mmio_spte_access(spte); + unsigned int access = get_mmio_spte_access(spte); if (!check_mmio_spte(vcpu, spte)) return RET_PF_INVALID; @@ -3989,9 +4063,6 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) struct kvm_shadow_walk_iterator iterator; u64 spte; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - return; - walk_shadow_page_lockless_begin(vcpu); for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { clear_sp_write_flooding_count(iterator.sptep); @@ -4001,29 +4072,8 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } -static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, - u32 error_code, bool prefault) -{ - gfn_t gfn = gva >> PAGE_SHIFT; - int r; - - pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); - - if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return RET_PF_EMULATE; - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); - - - return nonpaging_map(vcpu, gva & PAGE_MASK, - error_code, gfn, prefault); -} - -static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) +static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + gfn_t gfn) { struct kvm_arch_async_pf arch; @@ -4032,11 +4082,13 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); + return kvm_setup_async_pf(vcpu, cr2_or_gpa, + kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, + bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -4056,12 +4108,12 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; /* *pfn has correct page already */ if (!prefault && kvm_can_do_async_pf(vcpu)) { - trace_kvm_try_async_get_page(gva, gfn); + trace_kvm_try_async_get_page(cr2_or_gpa, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { - trace_kvm_async_pf_doublefault(gva, gfn); + trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return true; - } else if (kvm_arch_setup_async_pf(vcpu, gva, gfn)) + } else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn)) return true; } @@ -4069,11 +4121,77 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; } +static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault, int max_level, bool is_tdp) +{ + bool write = error_code & PFERR_WRITE_MASK; + bool exec = error_code & PFERR_FETCH_MASK; + bool lpage_disallowed = exec && is_nx_huge_page_enabled(); + bool map_writable; + + gfn_t gfn = gpa >> PAGE_SHIFT; + unsigned long mmu_seq; + kvm_pfn_t pfn; + int r; + + if (page_fault_handle_page_track(vcpu, error_code, gfn)) + return RET_PF_EMULATE; + + r = mmu_topup_memory_caches(vcpu); + if (r) + return r; + + if (lpage_disallowed) + max_level = PT_PAGE_TABLE_LEVEL; + + if (fast_page_fault(vcpu, gpa, error_code)) + return RET_PF_RETRY; + + mmu_seq = vcpu->kvm->mmu_notifier_seq; + smp_rmb(); + + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) + return RET_PF_RETRY; + + if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r)) + return r; + + r = RET_PF_RETRY; + spin_lock(&vcpu->kvm->mmu_lock); + if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) + goto out_unlock; + if (make_mmu_pages_available(vcpu) < 0) + goto out_unlock; + r = __direct_map(vcpu, gpa, write, map_writable, max_level, pfn, + prefault, is_tdp && lpage_disallowed); + +out_unlock: + spin_unlock(&vcpu->kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + return r; +} + +static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, + u32 error_code, bool prefault) +{ + pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code); + + /* This path builds a PAE pagetable, we can map 2mb pages at maximum. */ + return direct_page_fault(vcpu, gpa & PAGE_MASK, error_code, prefault, + PT_DIRECTORY_LEVEL, false); +} + int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len) { int r = 1; +#ifndef CONFIG_X86_64 + /* A 64-bit CR2 should be impossible on 32-bit KVM. */ + if (WARN_ON_ONCE(fault_address >> 32)) + return -EFAULT; +#endif + vcpu->arch.l1tf_flush_l1d = true; switch (vcpu->arch.apf.host_apf_reason) { default: @@ -4101,72 +4219,23 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); -static bool -check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) -{ - int page_num = KVM_PAGES_PER_HPAGE(level); - - gfn &= ~(page_num - 1); - - return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num); -} - -static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, - bool prefault) +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault) { - kvm_pfn_t pfn; - int r; - int level; - bool force_pt_level; - gfn_t gfn = gpa >> PAGE_SHIFT; - unsigned long mmu_seq; - int write = error_code & PFERR_WRITE_MASK; - bool map_writable; + int max_level; - MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); + for (max_level = PT_MAX_HUGEPAGE_LEVEL; + max_level > PT_PAGE_TABLE_LEVEL; + max_level--) { + int page_num = KVM_PAGES_PER_HPAGE(max_level); + gfn_t base = (gpa >> PAGE_SHIFT) & ~(page_num - 1); - if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return RET_PF_EMULATE; - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, - PT_DIRECTORY_LEVEL); - level = mapping_level(vcpu, gfn, &force_pt_level); - if (likely(!force_pt_level)) { - if (level > PT_DIRECTORY_LEVEL && - !check_hugepage_cache_consistency(vcpu, gfn, level)) - level = PT_DIRECTORY_LEVEL; - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num)) + break; } - if (fast_page_fault(vcpu, gpa, level, error_code)) - return RET_PF_RETRY; - - mmu_seq = vcpu->kvm->mmu_notifier_seq; - smp_rmb(); - - if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) - return RET_PF_RETRY; - - if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r)) - return r; - - r = RET_PF_RETRY; - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) - goto out_unlock; - if (make_mmu_pages_available(vcpu) < 0) - goto out_unlock; - if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault); -out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(pfn); - return r; + return direct_page_fault(vcpu, gpa, error_code, prefault, + max_level, true); } static void nonpaging_init_context(struct kvm_vcpu *vcpu, @@ -4233,10 +4302,17 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, return false; if (cached_root_available(vcpu, new_cr3, new_role)) { + /* + * It is possible that the cached previous root page is + * obsolete because of a change in the MMU generation + * number. However, changing the generation number is + * accompanied by KVM_REQ_MMU_RELOAD, which will free + * the root set here and allocate a new one. + */ kvm_make_request(KVM_REQ_LOAD_CR3, vcpu); if (!skip_tlb_flush) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - kvm_x86_ops->tlb_flush(vcpu, true); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } /* @@ -4286,7 +4362,7 @@ static void inject_page_fault(struct kvm_vcpu *vcpu, } static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - unsigned access, int *nr_present) + unsigned int access, int *nr_present) { if (unlikely(is_mmio_spte(*sptep))) { if (gfn != get_mmio_spte_gfn(*sptep)) { @@ -4849,7 +4925,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) return; context->mmu_role.as_u64 = new_role.as_u64; - context->page_fault = tdp_page_fault; + context->page_fault = kvm_tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; @@ -5337,50 +5413,31 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); -static int make_mmu_pages_available(struct kvm_vcpu *vcpu) -{ - LIST_HEAD(invalid_list); - - if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES)) - return 0; - - while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) { - if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list)) - break; - - ++vcpu->kvm->stat.mmu_recycled; - } - kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); - - if (!kvm_mmu_available_pages(vcpu->kvm)) - return -ENOSPC; - return 0; -} - -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { int r, emulation_type = 0; - enum emulation_result er; bool direct = vcpu->arch.mmu->direct_map; + if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) + return RET_PF_RETRY; + /* With shadow page tables, fault_address contains a GVA or nGPA. */ if (vcpu->arch.mmu->direct_map) { vcpu->arch.gpa_available = true; - vcpu->arch.gpa_val = cr2; + vcpu->arch.gpa_val = cr2_or_gpa; } r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, cr2, direct); + r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { - r = vcpu->arch.mmu->page_fault(vcpu, cr2, - lower_32_bits(error_code), - false); + r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, + lower_32_bits(error_code), false); WARN_ON(r == RET_PF_INVALID); } @@ -5398,7 +5455,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, */ if (vcpu->arch.mmu->direct_map && (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2)); + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); return 1; } @@ -5413,7 +5470,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, * explicitly shadowing L1's page tables, i.e. unprotecting something * for L1 isn't going to magically fix whatever issue cause L2 to fail. */ - if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* @@ -5428,19 +5485,8 @@ emulate: return 1; } - er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); - - switch (er) { - case EMULATE_DONE: - return 1; - case EMULATE_USER_EXIT: - ++vcpu->stat.mmio_exits; - /* fall through */ - case EMULATE_FAIL: - return 0; - default: - BUG(); - } + return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, + insn_len); } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); @@ -5592,13 +5638,13 @@ slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_PAGE_TABLE_LEVEL, lock_flush_tlb); } -static void free_mmu_pages(struct kvm_vcpu *vcpu) +static void free_mmu_pages(struct kvm_mmu *mmu) { - free_page((unsigned long)vcpu->arch.mmu->pae_root); - free_page((unsigned long)vcpu->arch.mmu->lm_root); + free_page((unsigned long)mmu->pae_root); + free_page((unsigned long)mmu->lm_root); } -static int alloc_mmu_pages(struct kvm_vcpu *vcpu) +static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { struct page *page; int i; @@ -5619,9 +5665,9 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) if (!page) return -ENOMEM; - vcpu->arch.mmu->pae_root = page_address(page); + mmu->pae_root = page_address(page); for (i = 0; i < 4; ++i) - vcpu->arch.mmu->pae_root[i] = INVALID_PAGE; + mmu->pae_root[i] = INVALID_PAGE; return 0; } @@ -5629,6 +5675,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) int kvm_mmu_create(struct kvm_vcpu *vcpu) { uint i; + int ret; vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; @@ -5646,47 +5693,124 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; - return alloc_mmu_pages(vcpu); -} -static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, - struct kvm_page_track_notifier_node *node) -{ - struct kvm_mmu_page *sp; - LIST_HEAD(invalid_list); - unsigned long i; - bool flush; - gfn_t gfn; + ret = alloc_mmu_pages(vcpu, &vcpu->arch.guest_mmu); + if (ret) + return ret; - spin_lock(&kvm->mmu_lock); + ret = alloc_mmu_pages(vcpu, &vcpu->arch.root_mmu); + if (ret) + goto fail_allocate_root; - if (list_empty(&kvm->arch.active_mmu_pages)) - goto out_unlock; + return ret; + fail_allocate_root: + free_mmu_pages(&vcpu->arch.guest_mmu); + return ret; +} - flush = slot_handle_all_level(kvm, slot, kvm_zap_rmapp, false); +#define BATCH_ZAP_PAGES 10 +static void kvm_zap_obsolete_pages(struct kvm *kvm) +{ + struct kvm_mmu_page *sp, *node; + int nr_zapped, batch = 0; - for (i = 0; i < slot->npages; i++) { - gfn = slot->base_gfn + i; +restart: + list_for_each_entry_safe_reverse(sp, node, + &kvm->arch.active_mmu_pages, link) { + /* + * No obsolete valid page exists before a newly created page + * since active_mmu_pages is a FIFO list. + */ + if (!is_obsolete_sp(kvm, sp)) + break; - for_each_valid_sp(kvm, sp, gfn) { - if (sp->gfn != gfn) - continue; + /* + * Skip invalid pages with a non-zero root count, zapping pages + * with a non-zero root count will never succeed, i.e. the page + * will get thrown back on active_mmu_pages and we'll get stuck + * in an infinite loop. + */ + if (sp->role.invalid && sp->root_count) + continue; - kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + /* + * No need to flush the TLB since we're only zapping shadow + * pages with an obsolete generation number and all vCPUS have + * loaded a new root, i.e. the shadow pages being zapped cannot + * be in active use by the guest. + */ + if (batch >= BATCH_ZAP_PAGES && + cond_resched_lock(&kvm->mmu_lock)) { + batch = 0; + goto restart; } - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); - flush = false; - cond_resched_lock(&kvm->mmu_lock); + + if (__kvm_mmu_prepare_zap_page(kvm, sp, + &kvm->arch.zapped_obsolete_pages, &nr_zapped)) { + batch += nr_zapped; + goto restart; } } - kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); -out_unlock: + /* + * Trigger a remote TLB flush before freeing the page tables to ensure + * KVM is not in the middle of a lockless shadow page table walk, which + * may reference the pages. + */ + kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages); +} + +/* + * Fast invalidate all shadow pages and use lock-break technique + * to zap obsolete pages. + * + * It's required when memslot is being deleted or VM is being + * destroyed, in these cases, we should ensure that KVM MMU does + * not use any resource of the being-deleted slot or all slots + * after calling the function. + */ +static void kvm_mmu_zap_all_fast(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->slots_lock); + + spin_lock(&kvm->mmu_lock); + trace_kvm_mmu_zap_all_fast(kvm); + + /* + * Toggle mmu_valid_gen between '0' and '1'. Because slots_lock is + * held for the entire duration of zapping obsolete pages, it's + * impossible for there to be multiple invalid generations associated + * with *valid* shadow pages at any given time, i.e. there is exactly + * one valid generation and (at most) one invalid generation. + */ + kvm->arch.mmu_valid_gen = kvm->arch.mmu_valid_gen ? 0 : 1; + + /* + * Notify all vcpus to reload its shadow page table and flush TLB. + * Then all vcpus will switch to new shadow page table with the new + * mmu_valid_gen. + * + * Note: we need to do this under the protection of mmu_lock, + * otherwise, vcpu would purge shadow page but miss tlb flush. + */ + kvm_reload_remote_mmus(kvm); + + kvm_zap_obsolete_pages(kvm); spin_unlock(&kvm->mmu_lock); } +static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) +{ + return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); +} + +static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, + struct kvm_page_track_notifier_node *node) +{ + kvm_mmu_zap_all_fast(kvm); +} + void kvm_mmu_init_vm(struct kvm *kvm) { struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; @@ -5789,9 +5913,9 @@ restart: * the guest, and the guest page table is using 4K page size * mapping if the indirect sp has level = 1. */ - if (sp->role.direct && - !kvm_is_reserved_pfn(pfn) && - PageTransCompoundMap(pfn_to_page(pfn))) { + if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && + (kvm_is_zone_device_pfn(pfn) || + PageCompound(pfn_to_page(pfn)))) { pte_list_remove(rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) @@ -5877,7 +6001,7 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm, } EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty); -static void __kvm_mmu_zap_all(struct kvm *kvm, bool mmio_only) +void kvm_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; LIST_HEAD(invalid_list); @@ -5886,14 +6010,10 @@ static void __kvm_mmu_zap_all(struct kvm *kvm, bool mmio_only) spin_lock(&kvm->mmu_lock); restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { - if (mmio_only && !sp->mmio_cached) - continue; if (sp->role.invalid && sp->root_count) continue; - if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) { - WARN_ON_ONCE(mmio_only); + if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) goto restart; - } if (cond_resched_lock(&kvm->mmu_lock)) goto restart; } @@ -5902,11 +6022,6 @@ restart: spin_unlock(&kvm->mmu_lock); } -void kvm_mmu_zap_all(struct kvm *kvm) -{ - return __kvm_mmu_zap_all(kvm, false); -} - void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) { WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); @@ -5928,7 +6043,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) */ if (unlikely(gen == 0)) { kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n"); - __kvm_mmu_zap_all(kvm, true); + kvm_mmu_zap_all_fast(kvm); } } @@ -5959,16 +6074,24 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) * want to shrink a VM that only started to populate its MMU * anyway. */ - if (!kvm->arch.n_used_mmu_pages) + if (!kvm->arch.n_used_mmu_pages && + !kvm_has_zapped_obsolete_pages(kvm)) continue; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); + if (kvm_has_zapped_obsolete_pages(kvm)) { + kvm_mmu_commit_zap_page(kvm, + &kvm->arch.zapped_obsolete_pages); + goto unlock; + } + if (prepare_zap_oldest_mmu_page(kvm, &invalid_list)) freed++; kvm_mmu_commit_zap_page(kvm, &invalid_list); +unlock: spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); @@ -6025,16 +6148,65 @@ static void kvm_set_mmio_spte_mask(void) * If reserved bit is not supported, clear the present bit to disable * mmio page fault. */ - if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52) + if (shadow_phys_bits == 52) mask &= ~1ull; - kvm_mmu_set_mmio_spte_mask(mask, mask); + kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); +} + +static bool get_nx_auto_mode(void) +{ + /* Return true when CPU has the bug, and mitigations are ON */ + return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off(); +} + +static void __set_nx_huge_pages(bool val) +{ + nx_huge_pages = itlb_multihit_kvm_mitigation = val; +} + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) +{ + bool old_val = nx_huge_pages; + bool new_val; + + /* In "auto" mode deploy workaround only if CPU has the bug. */ + if (sysfs_streq(val, "off")) + new_val = 0; + else if (sysfs_streq(val, "force")) + new_val = 1; + else if (sysfs_streq(val, "auto")) + new_val = get_nx_auto_mode(); + else if (strtobool(val, &new_val) < 0) + return -EINVAL; + + __set_nx_huge_pages(new_val); + + if (new_val != old_val) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + mutex_lock(&kvm->slots_lock); + kvm_mmu_zap_all_fast(kvm); + mutex_unlock(&kvm->slots_lock); + + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + } + mutex_unlock(&kvm_lock); + } + + return 0; } int kvm_mmu_module_init(void) { int ret = -ENOMEM; + if (nx_huge_pages == -1) + __set_nx_huge_pages(get_nx_auto_mode()); + /* * MMU roles use union aliasing which is, generally speaking, an * undefined behavior. However, we supposedly know how compilers behave @@ -6102,7 +6274,8 @@ unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); - free_mmu_pages(vcpu); + free_mmu_pages(&vcpu->arch.root_mmu); + free_mmu_pages(&vcpu->arch.guest_mmu); mmu_free_memory_caches(vcpu); } @@ -6113,3 +6286,116 @@ void kvm_mmu_module_exit(void) unregister_shrinker(&mmu_shrinker); mmu_audit_disable(); } + +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp) +{ + unsigned int old_val; + int err; + + old_val = nx_huge_pages_recovery_ratio; + err = param_set_uint(val, kp); + if (err) + return err; + + if (READ_ONCE(nx_huge_pages) && + !old_val && nx_huge_pages_recovery_ratio) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + + mutex_unlock(&kvm_lock); + } + + return err; +} + +static void kvm_recover_nx_lpages(struct kvm *kvm) +{ + int rcu_idx; + struct kvm_mmu_page *sp; + unsigned int ratio; + LIST_HEAD(invalid_list); + ulong to_zap; + + rcu_idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) { + /* + * We use a separate list instead of just using active_mmu_pages + * because the number of lpage_disallowed pages is expected to + * be relatively small compared to the total. + */ + sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + struct kvm_mmu_page, + lpage_disallowed_link); + WARN_ON_ONCE(!sp->lpage_disallowed); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + WARN_ON_ONCE(sp->lpage_disallowed); + + if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + if (to_zap) + cond_resched_lock(&kvm->mmu_lock); + } + } + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, rcu_idx); +} + +static long get_nx_lpage_recovery_timeout(u64 start_time) +{ + return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio) + ? start_time + 60 * HZ - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; +} + +static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +{ + u64 start_time; + long remaining_time; + + while (true) { + start_time = get_jiffies_64(); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop() && remaining_time > 0) { + schedule_timeout(remaining_time); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + set_current_state(TASK_INTERRUPTIBLE); + } + + set_current_state(TASK_RUNNING); + + if (kthread_should_stop()) + return 0; + + kvm_recover_nx_lpages(kvm); + } +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + int err; + + err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + "kvm-nx-lpage-recovery", + &kvm->arch.nx_lpage_recovery_thread); + if (!err) + kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + + return err; +} + +void kvm_mmu_pre_destroy_vm(struct kvm *kvm) +{ + if (kvm->arch.nx_lpage_recovery_thread) + kthread_stop(kvm->arch.nx_lpage_recovery_thread); +} diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/mmu/page_track.c index 3521e2d176f2..3521e2d176f2 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 7d5cdb3af594..e4c8a4cbf407 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -33,7 +33,7 @@ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define PT_HAVE_ACCESSED_DIRTY(mmu) true #ifdef CONFIG_X86_64 - #define PT_MAX_FULL_LEVELS 4 + #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #define CMPXCHG cmpxchg #else #define CMPXCHG cmpxchg64 @@ -128,6 +128,21 @@ static inline int FNAME(is_present_gpte)(unsigned long pte) #endif } +static bool FNAME(is_bad_mt_xwr)(struct rsvd_bits_validate *rsvd_check, u64 gpte) +{ +#if PTTYPE != PTTYPE_EPT + return false; +#else + return __is_bad_mt_xwr(rsvd_check, gpte); +#endif +} + +static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level) +{ + return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) || + FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte); +} + static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, pt_element_t __user *ptep_user, unsigned index, pt_element_t orig_pte, pt_element_t new_pte) @@ -175,9 +190,6 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, u64 gpte) { - if (is_rsvd_bits_set(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) - goto no_present; - if (!FNAME(is_present_gpte)(gpte)) goto no_present; @@ -186,6 +198,9 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, !(gpte & PT_GUEST_ACCESSED_MASK)) goto no_present; + if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) + goto no_present; + return false; no_present: @@ -291,11 +306,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte) } /* - * Fetch a guest pte for a guest virtual address + * Fetch a guest pte for a guest virtual address, or for an L2's GPA. */ static int FNAME(walk_addr_generic)(struct guest_walker *walker, struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gva_t addr, u32 access) + gpa_t addr, u32 access) { int ret; pt_element_t pte; @@ -400,7 +415,7 @@ retry_walk: if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; - if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) { + if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, walker->level))) { errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK; goto error; } @@ -496,7 +511,7 @@ error: } static int FNAME(walk_addr)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, u32 access) + struct kvm_vcpu *vcpu, gpa_t addr, u32 access) { return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr, access); @@ -611,16 +626,17 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, * If the guest tries to write a write-protected page, we need to * emulate this operation, return 1 to indicate this case. */ -static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, +static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, struct guest_walker *gw, - int write_fault, int hlevel, - kvm_pfn_t pfn, bool map_writable, bool prefault) + int write_fault, int max_level, + kvm_pfn_t pfn, bool map_writable, bool prefault, + bool lpage_disallowed) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; - int top_level, ret; - gfn_t base_gfn; + int top_level, hlevel, ret; + gfn_t base_gfn = gw->gfn; direct_access = gw->pte_access; @@ -636,7 +652,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (FNAME(gpte_changed)(vcpu, gw, top_level)) goto out_gpte_changed; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) + if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) goto out_gpte_changed; for (shadow_walk_init(&it, vcpu, addr); @@ -665,12 +681,19 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - base_gfn = gw->gfn; + hlevel = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn); trace_kvm_mmu_spte_requested(addr, gw->level, pfn); for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); + + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gw->gfn, &pfn, &hlevel); + base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == hlevel) break; @@ -683,6 +706,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, sp = kvm_mmu_get_page(vcpu, base_gfn, addr, it.level - 1, true, direct_access); link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -750,7 +775,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, * Returns: 1 if we need to emulate the instruction, 0 otherwise, or * a negative value on error. */ -static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, +static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, bool prefault) { int write_fault = error_code & PFERR_WRITE_MASK; @@ -758,10 +783,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, struct guest_walker walker; int r; kvm_pfn_t pfn; - int level = PT_PAGE_TABLE_LEVEL; - bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + int max_level; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -801,14 +827,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable); - if (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) { - level = mapping_level(vcpu, walker.gfn, &force_pt_level); - if (likely(!force_pt_level)) { - level = min(walker.level, level); - walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1); - } - } else - force_pt_level = true; + if (lpage_disallowed || is_self_change_mapping) + max_level = PT_PAGE_TABLE_LEVEL; + else + max_level = walker.level; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -848,10 +870,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; - if (!force_pt_level) - transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); - r = FNAME(fetch)(vcpu, addr, &walker, write_fault, - level, pfn, map_writable, prefault); + r = FNAME(fetch)(vcpu, addr, &walker, write_fault, max_level, pfn, + map_writable, prefault, lpage_disallowed); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); out_unlock: @@ -928,18 +948,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) spin_unlock(&vcpu->kvm->mmu_lock); } -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, +/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access, struct x86_exception *exception) { struct guest_walker walker; gpa_t gpa = UNMAPPED_GVA; int r; - r = FNAME(walk_addr)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr)(&walker, vcpu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; @@ -947,7 +968,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, } #if PTTYPE != PTTYPE_EPT -static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, +/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */ +static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -955,6 +977,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, gpa_t gpa = UNMAPPED_GVA; int r; +#ifndef CONFIG_X86_64 + /* A 64-bit GVA should be impossible on 32-bit KVM. */ + WARN_ON_ONCE(vaddr >> 32); +#endif + r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); if (r) { diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index d8001b4bca05..3c6522b84ff1 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -8,16 +8,18 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvmmmu -#define KVM_MMU_PAGE_FIELDS \ - __field(__u64, gfn) \ - __field(__u32, role) \ - __field(__u32, root_count) \ +#define KVM_MMU_PAGE_FIELDS \ + __field(__u8, mmu_valid_gen) \ + __field(__u64, gfn) \ + __field(__u32, role) \ + __field(__u32, root_count) \ __field(bool, unsync) -#define KVM_MMU_PAGE_ASSIGN(sp) \ - __entry->gfn = sp->gfn; \ - __entry->role = sp->role.word; \ - __entry->root_count = sp->root_count; \ +#define KVM_MMU_PAGE_ASSIGN(sp) \ + __entry->mmu_valid_gen = sp->mmu_valid_gen; \ + __entry->gfn = sp->gfn; \ + __entry->role = sp->role.word; \ + __entry->root_count = sp->root_count; \ __entry->unsync = sp->unsync; #define KVM_MMU_PAGE_PRINTK() ({ \ @@ -29,8 +31,9 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gfn %llx l%u %u-byte q%u%s %s%s" \ + trace_seq_printf(p, "sp gen %u gfn %llx l%u %u-byte q%u%s %s%s" \ " %snxe %sad root %u %s%c", \ + __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ role.gpte_is_8_bytes ? 8 : 4, \ role.quadrant, \ @@ -246,13 +249,13 @@ TRACE_EVENT( TRACE_EVENT( fast_page_fault, - TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, + TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code, u64 *sptep, u64 old_spte, bool retry), - TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry), + TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry), TP_STRUCT__entry( __field(int, vcpu_id) - __field(gva_t, gva) + __field(gpa_t, cr2_or_gpa) __field(u32, error_code) __field(u64 *, sptep) __field(u64, old_spte) @@ -262,7 +265,7 @@ TRACE_EVENT( TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; - __entry->gva = gva; + __entry->cr2_or_gpa = cr2_or_gpa; __entry->error_code = error_code; __entry->sptep = sptep; __entry->old_spte = old_spte; @@ -270,9 +273,9 @@ TRACE_EVENT( __entry->retry = retry; ), - TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx" + TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx" " new %llx spurious %d fixed %d", __entry->vcpu_id, - __entry->gva, __print_flags(__entry->error_code, "|", + __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|", kvm_mmu_trace_pferr_flags), __entry->sptep, __entry->old_spte, __entry->new_spte, __spte_satisfied(old_spte), __spte_satisfied(new_spte) @@ -280,6 +283,27 @@ TRACE_EVENT( ); TRACE_EVENT( + kvm_mmu_zap_all_fast, + TP_PROTO(struct kvm *kvm), + TP_ARGS(kvm), + + TP_STRUCT__entry( + __field(__u8, mmu_valid_gen) + __field(unsigned int, mmu_used_pages) + ), + + TP_fast_assign( + __entry->mmu_valid_gen = kvm->arch.mmu_valid_gen; + __entry->mmu_used_pages = kvm->arch.n_used_mmu_pages; + ), + + TP_printk("kvm-mmu-valid-gen %u used_pages %x", + __entry->mmu_valid_gen, __entry->mmu_used_pages + ) +); + + +TRACE_EVENT( check_mmio_spte, TP_PROTO(u64 spte, unsigned int kvm_gen, unsigned int spte_gen), TP_ARGS(spte, kvm_gen, spte_gen), diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 25ce3edd1872..7f0059aa30e1 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -192,11 +192,15 @@ static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) break; case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: *seg = 1; - *unit = msr - MSR_MTRRfix16K_80000; + *unit = array_index_nospec( + msr - MSR_MTRRfix16K_80000, + MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1); break; case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: *seg = 2; - *unit = msr - MSR_MTRRfix4K_C0000; + *unit = array_index_nospec( + msr - MSR_MTRRfix4K_C0000, + MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1); break; default: return false; diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 46875bbd0419..bcc6a73d6628 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -62,8 +62,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = pmc_to_pmu(pmc); - if (!test_and_set_bit(pmc->idx, - (unsigned long *)&pmu->reprogram_pmi)) { + if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } @@ -76,8 +75,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = pmc_to_pmu(pmc); - if (!test_and_set_bit(pmc->idx, - (unsigned long *)&pmu->reprogram_pmi)) { + if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); @@ -137,7 +135,37 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, } pmc->perf_event = event; - clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi); + pmc_to_pmu(pmc)->event_count++; + clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); +} + +static void pmc_pause_counter(struct kvm_pmc *pmc) +{ + u64 counter = pmc->counter; + + if (!pmc->perf_event) + return; + + /* update counter, reset event value to avoid redundant accumulation */ + counter += perf_event_pause(pmc->perf_event, true); + pmc->counter = counter & pmc_bitmask(pmc); +} + +static bool pmc_resume_counter(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event) + return false; + + /* recalibrate sample period and check if it's accepted by perf core */ + if (perf_event_period(pmc->perf_event, + (-pmc->counter) & pmc_bitmask(pmc))) + return false; + + /* reuse perf_event to serve as pmc_reprogram_counter() does*/ + perf_event_enable(pmc->perf_event); + + clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); + return true; } void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) @@ -154,7 +182,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) pmc->eventsel = eventsel; - pmc_stop_counter(pmc); + pmc_pause_counter(pmc); if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc)) return; @@ -193,6 +221,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (type == PERF_TYPE_RAW) config = eventsel & X86_RAW_EVENT_MASK; + if (pmc->current_config == eventsel && pmc_resume_counter(pmc)) + return; + + pmc_release_perf_event(pmc); + + pmc->current_config = eventsel; pmc_reprogram_counter(pmc, type, config, !(eventsel & ARCH_PERFMON_EVENTSEL_USR), !(eventsel & ARCH_PERFMON_EVENTSEL_OS), @@ -209,7 +243,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) struct kvm_pmu_event_filter *filter; struct kvm *kvm = pmc->vcpu->kvm; - pmc_stop_counter(pmc); + pmc_pause_counter(pmc); if (!en_field || !pmc_is_enabled(pmc)) return; @@ -224,6 +258,12 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) return; } + if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc)) + return; + + pmc_release_perf_event(pmc); + + pmc->current_config = (u64)ctrl; pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, kvm_x86_ops->pmu_ops->find_fixed_event(idx), !(en_field & 0x2), /* exclude user */ @@ -253,27 +293,32 @@ EXPORT_SYMBOL_GPL(reprogram_counter); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - u64 bitmask; int bit; - bitmask = pmu->reprogram_pmi; - - for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { + for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) { struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit); if (unlikely(!pmc || !pmc->perf_event)) { - clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); + clear_bit(bit, pmu->reprogram_pmi); continue; } reprogram_counter(pmu, bit); } + + /* + * Unused perf_events are only released if the corresponding MSRs + * weren't accessed during the last vCPU time slice. kvm_arch_sched_in + * triggers KVM_REQ_PMU if cleanup is needed. + */ + if (unlikely(pmu->need_cleanup)) + kvm_pmu_cleanup(vcpu); } /* check if idx is a valid index to access PMU */ -int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { - return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx); + return kvm_x86_ops->pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); } bool is_vmware_backdoor_pmc(u32 pmc_idx) @@ -323,7 +368,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (is_vmware_backdoor_pmc(idx)) return kvm_pmu_rdpmc_vmware(vcpu, idx, data); - pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask); + pmc = kvm_x86_ops->pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask); if (!pmc) return 1; @@ -339,7 +384,17 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { - return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); + return kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr) || + kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); +} + +static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr); + + if (pmc) + __set_bit(pmc->idx, pmu->pmc_in_use); } int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) @@ -349,6 +404,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { + kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index); return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info); } @@ -376,9 +432,45 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); kvm_x86_ops->pmu_ops->init(vcpu); init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); + pmu->event_count = 0; + pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); } +static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + if (pmc_is_fixed(pmc)) + return fixed_ctrl_field(pmu->fixed_ctr_ctrl, + pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3; + + return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE; +} + +/* Release perf_events for vPMCs that have been unused for a full time slice. */ +void kvm_pmu_cleanup(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = NULL; + DECLARE_BITMAP(bitmask, X86_PMC_IDX_MAX); + int i; + + pmu->need_cleanup = false; + + bitmap_andnot(bitmask, pmu->all_valid_pmc_idx, + pmu->pmc_in_use, X86_PMC_IDX_MAX); + + for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) { + pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, i); + + if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc)) + pmc_stop_counter(pmc); + } + + bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX); +} + void kvm_pmu_destroy(struct kvm_vcpu *vcpu) { kvm_pmu_reset(vcpu); @@ -416,8 +508,8 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) *filter = tmp; mutex_lock(&kvm->lock); - rcu_swap_protected(kvm->arch.pmu_event_filter, filter, - mutex_is_locked(&kvm->lock)); + filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter, + mutex_is_locked(&kvm->lock)); mutex_unlock(&kvm->lock); synchronize_srcu_expedited(&kvm->srcu); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 58265f761c3b..13332984b6d5 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -2,6 +2,8 @@ #ifndef __KVM_X86_PMU_H #define __KVM_X86_PMU_H +#include <linux/nospec.h> + #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) @@ -25,9 +27,10 @@ struct kvm_pmu_ops { unsigned (*find_fixed_event)(int idx); bool (*pmc_is_enabled)(struct kvm_pmc *pmc); struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); - struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx, - u64 *mask); - int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx); + struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, + unsigned int idx, u64 *mask); + struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); + int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -55,12 +58,21 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } -static inline void pmc_stop_counter(struct kvm_pmc *pmc) +static inline void pmc_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { - pmc->counter = pmc_read_counter(pmc); perf_event_release_kernel(pmc->perf_event); pmc->perf_event = NULL; + pmc->current_config = 0; + pmc_to_pmu(pmc)->event_count--; + } +} + +static inline void pmc_stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = pmc_read_counter(pmc); + pmc_release_perf_event(pmc); } } @@ -79,6 +91,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc) return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc); } +static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu, + u64 data) +{ + return !(pmu->global_ctrl_mask & data); +} + /* returns general purpose PMC with the specified MSR. Note that it can be * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a * paramenter to tell them apart. @@ -86,8 +104,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc) static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, u32 base) { - if (msr >= base && msr < base + pmu->nr_arch_gp_counters) - return &pmu->gp_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_gp_counters); + + return &pmu->gp_counters[index]; + } return NULL; } @@ -97,8 +119,12 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) { int base = MSR_CORE_PERF_FIXED_CTR0; - if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) - return &pmu->fixed_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_fixed_counters); + + return &pmu->fixed_counters[index]; + } return NULL; } @@ -110,13 +136,14 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx); +int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void kvm_pmu_refresh(struct kvm_vcpu *vcpu); void kvm_pmu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_init(struct kvm_vcpu *vcpu); +void kvm_pmu_cleanup(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp); diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index c8388389a3b0..ce0b10fe5e2b 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -174,7 +174,7 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -184,7 +184,8 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) } /* idx is the ECX register of RDPMC instruction */ -static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask) +static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, + unsigned int idx, u64 *mask) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *counters; @@ -199,13 +200,19 @@ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { + /* All MSRs refer to exactly one PMC, so msr_idx_to_pmc is enough. */ + return false; +} + +static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) +{ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - int ret = false; + struct kvm_pmc *pmc; - ret = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER) || - get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); + pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); + pmc = pmc ? pmc : get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); - return ret; + return pmc; } static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) @@ -272,6 +279,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->nr_arch_fixed_counters = 0; pmu->global_status = 0; + bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters); } static void amd_pmu_init(struct kvm_vcpu *vcpu) @@ -285,6 +293,7 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; + pmu->gp_counters[i].current_config = 0; } } @@ -306,8 +315,9 @@ struct kvm_pmu_ops amd_pmu_ops = { .find_fixed_event = amd_find_fixed_event, .pmc_is_enabled = amd_pmc_is_enabled, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, + .rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = amd_msr_idx_to_pmc, - .is_valid_msr_idx = amd_is_valid_msr_idx, + .is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx, .is_valid_msr = amd_is_valid_msr, .get_msr = amd_pmu_get_msr, .set_msr = amd_pmu_set_msr, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d685491fce4d..bef0ba35f121 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -38,6 +38,7 @@ #include <linux/file.h> #include <linux/pagemap.h> #include <linux/swap.h> +#include <linux/rwsem.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -68,10 +69,8 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 -#define SVM_FEATURE_NPT (1 << 0) #define SVM_FEATURE_LBRV (1 << 1) #define SVM_FEATURE_SVML (1 << 2) -#define SVM_FEATURE_NRIP (1 << 3) #define SVM_FEATURE_TSC_RATE (1 << 4) #define SVM_FEATURE_VMCB_CLEAN (1 << 5) #define SVM_FEATURE_FLUSH_ASID (1 << 6) @@ -388,6 +387,8 @@ static u8 rsm_ins_bytes[] = "\x0f\xaa"; static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); +static void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate); +static inline void avic_post_state_restore(struct kvm_vcpu *vcpu); static int nested_svm_exit_handled(struct vcpu_svm *svm); static int nested_svm_intercept(struct vcpu_svm *svm); @@ -420,9 +421,13 @@ enum { #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL +static int sev_flush_asids(void); +static DECLARE_RWSEM(sev_deactivate_lock); +static DEFINE_MUTEX(sev_bitmap_lock); static unsigned int max_sev_asid; static unsigned int min_sev_asid; static unsigned long *sev_asid_bitmap; +static unsigned long *sev_reclaim_asid_bitmap; #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) struct enc_region { @@ -736,8 +741,14 @@ static int get_npt_level(struct kvm_vcpu *vcpu) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { vcpu->arch.efer = efer; - if (!npt_enabled && !(efer & EFER_LMA)) - efer &= ~EFER_LME; + + if (!npt_enabled) { + /* Shadow paging assumes NX to be available. */ + efer |= EFER_NX; + + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + } to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -770,7 +781,7 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) } -static void skip_emulated_instruction(struct kvm_vcpu *vcpu) +static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -780,17 +791,17 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) } if (!svm->next_rip) { - if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) != - EMULATE_DONE) - printk(KERN_DEBUG "%s: NOP\n", __func__); - return; + if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) + return 0; + } else { + if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE) + pr_err("%s: ip 0x%lx next 0x%llx\n", + __func__, kvm_rip_read(vcpu), svm->next_rip); + kvm_rip_write(vcpu, svm->next_rip); } - if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE) - printk(KERN_ERR "%s: ip 0x%lx next 0x%llx\n", - __func__, kvm_rip_read(vcpu), svm->next_rip); - - kvm_rip_write(vcpu, svm->next_rip); svm_set_interrupt_shadow(vcpu, 0); + + return 1; } static void svm_queue_exception(struct kvm_vcpu *vcpu) @@ -821,7 +832,7 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu) * raises a fault that is not intercepted. Still better than * failing in all cases. */ - skip_emulated_instruction(&svm->vcpu); + (void)skip_emulated_instruction(&svm->vcpu); rip = kvm_rip_read(&svm->vcpu); svm->int3_rip = rip + svm->vmcb->save.cs.base; svm->int3_injected = rip - old_rip; @@ -1231,11 +1242,15 @@ static __init int sev_hardware_setup(void) /* Minimum ASID value that should be used for SEV guest */ min_sev_asid = cpuid_edx(0x8000001F); - /* Initialize SEV ASID bitmap */ + /* Initialize SEV ASID bitmaps */ sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_asid_bitmap) return 1; + sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + if (!sev_reclaim_asid_bitmap) + return 1; + status = kmalloc(sizeof(*status), GFP_KERNEL); if (!status) return 1; @@ -1269,11 +1284,11 @@ static void grow_ple_window(struct kvm_vcpu *vcpu) pause_filter_count_grow, pause_filter_count_max); - if (control->pause_filter_count != old) + if (control->pause_filter_count != old) { mark_dirty(svm->vmcb, VMCB_INTERCEPTS); - - trace_kvm_ple_window_grow(vcpu->vcpu_id, - control->pause_filter_count, old); + trace_kvm_ple_window_update(vcpu->vcpu_id, + control->pause_filter_count, old); + } } static void shrink_ple_window(struct kvm_vcpu *vcpu) @@ -1287,11 +1302,52 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) pause_filter_count, pause_filter_count_shrink, pause_filter_count); - if (control->pause_filter_count != old) + if (control->pause_filter_count != old) { mark_dirty(svm->vmcb, VMCB_INTERCEPTS); + trace_kvm_ple_window_update(vcpu->vcpu_id, + control->pause_filter_count, old); + } +} - trace_kvm_ple_window_shrink(vcpu->vcpu_id, - control->pause_filter_count, old); +/* + * The default MMIO mask is a single bit (excluding the present bit), + * which could conflict with the memory encryption bit. Check for + * memory encryption support and override the default MMIO mask if + * memory encryption is enabled. + */ +static __init void svm_adjust_mmio_mask(void) +{ + unsigned int enc_bit, mask_bit; + u64 msr, mask; + + /* If there is no memory encryption support, use existing mask */ + if (cpuid_eax(0x80000000) < 0x8000001f) + return; + + /* If memory encryption is not enabled, use existing mask */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + + enc_bit = cpuid_ebx(0x8000001f) & 0x3f; + mask_bit = boot_cpu_data.x86_phys_bits; + + /* Increment the mask bit if it is the same as the encryption bit */ + if (enc_bit == mask_bit) + mask_bit++; + + /* + * If the mask bit location is below 52, then some bits above the + * physical addressing limit will always be reserved, so use the + * rsvd_bits() function to generate the mask. This mask, along with + * the present bit, will be used to generate a page fault with + * PFER.RSV = 1. + * + * If the mask bit location is 52 (or above), then clear the mask. + */ + mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0; + + kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); } static __init int svm_hardware_setup(void) @@ -1348,6 +1404,8 @@ static __init int svm_hardware_setup(void) } } + svm_adjust_mmio_mask(); + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) @@ -1414,8 +1472,12 @@ static __exit void svm_hardware_unsetup(void) { int cpu; - if (svm_sev_enabled()) + if (svm_sev_enabled()) { bitmap_free(sev_asid_bitmap); + bitmap_free(sev_reclaim_asid_bitmap); + + sev_flush_asids(); + } for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -1485,7 +1547,10 @@ static void avic_init_vmcb(struct vcpu_svm *svm) vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT; - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + if (kvm_apicv_activated(svm->vcpu.kvm)) + vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + else + vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; } static void init_vmcb(struct vcpu_svm *svm) @@ -1542,6 +1607,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_SKINIT); set_intercept(svm, INTERCEPT_WBINVD); set_intercept(svm, INTERCEPT_XSETBV); + set_intercept(svm, INTERCEPT_RDPRU); set_intercept(svm, INTERCEPT_RSM); if (!kvm_mwait_in_guest(svm->vcpu.kvm)) { @@ -1668,23 +1734,28 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, * field of the VMCB. Therefore, we set up the * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here. */ -static int avic_init_access_page(struct kvm_vcpu *vcpu) +static int avic_update_access_page(struct kvm *kvm, bool activate) { - struct kvm *kvm = vcpu->kvm; int ret = 0; mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_page_done) + /* + * During kvm_destroy_vm(), kvm_pit_set_reinject() could trigger + * APICv mode change, which update APIC_ACCESS_PAGE_PRIVATE_MEMSLOT + * memory region. So, we need to ensure that kvm->mm == current->mm. + */ + if ((kvm->arch.apic_access_page_done == activate) || + (kvm->mm != current->mm)) goto out; ret = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, APIC_DEFAULT_PHYS_BASE, - PAGE_SIZE); + activate ? PAGE_SIZE : 0); if (ret) goto out; - kvm->arch.apic_access_page_done = true; + kvm->arch.apic_access_page_done = activate; out: mutex_unlock(&kvm->slots_lock); return ret; @@ -1692,21 +1763,24 @@ out: static int avic_init_backing_page(struct kvm_vcpu *vcpu) { - int ret; u64 *entry, new_entry; int id = vcpu->vcpu_id; struct vcpu_svm *svm = to_svm(vcpu); - ret = avic_init_access_page(vcpu); - if (ret) - return ret; - if (id >= AVIC_MAX_PHYSICAL_ID_COUNT) return -EINVAL; if (!svm->vcpu.arch.apic->regs) return -EINVAL; + if (kvm_apicv_activated(vcpu->kvm)) { + int ret; + + ret = avic_update_access_page(vcpu->kvm, true); + if (ret) + return ret; + } + svm->avic_backing_page = virt_to_page(svm->vcpu.arch.apic->regs); /* Setting AVIC backing page address in the phy APIC ID table */ @@ -1714,7 +1788,6 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) if (!entry) return -EINVAL; - new_entry = READ_ONCE(*entry); new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); @@ -1725,25 +1798,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } -static void __sev_asid_free(int asid) +static void sev_asid_free(int asid) { struct svm_cpu_data *sd; int cpu, pos; + mutex_lock(&sev_bitmap_lock); + pos = asid - 1; - clear_bit(pos, sev_asid_bitmap); + __set_bit(pos, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { sd = per_cpu(svm_data, cpu); sd->sev_vmcbs[pos] = NULL; } -} - -static void sev_asid_free(struct kvm *kvm) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - __sev_asid_free(sev->asid); + mutex_unlock(&sev_bitmap_lock); } static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) @@ -1760,10 +1830,12 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) /* deactivate handle */ data->handle = handle; + + /* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */ + down_read(&sev_deactivate_lock); sev_guest_deactivate(data, NULL); + up_read(&sev_deactivate_lock); - wbinvd_on_all_cpus(); - sev_guest_df_flush(NULL); kfree(data); decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); @@ -1912,7 +1984,7 @@ static void sev_vm_destroy(struct kvm *kvm) mutex_unlock(&kvm->lock); sev_unbind_asid(kvm, sev->handle); - sev_asid_free(kvm); + sev_asid_free(sev->asid); } static void avic_vm_destroy(struct kvm *kvm) @@ -1993,6 +2065,18 @@ free_avic: return err; } +static int svm_vm_init(struct kvm *kvm) +{ + if (avic) { + int ret = avic_vm_init(kvm); + if (ret) + return ret; + } + + kvm_apicv_init(kvm, avic); + return 0; +} + static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) { @@ -2091,7 +2175,6 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; - vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; svm->virt_spec_ctrl = 0; @@ -2128,7 +2211,7 @@ static int avic_init_vcpu(struct vcpu_svm *svm) return ret; } -static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) +static int svm_create_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm; struct page *page; @@ -2137,36 +2220,13 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) struct page *nested_msrpm_pages; int err; - svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); - if (!svm) { - err = -ENOMEM; - goto out; - } - - svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!svm->vcpu.arch.user_fpu) { - printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); - err = -ENOMEM; - goto free_partial_svm; - } - - svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!svm->vcpu.arch.guest_fpu) { - printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); - err = -ENOMEM; - goto free_user_fpu; - } - - err = kvm_vcpu_init(&svm->vcpu, kvm, id); - if (err) - goto free_svm; + BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0); + svm = to_svm(vcpu); err = -ENOMEM; page = alloc_page(GFP_KERNEL_ACCOUNT); if (!page) - goto uninit; + goto out; msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER); if (!msrpm_pages) @@ -2187,7 +2247,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) /* We initialize this flag to true to make sure that the is_running * bit would be set the first time the vcpu is loaded. */ - svm->avic_is_running = true; + if (irqchip_in_kernel(vcpu->kvm) && kvm_apicv_activated(vcpu->kvm)) + svm->avic_is_running = true; svm->nested.hsave = page_address(hsave_page); @@ -2203,9 +2264,10 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->asid_generation = 0; init_vmcb(svm); - svm_init_osvw(&svm->vcpu); + svm_init_osvw(vcpu); + vcpu->arch.microcode_version = 0x01000065; - return &svm->vcpu; + return 0; free_page4: __free_page(hsave_page); @@ -2215,16 +2277,8 @@ free_page2: __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER); free_page1: __free_page(page); -uninit: - kvm_vcpu_uninit(&svm->vcpu); -free_svm: - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); -free_user_fpu: - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); -free_partial_svm: - kmem_cache_free(kvm_vcpu_cache, svm); out: - return ERR_PTR(err); + return err; } static void svm_clear_current_vmcb(struct vmcb *vmcb) @@ -2250,10 +2304,6 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); - kmem_cache_free(kvm_vcpu_cache, svm); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -2324,6 +2374,8 @@ static void svm_vcpu_blocking(struct kvm_vcpu *vcpu) static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu) { + if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) + kvm_vcpu_update_apicv(vcpu); avic_set_running(vcpu, true); } @@ -2363,7 +2415,7 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); break; default: - BUG(); + WARN_ON_ONCE(1); } } @@ -2516,10 +2568,6 @@ static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { } -static void svm_decache_cr3(struct kvm_vcpu *vcpu) -{ -} - static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { } @@ -2769,17 +2817,18 @@ static int gp_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; u32 error_code = svm->vmcb->control.exit_info_1; - int er; WARN_ON_ONCE(!enable_vmware_backdoor); - er = kvm_emulate_instruction(vcpu, - EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); - if (er == EMULATE_USER_EXIT) - return 0; - else if (er != EMULATE_DONE) + /* + * VMware backdoor emulation on #GP interception only handles IN{S}, + * OUT{S}, and RDPMC, none of which generate a non-zero error code. + */ + if (error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); - return 1; + return 1; + } + return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP); } static bool is_erratum_383(void) @@ -2877,7 +2926,7 @@ static int io_interception(struct vcpu_svm *svm) string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; if (string) - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; @@ -2904,13 +2953,11 @@ static int nop_on_interception(struct vcpu_svm *svm) static int halt_interception(struct vcpu_svm *svm) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; return kvm_emulate_halt(&svm->vcpu); } static int vmmcall_interception(struct vcpu_svm *svm) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; return kvm_emulate_hypercall(&svm->vcpu); } @@ -3589,9 +3636,9 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, mark_all_dirty(svm->vmcb); } -static bool nested_svm_vmrun(struct vcpu_svm *svm) +static int nested_svm_vmrun(struct vcpu_svm *svm) { - int rc; + int ret; struct vmcb *nested_vmcb; struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; @@ -3600,13 +3647,16 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) vmcb_gpa = svm->vmcb->save.rax; - rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); - if (rc) { - if (rc == -EINVAL) - kvm_inject_gp(&svm->vcpu, 0); - return false; + ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); + if (ret == -EINVAL) { + kvm_inject_gp(&svm->vcpu, 0); + return 1; + } else if (ret) { + return kvm_skip_emulated_instruction(&svm->vcpu); } + ret = kvm_skip_emulated_instruction(&svm->vcpu); + nested_vmcb = map.hva; if (!nested_vmcb_checks(nested_vmcb)) { @@ -3617,7 +3667,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) kvm_vcpu_unmap(&svm->vcpu, &map, true); - return false; + return ret; } trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa, @@ -3661,7 +3711,16 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map); - return true; + if (!nested_svm_vmrun_msrpm(svm)) { + svm->vmcb->control.exit_code = SVM_EXIT_ERR; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + nested_svm_vmexit(svm); + } + + return ret; } static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) @@ -3698,7 +3757,6 @@ static int vmload_interception(struct vcpu_svm *svm) nested_vmcb = map.hva; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(nested_vmcb, svm->vmcb); @@ -3725,7 +3783,6 @@ static int vmsave_interception(struct vcpu_svm *svm) nested_vmcb = map.hva; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(svm->vmcb, nested_vmcb); @@ -3739,27 +3796,7 @@ static int vmrun_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - /* Save rip after vmrun instruction */ - kvm_rip_write(&svm->vcpu, kvm_rip_read(&svm->vcpu) + 3); - - if (!nested_svm_vmrun(svm)) - return 1; - - if (!nested_svm_vmrun_msrpm(svm)) - goto failed; - - return 1; - -failed: - - svm->vmcb->control.exit_code = SVM_EXIT_ERR; - svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - - nested_svm_vmexit(svm); - - return 1; + return nested_svm_vmrun(svm); } static int stgi_interception(struct vcpu_svm *svm) @@ -3776,7 +3813,6 @@ static int stgi_interception(struct vcpu_svm *svm) if (vgif_enabled(svm)) clr_intercept(svm, INTERCEPT_STGI); - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); @@ -3792,7 +3828,6 @@ static int clgi_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); disable_gif(svm); @@ -3817,7 +3852,6 @@ static int invlpga_interception(struct vcpu_svm *svm) /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ kvm_mmu_invlpg(vcpu, kvm_rax_read(&svm->vcpu)); - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; return kvm_skip_emulated_instruction(&svm->vcpu); } @@ -3840,13 +3874,18 @@ static int xsetbv_interception(struct vcpu_svm *svm) u32 index = kvm_rcx_read(&svm->vcpu); if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; return kvm_skip_emulated_instruction(&svm->vcpu); } return 1; } +static int rdpru_interception(struct vcpu_svm *svm) +{ + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; +} + static int task_switch_interception(struct vcpu_svm *svm) { u16 tss_selector; @@ -3899,25 +3938,20 @@ static int task_switch_interception(struct vcpu_svm *svm) if (reason != TASK_SWITCH_GATE || int_type == SVM_EXITINTINFO_TYPE_SOFT || (int_type == SVM_EXITINTINFO_TYPE_EXEPT && - (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) - skip_emulated_instruction(&svm->vcpu); + (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) { + if (!skip_emulated_instruction(&svm->vcpu)) + return 0; + } if (int_type != SVM_EXITINTINFO_TYPE_SOFT) int_vec = -1; - if (kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason, - has_error_code, error_code) == EMULATE_FAIL) { - svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - svm->vcpu.run->internal.ndata = 0; - return 0; - } - return 1; + return kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason, + has_error_code, error_code); } static int cpuid_interception(struct vcpu_svm *svm) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; return kvm_emulate_cpuid(&svm->vcpu); } @@ -3934,7 +3968,7 @@ static int iret_interception(struct vcpu_svm *svm) static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) - return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0); kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); return kvm_skip_emulated_instruction(&svm->vcpu); @@ -3942,13 +3976,12 @@ static int invlpg_interception(struct vcpu_svm *svm) static int emulate_on_interception(struct vcpu_svm *svm) { - return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0); } static int rsm_interception(struct vcpu_svm *svm) { - return kvm_emulate_instruction_from_buffer(&svm->vcpu, - rsm_ins_bytes, 2) == EMULATE_DONE; + return kvm_emulate_instruction_from_buffer(&svm->vcpu, rsm_ins_bytes, 2); } static int rdpmc_interception(struct vcpu_svm *svm) @@ -4192,6 +4225,8 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) && !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) return 1; @@ -4233,23 +4268,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static int rdmsr_interception(struct vcpu_svm *svm) { - u32 ecx = kvm_rcx_read(&svm->vcpu); - struct msr_data msr_info; - - msr_info.index = ecx; - msr_info.host_initiated = false; - if (svm_get_msr(&svm->vcpu, &msr_info)) { - trace_kvm_msr_read_ex(ecx); - kvm_inject_gp(&svm->vcpu, 0); - return 1; - } else { - trace_kvm_msr_read(ecx, msr_info.data); - - kvm_rax_write(&svm->vcpu, msr_info.data & 0xffffffff); - kvm_rdx_write(&svm->vcpu, msr_info.data >> 32); - svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - return kvm_skip_emulated_instruction(&svm->vcpu); - } + return kvm_emulate_rdmsr(&svm->vcpu); } static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) @@ -4293,16 +4312,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_SPEC_CTRL: if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) && !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) return 1; - /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) + if (data & ~kvm_spec_ctrl_valid_bits(vcpu)) return 1; svm->spec_ctrl = data; - if (!data) break; @@ -4326,13 +4345,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & ~PRED_CMD_IBPB) return 1; - + if (!boot_cpu_has(X86_FEATURE_AMD_IBPB)) + return 1; if (!data) break; wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - if (is_guest_mode(vcpu)) - break; set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); break; case MSR_AMD64_VIRT_SPEC_CTRL: @@ -4439,23 +4457,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) static int wrmsr_interception(struct vcpu_svm *svm) { - struct msr_data msr; - u32 ecx = kvm_rcx_read(&svm->vcpu); - u64 data = kvm_read_edx_eax(&svm->vcpu); - - msr.data = data; - msr.index = ecx; - msr.host_initiated = false; - - svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - if (kvm_set_msr(&svm->vcpu, &msr)) { - trace_kvm_msr_write_ex(ecx, data); - kvm_inject_gp(&svm->vcpu, 0); - return 1; - } else { - trace_kvm_msr_write(ecx, data); - return kvm_skip_emulated_instruction(&svm->vcpu); - } + return kvm_emulate_wrmsr(&svm->vcpu); } static int msr_interception(struct vcpu_svm *svm) @@ -4470,6 +4472,14 @@ static int interrupt_window_interception(struct vcpu_svm *svm) { kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); svm_clear_vintr(svm); + + /* + * For AVIC, the only reason to end up here is ExtINTs. + * In this case AVIC was temporarily disabled for + * requesting the IRQ window and we have to re-enable it. + */ + svm_toggle_avic_for_irq_window(&svm->vcpu, true); + svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; mark_dirty(svm->vmcb, VMCB_INTR); ++svm->vcpu.stat.irq_window_exits; @@ -4551,9 +4561,9 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) */ kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, apic, - icrl & KVM_APIC_SHORT_MASK, + icrl & APIC_SHORT_MASK, GET_APIC_DEST_FIELD(icrh), - icrl & KVM_APIC_DEST_MASK); + icrl & APIC_DEST_MASK); if (m && !avic_vcpu_is_running(vcpu)) kvm_vcpu_wake_up(vcpu); @@ -4637,6 +4647,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) int ret = 0; struct vcpu_svm *svm = to_svm(vcpu); u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); + u32 id = kvm_xapic_id(vcpu->arch.apic); if (ldr == svm->ldr_reg) return 0; @@ -4644,7 +4655,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) avic_invalidate_logical_id_entry(vcpu); if (ldr) - ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr); + ret = avic_ldr_write(vcpu, id, ldr); if (!ret) svm->ldr_reg = ldr; @@ -4656,8 +4667,7 @@ static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) { u64 *old, *new; struct vcpu_svm *svm = to_svm(vcpu); - u32 apic_id_reg = kvm_lapic_get_reg(vcpu->arch.apic, APIC_ID); - u32 id = (apic_id_reg >> 24) & 0xff; + u32 id = kvm_xapic_id(vcpu->arch.apic); if (vcpu->vcpu_id == id) return 0; @@ -4769,7 +4779,7 @@ static int avic_unaccelerated_access_interception(struct vcpu_svm *svm) ret = avic_unaccel_trap_write(svm); } else { /* Handling Fault */ - ret = (kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); + ret = kvm_emulate_instruction(&svm->vcpu, 0); } return ret; @@ -4836,6 +4846,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MONITOR] = monitor_interception, [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, + [SVM_EXIT_RDPRU] = rdpru_interception, [SVM_EXIT_NPF] = npf_interception, [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, @@ -4966,7 +4977,8 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = control->exit_info_2; } -static int handle_exit(struct kvm_vcpu *vcpu) +static int handle_exit(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_run *kvm_run = vcpu->run; @@ -5024,13 +5036,33 @@ static int handle_exit(struct kvm_vcpu *vcpu) __func__, svm->vmcb->control.exit_int_info, exit_code); - if (exit_code >= ARRAY_SIZE(svm_exit_handlers) - || !svm_exit_handlers[exit_code]) { - WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code); - kvm_queue_exception(vcpu, UD_VECTOR); + if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { + kvm_skip_emulated_instruction(vcpu); return 1; + } else if (exit_code >= ARRAY_SIZE(svm_exit_handlers) + || !svm_exit_handlers[exit_code]) { + vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code); + dump_vmcb(vcpu); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 1; + vcpu->run->internal.data[0] = exit_code; + return 0; } +#ifdef CONFIG_RETPOLINE + if (exit_code == SVM_EXIT_MSR) + return msr_interception(svm); + else if (exit_code == SVM_EXIT_VINTR) + return interrupt_window_interception(svm); + else if (exit_code == SVM_EXIT_INTR) + return intr_interception(svm); + else if (exit_code == SVM_EXIT_HLT) + return halt_interception(svm); + else if (exit_code == SVM_EXIT_NPF) + return npf_interception(svm); +#endif return svm_exit_handlers[exit_code](svm); } @@ -5126,8 +5158,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); - if (svm_nested_virtualize_tpr(vcpu) || - kvm_vcpu_apicv_active(vcpu)) + if (svm_nested_virtualize_tpr(vcpu)) return; clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); @@ -5144,30 +5175,79 @@ static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu) return; } -static bool svm_get_enable_apicv(struct kvm_vcpu *vcpu) +static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) { - return avic && irqchip_split(vcpu->kvm); } -static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) +static void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { } -static void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) +static void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate) { + if (!avic || !lapic_in_kernel(vcpu)) + return; + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_request_apicv_update(vcpu->kvm, activate, + APICV_INHIBIT_REASON_IRQWIN); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) +{ + int ret = 0; + unsigned long flags; + struct amd_svm_iommu_ir *ir; + struct vcpu_svm *svm = to_svm(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; + + /* + * Here, we go through the per-vcpu ir_list to update all existing + * interrupt remapping table entry targeting this vcpu. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); + + if (list_empty(&svm->ir_list)) + goto out; + + list_for_each_entry(ir, &svm->ir_list, node) { + if (activate) + ret = amd_iommu_activate_guest_mode(ir->data); + else + ret = amd_iommu_deactivate_guest_mode(ir->data); + if (ret) + break; + } +out: + spin_unlock_irqrestore(&svm->ir_list_lock, flags); + return ret; } -/* Note: Currently only used by Hyper-V. */ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; + bool activated = kvm_vcpu_apicv_active(vcpu); - if (kvm_vcpu_apicv_active(vcpu)) + if (activated) { + /** + * During AVIC temporary deactivation, guest could update + * APIC ID, DFR and LDR registers, which would not be trapped + * by avic_unaccelerated_access_interception(). In this case, + * we need to check and update the AVIC logical APIC ID table + * accordingly before re-activating. + */ + avic_post_state_restore(vcpu); vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - else + } else { vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; + } mark_dirty(vmcb, VMCB_AVIC); + + svm_set_pi_irte_mode(vcpu, activated); } static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -5275,7 +5355,8 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, kvm_set_msi_irq(kvm, e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || + !kvm_irq_is_postable(&irq)) { pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n", __func__, irq.vector); return -1; @@ -5329,6 +5410,7 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * 1. When cannot target interrupt to a specific vcpu. * 2. Unsetting posted interrupt. * 3. APIC virtialization is disabled for the vcpu. + * 4. IRQ has incompatible delivery mode (SMI, INIT, etc) */ if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && kvm_vcpu_apicv_active(&svm->vcpu)) { @@ -5452,9 +5534,6 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (kvm_vcpu_apicv_active(vcpu)) - return; - /* * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes * 1, because that's a separate STGI/VMRUN intercept. The next time we @@ -5464,6 +5543,13 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) * window under the assumption that the hardware will set the GIF. */ if ((vgif_enabled(svm) || gif_set(svm)) && nested_svm_intr(svm)) { + /* + * IRQ window is not needed when AVIC is enabled, + * unless we have pending ExtINT since it cannot be injected + * via AVIC. In such case, we need to temporarily disable AVIC, + * and fallback to injecting IRQ via V_IRQ. + */ + svm_toggle_avic_for_irq_window(vcpu, false); svm_set_vintr(svm); svm_inject_irq(svm, 0x0); } @@ -5666,7 +5752,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); - kvm_load_guest_xcr0(vcpu); + kvm_load_guest_xsave_state(vcpu); if (lapic_in_kernel(vcpu) && vcpu->arch.apic->lapic_timer.timer_advance_ns) @@ -5816,7 +5902,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); - kvm_put_guest_xcr0(vcpu); + kvm_load_host_xsave_state(vcpu); stgi(); /* Any pending NMI will happen here */ @@ -5925,6 +6011,10 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVES); + /* Update nrips enabled cache */ svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); @@ -5932,19 +6022,34 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) return; guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC); + + /* + * Currently, AVIC does not work with nested virtualization. + * So, we disable AVIC when cpuid for SVM is set in the L1 guest. + */ + if (nested && guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + kvm_request_apicv_update(vcpu->kvm, false, + APICV_INHIBIT_REASON_NESTED); } +#define F feature_bit + static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { switch (func) { case 0x1: if (avic) - entry->ecx &= ~bit(X86_FEATURE_X2APIC); + entry->ecx &= ~F(X2APIC); break; case 0x80000001: if (nested) entry->ecx |= (1 << 2); /* Set SVM bit */ break; + case 0x80000008: + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->ebx |= F(VIRT_SSBD); + break; case 0x8000000A: entry->eax = 1; /* SVM revision 1 */ entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper @@ -5955,18 +6060,11 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) /* Support next_rip if host supports it */ if (boot_cpu_has(X86_FEATURE_NRIPS)) - entry->edx |= SVM_FEATURE_NRIP; + entry->edx |= F(NRIPS); /* Support NPT for the guest if enabled */ if (npt_enabled) - entry->edx |= SVM_FEATURE_NPT; - - break; - case 0x8000001F: - /* Support memory encryption cpuid if host supports it */ - if (boot_cpu_has(X86_FEATURE_SEV)) - cpuid(0x8000001f, &entry->eax, &entry->ebx, - &entry->ecx, &entry->edx); + entry->edx |= F(NPT); } } @@ -5993,7 +6091,7 @@ static bool svm_mpx_supported(void) static bool svm_xsaves_supported(void) { - return false; + return boot_cpu_has(X86_FEATURE_XSAVES); } static bool svm_umip_emulated(void) @@ -6011,6 +6109,11 @@ static bool svm_has_wbinvd_exit(void) return true; } +static bool svm_pku_supported(void) +{ + return false; +} + #define PRE_EX(exit) { .exit_code = (exit), \ .stage = X86_ICPT_PRE_EXCEPT, } #define POST_EX(exit) { .exit_code = (exit), \ @@ -6068,6 +6171,7 @@ static const struct __x86_intercept { [x86_intercept_ins] = POST_EX(SVM_EXIT_IOIO), [x86_intercept_out] = POST_EX(SVM_EXIT_IOIO), [x86_intercept_outs] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_xsetbv] = PRE_EX(SVM_EXIT_XSETBV), }; #undef PRE_EX @@ -6195,9 +6299,12 @@ out: return ret; } -static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) +static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion *exit_fastpath) { - + if (!is_guest_mode(vcpu) && + to_svm(vcpu)->vmcb->control.exit_code == EXIT_REASON_MSR_WRITE) + *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) @@ -6294,18 +6401,73 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static int sev_flush_asids(void) +{ + int ret, error; + + /* + * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail, + * so it must be guarded. + */ + down_write(&sev_deactivate_lock); + + wbinvd_on_all_cpus(); + ret = sev_guest_df_flush(&error); + + up_write(&sev_deactivate_lock); + + if (ret) + pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error); + + return ret; +} + +/* Must be called with the sev_bitmap_lock held */ +static bool __sev_recycle_asids(void) +{ + int pos; + + /* Check if there are any ASIDs to reclaim before performing a flush */ + pos = find_next_bit(sev_reclaim_asid_bitmap, + max_sev_asid, min_sev_asid - 1); + if (pos >= max_sev_asid) + return false; + + if (sev_flush_asids()) + return false; + + bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap, + max_sev_asid); + bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid); + + return true; +} + static int sev_asid_new(void) { + bool retry = true; int pos; + mutex_lock(&sev_bitmap_lock); + /* * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid. */ +again: pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1); - if (pos >= max_sev_asid) + if (pos >= max_sev_asid) { + if (retry && __sev_recycle_asids()) { + retry = false; + goto again; + } + mutex_unlock(&sev_bitmap_lock); return -EBUSY; + } + + __set_bit(pos, sev_asid_bitmap); + + mutex_unlock(&sev_bitmap_lock); - set_bit(pos, sev_asid_bitmap); return pos + 1; } @@ -6333,7 +6495,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) return 0; e_free: - __sev_asid_free(asid); + sev_asid_free(asid); return ret; } @@ -6343,12 +6505,6 @@ static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) int asid = sev_get_asid(kvm); int ret; - wbinvd_on_all_cpus(); - - ret = sev_guest_df_flush(error); - if (ret) - return ret; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -7129,19 +7285,6 @@ failed: return ret; } -static uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) -{ - /* Not supported */ - return 0; -} - -static int nested_enable_evmcs(struct kvm_vcpu *vcpu, - uint16_t *vmcs_version) -{ - /* Intel-only feature */ - return -ENODEV; -} - static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) { unsigned long cr4 = kvm_read_cr4(vcpu); @@ -7200,6 +7343,37 @@ static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) return false; } +static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * TODO: Last condition latch INIT signals on vCPU when + * vCPU is in guest-mode and vmcb12 defines intercept on INIT. + * To properly emulate the INIT intercept, SVM should implement + * kvm_x86_ops->check_nested_events() and call nested_svm_vmexit() + * there if an INIT signal is pending. + */ + return !gif_set(svm) || + (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT)); +} + +static bool svm_check_apicv_inhibit_reasons(ulong bit) +{ + ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_HYPERV) | + BIT(APICV_INHIBIT_REASON_NESTED) | + BIT(APICV_INHIBIT_REASON_IRQWIN) | + BIT(APICV_INHIBIT_REASON_PIT_REINJ); + + return supported & BIT(bit); +} + +static void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate) +{ + avic_update_access_page(kvm, activate); +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -7217,7 +7391,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .vm_alloc = svm_vm_alloc, .vm_free = svm_vm_free, - .vm_init = avic_vm_init, + .vm_init = svm_vm_init, .vm_destroy = svm_vm_destroy, .prepare_guest_switch = svm_prepare_guest_switch, @@ -7236,7 +7410,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_cpl = svm_get_cpl, .get_cs_db_l_bits = kvm_get_cs_db_l_bits, .decache_cr0_guest_bits = svm_decache_cr0_guest_bits, - .decache_cr3 = svm_decache_cr3, .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, .set_cr3 = svm_set_cr3, @@ -7275,8 +7448,9 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_apic_mode = svm_set_virtual_apic_mode, - .get_enable_apicv = svm_get_enable_apicv, .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, + .check_apicv_inhibit_reasons = svm_check_apicv_inhibit_reasons, + .pre_update_apicv_exec_ctrl = svm_pre_update_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, @@ -7300,6 +7474,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .xsaves_supported = svm_xsaves_supported, .umip_emulated = svm_umip_emulated, .pt_supported = svm_pt_supported, + .pku_supported = svm_pku_supported, .set_supported_cpuid = svm_set_supported_cpuid, @@ -7332,10 +7507,12 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .mem_enc_reg_region = svm_register_enc_region, .mem_enc_unreg_region = svm_unregister_enc_region, - .nested_enable_evmcs = nested_enable_evmcs, - .nested_get_evmcs_version = nested_get_evmcs_version, + .nested_enable_evmcs = NULL, + .nested_get_evmcs_version = NULL, .need_emulation_on_page_fault = svm_need_emulation_on_page_fault, + + .apic_init_signal_blocked = svm_apic_init_signal_blocked, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index b5c831e79094..f194dd058470 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -232,17 +232,20 @@ TRACE_EVENT(kvm_exit, __field( u32, isa ) __field( u64, info1 ) __field( u64, info2 ) + __field( unsigned int, vcpu_id ) ), TP_fast_assign( __entry->exit_reason = exit_reason; __entry->guest_rip = kvm_rip_read(vcpu); __entry->isa = isa; + __entry->vcpu_id = vcpu->vcpu_id; kvm_x86_ops->get_exit_info(vcpu, &__entry->info1, &__entry->info2); ), - TP_printk("reason %s rip 0x%lx info %llx %llx", + TP_printk("vcpu %u reason %s rip 0x%lx info %llx %llx", + __entry->vcpu_id, (__entry->isa == KVM_ISA_VMX) ? __print_symbolic(__entry->exit_reason, VMX_EXIT_REASONS) : __print_symbolic(__entry->exit_reason, SVM_EXIT_REASONS), @@ -887,36 +890,27 @@ TRACE_EVENT(kvm_pml_full, TP_printk("vcpu %d: PML full", __entry->vcpu_id) ); -TRACE_EVENT(kvm_ple_window, - TP_PROTO(bool grow, unsigned int vcpu_id, int new, int old), - TP_ARGS(grow, vcpu_id, new, old), +TRACE_EVENT(kvm_ple_window_update, + TP_PROTO(unsigned int vcpu_id, unsigned int new, unsigned int old), + TP_ARGS(vcpu_id, new, old), TP_STRUCT__entry( - __field( bool, grow ) __field( unsigned int, vcpu_id ) - __field( int, new ) - __field( int, old ) + __field( unsigned int, new ) + __field( unsigned int, old ) ), TP_fast_assign( - __entry->grow = grow; __entry->vcpu_id = vcpu_id; __entry->new = new; __entry->old = old; ), - TP_printk("vcpu %u: ple_window %d (%s %d)", - __entry->vcpu_id, - __entry->new, - __entry->grow ? "grow" : "shrink", - __entry->old) + TP_printk("vcpu %u old %u new %u (%s)", + __entry->vcpu_id, __entry->old, __entry->new, + __entry->old < __entry->new ? "growed" : "shrinked") ); -#define trace_kvm_ple_window_grow(vcpu_id, new, old) \ - trace_kvm_ple_window(true, vcpu_id, new, old) -#define trace_kvm_ple_window_shrink(vcpu_id, new, old) \ - trace_kvm_ple_window(false, vcpu_id, new, old) - TRACE_EVENT(kvm_pvclock_update, TP_PROTO(unsigned int vcpu_id, struct pvclock_vcpu_time_info *pvclock), TP_ARGS(vcpu_id, pvclock), @@ -1297,6 +1291,25 @@ TRACE_EVENT(kvm_hv_stimer_cleanup, __entry->vcpu_id, __entry->timer_index) ); +TRACE_EVENT(kvm_apicv_update_request, + TP_PROTO(bool activate, unsigned long bit), + TP_ARGS(activate, bit), + + TP_STRUCT__entry( + __field(bool, activate) + __field(unsigned long, bit) + ), + + TP_fast_assign( + __entry->activate = activate; + __entry->bit = bit; + ), + + TP_printk("%s bit=%lu", + __entry->activate ? "activate" : "deactivate", + __entry->bit) +); + /* * Tracepoint for AMD AVIC */ @@ -1320,7 +1333,7 @@ TRACE_EVENT(kvm_avic_incomplete_ipi, __entry->index = index; ), - TP_printk("vcpu=%u, icrh:icrl=%#010x:%08x, id=%u, index=%u\n", + TP_printk("vcpu=%u, icrh:icrl=%#010x:%08x, id=%u, index=%u", __entry->vcpu, __entry->icrh, __entry->icrl, __entry->id, __entry->index) ); @@ -1345,7 +1358,7 @@ TRACE_EVENT(kvm_avic_unaccelerated_access, __entry->vec = vec; ), - TP_printk("vcpu=%u, offset=%#x(%s), %s, %s, vec=%#x\n", + TP_printk("vcpu=%u, offset=%#x(%s), %s, %s, vec=%#x", __entry->vcpu, __entry->offset, __print_symbolic(__entry->offset, kvm_trace_symbol_apic), @@ -1462,6 +1475,46 @@ TRACE_EVENT(kvm_hv_send_ipi_ex, __entry->vector, __entry->format, __entry->valid_bank_mask) ); + +TRACE_EVENT(kvm_pv_tlb_flush, + TP_PROTO(unsigned int vcpu_id, bool need_flush_tlb), + TP_ARGS(vcpu_id, need_flush_tlb), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( bool, need_flush_tlb ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->need_flush_tlb = need_flush_tlb; + ), + + TP_printk("vcpu %u need_flush_tlb %s", __entry->vcpu_id, + __entry->need_flush_tlb ? "true" : "false") +); + +/* + * Tracepoint for failed nested VMX VM-Enter. + */ +TRACE_EVENT(kvm_nested_vmenter_failed, + TP_PROTO(const char *msg, u32 err), + TP_ARGS(msg, err), + + TP_STRUCT__entry( + __field(const char *, msg) + __field(u32, err) + ), + + TP_fast_assign( + __entry->msg = msg; + __entry->err = err; + ), + + TP_printk("%s%s", __entry->msg, !__entry->err ? "" : + __print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS)) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index d6664ee3d127..283bdb7071af 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -145,6 +145,11 @@ static inline bool vmx_umip_emulated(void) SECONDARY_EXEC_DESC; } +static inline bool vmx_pku_supported(void) +{ + return boot_cpu_has(X86_FEATURE_PKU); +} + static inline bool cpu_has_vmx_rdtscp(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -247,6 +252,12 @@ static inline bool vmx_xsaves_supported(void) SECONDARY_EXEC_XSAVES; } +static inline bool vmx_waitpkg_supported(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; +} + static inline bool cpu_has_vmx_tsc_scaling(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 72359709cdc1..303813423c3e 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -7,6 +7,7 @@ #include "evmcs.h" #include "vmcs.h" #include "vmx.h" +#include "trace.h" DEFINE_STATIC_KEY_FALSE(enable_evmcs); @@ -346,26 +347,93 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) return 0; } +void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) +{ + u32 ctl_low = (u32)*pdata; + u32 ctl_high = (u32)(*pdata >> 32); + + /* + * Hyper-V 2016 and 2019 try using these features even when eVMCS + * is enabled but there are no corresponding fields. + */ + switch (msr_index) { + case MSR_IA32_VMX_EXIT_CTLS: + case MSR_IA32_VMX_TRUE_EXIT_CTLS: + ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + break; + case MSR_IA32_VMX_ENTRY_CTLS: + case MSR_IA32_VMX_TRUE_ENTRY_CTLS: + ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + break; + case MSR_IA32_VMX_PROCBASED_CTLS2: + ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + break; + } + + *pdata = ctl_low | ((u64)ctl_high << 32); +} + +int nested_evmcs_check_controls(struct vmcs12 *vmcs12) +{ + int ret = 0; + u32 unsupp_ctl; + + unsupp_ctl = vmcs12->pin_based_vm_exec_control & + EVMCS1_UNSUPPORTED_PINCTRL; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported pin-based VM-execution controls", + unsupp_ctl); + ret = -EINVAL; + } + + unsupp_ctl = vmcs12->secondary_vm_exec_control & + EVMCS1_UNSUPPORTED_2NDEXEC; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported secondary VM-execution controls", + unsupp_ctl); + ret = -EINVAL; + } + + unsupp_ctl = vmcs12->vm_exit_controls & + EVMCS1_UNSUPPORTED_VMEXIT_CTRL; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported VM-exit controls", + unsupp_ctl); + ret = -EINVAL; + } + + unsupp_ctl = vmcs12->vm_entry_controls & + EVMCS1_UNSUPPORTED_VMENTRY_CTRL; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported VM-entry controls", + unsupp_ctl); + ret = -EINVAL; + } + + unsupp_ctl = vmcs12->vm_function_control & EVMCS1_UNSUPPORTED_VMFUNC; + if (unsupp_ctl) { + trace_kvm_nested_vmenter_failed( + "eVMCS: unsupported VM-function controls", + unsupp_ctl); + ret = -EINVAL; + } + + return ret; +} + int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { struct vcpu_vmx *vmx = to_vmx(vcpu); - bool evmcs_already_enabled = vmx->nested.enlightened_vmcs_enabled; vmx->nested.enlightened_vmcs_enabled = true; if (vmcs_version) *vmcs_version = nested_get_evmcs_version(vcpu); - /* We don't support disabling the feature for simplicity. */ - if (evmcs_already_enabled) - return 0; - - vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; - vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; - vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; - vmx->nested.msrs.secondary_ctls_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; - vmx->nested.msrs.vmfunc_controls &= ~EVMCS1_UNSUPPORTED_VMFUNC; - return 0; } diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 39a24eec8884..6de47f2569c9 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -10,6 +10,7 @@ #include "capabilities.h" #include "vmcs.h" +#include "vmcs12.h" struct vmcs_config; @@ -178,6 +179,8 @@ static inline void evmcs_load(u64 phys_addr) struct hv_vp_assist_page *vp_ap = hv_get_vp_assist_page(smp_processor_id()); + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) + vp_ap->nested_control.features.directhypercall = 1; vp_ap->current_nested_vmcs = phys_addr; vp_ap->enlighten_vmentry = 1; } @@ -199,5 +202,7 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); +void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata); +int nested_evmcs_check_controls(struct vmcs12 *vmcs12); #endif /* __KVM_X86_VMX_EVMCS_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index ced9fba32598..3589cd3c0fcc 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -10,6 +10,7 @@ #include "hyperv.h" #include "mmu.h" #include "nested.h" +#include "pmu.h" #include "trace.h" #include "x86.h" @@ -19,6 +20,14 @@ module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); static bool __read_mostly nested_early_check = 0; module_param(nested_early_check, bool, S_IRUGO); +#define CC(consistency_check) \ +({ \ + bool failed = (consistency_check); \ + if (failed) \ + trace_kvm_nested_vmenter_failed(#consistency_check, 0); \ + failed; \ +}) + /* * Hyper-V requires all of these, so mark them as supported even though * they are just treated the same as all-context. @@ -190,6 +199,16 @@ static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator) pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator); } +static inline bool vmx_control_verify(u32 control, u32 low, u32 high) +{ + return fixed_bits_valid(control, low, high); +} + +static inline u64 vmx_control_msr(u32 low, u32 high) +{ + return low | ((u64)high << 32); +} + static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) { secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS); @@ -239,7 +258,7 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->nested.cached_shadow_vmcs12 = NULL; /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { - kvm_release_page_dirty(vmx->nested.apic_access_page); + kvm_release_page_clean(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; } kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true); @@ -430,8 +449,8 @@ static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) return 0; - if (!page_address_valid(vcpu, vmcs12->io_bitmap_a) || - !page_address_valid(vcpu, vmcs12->io_bitmap_b)) + if (CC(!page_address_valid(vcpu, vmcs12->io_bitmap_a)) || + CC(!page_address_valid(vcpu, vmcs12->io_bitmap_b))) return -EINVAL; return 0; @@ -443,7 +462,7 @@ static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return 0; - if (!page_address_valid(vcpu, vmcs12->msr_bitmap)) + if (CC(!page_address_valid(vcpu, vmcs12->msr_bitmap))) return -EINVAL; return 0; @@ -455,7 +474,7 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) return 0; - if (!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr)) + if (CC(!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))) return -EINVAL; return 0; @@ -525,7 +544,8 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { +static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) +{ int msr; for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { @@ -688,7 +708,7 @@ static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && - !page_address_valid(vcpu, vmcs12->apic_access_addr)) + CC(!page_address_valid(vcpu, vmcs12->apic_access_addr))) return -EINVAL; else return 0; @@ -707,16 +727,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, * If virtualize x2apic mode is enabled, * virtualize apic access must be disabled. */ - if (nested_cpu_has_virt_x2apic_mode(vmcs12) && - nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) + if (CC(nested_cpu_has_virt_x2apic_mode(vmcs12) && + nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))) return -EINVAL; /* * If virtual interrupt delivery is enabled, * we must exit on external interrupts. */ - if (nested_cpu_has_vid(vmcs12) && - !nested_exit_on_intr(vcpu)) + if (CC(nested_cpu_has_vid(vmcs12) && !nested_exit_on_intr(vcpu))) return -EINVAL; /* @@ -727,15 +746,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, * bits 5:0 of posted_intr_desc_addr should be zero. */ if (nested_cpu_has_posted_intr(vmcs12) && - (!nested_cpu_has_vid(vmcs12) || - !nested_exit_intr_ack_set(vcpu) || - (vmcs12->posted_intr_nv & 0xff00) || - (vmcs12->posted_intr_desc_addr & 0x3f) || - (vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu)))) + (CC(!nested_cpu_has_vid(vmcs12)) || + CC(!nested_exit_intr_ack_set(vcpu)) || + CC((vmcs12->posted_intr_nv & 0xff00)) || + CC((vmcs12->posted_intr_desc_addr & 0x3f)) || + CC((vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu))))) return -EINVAL; /* tpr shadow is needed by all apicv features. */ - if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) + if (CC(!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))) return -EINVAL; return 0; @@ -759,10 +778,12 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, static int nested_vmx_check_exit_msr_switch_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - if (nested_vmx_check_msr_switch(vcpu, vmcs12->vm_exit_msr_load_count, - vmcs12->vm_exit_msr_load_addr) || - nested_vmx_check_msr_switch(vcpu, vmcs12->vm_exit_msr_store_count, - vmcs12->vm_exit_msr_store_addr)) + if (CC(nested_vmx_check_msr_switch(vcpu, + vmcs12->vm_exit_msr_load_count, + vmcs12->vm_exit_msr_load_addr)) || + CC(nested_vmx_check_msr_switch(vcpu, + vmcs12->vm_exit_msr_store_count, + vmcs12->vm_exit_msr_store_addr))) return -EINVAL; return 0; @@ -771,8 +792,9 @@ static int nested_vmx_check_exit_msr_switch_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_entry_msr_switch_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - if (nested_vmx_check_msr_switch(vcpu, vmcs12->vm_entry_msr_load_count, - vmcs12->vm_entry_msr_load_addr)) + if (CC(nested_vmx_check_msr_switch(vcpu, + vmcs12->vm_entry_msr_load_count, + vmcs12->vm_entry_msr_load_addr))) return -EINVAL; return 0; @@ -784,8 +806,8 @@ static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has_pml(vmcs12)) return 0; - if (!nested_cpu_has_ept(vmcs12) || - !page_address_valid(vcpu, vmcs12->pml_address)) + if (CC(!nested_cpu_has_ept(vmcs12)) || + CC(!page_address_valid(vcpu, vmcs12->pml_address))) return -EINVAL; return 0; @@ -794,8 +816,8 @@ static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_unrestricted_guest_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST) && - !nested_cpu_has_ept(vmcs12)) + if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST) && + !nested_cpu_has_ept(vmcs12))) return -EINVAL; return 0; } @@ -803,8 +825,8 @@ static int nested_vmx_check_unrestricted_guest_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_mode_based_ept_exec_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_MODE_BASED_EPT_EXEC) && - !nested_cpu_has_ept(vmcs12)) + if (CC(nested_cpu_has2(vmcs12, SECONDARY_EXEC_MODE_BASED_EPT_EXEC) && + !nested_cpu_has_ept(vmcs12))) return -EINVAL; return 0; } @@ -815,8 +837,8 @@ static int nested_vmx_check_shadow_vmcs_controls(struct kvm_vcpu *vcpu, if (!nested_cpu_has_shadow_vmcs(vmcs12)) return 0; - if (!page_address_valid(vcpu, vmcs12->vmread_bitmap) || - !page_address_valid(vcpu, vmcs12->vmwrite_bitmap)) + if (CC(!page_address_valid(vcpu, vmcs12->vmread_bitmap)) || + CC(!page_address_valid(vcpu, vmcs12->vmwrite_bitmap))) return -EINVAL; return 0; @@ -826,12 +848,12 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { /* x2APIC MSR accesses are not allowed */ - if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8) + if (CC(vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)) return -EINVAL; - if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */ - e->index == MSR_IA32_UCODE_REV) + if (CC(e->index == MSR_IA32_UCODE_WRITE) || /* SDM Table 35-2 */ + CC(e->index == MSR_IA32_UCODE_REV)) return -EINVAL; - if (e->reserved != 0) + if (CC(e->reserved != 0)) return -EINVAL; return 0; } @@ -839,9 +861,9 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { - if (e->index == MSR_FS_BASE || - e->index == MSR_GS_BASE || - e->index == MSR_IA32_SMM_MONITOR_CTL || /* SMM is not supported */ + if (CC(e->index == MSR_FS_BASE) || + CC(e->index == MSR_GS_BASE) || + CC(e->index == MSR_IA32_SMM_MONITOR_CTL) || /* SMM is not supported */ nested_vmx_msr_check_common(vcpu, e)) return -EINVAL; return 0; @@ -850,24 +872,40 @@ static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu, static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { - if (e->index == MSR_IA32_SMBASE || /* SMM is not supported */ + if (CC(e->index == MSR_IA32_SMBASE) || /* SMM is not supported */ nested_vmx_msr_check_common(vcpu, e)) return -EINVAL; return 0; } +static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low, + vmx->nested.msrs.misc_high); + + return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER; +} + /* * Load guest's/host's msr at nested entry/exit. * return 0 for success, entry index for failure. + * + * One of the failure modes for MSR load/store is when a list exceeds the + * virtual hardware's capacity. To maintain compatibility with hardware inasmuch + * as possible, process all valid entries before failing rather than precheck + * for a capacity violation. */ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) { u32 i; struct vmx_msr_entry e; - struct msr_data msr; + u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); - msr.host_initiated = false; for (i = 0; i < count; i++) { + if (unlikely(i >= max_msr_list_size)) + goto fail; + if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), &e, sizeof(e))) { pr_debug_ratelimited( @@ -881,9 +919,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); goto fail; } - msr.index = e.index; - msr.data = e.value; - if (kvm_set_msr(vcpu, &msr)) { + if (kvm_set_msr(vcpu, e.index, e.value)) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, e.value); @@ -895,48 +931,141 @@ fail: return i + 1; } +static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu, + u32 msr_index, + u64 *data) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * If the L0 hypervisor stored a more accurate value for the TSC that + * does not include the time taken for emulation of the L2->L1 + * VM-exit in L0, use the more accurate value. + */ + if (msr_index == MSR_IA32_TSC) { + int index = vmx_find_msr_index(&vmx->msr_autostore.guest, + MSR_IA32_TSC); + + if (index >= 0) { + u64 val = vmx->msr_autostore.guest.val[index].value; + + *data = kvm_read_l1_tsc(vcpu, val); + return true; + } + } + + if (kvm_get_msr(vcpu, msr_index, data)) { + pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__, + msr_index); + return false; + } + return true; +} + +static bool read_and_check_msr_entry(struct kvm_vcpu *vcpu, u64 gpa, int i, + struct vmx_msr_entry *e) +{ + if (kvm_vcpu_read_guest(vcpu, + gpa + i * sizeof(*e), + e, 2 * sizeof(u32))) { + pr_debug_ratelimited( + "%s cannot read MSR entry (%u, 0x%08llx)\n", + __func__, i, gpa + i * sizeof(*e)); + return false; + } + if (nested_vmx_store_msr_check(vcpu, e)) { + pr_debug_ratelimited( + "%s check failed (%u, 0x%x, 0x%x)\n", + __func__, i, e->index, e->reserved); + return false; + } + return true; +} + static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) { + u64 data; u32 i; struct vmx_msr_entry e; + u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); for (i = 0; i < count; i++) { - struct msr_data msr_info; - if (kvm_vcpu_read_guest(vcpu, - gpa + i * sizeof(e), - &e, 2 * sizeof(u32))) { - pr_debug_ratelimited( - "%s cannot read MSR entry (%u, 0x%08llx)\n", - __func__, i, gpa + i * sizeof(e)); + if (unlikely(i >= max_msr_list_size)) return -EINVAL; - } - if (nested_vmx_store_msr_check(vcpu, &e)) { - pr_debug_ratelimited( - "%s check failed (%u, 0x%x, 0x%x)\n", - __func__, i, e.index, e.reserved); + + if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) return -EINVAL; - } - msr_info.host_initiated = false; - msr_info.index = e.index; - if (kvm_get_msr(vcpu, &msr_info)) { - pr_debug_ratelimited( - "%s cannot read MSR (%u, 0x%x)\n", - __func__, i, e.index); + + if (!nested_vmx_get_vmexit_msr_value(vcpu, e.index, &data)) return -EINVAL; - } + if (kvm_vcpu_write_guest(vcpu, gpa + i * sizeof(e) + offsetof(struct vmx_msr_entry, value), - &msr_info.data, sizeof(msr_info.data))) { + &data, sizeof(data))) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", - __func__, i, e.index, msr_info.data); + __func__, i, e.index, data); return -EINVAL; } } return 0; } +static bool nested_msr_store_list_has_msr(struct kvm_vcpu *vcpu, u32 msr_index) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + u32 count = vmcs12->vm_exit_msr_store_count; + u64 gpa = vmcs12->vm_exit_msr_store_addr; + struct vmx_msr_entry e; + u32 i; + + for (i = 0; i < count; i++) { + if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) + return false; + + if (e.index == msr_index) + return true; + } + return false; +} + +static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, + u32 msr_index) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmx_msrs *autostore = &vmx->msr_autostore.guest; + bool in_vmcs12_store_list; + int msr_autostore_index; + bool in_autostore_list; + int last; + + msr_autostore_index = vmx_find_msr_index(autostore, msr_index); + in_autostore_list = msr_autostore_index >= 0; + in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index); + + if (in_vmcs12_store_list && !in_autostore_list) { + if (autostore->nr == NR_LOADSTORE_MSRS) { + /* + * Emulated VMEntry does not fail here. Instead a less + * accurate value will be returned by + * nested_vmx_get_vmexit_msr_value() using kvm_get_msr() + * instead of reading the value from the vmcs02 VMExit + * MSR-store area. + */ + pr_warn_ratelimited( + "Not enough msr entries in msr_autostore. Can't add msr %x\n", + msr_index); + return; + } + last = autostore->nr++; + autostore->val[last].index = msr_index; + } else if (!in_vmcs12_store_list && in_autostore_list) { + last = --autostore->nr; + autostore->val[msr_autostore_index] = autostore->val[last]; + } +} + static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) { unsigned long invalid_mask; @@ -946,16 +1075,16 @@ static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) } /* - * Load guest's/host's cr3 at nested entry/exit. nested_ept is true if we are - * emulating VM entry into a guest with EPT enabled. - * Returns 0 on success, 1 on failure. Invalid state exit qualification code - * is assigned to entry_failure_code on failure. + * Load guest's/host's cr3 at nested entry/exit. @nested_ept is true if we are + * emulating VM-Entry into a guest with EPT enabled. On failure, the expected + * Exit Qualification (for a VM-Entry consistency check VM-Exit) is assigned to + * @entry_failure_code. */ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, u32 *entry_failure_code) { if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) { - if (!nested_cr3_valid(vcpu, cr3)) { + if (CC(!nested_cr3_valid(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -965,7 +1094,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * must not be dereferenced. */ if (is_pae_paging(vcpu) && !nested_ept) { - if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) { + if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { *entry_failure_code = ENTRY_FAIL_PDPTE; return -EINVAL; } @@ -976,7 +1105,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne kvm_mmu_new_cr3(vcpu, cr3, false); vcpu->arch.cr3 = cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_init_mmu(vcpu, false); @@ -988,7 +1117,9 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * populated by L2 differently than TLB entries populated * by L1. * - * If L1 uses EPT, then TLB entries are tagged with different EPTP. + * If L0 uses EPT, L1 and L2 run with different EPTP because + * guest_mode is part of kvm_mmu_page_role. Thus, TLB entries + * are tagged with different EPTP. * * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged * with different VPID (L1 entries are tagged with vmx->vpid @@ -998,7 +1129,7 @@ static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - return nested_cpu_has_ept(vmcs12) || + return enable_ept || (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02); } @@ -1009,17 +1140,6 @@ static u16 nested_get_vpid02(struct kvm_vcpu *vcpu) return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid; } - -static inline bool vmx_control_verify(u32 control, u32 low, u32 high) -{ - return fixed_bits_valid(control, low, high); -} - -static inline u64 vmx_control_msr(u32 low, u32 high) -{ - return low | ((u64)high << 32); -} - static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) { superset &= mask; @@ -1862,7 +1982,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, } /* - * Clean fields data can't de used on VMLAUNCH and when we switch + * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ if (from_launch || evmcs_gpa_changed) @@ -1993,7 +2113,7 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) * addresses are constant (for vmcs02), the counts can change based * on L2's behavior, e.g. switching to/from long mode. */ - vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); + vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val)); vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); @@ -2043,11 +2163,12 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * EXEC CONTROLS */ exec_control = vmx_exec_control(vmx); /* L0's desires */ - exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; - exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING; + exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING; + exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING; exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; + vmx->nested.l1_tpr_threshold = -1; if (exec_control & CPU_BASED_TPR_SHADOW) vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); #ifdef CONFIG_X86_64 @@ -2085,6 +2206,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC); @@ -2259,6 +2381,13 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3); } + /* + * Make sure the msr_autostore list is up to date before we set the + * count in the vmcs02. + */ + prepare_vmx_msr_autostore_list(&vmx->vcpu, MSR_IA32_TSC); + + vmcs_write32(VM_EXIT_MSR_STORE_COUNT, vmx->msr_autostore.guest.nr); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); @@ -2355,9 +2484,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (nested_cpu_has_ept(vmcs12)) nested_ept_init_mmu_context(vcpu); - else if (nested_cpu_has2(vmcs12, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) - vmx_flush_tlb(vcpu, true); /* * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those @@ -2392,6 +2518,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, entry_failure_code)) return -EINVAL; + /* + * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 + * on nested VM-Exit, which can occur without actually running L2 and + * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with + * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the + * transition to HLT instead of running L2. + */ + if (enable_ept) + vmcs_writel(GUEST_CR3, vmcs12->guest_cr3); + /* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */ if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { @@ -2404,6 +2540,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && + WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->guest_ia32_perf_global_ctrl))) + return -EINVAL; + kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); return 0; @@ -2411,12 +2552,12 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12) { - if (!nested_cpu_has_nmi_exiting(vmcs12) && - nested_cpu_has_virtual_nmis(vmcs12)) + if (CC(!nested_cpu_has_nmi_exiting(vmcs12) && + nested_cpu_has_virtual_nmis(vmcs12))) return -EINVAL; - if (!nested_cpu_has_virtual_nmis(vmcs12) && - nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING)) + if (CC(!nested_cpu_has_virtual_nmis(vmcs12) && + nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING))) return -EINVAL; return 0; @@ -2430,11 +2571,11 @@ static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address) /* Check for memory type validity */ switch (address & VMX_EPTP_MT_MASK) { case VMX_EPTP_MT_UC: - if (!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT)) + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT))) return false; break; case VMX_EPTP_MT_WB: - if (!(vmx->nested.msrs.ept_caps & VMX_EPTP_WB_BIT)) + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_WB_BIT))) return false; break; default: @@ -2442,16 +2583,16 @@ static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address) } /* only 4 levels page-walk length are valid */ - if ((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4) + if (CC((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4)) return false; /* Reserved bits should not be set */ - if (address >> maxphyaddr || ((address >> 7) & 0x1f)) + if (CC(address >> maxphyaddr || ((address >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ if (address & VMX_EPTP_AD_ENABLE_BIT) { - if (!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT)) + if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT))) return false; } @@ -2466,21 +2607,21 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx_control_verify(vmcs12->pin_based_vm_exec_control, - vmx->nested.msrs.pinbased_ctls_low, - vmx->nested.msrs.pinbased_ctls_high) || - !vmx_control_verify(vmcs12->cpu_based_vm_exec_control, - vmx->nested.msrs.procbased_ctls_low, - vmx->nested.msrs.procbased_ctls_high)) + if (CC(!vmx_control_verify(vmcs12->pin_based_vm_exec_control, + vmx->nested.msrs.pinbased_ctls_low, + vmx->nested.msrs.pinbased_ctls_high)) || + CC(!vmx_control_verify(vmcs12->cpu_based_vm_exec_control, + vmx->nested.msrs.procbased_ctls_low, + vmx->nested.msrs.procbased_ctls_high))) return -EINVAL; if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) && - !vmx_control_verify(vmcs12->secondary_vm_exec_control, - vmx->nested.msrs.secondary_ctls_low, - vmx->nested.msrs.secondary_ctls_high)) + CC(!vmx_control_verify(vmcs12->secondary_vm_exec_control, + vmx->nested.msrs.secondary_ctls_low, + vmx->nested.msrs.secondary_ctls_high))) return -EINVAL; - if (vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu) || + if (CC(vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu)) || nested_vmx_check_io_bitmap_controls(vcpu, vmcs12) || nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12) || nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12) || @@ -2491,7 +2632,7 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, nested_vmx_check_unrestricted_guest_controls(vcpu, vmcs12) || nested_vmx_check_mode_based_ept_exec_controls(vcpu, vmcs12) || nested_vmx_check_shadow_vmcs_controls(vcpu, vmcs12) || - (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)) + CC(nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)) return -EINVAL; if (!nested_cpu_has_preemption_timer(vmcs12) && @@ -2499,17 +2640,17 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, return -EINVAL; if (nested_cpu_has_ept(vmcs12) && - !valid_ept_address(vcpu, vmcs12->ept_pointer)) + CC(!valid_ept_address(vcpu, vmcs12->ept_pointer))) return -EINVAL; if (nested_cpu_has_vmfunc(vmcs12)) { - if (vmcs12->vm_function_control & - ~vmx->nested.msrs.vmfunc_controls) + if (CC(vmcs12->vm_function_control & + ~vmx->nested.msrs.vmfunc_controls)) return -EINVAL; if (nested_cpu_has_eptp_switching(vmcs12)) { - if (!nested_cpu_has_ept(vmcs12) || - !page_address_valid(vcpu, vmcs12->eptp_list_address)) + if (CC(!nested_cpu_has_ept(vmcs12)) || + CC(!page_address_valid(vcpu, vmcs12->eptp_list_address))) return -EINVAL; } } @@ -2525,10 +2666,10 @@ static int nested_check_vm_exit_controls(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx_control_verify(vmcs12->vm_exit_controls, - vmx->nested.msrs.exit_ctls_low, - vmx->nested.msrs.exit_ctls_high) || - nested_vmx_check_exit_msr_switch_controls(vcpu, vmcs12)) + if (CC(!vmx_control_verify(vmcs12->vm_exit_controls, + vmx->nested.msrs.exit_ctls_low, + vmx->nested.msrs.exit_ctls_high)) || + CC(nested_vmx_check_exit_msr_switch_controls(vcpu, vmcs12))) return -EINVAL; return 0; @@ -2542,9 +2683,9 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx_control_verify(vmcs12->vm_entry_controls, - vmx->nested.msrs.entry_ctls_low, - vmx->nested.msrs.entry_ctls_high)) + if (CC(!vmx_control_verify(vmcs12->vm_entry_controls, + vmx->nested.msrs.entry_ctls_low, + vmx->nested.msrs.entry_ctls_high))) return -EINVAL; /* @@ -2564,31 +2705,31 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE; /* VM-entry interruption-info field: interruption type */ - if (intr_type == INTR_TYPE_RESERVED || - (intr_type == INTR_TYPE_OTHER_EVENT && - !nested_cpu_supports_monitor_trap_flag(vcpu))) + if (CC(intr_type == INTR_TYPE_RESERVED) || + CC(intr_type == INTR_TYPE_OTHER_EVENT && + !nested_cpu_supports_monitor_trap_flag(vcpu))) return -EINVAL; /* VM-entry interruption-info field: vector */ - if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) || - (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) || - (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) + if (CC(intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) || + CC(intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) || + CC(intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) return -EINVAL; /* VM-entry interruption-info field: deliver error code */ should_have_error_code = intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode && x86_exception_has_error_code(vector); - if (has_error_code != should_have_error_code) + if (CC(has_error_code != should_have_error_code)) return -EINVAL; /* VM-entry exception error code */ - if (has_error_code && - vmcs12->vm_entry_exception_error_code & GENMASK(31, 15)) + if (CC(has_error_code && + vmcs12->vm_entry_exception_error_code & GENMASK(31, 16))) return -EINVAL; /* VM-entry interruption-info field: reserved bits */ - if (intr_info & INTR_INFO_RESVD_BITS_MASK) + if (CC(intr_info & INTR_INFO_RESVD_BITS_MASK)) return -EINVAL; /* VM-entry instruction length */ @@ -2596,9 +2737,9 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, case INTR_TYPE_SOFT_EXCEPTION: case INTR_TYPE_SOFT_INTR: case INTR_TYPE_PRIV_SW_EXCEPTION: - if ((vmcs12->vm_entry_instruction_len > 15) || - (vmcs12->vm_entry_instruction_len == 0 && - !nested_cpu_has_zero_length_injection(vcpu))) + if (CC(vmcs12->vm_entry_instruction_len > 15) || + CC(vmcs12->vm_entry_instruction_len == 0 && + CC(!nested_cpu_has_zero_length_injection(vcpu)))) return -EINVAL; } } @@ -2617,6 +2758,9 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; + if (to_vmx(vcpu)->nested.enlightened_vmcs_enabled) + return nested_evmcs_check_controls(vmcs12); + return 0; } @@ -2625,43 +2769,62 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, { bool ia32e; - if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) || - !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) || - !nested_cr3_valid(vcpu, vmcs12->host_cr3)) + if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || + CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || + CC(!nested_cr3_valid(vcpu, vmcs12->host_cr3))) return -EINVAL; - if (is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu) || - is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu)) + if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))) return -EINVAL; if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) && - !kvm_pat_valid(vmcs12->host_ia32_pat)) + CC(!kvm_pat_valid(vmcs12->host_ia32_pat))) return -EINVAL; - ia32e = (vmcs12->vm_exit_controls & - VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0; - - if (vmcs12->host_cs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_ss_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_ds_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_es_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_fs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_gs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_tr_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || - vmcs12->host_cs_selector == 0 || - vmcs12->host_tr_selector == 0 || - (vmcs12->host_ss_selector == 0 && !ia32e)) + if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) && + CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu), + vmcs12->host_ia32_perf_global_ctrl))) return -EINVAL; #ifdef CONFIG_X86_64 - if (is_noncanonical_address(vmcs12->host_fs_base, vcpu) || - is_noncanonical_address(vmcs12->host_gs_base, vcpu) || - is_noncanonical_address(vmcs12->host_gdtr_base, vcpu) || - is_noncanonical_address(vmcs12->host_idtr_base, vcpu) || - is_noncanonical_address(vmcs12->host_tr_base, vcpu)) - return -EINVAL; + ia32e = !!(vcpu->arch.efer & EFER_LMA); +#else + ia32e = false; #endif + if (ia32e) { + if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) || + CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) + return -EINVAL; + } else { + if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) || + CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || + CC(vmcs12->host_cr4 & X86_CR4_PCIDE) || + CC((vmcs12->host_rip) >> 32)) + return -EINVAL; + } + + if (CC(vmcs12->host_cs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_ss_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_ds_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_es_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_fs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_gs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_tr_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK)) || + CC(vmcs12->host_cs_selector == 0) || + CC(vmcs12->host_tr_selector == 0) || + CC(vmcs12->host_ss_selector == 0 && !ia32e)) + return -EINVAL; + + if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_rip, vcpu))) + return -EINVAL; + /* * If the load IA32_EFER VM-exit control is 1, bits reserved in the * IA32_EFER MSR must be 0 in the field for that register. In addition, @@ -2669,9 +2832,9 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, * the host address-space size VM-exit control. */ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) { - if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) || - ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) || - ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) + if (CC(!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer)) || + CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA)) || + CC(ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))) return -EINVAL; } @@ -2688,16 +2851,16 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, if (vmcs12->vmcs_link_pointer == -1ull) return 0; - if (!page_address_valid(vcpu, vmcs12->vmcs_link_pointer)) + if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer))) return -EINVAL; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)) + if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))) return -EINVAL; shadow = map.hva; - if (shadow->hdr.revision_id != VMCS12_REVISION || - shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)) + if (CC(shadow->hdr.revision_id != VMCS12_REVISION) || + CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))) r = -EINVAL; kvm_vcpu_unmap(vcpu, &map, false); @@ -2709,8 +2872,8 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, */ static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12) { - if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && - vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) + if (CC(vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && + vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)) return -EINVAL; return 0; @@ -2724,12 +2887,16 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, *exit_qual = ENTRY_FAIL_DEFAULT; - if (!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0) || - !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) + if (CC(!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0)) || + CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))) + return -EINVAL; + + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && + CC(!kvm_dr7_valid(vmcs12->guest_dr7))) return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && - !kvm_pat_valid(vmcs12->guest_ia32_pat)) + CC(!kvm_pat_valid(vmcs12->guest_ia32_pat))) return -EINVAL; if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) { @@ -2737,6 +2904,11 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, return -EINVAL; } + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && + CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu), + vmcs12->guest_ia32_perf_global_ctrl))) + return -EINVAL; + /* * If the load IA32_EFER VM-entry control is 1, the following checks * are performed on the field for the IA32_EFER MSR: @@ -2749,16 +2921,16 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, if (to_vmx(vcpu)->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; - if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) || - ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) || - ((vmcs12->guest_cr0 & X86_CR0_PG) && - ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) + if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) || + CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) || + CC(((vmcs12->guest_cr0 & X86_CR0_PG) && + ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME)))) return -EINVAL; } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) && - (is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) || - (vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD))) + (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || + CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))) return -EINVAL; if (nested_check_guest_non_reg_state(vmcs12)) @@ -2841,9 +3013,13 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); if (vm_fail) { + u32 error = vmcs_read32(VM_INSTRUCTION_ERROR); + preempt_enable(); - WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) != - VMXERR_ENTRY_INVALID_CONTROL_FIELD); + + trace_kvm_nested_vmenter_failed( + "early hardware check VM-instruction error: ", error); + WARN_ON_ONCE(error != VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } @@ -2868,10 +3044,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } -static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12); - -static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -2887,23 +3060,22 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * to it so we can release it later. */ if (vmx->nested.apic_access_page) { /* shouldn't happen */ - kvm_release_page_dirty(vmx->nested.apic_access_page); + kvm_release_page_clean(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; } page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr); - /* - * If translation failed, no matter: This feature asks - * to exit when accessing the given address, and if it - * can never be accessed, this feature won't do - * anything anyway. - */ if (!is_error_page(page)) { vmx->nested.apic_access_page = page; hpa = page_to_phys(vmx->nested.apic_access_page); vmcs_write64(APIC_ACCESS_ADDR, hpa); } else { - secondary_exec_controls_clearbit(vmx, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + pr_debug_ratelimited("%s: no backing 'struct page' for APIC-access address in vmcs12\n", + __func__); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; } } @@ -2948,6 +3120,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS); else exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS); + return true; } /* @@ -2986,13 +3159,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, /* * If from_vmentry is false, this is being called from state restore (either RSM * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. -+ * -+ * Returns: -+ * 0 - success, i.e. proceed with actual VMEnter -+ * 1 - consistency check VMExit -+ * -1 - consistency check VMFail + * + * Returns: + * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode + * NVMX_ENTRY_VMFAIL: Consistency check VMFail + * NVMX_ENTRY_VMEXIT: Consistency check VMExit + * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error */ -int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) +enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, + bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -3001,7 +3176,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) u32 exit_qual; evaluate_pending_interrupts = exec_controls_get(vmx) & - (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING); + (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); @@ -3035,11 +3210,12 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) prepare_vmcs02_early(vmx, vmcs12); if (from_vmentry) { - nested_get_vmcs12_pages(vcpu); + if (unlikely(!nested_get_vmcs12_pages(vcpu))) + return NVMX_VMENTRY_KVM_INTERNAL_ERROR; if (nested_vmx_check_vmentry_hw(vcpu)) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); - return -1; + return NVMX_VMENTRY_VMFAIL; } if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual)) @@ -3047,7 +3223,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) } enter_guest_mode(vcpu); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset += vmcs12->tsc_offset; if (prepare_vmcs02(vcpu, vmcs12, &exit_qual)) @@ -3103,7 +3279,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) * returned as far as L1 is concerned. It will only return (and set * the success flag) when L2 exits (see nested_vmx_vmexit()). */ - return 0; + return NVMX_VMENTRY_SUCCESS; /* * A failed consistency check that leads to a VMExit during L1's @@ -3111,7 +3287,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) * 26.7 "VM-entry failures during or after loading guest state". */ vmentry_fail_vmexit_guest_mode: - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; leave_guest_mode(vcpu); @@ -3119,14 +3295,14 @@ vmentry_fail_vmexit: vmx_switch_vmcs(vcpu, &vmx->vmcs01); if (!from_vmentry) - return 1; + return NVMX_VMENTRY_VMEXIT; load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY; vmcs12->exit_qualification = exit_qual; if (enable_shadow_vmcs || vmx->nested.hv_evmcs) vmx->nested.need_vmcs12_to_shadow_sync = true; - return 1; + return NVMX_VMENTRY_VMEXIT; } /* @@ -3136,9 +3312,9 @@ vmentry_fail_vmexit: static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) { struct vmcs12 *vmcs12; + enum nvmx_vmentry_status status; struct vcpu_vmx *vmx = to_vmx(vcpu); u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); - int ret; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -3198,13 +3374,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * the nested entry. */ vmx->nested.nested_run_pending = 1; - ret = nested_vmx_enter_non_root_mode(vcpu, true); - vmx->nested.nested_run_pending = !ret; - if (ret > 0) - return 1; - else if (ret) - return nested_vmx_failValid(vcpu, - VMXERR_ENTRY_INVALID_CONTROL_FIELD); + status = nested_vmx_enter_non_root_mode(vcpu, true); + if (unlikely(status != NVMX_VMENTRY_SUCCESS)) + goto vmentry_failed; /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; @@ -3228,18 +3400,27 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) */ if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) && - !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_NMI_PENDING) && - !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_INTR_PENDING) && + !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_NMI_WINDOW_EXITING) && + !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; return kvm_vcpu_halt(vcpu); } return 1; + +vmentry_failed: + vmx->nested.nested_run_pending = 0; + if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR) + return 0; + if (status == NVMX_VMENTRY_VMEXIT) + return 1; + WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL); + return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); } /* * On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date - * because L2 may have changed some cr0 bits directly (CRO_GUEST_HOST_MASK). + * because L2 may have changed some cr0 bits directly (CR0_GUEST_HOST_MASK). * This function returns the new value we should put in vmcs12.guest_cr0. * It's not enough to just return the vmcs02 GUEST_CR0. Rather, * 1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now @@ -3395,12 +3576,50 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); } +/* + * Returns true if a debug trap is pending delivery. + * + * In KVM, debug traps bear an exception payload. As such, the class of a #DB + * exception may be inferred from the presence of an exception payload. + */ +static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.exception.pending && + vcpu->arch.exception.nr == DB_VECTOR && + vcpu->arch.exception.payload; +} + +/* + * Certain VM-exits set the 'pending debug exceptions' field to indicate a + * recognized #DB (data or single-step) that has yet to be delivered. Since KVM + * represents these debug traps with a payload that is said to be compatible + * with the 'pending debug exceptions' field, write the payload to the VMCS + * field if a VM-exit is delivered before the debug trap. + */ +static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) +{ + if (vmx_pending_dbg_trap(vcpu)) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vcpu->arch.exception.payload); +} + static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qual; bool block_nested_events = vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); + struct kvm_lapic *apic = vcpu->arch.apic; + + if (lapic_in_kernel(vcpu) && + test_bit(KVM_APIC_INIT, &apic->pending_events)) { + if (block_nested_events) + return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); + clear_bit(KVM_APIC_INIT, &apic->pending_events); + nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); + return 0; + } if (vcpu->arch.exception.pending && nested_vmx_check_exception(vcpu, &exit_qual)) { @@ -3801,8 +4020,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.pat = vmcs12->host_ia32_pat; } if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) - vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, - vmcs12->host_ia32_perf_global_ctrl); + WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->host_ia32_perf_global_ctrl)); /* Set L1 segment info according to Intel SDM 27.5.2 Loading Host Segment and Descriptor-Table Registers */ @@ -3889,7 +4108,6 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_msr_entry g, h; - struct msr_data msr; gpa_t gpa; u32 i, j; @@ -3922,7 +4140,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) nested_ept_uninit_mmu_context(vcpu); vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); /* * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs @@ -3949,7 +4167,6 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) * from the guest value. The intent is to stuff host state as * silently as possible, not to fully process the exit load list. */ - msr.host_initiated = false; for (i = 0; i < vmcs12->vm_entry_msr_load_count; i++) { gpa = vmcs12->vm_entry_msr_load_addr + (i * sizeof(g)); if (kvm_vcpu_read_guest(vcpu, gpa, &g, sizeof(g))) { @@ -3979,9 +4196,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) goto vmabort; } - msr.index = h.index; - msr.data = h.value; - if (kvm_set_msr(vcpu, &msr)) { + if (kvm_set_msr(vcpu, h.index, h.value)) { pr_debug_ratelimited( "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", __func__, j, h.index, h.value); @@ -4015,7 +4230,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, if (nested_cpu_has_preemption_timer(vmcs12)) hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; if (likely(!vmx->fail)) { @@ -4053,6 +4268,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + if (vmx->nested.l1_tpr_threshold != -1) + vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold); if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -4060,15 +4277,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, if (vmx->nested.change_vmcs01_virtual_apic_mode) { vmx->nested.change_vmcs01_virtual_apic_mode = false; vmx_set_virtual_apic_mode(vcpu); - } else if (!nested_cpu_has_ept(vmcs12) && - nested_cpu_has2(vmcs12, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - vmx_flush_tlb(vcpu, true); } /* Unpin physical memory we referred to in vmcs02 */ if (vmx->nested.apic_access_page) { - kvm_release_page_dirty(vmx->nested.apic_access_page); + kvm_release_page_clean(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; } kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true); @@ -4268,6 +4481,27 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, return 0; } +void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx; + + if (!nested_vmx_allowed(vcpu)) + return; + + vmx = to_vmx(vcpu); + if (kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) { + vmx->nested.msrs.entry_ctls_high |= + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + vmx->nested.msrs.exit_ctls_high |= + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + } else { + vmx->nested.msrs.entry_ctls_high &= + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + vmx->nested.msrs.exit_ctls_high &= + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + } +} + static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer) { gva_t gva; @@ -4375,8 +4609,8 @@ static int handle_vmon(struct kvm_vcpu *vcpu) gpa_t vmptr; uint32_t revision; struct vcpu_vmx *vmx = to_vmx(vcpu); - const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED - | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + const u64 VMXON_NEEDED_FEATURES = FEAT_CTL_LOCKED + | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; /* * The Intel VMX Instruction Reference lists a bunch of bits that are @@ -4466,7 +4700,12 @@ static int handle_vmoff(struct kvm_vcpu *vcpu) { if (!nested_vmx_check_permission(vcpu)) return 1; + free_nested(vcpu); + + /* Process a latched INIT during time CPU was in VMX operation */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + return nested_vmx_succeed(vcpu); } @@ -4516,8 +4755,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) return nested_vmx_succeed(vcpu); } -static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch); - /* Emulate the VMLAUNCH instruction */ static int handle_vmlaunch(struct kvm_vcpu *vcpu) { @@ -4533,35 +4770,32 @@ static int handle_vmresume(struct kvm_vcpu *vcpu) static int handle_vmread(struct kvm_vcpu *vcpu) { - unsigned long field; - u64 field_value; + struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) + : get_vmcs12(vcpu); unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - int len; + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct x86_exception e; + unsigned long field; + u64 value; gva_t gva = 0; - struct vmcs12 *vmcs12; short offset; + int len; if (!nested_vmx_check_permission(vcpu)) return 1; - if (to_vmx(vcpu)->nested.current_vmptr == -1ull) + /* + * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * any VMREAD sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == -1ull || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) return nested_vmx_failInvalid(vcpu); - if (!is_guest_mode(vcpu)) - vmcs12 = get_vmcs12(vcpu); - else { - /* - * When vmcs->vmcs_link_pointer is -1ull, any VMREAD - * to shadowed-field sets the ALU flags for VMfailInvalid. - */ - if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) - return nested_vmx_failInvalid(vcpu); - vmcs12 = get_shadow_vmcs12(vcpu); - } - /* Decode instruction info and find the field to read */ - field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); + field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf)); offset = vmcs_field_to_offset(field); if (offset < 0) @@ -4571,24 +4805,26 @@ static int handle_vmread(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - /* Read the field, zero-extended to a u64 field_value */ - field_value = vmcs12_read_any(vmcs12, field, offset); + /* Read the field, zero-extended to a u64 value */ + value = vmcs12_read_any(vmcs12, field, offset); /* * Now copy part of this value to register or memory, as requested. * Note that the number of bits actually copied is 32 or 64 depending * on the guest's mode (32 or 64 bit), not on the given field's length. */ - if (vmx_instruction_info & (1u << 10)) { - kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf), - field_value); + if (instr_info & BIT(10)) { + kvm_register_writel(vcpu, (((instr_info) >> 3) & 0xf), value); } else { len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, true, len, &gva)) + instr_info, true, len, &gva)) return 1; /* _system ok, nested_vmx_check_permission has verified cpl=0 */ - kvm_write_guest_virt_system(vcpu, gva, &field_value, len, NULL); + if (kvm_write_guest_virt_system(vcpu, gva, &value, len, &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } } return nested_vmx_succeed(vcpu); @@ -4620,46 +4856,58 @@ static bool is_shadow_field_ro(unsigned long field) static int handle_vmwrite(struct kvm_vcpu *vcpu) { + struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) + : get_vmcs12(vcpu); + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct x86_exception e; unsigned long field; - int len; + short offset; gva_t gva; - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + int len; - /* The value to write might be 32 or 64 bits, depending on L1's long + /* + * The value to write might be 32 or 64 bits, depending on L1's long * mode, and eventually we need to write that into a field of several * possible lengths. The code below first zero-extends the value to 64 - * bit (field_value), and then copies only the appropriate number of + * bit (value), and then copies only the appropriate number of * bits into the vmcs12 field. */ - u64 field_value = 0; - struct x86_exception e; - struct vmcs12 *vmcs12; - short offset; + u64 value = 0; if (!nested_vmx_check_permission(vcpu)) return 1; - if (vmx->nested.current_vmptr == -1ull) + /* + * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * any VMWRITE sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == -1ull || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) return nested_vmx_failInvalid(vcpu); - if (vmx_instruction_info & (1u << 10)) - field_value = kvm_register_readl(vcpu, - (((vmx_instruction_info) >> 3) & 0xf)); + if (instr_info & BIT(10)) + value = kvm_register_readl(vcpu, (((instr_info) >> 3) & 0xf)); else { len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, false, len, &gva)) + instr_info, false, len, &gva)) return 1; - if (kvm_read_guest_virt(vcpu, gva, &field_value, len, &e)) { + if (kvm_read_guest_virt(vcpu, gva, &value, len, &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } } + field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf)); + + offset = vmcs_field_to_offset(field); + if (offset < 0) + return nested_vmx_failValid(vcpu, + VMXERR_UNSUPPORTED_VMCS_COMPONENT); - field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); /* * If the vCPU supports "VMWRITE to any supported field in the * VMCS," then the "read-only" fields are actually read/write. @@ -4669,29 +4917,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return nested_vmx_failValid(vcpu, VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT); - if (!is_guest_mode(vcpu)) { - vmcs12 = get_vmcs12(vcpu); - - /* - * Ensure vmcs12 is up-to-date before any VMWRITE that dirties - * vmcs12, else we may crush a field or consume a stale value. - */ - if (!is_shadow_field_rw(field)) - copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - } else { - /* - * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE - * to shadowed-field sets the ALU flags for VMfailInvalid. - */ - if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) - return nested_vmx_failInvalid(vcpu); - vmcs12 = get_shadow_vmcs12(vcpu); - } - - offset = vmcs_field_to_offset(field); - if (offset < 0) - return nested_vmx_failValid(vcpu, - VMXERR_UNSUPPORTED_VMCS_COMPONENT); + /* + * Ensure vmcs12 is up-to-date before any VMWRITE that dirties + * vmcs12, else we may crush a field or consume a stale value. + */ + if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field)) + copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); /* * Some Intel CPUs intentionally drop the reserved bits of the AR byte @@ -4702,9 +4933,9 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) * the stripped down value, L2 sees the full value as stored by KVM). */ if (field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES) - field_value &= 0x1f0ff; + value &= 0x1f0ff; - vmcs12_write_any(vmcs12, field, offset, field_value); + vmcs12_write_any(vmcs12, field, offset, value); /* * Do not track vmcs12 dirty-state if in guest-mode as we actually @@ -4721,7 +4952,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) preempt_disable(); vmcs_load(vmx->vmcs01.shadow_vmcs); - __vmcs_writel(field, field_value); + __vmcs_writel(field, value); vmcs_clear(vmx->vmcs01.shadow_vmcs); vmcs_load(vmx->loaded_vmcs->vmcs); @@ -5259,8 +5490,9 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) return false; if (unlikely(vmx->fail)) { - pr_info_ratelimited("%s failed vm entry %x\n", __func__, - vmcs_read32(VM_INSTRUCTION_ERROR)); + trace_kvm_nested_vmenter_failed( + "hardware VM-instruction error: ", + vmcs_read32(VM_INSTRUCTION_ERROR)); return true; } @@ -5303,10 +5535,10 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) return false; case EXIT_REASON_TRIPLE_FAULT: return true; - case EXIT_REASON_PENDING_INTERRUPT: - return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); + case EXIT_REASON_INTERRUPT_WINDOW: + return nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING); case EXIT_REASON_NMI_WINDOW: - return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); + return nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING); case EXIT_REASON_TASK_SWITCH: return true; case EXIT_REASON_CPUID: @@ -5420,6 +5652,10 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_ENCLS: /* SGX is never exposed to L1 */ return false; + case EXIT_REASON_UMWAIT: + case EXIT_REASON_TPAUSE: + return nested_cpu_has2(vmcs12, + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE); default: return true; } @@ -5695,7 +5931,7 @@ error_guest_mode: return ret; } -void nested_vmx_vcpu_setup(void) +void nested_vmx_set_vmcs_shadowing_bitmap(void) { if (enable_shadow_vmcs) { vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap)); @@ -5790,8 +6026,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; msrs->procbased_ctls_high &= - CPU_BASED_VIRTUAL_INTR_PENDING | - CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING | CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING | CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | @@ -5976,23 +6212,23 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) init_vmcs_shadow_fields(); } - exit_handlers[EXIT_REASON_VMCLEAR] = handle_vmclear, - exit_handlers[EXIT_REASON_VMLAUNCH] = handle_vmlaunch, - exit_handlers[EXIT_REASON_VMPTRLD] = handle_vmptrld, - exit_handlers[EXIT_REASON_VMPTRST] = handle_vmptrst, - exit_handlers[EXIT_REASON_VMREAD] = handle_vmread, - exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume, - exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite, - exit_handlers[EXIT_REASON_VMOFF] = handle_vmoff, - exit_handlers[EXIT_REASON_VMON] = handle_vmon, - exit_handlers[EXIT_REASON_INVEPT] = handle_invept, - exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid, - exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc, + exit_handlers[EXIT_REASON_VMCLEAR] = handle_vmclear; + exit_handlers[EXIT_REASON_VMLAUNCH] = handle_vmlaunch; + exit_handlers[EXIT_REASON_VMPTRLD] = handle_vmptrld; + exit_handlers[EXIT_REASON_VMPTRST] = handle_vmptrst; + exit_handlers[EXIT_REASON_VMREAD] = handle_vmread; + exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume; + exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite; + exit_handlers[EXIT_REASON_VMOFF] = handle_vmoff; + exit_handlers[EXIT_REASON_VMON] = handle_vmon; + exit_handlers[EXIT_REASON_INVEPT] = handle_invept; + exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid; + exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc; kvm_x86_ops->check_nested_events = vmx_check_nested_events; kvm_x86_ops->get_nested_state = vmx_get_nested_state; kvm_x86_ops->set_nested_state = vmx_set_nested_state; - kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages, + kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages; kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs; kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 187d39bf0bf1..fc874d4ead0f 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -6,14 +6,25 @@ #include "vmcs12.h" #include "vmx.h" +/* + * Status returned by nested_vmx_enter_non_root_mode(): + */ +enum nvmx_vmentry_status { + NVMX_VMENTRY_SUCCESS, /* Entered VMX non-root mode */ + NVMX_VMENTRY_VMFAIL, /* Consistency check VMFail */ + NVMX_VMENTRY_VMEXIT, /* Consistency check VMExit */ + NVMX_VMENTRY_KVM_INTERNAL_ERROR,/* KVM internal error */ +}; + void vmx_leave_nested(struct kvm_vcpu *vcpu); void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, bool apicv); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); -void nested_vmx_vcpu_setup(void); +void nested_vmx_set_vmcs_shadowing_bitmap(void); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); -int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); +enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, + bool from_vmentry); bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason); void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, u32 exit_intr_info, unsigned long exit_qualification); @@ -22,6 +33,7 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); +void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { @@ -245,7 +257,7 @@ static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1) return ((val & fixed1) | fixed0) == val; } -static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) +static inline bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) { u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0; u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1; @@ -259,7 +271,7 @@ static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) return fixed_bits_valid(val, fixed0, fixed1); } -static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) +static inline bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) { u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0; u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1; @@ -267,7 +279,7 @@ static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val) return fixed_bits_valid(val, fixed0, fixed1); } -static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val) +static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val) { u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr4_fixed0; u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr4_fixed1; diff --git a/arch/x86/kvm/vmx/ops.h b/arch/x86/kvm/vmx/ops.h index 2200fb698dd0..45eaedee2ac0 100644 --- a/arch/x86/kvm/vmx/ops.h +++ b/arch/x86/kvm/vmx/ops.h @@ -11,8 +11,13 @@ #include "vmcs.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) -#define __ex_clear(x, reg) \ - ____kvm_handle_fault_on_reboot(x, "xor " reg ", " reg) + +asmlinkage void vmread_error(unsigned long field, bool fault); +void vmwrite_error(unsigned long field, unsigned long value); +void vmclear_error(struct vmcs *vmcs, u64 phys_addr); +void vmptrld_error(struct vmcs *vmcs, u64 phys_addr); +void invvpid_error(unsigned long ext, u16 vpid, gva_t gva); +void invept_error(unsigned long ext, u64 eptp, gpa_t gpa); static __always_inline void vmcs_check16(unsigned long field) { @@ -62,8 +67,22 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) { unsigned long value; - asm volatile (__ex_clear("vmread %1, %0", "%k0") - : "=r"(value) : "r"(field)); + asm volatile("1: vmread %2, %1\n\t" + ".byte 0x3e\n\t" /* branch taken hint */ + "ja 3f\n\t" + "mov %2, %%" _ASM_ARG1 "\n\t" + "xor %%" _ASM_ARG2 ", %%" _ASM_ARG2 "\n\t" + "2: call vmread_error\n\t" + "xor %k1, %k1\n\t" + "3:\n\t" + + ".pushsection .fixup, \"ax\"\n\t" + "4: mov %2, %%" _ASM_ARG1 "\n\t" + "mov $1, %%" _ASM_ARG2 "\n\t" + "jmp 2b\n\t" + ".popsection\n\t" + _ASM_EXTABLE(1b, 4b) + : ASM_CALL_CONSTRAINT, "=r"(value) : "r"(field) : "cc"); return value; } @@ -103,21 +122,39 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) return __vmcs_readl(field); } -static noinline void vmwrite_error(unsigned long field, unsigned long value) -{ - printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n", - field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); - dump_stack(); -} +#define vmx_asm1(insn, op1, error_args...) \ +do { \ + asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + ".byte 0x2e\n\t" /* branch not taken hint */ \ + "jna %l[error]\n\t" \ + _ASM_EXTABLE(1b, %l[fault]) \ + : : op1 : "cc" : error, fault); \ + return; \ +error: \ + insn##_error(error_args); \ + return; \ +fault: \ + kvm_spurious_fault(); \ +} while (0) + +#define vmx_asm2(insn, op1, op2, error_args...) \ +do { \ + asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + ".byte 0x2e\n\t" /* branch not taken hint */ \ + "jna %l[error]\n\t" \ + _ASM_EXTABLE(1b, %l[fault]) \ + : : op1, op2 : "cc" : error, fault); \ + return; \ +error: \ + insn##_error(error_args); \ + return; \ +fault: \ + kvm_spurious_fault(); \ +} while (0) static __always_inline void __vmcs_writel(unsigned long field, unsigned long value) { - bool error; - - asm volatile (__ex("vmwrite %2, %1") CC_SET(na) - : CC_OUT(na) (error) : "r"(field), "rm"(value)); - if (unlikely(error)) - vmwrite_error(field, value); + vmx_asm2(vmwrite, "r"(field), "rm"(value), field, value); } static __always_inline void vmcs_write16(unsigned long field, u16 value) @@ -182,28 +219,18 @@ static __always_inline void vmcs_set_bits(unsigned long field, u32 mask) static inline void vmcs_clear(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); - bool error; - asm volatile (__ex("vmclear %1") CC_SET(na) - : CC_OUT(na) (error) : "m"(phys_addr)); - if (unlikely(error)) - printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n", - vmcs, phys_addr); + vmx_asm1(vmclear, "m"(phys_addr), vmcs, phys_addr); } static inline void vmcs_load(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); - bool error; if (static_branch_unlikely(&enable_evmcs)) return evmcs_load(phys_addr); - asm volatile (__ex("vmptrld %1") CC_SET(na) - : CC_OUT(na) (error) : "m"(phys_addr)); - if (unlikely(error)) - printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n", - vmcs, phys_addr); + vmx_asm1(vmptrld, "m"(phys_addr), vmcs, phys_addr); } static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva) @@ -213,11 +240,8 @@ static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva) u64 rsvd : 48; u64 gva; } operand = { vpid, 0, gva }; - bool error; - asm volatile (__ex("invvpid %2, %1") CC_SET(na) - : CC_OUT(na) (error) : "r"(ext), "m"(operand)); - BUG_ON(error); + vmx_asm2(invvpid, "r"(ext), "m"(operand), ext, vpid, gva); } static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) @@ -225,11 +249,8 @@ static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) struct { u64 eptp, gpa; } operand = {eptp, gpa}; - bool error; - asm volatile (__ex("invept %2, %1") CC_SET(na) - : CC_OUT(na) (error) : "r"(ext), "m"(operand)); - BUG_ON(error); + vmx_asm2(invept, "r"(ext), "m"(operand), ext, eptp, gpa); } static inline bool vpid_sync_vcpu_addr(int vpid, gva_t addr) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 4dea0e0e7e39..fd21cdb10b79 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -15,6 +15,7 @@ #include "x86.h" #include "cpuid.h" #include "lapic.h" +#include "nested.h" #include "pmu.h" static struct kvm_event_hw_type_mapping intel_arch_events[] = { @@ -46,6 +47,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) if (old_ctrl == new_ctrl) continue; + __set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use); reprogram_fixed_counter(pmc, new_ctrl, i); } @@ -84,10 +86,14 @@ static unsigned intel_find_arch_event(struct kvm_pmu *pmu, static unsigned intel_find_fixed_event(int idx) { - if (idx >= ARRAY_SIZE(fixed_pmc_events)) + u32 event; + size_t size = ARRAY_SIZE(fixed_pmc_events); + + if (idx >= size) return PERF_COUNT_HW_MAX; - return intel_arch_events[fixed_pmc_events[idx]].event_type; + event = fixed_pmc_events[array_index_nospec(idx, size)]; + return intel_arch_events[event].event_type; } /* check if a PMC is enabled by comparing it with globl_ctrl bits. */ @@ -111,7 +117,7 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +static int intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); @@ -122,22 +128,26 @@ static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) (fixed && idx >= pmu->nr_arch_fixed_counters); } -static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, - unsigned idx, u64 *mask) +static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, + unsigned int idx, u64 *mask) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); struct kvm_pmc *counters; + unsigned int num_counters; idx &= ~(3u << 30); - if (!fixed && idx >= pmu->nr_arch_gp_counters) - return NULL; - if (fixed && idx >= pmu->nr_arch_fixed_counters) + if (fixed) { + counters = pmu->fixed_counters; + num_counters = pmu->nr_arch_fixed_counters; + } else { + counters = pmu->gp_counters; + num_counters = pmu->nr_arch_gp_counters; + } + if (idx >= num_counters) return NULL; - counters = fixed ? pmu->fixed_counters : pmu->gp_counters; *mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP]; - - return &counters[idx]; + return &counters[array_index_nospec(idx, num_counters)]; } static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) @@ -162,6 +172,18 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) return ret; } +static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + pmc = get_fixed_pmc(pmu, msr); + pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0); + pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0); + + return pmc; +} + static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -223,7 +245,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_CORE_PERF_GLOBAL_CTRL: if (pmu->global_ctrl == data) return 0; - if (!(data & pmu->global_ctrl_mask)) { + if (kvm_valid_perf_global_ctrl(pmu, data)) { global_ctrl_changed(pmu, data); return 0; } @@ -238,13 +260,12 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; default: if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) { - if (msr_info->host_initiated) - pmc->counter = data; - else - pmc->counter = (s32)data; + if (!msr_info->host_initiated) + data = (s64)(s32)data; + pmc->counter += data - pmc_read_counter(pmc); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { - pmc->counter = data; + pmc->counter += data - pmc_read_counter(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) @@ -262,6 +283,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void intel_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct x86_pmu_capability x86_pmu; struct kvm_cpuid_entry2 *entry; union cpuid10_eax eax; union cpuid10_edx edx; @@ -283,8 +305,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) if (!pmu->version) return; + perf_get_x86_pmu_capability(&x86_pmu); + pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, - INTEL_PMC_MAX_GENERIC); + x86_pmu.num_counters_gp); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; pmu->available_event_types = ~entry->ebx & ((1ull << eax.split.mask_length) - 1); @@ -294,7 +318,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) } else { pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed, - INTEL_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; } @@ -314,6 +338,13 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; + + bitmap_set(pmu->all_valid_pmc_idx, + 0, pmu->nr_arch_gp_counters); + bitmap_set(pmu->all_valid_pmc_idx, + INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters); + + nested_vmx_pmu_entry_exit_ctls_update(vcpu); } static void intel_pmu_init(struct kvm_vcpu *vcpu) @@ -325,12 +356,14 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; + pmu->gp_counters[i].current_config = 0; } for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { pmu->fixed_counters[i].type = KVM_PMC_FIXED; pmu->fixed_counters[i].vcpu = vcpu; pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; + pmu->fixed_counters[i].current_config = 0; } } @@ -363,8 +396,9 @@ struct kvm_pmu_ops intel_pmu_ops = { .find_fixed_event = intel_find_fixed_event, .pmc_is_enabled = intel_pmc_is_enabled, .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, + .rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = intel_msr_idx_to_pmc, - .is_valid_msr_idx = intel_is_valid_msr_idx, + .is_valid_rdpmc_ecx = intel_is_valid_rdpmc_ecx, .is_valid_msr = intel_is_valid_msr, .get_msr = intel_pmu_get_msr, .set_msr = intel_pmu_set_msr, diff --git a/arch/x86/kvm/vmx/vmcs_shadow_fields.h b/arch/x86/kvm/vmx/vmcs_shadow_fields.h index eb1ecd16fd22..cad128d1657b 100644 --- a/arch/x86/kvm/vmx/vmcs_shadow_fields.h +++ b/arch/x86/kvm/vmx/vmcs_shadow_fields.h @@ -23,12 +23,12 @@ BUILD_BUG_ON(1) * * When adding or removing fields here, note that shadowed * fields must always be synced by prepare_vmcs02, not just - * prepare_vmcs02_full. + * prepare_vmcs02_rare. */ /* * Keeping the fields ordered by size is an attempt at improving - * branch prediction in vmcs_read_any and vmcs_write_any. + * branch prediction in vmcs12_read_any and vmcs12_write_any. */ /* 16-bits */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 4010d519eb8c..81ada2ce99e7 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -43,7 +43,7 @@ * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump * to vmx_vmexit. */ -ENTRY(vmx_vmenter) +SYM_FUNC_START(vmx_vmenter) /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ je 2f @@ -65,7 +65,7 @@ ENTRY(vmx_vmenter) _ASM_EXTABLE(1b, 5b) _ASM_EXTABLE(2b, 5b) -ENDPROC(vmx_vmenter) +SYM_FUNC_END(vmx_vmenter) /** * vmx_vmexit - Handle a VMX VM-Exit @@ -77,7 +77,7 @@ ENDPROC(vmx_vmenter) * here after hardware loads the host's state, i.e. this is the destination * referred to by VMCS.HOST_RIP. */ -ENTRY(vmx_vmexit) +SYM_FUNC_START(vmx_vmexit) #ifdef CONFIG_RETPOLINE ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE /* Preserve guest's RAX, it's used to stuff the RSB. */ @@ -90,18 +90,18 @@ ENTRY(vmx_vmexit) .Lvmexit_skip_rsb: #endif ret -ENDPROC(vmx_vmexit) +SYM_FUNC_END(vmx_vmexit) /** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode - * @vmx: struct vcpu_vmx * + * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) * @regs: unsigned long * (to guest registers) * @launched: %true if the VMCS has been launched * * Returns: * 0 on VM-Exit, 1 on VM-Fail */ -ENTRY(__vmx_vcpu_run) +SYM_FUNC_START(__vmx_vcpu_run) push %_ASM_BP mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 @@ -151,7 +151,7 @@ ENTRY(__vmx_vcpu_run) mov VCPU_R14(%_ASM_AX), %r14 mov VCPU_R15(%_ASM_AX), %r15 #endif - /* Load guest RAX. This kills the vmx_vcpu pointer! */ + /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX /* Enter guest mode */ @@ -233,4 +233,4 @@ ENTRY(__vmx_vcpu_run) /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ 2: mov $1, %eax jmp 1b -ENDPROC(__vmx_vcpu_run) +SYM_FUNC_END(__vmx_vcpu_run) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 42ed3faa6af8..3be25ecae145 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -106,8 +106,6 @@ module_param(enable_apicv, bool, S_IRUGO); static bool __read_mostly nested = 1; module_param(nested, bool, S_IRUGO); -static u64 __read_mostly host_xss; - bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); @@ -209,6 +207,11 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) struct page *page; unsigned int i; + if (!boot_cpu_has_bug(X86_BUG_L1TF)) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; + return 0; + } + if (!enable_ept) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; return 0; @@ -343,6 +346,48 @@ static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bit void vmx_vmexit(void); +#define vmx_insn_failed(fmt...) \ +do { \ + WARN_ONCE(1, fmt); \ + pr_warn_ratelimited(fmt); \ +} while (0) + +asmlinkage void vmread_error(unsigned long field, bool fault) +{ + if (fault) + kvm_spurious_fault(); + else + vmx_insn_failed("kvm: vmread failed: field=%lx\n", field); +} + +noinline void vmwrite_error(unsigned long field, unsigned long value) +{ + vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%d\n", + field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); +} + +noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) +{ + vmx_insn_failed("kvm: vmclear failed: %p/%llx\n", vmcs, phys_addr); +} + +noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) +{ + vmx_insn_failed("kvm: vmptrld failed: %p/%llx\n", vmcs, phys_addr); +} + +noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) +{ + vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", + ext, vpid, gva); +} + +noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa) +{ + vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", + ext, eptp, gpa); +} + static DEFINE_PER_CPU(struct vmcs *, vmxarea); DEFINE_PER_CPU(struct vmcs *, current_vmcs); /* @@ -403,6 +448,7 @@ const u32 vmx_msr_index[] = { MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif MSR_EFER, MSR_TSC_AUX, MSR_STAR, + MSR_IA32_TSX_CTRL, }; #if IS_ENABLED(CONFIG_HYPERV) @@ -486,6 +532,31 @@ static int hv_remote_flush_tlb(struct kvm *kvm) return hv_remote_flush_tlb_with_range(kvm, NULL); } +static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +{ + struct hv_enlightened_vmcs *evmcs; + struct hv_partition_assist_pg **p_hv_pa_pg = + &vcpu->kvm->arch.hyperv.hv_pa_pg; + /* + * Synthetic VM-Exit is not enabled in current code and so All + * evmcs in singe VM shares same assist page. + */ + if (!*p_hv_pa_pg) + *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); + + if (!*p_hv_pa_pg) + return -ENOMEM; + + evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; + + evmcs->partition_assist_page = + __pa(*p_hv_pa_pg); + evmcs->hv_vm_id = (unsigned long)vcpu->kvm; + evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; + + return 0; +} + #endif /* IS_ENABLED(CONFIG_HYPERV) */ /* @@ -566,6 +637,23 @@ struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) return NULL; } +static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data) +{ + int ret = 0; + + u64 old_msr_data = msr->data; + msr->data = data; + if (msr - vmx->guest_msrs < vmx->save_nmsrs) { + preempt_disable(); + ret = kvm_set_shared_msr(msr->index, msr->data, + msr->mask); + preempt_enable(); + if (ret) + msr->data = old_msr_data; + } + return ret; +} + void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) { vmcs_clear(loaded_vmcs->vmcs); @@ -654,8 +742,8 @@ static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg, bool ret; u32 mask = 1 << (seg * SEG_FIELD_NR + field); - if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) { - vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS); + if (!kvm_register_is_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS)) { + kvm_register_mark_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS); vmx->segment_cache.bitmask = 0; } ret = vmx->segment_cache.bitmask & mask; @@ -763,7 +851,7 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, vm_exit_controls_clearbit(vmx, exit); } -static int find_msr(struct vmx_msrs *m, unsigned int msr) +int vmx_find_msr_index(struct vmx_msrs *m, u32 msr) { unsigned int i; @@ -797,7 +885,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) } break; } - i = find_msr(&m->guest, msr); + i = vmx_find_msr_index(&m->guest, msr); if (i < 0) goto skip_guest; --m->guest.nr; @@ -805,7 +893,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); skip_guest: - i = find_msr(&m->host, msr); + i = vmx_find_msr_index(&m->host, msr); if (i < 0) return; @@ -864,12 +952,12 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } - i = find_msr(&m->guest, msr); + i = vmx_find_msr_index(&m->guest, msr); if (!entry_only) - j = find_msr(&m->host, msr); + j = vmx_find_msr_index(&m->host, msr); - if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) || - (j < 0 && m->host.nr == NR_AUTOLOAD_MSRS)) { + if ((i < 0 && m->guest.nr == NR_LOADSTORE_MSRS) || + (j < 0 && m->host.nr == NR_LOADSTORE_MSRS)) { printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; @@ -897,17 +985,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; - if (!enable_ept) { - /* - * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing - * host CPUID is more efficient than testing guest CPUID - * or CR4. Host SMEP is anyway a requirement for guest SMEP. - */ - if (boot_cpu_has(X86_FEATURE_SMEP)) - guest_efer |= EFER_NX; - else if (!(guest_efer & EFER_NX)) - ignore_bits |= EFER_NX; - } + /* Shadow paging assumes NX to be available. */ + if (!enable_ept) + guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. @@ -977,6 +1057,12 @@ static unsigned long segment_base(u16 selector) } #endif +static inline bool pt_can_write_msr(struct vcpu_vmx *vmx) +{ + return (pt_mode == PT_MODE_HOST_GUEST) && + !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); +} + static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; @@ -1204,6 +1290,18 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block is the one expected to change PID.NDST and the + * wakeup handler expects the vCPU to be on the blocked_vcpu_list that + * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up + * correctly. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + goto after_clear_sn; + } + /* The full case. */ do { old.control = new.control = pi_desc->control; @@ -1219,6 +1317,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) } while (cmpxchg64(&pi_desc->control, old.control, new.control) != old.control); +after_clear_sn: + /* * Clear SN before reading the bitmap. The VT-d firmware * writes the bitmap and reads SN atomically (5.2.3 in the @@ -1227,7 +1327,7 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) */ smp_mb__after_atomic(); - if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS)) + if (!pi_is_pir_empty(pi_desc)) pi_set_on(pi_desc); } @@ -1274,14 +1374,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ - /* - * VM exits change the host TR limit to 0x67 after a VM - * exit. This is okay, since 0x67 covers everything except - * the IO bitmap and have have code to handle the IO bitmap - * being lost after a VM exit. - */ - BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67); - rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ @@ -1336,39 +1428,46 @@ static bool emulation_required(struct kvm_vcpu *vcpu) return emulate_invalid_guest_state && !guest_state_valid(vcpu); } -static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); - unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long rflags, save_rflags; - if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) { - __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_RFLAGS)) { + kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); rflags = vmcs_readl(GUEST_RFLAGS); - if (to_vmx(vcpu)->rmode.vm86_active) { + if (vmx->rmode.vm86_active) { rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; - save_rflags = to_vmx(vcpu)->rmode.save_rflags; + save_rflags = vmx->rmode.save_rflags; rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; } - to_vmx(vcpu)->rflags = rflags; + vmx->rflags = rflags; } - return to_vmx(vcpu)->rflags; + return vmx->rflags; } void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { - unsigned long old_rflags = vmx_get_rflags(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long old_rflags; - __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); - to_vmx(vcpu)->rflags = rflags; - if (to_vmx(vcpu)->rmode.vm86_active) { - to_vmx(vcpu)->rmode.save_rflags = rflags; + if (enable_unrestricted_guest) { + kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); + vmx->rflags = rflags; + vmcs_writel(GUEST_RFLAGS, rflags); + return; + } + + old_rflags = vmx_get_rflags(vcpu); + vmx->rflags = rflags; + if (vmx->rmode.vm86_active) { + vmx->rmode.save_rflags = rflags; rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; } vmcs_writel(GUEST_RFLAGS, rflags); - if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM) - to_vmx(vcpu)->emulation_required = emulation_required(vcpu); + if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) + vmx->emulation_required = emulation_required(vcpu); } u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) @@ -1472,17 +1571,32 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } - -static void skip_emulated_instruction(struct kvm_vcpu *vcpu) +static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { unsigned long rip; - rip = kvm_rip_read(vcpu); - rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - kvm_rip_write(vcpu, rip); + /* + * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on + * undefined behavior: Intel's SDM doesn't mandate the VMCS field be + * set when EPT misconfig occurs. In practice, real hardware updates + * VM_EXIT_INSTRUCTION_LEN on EPT misconfig, but other hypervisors + * (namely Hyper-V) don't set it due to it being undefined behavior, + * i.e. we end up advancing IP with some random value. + */ + if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || + to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) { + rip = kvm_rip_read(vcpu); + rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + kvm_rip_write(vcpu, rip); + } else { + if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) + return 0; + } /* skipping an emulated instruction also counts */ vmx_set_interrupt_shadow(vcpu, 0); + + return 1; } static void vmx_clear_hlt(struct kvm_vcpu *vcpu) @@ -1517,8 +1631,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) int inc_eip = 0; if (kvm_exception_is_soft(nr)) inc_eip = vcpu->arch.event_exit_inst_len; - if (kvm_inject_realmode_interrupt(vcpu, nr, inc_eip) != EMULATE_DONE) - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + kvm_inject_realmode_interrupt(vcpu, nr, inc_eip); return; } @@ -1591,6 +1704,9 @@ static void setup_msrs(struct vcpu_vmx *vmx) index = __find_msr_index(vmx, MSR_TSC_AUX); if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) move_msr_up(vmx, index, save_nmsrs++); + index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL); + if (index >= 0) + move_msr_up(vmx, index, save_nmsrs++); vmx->save_nmsrs = save_nmsrs; vmx->guest_msrs_ready = false; @@ -1604,7 +1720,7 @@ static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) return vcpu->arch.tsc_offset - vmcs12->tsc_offset; return vcpu->arch.tsc_offset; @@ -1622,7 +1738,7 @@ static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) * to the newly set TSC to get L2's TSC. */ if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) g_tsc_offset = vmcs12->tsc_offset; trace_kvm_write_tsc_offset(vcpu->vcpu_id, @@ -1661,8 +1777,6 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) default: return 1; } - - return 0; } /* @@ -1690,6 +1804,17 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); + case MSR_IA32_TSX_CTRL: + if (!msr_info->host_initiated && + !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) + return 1; + goto find_shared_msr; + case MSR_IA32_UMWAIT_CONTROL: + if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) + return 1; + + msr_info->data = vmx->msr_ia32_umwait_control; + break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) @@ -1716,25 +1841,29 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MCG_EXT_CTL: if (!msr_info->host_initiated && !(vmx->msr_ia32_feature_control & - FEATURE_CONTROL_LMCE)) + FEAT_CTL_LMCE_ENABLED)) return 1; msr_info->data = vcpu->arch.mcg_ext_ctl; break; - case MSR_IA32_FEATURE_CONTROL: + case MSR_IA32_FEAT_CTL: msr_info->data = vmx->msr_ia32_feature_control; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) return 1; - return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, - &msr_info->data); - case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) + if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, + &msr_info->data)) return 1; - msr_info->data = vcpu->arch.ia32_xss; + /* + * Enlightened VMCS v1 doesn't have certain fields, but buggy + * Hyper-V versions are still trying to use corresponding + * features when they are exposed. Filter out the essential + * minimum. + */ + if (!msr_info->host_initiated && + vmx->nested.enlightened_vmcs_enabled) + nested_evmcs_filter_control_msr(msr_info->index, + &msr_info->data); break; case MSR_IA32_RTIT_CTL: if (pt_mode != PT_MODE_HOST_GUEST) @@ -1786,8 +1915,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) return 1; - /* Else, falls through */ + goto find_shared_msr; default: + find_shared_msr: msr = find_msr_entry(vmx, msr_info->index); if (msr) { msr_info->data = msr->data; @@ -1800,7 +1930,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } /* - * Writes msr value into into the appropriate "register". + * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ @@ -1863,17 +1993,25 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vmcs_write64(GUEST_BNDCFGS, data); break; + case MSR_IA32_UMWAIT_CONTROL: + if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) + return 1; + + /* The reserved bit 1 and non-32 bit [63:32] should be zero */ + if (data & (BIT_ULL(1) | GENMASK_ULL(63, 32))) + return 1; + + vmx->msr_ia32_umwait_control = data; + break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; - /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) + if (data & ~kvm_spec_ctrl_valid_bits(vcpu)) return 1; vmx->spec_ctrl = data; - if (!data) break; @@ -1884,7 +2022,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * * For nested: * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_merge_msr_bitmap. We should not touch the + * nested_vmx_prepare_msr_bitmap. We should not touch the * vmcs02.msr_bitmap here since it gets completely overwritten * in the merging. We update the vmcs01 here for L1 as well * since it will end up touching the MSR anyway now. @@ -1893,6 +2031,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); break; + case MSR_IA32_TSX_CTRL: + if (!msr_info->host_initiated && + !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) + return 1; + if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) + return 1; + goto find_shared_msr; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) @@ -1900,7 +2045,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~PRED_CMD_IBPB) return 1; - + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL)) + return 1; if (!data) break; @@ -1913,7 +2059,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * * For nested: * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_merge_msr_bitmap. We should not touch the + * nested_vmx_prepare_msr_bitmap. We should not touch the * vmcs02.msr_bitmap here since it gets completely overwritten * in the merging. */ @@ -1941,15 +2087,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && !(to_vmx(vcpu)->msr_ia32_feature_control & - FEATURE_CONTROL_LMCE)) || + FEAT_CTL_LMCE_ENABLED)) || (data & ~MCG_EXT_CTL_LMCE_EN)) return 1; vcpu->arch.mcg_ext_ctl = data; break; - case MSR_IA32_FEATURE_CONTROL: + case MSR_IA32_FEAT_CTL: if (!vmx_feature_control_msr_valid(vcpu, data) || (to_vmx(vcpu)->msr_ia32_feature_control & - FEATURE_CONTROL_LOCKED && !msr_info->host_initiated)) + FEAT_CTL_LOCKED && !msr_info->host_initiated)) return 1; vmx->msr_ia32_feature_control = data; if (msr_info->host_initiated && data == 0) @@ -1961,25 +2107,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!nested_vmx_allowed(vcpu)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); - case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) - return 1; - /* - * The only supported bit as of Skylake is bit 8, but - * it is not supported on KVM. - */ - if (data != 0) - return 1; - vcpu->arch.ia32_xss = data; - if (vcpu->arch.ia32_xss != host_xss) - add_atomic_switch_msr(vmx, MSR_IA32_XSS, - vcpu->arch.ia32_xss, host_xss, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_XSS); - break; case MSR_IA32_RTIT_CTL: if ((pt_mode != PT_MODE_HOST_GUEST) || vmx_rtit_ctl_check(vcpu, data) || @@ -1990,47 +2117,50 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pt_update_intercept_for_msr(vmx); break; case MSR_IA32_RTIT_STATUS: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (data & MSR_IA32_RTIT_STATUS_MASK)) + if (!pt_can_write_msr(vmx)) + return 1; + if (data & MSR_IA32_RTIT_STATUS_MASK) return 1; vmx->pt_desc.guest.status = data; break; case MSR_IA32_RTIT_CR3_MATCH: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_cr3_filtering)) + if (!pt_can_write_msr(vmx)) + return 1; + if (!intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_cr3_filtering)) return 1; vmx->pt_desc.guest.cr3_match = data; break; case MSR_IA32_RTIT_OUTPUT_BASE: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output)) || - (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK)) + if (!pt_can_write_msr(vmx)) + return 1; + if (!intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_topa_output) && + !intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_single_range_output)) + return 1; + if (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK) return 1; vmx->pt_desc.guest.output_base = data; break; case MSR_IA32_RTIT_OUTPUT_MASK: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output))) + if (!pt_can_write_msr(vmx)) + return 1; + if (!intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_topa_output) && + !intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_single_range_output)) return 1; vmx->pt_desc.guest.output_mask = data; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: + if (!pt_can_write_msr(vmx)) + return 1; index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges))) + if (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_num_address_ranges)) + return 1; + if (is_noncanonical_address(data, vcpu)) return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; @@ -2044,23 +2174,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) return 1; - /* Else, falls through */ + goto find_shared_msr; + default: + find_shared_msr: msr = find_msr_entry(vmx, msr_index); - if (msr) { - u64 old_msr_data = msr->data; - msr->data = data; - if (msr - vmx->guest_msrs < vmx->save_nmsrs) { - preempt_disable(); - ret = kvm_set_shared_msr(msr->index, msr->data, - msr->mask); - preempt_enable(); - if (ret) - msr->data = old_msr_data; - } - break; - } - ret = kvm_set_msr_common(vcpu, msr_info); + if (msr) + ret = vmx_set_guest_msr(vmx, msr, data); + else + ret = kvm_set_msr_common(vcpu, msr_info); } return ret; @@ -2068,7 +2190,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, reg); + switch (reg) { case VCPU_REGS_RSP: vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); @@ -2080,7 +2203,12 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) if (enable_ept) ept_save_pdptrs(vcpu); break; + case VCPU_EXREG_CR3: + if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu))) + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + break; default: + WARN_ON_ONCE(1); break; } } @@ -2092,29 +2220,8 @@ static __init int cpu_has_kvm_support(void) static __init int vmx_disabled_by_bios(void) { - u64 msr; - - rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); - if (msr & FEATURE_CONTROL_LOCKED) { - /* launched w/ TXT and VMX disabled */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) - && tboot_enabled()) - return 1; - /* launched w/o TXT and VMX only enabled w/ TXT */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) - && (msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) - && !tboot_enabled()) { - printk(KERN_WARNING "kvm: disable TXT in the BIOS or " - "activate TXT before enabling KVM\n"); - return 1; - } - /* launched w/o TXT and VMX disabled */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) - && !tboot_enabled()) - return 1; - } - - return 0; + return !boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || + !boot_cpu_has(X86_FEATURE_VMX); } static void kvm_cpu_vmxon(u64 addr) @@ -2129,7 +2236,6 @@ static int hardware_enable(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - u64 old, test_bits; if (cr4_read_shadow() & X86_CR4_VMXE) return -EBUSY; @@ -2157,17 +2263,6 @@ static int hardware_enable(void) */ crash_enable_local_vmclear(cpu); - rdmsrl(MSR_IA32_FEATURE_CONTROL, old); - - test_bits = FEATURE_CONTROL_LOCKED; - test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - if (tboot_enabled()) - test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX; - - if ((old & test_bits) != test_bits) { - /* enable and lock */ - wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits); - } kvm_cpu_vmxon(phys_addr); if (enable_ept) ept_sync_global(); @@ -2243,7 +2338,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, CPU_BASED_CR3_STORE_EXITING | CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_USE_TSC_OFFSETTING | CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING | CPU_BASED_INVLPG_EXITING | @@ -2280,6 +2375,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_PML | SECONDARY_EXEC_TSC_SCALING | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX | SECONDARY_EXEC_ENABLE_VMFUNC | @@ -2577,8 +2673,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmx->rmode.vm86_active = 0; - vmx_segment_cache_clear(vmx); - vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); flags = vmcs_readl(GUEST_RFLAGS); @@ -2750,13 +2844,6 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits; } -static void vmx_decache_cr3(struct kvm_vcpu *vcpu) -{ - if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu))) - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); -} - static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits; @@ -2769,8 +2856,7 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty)) + if (!kvm_register_is_dirty(vcpu, VCPU_EXREG_PDPTR)) return; if (is_pae_paging(vcpu)) { @@ -2792,10 +2878,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); } - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); } static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, @@ -2804,8 +2887,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - vmx_decache_cr3(vcpu); + if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) + vmx_cache_reg(vcpu, VCPU_EXREG_CR3); if (!(cr0 & X86_CR0_PG)) { /* From paging/starting to nonpaging */ exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING | @@ -2864,6 +2947,9 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) static int get_ept_level(struct kvm_vcpu *vcpu) { + /* Nested EPT currently only supports 4-level walks. */ + if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) + return 4; if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4; @@ -2886,6 +2972,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm *kvm = vcpu->kvm; + bool update_guest_cr3 = true; unsigned long guest_cr3; u64 eptp; @@ -2902,15 +2989,20 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); } - if (enable_unrestricted_guest || is_paging(vcpu) || - is_guest_mode(vcpu)) - guest_cr3 = kvm_read_cr3(vcpu); - else + /* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */ + if (is_guest_mode(vcpu)) + update_guest_cr3 = false; + else if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; + else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + guest_cr3 = vcpu->arch.cr3; + else /* vmcs01.GUEST_CR3 is already up-to-date. */ + update_guest_cr3 = false; ept_load_pdptrs(vcpu); } - vmcs_writel(GUEST_CR3, guest_cr3); + if (update_guest_cr3) + vmcs_writel(GUEST_CR3, guest_cr3); } int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -3369,7 +3461,7 @@ out: static int init_rmode_identity_map(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); - int i, idx, r = 0; + int i, r = 0; kvm_pfn_t identity_map_pfn; u32 tmp; @@ -3377,7 +3469,7 @@ static int init_rmode_identity_map(struct kvm *kvm) mutex_lock(&kvm->slots_lock); if (likely(kvm_vmx->ept_identity_pagetable_done)) - goto out2; + goto out; if (!kvm_vmx->ept_identity_map_addr) kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; @@ -3386,9 +3478,8 @@ static int init_rmode_identity_map(struct kvm *kvm) r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, kvm_vmx->ept_identity_map_addr, PAGE_SIZE); if (r < 0) - goto out2; + goto out; - idx = srcu_read_lock(&kvm->srcu); r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -3404,9 +3495,6 @@ static int init_rmode_identity_map(struct kvm *kvm) kvm_vmx->ept_identity_pagetable_done = true; out: - srcu_read_unlock(&kvm->srcu, idx); - -out2: mutex_unlock(&kvm->slots_lock); return r; } @@ -3644,11 +3732,6 @@ void pt_update_intercept_for_msr(struct vcpu_vmx *vmx) } } -static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu) -{ - return enable_apicv; -} - static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3934,9 +4017,12 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) if (vmx_xsaves_supported()) { /* Exposing XSAVES only when XSAVE is exposed */ bool xsaves_enabled = + boot_cpu_has(X86_FEATURE_XSAVE) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); + vcpu->arch.xsaves_enabled = xsaves_enabled; + if (!xsaves_enabled) exec_control &= ~SECONDARY_EXEC_XSAVES; @@ -4016,6 +4102,23 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) } } + if (vmx_waitpkg_supported()) { + bool waitpkg_enabled = + guest_cpuid_has(vcpu, X86_FEATURE_WAITPKG); + + if (!waitpkg_enabled) + exec_control &= ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; + + if (nested) { + if (waitpkg_enabled) + vmx->nested.msrs.secondary_ctls_high |= + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; + else + vmx->nested.msrs.secondary_ctls_high &= + ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; + } + } + vmx->secondary_exec_control = exec_control; } @@ -4026,20 +4129,19 @@ static void ept_set_mmio_spte_mask(void) * of an EPT paging-structure entry is 110b (write/execute). */ kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, - VMX_EPT_MISCONFIG_WX_VALUE); + VMX_EPT_MISCONFIG_WX_VALUE, 0); } #define VMX_XSS_EXIT_BITMAP 0 /* - * Sets up the vmcs for emulated real mode. + * Noting that the initialization of Guest-state Area of VMCS is in + * vmx_vcpu_reset(). */ -static void vmx_vcpu_setup(struct vcpu_vmx *vmx) +static void init_vmcs(struct vcpu_vmx *vmx) { - int i; - if (nested) - nested_vmx_vcpu_setup(); + nested_vmx_set_vmcs_shadowing_bitmap(); if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); @@ -4048,7 +4150,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) /* Control */ pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); - vmx->hv_deadline_tsc = -1; exec_controls_set(vmx, vmx_exec_control(vmx)); @@ -4097,21 +4198,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); - for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { - u32 index = vmx_msr_index[i]; - u32 data_low, data_high; - int j = vmx->nmsrs; - - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) - continue; - vmx->guest_msrs[j].index = i; - vmx->guest_msrs[j].data = 0; - vmx->guest_msrs[j].mask = -1ull; - ++vmx->nmsrs; - } - vm_exit_controls_set(vmx, vmx_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ @@ -4122,6 +4208,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) set_cr4_guest_host_mask(vmx); + if (vmx->vpid != 0) + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); + if (vmx_xsaves_supported()) vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP); @@ -4150,8 +4239,10 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->rmode.vm86_active = 0; vmx->spec_ctrl = 0; - vcpu->arch.microcode_version = 0x100000000ULL; + vmx->msr_ia32_umwait_control = 0; + vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); + vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); if (!init_event) { @@ -4221,9 +4312,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (vmx->vpid != 0) - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; vmx->vcpu.arch.cr0 = cr0; vmx_set_cr0(vcpu, cr0); /* enter rmode */ @@ -4239,7 +4327,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) static void enable_irq_window(struct kvm_vcpu *vcpu) { - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } static void enable_nmi_window(struct kvm_vcpu *vcpu) @@ -4250,7 +4338,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) return; } - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -4266,8 +4354,7 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu) int inc_eip = 0; if (vcpu->arch.interrupt.soft) inc_eip = vcpu->arch.event_exit_inst_len; - if (kvm_inject_realmode_interrupt(vcpu, irq, inc_eip) != EMULATE_DONE) - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + kvm_inject_realmode_interrupt(vcpu, irq, inc_eip); return; } intr = irq | INTR_INFO_VALID_MASK; @@ -4303,8 +4390,7 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->nmi_known_unmasked = false; if (vmx->rmode.vm86_active) { - if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE) - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0); return; } @@ -4377,8 +4463,11 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) if (enable_unrestricted_guest) return 0; - ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, - PAGE_SIZE * 3); + mutex_lock(&kvm->slots_lock); + ret = __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, + PAGE_SIZE * 3); + mutex_unlock(&kvm->slots_lock); + if (ret) return ret; to_kvm_vmx(kvm)->tss_addr = addr; @@ -4431,7 +4520,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { - if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) { + if (kvm_emulate_instruction(vcpu, 0)) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_vcpu_halt(vcpu); @@ -4482,7 +4571,6 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) u32 intr_info, ex_no, error_code; unsigned long cr2, rip, dr6; u32 vect_info; - enum emulation_result er; vect_info = vmx->idt_vectoring_info; intr_info = vmx->exit_intr_info; @@ -4499,13 +4587,17 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { WARN_ON_ONCE(!enable_vmware_backdoor); - er = kvm_emulate_instruction(vcpu, - EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); - if (er == EMULATE_USER_EXIT) - return 0; - else if (er != EMULATE_DONE) + + /* + * VMware backdoor emulation on #GP interception only handles + * IN{S}, OUT{S}, and RDPMC, none of which generate a non-zero + * error code on #GP. + */ + if (error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); - return 1; + return 1; + } + return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP); } /* @@ -4547,7 +4639,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vcpu->arch.dr6 &= ~DR_TRAP_BITS; vcpu->arch.dr6 |= dr6 | DR6_RTM; if (is_icebp(intr_info)) - skip_emulated_instruction(vcpu); + WARN_ON(!skip_emulated_instruction(vcpu)); kvm_queue_exception(vcpu, DB_VECTOR); return 1; @@ -4577,7 +4669,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) return 0; } -static int handle_external_interrupt(struct kvm_vcpu *vcpu) +static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; return 1; @@ -4602,7 +4694,7 @@ static int handle_io(struct kvm_vcpu *vcpu) ++vcpu->stat.io_exits; if (string) - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; @@ -4676,7 +4768,7 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) static int handle_desc(struct kvm_vcpu *vcpu) { WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); } static int handle_cr(struct kvm_vcpu *vcpu) @@ -4849,50 +4941,6 @@ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) vmcs_writel(GUEST_DR7, val); } -static int handle_cpuid(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_cpuid(vcpu); -} - -static int handle_rdmsr(struct kvm_vcpu *vcpu) -{ - u32 ecx = kvm_rcx_read(vcpu); - struct msr_data msr_info; - - msr_info.index = ecx; - msr_info.host_initiated = false; - if (vmx_get_msr(vcpu, &msr_info)) { - trace_kvm_msr_read_ex(ecx); - kvm_inject_gp(vcpu, 0); - return 1; - } - - trace_kvm_msr_read(ecx, msr_info.data); - - kvm_rax_write(vcpu, msr_info.data & -1u); - kvm_rdx_write(vcpu, (msr_info.data >> 32) & -1u); - return kvm_skip_emulated_instruction(vcpu); -} - -static int handle_wrmsr(struct kvm_vcpu *vcpu) -{ - struct msr_data msr; - u32 ecx = kvm_rcx_read(vcpu); - u64 data = kvm_read_edx_eax(vcpu); - - msr.data = data; - msr.index = ecx; - msr.host_initiated = false; - if (kvm_set_msr(vcpu, &msr) != 0) { - trace_kvm_msr_write_ex(ecx, data); - kvm_inject_gp(vcpu, 0); - return 1; - } - - trace_kvm_msr_write(ecx, data); - return kvm_skip_emulated_instruction(vcpu); -} - static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { kvm_apic_update_ppr(vcpu); @@ -4901,7 +4949,7 @@ static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) static int handle_interrupt_window(struct kvm_vcpu *vcpu) { - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -4909,11 +4957,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) return 1; } -static int handle_halt(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_halt(vcpu); -} - static int handle_vmcall(struct kvm_vcpu *vcpu) { return kvm_emulate_hypercall(vcpu); @@ -4921,7 +4964,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu) static int handle_invd(struct kvm_vcpu *vcpu) { - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); } static int handle_invlpg(struct kvm_vcpu *vcpu) @@ -4955,20 +4998,6 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu) return 1; } -static int handle_xsaves(struct kvm_vcpu *vcpu) -{ - kvm_skip_emulated_instruction(vcpu); - WARN(1, "this should never happen\n"); - return 1; -} - -static int handle_xrstors(struct kvm_vcpu *vcpu) -{ - kvm_skip_emulated_instruction(vcpu); - WARN(1, "this should never happen\n"); - return 1; -} - static int handle_apic_access(struct kvm_vcpu *vcpu) { if (likely(fasteoi)) { @@ -4988,7 +5017,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } } - return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0); } static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) @@ -5057,23 +5086,15 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION && type != INTR_TYPE_EXT_INTR && type != INTR_TYPE_NMI_INTR)) - skip_emulated_instruction(vcpu); - - if (kvm_task_switch(vcpu, tss_selector, - type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason, - has_error_code, error_code) == EMULATE_FAIL) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - return 0; - } + WARN_ON(!skip_emulated_instruction(vcpu)); /* * TODO: What about debug traps on tss switch? * Are we supposed to inject them and update dr6? */ - - return 1; + return kvm_task_switch(vcpu, tss_selector, + type == INTR_TYPE_SOFT_INTR ? idt_index : -1, + reason, has_error_code, error_code); } static int handle_ept_violation(struct kvm_vcpu *vcpu) @@ -5132,21 +5153,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu) && !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { trace_kvm_fast_mmio(gpa); - /* - * Doing kvm_skip_emulated_instruction() depends on undefined - * behavior: Intel's manual doesn't mandate - * VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG - * occurs and while on real hardware it was observed to be set, - * other hypervisors (namely Hyper-V) don't set it, we end up - * advancing IP with some random value. Disable fast mmio when - * running nested and keep it for real hardware in hope that - * VM_EXIT_INSTRUCTION_LEN will always be set correctly. - */ - if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) - return kvm_skip_emulated_instruction(vcpu); - else - return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) == - EMULATE_DONE; + return kvm_skip_emulated_instruction(vcpu); } return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); @@ -5155,7 +5162,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { WARN_ON_ONCE(!enable_vnmi); - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -5165,8 +5172,6 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu) static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - enum emulation_result err = EMULATE_DONE; - int ret = 1; bool intr_window_requested; unsigned count = 130; @@ -5178,7 +5183,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending); intr_window_requested = exec_controls_get(vmx) & - CPU_BASED_VIRTUAL_INTR_PENDING; + CPU_BASED_INTR_WINDOW_EXITING; while (vmx->emulation_required && count-- != 0) { if (intr_window_requested && vmx_interrupt_allowed(vcpu)) @@ -5187,71 +5192,67 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_EVENT, vcpu)) return 1; - err = kvm_emulate_instruction(vcpu, 0); - - if (err == EMULATE_USER_EXIT) { - ++vcpu->stat.mmio_exits; - ret = 0; - goto out; - } - - if (err != EMULATE_DONE) - goto emulation_error; + if (!kvm_emulate_instruction(vcpu, 0)) + return 0; if (vmx->emulation_required && !vmx->rmode.vm86_active && - vcpu->arch.exception.pending) - goto emulation_error; + vcpu->arch.exception.pending) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return 0; + } if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - ret = kvm_vcpu_halt(vcpu); - goto out; + return kvm_vcpu_halt(vcpu); } + /* + * Note, return 1 and not 0, vcpu_run() is responsible for + * morphing the pending signal into the proper return code. + */ if (signal_pending(current)) - goto out; + return 1; + if (need_resched()) schedule(); } -out: - return ret; - -emulation_error: - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - return 0; + return 1; } static void grow_ple_window(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int old = vmx->ple_window; + unsigned int old = vmx->ple_window; vmx->ple_window = __grow_ple_window(old, ple_window, ple_window_grow, ple_window_max); - if (vmx->ple_window != old) + if (vmx->ple_window != old) { vmx->ple_window_dirty = true; - - trace_kvm_ple_window_grow(vcpu->vcpu_id, vmx->ple_window, old); + trace_kvm_ple_window_update(vcpu->vcpu_id, + vmx->ple_window, old); + } } static void shrink_ple_window(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int old = vmx->ple_window; + unsigned int old = vmx->ple_window; vmx->ple_window = __shrink_ple_window(old, ple_window, ple_window_shrink, ple_window); - if (vmx->ple_window != old) + if (vmx->ple_window != old) { vmx->ple_window_dirty = true; - - trace_kvm_ple_window_shrink(vcpu->vcpu_id, vmx->ple_window, old); + trace_kvm_ple_window_update(vcpu->vcpu_id, + vmx->ple_window, old); + } } /* @@ -5503,11 +5504,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_IO_INSTRUCTION] = handle_io, [EXIT_REASON_CR_ACCESS] = handle_cr, [EXIT_REASON_DR_ACCESS] = handle_dr, - [EXIT_REASON_CPUID] = handle_cpuid, - [EXIT_REASON_MSR_READ] = handle_rdmsr, - [EXIT_REASON_MSR_WRITE] = handle_wrmsr, - [EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window, - [EXIT_REASON_HLT] = handle_halt, + [EXIT_REASON_CPUID] = kvm_emulate_cpuid, + [EXIT_REASON_MSR_READ] = kvm_emulate_rdmsr, + [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, + [EXIT_REASON_INTERRUPT_WINDOW] = handle_interrupt_window, + [EXIT_REASON_HLT] = kvm_emulate_halt, [EXIT_REASON_INVD] = handle_invd, [EXIT_REASON_INVLPG] = handle_invlpg, [EXIT_REASON_RDPMC] = handle_rdpmc, @@ -5541,8 +5542,6 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_INVVPID] = handle_vmx_instruction, [EXIT_REASON_RDRAND] = handle_invalid_op, [EXIT_REASON_RDSEED] = handle_invalid_op, - [EXIT_REASON_XSAVES] = handle_xsaves, - [EXIT_REASON_XRSTORS] = handle_xrstors, [EXIT_REASON_PML_FULL] = handle_pml_full, [EXIT_REASON_INVPCID] = handle_invpcid, [EXIT_REASON_VMFUNC] = handle_vmx_instruction, @@ -5795,7 +5794,8 @@ void dump_vmcs(void) * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_vcpu *vcpu) +static int vmx_handle_exit(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exit_reason = vmx->exit_reason; @@ -5881,15 +5881,44 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } } - if (exit_reason < kvm_vmx_max_exit_handlers - && kvm_vmx_exit_handlers[exit_reason]) - return kvm_vmx_exit_handlers[exit_reason](vcpu); - else { - vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", - exit_reason); - kvm_queue_exception(vcpu, UD_VECTOR); + if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { + kvm_skip_emulated_instruction(vcpu); return 1; } + + if (exit_reason >= kvm_vmx_max_exit_handlers) + goto unexpected_vmexit; +#ifdef CONFIG_RETPOLINE + if (exit_reason == EXIT_REASON_MSR_WRITE) + return kvm_emulate_wrmsr(vcpu); + else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) + return handle_preemption_timer(vcpu); + else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW) + return handle_interrupt_window(vcpu); + else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + return handle_external_interrupt(vcpu); + else if (exit_reason == EXIT_REASON_HLT) + return kvm_emulate_halt(vcpu); + else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) + return handle_ept_misconfig(vcpu); +#endif + + exit_reason = array_index_nospec(exit_reason, + kvm_vmx_max_exit_handlers); + if (!kvm_vmx_exit_handlers[exit_reason]) + goto unexpected_vmexit; + + return kvm_vmx_exit_handlers[exit_reason](vcpu); + +unexpected_vmexit: + vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason); + dump_vmcs(); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 1; + vcpu->run->internal.data[0] = exit_reason; + return 0; } /* @@ -5965,17 +5994,17 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu) static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + int tpr_threshold; if (is_guest_mode(vcpu) && nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) return; - if (irr == -1 || tpr < irr) { - vmcs_write32(TPR_THRESHOLD, 0); - return; - } - - vmcs_write32(TPR_THRESHOLD, irr); + tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr; + if (is_guest_mode(vcpu)) + to_vmx(vcpu)->nested.l1_tpr_threshold = tpr_threshold; + else + vmcs_write32(TPR_THRESHOLD, tpr_threshold); } void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) @@ -6089,7 +6118,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) if (pi_test_on(&vmx->pi_desc)) { pi_clear_on(&vmx->pi_desc); /* - * IOMMU can write to PIR.ON, so the barrier matters even on UP. + * IOMMU can write to PID.ON, so the barrier matters even on UP. * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); @@ -6119,7 +6148,10 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { - return pi_test_on(vcpu_to_pi_desc(vcpu)); + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + return pi_test_on(pi_desc) || + (pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc)); } static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -6207,7 +6239,8 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) } STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff); -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) +static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion *exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6215,6 +6248,9 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) handle_external_interrupt_irqoff(vcpu); else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI) handle_exception_nmi_irqoff(vmx); + else if (!is_guest_mode(vcpu) && + vmx->exit_reason == EXIT_REASON_MSR_WRITE) + *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } static bool vmx_has_emulated_msr(int index) @@ -6373,6 +6409,23 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } +static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx) +{ + u32 host_umwait_control; + + if (!vmx_has_waitpkg(vmx)) + return; + + host_umwait_control = get_umwait_control_msr(); + + if (vmx->msr_ia32_umwait_control != host_umwait_control) + add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL, + vmx->msr_ia32_umwait_control, + host_umwait_control, false); + else + clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL); +} + static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6432,9 +6485,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vmx->nested.need_vmcs12_to_shadow_sync) nested_sync_vmcs12_to_shadow(vcpu); - if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); - if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) + if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); @@ -6457,7 +6510,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - kvm_load_guest_xcr0(vcpu); + kvm_load_guest_xsave_state(vcpu); if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && @@ -6467,6 +6520,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); + atomic_switch_umwait_control_msr(vmx); if (enable_preemption_timer) vmx_update_hv_timer(vcpu); @@ -6522,6 +6576,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + if (static_branch_unlikely(&enable_evmcs)) + current_evmcs->hv_vp_id = vcpu->arch.hyperv.vp_index; + /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (vmx->host_debugctlmsr) update_debugctlmsr(vmx->host_debugctlmsr); @@ -6560,7 +6617,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } - kvm_put_guest_xcr0(vcpu); + kvm_load_host_xsave_state(vcpu); vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; @@ -6589,6 +6646,7 @@ static struct kvm *vmx_vm_alloc(void) static void vmx_vm_free(struct kvm *kvm) { + kfree(kvm->arch.hyperv.hv_pa_pg); vfree(to_kvm_vmx(kvm)); } @@ -6601,70 +6659,66 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); - kfree(vmx->guest_msrs); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); - kmem_cache_free(kvm_vcpu_cache, vmx); } -static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) +static int vmx_create_vcpu(struct kvm_vcpu *vcpu) { - int err; struct vcpu_vmx *vmx; unsigned long *msr_bitmap; - int cpu; - - vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); - if (!vmx) - return ERR_PTR(-ENOMEM); + int i, cpu, err; - vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vmx->vcpu.arch.user_fpu) { - printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); - err = -ENOMEM; - goto free_partial_vcpu; - } + BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); + vmx = to_vmx(vcpu); - vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vmx->vcpu.arch.guest_fpu) { - printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); - err = -ENOMEM; - goto free_user_fpu; - } + err = -ENOMEM; vmx->vpid = allocate_vpid(); - err = kvm_vcpu_init(&vmx->vcpu, kvm, id); - if (err) - goto free_vcpu; - - err = -ENOMEM; - /* * If PML is turned on, failure on enabling PML just results in failure * of creating the vcpu, therefore we can simplify PML logic (by * avoiding dealing with cases, such as enabling PML partially on vcpus - * for the guest, etc. + * for the guest), etc. */ if (enable_pml) { vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vmx->pml_pg) - goto uninit_vcpu; + goto free_vpid; } - vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); - BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0]) - > PAGE_SIZE); + BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) != NR_SHARED_MSRS); - if (!vmx->guest_msrs) - goto free_pml; + for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { + u32 index = vmx_msr_index[i]; + u32 data_low, data_high; + int j = vmx->nmsrs; + + if (rdmsr_safe(index, &data_low, &data_high) < 0) + continue; + if (wrmsr_safe(index, data_low, data_high) < 0) + continue; + + vmx->guest_msrs[j].index = i; + vmx->guest_msrs[j].data = 0; + switch (index) { + case MSR_IA32_TSX_CTRL: + /* + * No need to pass TSX_CTRL_CPUID_CLEAR through, so + * let's avoid changing CPUID bits under the host + * kernel's feet. + */ + vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + break; + default: + vmx->guest_msrs[j].mask = -1ull; + break; + } + ++vmx->nmsrs; + } err = alloc_loaded_vmcs(&vmx->vmcs01); if (err < 0) - goto free_msrs; + goto free_pml; msr_bitmap = vmx->vmcs01.msr_bitmap; vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R); @@ -6674,7 +6728,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); - if (kvm_cstate_in_guest(kvm)) { + if (kvm_cstate_in_guest(vcpu->kvm)) { vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R); vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); @@ -6684,19 +6738,19 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); - vmx_vcpu_load(&vmx->vcpu, cpu); - vmx->vcpu.cpu = cpu; - vmx_vcpu_setup(vmx); - vmx_vcpu_put(&vmx->vcpu); + vmx_vcpu_load(vcpu, cpu); + vcpu->cpu = cpu; + init_vmcs(vmx); + vmx_vcpu_put(vcpu); put_cpu(); - if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { - err = alloc_apic_access_page(kvm); + if (cpu_need_virtualize_apic_accesses(vcpu)) { + err = alloc_apic_access_page(vcpu->kvm); if (err) goto free_vmcs; } if (enable_ept && !enable_unrestricted_guest) { - err = init_rmode_identity_map(kvm); + err = init_rmode_identity_map(vcpu->kvm); if (err) goto free_vmcs; } @@ -6704,14 +6758,15 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, vmx_capability.ept, - kvm_vcpu_apicv_active(&vmx->vcpu)); + kvm_vcpu_apicv_active(vcpu)); else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; - vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; + vcpu->arch.microcode_version = 0x100000000ULL; + vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; /* * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR @@ -6722,24 +6777,15 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->ept_pointer = INVALID_PAGE; - return &vmx->vcpu; + return 0; free_vmcs: free_loaded_vmcs(vmx->loaded_vmcs); -free_msrs: - kfree(vmx->guest_msrs); free_pml: vmx_destroy_pml_buffer(vmx); -uninit_vcpu: - kvm_vcpu_uninit(&vmx->vcpu); -free_vcpu: +free_vpid: free_vpid(vmx->vpid); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); -free_user_fpu: - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); -free_partial_vcpu: - kmem_cache_free(kvm_vcpu_cache, vmx); - return ERR_PTR(err); + return err; } #define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" @@ -6775,6 +6821,7 @@ static int vmx_vm_init(struct kvm *kvm) break; } } + kvm_apicv_init(kvm, enable_apicv); return 0; } @@ -6783,6 +6830,12 @@ static int __init vmx_check_processor_compat(void) struct vmcs_config vmcs_conf; struct vmx_capability vmx_cap; + if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || + !this_cpu_has(X86_FEATURE_VMX)) { + pr_err("kvm: VMX is disabled on CPU %d\n", smp_processor_id()); + return -EIO; + } + if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) return -EIO; if (nested) @@ -6885,27 +6938,28 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) } while (0) entry = kvm_find_cpuid_entry(vcpu, 0x1, 0); - cr4_fixed1_update(X86_CR4_VME, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_PVI, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_TSD, edx, bit(X86_FEATURE_TSC)); - cr4_fixed1_update(X86_CR4_DE, edx, bit(X86_FEATURE_DE)); - cr4_fixed1_update(X86_CR4_PSE, edx, bit(X86_FEATURE_PSE)); - cr4_fixed1_update(X86_CR4_PAE, edx, bit(X86_FEATURE_PAE)); - cr4_fixed1_update(X86_CR4_MCE, edx, bit(X86_FEATURE_MCE)); - cr4_fixed1_update(X86_CR4_PGE, edx, bit(X86_FEATURE_PGE)); - cr4_fixed1_update(X86_CR4_OSFXSR, edx, bit(X86_FEATURE_FXSR)); - cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM)); - cr4_fixed1_update(X86_CR4_VMXE, ecx, bit(X86_FEATURE_VMX)); - cr4_fixed1_update(X86_CR4_SMXE, ecx, bit(X86_FEATURE_SMX)); - cr4_fixed1_update(X86_CR4_PCIDE, ecx, bit(X86_FEATURE_PCID)); - cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, bit(X86_FEATURE_XSAVE)); + cr4_fixed1_update(X86_CR4_VME, edx, feature_bit(VME)); + cr4_fixed1_update(X86_CR4_PVI, edx, feature_bit(VME)); + cr4_fixed1_update(X86_CR4_TSD, edx, feature_bit(TSC)); + cr4_fixed1_update(X86_CR4_DE, edx, feature_bit(DE)); + cr4_fixed1_update(X86_CR4_PSE, edx, feature_bit(PSE)); + cr4_fixed1_update(X86_CR4_PAE, edx, feature_bit(PAE)); + cr4_fixed1_update(X86_CR4_MCE, edx, feature_bit(MCE)); + cr4_fixed1_update(X86_CR4_PGE, edx, feature_bit(PGE)); + cr4_fixed1_update(X86_CR4_OSFXSR, edx, feature_bit(FXSR)); + cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, feature_bit(XMM)); + cr4_fixed1_update(X86_CR4_VMXE, ecx, feature_bit(VMX)); + cr4_fixed1_update(X86_CR4_SMXE, ecx, feature_bit(SMX)); + cr4_fixed1_update(X86_CR4_PCIDE, ecx, feature_bit(PCID)); + cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, feature_bit(XSAVE)); entry = kvm_find_cpuid_entry(vcpu, 0x7, 0); - cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, bit(X86_FEATURE_FSGSBASE)); - cr4_fixed1_update(X86_CR4_SMEP, ebx, bit(X86_FEATURE_SMEP)); - cr4_fixed1_update(X86_CR4_SMAP, ebx, bit(X86_FEATURE_SMAP)); - cr4_fixed1_update(X86_CR4_PKE, ecx, bit(X86_FEATURE_PKU)); - cr4_fixed1_update(X86_CR4_UMIP, ecx, bit(X86_FEATURE_UMIP)); + cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, feature_bit(FSGSBASE)); + cr4_fixed1_update(X86_CR4_SMEP, ebx, feature_bit(SMEP)); + cr4_fixed1_update(X86_CR4_SMAP, ebx, feature_bit(SMAP)); + cr4_fixed1_update(X86_CR4_PKE, ecx, feature_bit(PKU)); + cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); + cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); #undef cr4_fixed1_update } @@ -7000,6 +7054,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ + vcpu->arch.xsaves_enabled = false; + if (cpu_has_secondary_exec_ctrls()) { vmx_compute_secondary_exec_control(vmx); vmcs_set_secondary_exec_control(vmx); @@ -7007,10 +7064,12 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (nested_vmx_allowed(vcpu)) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= - FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + FEAT_CTL_VMX_ENABLED_INSIDE_SMX | + FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; else to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= - ~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + ~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX | + FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX); if (nested_vmx_allowed(vcpu)) { nested_vmx_cr_fixed1_bits_update(vcpu); @@ -7020,12 +7079,21 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (boot_cpu_has(X86_FEATURE_INTEL_PT) && guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); + + if (boot_cpu_has(X86_FEATURE_RTM)) { + struct shared_msr_entry *msr; + msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL); + if (msr) { + bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); + vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); + } + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { if (func == 1 && nested) - entry->ecx |= bit(X86_FEATURE_VMX); + entry->ecx |= feature_bit(VMX); } static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -7369,10 +7437,14 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * irqbalance to make the interrupts single-CPU. * * We will support full lowest-priority interrupt later. + * + * In addition, we can only inject generic interrupts using + * the PI mechanism, refuse to route others through it. */ kvm_set_msi_irq(kvm, e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || + !kvm_irq_is_postable(&irq)) { /* * Make sure the IRTE is in remapped mode if * we don't handle it in posted mode. @@ -7416,10 +7488,10 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) { if (vcpu->arch.mcg_cap & MCG_LMCE_P) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= - FEATURE_CONTROL_LMCE; + FEAT_CTL_LMCE_ENABLED; else to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= - ~FEATURE_CONTROL_LMCE; + ~FEAT_CTL_LMCE_ENABLED; } static int vmx_smi_allowed(struct kvm_vcpu *vcpu) @@ -7474,6 +7546,11 @@ static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) return false; } +static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.vmxon; +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; @@ -7499,9 +7576,6 @@ static __init int hardware_setup(void) WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); } - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); - if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; @@ -7649,6 +7723,14 @@ static __exit void hardware_unsetup(void) free_kvm_area(); } +static bool vmx_check_apicv_inhibit_reasons(ulong bit) +{ + ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_HYPERV); + + return supported & BIT(bit); +} + static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -7682,7 +7764,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_cpl = vmx_get_cpl, .get_cs_db_l_bits = vmx_get_cs_db_l_bits, .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, - .decache_cr3 = vmx_decache_cr3, .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, .set_cr0 = vmx_set_cr0, .set_cr3 = vmx_set_cr3, @@ -7722,10 +7803,10 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .update_cr8_intercept = update_cr8_intercept, .set_virtual_apic_mode = vmx_set_virtual_apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .get_enable_apicv = vmx_get_enable_apicv, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, .apicv_post_state_restore = vmx_apicv_post_state_restore, + .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, @@ -7762,6 +7843,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .xsaves_supported = vmx_xsaves_supported, .umip_emulated = vmx_umip_emulated, .pt_supported = vmx_pt_supported, + .pku_supported = vmx_pku_supported, .request_immediate_exit = vmx_request_immediate_exit, @@ -7797,7 +7879,9 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .set_nested_state = NULL, .get_vmcs12_pages = NULL, .nested_enable_evmcs = NULL, + .nested_get_evmcs_version = NULL, .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, + .apic_init_signal_blocked = vmx_apic_init_signal_blocked, }; static void vmx_cleanup_l1d_flush(void) @@ -7834,6 +7918,7 @@ static void vmx_exit(void) if (!vp_ap) continue; + vp_ap->nested_control.features.directhypercall = 0; vp_ap->current_nested_vmcs = 0; vp_ap->enlighten_vmentry = 0; } @@ -7873,6 +7958,11 @@ static int __init vmx_init(void) pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n"); static_branch_enable(&enable_evmcs); } + + if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) + vmx_x86_ops.enable_direct_tlbflush + = hv_enable_direct_tlbflush; + } else { enlightened_vmcs = false; } @@ -7890,12 +7980,10 @@ static int __init vmx_init(void) * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ - if (boot_cpu_has(X86_BUG_L1TF)) { - r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } + r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); + if (r) { + vmx_exit(); + return r; } #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 82d0bc3a4d52..7f42cf3dcd70 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -14,17 +14,25 @@ extern const u32 vmx_msr_index[]; extern u64 host_efer; +extern u32 get_umwait_control_msr(void); + #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 #define MSR_TYPE_RW 3 #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) -#define NR_AUTOLOAD_MSRS 8 +#ifdef CONFIG_X86_64 +#define NR_SHARED_MSRS 7 +#else +#define NR_SHARED_MSRS 4 +#endif + +#define NR_LOADSTORE_MSRS 8 struct vmx_msrs { unsigned int nr; - struct vmx_msr_entry val[NR_AUTOLOAD_MSRS]; + struct vmx_msr_entry val[NR_LOADSTORE_MSRS]; }; struct shared_msr_entry { @@ -165,6 +173,9 @@ struct nested_vmx { u64 vmcs01_debugctl; u64 vmcs01_guest_bndcfgs; + /* to migrate it to L1 if L2 writes to L1's CR8 directly */ + int l1_tpr_threshold; + u16 vpid02; u16 last_vpid; @@ -201,7 +212,7 @@ struct vcpu_vmx { u32 idt_vectoring_info; ulong rflags; - struct shared_msr_entry *guest_msrs; + struct shared_msr_entry guest_msrs[NR_SHARED_MSRS]; int nmsrs; int save_nmsrs; bool guest_msrs_ready; @@ -211,6 +222,7 @@ struct vcpu_vmx { #endif u64 spec_ctrl; + u32 msr_ia32_umwait_control; u32 secondary_exec_control; @@ -227,6 +239,10 @@ struct vcpu_vmx { struct vmx_msrs host; } msr_autoload; + struct msr_autostore { + struct vmx_msrs guest; + } msr_autostore; + struct { int vm86_active; ulong save_rflags; @@ -253,7 +269,7 @@ struct vcpu_vmx { struct nested_vmx nested; /* Dynamic PLE window. */ - int ple_window; + unsigned int ple_window; bool ple_window_dirty; bool req_immediate_exit; @@ -273,7 +289,7 @@ struct vcpu_vmx { /* * Only bits masked by msr_ia32_feature_control_valid_bits can be set in - * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included + * msr_ia32_feature_control. FEAT_CTL_LOCKED is always included * in msr_ia32_feature_control_valid_bits. */ u64 msr_ia32_feature_control; @@ -331,6 +347,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct vcpu_vmx *vmx); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); +int vmx_find_msr_index(struct vmx_msrs *m, u32 msr); #define POSTED_INTR_ON 0 #define POSTED_INTR_SN 1 @@ -352,6 +369,11 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } +static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) +{ + return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); +} + static inline void pi_set_sn(struct pi_desc *pi_desc) { set_bit(POSTED_INTR_SN, @@ -370,6 +392,12 @@ static inline void pi_clear_on(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + static inline int pi_test_on(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_ON, @@ -497,6 +525,12 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx) vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); } +static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) +{ + return vmx->secondary_exec_control & + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; +} + void dump_vmcs(void); #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 93b0bd45ac73..fb5d64ebc35d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -26,6 +26,7 @@ #include "cpuid.h" #include "pmu.h" #include "hyperv.h" +#include "lapic.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -68,6 +69,7 @@ #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/intel_pt.h> +#include <asm/emulate_prefix.h> #include <clocksource/hyperv_timer.h> #define CREATE_TRACE_POINTS @@ -92,8 +94,10 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; + +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -176,6 +180,8 @@ struct kvm_shared_msrs { static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; static struct kvm_shared_msrs __percpu *shared_msrs; +static u64 __read_mostly host_xss; + struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, { "pf_guest", VCPU_STAT(pf_guest) }, @@ -212,7 +218,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, - { "largepages", VM_STAT(lpages) }, + { "largepages", VM_STAT(lpages, .mode = 0444) }, + { "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) }, { "max_mmu_page_hash_collisions", VM_STAT(max_mmu_page_hash_collisions) }, { NULL } @@ -259,23 +266,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn) } } -static void shared_msr_update(unsigned slot, u32 msr) -{ - u64 value; - unsigned int cpu = smp_processor_id(); - struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); - - /* only read, and nobody should modify it at this time, - * so don't need lock */ - if (slot >= shared_msrs_global.nr) { - printk(KERN_ERR "kvm: invalid MSR slot!"); - return; - } - rdmsrl_safe(msr, &value); - smsr->values[slot].host = value; - smsr->values[slot].curr = value; -} - void kvm_define_shared_msr(unsigned slot, u32 msr) { BUG_ON(slot >= KVM_NR_SHARED_MSRS); @@ -287,10 +277,16 @@ EXPORT_SYMBOL_GPL(kvm_define_shared_msr); static void kvm_shared_msr_cpu_online(void) { - unsigned i; + unsigned int cpu = smp_processor_id(); + struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + u64 value; + int i; - for (i = 0; i < shared_msrs_global.nr; ++i) - shared_msr_update(i, shared_msrs_global.msrs[i]); + for (i = 0; i < shared_msrs_global.nr; ++i) { + rdmsrl_safe(shared_msrs_global.msrs[i], &value); + smsr->values[i].host = value; + smsr->values[i].curr = value; + } } int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) @@ -299,13 +295,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); int err; - if (((value ^ smsr->values[slot].curr) & mask) == 0) + value = (value & mask) | (smsr->values[slot].host & ~mask); + if (value == smsr->values[slot].curr) return 0; - smsr->values[slot].curr = value; err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); if (err) return 1; + smsr->values[slot].curr = value; if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); @@ -360,7 +357,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base); asmlinkage __visible void kvm_spurious_fault(void) { /* Fault while not rebooting. We want the trace. */ - BUG(); + BUG_ON(!kvm_rebooting); } EXPORT_SYMBOL_GPL(kvm_spurious_fault); @@ -441,6 +438,14 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * for #DB exceptions under VMX. */ vcpu->arch.dr6 ^= payload & DR6_RTM; + + /* + * The #DB payload is defined as compatible with the 'pending + * debug exceptions' field under VMX, not DR6. While bit 12 is + * defined in the 'pending debug exceptions' field (enabled + * breakpoint), it is reserved and must be zero in DR6. + */ + vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: vcpu->arch.cr2 = payload; @@ -493,19 +498,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; - /* - * In guest mode, payload delivery should be deferred, - * so that the L1 hypervisor can intercept #PF before - * CR2 is modified (or intercept #DB before DR6 is - * modified under nVMX). However, for ABI - * compatibility with KVM_GET_VCPU_EVENTS and - * KVM_SET_VCPU_EVENTS, we can't delay payload - * delivery unless userspace has enabled this - * functionality via the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD. - */ - if (!vcpu->kvm->arch.exception_payload_enabled || - !is_guest_mode(vcpu)) + if (!is_guest_mode(vcpu)) kvm_deliver_exception_payload(vcpu); return; } @@ -674,8 +667,14 @@ static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, data, offset, len, access); } +static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) +{ + return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) | + rsvd_bits(1, 2); +} + /* - * Load the pae pdptrs. Return true is they are all valid. + * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) { @@ -694,8 +693,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if ((pdpte[i] & PT_PRESENT_MASK) && - (pdpte[i] & - vcpu->arch.mmu->guest_rsvd_check.rsvd_bits_mask[0][2])) { + (pdpte[i] & pdptr_rsvd_bits(vcpu))) { ret = 0; goto out; } @@ -703,10 +701,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) ret = 1; memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + out: return ret; @@ -716,7 +712,6 @@ EXPORT_SYMBOL_GPL(load_pdptrs); bool pdptrs_changed(struct kvm_vcpu *vcpu) { u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; - bool changed = true; int offset; gfn_t gfn; int r; @@ -724,8 +719,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) if (!is_pae_paging(vcpu)) return false; - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail)) + if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) return true; gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT; @@ -733,11 +727,9 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), PFERR_USER_MASK | PFERR_WRITE_MASK); if (r < 0) - goto out; - changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; -out: + return true; - return changed; + return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; } EXPORT_SYMBOL_GPL(pdptrs_changed); @@ -806,27 +798,34 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) { - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && - !vcpu->guest_xcr0_loaded) { - /* kvm_set_xcr() also depends on this */ + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); - vcpu->guest_xcr0_loaded = 1; + + if (vcpu->arch.xsaves_enabled && + vcpu->arch.ia32_xss != host_xss) + wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } } -EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); +EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); -void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) { - if (vcpu->guest_xcr0_loaded) { + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); - vcpu->guest_xcr0_loaded = 0; + + if (vcpu->arch.xsaves_enabled && + vcpu->arch.ia32_xss != host_xss) + wrmsrl(MSR_IA32_XSS, host_xss); } + } -EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); +EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -879,34 +878,58 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); -int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +#define __cr4_reserved_bits(__cpu_has, __c) \ +({ \ + u64 __reserved_bits = CR4_RESERVED_BITS; \ + \ + if (!__cpu_has(__c, X86_FEATURE_XSAVE)) \ + __reserved_bits |= X86_CR4_OSXSAVE; \ + if (!__cpu_has(__c, X86_FEATURE_SMEP)) \ + __reserved_bits |= X86_CR4_SMEP; \ + if (!__cpu_has(__c, X86_FEATURE_SMAP)) \ + __reserved_bits |= X86_CR4_SMAP; \ + if (!__cpu_has(__c, X86_FEATURE_FSGSBASE)) \ + __reserved_bits |= X86_CR4_FSGSBASE; \ + if (!__cpu_has(__c, X86_FEATURE_PKU)) \ + __reserved_bits |= X86_CR4_PKE; \ + if (!__cpu_has(__c, X86_FEATURE_LA57)) \ + __reserved_bits |= X86_CR4_LA57; \ + if (!__cpu_has(__c, X86_FEATURE_UMIP)) \ + __reserved_bits |= X86_CR4_UMIP; \ + __reserved_bits; \ +}) + +static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) { - unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - if (cr4 & CR4_RESERVED_BITS) - return 1; + if (cpuid_ecx(0x7) & feature_bit(LA57)) + reserved_bits &= ~X86_CR4_LA57; - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE)) - return 1; + if (kvm_x86_ops->umip_emulated()) + reserved_bits &= ~X86_CR4_UMIP; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP)) - return 1; + return reserved_bits; +} - if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP)) - return 1; +static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + if (cr4 & cr4_reserved_bits) + return -EINVAL; - if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE)) - return 1; + if (cr4 & __cr4_reserved_bits(guest_cpuid_has, vcpu)) + return -EINVAL; - if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE)) - return 1; + return 0; +} - if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57)) - return 1; +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long old_cr4 = kvm_read_cr4(vcpu); + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; - if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP)) + if (kvm_valid_cr4(vcpu, cr4)) return 1; if (is_long_mode(vcpu)) { @@ -970,7 +993,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush); vcpu->arch.cr3 = cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); return 0; } @@ -1039,9 +1062,11 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - vcpu->arch.db[dr] = val; + vcpu->arch.db[array_index_nospec(dr, size)] = val; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) vcpu->arch.eff_db[dr] = val; break; @@ -1056,7 +1081,7 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) case 5: /* fall through */ default: /* 7 */ - if (val & 0xffffffff00000000ULL) + if (!kvm_dr7_valid(val)) return -1; /* #GP */ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; kvm_update_dr7(vcpu); @@ -1078,9 +1103,11 @@ EXPORT_SYMBOL_GPL(kvm_set_dr); int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - *val = vcpu->arch.db[dr]; + *val = vcpu->arch.db[array_index_nospec(dr, size)]; break; case 4: /* fall through */ @@ -1119,20 +1146,22 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * - * This list is modified at module load time to reflect the + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) + * extract the supported MSRs from the related const lists. + * msrs_to_save is selected from the msrs_to_save_all to reflect the * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs + * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs * may depend on host virtualization features rather than host cpu features. */ -static u32 msrs_to_save[] = { +static const u32 msrs_to_save_all[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, MSR_IA32_SPEC_CTRL, MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, @@ -1140,11 +1169,36 @@ static u32 msrs_to_save[] = { MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, + MSR_IA32_UMWAIT_CONTROL, + + MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3, + MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, + MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, + MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, + MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, + MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, + MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, + MSR_ARCH_PERFMON_PERFCTR0 + 8, MSR_ARCH_PERFMON_PERFCTR0 + 9, + MSR_ARCH_PERFMON_PERFCTR0 + 10, MSR_ARCH_PERFMON_PERFCTR0 + 11, + MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13, + MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15, + MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17, + MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, + MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, + MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, + MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, + MSR_ARCH_PERFMON_EVENTSEL0 + 8, MSR_ARCH_PERFMON_EVENTSEL0 + 9, + MSR_ARCH_PERFMON_EVENTSEL0 + 10, MSR_ARCH_PERFMON_EVENTSEL0 + 11, + MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, + MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, + MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, }; +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; static unsigned num_msrs_to_save; -static u32 emulated_msrs[] = { +static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, @@ -1177,13 +1231,14 @@ static u32 emulated_msrs[] = { MSR_MISC_FEATURES_ENABLES, MSR_AMD64_VIRT_SPEC_CTRL, MSR_IA32_POWER_CTL, + MSR_IA32_UCODE_REV, /* * The following list leaves out MSRs whose values are determined * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs. * We always support the "true" VMX control MSRs, even if the host * processor does not, so I am putting these registers here rather - * than in msrs_to_save. + * than in msrs_to_save_all. */ MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, @@ -1202,13 +1257,14 @@ static u32 emulated_msrs[] = { MSR_KVM_POLL_CONTROL, }; +static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; static unsigned num_emulated_msrs; /* * List of msr numbers which are used to expose MSR-based features that * can be used by a hypervisor to validate requested CPU features. */ -static u32 msr_based_features[] = { +static const u32 msr_based_features_all[] = { MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, MSR_IA32_VMX_PINBASED_CTLS, @@ -1233,6 +1289,7 @@ static u32 msr_based_features[] = { MSR_IA32_ARCH_CAPABILITIES, }; +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; static unsigned int num_msr_based_features; static u64 kvm_get_arch_capabilities(void) @@ -1243,6 +1300,14 @@ static u64 kvm_get_arch_capabilities(void) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); /* + * If nx_huge_pages is enabled, KVM's shadow paging will ensure that + * the nested hypervisor runs with NX huge pages. If it is not, + * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 guests, so it need not worry about its own (L2) guests. + */ + data |= ARCH_CAP_PSCHANGE_MC_NO; + + /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us @@ -1254,6 +1319,24 @@ static u64 kvm_get_arch_capabilities(void) if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + data |= ARCH_CAP_RDCL_NO; + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + data |= ARCH_CAP_SSB_NO; + if (!boot_cpu_has_bug(X86_BUG_MDS)) + data |= ARCH_CAP_MDS_NO; + + /* + * On TAA affected systems: + * - nothing to do if TSX is disabled on the host. + * - we emulate TSX_CTRL if present on the host. + * This lets the guest use VERW to clear CPU buffers. + */ + if (!boot_cpu_has(X86_FEATURE_RTM)) + data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR); + else if (!boot_cpu_has_bug(X86_BUG_TAA)) + data |= ARCH_CAP_TAA_NO; + return data; } @@ -1351,19 +1434,23 @@ void kvm_enable_efer_bits(u64 mask) EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); /* - * Writes msr value into into the appropriate "register". + * Write @data into the MSR specified by @index. Select MSR specific fault + * checks are bypassed if @host_initiated is %true. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) +static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, + bool host_initiated) { - switch (msr->index) { + struct msr_data msr; + + switch (index) { case MSR_FS_BASE: case MSR_GS_BASE: case MSR_KERNEL_GS_BASE: case MSR_CSTAR: case MSR_LSTAR: - if (is_noncanonical_address(msr->data, vcpu)) + if (is_noncanonical_address(data, vcpu)) return 1; break; case MSR_IA32_SYSENTER_EIP: @@ -1380,54 +1467,158 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * value, and that something deterministic happens if the guest * invokes 64-bit SYSENTER. */ - msr->data = get_canonical(msr->data, vcpu_virt_addr_bits(vcpu)); + data = get_canonical(data, vcpu_virt_addr_bits(vcpu)); } - return kvm_x86_ops->set_msr(vcpu, msr); + + msr.data = data; + msr.index = index; + msr.host_initiated = host_initiated; + + return kvm_x86_ops->set_msr(vcpu, &msr); } -EXPORT_SYMBOL_GPL(kvm_set_msr); /* - * Adapt set_msr() to msr_io()'s calling convention + * Read the MSR specified by @index into @data. Select MSR specific fault + * checks are bypassed if @host_initiated is %true. + * Returns 0 on success, non-0 otherwise. + * Assumes vcpu_load() was already called. */ -static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) { struct msr_data msr; - int r; + int ret; msr.index = index; - msr.host_initiated = true; - r = kvm_get_msr(vcpu, &msr); - if (r) - return r; + msr.host_initiated = host_initiated; - *data = msr.data; - return 0; + ret = kvm_x86_ops->get_msr(vcpu, &msr); + if (!ret) + *data = msr.data; + return ret; } -static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) { - struct msr_data msr; + return __kvm_get_msr(vcpu, index, data, false); +} +EXPORT_SYMBOL_GPL(kvm_get_msr); - msr.data = *data; - msr.index = index; - msr.host_initiated = true; - return kvm_set_msr(vcpu, &msr); +int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) +{ + return __kvm_set_msr(vcpu, index, data, false); +} +EXPORT_SYMBOL_GPL(kvm_set_msr); + +int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) +{ + u32 ecx = kvm_rcx_read(vcpu); + u64 data; + + if (kvm_get_msr(vcpu, ecx, &data)) { + trace_kvm_msr_read_ex(ecx); + kvm_inject_gp(vcpu, 0); + return 1; + } + + trace_kvm_msr_read(ecx, data); + + kvm_rax_write(vcpu, data & -1u); + kvm_rdx_write(vcpu, (data >> 32) & -1u); + return kvm_skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr); + +int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) +{ + u32 ecx = kvm_rcx_read(vcpu); + u64 data = kvm_read_edx_eax(vcpu); + + if (kvm_set_msr(vcpu, ecx, data)) { + trace_kvm_msr_write_ex(ecx, data); + kvm_inject_gp(vcpu, 0); + return 1; + } + + trace_kvm_msr_write(ecx, data); + return kvm_skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); + +/* + * The fast path for frequent and performance sensitive wrmsr emulation, + * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces + * the latency of virtual IPI by avoiding the expensive bits of transitioning + * from guest to host, e.g. reacquiring KVM's SRCU lock. In contrast to the + * other cases which must be called after interrupts are enabled on the host. + */ +static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data) +{ + if (lapic_in_kernel(vcpu) && apic_x2apic_mode(vcpu->arch.apic) && + ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && + ((data & APIC_MODE_MASK) == APIC_DM_FIXED)) { + + kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR2, (u32)(data >> 32)); + return kvm_lapic_reg_write(vcpu->arch.apic, APIC_ICR, (u32)data); + } + + return 1; +} + +enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) +{ + u32 msr = kvm_rcx_read(vcpu); + u64 data = kvm_read_edx_eax(vcpu); + int ret = 0; + + switch (msr) { + case APIC_BASE_MSR + (APIC_ICR >> 4): + ret = handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); + break; + default: + return EXIT_FASTPATH_NONE; + } + + if (!ret) { + trace_kvm_msr_write(msr, data); + return EXIT_FASTPATH_SKIP_EMUL_INS; + } + + return EXIT_FASTPATH_NONE; +} +EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff); + +/* + * Adapt set_msr() to msr_io()'s calling convention + */ +static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + return __kvm_get_msr(vcpu, index, data, true); +} + +static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + return __kvm_set_msr(vcpu, index, *data, true); } #ifdef CONFIG_X86_64 +struct pvclock_clock { + int vclock_mode; + u64 cycle_last; + u64 mask; + u32 mult; + u32 shift; + u64 base_cycles; + u64 offset; +}; + struct pvclock_gtod_data { seqcount_t seq; - struct { /* extract of a clocksource struct */ - int vclock_mode; - u64 cycle_last; - u64 mask; - u32 mult; - u32 shift; - } clock; + struct pvclock_clock clock; /* extract of a clocksource struct */ + struct pvclock_clock raw_clock; /* extract of a clocksource struct */ - u64 boot_ns; - u64 nsec_base; + ktime_t offs_boot; u64 wall_time_sec; }; @@ -1436,9 +1627,6 @@ static struct pvclock_gtod_data pvclock_gtod_data; static void update_pvclock_gtod(struct timekeeper *tk) { struct pvclock_gtod_data *vdata = &pvclock_gtod_data; - u64 boot_ns; - - boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot)); write_seqcount_begin(&vdata->seq); @@ -1448,14 +1636,35 @@ static void update_pvclock_gtod(struct timekeeper *tk) vdata->clock.mask = tk->tkr_mono.mask; vdata->clock.mult = tk->tkr_mono.mult; vdata->clock.shift = tk->tkr_mono.shift; + vdata->clock.base_cycles = tk->tkr_mono.xtime_nsec; + vdata->clock.offset = tk->tkr_mono.base; - vdata->boot_ns = boot_ns; - vdata->nsec_base = tk->tkr_mono.xtime_nsec; + vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->archdata.vclock_mode; + vdata->raw_clock.cycle_last = tk->tkr_raw.cycle_last; + vdata->raw_clock.mask = tk->tkr_raw.mask; + vdata->raw_clock.mult = tk->tkr_raw.mult; + vdata->raw_clock.shift = tk->tkr_raw.shift; + vdata->raw_clock.base_cycles = tk->tkr_raw.xtime_nsec; + vdata->raw_clock.offset = tk->tkr_raw.base; vdata->wall_time_sec = tk->xtime_sec; + vdata->offs_boot = tk->offs_boot; + write_seqcount_end(&vdata->seq); } + +static s64 get_kvmclock_base_ns(void) +{ + /* Count up from boot time, but with the frequency of the raw clock. */ + return ktime_to_ns(ktime_add(ktime_get_raw(), pvclock_gtod_data.offs_boot)); +} +#else +static s64 get_kvmclock_base_ns(void) +{ + /* Master clock not used, so we can just use CLOCK_BOOTTIME. */ + return ktime_get_boottime_ns(); +} #endif void kvm_set_pending_timer(struct kvm_vcpu *vcpu) @@ -1469,7 +1678,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) int version; int r; struct pvclock_wall_clock wc; - struct timespec64 boot; + u64 wall_nsec; if (!wall_clock) return; @@ -1489,17 +1698,12 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) /* * The guest calculates current wall clock time by adding * system time (updated by kvm_guest_time_update below) to the - * wall clock specified here. guest system time equals host - * system time for us, thus we must fill in host boot time here. + * wall clock specified here. We do the reverse here. */ - getboottime64(&boot); + wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm); - if (kvm->arch.kvmclock_offset) { - struct timespec64 ts = ns_to_timespec64(kvm->arch.kvmclock_offset); - boot = timespec64_sub(boot, ts); - } - wc.sec = (u32)boot.tv_sec; /* overflow in 2106 guest time */ - wc.nsec = boot.tv_nsec; + wc.nsec = do_div(wall_nsec, 1000000000); + wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */ wc.version = version; kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); @@ -1747,7 +1951,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_compute_tsc_offset(vcpu, data); - ns = ktime_get_boottime_ns(); + ns = get_kvmclock_base_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { @@ -1877,21 +2081,21 @@ static u64 read_tsc(void) return last; } -static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) +static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, + int *mode) { long v; - struct pvclock_gtod_data *gtod = &pvclock_gtod_data; u64 tsc_pg_val; - switch (gtod->clock.vclock_mode) { + switch (clock->vclock_mode) { case VCLOCK_HVCLOCK: tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(), tsc_timestamp); if (tsc_pg_val != U64_MAX) { /* TSC page valid */ *mode = VCLOCK_HVCLOCK; - v = (tsc_pg_val - gtod->clock.cycle_last) & - gtod->clock.mask; + v = (tsc_pg_val - clock->cycle_last) & + clock->mask; } else { /* TSC page invalid */ *mode = VCLOCK_NONE; @@ -1900,8 +2104,8 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) case VCLOCK_TSC: *mode = VCLOCK_TSC; *tsc_timestamp = read_tsc(); - v = (*tsc_timestamp - gtod->clock.cycle_last) & - gtod->clock.mask; + v = (*tsc_timestamp - clock->cycle_last) & + clock->mask; break; default: *mode = VCLOCK_NONE; @@ -1910,10 +2114,10 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) if (*mode == VCLOCK_NONE) *tsc_timestamp = v = 0; - return v * gtod->clock.mult; + return v * clock->mult; } -static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) +static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -1922,10 +2126,10 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) do { seq = read_seqcount_begin(>od->seq); - ns = gtod->nsec_base; - ns += vgettsc(tsc_timestamp, &mode); - ns >>= gtod->clock.shift; - ns += gtod->boot_ns; + ns = gtod->raw_clock.base_cycles; + ns += vgettsc(>od->raw_clock, tsc_timestamp, &mode); + ns >>= gtod->raw_clock.shift; + ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot)); } while (unlikely(read_seqcount_retry(>od->seq, seq))); *t = ns; @@ -1942,8 +2146,8 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) do { seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_sec; - ns = gtod->nsec_base; - ns += vgettsc(tsc_timestamp, &mode); + ns = gtod->clock.base_cycles; + ns += vgettsc(>od->clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -1960,7 +2164,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns, + return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns, tsc_timestamp)); } @@ -2085,7 +2289,7 @@ u64 get_kvmclock_ns(struct kvm *kvm) spin_lock(&ka->pvclock_gtod_sync_lock); if (!ka->use_master_clock) { spin_unlock(&ka->pvclock_gtod_sync_lock); - return ktime_get_boottime_ns() + ka->kvmclock_offset; + return get_kvmclock_base_ns() + ka->kvmclock_offset; } hv_clock.tsc_timestamp = ka->master_cycle_now; @@ -2101,7 +2305,7 @@ u64 get_kvmclock_ns(struct kvm *kvm) &hv_clock.tsc_to_system_mul); ret = __pvclock_read_cycles(&hv_clock, rdtsc()); } else - ret = ktime_get_boottime_ns() + ka->kvmclock_offset; + ret = get_kvmclock_base_ns() + ka->kvmclock_offset; put_cpu(); @@ -2200,7 +2404,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) } if (!use_master_clock) { host_tsc = rdtsc(); - kernel_ns = ktime_get_boottime_ns(); + kernel_ns = get_kvmclock_base_ns(); } tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); @@ -2240,6 +2444,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.tsc_timestamp = tsc_timestamp; vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_guest_tsc = tsc_timestamp; + WARN_ON((s64)vcpu->hv_clock.system_time < 0); /* If the host uses TSC clocksource, then it is stable */ pvclock_flags = 0; @@ -2346,7 +2551,10 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + /* only 0 or all 1s can be written to IA32_MCi_CTL * some Linux kernels though clear bit 10 in bank 4 to * workaround a BIOS/GART TBL issue on AMD K8s, ignore @@ -2431,6 +2639,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { vcpu->arch.pv_time_enabled = false; + vcpu->arch.time = 0; } static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) @@ -2441,43 +2650,47 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) static void record_steal_time(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) + /* -EAGAIN is returned in atomic context so we can just return. */ + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, + &map, &vcpu->arch.st.cache, false)) return; + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ - if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB) + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, + st->preempted & KVM_VCPU_FLUSH_TLB); + if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb(vcpu, false); - if (vcpu->arch.st.steal.version & 1) - vcpu->arch.st.steal.version += 1; /* first time write, random junk */ + vcpu->arch.st.preempted = 0; - vcpu->arch.st.steal.version += 1; + if (st->version & 1) + st->version += 1; /* first time write, random junk */ - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + st->version += 1; smp_wmb(); - vcpu->arch.st.steal.steal += current->sched_info.run_delay - + st->steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); - smp_wmb(); - vcpu->arch.st.steal.version += 1; + st->version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -2580,6 +2793,20 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_XSS: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + return 1; + /* + * We do support PT if kvm_x86_ops->pt_supported(), but we do + * not support IA32_XSS[bit 8]. Guests will have to use + * RDMSR/WRMSR rather than XSAVES/XRSTORS to save/restore PT + * MSRs. + */ + if (data != 0) + return 1; + vcpu->arch.ia32_xss = data; + break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) return 1; @@ -2594,8 +2821,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_KVM_SYSTEM_TIME: { struct kvm_arch *ka = &vcpu->kvm->arch; - kvmclock_reset(vcpu); - if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) { bool tmp = (msr == MSR_KVM_SYSTEM_TIME); @@ -2609,14 +2834,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ + vcpu->arch.pv_time_enabled = false; if (!(data & 1)) break; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (!kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_time, data & ~1ULL, sizeof(struct pvclock_vcpu_time_info))) - vcpu->arch.pv_time_enabled = false; - else vcpu->arch.pv_time_enabled = true; break; @@ -2633,11 +2857,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & KVM_STEAL_RESERVED_MASK) return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, - data & KVM_STEAL_VALID_BITS, - sizeof(struct kvm_steal_time))) - return 1; - vcpu->arch.st.msr_val = data; if (!(data & KVM_MSR_ENABLED)) @@ -2748,18 +2967,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } EXPORT_SYMBOL_GPL(kvm_set_msr_common); - -/* - * Reads an msr value (of 'msr_index') into 'pdata'. - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) -{ - return kvm_x86_ops->get_msr(vcpu, msr); -} -EXPORT_SYMBOL_GPL(kvm_get_msr); - static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { u64 data; @@ -2785,7 +2992,10 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + data = vcpu->arch.mce_banks[offset]; break; } @@ -2922,6 +3132,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: return get_msr_mce(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); + case MSR_IA32_XSS: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + return 1; + msr_info->data = vcpu->arch.ia32_xss; + break; case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other @@ -3106,7 +3322,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_EVENTFD: case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: - case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: case KVM_CAP_HYPERV_CPUID: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: @@ -3183,6 +3398,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_x86_ops->get_nested_state ? kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0; break; + case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: + r = kvm_x86_ops->enable_direct_tlbflush != NULL; + break; + case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: + r = kvm_x86_ops->nested_enable_evmcs != NULL; + break; default: break; } @@ -3306,10 +3527,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->vcpu_load(vcpu, cpu); - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); - /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); @@ -3349,15 +3566,25 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED; + if (vcpu->arch.st.preempted) + return; - kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal.preempted, - offsetof(struct kvm_steal_time, preempted), - sizeof(vcpu->arch.st.steal.preempted)); + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, + &vcpu->arch.st.cache, true)) + return; + + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + + st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -3506,8 +3733,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; - if (kvm_x86_ops->setup_mce) - kvm_x86_ops->setup_mce(vcpu); + kvm_x86_ops->setup_mce(vcpu); out: return r; } @@ -3566,6 +3792,21 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, process_nmi(vcpu); /* + * In guest mode, payload delivery should be deferred, + * so that the L1 hypervisor can intercept #PF before + * CR2 is modified (or intercept #DB before DR6 is + * modified under nVMX). Unless the per-VM capability, + * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of + * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we + * opportunistically defer the exception payload, deliver it if the + * capability hasn't been requested before processing a + * KVM_GET_VCPU_EVENTS. + */ + if (!vcpu->kvm->arch.exception_payload_enabled && + vcpu->arch.exception.pending && vcpu->arch.exception.has_payload) + kvm_deliver_exception_payload(vcpu); + + /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP * isn't advanced, we should expect to encounter the exception @@ -3695,12 +3936,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; - if (lapic_in_kernel(vcpu)) { - if (events->smi.latched_init) - set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); - else - clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); - } + } + + if (lapic_in_kernel(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } } @@ -3957,6 +4199,11 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, r = -EFAULT; } return r; + case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: + if (!kvm_x86_ops->enable_direct_tlbflush) + return -ENOTTY; + + return kvm_x86_ops->enable_direct_tlbflush(vcpu); default: return -EINVAL; @@ -4286,6 +4533,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_SET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; struct kvm_nested_state kvm_state; + int idx; r = -EINVAL; if (!kvm_x86_ops->set_nested_state) @@ -4309,7 +4557,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE)) break; + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_GET_SUPPORTED_HV_CPUID: { @@ -4500,9 +4750,6 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, { struct kvm_pit *pit = kvm->arch.vpit; - if (!pit) - return -ENXIO; - /* pit->pit_state.lock was overloaded to prevent userspace from getting * an inconsistent state after running multiple KVM_REINJECT_CONTROL * ioctls in parallel. Use a separate lock if that ioctl isn't rare. @@ -4811,9 +5058,6 @@ set_identity_unlock: if (!irqchip_kernel(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); - if (r) - goto set_irqchip_out; - r = 0; set_irqchip_out: kfree(chip); break; @@ -4872,6 +5116,9 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&control, argp, sizeof(control))) goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; r = kvm_vm_ioctl_reinject(kvm, &control); break; } @@ -4986,18 +5233,28 @@ out: static void kvm_init_msr_list(void) { + struct x86_pmu_capability x86_pmu; u32 dummy[2]; - unsigned i, j; + unsigned i; + + BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4, + "Please update the fixed PMCs in msrs_to_saved_all[]"); + + perf_get_x86_pmu_capability(&x86_pmu); + + num_msrs_to_save = 0; + num_emulated_msrs = 0; + num_msr_based_features = 0; - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { - if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) + for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) { + if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0) continue; /* * Even MSRs that are valid in the host may not be exposed * to the guests in some cases. */ - switch (msrs_to_save[i]) { + switch (msrs_to_save_all[i]) { case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported()) continue; @@ -5025,43 +5282,43 @@ static void kvm_init_msr_list(void) break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: { if (!kvm_x86_ops->pt_supported() || - msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >= + msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; + break; + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; } default: break; } - if (j < i) - msrs_to_save[j] = msrs_to_save[i]; - j++; + msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i]; } - num_msrs_to_save = j; - for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { - if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i])) + for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { + if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i])) continue; - if (j < i) - emulated_msrs[j] = emulated_msrs[i]; - j++; + emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } - num_emulated_msrs = j; - for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) { + for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) { struct kvm_msr_entry msr; - msr.index = msr_based_features[i]; + msr.index = msr_based_features_all[i]; if (kvm_get_msr_feature(&msr)) continue; - if (j < i) - msr_based_features[j] = msr_based_features[i]; - j++; + msr_based_features[num_msr_based_features++] = msr_based_features_all[i]; } - num_msr_based_features = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -5312,6 +5569,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, /* kvm_write_guest_virt_system can pull in tons of pages. */ vcpu->arch.l1tf_flush_l1d = true; + /* + * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED + * is returned, but our callers are not ready for that and they blindly + * call kvm_inject_page_fault. Ensure that they at least do not leak + * uninitialized kernel stack memory into cr2 and error code. + */ + memset(exception, 0, sizeof(*exception)); return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, PFERR_WRITE_MASK, exception); } @@ -5319,25 +5583,20 @@ EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); int handle_ud(struct kvm_vcpu *vcpu) { + static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; int emul_type = EMULTYPE_TRAP_UD; - enum emulation_result er; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; if (force_emulation_prefix && kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 0 && - memcmp(sig, "\xf\xbkvm", sizeof(sig)) == 0) { + memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) { kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig)); - emul_type = 0; + emul_type = EMULTYPE_TRAP_UD_FORCED; } - er = kvm_emulate_instruction(vcpu, emul_type); - if (er == EMULATE_USER_EXIT) - return 0; - if (er != EMULATE_DONE) - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; + return kvm_emulate_instruction(vcpu, emul_type); } EXPORT_SYMBOL_GPL(handle_ud); @@ -5370,7 +5629,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, */ if (vcpu_match_mmio_gva(vcpu, gva) && !permission_fault(vcpu, vcpu->arch.walk_mmu, - vcpu->arch.access, 0, access)) { + vcpu->arch.mmio_access, 0, access)) { *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | (gva & (PAGE_SIZE - 1)); trace_vcpu_match_mmio(gva, *gpa, write, false); @@ -5964,28 +6223,13 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { - struct msr_data msr; - int r; - - msr.index = msr_index; - msr.host_initiated = false; - r = kvm_get_msr(emul_to_vcpu(ctxt), &msr); - if (r) - return r; - - *pdata = msr.data; - return 0; + return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); } static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data) { - struct msr_data msr; - - msr.data = data; - msr.index = msr_index; - msr.host_initiated = false; - return kvm_set_msr(emul_to_vcpu(ctxt), &msr); + return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); } static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) @@ -6005,7 +6249,7 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { - return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc); + return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -6032,6 +6276,21 @@ static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, check_limit); } +static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_LM); +} + +static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); +} + +static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); +} + static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) { return kvm_register_read(emul_to_vcpu(ctxt), reg); @@ -6068,6 +6327,11 @@ static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) kvm_smm_changed(emul_to_vcpu(ctxt)); } +static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) +{ + return __kvm_set_xcr(emul_to_vcpu(ctxt), index, xcr); +} + static const struct x86_emulate_ops emulate_ops = { .read_gpr = emulator_read_gpr, .write_gpr = emulator_write_gpr, @@ -6104,11 +6368,15 @@ static const struct x86_emulate_ops emulate_ops = { .fix_hypercall = emulator_fix_hypercall, .intercept = emulator_intercept, .get_cpuid = emulator_get_cpuid, + .guest_has_long_mode = emulator_guest_has_long_mode, + .guest_has_movbe = emulator_guest_has_movbe, + .guest_has_fxsr = emulator_guest_has_fxsr, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, .set_hflags = emulator_set_hflags, .pre_leave_smm = emulator_pre_leave_smm, .post_leave_smm = emulator_post_leave_smm, + .set_xcr = emulator_set_xcr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -6168,7 +6436,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } -int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) +void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) { struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; int ret; @@ -6180,44 +6448,50 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) ctxt->_eip = ctxt->eip + inc_eip; ret = emulate_int_real(ctxt, irq); - if (ret != X86EMUL_CONTINUE) - return EMULATE_FAIL; - - ctxt->eip = ctxt->_eip; - kvm_rip_write(vcpu, ctxt->eip); - kvm_set_rflags(vcpu, ctxt->eflags); - - return EMULATE_DONE; + if (ret != X86EMUL_CONTINUE) { + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + } else { + ctxt->eip = ctxt->_eip; + kvm_rip_write(vcpu, ctxt->eip); + kvm_set_rflags(vcpu, ctxt->eflags); + } } EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { - int r = EMULATE_DONE; - ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); - if (emulation_type & EMULTYPE_NO_UD_ON_FAIL) - return EMULATE_FAIL; + if (emulation_type & EMULTYPE_VMWARE_GP) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } - if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { + if (emulation_type & EMULTYPE_SKIP) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; - r = EMULATE_USER_EXIT; + return 0; } kvm_queue_exception(vcpu, UD_VECTOR); - return r; + if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return 0; + } + + return 1; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool write_fault_to_shadow_pgtable, int emulation_type) { - gpa_t gpa = cr2; + gpa_t gpa = cr2_or_gpa; kvm_pfn_t pfn; if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) @@ -6231,7 +6505,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, * Write permission should be allowed since only * write access need to be emulated. */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); /* * If the mapping is invalid in guest, let cpu retry @@ -6288,10 +6562,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - unsigned long cr2, int emulation_type) + gpa_t cr2_or_gpa, int emulation_type) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; last_retry_eip = vcpu->arch.last_retry_eip; last_retry_addr = vcpu->arch.last_retry_addr; @@ -6320,14 +6594,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, if (x86_page_table_writing_insn(ctxt)) return false; - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) return false; vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2; + vcpu->arch.last_retry_addr = cr2_or_gpa; if (!vcpu->arch.mmu->direct_map) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); @@ -6365,7 +6639,7 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, return dr6; } -static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) +static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; @@ -6374,18 +6648,20 @@ static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; - } else { - kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS); + return 0; } + kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS); + return 1; } int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); - int r = EMULATE_DONE; + int r; - kvm_x86_ops->skip_emulated_instruction(vcpu); + r = kvm_x86_ops->skip_emulated_instruction(vcpu); + if (unlikely(!r)) + return 0; /* * rflags is the old, "raw" value of the flags. The new value has @@ -6396,8 +6672,8 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) * that sets the TF flag". */ if (unlikely(rflags & X86_EFLAGS_TF)) - kvm_vcpu_do_singlestep(vcpu, &r); - return r == EMULATE_DONE; + r = kvm_vcpu_do_singlestep(vcpu); + return r; } EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); @@ -6416,7 +6692,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) kvm_run->debug.arch.pc = eip; kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; + *r = 0; return true; } } @@ -6432,7 +6708,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) vcpu->arch.dr6 &= ~DR_TRAP_BITS; vcpu->arch.dr6 |= dr6 | DR6_RTM; kvm_queue_exception(vcpu, DB_VECTOR); - *r = EMULATE_DONE; + *r = 1; return true; } } @@ -6471,11 +6747,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } -int x86_emulate_instruction(struct kvm_vcpu *vcpu, - unsigned long cr2, - int emulation_type, - void *insn, - int insn_len) +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + int emulation_type, void *insn, int insn_len) { int r; struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; @@ -6516,32 +6789,49 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; if (r != EMULATION_OK) { - if (emulation_type & EMULTYPE_TRAP_UD) - return EMULATE_FAIL; - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, - emulation_type)) - return EMULATE_DONE; - if (ctxt->have_exception && inject_emulated_exception(vcpu)) - return EMULATE_DONE; - if (emulation_type & EMULTYPE_SKIP) - return EMULATE_FAIL; + if ((emulation_type & EMULTYPE_TRAP_UD) || + (emulation_type & EMULTYPE_TRAP_UD_FORCED)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + if (reexecute_instruction(vcpu, cr2_or_gpa, + write_fault_to_spt, + emulation_type)) + return 1; + if (ctxt->have_exception) { + /* + * #UD should result in just EMULATION_FAILED, and trap-like + * exception should not be encountered during decode. + */ + WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR || + exception_type(ctxt->exception.vector) == EXCPT_TRAP); + inject_emulated_exception(vcpu); + return 1; + } return handle_emulation_failure(vcpu, emulation_type); } } - if ((emulation_type & EMULTYPE_VMWARE) && - !is_vmware_backdoor_opcode(ctxt)) - return EMULATE_FAIL; + if ((emulation_type & EMULTYPE_VMWARE_GP) && + !is_vmware_backdoor_opcode(ctxt)) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } + /* + * Note, EMULTYPE_SKIP is intended for use *only* by vendor callbacks + * for kvm_skip_emulated_instruction(). The caller is responsible for + * updating interruptibility state and injecting single-step #DBs. + */ if (emulation_type & EMULTYPE_SKIP) { kvm_rip_write(vcpu, ctxt->_eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); - return EMULATE_DONE; + return 1; } - if (retry_instruction(ctxt, cr2, emulation_type)) - return EMULATE_DONE; + if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) + return 1; /* this is needed for vmware backdoor interface to work since it changes registers values during IO operation */ @@ -6552,23 +6842,23 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, restart: /* Save the faulting GPA (cr2) in the address field */ - ctxt->exception.address = cr2; + ctxt->exception.address = cr2_or_gpa; r = x86_emulate_insn(ctxt); if (r == EMULATION_INTERCEPTED) - return EMULATE_DONE; + return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt, emulation_type)) - return EMULATE_DONE; + return 1; return handle_emulation_failure(vcpu, emulation_type); } if (ctxt->have_exception) { - r = EMULATE_DONE; + r = 1; if (inject_emulated_exception(vcpu)) return r; } else if (vcpu->arch.pio.count) { @@ -6579,27 +6869,30 @@ restart: writeback = false; vcpu->arch.complete_userspace_io = complete_emulated_pio; } - r = EMULATE_USER_EXIT; + r = 0; } else if (vcpu->mmio_needed) { + ++vcpu->stat.mmio_exits; + if (!vcpu->mmio_is_write) writeback = false; - r = EMULATE_USER_EXIT; + r = 0; vcpu->arch.complete_userspace_io = complete_emulated_mmio; } else if (r == EMULATION_RESTART) goto restart; else - r = EMULATE_DONE; + r = 1; if (writeback) { unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; - kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE && ctxt->tf) - kvm_vcpu_do_singlestep(vcpu, &r); if (!ctxt->have_exception || - exception_type(ctxt->exception.vector) == EXCPT_TRAP) + exception_type(ctxt->exception.vector) == EXCPT_TRAP) { + kvm_rip_write(vcpu, ctxt->eip); + if (r && ctxt->tf) + r = kvm_vcpu_do_singlestep(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); + } /* * For STI, interrupts are shadowed; so KVM_REQ_EVENT will @@ -7170,8 +7463,8 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) { struct kvm_lapic_irq lapic_irq; - lapic_irq.shorthand = 0; - lapic_irq.dest_mode = 0; + lapic_irq.shorthand = APIC_DEST_NOSHORT; + lapic_irq.dest_mode = APIC_DEST_PHYSICAL; lapic_irq.level = 0; lapic_irq.dest_id = apicid; lapic_irq.msi_redir_hint = false; @@ -7180,18 +7473,22 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } -void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) +bool kvm_apicv_activated(struct kvm *kvm) { - if (!lapic_in_kernel(vcpu)) { - WARN_ON_ONCE(vcpu->arch.apicv_active); - return; - } - if (!vcpu->arch.apicv_active) - return; + return (READ_ONCE(kvm->arch.apicv_inhibit_reasons) == 0); +} +EXPORT_SYMBOL_GPL(kvm_apicv_activated); - vcpu->arch.apicv_active = false; - kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); +void kvm_apicv_init(struct kvm *kvm, bool enable) +{ + if (enable) + clear_bit(APICV_INHIBIT_REASON_DISABLE, + &kvm->arch.apicv_inhibit_reasons); + else + set_bit(APICV_INHIBIT_REASON_DISABLE, + &kvm->arch.apicv_inhibit_reasons); } +EXPORT_SYMBOL_GPL(kvm_apicv_init); static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id) { @@ -7702,11 +7999,65 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } +void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, + unsigned long *vcpu_bitmap) +{ + cpumask_var_t cpus; + + zalloc_cpumask_var(&cpus, GFP_ATOMIC); + + kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, + vcpu_bitmap, cpus); + + free_cpumask_var(cpus); +} + void kvm_make_scan_ioapic_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); } +void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) +{ + if (!lapic_in_kernel(vcpu)) + return; + + vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); + kvm_apic_update_apicv(vcpu); + kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); + +/* + * NOTE: Do not hold any lock prior to calling this. + * + * In particular, kvm_request_apicv_update() expects kvm->srcu not to be + * locked, because it calls __x86_set_memory_region() which does + * synchronize_srcu(&kvm->srcu). + */ +void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) +{ + if (!kvm_x86_ops->check_apicv_inhibit_reasons || + !kvm_x86_ops->check_apicv_inhibit_reasons(bit)) + return; + + if (activate) { + if (!test_and_clear_bit(bit, &kvm->arch.apicv_inhibit_reasons) || + !kvm_apicv_activated(kvm)) + return; + } else { + if (test_and_set_bit(bit, &kvm->arch.apicv_inhibit_reasons) || + kvm_apicv_activated(kvm)) + return; + } + + trace_kvm_apicv_update_request(activate, bit); + if (kvm_x86_ops->pre_update_apicv_exec_ctrl) + kvm_x86_ops->pre_update_apicv_exec_ctrl(kvm, activate); + kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); +} +EXPORT_SYMBOL_GPL(kvm_request_apicv_update); + static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { if (!kvm_apic_present(vcpu)) @@ -7779,7 +8130,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) */ put_page(page); } -EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) { @@ -7798,12 +8148,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_int_win = dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); + enum exit_fastpath_completion exit_fastpath = EXIT_FASTPATH_NONE; bool req_immediate_exit = false; if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) - kvm_x86_ops->get_vmcs12_pages(vcpu); + if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) { + if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) { + r = 0; + goto out; + } + } if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) kvm_mmu_unload(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) @@ -7893,6 +8248,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) kvm_hv_process_stimers(vcpu); + if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) + kvm_vcpu_update_apicv(vcpu); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { @@ -7995,8 +8352,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) trace_kvm_entry(vcpu->vcpu_id); guest_enter_irqoff(); - /* The preempt notifier should have taken care of the FPU already. */ - WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD)); + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -8040,7 +8398,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_x86_ops->handle_exit_irqoff(vcpu); + kvm_x86_ops->handle_exit_irqoff(vcpu, &exit_fastpath); /* * Consume any pending interrupts, including the possible source of @@ -8084,7 +8442,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_lapic_sync_from_vapic(vcpu); vcpu->arch.gpa_available = false; - r = kvm_x86_ops->handle_exit(vcpu); + r = kvm_x86_ops->handle_exit(vcpu, exit_fastpath); return r; cancel_injection: @@ -8191,12 +8549,11 @@ static int vcpu_run(struct kvm_vcpu *vcpu) static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { int r; + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (r != EMULATE_DONE) - return 0; - return 1; + return r; } static int complete_emulated_pio(struct kvm_vcpu *vcpu) @@ -8269,12 +8626,26 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +static void kvm_save_current_fpu(struct fpu *fpu) +{ + /* + * If the target FPU state is not resident in the CPU registers, just + * memcpy() from current, else save CPU state directly to the target. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + memcpy(&fpu->state, ¤t->thread.fpu.state, + fpu_kernel_xstate_size); + else + copy_fpregs_to_fpstate(fpu); +} + /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(vcpu->arch.user_fpu); + kvm_save_current_fpu(vcpu->arch.user_fpu); + /* PKRU is separately restored in kvm_x86_ops->run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8290,7 +8661,8 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); + kvm_save_current_fpu(vcpu->arch.guest_fpu); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); fpregs_mark_activate(); @@ -8512,6 +8884,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { vcpu_load(vcpu); + if (kvm_mpx_supported()) + kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && @@ -8520,6 +8894,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; + if (kvm_mpx_supported()) + kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); return 0; } @@ -8535,8 +8911,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, mp_state->mp_state != KVM_MP_STATE_RUNNABLE) goto out; - /* INITs are latched while in SMM */ - if ((is_smm(vcpu) || vcpu->arch.smi_pending) && + /* + * KVM_MP_STATE_INIT_RECEIVED means the processor is in + * INIT state; latched init should be reported using + * KVM_SET_VCPU_EVENTS, so reject it here. + */ + if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) && (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) goto out; @@ -8564,23 +8944,21 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); - - if (ret) - return EMULATE_FAIL; + if (ret) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return 0; + } kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); - kvm_make_request(KVM_REQ_EVENT, vcpu); - return EMULATE_DONE; + return 1; } EXPORT_SYMBOL_GPL(kvm_task_switch); static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - (sregs->cr4 & X86_CR4_OSXSAVE)) - return -EINVAL; - if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in @@ -8599,7 +8977,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return -EINVAL; } - return 0; + return kvm_valid_cr4(vcpu, sregs->cr4); } static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) @@ -8629,7 +9007,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) vcpu->arch.cr2 = sregs->cr2; mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); @@ -8877,33 +9255,91 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } -void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { - void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; - - kvmclock_reset(vcpu); + if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) + pr_warn_once("kvm: SMP vm created on host with unstable TSC; " + "guest TSC will not be reliable\n"); - kvm_x86_ops->vcpu_free(vcpu); - free_cpumask_var(wbinvd_dirty_mask); + return 0; } -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, - unsigned int id) +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu; + struct page *page; + int r; - if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) - printk_once(KERN_WARNING - "kvm: SMP vm created on host with unstable TSC; " - "guest TSC will not be reliable\n"); + vcpu->arch.emulate_ctxt.ops = &emulate_ops; + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + else + vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - vcpu = kvm_x86_ops->vcpu_create(kvm, id); + kvm_set_tsc_khz(vcpu, max_tsc_khz); - return vcpu; -} + r = kvm_mmu_create(vcpu); + if (r < 0) + return r; + + if (irqchip_in_kernel(vcpu->kvm)) { + r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); + if (r < 0) + goto fail_mmu_destroy; + if (kvm_apicv_activated(vcpu->kvm)) + vcpu->arch.apicv_active = true; + } else + static_key_slow_inc(&kvm_no_apic_vcpu); + + r = -ENOMEM; + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + goto fail_free_lapic; + vcpu->arch.pio_data = page_address(page); + + vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.mce_banks) + goto fail_free_pio_data; + vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; + + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, + GFP_KERNEL_ACCOUNT)) + goto fail_free_mce_banks; + + vcpu->arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.user_fpu) { + pr_err("kvm: failed to allocate userspace's fpu\n"); + goto free_wbinvd_dirty_mask; + } + + vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.guest_fpu) { + pr_err("kvm: failed to allocate vcpu's fpu\n"); + goto free_user_fpu; + } + fx_init(vcpu); + + vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + + kvm_async_pf_hash_reset(vcpu); + kvm_pmu_init(vcpu); + + vcpu->arch.pending_external_vector = -1; + vcpu->arch.preempted_in_kernel = false; + + kvm_hv_vcpu_init(vcpu); + + r = kvm_x86_ops->vcpu_create(vcpu); + if (r) + goto free_guest_fpu; -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -{ vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_vcpu_mtrr_init(vcpu); @@ -8912,6 +9348,22 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) kvm_init_mmu(vcpu, false); vcpu_put(vcpu); return 0; + +free_guest_fpu: + kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); +free_wbinvd_dirty_mask: + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); +fail_free_mce_banks: + kfree(vcpu->arch.mce_banks); +fail_free_pio_data: + free_page((unsigned long)vcpu->arch.pio_data); +fail_free_lapic: + kvm_free_lapic(vcpu); +fail_mmu_destroy: + kvm_mmu_destroy(vcpu); + return r; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) @@ -8944,13 +9396,29 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - vcpu->arch.apf.msr_val = 0; + struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; + int idx; - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); + kvm_release_pfn(cache->pfn, cache->dirty, cache); + + kvmclock_reset(vcpu); kvm_x86_ops->vcpu_free(vcpu); + + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); + kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); + kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); + + kvm_hv_vcpu_uninit(vcpu); + kvm_pmu_destroy(vcpu); + kfree(vcpu->arch.mce_banks); + kvm_free_lapic(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_mmu_destroy(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + free_page((unsigned long)vcpu->arch.pio_data); + if (!lapic_in_kernel(vcpu)) + static_key_slow_dec(&kvm_no_apic_vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -8966,7 +9434,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.nmi_injected = false; kvm_clear_interrupt_queue(vcpu); kvm_clear_exception_queue(vcpu); - vcpu->arch.exception.pending = false; memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); @@ -9142,6 +9609,8 @@ int kvm_arch_hardware_setup(void) if (r != 0) return r; + cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); + if (kvm_has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that @@ -9156,6 +9625,9 @@ int kvm_arch_hardware_setup(void) kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; } + if (boot_cpu_has(X86_FEATURE_XSAVES)) + rdmsrl(MSR_IA32_XSS, host_xss); + kvm_init_msr_list(); return 0; } @@ -9167,6 +9639,13 @@ void kvm_arch_hardware_unsetup(void) int kvm_arch_check_processor_compat(void) { + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + + WARN_ON(!irqs_disabled()); + + if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) + return -EIO; + return kvm_x86_ops->check_processor_compatibility(); } @@ -9184,101 +9663,15 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) struct static_key kvm_no_apic_vcpu __read_mostly; EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu); -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) -{ - struct page *page; - int r; - - vcpu->arch.emulate_ctxt.ops = &emulate_ops; - if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - else - vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto fail; - } - vcpu->arch.pio_data = page_address(page); - - kvm_set_tsc_khz(vcpu, max_tsc_khz); - - r = kvm_mmu_create(vcpu); - if (r < 0) - goto fail_free_pio_data; - - if (irqchip_in_kernel(vcpu->kvm)) { - vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); - r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); - if (r < 0) - goto fail_mmu_destroy; - } else - static_key_slow_inc(&kvm_no_apic_vcpu); - - vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, - GFP_KERNEL_ACCOUNT); - if (!vcpu->arch.mce_banks) { - r = -ENOMEM; - goto fail_free_lapic; - } - vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; - - if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, - GFP_KERNEL_ACCOUNT)) { - r = -ENOMEM; - goto fail_free_mce_banks; - } - - fx_init(vcpu); - - vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; - - vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - - vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; - - kvm_async_pf_hash_reset(vcpu); - kvm_pmu_init(vcpu); - - vcpu->arch.pending_external_vector = -1; - vcpu->arch.preempted_in_kernel = false; - - kvm_hv_vcpu_init(vcpu); - - return 0; - -fail_free_mce_banks: - kfree(vcpu->arch.mce_banks); -fail_free_lapic: - kvm_free_lapic(vcpu); -fail_mmu_destroy: - kvm_mmu_destroy(vcpu); -fail_free_pio_data: - free_page((unsigned long)vcpu->arch.pio_data); -fail: - return r; -} - -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) -{ - int idx; - - kvm_hv_vcpu_uninit(vcpu); - kvm_pmu_destroy(vcpu); - kfree(vcpu->arch.mce_banks); - kvm_free_lapic(vcpu); - idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_mmu_destroy(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - free_page((unsigned long)vcpu->arch.pio_data); - if (!lapic_in_kernel(vcpu)) - static_key_slow_dec(&kvm_no_apic_vcpu); -} - void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + vcpu->arch.l1tf_flush_l1d = true; + if (pmu->version && unlikely(pmu->event_count)) { + pmu->need_cleanup = true; + kvm_make_request(KVM_REQ_PMU, vcpu); + } kvm_x86_ops->sched_in(vcpu, cpu); } @@ -9289,6 +9682,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -9302,7 +9697,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) mutex_init(&kvm->arch.apic_map_lock); spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); - kvm->arch.kvmclock_offset = -ktime_get_boottime_ns(); + kvm->arch.kvmclock_offset = -get_kvmclock_base_ns(); pvclock_update_vm_gtod_copy(kvm); kvm->arch.guest_can_read_msr_platform_info = true; @@ -9314,10 +9709,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); - if (kvm_x86_ops->vm_init) - return kvm_x86_ops->vm_init(kvm); + return kvm_x86_ops->vm_init(kvm); +} - return 0; +int kvm_arch_post_init_vm(struct kvm *kvm) +{ + return kvm_mmu_post_init_vm(kvm); } static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) @@ -9340,7 +9737,7 @@ static void kvm_free_vcpus(struct kvm *kvm) kvm_unload_vcpu_mmu(vcpu); } kvm_for_each_vcpu(i, vcpu, kvm) - kvm_arch_vcpu_free(vcpu); + kvm_vcpu_destroy(vcpu); mutex_lock(&kvm->lock); for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) @@ -9409,17 +9806,10 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } EXPORT_SYMBOL_GPL(__x86_set_memory_region); -int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) +void kvm_arch_pre_destroy_vm(struct kvm *kvm) { - int r; - - mutex_lock(&kvm->slots_lock); - r = __x86_set_memory_region(kvm, id, gpa, size); - mutex_unlock(&kvm->slots_lock); - - return r; + kvm_mmu_pre_destroy_vm(kvm); } -EXPORT_SYMBOL_GPL(x86_set_memory_region); void kvm_arch_destroy_vm(struct kvm *kvm) { @@ -9429,9 +9819,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm) * unless the the memory map has changed due to process exit * or fd copying. */ - x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); - x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); - x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); + mutex_lock(&kvm->slots_lock); + __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + 0, 0); + __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + 0, 0); + __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); + mutex_unlock(&kvm->slots_lock); } if (kvm_x86_ops->vm_destroy) kvm_x86_ops->vm_destroy(kvm); @@ -9535,11 +9929,18 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { + struct kvm_vcpu *vcpu; + int i; + /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ kvm_mmu_invalidate_mmio_sptes(kvm, gen); + + /* Force re-initialization of steal_time cache */ + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vcpu_kick(vcpu); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -9569,7 +9970,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * * The reason is, in case of PML, we need to set D-bit for any slots * with dirty logging disabled in order to eliminate unnecessary GPA - * logging in PML buffer (and potential PML buffer full VMEXT). This + * logging in PML buffer (and potential PML buffer full VMEXIT). This * guarantees leaving PML enabled during guest's lifetime won't have * any additional overhead from PML when guest is running with dirty * logging disabled for memory slots. @@ -9621,8 +10022,13 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * Scan sptes if dirty logging has been stopped, dropping those * which can be collapsed into a single large-page spte. Later * page faults will create the large-page sptes. + * + * There is no need to do this in any of the following cases: + * CREATE: No dirty mappings will already exist. + * MOVE/DELETE: The old mappings will already have been cleaned up by + * kvm_arch_flush_shadow_memslot() */ - if ((change != KVM_MR_DELETE) && + if (change == KVM_MR_FLAGS_ONLY && (old->flags & KVM_MEM_LOG_DIRTY_PAGES) && !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) kvm_mmu_zap_collapsible_sptes(kvm, new); @@ -9786,7 +10192,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) return; - vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true); + kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); } static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) @@ -9899,7 +10305,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, { struct x86_exception fault; - trace_kvm_async_pf_not_present(work->arch.token, work->gva); + trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); if (kvm_can_deliver_async_pf(vcpu) && @@ -9934,7 +10340,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); - trace_kvm_async_pf_ready(work->arch.token, work->gva); + trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && !apf_get_user(vcpu, &val)) { @@ -10009,7 +10415,7 @@ EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); bool kvm_arch_has_irq_bypass(void) { - return kvm_x86_ops->update_pi_irte != NULL; + return true; } int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, @@ -10049,9 +10455,6 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set) { - if (!kvm_x86_ops->update_pi_irte) - return -EINVAL; - return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set); } @@ -10059,7 +10462,6 @@ bool kvm_vector_hashing_enabled(void) { return vector_hashing; } -EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled); bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { @@ -10067,6 +10469,28 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_arch_no_poll); +u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu) +{ + uint64_t bits = SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) + bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP); + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL) && + !boot_cpu_has(X86_FEATURE_AMD_IBRS)) + bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP); + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL_SSBD) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + bits &= ~SPEC_CTRL_SSBD; + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && + !boot_cpu_has(X86_FEATURE_AMD_SSBD)) + bits &= ~SPEC_CTRL_SSBD; + + return bits; +} +EXPORT_SYMBOL_GPL(kvm_spec_ctrl_valid_bits); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); @@ -10078,12 +10502,14 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter_failed); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); -EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 6594020c0691..3624665acee4 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -144,11 +144,6 @@ static inline bool is_pae_paging(struct kvm_vcpu *vcpu) return !is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu); } -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu) { return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48; @@ -166,21 +161,13 @@ static inline u64 get_canonical(u64 la, u8 vaddr_bits) static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu) { -#ifdef CONFIG_X86_64 return get_canonical(la, vcpu_virt_addr_bits(vcpu)) != la; -#else - return false; -#endif } static inline bool emul_is_noncanonical_address(u64 la, struct x86_emulate_ctxt *ctxt) { -#ifdef CONFIG_X86_64 return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la; -#else - return false; -#endif } static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, @@ -196,7 +183,7 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, * actually a nGPA. */ vcpu->arch.mmio_gva = mmu_is_nested(vcpu) ? 0 : gva & PAGE_MASK; - vcpu->arch.access = access; + vcpu->arch.mmio_access = access; vcpu->arch.mmio_gfn = gfn; vcpu->arch.mmio_gen = gen; } @@ -238,8 +225,7 @@ static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) return false; } -static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, - enum kvm_reg reg) +static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, int reg) { unsigned long val = kvm_register_read(vcpu, reg); @@ -247,8 +233,7 @@ static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, } static inline void kvm_register_writel(struct kvm_vcpu *vcpu, - enum kvm_reg reg, - unsigned long val) + int reg, unsigned long val) { if (!is_64_bit_mode(vcpu)) val = (u32)val; @@ -260,8 +245,13 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) return !(kvm->arch.disabled_quirks & quirk); } +static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) +{ + return is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu); +} + void kvm_set_pending_timer(struct kvm_vcpu *vcpu); -int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); +void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 get_kvmclock_ns(struct kvm *kvm); @@ -286,8 +276,9 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); +enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ @@ -366,7 +357,14 @@ static inline bool kvm_pat_valid(u64 data) return (data | ((data & 0x0202020202020202ull) << 1)) == data; } -void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); -void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); +static inline bool kvm_dr7_valid(u64 data) +{ + /* Bits [63:32] are reserved */ + return !(data >> 32); +} + +void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); +void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); +u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index e0788bade5ab..3b6544111ac9 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -20,10 +20,10 @@ #define BEGIN(op) \ .macro endp; \ -ENDPROC(atomic64_##op##_386); \ +SYM_FUNC_END(atomic64_##op##_386); \ .purgem endp; \ .endm; \ -ENTRY(atomic64_##op##_386); \ +SYM_FUNC_START(atomic64_##op##_386); \ LOCK v; #define ENDP endp diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 843d978ee341..1c5c81c16b06 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -16,12 +16,12 @@ cmpxchg8b (\reg) .endm -ENTRY(atomic64_read_cx8) +SYM_FUNC_START(atomic64_read_cx8) read64 %ecx ret -ENDPROC(atomic64_read_cx8) +SYM_FUNC_END(atomic64_read_cx8) -ENTRY(atomic64_set_cx8) +SYM_FUNC_START(atomic64_set_cx8) 1: /* we don't need LOCK_PREFIX since aligned 64-bit writes * are atomic on 586 and newer */ @@ -29,19 +29,19 @@ ENTRY(atomic64_set_cx8) jne 1b ret -ENDPROC(atomic64_set_cx8) +SYM_FUNC_END(atomic64_set_cx8) -ENTRY(atomic64_xchg_cx8) +SYM_FUNC_START(atomic64_xchg_cx8) 1: LOCK_PREFIX cmpxchg8b (%esi) jne 1b ret -ENDPROC(atomic64_xchg_cx8) +SYM_FUNC_END(atomic64_xchg_cx8) .macro addsub_return func ins insc -ENTRY(atomic64_\func\()_return_cx8) +SYM_FUNC_START(atomic64_\func\()_return_cx8) pushl %ebp pushl %ebx pushl %esi @@ -69,14 +69,14 @@ ENTRY(atomic64_\func\()_return_cx8) popl %ebx popl %ebp ret -ENDPROC(atomic64_\func\()_return_cx8) +SYM_FUNC_END(atomic64_\func\()_return_cx8) .endm addsub_return add add adc addsub_return sub sub sbb .macro incdec_return func ins insc -ENTRY(atomic64_\func\()_return_cx8) +SYM_FUNC_START(atomic64_\func\()_return_cx8) pushl %ebx read64 %esi @@ -94,13 +94,13 @@ ENTRY(atomic64_\func\()_return_cx8) movl %ecx, %edx popl %ebx ret -ENDPROC(atomic64_\func\()_return_cx8) +SYM_FUNC_END(atomic64_\func\()_return_cx8) .endm incdec_return inc add adc incdec_return dec sub sbb -ENTRY(atomic64_dec_if_positive_cx8) +SYM_FUNC_START(atomic64_dec_if_positive_cx8) pushl %ebx read64 %esi @@ -119,9 +119,9 @@ ENTRY(atomic64_dec_if_positive_cx8) movl %ecx, %edx popl %ebx ret -ENDPROC(atomic64_dec_if_positive_cx8) +SYM_FUNC_END(atomic64_dec_if_positive_cx8) -ENTRY(atomic64_add_unless_cx8) +SYM_FUNC_START(atomic64_add_unless_cx8) pushl %ebp pushl %ebx /* these just push these two parameters on the stack */ @@ -155,9 +155,9 @@ ENTRY(atomic64_add_unless_cx8) jne 2b xorl %eax, %eax jmp 3b -ENDPROC(atomic64_add_unless_cx8) +SYM_FUNC_END(atomic64_add_unless_cx8) -ENTRY(atomic64_inc_not_zero_cx8) +SYM_FUNC_START(atomic64_inc_not_zero_cx8) pushl %ebx read64 %esi @@ -177,4 +177,4 @@ ENTRY(atomic64_inc_not_zero_cx8) 3: popl %ebx ret -ENDPROC(atomic64_inc_not_zero_cx8) +SYM_FUNC_END(atomic64_inc_not_zero_cx8) diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 4df90c9ea383..4742e8fa7ee7 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -46,7 +46,7 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum) * Fortunately, it is easy to convert 2-byte alignment to 4-byte * alignment for the unrolled loop. */ -ENTRY(csum_partial) +SYM_FUNC_START(csum_partial) pushl %esi pushl %ebx movl 20(%esp),%eax # Function arg: unsigned int sum @@ -128,13 +128,13 @@ ENTRY(csum_partial) popl %ebx popl %esi ret -ENDPROC(csum_partial) +SYM_FUNC_END(csum_partial) #else /* Version for PentiumII/PPro */ -ENTRY(csum_partial) +SYM_FUNC_START(csum_partial) pushl %esi pushl %ebx movl 20(%esp),%eax # Function arg: unsigned int sum @@ -246,7 +246,7 @@ ENTRY(csum_partial) popl %ebx popl %esi ret -ENDPROC(csum_partial) +SYM_FUNC_END(csum_partial) #endif EXPORT_SYMBOL(csum_partial) @@ -280,7 +280,7 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst, #define ARGBASE 16 #define FP 12 -ENTRY(csum_partial_copy_generic) +SYM_FUNC_START(csum_partial_copy_generic) subl $4,%esp pushl %edi pushl %esi @@ -398,7 +398,7 @@ DST( movb %cl, (%edi) ) popl %edi popl %ecx # equivalent to addl $4,%esp ret -ENDPROC(csum_partial_copy_generic) +SYM_FUNC_END(csum_partial_copy_generic) #else @@ -416,7 +416,7 @@ ENDPROC(csum_partial_copy_generic) #define ARGBASE 12 -ENTRY(csum_partial_copy_generic) +SYM_FUNC_START(csum_partial_copy_generic) pushl %ebx pushl %edi pushl %esi @@ -483,7 +483,7 @@ DST( movb %dl, (%edi) ) popl %edi popl %ebx ret -ENDPROC(csum_partial_copy_generic) +SYM_FUNC_END(csum_partial_copy_generic) #undef ROUND #undef ROUND1 diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index 75a5a4515fa7..c4c7dd115953 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -13,15 +13,15 @@ * Zero a page. * %rdi - page */ -ENTRY(clear_page_rep) +SYM_FUNC_START(clear_page_rep) movl $4096/8,%ecx xorl %eax,%eax rep stosq ret -ENDPROC(clear_page_rep) +SYM_FUNC_END(clear_page_rep) EXPORT_SYMBOL_GPL(clear_page_rep) -ENTRY(clear_page_orig) +SYM_FUNC_START(clear_page_orig) xorl %eax,%eax movl $4096/64,%ecx .p2align 4 @@ -40,13 +40,13 @@ ENTRY(clear_page_orig) jnz .Lloop nop ret -ENDPROC(clear_page_orig) +SYM_FUNC_END(clear_page_orig) EXPORT_SYMBOL_GPL(clear_page_orig) -ENTRY(clear_page_erms) +SYM_FUNC_START(clear_page_erms) movl $4096,%ecx xorl %eax,%eax rep stosb ret -ENDPROC(clear_page_erms) +SYM_FUNC_END(clear_page_erms) EXPORT_SYMBOL_GPL(clear_page_erms) diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S index d63185698a23..3542502faa3b 100644 --- a/arch/x86/lib/cmpxchg16b_emu.S +++ b/arch/x86/lib/cmpxchg16b_emu.S @@ -13,7 +13,7 @@ * %rcx : high 64 bits of new value * %al : Operation successful */ -ENTRY(this_cpu_cmpxchg16b_emu) +SYM_FUNC_START(this_cpu_cmpxchg16b_emu) # # Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not @@ -44,4 +44,4 @@ ENTRY(this_cpu_cmpxchg16b_emu) xor %al,%al ret -ENDPROC(this_cpu_cmpxchg16b_emu) +SYM_FUNC_END(this_cpu_cmpxchg16b_emu) diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index 691d80e97488..ca01ed6029f4 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -13,7 +13,7 @@ * %ebx : low 32 bits of new value * %ecx : high 32 bits of new value */ -ENTRY(cmpxchg8b_emu) +SYM_FUNC_START(cmpxchg8b_emu) # # Emulate 'cmpxchg8b (%esi)' on UP except we don't @@ -42,5 +42,5 @@ ENTRY(cmpxchg8b_emu) popfl ret -ENDPROC(cmpxchg8b_emu) +SYM_FUNC_END(cmpxchg8b_emu) EXPORT_SYMBOL(cmpxchg8b_emu) diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index fd2d09afa097..2402d4c489d2 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -13,15 +13,15 @@ * prefetch distance based on SMP/UP. */ ALIGN -ENTRY(copy_page) +SYM_FUNC_START(copy_page) ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD movl $4096/8, %ecx rep movsq ret -ENDPROC(copy_page) +SYM_FUNC_END(copy_page) EXPORT_SYMBOL(copy_page) -ENTRY(copy_page_regs) +SYM_FUNC_START_LOCAL(copy_page_regs) subq $2*8, %rsp movq %rbx, (%rsp) movq %r12, 1*8(%rsp) @@ -86,4 +86,4 @@ ENTRY(copy_page_regs) movq 1*8(%rsp), %r12 addq $2*8, %rsp ret -ENDPROC(copy_page_regs) +SYM_FUNC_END(copy_page_regs) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 4fe1601dbc5d..816f128a6d52 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -33,7 +33,7 @@ 102: .section .fixup,"ax" 103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail + jmp .Lcopy_user_handle_tail .previous _ASM_EXTABLE_UA(100b, 103b) @@ -53,7 +53,7 @@ * Output: * eax uncopied bytes or 0 if successful. */ -ENTRY(copy_user_generic_unrolled) +SYM_FUNC_START(copy_user_generic_unrolled) ASM_STAC cmpl $8,%edx jb 20f /* less then 8 bytes, go to byte copy loop */ @@ -113,7 +113,7 @@ ENTRY(copy_user_generic_unrolled) 40: leal (%rdx,%rcx,8),%edx jmp 60f 50: movl %ecx,%edx -60: jmp copy_user_handle_tail /* ecx is zerorest also */ +60: jmp .Lcopy_user_handle_tail /* ecx is zerorest also */ .previous _ASM_EXTABLE_UA(1b, 30b) @@ -136,7 +136,7 @@ ENTRY(copy_user_generic_unrolled) _ASM_EXTABLE_UA(19b, 40b) _ASM_EXTABLE_UA(21b, 50b) _ASM_EXTABLE_UA(22b, 50b) -ENDPROC(copy_user_generic_unrolled) +SYM_FUNC_END(copy_user_generic_unrolled) EXPORT_SYMBOL(copy_user_generic_unrolled) /* Some CPUs run faster using the string copy instructions. @@ -157,7 +157,7 @@ EXPORT_SYMBOL(copy_user_generic_unrolled) * Output: * eax uncopied bytes or 0 if successful. */ -ENTRY(copy_user_generic_string) +SYM_FUNC_START(copy_user_generic_string) ASM_STAC cmpl $8,%edx jb 2f /* less than 8 bytes, go to byte copy loop */ @@ -177,12 +177,12 @@ ENTRY(copy_user_generic_string) .section .fixup,"ax" 11: leal (%rdx,%rcx,8),%ecx 12: movl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail + jmp .Lcopy_user_handle_tail .previous _ASM_EXTABLE_UA(1b, 11b) _ASM_EXTABLE_UA(3b, 12b) -ENDPROC(copy_user_generic_string) +SYM_FUNC_END(copy_user_generic_string) EXPORT_SYMBOL(copy_user_generic_string) /* @@ -197,7 +197,7 @@ EXPORT_SYMBOL(copy_user_generic_string) * Output: * eax uncopied bytes or 0 if successful. */ -ENTRY(copy_user_enhanced_fast_string) +SYM_FUNC_START(copy_user_enhanced_fast_string) ASM_STAC cmpl $64,%edx jb .L_copy_short_string /* less then 64 bytes, avoid the costly 'rep' */ @@ -210,11 +210,11 @@ ENTRY(copy_user_enhanced_fast_string) .section .fixup,"ax" 12: movl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail + jmp .Lcopy_user_handle_tail .previous _ASM_EXTABLE_UA(1b, 12b) -ENDPROC(copy_user_enhanced_fast_string) +SYM_FUNC_END(copy_user_enhanced_fast_string) EXPORT_SYMBOL(copy_user_enhanced_fast_string) /* @@ -230,8 +230,7 @@ EXPORT_SYMBOL(copy_user_enhanced_fast_string) * Output: * eax uncopied bytes or 0 if successful. */ -ALIGN; -copy_user_handle_tail: +SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) movl %edx,%ecx 1: rep movsb 2: mov %ecx,%eax @@ -239,7 +238,7 @@ copy_user_handle_tail: ret _ASM_EXTABLE_UA(1b, 2b) -END(copy_user_handle_tail) +SYM_CODE_END(.Lcopy_user_handle_tail) /* * copy_user_nocache - Uncached memory copy with exception handling @@ -250,7 +249,7 @@ END(copy_user_handle_tail) * - Require 8-byte alignment when size is 8 bytes or larger. * - Require 4-byte alignment when size is 4 bytes. */ -ENTRY(__copy_user_nocache) +SYM_FUNC_START(__copy_user_nocache) ASM_STAC /* If size is less than 8 bytes, go to 4-byte copy */ @@ -364,7 +363,7 @@ ENTRY(__copy_user_nocache) movl %ecx,%edx .L_fixup_handle_tail: sfence - jmp copy_user_handle_tail + jmp .Lcopy_user_handle_tail .previous _ASM_EXTABLE_UA(1b, .L_fixup_4x8b_copy) @@ -389,5 +388,5 @@ ENTRY(__copy_user_nocache) _ASM_EXTABLE_UA(31b, .L_fixup_4b_copy) _ASM_EXTABLE_UA(40b, .L_fixup_1b_copy) _ASM_EXTABLE_UA(41b, .L_fixup_1b_copy) -ENDPROC(__copy_user_nocache) +SYM_FUNC_END(__copy_user_nocache) EXPORT_SYMBOL(__copy_user_nocache) diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S index a4a379e79259..3394a8ff7fd0 100644 --- a/arch/x86/lib/csum-copy_64.S +++ b/arch/x86/lib/csum-copy_64.S @@ -49,7 +49,7 @@ .endm -ENTRY(csum_partial_copy_generic) +SYM_FUNC_START(csum_partial_copy_generic) cmpl $3*64, %edx jle .Lignore @@ -225,4 +225,4 @@ ENTRY(csum_partial_copy_generic) jz .Lende movl $-EFAULT, (%rax) jmp .Lende -ENDPROC(csum_partial_copy_generic) +SYM_FUNC_END(csum_partial_copy_generic) diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index b7375dc6898f..c126571e5e2e 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -113,8 +113,8 @@ static void delay_mwaitx(unsigned long __loops) __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* - * AMD, like Intel, supports the EAX hint and EAX=0xf - * means, do not enter any deep C-state and we use it + * AMD, like Intel's MWAIT version, supports the EAX hint and + * EAX=0xf0 means, do not enter any deep C-state and we use it * here in delay() to minimize wakeup latency. */ __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE); diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 304f958c27b2..c8a85b512796 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -36,7 +36,7 @@ #include <asm/export.h> .text -ENTRY(__get_user_1) +SYM_FUNC_START(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user @@ -47,10 +47,10 @@ ENTRY(__get_user_1) xor %eax,%eax ASM_CLAC ret -ENDPROC(__get_user_1) +SYM_FUNC_END(__get_user_1) EXPORT_SYMBOL(__get_user_1) -ENTRY(__get_user_2) +SYM_FUNC_START(__get_user_2) add $1,%_ASM_AX jc bad_get_user mov PER_CPU_VAR(current_task), %_ASM_DX @@ -63,10 +63,10 @@ ENTRY(__get_user_2) xor %eax,%eax ASM_CLAC ret -ENDPROC(__get_user_2) +SYM_FUNC_END(__get_user_2) EXPORT_SYMBOL(__get_user_2) -ENTRY(__get_user_4) +SYM_FUNC_START(__get_user_4) add $3,%_ASM_AX jc bad_get_user mov PER_CPU_VAR(current_task), %_ASM_DX @@ -79,10 +79,10 @@ ENTRY(__get_user_4) xor %eax,%eax ASM_CLAC ret -ENDPROC(__get_user_4) +SYM_FUNC_END(__get_user_4) EXPORT_SYMBOL(__get_user_4) -ENTRY(__get_user_8) +SYM_FUNC_START(__get_user_8) #ifdef CONFIG_X86_64 add $7,%_ASM_AX jc bad_get_user @@ -111,33 +111,35 @@ ENTRY(__get_user_8) ASM_CLAC ret #endif -ENDPROC(__get_user_8) +SYM_FUNC_END(__get_user_8) EXPORT_SYMBOL(__get_user_8) -bad_get_user_clac: +SYM_CODE_START_LOCAL(.Lbad_get_user_clac) ASM_CLAC bad_get_user: xor %edx,%edx mov $(-EFAULT),%_ASM_AX ret +SYM_CODE_END(.Lbad_get_user_clac) #ifdef CONFIG_X86_32 -bad_get_user_8_clac: +SYM_CODE_START_LOCAL(.Lbad_get_user_8_clac) ASM_CLAC bad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX ret +SYM_CODE_END(.Lbad_get_user_8_clac) #endif - _ASM_EXTABLE_UA(1b, bad_get_user_clac) - _ASM_EXTABLE_UA(2b, bad_get_user_clac) - _ASM_EXTABLE_UA(3b, bad_get_user_clac) + _ASM_EXTABLE_UA(1b, .Lbad_get_user_clac) + _ASM_EXTABLE_UA(2b, .Lbad_get_user_clac) + _ASM_EXTABLE_UA(3b, .Lbad_get_user_clac) #ifdef CONFIG_X86_64 - _ASM_EXTABLE_UA(4b, bad_get_user_clac) + _ASM_EXTABLE_UA(4b, .Lbad_get_user_clac) #else - _ASM_EXTABLE_UA(4b, bad_get_user_8_clac) - _ASM_EXTABLE_UA(5b, bad_get_user_8_clac) + _ASM_EXTABLE_UA(4b, .Lbad_get_user_8_clac) + _ASM_EXTABLE_UA(5b, .Lbad_get_user_8_clac) #endif diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index a14f9939c365..dbf8cc97b7f5 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -8,7 +8,7 @@ * unsigned int __sw_hweight32(unsigned int w) * %rdi: w */ -ENTRY(__sw_hweight32) +SYM_FUNC_START(__sw_hweight32) #ifdef CONFIG_X86_64 movl %edi, %eax # w @@ -33,10 +33,10 @@ ENTRY(__sw_hweight32) shrl $24, %eax # w = w_tmp >> 24 __ASM_SIZE(pop,) %__ASM_REG(dx) ret -ENDPROC(__sw_hweight32) +SYM_FUNC_END(__sw_hweight32) EXPORT_SYMBOL(__sw_hweight32) -ENTRY(__sw_hweight64) +SYM_FUNC_START(__sw_hweight64) #ifdef CONFIG_X86_64 pushq %rdi pushq %rdx @@ -79,5 +79,5 @@ ENTRY(__sw_hweight64) popl %ecx ret #endif -ENDPROC(__sw_hweight64) +SYM_FUNC_END(__sw_hweight64) EXPORT_SYMBOL(__sw_hweight64) diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 306c3a0902ba..31600d851fd8 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -155,7 +155,7 @@ static bool check_seg_overrides(struct insn *insn, int regoff) */ static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off) { - if (user_64bit_mode(regs)) + if (any_64bit_mode(regs)) return INAT_SEG_REG_IGNORE; /* * Resolve the default segment register as described in Section 3.7.4 @@ -266,7 +266,7 @@ static int resolve_seg_reg(struct insn *insn, struct pt_regs *regs, int regoff) * which may be invalid at this point. */ if (regoff == offsetof(struct pt_regs, ip)) { - if (user_64bit_mode(regs)) + if (any_64bit_mode(regs)) return INAT_SEG_REG_IGNORE; else return INAT_SEG_REG_CS; @@ -289,7 +289,7 @@ static int resolve_seg_reg(struct insn *insn, struct pt_regs *regs, int regoff) * In long mode, segment override prefixes are ignored, except for * overrides for FS and GS. */ - if (user_64bit_mode(regs)) { + if (any_64bit_mode(regs)) { if (idx != INAT_SEG_REG_FS && idx != INAT_SEG_REG_GS) idx = INAT_SEG_REG_IGNORE; @@ -646,23 +646,27 @@ unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx) */ return (unsigned long)(sel << 4); - if (user_64bit_mode(regs)) { + if (any_64bit_mode(regs)) { /* * Only FS or GS will have a base address, the rest of * the segments' bases are forced to 0. */ unsigned long base; - if (seg_reg_idx == INAT_SEG_REG_FS) + if (seg_reg_idx == INAT_SEG_REG_FS) { rdmsrl(MSR_FS_BASE, base); - else if (seg_reg_idx == INAT_SEG_REG_GS) + } else if (seg_reg_idx == INAT_SEG_REG_GS) { /* * swapgs was called at the kernel entry point. Thus, * MSR_KERNEL_GS_BASE will have the user-space GS base. */ - rdmsrl(MSR_KERNEL_GS_BASE, base); - else + if (user_mode(regs)) + rdmsrl(MSR_KERNEL_GS_BASE, base); + else + rdmsrl(MSR_GS_BASE, base); + } else { base = 0; + } return base; } @@ -703,7 +707,7 @@ static unsigned long get_seg_limit(struct pt_regs *regs, int seg_reg_idx) if (sel < 0) return 0; - if (user_64bit_mode(regs) || v8086_mode(regs)) + if (any_64bit_mode(regs) || v8086_mode(regs)) return -1L; if (!sel) @@ -948,7 +952,7 @@ static int get_eff_addr_modrm(struct insn *insn, struct pt_regs *regs, * following instruction. */ if (*regoff == -EDOM) { - if (user_64bit_mode(regs)) + if (any_64bit_mode(regs)) tmp = regs->ip + insn->length; else tmp = 0; @@ -1250,7 +1254,7 @@ static void __user *get_addr_ref_32(struct insn *insn, struct pt_regs *regs) * After computed, the effective address is treated as an unsigned * quantity. */ - if (!user_64bit_mode(regs) && ((unsigned int)eff_addr > seg_limit)) + if (!any_64bit_mode(regs) && ((unsigned int)eff_addr > seg_limit)) goto out; /* diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 0b5862ba6a75..404279563891 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -13,6 +13,8 @@ #include <asm/inat.h> #include <asm/insn.h> +#include <asm/emulate_prefix.h> + /* Verify next sizeof(t) bytes can be on the same instruction */ #define validate_next(t, insn, n) \ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) @@ -58,6 +60,36 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) insn->addr_bytes = 4; } +static const insn_byte_t xen_prefix[] = { __XEN_EMULATE_PREFIX }; +static const insn_byte_t kvm_prefix[] = { __KVM_EMULATE_PREFIX }; + +static int __insn_get_emulate_prefix(struct insn *insn, + const insn_byte_t *prefix, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (peek_nbyte_next(insn_byte_t, insn, i) != prefix[i]) + goto err_out; + } + + insn->emulate_prefix_size = len; + insn->next_byte += len; + + return 1; + +err_out: + return 0; +} + +static void insn_get_emulate_prefix(struct insn *insn) +{ + if (__insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix))) + return; + + __insn_get_emulate_prefix(insn, kvm_prefix, sizeof(kvm_prefix)); +} + /** * insn_get_prefixes - scan x86 instruction prefix bytes * @insn: &struct insn containing instruction @@ -76,6 +108,8 @@ void insn_get_prefixes(struct insn *insn) if (prefixes->got) return; + insn_get_emulate_prefix(insn); + nb = 0; lb = 0; b = peek_next(insn_byte_t, insn); diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S index a9bdf0805be0..cb5a1964506b 100644 --- a/arch/x86/lib/iomap_copy_64.S +++ b/arch/x86/lib/iomap_copy_64.S @@ -8,8 +8,8 @@ /* * override generic version in lib/iomap_copy.c */ -ENTRY(__iowrite32_copy) +SYM_FUNC_START(__iowrite32_copy) movl %edx,%ecx rep movsd ret -ENDPROC(__iowrite32_copy) +SYM_FUNC_END(__iowrite32_copy) diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 92748660ba51..56b243b14c3a 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -28,8 +28,8 @@ * Output: * rax original destination */ -ENTRY(__memcpy) -ENTRY(memcpy) +SYM_FUNC_START_ALIAS(__memcpy) +SYM_FUNC_START_LOCAL(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS @@ -41,8 +41,8 @@ ENTRY(memcpy) movl %edx, %ecx rep movsb ret -ENDPROC(memcpy) -ENDPROC(__memcpy) +SYM_FUNC_END(memcpy) +SYM_FUNC_END_ALIAS(__memcpy) EXPORT_SYMBOL(memcpy) EXPORT_SYMBOL(__memcpy) @@ -50,14 +50,14 @@ EXPORT_SYMBOL(__memcpy) * memcpy_erms() - enhanced fast string memcpy. This is faster and * simpler than memcpy. Use memcpy_erms when possible. */ -ENTRY(memcpy_erms) +SYM_FUNC_START_LOCAL(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb ret -ENDPROC(memcpy_erms) +SYM_FUNC_END(memcpy_erms) -ENTRY(memcpy_orig) +SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax cmpq $0x20, %rdx @@ -182,7 +182,7 @@ ENTRY(memcpy_orig) .Lend: retq -ENDPROC(memcpy_orig) +SYM_FUNC_END(memcpy_orig) #ifndef CONFIG_UML @@ -193,7 +193,7 @@ MCSAFE_TEST_CTL * Note that we only catch machine checks when reading the source addresses. * Writes to target are posted and don't generate machine checks. */ -ENTRY(__memcpy_mcsafe) +SYM_FUNC_START(__memcpy_mcsafe) cmpl $8, %edx /* Less than 8 bytes? Go to byte copy loop */ jb .L_no_whole_words @@ -260,7 +260,7 @@ ENTRY(__memcpy_mcsafe) xorl %eax, %eax .L_done: ret -ENDPROC(__memcpy_mcsafe) +SYM_FUNC_END(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) .section .fixup, "ax" diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index bbec69d8223b..7ff00ea64e4f 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -26,13 +26,10 @@ */ .weak memmove -ENTRY(memmove) -ENTRY(__memmove) +SYM_FUNC_START_ALIAS(memmove) +SYM_FUNC_START(__memmove) - /* Handle more 32 bytes in loop */ mov %rdi, %rax - cmp $0x20, %rdx - jb 1f /* Decide forward/backward copy mode */ cmp %rdi, %rsi @@ -42,7 +39,9 @@ ENTRY(__memmove) cmp %rdi, %r8 jg 2f + /* FSRM implies ERMS => no length checks, do the copy directly */ .Lmemmove_begin_forward: + ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; retq", X86_FEATURE_ERMS /* @@ -114,6 +113,8 @@ ENTRY(__memmove) */ .p2align 4 2: + cmp $0x20, %rdx + jb 1f cmp $680, %rdx jb 6f cmp %dil, %sil @@ -207,7 +208,7 @@ ENTRY(__memmove) movb %r11b, (%rdi) 13: retq -ENDPROC(__memmove) -ENDPROC(memmove) +SYM_FUNC_END(__memmove) +SYM_FUNC_END_ALIAS(memmove) EXPORT_SYMBOL(__memmove) EXPORT_SYMBOL(memmove) diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 9bc861c71e75..9ff15ee404a4 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -19,8 +19,8 @@ * * rax original destination */ -ENTRY(memset) -ENTRY(__memset) +SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended * to use it when possible. If not available, use fast string instructions. @@ -43,8 +43,8 @@ ENTRY(__memset) rep stosb movq %r9,%rax ret -ENDPROC(memset) -ENDPROC(__memset) +SYM_FUNC_END(__memset) +SYM_FUNC_END_ALIAS(memset) EXPORT_SYMBOL(memset) EXPORT_SYMBOL(__memset) @@ -59,16 +59,16 @@ EXPORT_SYMBOL(__memset) * * rax original destination */ -ENTRY(memset_erms) +SYM_FUNC_START_LOCAL(memset_erms) movq %rdi,%r9 movb %sil,%al movq %rdx,%rcx rep stosb movq %r9,%rax ret -ENDPROC(memset_erms) +SYM_FUNC_END(memset_erms) -ENTRY(memset_orig) +SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 /* expand byte value */ @@ -139,4 +139,4 @@ ENTRY(memset_orig) subq %r8,%rdx jmp .Lafter_bad_alignment .Lfinal: -ENDPROC(memset_orig) +SYM_FUNC_END(memset_orig) diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index ed33cbab3958..a2b9caa5274c 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -12,7 +12,7 @@ * */ .macro op_safe_regs op -ENTRY(\op\()_safe_regs) +SYM_FUNC_START(\op\()_safe_regs) pushq %rbx pushq %r12 movq %rdi, %r10 /* Save pointer */ @@ -41,13 +41,13 @@ ENTRY(\op\()_safe_regs) jmp 2b _ASM_EXTABLE(1b, 3b) -ENDPROC(\op\()_safe_regs) +SYM_FUNC_END(\op\()_safe_regs) .endm #else /* X86_32 */ .macro op_safe_regs op -ENTRY(\op\()_safe_regs) +SYM_FUNC_START(\op\()_safe_regs) pushl %ebx pushl %ebp pushl %esi @@ -83,7 +83,7 @@ ENTRY(\op\()_safe_regs) jmp 2b _ASM_EXTABLE(1b, 3b) -ENDPROC(\op\()_safe_regs) +SYM_FUNC_END(\op\()_safe_regs) .endm #endif diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 14bf78341d3c..7c7c92db8497 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -34,52 +34,52 @@ #define ENTER mov PER_CPU_VAR(current_task), %_ASM_BX .text -ENTRY(__put_user_1) +SYM_FUNC_START(__put_user_1) ENTER cmp TASK_addr_limit(%_ASM_BX),%_ASM_CX - jae bad_put_user + jae .Lbad_put_user ASM_STAC 1: movb %al,(%_ASM_CX) xor %eax,%eax ASM_CLAC ret -ENDPROC(__put_user_1) +SYM_FUNC_END(__put_user_1) EXPORT_SYMBOL(__put_user_1) -ENTRY(__put_user_2) +SYM_FUNC_START(__put_user_2) ENTER mov TASK_addr_limit(%_ASM_BX),%_ASM_BX sub $1,%_ASM_BX cmp %_ASM_BX,%_ASM_CX - jae bad_put_user + jae .Lbad_put_user ASM_STAC 2: movw %ax,(%_ASM_CX) xor %eax,%eax ASM_CLAC ret -ENDPROC(__put_user_2) +SYM_FUNC_END(__put_user_2) EXPORT_SYMBOL(__put_user_2) -ENTRY(__put_user_4) +SYM_FUNC_START(__put_user_4) ENTER mov TASK_addr_limit(%_ASM_BX),%_ASM_BX sub $3,%_ASM_BX cmp %_ASM_BX,%_ASM_CX - jae bad_put_user + jae .Lbad_put_user ASM_STAC 3: movl %eax,(%_ASM_CX) xor %eax,%eax ASM_CLAC ret -ENDPROC(__put_user_4) +SYM_FUNC_END(__put_user_4) EXPORT_SYMBOL(__put_user_4) -ENTRY(__put_user_8) +SYM_FUNC_START(__put_user_8) ENTER mov TASK_addr_limit(%_ASM_BX),%_ASM_BX sub $7,%_ASM_BX cmp %_ASM_BX,%_ASM_CX - jae bad_put_user + jae .Lbad_put_user ASM_STAC 4: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 @@ -88,19 +88,20 @@ ENTRY(__put_user_8) xor %eax,%eax ASM_CLAC RET -ENDPROC(__put_user_8) +SYM_FUNC_END(__put_user_8) EXPORT_SYMBOL(__put_user_8) -bad_put_user_clac: +SYM_CODE_START_LOCAL(.Lbad_put_user_clac) ASM_CLAC -bad_put_user: +.Lbad_put_user: movl $-EFAULT,%eax RET +SYM_CODE_END(.Lbad_put_user_clac) - _ASM_EXTABLE_UA(1b, bad_put_user_clac) - _ASM_EXTABLE_UA(2b, bad_put_user_clac) - _ASM_EXTABLE_UA(3b, bad_put_user_clac) - _ASM_EXTABLE_UA(4b, bad_put_user_clac) + _ASM_EXTABLE_UA(1b, .Lbad_put_user_clac) + _ASM_EXTABLE_UA(2b, .Lbad_put_user_clac) + _ASM_EXTABLE_UA(3b, .Lbad_put_user_clac) + _ASM_EXTABLE_UA(4b, .Lbad_put_user_clac) #ifdef CONFIG_X86_32 - _ASM_EXTABLE_UA(5b, bad_put_user_clac) + _ASM_EXTABLE_UA(5b, .Lbad_put_user_clac) #endif diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index c909961e678a..363ec132df7e 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -11,11 +11,11 @@ .macro THUNK reg .section .text.__x86.indirect_thunk -ENTRY(__x86_indirect_thunk_\reg) +SYM_FUNC_START(__x86_indirect_thunk_\reg) CFI_STARTPROC JMP_NOSPEC %\reg CFI_ENDPROC -ENDPROC(__x86_indirect_thunk_\reg) +SYM_FUNC_END(__x86_indirect_thunk_\reg) .endm /* diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index e0b85930dd77..53adc1762ec0 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -333,7 +333,7 @@ AVXcode: 1 06: CLTS 07: SYSRET (o64) 08: INVD -09: WBINVD +09: WBINVD | WBNOINVD (F3) 0a: 0b: UD2 (1B) 0c: @@ -364,7 +364,7 @@ AVXcode: 1 # a ModR/M byte. 1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev 1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv -1c: +1c: Grp20 (1A),(1C) 1d: 1e: 1f: NOP Ev @@ -695,16 +695,28 @@ AVXcode: 2 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) -# Skip 0x50-0x57 +50: vpdpbusd Vx,Hx,Wx (66),(ev) +51: vpdpbusds Vx,Hx,Wx (66),(ev) +52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) +53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) +54: vpopcntb/w Vx,Wx (66),(ev) +55: vpopcntd/q Vx,Wx (66),(ev) 58: vpbroadcastd Vx,Wx (66),(v) 59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) 5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) 5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) -# Skip 0x5c-0x63 +# Skip 0x5c-0x61 +62: vpexpandb/w Vx,Wx (66),(ev) +63: vpcompressb/w Wx,Vx (66),(ev) 64: vpblendmd/q Vx,Hx,Wx (66),(ev) 65: vblendmps/d Vx,Hx,Wx (66),(ev) 66: vpblendmb/w Vx,Hx,Wx (66),(ev) -# Skip 0x67-0x74 +68: vp2intersectd/q Kx,Hx,Wx (F2),(ev) +# Skip 0x69-0x6f +70: vpshldvw Vx,Hx,Wx (66),(ev) +71: vpshldvd/q Vx,Hx,Wx (66),(ev) +72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev) +73: vpshrdvd/q Vx,Hx,Wx (66),(ev) 75: vpermi2b/w Vx,Hx,Wx (66),(ev) 76: vpermi2d/q Vx,Hx,Wx (66),(ev) 77: vpermi2ps/d Vx,Hx,Wx (66),(ev) @@ -727,6 +739,7 @@ AVXcode: 2 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v) 8d: vpermb/w Vx,Hx,Wx (66),(ev) 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v) +8f: vpshufbitqmb Kx,Hx,Wx (66),(ev) # 0x0f 0x38 0x90-0xbf (FMA) 90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo) 91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo) @@ -738,8 +751,8 @@ AVXcode: 2 97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v) 98: vfmadd132ps/d Vx,Hx,Wx (66),(v) 99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1) -9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) -9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) +9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) | v4fmaddps Vdqq,Hdqq,Wdq (F2),(ev) +9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) | v4fmaddss Vdq,Hdq,Wdq (F2),(ev) 9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v) 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1) 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v) @@ -752,8 +765,8 @@ a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v) a8: vfmadd213ps/d Vx,Hx,Wx (66),(v) a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1) -aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) -ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) +aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) | v4fnmaddps Vdqq,Hdqq,Wdq (F2),(ev) +ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) | v4fnmaddss Vdq,Hdq,Wdq (F2),(ev) ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v) ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1) ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v) @@ -780,11 +793,12 @@ ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) +cf: vgf2p8mulb Vx,Wx (66) db: VAESIMC Vdq,Wdq (66),(v1) -dc: VAESENC Vdq,Hdq,Wdq (66),(v1) -dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) -de: VAESDEC Vdq,Hdq,Wdq (66),(v1) -df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1) +dc: vaesenc Vx,Hx,Wx (66) +dd: vaesenclast Vx,Hx,Wx (66) +de: vaesdec Vx,Hx,Wx (66) +df: vaesdeclast Vx,Hx,Wx (66) f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2) f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2) f2: ANDN Gy,By,Ey (v) @@ -792,6 +806,8 @@ f3: Grp17 (1A) f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) +f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) +f9: MOVDIRI My,Gy EndTable Table: 3-byte opcode 2 (0x0f 0x3a) @@ -846,7 +862,7 @@ AVXcode: 3 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1) 42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo) 43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) -44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1) +44: vpclmulqdq Vx,Hx,Wx,Ib (66) 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v) 4a: vblendvps Vx,Hx,Wx,Lx (66),(v) 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v) @@ -863,7 +879,13 @@ AVXcode: 3 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) 66: vfpclassps/d Vk,Wx,Ib (66),(ev) 67: vfpclassss/d Vk,Wx,Ib (66),(ev) +70: vpshldw Vx,Hx,Wx,Ib (66),(ev) +71: vpshldd/q Vx,Hx,Wx,Ib (66),(ev) +72: vpshrdw Vx,Hx,Wx,Ib (66),(ev) +73: vpshrdd/q Vx,Hx,Wx,Ib (66),(ev) cc: sha1rnds4 Vdq,Wdq,Ib +ce: vgf2p8affineqb Vx,Wx,Ib (66) +cf: vgf2p8affineinvqb Vx,Wx,Ib (66) df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) f0: RORX Gy,Ey,Ib (F2),(v) EndTable @@ -907,7 +929,7 @@ EndTable GrpTable: Grp3_2 0: TEST Ev,Iz -1: +1: TEST Ev,Iz 2: NOT Ev 3: NEG Ev 4: MUL rAX,Ev @@ -943,9 +965,9 @@ GrpTable: Grp6 EndTable GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) -2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) +2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv 5: rdpkru (110),(11B) | wrpkru (111),(11B) @@ -1020,7 +1042,7 @@ GrpTable: Grp15 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) 4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) -6: XSAVEOPT | clwb (66) | mfence (11B) +6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B) 7: clflush | clflushopt (66) | sfence (11B) EndTable @@ -1051,6 +1073,10 @@ GrpTable: Grp19 6: vscatterpf1qps/d Wx (66),(ev) EndTable +GrpTable: Grp20 +0: cldemote Mb +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH diff --git a/arch/x86/math-emu/div_Xsig.S b/arch/x86/math-emu/div_Xsig.S index ee08449d20fd..951da2ad54bb 100644 --- a/arch/x86/math-emu/div_Xsig.S +++ b/arch/x86/math-emu/div_Xsig.S @@ -75,7 +75,7 @@ FPU_result_1: .text -ENTRY(div_Xsig) +SYM_FUNC_START(div_Xsig) pushl %ebp movl %esp,%ebp #ifndef NON_REENTRANT_FPU @@ -364,4 +364,4 @@ L_bugged_2: pop %ebx jmp L_exit #endif /* PARANOID */ -ENDPROC(div_Xsig) +SYM_FUNC_END(div_Xsig) diff --git a/arch/x86/math-emu/div_small.S b/arch/x86/math-emu/div_small.S index 8f5025c80ee0..d047d1816abe 100644 --- a/arch/x86/math-emu/div_small.S +++ b/arch/x86/math-emu/div_small.S @@ -19,7 +19,7 @@ #include "fpu_emu.h" .text -ENTRY(FPU_div_small) +SYM_FUNC_START(FPU_div_small) pushl %ebp movl %esp,%ebp @@ -45,4 +45,4 @@ ENTRY(FPU_div_small) leave ret -ENDPROC(FPU_div_small) +SYM_FUNC_END(FPU_div_small) diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index f98a0c956764..9b41391867dc 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -107,6 +107,8 @@ static inline bool seg_writable(struct desc_struct *d) #define FPU_access_ok(y,z) if ( !access_ok(y,z) ) \ math_abort(FPU_info,SIGSEGV) #define FPU_abort math_abort(FPU_info, SIGSEGV) +#define FPU_copy_from_user(to, from, n) \ + do { if (copy_from_user(to, from, n)) FPU_abort; } while (0) #undef FPU_IGNORE_CODE_SEGV #ifdef FPU_IGNORE_CODE_SEGV @@ -122,7 +124,7 @@ static inline bool seg_writable(struct desc_struct *d) #define FPU_code_access_ok(z) FPU_access_ok((void __user *)FPU_EIP,z) #endif -#define FPU_get_user(x,y) get_user((x),(y)) -#define FPU_put_user(x,y) put_user((x),(y)) +#define FPU_get_user(x,y) do { if (get_user((x),(y))) FPU_abort; } while (0) +#define FPU_put_user(x,y) do { if (put_user((x),(y))) FPU_abort; } while (0) #endif diff --git a/arch/x86/math-emu/mul_Xsig.S b/arch/x86/math-emu/mul_Xsig.S index 3e489122a2b0..4afc7b1fa6e9 100644 --- a/arch/x86/math-emu/mul_Xsig.S +++ b/arch/x86/math-emu/mul_Xsig.S @@ -25,7 +25,7 @@ #include "fpu_emu.h" .text -ENTRY(mul32_Xsig) +SYM_FUNC_START(mul32_Xsig) pushl %ebp movl %esp,%ebp subl $16,%esp @@ -63,10 +63,10 @@ ENTRY(mul32_Xsig) popl %esi leave ret -ENDPROC(mul32_Xsig) +SYM_FUNC_END(mul32_Xsig) -ENTRY(mul64_Xsig) +SYM_FUNC_START(mul64_Xsig) pushl %ebp movl %esp,%ebp subl $16,%esp @@ -116,11 +116,11 @@ ENTRY(mul64_Xsig) popl %esi leave ret -ENDPROC(mul64_Xsig) +SYM_FUNC_END(mul64_Xsig) -ENTRY(mul_Xsig_Xsig) +SYM_FUNC_START(mul_Xsig_Xsig) pushl %ebp movl %esp,%ebp subl $16,%esp @@ -176,4 +176,4 @@ ENTRY(mul_Xsig_Xsig) popl %esi leave ret -ENDPROC(mul_Xsig_Xsig) +SYM_FUNC_END(mul_Xsig_Xsig) diff --git a/arch/x86/math-emu/polynom_Xsig.S b/arch/x86/math-emu/polynom_Xsig.S index 604f0b2d17e8..702315eecb86 100644 --- a/arch/x86/math-emu/polynom_Xsig.S +++ b/arch/x86/math-emu/polynom_Xsig.S @@ -37,7 +37,7 @@ #define OVERFLOWED -16(%ebp) /* addition overflow flag */ .text -ENTRY(polynomial_Xsig) +SYM_FUNC_START(polynomial_Xsig) pushl %ebp movl %esp,%ebp subl $32,%esp @@ -134,4 +134,4 @@ L_accum_done: popl %esi leave ret -ENDPROC(polynomial_Xsig) +SYM_FUNC_END(polynomial_Xsig) diff --git a/arch/x86/math-emu/reg_ld_str.c b/arch/x86/math-emu/reg_ld_str.c index f3779743d15e..fe6246ff9887 100644 --- a/arch/x86/math-emu/reg_ld_str.c +++ b/arch/x86/math-emu/reg_ld_str.c @@ -85,7 +85,7 @@ int FPU_load_extended(long double __user *s, int stnr) RE_ENTRANT_CHECK_OFF; FPU_access_ok(s, 10); - __copy_from_user(sti_ptr, s, 10); + FPU_copy_from_user(sti_ptr, s, 10); RE_ENTRANT_CHECK_ON; return FPU_tagof(sti_ptr); @@ -1126,9 +1126,9 @@ void frstor(fpu_addr_modes addr_modes, u_char __user *data_address) /* Copy all registers in stack order. */ RE_ENTRANT_CHECK_OFF; FPU_access_ok(s, 80); - __copy_from_user(register_base + offset, s, other); + FPU_copy_from_user(register_base + offset, s, other); if (offset) - __copy_from_user(register_base, s + other, offset); + FPU_copy_from_user(register_base, s + other, offset); RE_ENTRANT_CHECK_ON; for (i = 0; i < 8; i++) { diff --git a/arch/x86/math-emu/reg_norm.S b/arch/x86/math-emu/reg_norm.S index 7f6b4392a15d..cad1d60b1e84 100644 --- a/arch/x86/math-emu/reg_norm.S +++ b/arch/x86/math-emu/reg_norm.S @@ -22,7 +22,7 @@ .text -ENTRY(FPU_normalize) +SYM_FUNC_START(FPU_normalize) pushl %ebp movl %esp,%ebp pushl %ebx @@ -95,12 +95,12 @@ L_overflow: call arith_overflow pop %ebx jmp L_exit -ENDPROC(FPU_normalize) +SYM_FUNC_END(FPU_normalize) /* Normalise without reporting underflow or overflow */ -ENTRY(FPU_normalize_nuo) +SYM_FUNC_START(FPU_normalize_nuo) pushl %ebp movl %esp,%ebp pushl %ebx @@ -147,4 +147,4 @@ L_exit_nuo_zero: popl %ebx leave ret -ENDPROC(FPU_normalize_nuo) +SYM_FUNC_END(FPU_normalize_nuo) diff --git a/arch/x86/math-emu/reg_round.S b/arch/x86/math-emu/reg_round.S index 04563421ee7d..11a1f798451b 100644 --- a/arch/x86/math-emu/reg_round.S +++ b/arch/x86/math-emu/reg_round.S @@ -109,7 +109,7 @@ FPU_denormal: .globl fpu_Arith_exit /* Entry point when called from C */ -ENTRY(FPU_round) +SYM_FUNC_START(FPU_round) pushl %ebp movl %esp,%ebp pushl %esi @@ -708,4 +708,4 @@ L_exception_exit: jmp fpu_reg_round_special_exit #endif /* PARANOID */ -ENDPROC(FPU_round) +SYM_FUNC_END(FPU_round) diff --git a/arch/x86/math-emu/reg_u_add.S b/arch/x86/math-emu/reg_u_add.S index 50fe9f8c893c..9c9e2c810afe 100644 --- a/arch/x86/math-emu/reg_u_add.S +++ b/arch/x86/math-emu/reg_u_add.S @@ -32,7 +32,7 @@ #include "control_w.h" .text -ENTRY(FPU_u_add) +SYM_FUNC_START(FPU_u_add) pushl %ebp movl %esp,%ebp pushl %esi @@ -166,4 +166,4 @@ L_exit: leave ret #endif /* PARANOID */ -ENDPROC(FPU_u_add) +SYM_FUNC_END(FPU_u_add) diff --git a/arch/x86/math-emu/reg_u_div.S b/arch/x86/math-emu/reg_u_div.S index 94d545e118e4..e2fb5c2644c5 100644 --- a/arch/x86/math-emu/reg_u_div.S +++ b/arch/x86/math-emu/reg_u_div.S @@ -75,7 +75,7 @@ FPU_ovfl_flag: #define DEST PARAM3 .text -ENTRY(FPU_u_div) +SYM_FUNC_START(FPU_u_div) pushl %ebp movl %esp,%ebp #ifndef NON_REENTRANT_FPU @@ -471,4 +471,4 @@ L_exit: ret #endif /* PARANOID */ -ENDPROC(FPU_u_div) +SYM_FUNC_END(FPU_u_div) diff --git a/arch/x86/math-emu/reg_u_mul.S b/arch/x86/math-emu/reg_u_mul.S index 21cde47fb3e5..0c779c87ac5b 100644 --- a/arch/x86/math-emu/reg_u_mul.S +++ b/arch/x86/math-emu/reg_u_mul.S @@ -45,7 +45,7 @@ FPU_accum_1: .text -ENTRY(FPU_u_mul) +SYM_FUNC_START(FPU_u_mul) pushl %ebp movl %esp,%ebp #ifndef NON_REENTRANT_FPU @@ -147,4 +147,4 @@ L_exit: ret #endif /* PARANOID */ -ENDPROC(FPU_u_mul) +SYM_FUNC_END(FPU_u_mul) diff --git a/arch/x86/math-emu/reg_u_sub.S b/arch/x86/math-emu/reg_u_sub.S index f05dea7dec38..e9bb7c248649 100644 --- a/arch/x86/math-emu/reg_u_sub.S +++ b/arch/x86/math-emu/reg_u_sub.S @@ -33,7 +33,7 @@ #include "control_w.h" .text -ENTRY(FPU_u_sub) +SYM_FUNC_START(FPU_u_sub) pushl %ebp movl %esp,%ebp pushl %esi @@ -271,4 +271,4 @@ L_exit: popl %esi leave ret -ENDPROC(FPU_u_sub) +SYM_FUNC_END(FPU_u_sub) diff --git a/arch/x86/math-emu/round_Xsig.S b/arch/x86/math-emu/round_Xsig.S index 226a51e991f1..d9d7de8dbd7b 100644 --- a/arch/x86/math-emu/round_Xsig.S +++ b/arch/x86/math-emu/round_Xsig.S @@ -23,7 +23,7 @@ .text -ENTRY(round_Xsig) +SYM_FUNC_START(round_Xsig) pushl %ebp movl %esp,%ebp pushl %ebx /* Reserve some space */ @@ -79,11 +79,11 @@ L_exit: popl %ebx leave ret -ENDPROC(round_Xsig) +SYM_FUNC_END(round_Xsig) -ENTRY(norm_Xsig) +SYM_FUNC_START(norm_Xsig) pushl %ebp movl %esp,%ebp pushl %ebx /* Reserve some space */ @@ -139,4 +139,4 @@ L_n_exit: popl %ebx leave ret -ENDPROC(norm_Xsig) +SYM_FUNC_END(norm_Xsig) diff --git a/arch/x86/math-emu/shr_Xsig.S b/arch/x86/math-emu/shr_Xsig.S index 96f4779aa9c1..726af985f758 100644 --- a/arch/x86/math-emu/shr_Xsig.S +++ b/arch/x86/math-emu/shr_Xsig.S @@ -22,7 +22,7 @@ #include "fpu_emu.h" .text -ENTRY(shr_Xsig) +SYM_FUNC_START(shr_Xsig) push %ebp movl %esp,%ebp pushl %esi @@ -86,4 +86,4 @@ L_more_than_95: popl %esi leave ret -ENDPROC(shr_Xsig) +SYM_FUNC_END(shr_Xsig) diff --git a/arch/x86/math-emu/wm_shrx.S b/arch/x86/math-emu/wm_shrx.S index d588874eb6fb..4fc89174caf0 100644 --- a/arch/x86/math-emu/wm_shrx.S +++ b/arch/x86/math-emu/wm_shrx.S @@ -33,7 +33,7 @@ | Results returned in the 64 bit arg and eax. | +---------------------------------------------------------------------------*/ -ENTRY(FPU_shrx) +SYM_FUNC_START(FPU_shrx) push %ebp movl %esp,%ebp pushl %esi @@ -93,7 +93,7 @@ L_more_than_95: popl %esi leave ret -ENDPROC(FPU_shrx) +SYM_FUNC_END(FPU_shrx) /*---------------------------------------------------------------------------+ @@ -112,7 +112,7 @@ ENDPROC(FPU_shrx) | part which has been shifted out of the arg. | | Results returned in the 64 bit arg and eax. | +---------------------------------------------------------------------------*/ -ENTRY(FPU_shrxs) +SYM_FUNC_START(FPU_shrxs) push %ebp movl %esp,%ebp pushl %esi @@ -204,4 +204,4 @@ Ls_more_than_95: popl %esi leave ret -ENDPROC(FPU_shrxs) +SYM_FUNC_END(FPU_shrxs) diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S index f031c0e19356..3b2b58164ec1 100644 --- a/arch/x86/math-emu/wm_sqrt.S +++ b/arch/x86/math-emu/wm_sqrt.S @@ -75,7 +75,7 @@ FPU_fsqrt_arg_0: .text -ENTRY(wm_sqrt) +SYM_FUNC_START(wm_sqrt) pushl %ebp movl %esp,%ebp #ifndef NON_REENTRANT_FPU @@ -469,4 +469,4 @@ sqrt_more_prec_large: /* Our estimate is too large */ movl $0x7fffff00,%eax jmp sqrt_round_result -ENDPROC(wm_sqrt) +SYM_FUNC_END(wm_sqrt) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 84373dc9b341..98f7c6fa2eaa 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -12,8 +12,10 @@ CFLAGS_REMOVE_mem_encrypt.o = -pg CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif -obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o +obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ + pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o + +obj-y += pat/ # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) @@ -23,13 +25,11 @@ CFLAGS_mem_encrypt_identity.o := $(nostackp) CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace -obj-$(CONFIG_X86_PAT) += pat_rbtree.o - obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_X86_PTDUMP_CORE) += dump_pagetables.o -obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o +obj-$(CONFIG_PTDUMP_CORE) += dump_pagetables.o +obj-$(CONFIG_PTDUMP_DEBUGFS) += debug_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o @@ -45,7 +45,6 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o obj-$(CONFIG_ACPI_NUMA) += srat.o obj-$(CONFIG_NUMA_EMU) += numa_emulation.o -obj-$(CONFIG_X86_INTEL_MPX) += mpx.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index 752ad11d6868..56f9189bbadb 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -17,6 +17,10 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks); DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks); #endif +#if defined(CONFIG_X86_32) && defined(CONFIG_DOUBLEFAULT) +DECLARE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack); +#endif + struct cpu_entry_area *get_cpu_entry_area(int cpu) { unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE; @@ -108,7 +112,15 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu) cea_map_stack(MCE); } #else -static inline void percpu_setup_exception_stacks(unsigned int cpu) {} +static inline void percpu_setup_exception_stacks(unsigned int cpu) +{ +#ifdef CONFIG_DOUBLEFAULT + struct cpu_entry_area *cea = get_cpu_entry_area(cpu); + + cea_map_percpu_pages(&cea->doublefault_stack, + &per_cpu(doublefault_stack, cpu), 1, PAGE_KERNEL); +#endif +} #endif /* Setup the fixmap mappings only once per-processor */ @@ -161,6 +173,14 @@ static void __init setup_cpu_entry_area(unsigned int cpu) BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^ offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK); BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0); + /* + * VMX changes the host TR limit to 0x67 after a VM exit. This is + * okay, since 0x67 covers the size of struct x86_hw_tss. Make sure + * that this is correct. + */ + BUILD_BUG_ON(offsetof(struct tss_struct, x86_tss) != 0); + BUILD_BUG_ON(sizeof(struct x86_hw_tss) != 0x68); + cea_map_percpu_pages(&cea->tss, &per_cpu(cpu_tss_rw, cpu), sizeof(struct tss_struct) / PAGE_SIZE, tss_prot); @@ -178,7 +198,9 @@ static __init void setup_cpu_entry_area_ptes(void) #ifdef CONFIG_X86_32 unsigned long start, end; - BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE); + /* The +1 is for the readonly IDT: */ + BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE); + BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE); BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK); start = CPU_ENTRY_AREA_BASE; diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index 39001a401eff..4a3b62f780b4 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -7,7 +7,7 @@ static int ptdump_show(struct seq_file *m, void *v) { - ptdump_walk_pgd_level_debugfs(m, NULL, false); + ptdump_walk_pgd_level_debugfs(m, &init_mm, false); return 0; } @@ -15,11 +15,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump); static int ptdump_curknl_show(struct seq_file *m, void *v) { - if (current->mm->pgd) { - down_read(¤t->mm->mmap_sem); - ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false); - up_read(¤t->mm->mmap_sem); - } + if (current->mm->pgd) + ptdump_walk_pgd_level_debugfs(m, current->mm, false); return 0; } @@ -28,11 +25,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curknl); #ifdef CONFIG_PAGE_TABLE_ISOLATION static int ptdump_curusr_show(struct seq_file *m, void *v) { - if (current->mm->pgd) { - down_read(¤t->mm->mmap_sem); - ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true); - up_read(¤t->mm->mmap_sem); - } + if (current->mm->pgd) + ptdump_walk_pgd_level_debugfs(m, current->mm, true); return 0; } @@ -43,7 +37,7 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curusr); static int ptdump_efi_show(struct seq_file *m, void *v) { if (efi_mm.pgd) - ptdump_walk_pgd_level_debugfs(m, efi_mm.pgd, false); + ptdump_walk_pgd_level_debugfs(m, &efi_mm, false); return 0; } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index ab67822fd2f4..64229dad7eab 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -16,6 +16,7 @@ #include <linux/seq_file.h> #include <linux/highmem.h> #include <linux/pci.h> +#include <linux/ptdump.h> #include <asm/e820/types.h> #include <asm/pgtable.h> @@ -26,16 +27,18 @@ * when a "break" in the continuity is found. */ struct pg_state { + struct ptdump_state ptdump; int level; - pgprot_t current_prot; + pgprotval_t current_prot; pgprotval_t effective_prot; + pgprotval_t prot_levels[5]; unsigned long start_address; - unsigned long current_address; const struct addr_marker *marker; unsigned long lines; bool to_dmesg; bool check_wx; unsigned long wx_pages; + struct seq_file *seq; }; struct addr_marker { @@ -174,11 +177,10 @@ static struct addr_marker address_markers[] = { /* * Print a readable form of a pgprot_t to the seq_file */ -static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) +static void printk_prot(struct seq_file *m, pgprotval_t pr, int level, bool dmsg) { - pgprotval_t pr = pgprot_val(prot); static const char * const level_name[] = - { "cr3", "pgd", "p4d", "pud", "pmd", "pte" }; + { "pgd", "p4d", "pud", "pmd", "pte" }; if (!(pr & _PAGE_PRESENT)) { /* Not present */ @@ -202,12 +204,12 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) pt_dump_cont_printf(m, dmsg, " "); /* Bit 7 has a different meaning on level 3 vs 4 */ - if (level <= 4 && pr & _PAGE_PSE) + if (level <= 3 && pr & _PAGE_PSE) pt_dump_cont_printf(m, dmsg, "PSE "); else pt_dump_cont_printf(m, dmsg, " "); - if ((level == 5 && pr & _PAGE_PAT) || - ((level == 4 || level == 3) && pr & _PAGE_PAT_LARGE)) + if ((level == 4 && pr & _PAGE_PAT) || + ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE)) pt_dump_cont_printf(m, dmsg, "PAT "); else pt_dump_cont_printf(m, dmsg, " "); @@ -223,24 +225,11 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]); } -/* - * On 64 bits, sign-extend the 48 bit address to 64 bit - */ -static unsigned long normalize_addr(unsigned long u) -{ - int shift; - if (!IS_ENABLED(CONFIG_X86_64)) - return u; - - shift = 64 - (__VIRTUAL_MASK_SHIFT + 1); - return (signed long)(u << shift) >> shift; -} - -static void note_wx(struct pg_state *st) +static void note_wx(struct pg_state *st, unsigned long addr) { unsigned long npages; - npages = (st->current_address - st->start_address) / PAGE_SIZE; + npages = (addr - st->start_address) / PAGE_SIZE; #ifdef CONFIG_PCI_BIOS /* @@ -248,7 +237,7 @@ static void note_wx(struct pg_state *st) * Inform about it, but avoid the warning. */ if (pcibios_enabled && st->start_address >= PAGE_OFFSET + BIOS_BEGIN && - st->current_address <= PAGE_OFFSET + BIOS_END) { + addr <= PAGE_OFFSET + BIOS_END) { pr_warn_once("x86/mm: PCI BIOS W+X mapping %lu pages\n", npages); return; } @@ -260,27 +249,47 @@ static void note_wx(struct pg_state *st) (void *)st->start_address); } +static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2) +{ + return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) | + ((prot1 | prot2) & _PAGE_NX); +} + /* * This function gets called on a break in a continuous series * of PTE entries; the next one is different so we need to * print what we collected so far. */ -static void note_page(struct seq_file *m, struct pg_state *st, - pgprot_t new_prot, pgprotval_t new_eff, int level) +static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, + unsigned long val) { - pgprotval_t prot, cur, eff; + struct pg_state *st = container_of(pt_st, struct pg_state, ptdump); + pgprotval_t new_prot, new_eff; + pgprotval_t cur, eff; static const char units[] = "BKMGTPE"; + struct seq_file *m = st->seq; + + new_prot = val & PTE_FLAGS_MASK; + + if (level > 0) { + new_eff = effective_prot(st->prot_levels[level - 1], + new_prot); + } else { + new_eff = new_prot; + } + + if (level >= 0) + st->prot_levels[level] = new_eff; /* * If we have a "break" in the series, we need to flush the state that * we have now. "break" is either changing perms, levels or * address space marker. */ - prot = pgprot_val(new_prot); - cur = pgprot_val(st->current_prot); + cur = st->current_prot; eff = st->effective_prot; - if (!st->level) { + if (st->level == -1) { /* First entry */ st->current_prot = new_prot; st->effective_prot = new_eff; @@ -289,14 +298,14 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->lines = 0; pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", st->marker->name); - } else if (prot != cur || new_eff != eff || level != st->level || - st->current_address >= st->marker[1].start_address) { + } else if (new_prot != cur || new_eff != eff || level != st->level || + addr >= st->marker[1].start_address) { const char *unit = units; unsigned long delta; int width = sizeof(unsigned long) * 2; if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX)) - note_wx(st); + note_wx(st, addr); /* * Now print the actual finished series @@ -306,9 +315,9 @@ static void note_page(struct seq_file *m, struct pg_state *st, pt_dump_seq_printf(m, st->to_dmesg, "0x%0*lx-0x%0*lx ", width, st->start_address, - width, st->current_address); + width, addr); - delta = st->current_address - st->start_address; + delta = addr - st->start_address; while (!(delta & 1023) && unit[1]) { delta >>= 10; unit++; @@ -325,7 +334,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, * such as the start of vmalloc space etc. * This helps in the interpretation. */ - if (st->current_address >= st->marker[1].start_address) { + if (addr >= st->marker[1].start_address) { if (st->marker->max_lines && st->lines > st->marker->max_lines) { unsigned long nskip = @@ -341,222 +350,45 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->marker->name); } - st->start_address = st->current_address; + st->start_address = addr; st->current_prot = new_prot; st->effective_prot = new_eff; st->level = level; } } -static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2) -{ - return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) | - ((prot1 | prot2) & _PAGE_NX); -} - -static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, - pgprotval_t eff_in, unsigned long P) -{ - int i; - pte_t *pte; - pgprotval_t prot, eff; - - for (i = 0; i < PTRS_PER_PTE; i++) { - st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); - pte = pte_offset_map(&addr, st->current_address); - prot = pte_flags(*pte); - eff = effective_prot(eff_in, prot); - note_page(m, st, __pgprot(prot), eff, 5); - pte_unmap(pte); - } -} -#ifdef CONFIG_KASAN - -/* - * This is an optimization for KASAN=y case. Since all kasan page tables - * eventually point to the kasan_early_shadow_page we could call note_page() - * right away without walking through lower level page tables. This saves - * us dozens of seconds (minutes for 5-level config) while checking for - * W+X mapping or reading kernel_page_tables debugfs file. - */ -static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, - void *pt) -{ - if (__pa(pt) == __pa(kasan_early_shadow_pmd) || - (pgtable_l5_enabled() && - __pa(pt) == __pa(kasan_early_shadow_p4d)) || - __pa(pt) == __pa(kasan_early_shadow_pud)) { - pgprotval_t prot = pte_flags(kasan_early_shadow_pte[0]); - note_page(m, st, __pgprot(prot), 0, 5); - return true; - } - return false; -} -#else -static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, - void *pt) -{ - return false; -} -#endif - -#if PTRS_PER_PMD > 1 - -static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, - pgprotval_t eff_in, unsigned long P) -{ - int i; - pmd_t *start, *pmd_start; - pgprotval_t prot, eff; - - pmd_start = start = (pmd_t *)pud_page_vaddr(addr); - for (i = 0; i < PTRS_PER_PMD; i++) { - st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); - if (!pmd_none(*start)) { - prot = pmd_flags(*start); - eff = effective_prot(eff_in, prot); - if (pmd_large(*start) || !pmd_present(*start)) { - note_page(m, st, __pgprot(prot), eff, 4); - } else if (!kasan_page_table(m, st, pmd_start)) { - walk_pte_level(m, st, *start, eff, - P + i * PMD_LEVEL_MULT); - } - } else - note_page(m, st, __pgprot(0), 0, 4); - start++; - } -} - -#else -#define walk_pmd_level(m,s,a,e,p) walk_pte_level(m,s,__pmd(pud_val(a)),e,p) -#define pud_large(a) pmd_large(__pmd(pud_val(a))) -#define pud_none(a) pmd_none(__pmd(pud_val(a))) -#endif - -#if PTRS_PER_PUD > 1 - -static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, - pgprotval_t eff_in, unsigned long P) -{ - int i; - pud_t *start, *pud_start; - pgprotval_t prot, eff; - - pud_start = start = (pud_t *)p4d_page_vaddr(addr); - - for (i = 0; i < PTRS_PER_PUD; i++) { - st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); - if (!pud_none(*start)) { - prot = pud_flags(*start); - eff = effective_prot(eff_in, prot); - if (pud_large(*start) || !pud_present(*start)) { - note_page(m, st, __pgprot(prot), eff, 3); - } else if (!kasan_page_table(m, st, pud_start)) { - walk_pmd_level(m, st, *start, eff, - P + i * PUD_LEVEL_MULT); - } - } else - note_page(m, st, __pgprot(0), 0, 3); - - start++; - } -} - -#else -#define walk_pud_level(m,s,a,e,p) walk_pmd_level(m,s,__pud(p4d_val(a)),e,p) -#define p4d_large(a) pud_large(__pud(p4d_val(a))) -#define p4d_none(a) pud_none(__pud(p4d_val(a))) -#endif - -static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, - pgprotval_t eff_in, unsigned long P) -{ - int i; - p4d_t *start, *p4d_start; - pgprotval_t prot, eff; - - if (PTRS_PER_P4D == 1) - return walk_pud_level(m, st, __p4d(pgd_val(addr)), eff_in, P); - - p4d_start = start = (p4d_t *)pgd_page_vaddr(addr); - - for (i = 0; i < PTRS_PER_P4D; i++) { - st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT); - if (!p4d_none(*start)) { - prot = p4d_flags(*start); - eff = effective_prot(eff_in, prot); - if (p4d_large(*start) || !p4d_present(*start)) { - note_page(m, st, __pgprot(prot), eff, 2); - } else if (!kasan_page_table(m, st, p4d_start)) { - walk_pud_level(m, st, *start, eff, - P + i * P4D_LEVEL_MULT); - } - } else - note_page(m, st, __pgprot(0), 0, 2); - - start++; - } -} - -#define pgd_large(a) (pgtable_l5_enabled() ? pgd_large(a) : p4d_large(__p4d(pgd_val(a)))) -#define pgd_none(a) (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a)))) - -static inline bool is_hypervisor_range(int idx) -{ -#ifdef CONFIG_X86_64 - /* - * A hole in the beginning of kernel address space reserved - * for a hypervisor. - */ - return (idx >= pgd_index(GUARD_HOLE_BASE_ADDR)) && - (idx < pgd_index(GUARD_HOLE_END_ADDR)); -#else - return false; -#endif -} - -static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, +static void ptdump_walk_pgd_level_core(struct seq_file *m, + struct mm_struct *mm, pgd_t *pgd, bool checkwx, bool dmesg) { - pgd_t *start = INIT_PGD; - pgprotval_t prot, eff; - int i; - struct pg_state st = {}; - - if (pgd) { - start = pgd; - st.to_dmesg = dmesg; - } + const struct ptdump_range ptdump_ranges[] = { +#ifdef CONFIG_X86_64 - st.check_wx = checkwx; - if (checkwx) - st.wx_pages = 0; +#define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1)) +#define normalize_addr(u) ((signed long)((u) << normalize_addr_shift) >> \ + normalize_addr_shift) - for (i = 0; i < PTRS_PER_PGD; i++) { - st.current_address = normalize_addr(i * PGD_LEVEL_MULT); - if (!pgd_none(*start) && !is_hypervisor_range(i)) { - prot = pgd_flags(*start); -#ifdef CONFIG_X86_PAE - eff = _PAGE_USER | _PAGE_RW; + {0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2}, + {normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL}, #else - eff = prot; + {0, ~0UL}, #endif - if (pgd_large(*start) || !pgd_present(*start)) { - note_page(m, &st, __pgprot(prot), eff, 1); - } else { - walk_p4d_level(m, &st, *start, eff, - i * PGD_LEVEL_MULT); - } - } else - note_page(m, &st, __pgprot(0), 0, 1); + {0, 0} +}; - cond_resched(); - start++; - } + struct pg_state st = { + .ptdump = { + .note_page = note_page, + .range = ptdump_ranges + }, + .level = -1, + .to_dmesg = dmesg, + .check_wx = checkwx, + .seq = m + }; + + ptdump_walk_pgd(&st.ptdump, mm, pgd); - /* Flush out the last page */ - st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT); - note_page(m, &st, __pgprot(0), 0, 0); if (!checkwx) return; if (st.wx_pages) @@ -566,18 +398,20 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n"); } -void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) +void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm) { - ptdump_walk_pgd_level_core(m, pgd, false, true); + ptdump_walk_pgd_level_core(m, mm, mm->pgd, false, true); } -void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user) +void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, + bool user) { + pgd_t *pgd = mm->pgd; #ifdef CONFIG_PAGE_TABLE_ISOLATION if (user && boot_cpu_has(X86_FEATURE_PTI)) pgd = kernel_to_user_pgdp(pgd); #endif - ptdump_walk_pgd_level_core(m, pgd, false, false); + ptdump_walk_pgd_level_core(m, mm, pgd, false, false); } EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs); @@ -592,13 +426,13 @@ void ptdump_walk_user_pgd_level_checkwx(void) pr_info("x86/mm: Checking user space page tables\n"); pgd = kernel_to_user_pgdp(pgd); - ptdump_walk_pgd_level_core(NULL, pgd, true, false); + ptdump_walk_pgd_level_core(NULL, &init_mm, pgd, true, false); #endif } void ptdump_walk_pgd_level_checkwx(void) { - ptdump_walk_pgd_level_core(NULL, NULL, true, false); + ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false); } static int __init pt_dump_init(void) diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 4d75bc656f97..30bb0bd3b1b8 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -45,55 +45,6 @@ __visible bool ex_handler_fault(const struct exception_table_entry *fixup, EXPORT_SYMBOL_GPL(ex_handler_fault); /* - * Handler for UD0 exception following a failed test against the - * result of a refcount inc/dec/add/sub. - */ -__visible bool ex_handler_refcount(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) -{ - /* First unconditionally saturate the refcount. */ - *(int *)regs->cx = INT_MIN / 2; - - /* - * Strictly speaking, this reports the fixup destination, not - * the fault location, and not the actually overflowing - * instruction, which is the instruction before the "js", but - * since that instruction could be a variety of lengths, just - * report the location after the overflow, which should be close - * enough for finding the overflow, as it's at least back in - * the function, having returned from .text.unlikely. - */ - regs->ip = ex_fixup_addr(fixup); - - /* - * This function has been called because either a negative refcount - * value was seen by any of the refcount functions, or a zero - * refcount value was seen by refcount_dec(). - * - * If we crossed from INT_MAX to INT_MIN, OF (Overflow Flag: result - * wrapped around) will be set. Additionally, seeing the refcount - * reach 0 will set ZF (Zero Flag: result was zero). In each of - * these cases we want a report, since it's a boundary condition. - * The SF case is not reported since it indicates post-boundary - * manipulations below zero or above INT_MAX. And if none of the - * flags are set, something has gone very wrong, so report it. - */ - if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) { - bool zero = regs->flags & X86_EFLAGS_ZF; - - refcount_error_report(regs, zero ? "hit zero" : "overflow"); - } else if ((regs->flags & X86_EFLAGS_SF) == 0) { - /* Report if none of OF, ZF, nor SF are set. */ - refcount_error_report(regs, "unexpected saturation"); - } - - return true; -} -EXPORT_SYMBOL(ex_handler_refcount); - -/* * Handler for when we fail to restore a task's FPU state. We should never get * here because the FPU state of a task using the FPU (task->thread.fpu.state) * should always be valid. However, past bugs have allowed userspace to set diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9ceacd1156db..fa4ea09593ab 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -29,6 +29,7 @@ #include <asm/efi.h> /* efi_recover_from_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ #include <asm/cpu_entry_area.h> /* exception stack */ +#include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -197,7 +198,7 @@ void vmalloc_sync_all(void) return; for (address = VMALLOC_START & PMD_MASK; - address >= TASK_SIZE_MAX && address < FIXADDR_TOP; + address >= TASK_SIZE_MAX && address < VMALLOC_END; address += PMD_SIZE) { struct page *page; @@ -1486,27 +1487,6 @@ good_area: } NOKPROBE_SYMBOL(do_user_addr_fault); -/* - * Explicitly marked noinline such that the function tracer sees this as the - * page_fault entry point. - */ -static noinline void -__do_page_fault(struct pt_regs *regs, unsigned long hw_error_code, - unsigned long address) -{ - prefetchw(¤t->mm->mmap_sem); - - if (unlikely(kmmio_fault(regs, address))) - return; - - /* Was the fault on kernel-controlled part of the address space? */ - if (unlikely(fault_in_kernel_space(address))) - do_kern_addr_fault(regs, hw_error_code, address); - else - do_user_addr_fault(regs, hw_error_code, address); -} -NOKPROBE_SYMBOL(__do_page_fault); - static __always_inline void trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code, unsigned long address) @@ -1521,13 +1501,19 @@ trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code, } dotraplinkage void -do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) +do_page_fault(struct pt_regs *regs, unsigned long hw_error_code, + unsigned long address) { - enum ctx_state prev_state; + prefetchw(¤t->mm->mmap_sem); + trace_page_fault_entries(regs, hw_error_code, address); - prev_state = exception_enter(); - trace_page_fault_entries(regs, error_code, address); - __do_page_fault(regs, error_code, address); - exception_exit(prev_state); + if (unlikely(kmmio_fault(regs, address))) + return; + + /* Was the fault on kernel-controlled part of the address space? */ + if (unlikely(fault_in_kernel_space(address))) + do_kern_addr_fault(regs, hw_error_code, address); + else + do_user_addr_fault(regs, hw_error_code, address); } NOKPROBE_SYMBOL(do_page_fault); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index fab095362c50..5bfd5aef5378 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -19,7 +19,6 @@ #include <asm/tlbflush.h> #include <asm/pgalloc.h> #include <asm/elf.h> -#include <asm/mpx.h> #if 0 /* This is just for testing */ struct page * @@ -151,10 +150,6 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (len & ~huge_page_mask(h)) return -EINVAL; - addr = mpx_unmapped_area_check(addr, len, flags); - if (IS_ERR_VALUE(addr)) - return addr; - if (len > TASK_SIZE) return -ENOMEM; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fd10d91a6115..e7bb483557c9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -829,14 +829,13 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end) * used for the kernel image only. free_init_pages() will do the * right thing for either kind of address. */ -void free_kernel_image_pages(void *begin, void *end) +void free_kernel_image_pages(const char *what, void *begin, void *end) { unsigned long begin_ul = (unsigned long)begin; unsigned long end_ul = (unsigned long)end; unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT; - - free_init_pages("unused kernel image", begin_ul, end_ul); + free_init_pages(what, begin_ul, end_ul); /* * PTI maps some of the kernel into userspace. For performance, @@ -865,7 +864,8 @@ void __ref free_initmem(void) mem_encrypt_free_decrypted_mem(); - free_kernel_image_pages(&__init_begin, &__init_end); + free_kernel_image_pages("unused kernel image (initmem)", + &__init_begin, &__init_end); } #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 4068abb9427f..23df4885bbed 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -52,6 +52,7 @@ #include <asm/page_types.h> #include <asm/cpu_entry_area.h> #include <asm/init.h> +#include <asm/pgtable_areas.h> #include "mm_internal.h" @@ -865,43 +866,13 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif int kernel_set_to_readonly __read_mostly; -void set_kernel_text_rw(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long size = PFN_ALIGN(_etext) - start; - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read write\n", - start, start+size); - - set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long size = PFN_ALIGN(_etext) - start; - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read only\n", - start, start+size); - - set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); -} - static void mark_nxdata_nx(void) { /* @@ -916,7 +887,7 @@ static void mark_nxdata_nx(void) if (__supported_pte_mask & _PAGE_NX) printk(KERN_INFO "NX-protecting the kernel data: %luk\n", size >> 10); - set_pages_nx(virt_to_page(start), size >> PAGE_SHIFT); + set_memory_nx(start, size >> PAGE_SHIFT); } void mark_rodata_ro(void) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a6b5c653727b..abbdecb75fad 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1212,10 +1212,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); - struct zone *zone = page_zone(page); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } #endif /* CONFIG_MEMORY_HOTPLUG */ @@ -1260,49 +1258,13 @@ void __init mem_init(void) int kernel_set_to_readonly; -void set_kernel_text_rw(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long end = PFN_ALIGN(__stop___ex_table); - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read write\n", - start, end); - - /* - * Make the kernel identity mapping for text RW. Kernel text - * mapping will always be RO. Refer to the comment in - * static_protections() in pageattr.c - */ - set_memory_rw(start, (end - start) >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long end = PFN_ALIGN(__stop___ex_table); - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read only\n", - start, end); - - /* - * Set the kernel identity mapping for text RO. - */ - set_memory_ro(start, (end - start) >> PAGE_SHIFT); -} - void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long rodata_start = PFN_ALIGN(__start_rodata); - unsigned long end = (unsigned long) &__end_rodata_hpage_align; - unsigned long text_end = PFN_ALIGN(&__stop___ex_table); - unsigned long rodata_end = PFN_ALIGN(&__end_rodata); + unsigned long end = (unsigned long)__end_rodata_hpage_align; + unsigned long text_end = PFN_ALIGN(_etext); + unsigned long rodata_end = PFN_ALIGN(__end_rodata); unsigned long all_end; printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", @@ -1334,8 +1296,10 @@ void mark_rodata_ro(void) set_memory_ro(start, (end-start) >> PAGE_SHIFT); #endif - free_kernel_image_pages((void *)text_end, (void *)rodata_start); - free_kernel_image_pages((void *)rodata_end, (void *)_sdata); + free_kernel_image_pages("unused kernel image (text/rodata gap)", + (void *)text_end, (void *)rodata_start); + free_kernel_image_pages("unused kernel image (rodata/data gap)", + (void *)rodata_end, (void *)_sdata); debug_checkwx(); } diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 6748b4c2baff..f60398aeb644 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -4,7 +4,7 @@ */ #include <asm/iomap.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <linux/export.h> #include <linux/highmem.h> @@ -26,7 +26,7 @@ int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot) if (!is_io_mapping_possible(base, size)) return -EINVAL; - ret = io_reserve_memtype(base, base + size, &pcm); + ret = memtype_reserve_io(base, base + size, &pcm); if (ret) return ret; @@ -40,7 +40,7 @@ EXPORT_SYMBOL_GPL(iomap_create_wc); void iomap_free(resource_size_t base, unsigned long size) { - io_free_memtype(base, base + size); + memtype_free_io(base, base + size); } EXPORT_SYMBOL_GPL(iomap_free); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 63e99f15d7cf..44e4beb4239f 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -19,11 +19,12 @@ #include <asm/set_memory.h> #include <asm/e820/api.h> +#include <asm/efi.h> #include <asm/fixmap.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/pgalloc.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/setup.h> #include "physaddr.h" @@ -195,10 +196,10 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, phys_addr &= PHYSICAL_PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; - retval = reserve_memtype(phys_addr, (u64)phys_addr + size, + retval = memtype_reserve(phys_addr, (u64)phys_addr + size, pcm, &new_pcm); if (retval) { - printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval); + printk(KERN_ERR "ioremap memtype_reserve failed %d\n", retval); return NULL; } @@ -254,7 +255,7 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, area->phys_addr = phys_addr; vaddr = (unsigned long) area->addr; - if (kernel_map_sync_memtype(phys_addr, size, pcm)) + if (memtype_kernel_map_sync(phys_addr, size, pcm)) goto err_free_area; if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) @@ -274,16 +275,16 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, err_free_area: free_vm_area(area); err_free_memtype: - free_memtype(phys_addr, phys_addr + size); + memtype_free(phys_addr, phys_addr + size); return NULL; } /** - * ioremap_nocache - map bus memory into CPU space + * ioremap - map bus memory into CPU space * @phys_addr: bus address of the memory * @size: size of the resource to map * - * ioremap_nocache performs a platform specific sequence of operations to + * ioremap performs a platform specific sequence of operations to * make bus memory CPU accessible via the readb/readw/readl/writeb/ * writew/writel functions and the other mmio helpers. The returned * address is not guaranteed to be usable directly as a virtual @@ -299,7 +300,7 @@ err_free_memtype: * * Must be freed with iounmap. */ -void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) +void __iomem *ioremap(resource_size_t phys_addr, unsigned long size) { /* * Ideally, this should be: @@ -314,7 +315,7 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) return __ioremap_caller(phys_addr, size, pcm, __builtin_return_address(0), false); } -EXPORT_SYMBOL(ioremap_nocache); +EXPORT_SYMBOL(ioremap); /** * ioremap_uc - map bus memory into CPU space as strongly uncachable @@ -450,7 +451,7 @@ void iounmap(volatile void __iomem *addr) return; } - free_memtype(p->phys_addr, p->phys_addr + get_vm_area_size(p)); + memtype_free(p->phys_addr, p->phys_addr + get_vm_area_size(p)); /* Finally remove it */ o = remove_vm_area((void __force *)addr); @@ -625,6 +626,17 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, paddr_next = data->next; len = data->len; + if ((phys_addr > paddr) && (phys_addr < (paddr + len))) { + memunmap(data); + return true; + } + + if (data->type == SETUP_INDIRECT && + ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { + paddr = ((struct setup_indirect *)data->data)->addr; + len = ((struct setup_indirect *)data->data)->len; + } + memunmap(data); if ((phys_addr > paddr) && (phys_addr < (paddr + len))) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 296da58f3013..763e71abc0fe 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -245,22 +245,48 @@ static void __init kasan_map_early_shadow(pgd_t *pgd) } while (pgd++, addr = next, addr != end); } -#ifdef CONFIG_KASAN_INLINE -static int kasan_die_handler(struct notifier_block *self, - unsigned long val, - void *data) +static void __init kasan_shallow_populate_p4ds(pgd_t *pgd, + unsigned long addr, + unsigned long end) { - if (val == DIE_GPF) { - pr_emerg("CONFIG_KASAN_INLINE enabled\n"); - pr_emerg("GPF could be caused by NULL-ptr deref or user memory access\n"); - } - return NOTIFY_OK; + p4d_t *p4d; + unsigned long next; + void *p; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + + if (p4d_none(*p4d)) { + p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true); + p4d_populate(&init_mm, p4d, p); + } + } while (p4d++, addr = next, addr != end); } -static struct notifier_block kasan_die_notifier = { - .notifier_call = kasan_die_handler, -}; -#endif +static void __init kasan_shallow_populate_pgds(void *start, void *end) +{ + unsigned long addr, next; + pgd_t *pgd; + void *p; + + addr = (unsigned long)start; + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, (unsigned long)end); + + if (pgd_none(*pgd)) { + p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true); + pgd_populate(&init_mm, pgd, p); + } + + /* + * we need to populate p4ds to be synced when running in + * four level mode - see sync_global_pgds_l4() + */ + kasan_shallow_populate_p4ds(pgd, addr, next); + } while (pgd++, addr = next, addr != (unsigned long)end); +} void __init kasan_early_init(void) { @@ -298,10 +324,6 @@ void __init kasan_init(void) int i; void *shadow_cpu_entry_begin, *shadow_cpu_entry_end; -#ifdef CONFIG_KASAN_INLINE - register_die_notifier(&kasan_die_notifier); -#endif - memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt)); /* @@ -354,6 +376,24 @@ void __init kasan_init(void) kasan_populate_early_shadow( kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), + kasan_mem_to_shadow((void *)VMALLOC_START)); + + /* + * If we're in full vmalloc mode, don't back vmalloc space with early + * shadow pages. Instead, prepopulate pgds/p4ds so they are synced to + * the global table and we can populate the lower levels on demand. + */ + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) + kasan_shallow_populate_pgds( + kasan_mem_to_shadow((void *)VMALLOC_START), + kasan_mem_to_shadow((void *)VMALLOC_END)); + else + kasan_populate_early_shadow( + kasan_mem_to_shadow((void *)VMALLOC_START), + kasan_mem_to_shadow((void *)VMALLOC_END)); + + kasan_populate_early_shadow( + kasan_mem_to_shadow((void *)VMALLOC_END + 1), shadow_cpu_entry_begin); kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin, diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 79eb55ce69a9..49d7814b59a9 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -193,8 +193,8 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f) int ret; WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n")); if (f->armed) { - pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n", - f->addr, f->count, !!f->old_presence); + pr_warn("double-arm: addr 0x%08lx, ref %d, old %d\n", + f->addr, f->count, !!f->old_presence); } ret = clear_page_presence(f, true); WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"), @@ -341,8 +341,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) * something external causing them (f.e. using a debugger while * mmio tracing enabled), or erroneous behaviour */ - pr_warning("unexpected debug trap on CPU %d.\n", - smp_processor_id()); + pr_warn("unexpected debug trap on CPU %d.\n", smp_processor_id()); goto out; } diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c new file mode 100644 index 000000000000..f5b85bdc0535 --- /dev/null +++ b/arch/x86/mm/maccess.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/uaccess.h> +#include <linux/kernel.h> + +#ifdef CONFIG_X86_64 +static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits) +{ + return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); +} + +static __always_inline bool invalid_probe_range(u64 vaddr) +{ + /* + * Range covering the highest possible canonical userspace address + * as well as non-canonical address range. For the canonical range + * we also need to include the userspace guard page. + */ + return vaddr < TASK_SIZE_MAX + PAGE_SIZE || + canonical_address(vaddr, boot_cpu_data.x86_virt_bits) != vaddr; +} +#else +static __always_inline bool invalid_probe_range(u64 vaddr) +{ + return vaddr < TASK_SIZE_MAX; +} +#endif + +long probe_kernel_read_strict(void *dst, const void *src, size_t size) +{ + if (unlikely(invalid_probe_range((unsigned long)src))) + return -EFAULT; + + return __probe_kernel_read(dst, src, size); +} + +long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, long count) +{ + if (unlikely(invalid_probe_range((unsigned long)unsafe_addr))) + return -EFAULT; + + return __strncpy_from_unsafe(dst, unsafe_addr, count); +} diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index fece30ca8b0c..a03614bd3e1a 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -344,13 +344,11 @@ bool sme_active(void) { return sme_me_mask && !sev_enabled; } -EXPORT_SYMBOL(sme_active); bool sev_active(void) { return sme_me_mask && sev_enabled; } -EXPORT_SYMBOL(sev_active); /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) @@ -369,7 +367,7 @@ bool force_dma_unencrypted(struct device *dev) if (sme_active()) { u64 dma_enc_mask = DMA_BIT_MASK(__ffs64(sme_me_mask)); u64 dma_dev_mask = min_not_zero(dev->coherent_dma_mask, - dev->bus_dma_mask); + dev->bus_dma_limit); if (dma_dev_mask <= dma_enc_mask) return true; diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 6d71481a1e70..106ead05bbe3 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -16,7 +16,7 @@ .text .code64 -ENTRY(sme_encrypt_execute) +SYM_FUNC_START(sme_encrypt_execute) /* * Entry parameters: @@ -66,9 +66,9 @@ ENTRY(sme_encrypt_execute) pop %rbp ret -ENDPROC(sme_encrypt_execute) +SYM_FUNC_END(sme_encrypt_execute) -ENTRY(__enc_copy) +SYM_FUNC_START(__enc_copy) /* * Routine used to encrypt memory in place. * This routine must be run outside of the kernel proper since @@ -153,4 +153,4 @@ ENTRY(__enc_copy) ret .L__enc_copy_end: -ENDPROC(__enc_copy) +SYM_FUNC_END(__enc_copy) diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index aae9a933dfd4..cb91eccc4960 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -163,8 +163,6 @@ unsigned long get_mmap_base(int is_legacy) const char *arch_vma_name(struct vm_area_struct *vma) { - if (vma->vm_flags & VM_MPX) - return "[mpx]"; return NULL; } diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index b8ef8557d4b3..673de6063345 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -394,7 +394,7 @@ static void enter_uniprocessor(void) } out: if (num_online_cpus() > 1) - pr_warning("multiple CPUs still online, may miss events.\n"); + pr_warn("multiple CPUs still online, may miss events.\n"); } static void leave_uniprocessor(void) @@ -418,8 +418,8 @@ static void leave_uniprocessor(void) static void enter_uniprocessor(void) { if (num_online_cpus() > 1) - pr_warning("multiple CPUs are online, may miss events. " - "Suggest booting with maxcpus=1 kernel argument.\n"); + pr_warn("multiple CPUs are online, may miss events. " + "Suggest booting with maxcpus=1 kernel argument.\n"); } static void leave_uniprocessor(void) diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c deleted file mode 100644 index 895fb7a9294d..000000000000 --- a/arch/x86/mm/mpx.c +++ /dev/null @@ -1,938 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * mpx.c - Memory Protection eXtensions - * - * Copyright (c) 2014, Intel Corporation. - * Qiaowei Ren <qiaowei.ren@intel.com> - * Dave Hansen <dave.hansen@intel.com> - */ -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/mm_types.h> -#include <linux/mman.h> -#include <linux/syscalls.h> -#include <linux/sched/sysctl.h> - -#include <asm/insn.h> -#include <asm/insn-eval.h> -#include <asm/mmu_context.h> -#include <asm/mpx.h> -#include <asm/processor.h> -#include <asm/fpu/internal.h> - -#define CREATE_TRACE_POINTS -#include <asm/trace/mpx.h> - -static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm) -{ - if (is_64bit_mm(mm)) - return MPX_BD_SIZE_BYTES_64; - else - return MPX_BD_SIZE_BYTES_32; -} - -static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm) -{ - if (is_64bit_mm(mm)) - return MPX_BT_SIZE_BYTES_64; - else - return MPX_BT_SIZE_BYTES_32; -} - -/* - * This is really a simplified "vm_mmap". it only handles MPX - * bounds tables (the bounds directory is user-allocated). - */ -static unsigned long mpx_mmap(unsigned long len) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, populate; - - /* Only bounds table can be allocated here */ - if (len != mpx_bt_size_bytes(mm)) - return -EINVAL; - - down_write(&mm->mmap_sem); - addr = do_mmap(NULL, 0, len, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate, NULL); - up_write(&mm->mmap_sem); - if (populate) - mm_populate(addr, populate); - - return addr; -} - -static int mpx_insn_decode(struct insn *insn, - struct pt_regs *regs) -{ - unsigned char buf[MAX_INSN_SIZE]; - int x86_64 = !test_thread_flag(TIF_IA32); - int not_copied; - int nr_copied; - - not_copied = copy_from_user(buf, (void __user *)regs->ip, sizeof(buf)); - nr_copied = sizeof(buf) - not_copied; - /* - * The decoder _should_ fail nicely if we pass it a short buffer. - * But, let's not depend on that implementation detail. If we - * did not get anything, just error out now. - */ - if (!nr_copied) - return -EFAULT; - insn_init(insn, buf, nr_copied, x86_64); - insn_get_length(insn); - /* - * copy_from_user() tries to get as many bytes as we could see in - * the largest possible instruction. If the instruction we are - * after is shorter than that _and_ we attempt to copy from - * something unreadable, we might get a short read. This is OK - * as long as the read did not stop in the middle of the - * instruction. Check to see if we got a partial instruction. - */ - if (nr_copied < insn->length) - return -EFAULT; - - insn_get_opcode(insn); - /* - * We only _really_ need to decode bndcl/bndcn/bndcu - * Error out on anything else. - */ - if (insn->opcode.bytes[0] != 0x0f) - goto bad_opcode; - if ((insn->opcode.bytes[1] != 0x1a) && - (insn->opcode.bytes[1] != 0x1b)) - goto bad_opcode; - - return 0; -bad_opcode: - return -EINVAL; -} - -/* - * If a bounds overflow occurs then a #BR is generated. This - * function decodes MPX instructions to get violation address - * and set this address into extended struct siginfo. - * - * Note that this is not a super precise way of doing this. - * Userspace could have, by the time we get here, written - * anything it wants in to the instructions. We can not - * trust anything about it. They might not be valid - * instructions or might encode invalid registers, etc... - */ -int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs) -{ - const struct mpx_bndreg_state *bndregs; - const struct mpx_bndreg *bndreg; - struct insn insn; - uint8_t bndregno; - int err; - - err = mpx_insn_decode(&insn, regs); - if (err) - goto err_out; - - /* - * We know at this point that we are only dealing with - * MPX instructions. - */ - insn_get_modrm(&insn); - bndregno = X86_MODRM_REG(insn.modrm.value); - if (bndregno > 3) { - err = -EINVAL; - goto err_out; - } - /* get bndregs field from current task's xsave area */ - bndregs = get_xsave_field_ptr(XFEATURE_BNDREGS); - if (!bndregs) { - err = -EINVAL; - goto err_out; - } - /* now go select the individual register in the set of 4 */ - bndreg = &bndregs->bndreg[bndregno]; - - /* - * The registers are always 64-bit, but the upper 32 - * bits are ignored in 32-bit mode. Also, note that the - * upper bounds are architecturally represented in 1's - * complement form. - * - * The 'unsigned long' cast is because the compiler - * complains when casting from integers to different-size - * pointers. - */ - info->lower = (void __user *)(unsigned long)bndreg->lower_bound; - info->upper = (void __user *)(unsigned long)~bndreg->upper_bound; - info->addr = insn_get_addr_ref(&insn, regs); - - /* - * We were not able to extract an address from the instruction, - * probably because there was something invalid in it. - */ - if (info->addr == (void __user *)-1) { - err = -EINVAL; - goto err_out; - } - trace_mpx_bounds_register_exception(info->addr, bndreg); - return 0; -err_out: - /* info might be NULL, but kfree() handles that */ - return err; -} - -static __user void *mpx_get_bounds_dir(void) -{ - const struct mpx_bndcsr *bndcsr; - - if (!cpu_feature_enabled(X86_FEATURE_MPX)) - return MPX_INVALID_BOUNDS_DIR; - - /* - * The bounds directory pointer is stored in a register - * only accessible if we first do an xsave. - */ - bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR); - if (!bndcsr) - return MPX_INVALID_BOUNDS_DIR; - - /* - * Make sure the register looks valid by checking the - * enable bit. - */ - if (!(bndcsr->bndcfgu & MPX_BNDCFG_ENABLE_FLAG)) - return MPX_INVALID_BOUNDS_DIR; - - /* - * Lastly, mask off the low bits used for configuration - * flags, and return the address of the bounds table. - */ - return (void __user *)(unsigned long) - (bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK); -} - -int mpx_enable_management(void) -{ - void __user *bd_base = MPX_INVALID_BOUNDS_DIR; - struct mm_struct *mm = current->mm; - int ret = 0; - - /* - * runtime in the userspace will be responsible for allocation of - * the bounds directory. Then, it will save the base of the bounds - * directory into XSAVE/XRSTOR Save Area and enable MPX through - * XRSTOR instruction. - * - * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is - * expected to be relatively expensive. Storing the bounds - * directory here means that we do not have to do xsave in the - * unmap path; we can just use mm->context.bd_addr instead. - */ - bd_base = mpx_get_bounds_dir(); - down_write(&mm->mmap_sem); - - /* MPX doesn't support addresses above 47 bits yet. */ - if (find_vma(mm, DEFAULT_MAP_WINDOW)) { - pr_warn_once("%s (%d): MPX cannot handle addresses " - "above 47-bits. Disabling.", - current->comm, current->pid); - ret = -ENXIO; - goto out; - } - mm->context.bd_addr = bd_base; - if (mm->context.bd_addr == MPX_INVALID_BOUNDS_DIR) - ret = -ENXIO; -out: - up_write(&mm->mmap_sem); - return ret; -} - -int mpx_disable_management(void) -{ - struct mm_struct *mm = current->mm; - - if (!cpu_feature_enabled(X86_FEATURE_MPX)) - return -ENXIO; - - down_write(&mm->mmap_sem); - mm->context.bd_addr = MPX_INVALID_BOUNDS_DIR; - up_write(&mm->mmap_sem); - return 0; -} - -static int mpx_cmpxchg_bd_entry(struct mm_struct *mm, - unsigned long *curval, - unsigned long __user *addr, - unsigned long old_val, unsigned long new_val) -{ - int ret; - /* - * user_atomic_cmpxchg_inatomic() actually uses sizeof() - * the pointer that we pass to it to figure out how much - * data to cmpxchg. We have to be careful here not to - * pass a pointer to a 64-bit data type when we only want - * a 32-bit copy. - */ - if (is_64bit_mm(mm)) { - ret = user_atomic_cmpxchg_inatomic(curval, - addr, old_val, new_val); - } else { - u32 uninitialized_var(curval_32); - u32 old_val_32 = old_val; - u32 new_val_32 = new_val; - u32 __user *addr_32 = (u32 __user *)addr; - - ret = user_atomic_cmpxchg_inatomic(&curval_32, - addr_32, old_val_32, new_val_32); - *curval = curval_32; - } - return ret; -} - -/* - * With 32-bit mode, a bounds directory is 4MB, and the size of each - * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB, - * and the size of each bounds table is 4MB. - */ -static int allocate_bt(struct mm_struct *mm, long __user *bd_entry) -{ - unsigned long expected_old_val = 0; - unsigned long actual_old_val = 0; - unsigned long bt_addr; - unsigned long bd_new_entry; - int ret = 0; - - /* - * Carve the virtual space out of userspace for the new - * bounds table: - */ - bt_addr = mpx_mmap(mpx_bt_size_bytes(mm)); - if (IS_ERR((void *)bt_addr)) - return PTR_ERR((void *)bt_addr); - /* - * Set the valid flag (kinda like _PAGE_PRESENT in a pte) - */ - bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG; - - /* - * Go poke the address of the new bounds table in to the - * bounds directory entry out in userspace memory. Note: - * we may race with another CPU instantiating the same table. - * In that case the cmpxchg will see an unexpected - * 'actual_old_val'. - * - * This can fault, but that's OK because we do not hold - * mmap_sem at this point, unlike some of the other part - * of the MPX code that have to pagefault_disable(). - */ - ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, bd_entry, - expected_old_val, bd_new_entry); - if (ret) - goto out_unmap; - - /* - * The user_atomic_cmpxchg_inatomic() will only return nonzero - * for faults, *not* if the cmpxchg itself fails. Now we must - * verify that the cmpxchg itself completed successfully. - */ - /* - * We expected an empty 'expected_old_val', but instead found - * an apparently valid entry. Assume we raced with another - * thread to instantiate this table and desclare succecss. - */ - if (actual_old_val & MPX_BD_ENTRY_VALID_FLAG) { - ret = 0; - goto out_unmap; - } - /* - * We found a non-empty bd_entry but it did not have the - * VALID_FLAG set. Return an error which will result in - * a SEGV since this probably means that somebody scribbled - * some invalid data in to a bounds table. - */ - if (expected_old_val != actual_old_val) { - ret = -EINVAL; - goto out_unmap; - } - trace_mpx_new_bounds_table(bt_addr); - return 0; -out_unmap: - vm_munmap(bt_addr, mpx_bt_size_bytes(mm)); - return ret; -} - -/* - * When a BNDSTX instruction attempts to save bounds to a bounds - * table, it will first attempt to look up the table in the - * first-level bounds directory. If it does not find a table in - * the directory, a #BR is generated and we get here in order to - * allocate a new table. - * - * With 32-bit mode, the size of BD is 4MB, and the size of each - * bound table is 16KB. With 64-bit mode, the size of BD is 2GB, - * and the size of each bound table is 4MB. - */ -static int do_mpx_bt_fault(void) -{ - unsigned long bd_entry, bd_base; - const struct mpx_bndcsr *bndcsr; - struct mm_struct *mm = current->mm; - - bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR); - if (!bndcsr) - return -EINVAL; - /* - * Mask off the preserve and enable bits - */ - bd_base = bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK; - /* - * The hardware provides the address of the missing or invalid - * entry via BNDSTATUS, so we don't have to go look it up. - */ - bd_entry = bndcsr->bndstatus & MPX_BNDSTA_ADDR_MASK; - /* - * Make sure the directory entry is within where we think - * the directory is. - */ - if ((bd_entry < bd_base) || - (bd_entry >= bd_base + mpx_bd_size_bytes(mm))) - return -EINVAL; - - return allocate_bt(mm, (long __user *)bd_entry); -} - -int mpx_handle_bd_fault(void) -{ - /* - * Userspace never asked us to manage the bounds tables, - * so refuse to help. - */ - if (!kernel_managing_mpx_tables(current->mm)) - return -EINVAL; - - return do_mpx_bt_fault(); -} - -/* - * A thin wrapper around get_user_pages(). Returns 0 if the - * fault was resolved or -errno if not. - */ -static int mpx_resolve_fault(long __user *addr, int write) -{ - long gup_ret; - int nr_pages = 1; - - gup_ret = get_user_pages((unsigned long)addr, nr_pages, - write ? FOLL_WRITE : 0, NULL, NULL); - /* - * get_user_pages() returns number of pages gotten. - * 0 means we failed to fault in and get anything, - * probably because 'addr' is bad. - */ - if (!gup_ret) - return -EFAULT; - /* Other error, return it */ - if (gup_ret < 0) - return gup_ret; - /* must have gup'd a page and gup_ret>0, success */ - return 0; -} - -static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, - unsigned long bd_entry) -{ - unsigned long bt_addr = bd_entry; - int align_to_bytes; - /* - * Bit 0 in a bt_entry is always the valid bit. - */ - bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG; - /* - * Tables are naturally aligned at 8-byte boundaries - * on 64-bit and 4-byte boundaries on 32-bit. The - * documentation makes it appear that the low bits - * are ignored by the hardware, so we do the same. - */ - if (is_64bit_mm(mm)) - align_to_bytes = 8; - else - align_to_bytes = 4; - bt_addr &= ~(align_to_bytes-1); - return bt_addr; -} - -/* - * We only want to do a 4-byte get_user() on 32-bit. Otherwise, - * we might run off the end of the bounds table if we are on - * a 64-bit kernel and try to get 8 bytes. - */ -static int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret, - long __user *bd_entry_ptr) -{ - u32 bd_entry_32; - int ret; - - if (is_64bit_mm(mm)) - return get_user(*bd_entry_ret, bd_entry_ptr); - - /* - * Note that get_user() uses the type of the *pointer* to - * establish the size of the get, not the destination. - */ - ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr); - *bd_entry_ret = bd_entry_32; - return ret; -} - -/* - * Get the base of bounds tables pointed by specific bounds - * directory entry. - */ -static int get_bt_addr(struct mm_struct *mm, - long __user *bd_entry_ptr, - unsigned long *bt_addr_result) -{ - int ret; - int valid_bit; - unsigned long bd_entry; - unsigned long bt_addr; - - if (!access_ok((bd_entry_ptr), sizeof(*bd_entry_ptr))) - return -EFAULT; - - while (1) { - int need_write = 0; - - pagefault_disable(); - ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr); - pagefault_enable(); - if (!ret) - break; - if (ret == -EFAULT) - ret = mpx_resolve_fault(bd_entry_ptr, need_write); - /* - * If we could not resolve the fault, consider it - * userspace's fault and error out. - */ - if (ret) - return ret; - } - - valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG; - bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry); - - /* - * When the kernel is managing bounds tables, a bounds directory - * entry will either have a valid address (plus the valid bit) - * *OR* be completely empty. If we see a !valid entry *and* some - * data in the address field, we know something is wrong. This - * -EINVAL return will cause a SIGSEGV. - */ - if (!valid_bit && bt_addr) - return -EINVAL; - /* - * Do we have an completely zeroed bt entry? That is OK. It - * just means there was no bounds table for this memory. Make - * sure to distinguish this from -EINVAL, which will cause - * a SEGV. - */ - if (!valid_bit) - return -ENOENT; - - *bt_addr_result = bt_addr; - return 0; -} - -static inline int bt_entry_size_bytes(struct mm_struct *mm) -{ - if (is_64bit_mm(mm)) - return MPX_BT_ENTRY_BYTES_64; - else - return MPX_BT_ENTRY_BYTES_32; -} - -/* - * Take a virtual address and turns it in to the offset in bytes - * inside of the bounds table where the bounds table entry - * controlling 'addr' can be found. - */ -static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm, - unsigned long addr) -{ - unsigned long bt_table_nr_entries; - unsigned long offset = addr; - - if (is_64bit_mm(mm)) { - /* Bottom 3 bits are ignored on 64-bit */ - offset >>= 3; - bt_table_nr_entries = MPX_BT_NR_ENTRIES_64; - } else { - /* Bottom 2 bits are ignored on 32-bit */ - offset >>= 2; - bt_table_nr_entries = MPX_BT_NR_ENTRIES_32; - } - /* - * We know the size of the table in to which we are - * indexing, and we have eliminated all the low bits - * which are ignored for indexing. - * - * Mask out all the high bits which we do not need - * to index in to the table. Note that the tables - * are always powers of two so this gives us a proper - * mask. - */ - offset &= (bt_table_nr_entries-1); - /* - * We now have an entry offset in terms of *entries* in - * the table. We need to scale it back up to bytes. - */ - offset *= bt_entry_size_bytes(mm); - return offset; -} - -/* - * How much virtual address space does a single bounds - * directory entry cover? - * - * Note, we need a long long because 4GB doesn't fit in - * to a long on 32-bit. - */ -static inline unsigned long bd_entry_virt_space(struct mm_struct *mm) -{ - unsigned long long virt_space; - unsigned long long GB = (1ULL << 30); - - /* - * This covers 32-bit emulation as well as 32-bit kernels - * running on 64-bit hardware. - */ - if (!is_64bit_mm(mm)) - return (4ULL * GB) / MPX_BD_NR_ENTRIES_32; - - /* - * 'x86_virt_bits' returns what the hardware is capable - * of, and returns the full >32-bit address space when - * running 32-bit kernels on 64-bit hardware. - */ - virt_space = (1ULL << boot_cpu_data.x86_virt_bits); - return virt_space / MPX_BD_NR_ENTRIES_64; -} - -/* - * Free the backing physical pages of bounds table 'bt_addr'. - * Assume start...end is within that bounds table. - */ -static noinline int zap_bt_entries_mapping(struct mm_struct *mm, - unsigned long bt_addr, - unsigned long start_mapping, unsigned long end_mapping) -{ - struct vm_area_struct *vma; - unsigned long addr, len; - unsigned long start; - unsigned long end; - - /* - * if we 'end' on a boundary, the offset will be 0 which - * is not what we want. Back it up a byte to get the - * last bt entry. Then once we have the entry itself, - * move 'end' back up by the table entry size. - */ - start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping); - end = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1); - /* - * Move end back up by one entry. Among other things - * this ensures that it remains page-aligned and does - * not screw up zap_page_range() - */ - end += bt_entry_size_bytes(mm); - - /* - * Find the first overlapping vma. If vma->vm_start > start, there - * will be a hole in the bounds table. This -EINVAL return will - * cause a SIGSEGV. - */ - vma = find_vma(mm, start); - if (!vma || vma->vm_start > start) - return -EINVAL; - - /* - * A NUMA policy on a VM_MPX VMA could cause this bounds table to - * be split. So we need to look across the entire 'start -> end' - * range of this bounds table, find all of the VM_MPX VMAs, and - * zap only those. - */ - addr = start; - while (vma && vma->vm_start < end) { - /* - * We followed a bounds directory entry down - * here. If we find a non-MPX VMA, that's bad, - * so stop immediately and return an error. This - * probably results in a SIGSEGV. - */ - if (!(vma->vm_flags & VM_MPX)) - return -EINVAL; - - len = min(vma->vm_end, end) - addr; - zap_page_range(vma, addr, len); - trace_mpx_unmap_zap(addr, addr+len); - - vma = vma->vm_next; - addr = vma->vm_start; - } - return 0; -} - -static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm, - unsigned long addr) -{ - /* - * There are several ways to derive the bd offsets. We - * use the following approach here: - * 1. We know the size of the virtual address space - * 2. We know the number of entries in a bounds table - * 3. We know that each entry covers a fixed amount of - * virtual address space. - * So, we can just divide the virtual address by the - * virtual space used by one entry to determine which - * entry "controls" the given virtual address. - */ - if (is_64bit_mm(mm)) { - int bd_entry_size = 8; /* 64-bit pointer */ - /* - * Take the 64-bit addressing hole in to account. - */ - addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1); - return (addr / bd_entry_virt_space(mm)) * bd_entry_size; - } else { - int bd_entry_size = 4; /* 32-bit pointer */ - /* - * 32-bit has no hole so this case needs no mask - */ - return (addr / bd_entry_virt_space(mm)) * bd_entry_size; - } - /* - * The two return calls above are exact copies. If we - * pull out a single copy and put it in here, gcc won't - * realize that we're doing a power-of-2 divide and use - * shifts. It uses a real divide. If we put them up - * there, it manages to figure it out (gcc 4.8.3). - */ -} - -static int unmap_entire_bt(struct mm_struct *mm, - long __user *bd_entry, unsigned long bt_addr) -{ - unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG; - unsigned long uninitialized_var(actual_old_val); - int ret; - - while (1) { - int need_write = 1; - unsigned long cleared_bd_entry = 0; - - pagefault_disable(); - ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, - bd_entry, expected_old_val, cleared_bd_entry); - pagefault_enable(); - if (!ret) - break; - if (ret == -EFAULT) - ret = mpx_resolve_fault(bd_entry, need_write); - /* - * If we could not resolve the fault, consider it - * userspace's fault and error out. - */ - if (ret) - return ret; - } - /* - * The cmpxchg was performed, check the results. - */ - if (actual_old_val != expected_old_val) { - /* - * Someone else raced with us to unmap the table. - * That is OK, since we were both trying to do - * the same thing. Declare success. - */ - if (!actual_old_val) - return 0; - /* - * Something messed with the bounds directory - * entry. We hold mmap_sem for read or write - * here, so it could not be a _new_ bounds table - * that someone just allocated. Something is - * wrong, so pass up the error and SIGSEGV. - */ - return -EINVAL; - } - /* - * Note, we are likely being called under do_munmap() already. To - * avoid recursion, do_munmap() will check whether it comes - * from one bounds table through VM_MPX flag. - */ - return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm), NULL); -} - -static int try_unmap_single_bt(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - struct vm_area_struct *next; - struct vm_area_struct *prev; - /* - * "bta" == Bounds Table Area: the area controlled by the - * bounds table that we are unmapping. - */ - unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1); - unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm); - unsigned long uninitialized_var(bt_addr); - void __user *bde_vaddr; - int ret; - /* - * We already unlinked the VMAs from the mm's rbtree so 'start' - * is guaranteed to be in a hole. This gets us the first VMA - * before the hole in to 'prev' and the next VMA after the hole - * in to 'next'. - */ - next = find_vma_prev(mm, start, &prev); - /* - * Do not count other MPX bounds table VMAs as neighbors. - * Although theoretically possible, we do not allow bounds - * tables for bounds tables so our heads do not explode. - * If we count them as neighbors here, we may end up with - * lots of tables even though we have no actual table - * entries in use. - */ - while (next && (next->vm_flags & VM_MPX)) - next = next->vm_next; - while (prev && (prev->vm_flags & VM_MPX)) - prev = prev->vm_prev; - /* - * We know 'start' and 'end' lie within an area controlled - * by a single bounds table. See if there are any other - * VMAs controlled by that bounds table. If there are not - * then we can "expand" the are we are unmapping to possibly - * cover the entire table. - */ - next = find_vma_prev(mm, start, &prev); - if ((!prev || prev->vm_end <= bta_start_vaddr) && - (!next || next->vm_start >= bta_end_vaddr)) { - /* - * No neighbor VMAs controlled by same bounds - * table. Try to unmap the whole thing - */ - start = bta_start_vaddr; - end = bta_end_vaddr; - } - - bde_vaddr = mm->context.bd_addr + mpx_get_bd_entry_offset(mm, start); - ret = get_bt_addr(mm, bde_vaddr, &bt_addr); - /* - * No bounds table there, so nothing to unmap. - */ - if (ret == -ENOENT) { - ret = 0; - return 0; - } - if (ret) - return ret; - /* - * We are unmapping an entire table. Either because the - * unmap that started this whole process was large enough - * to cover an entire table, or that the unmap was small - * but was the area covered by a bounds table. - */ - if ((start == bta_start_vaddr) && - (end == bta_end_vaddr)) - return unmap_entire_bt(mm, bde_vaddr, bt_addr); - return zap_bt_entries_mapping(mm, bt_addr, start, end); -} - -static int mpx_unmap_tables(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - unsigned long one_unmap_start; - trace_mpx_unmap_search(start, end); - - one_unmap_start = start; - while (one_unmap_start < end) { - int ret; - unsigned long next_unmap_start = ALIGN(one_unmap_start+1, - bd_entry_virt_space(mm)); - unsigned long one_unmap_end = end; - /* - * if the end is beyond the current bounds table, - * move it back so we only deal with a single one - * at a time - */ - if (one_unmap_end > next_unmap_start) - one_unmap_end = next_unmap_start; - ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end); - if (ret) - return ret; - - one_unmap_start = next_unmap_start; - } - return 0; -} - -/* - * Free unused bounds tables covered in a virtual address region being - * munmap()ed. Assume end > start. - * - * This function will be called by do_munmap(), and the VMAs covering - * the virtual address region start...end have already been split if - * necessary, and the 'vma' is the first vma in this range (start -> end). - */ -void mpx_notify_unmap(struct mm_struct *mm, unsigned long start, - unsigned long end) -{ - struct vm_area_struct *vma; - int ret; - - /* - * Refuse to do anything unless userspace has asked - * the kernel to help manage the bounds tables, - */ - if (!kernel_managing_mpx_tables(current->mm)) - return; - /* - * This will look across the entire 'start -> end' range, - * and find all of the non-VM_MPX VMAs. - * - * To avoid recursion, if a VM_MPX vma is found in the range - * (start->end), we will not continue follow-up work. This - * recursion represents having bounds tables for bounds tables, - * which should not occur normally. Being strict about it here - * helps ensure that we do not have an exploitable stack overflow. - */ - vma = find_vma(mm, start); - while (vma && vma->vm_start < end) { - if (vma->vm_flags & VM_MPX) - return; - vma = vma->vm_next; - } - - ret = mpx_unmap_tables(mm, start, end); - if (ret) - force_sig(SIGSEGV); -} - -/* MPX cannot handle addresses above 47 bits yet. */ -unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, - unsigned long flags) -{ - if (!kernel_managing_mpx_tables(current->mm)) - return addr; - if (addr + len <= DEFAULT_MAP_WINDOW) - return addr; - if (flags & MAP_FIXED) - return -ENOMEM; - - /* - * Requested len is larger than the whole area we're allowed to map in. - * Resetting hinting address wouldn't do much good -- fail early. - */ - if (len > DEFAULT_MAP_WINDOW) - return -ENOMEM; - - /* Look for unmap area within DEFAULT_MAP_WINDOW */ - return 0; -} diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index e6dad600614c..99f7a68738f0 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -699,7 +699,7 @@ static int __init dummy_numa_init(void) * x86_numa_init - Initialize NUMA * * Try each configured NUMA initialization method until one succeeds. The - * last fallback is dummy single node config encomapssing whole memory and + * last fallback is dummy single node config encompassing whole memory and * never fails. */ void __init x86_numa_init(void) @@ -861,9 +861,9 @@ void numa_remove_cpu(int cpu) */ const struct cpumask *cpumask_of_node(int node) { - if (node >= nr_node_ids) { + if ((unsigned)node >= nr_node_ids) { printk(KERN_WARNING - "cpumask_of_node(%d): node > nr_node_ids(%u)\n", + "cpumask_of_node(%d): (unsigned)node >= nr_node_ids(%u)\n", node, nr_node_ids); dump_stack(); return cpu_none_mask; diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index abffa0be80da..7f1d2034df1e 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -438,7 +438,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) goto no_emu; if (numa_cleanup_meminfo(&ei) < 0) { - pr_warning("NUMA: Warning: constructed meminfo invalid, disabling emulation\n"); + pr_warn("NUMA: Warning: constructed meminfo invalid, disabling emulation\n"); goto no_emu; } @@ -449,7 +449,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), phys_size, PAGE_SIZE); if (!phys) { - pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); + pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); goto no_emu; } memblock_reserve(phys, phys_size); diff --git a/arch/x86/mm/pat/Makefile b/arch/x86/mm/pat/Makefile new file mode 100644 index 000000000000..ea464c995161 --- /dev/null +++ b/arch/x86/mm/pat/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y := set_memory.o memtype.o + +obj-$(CONFIG_X86_PAT) += memtype_interval.o diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pat/cpa-test.c index facce271e8b9..facce271e8b9 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pat/cpa-test.c diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat/memtype.c index d9fbd4f69920..394be8611748 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat/memtype.c @@ -1,11 +1,34 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Handle caching attributes in page tables (PAT) + * Page Attribute Table (PAT) support: handle memory caching attributes in page tables. * * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> * Suresh B Siddha <suresh.b.siddha@intel.com> * * Loosely based on earlier PAT patchset from Eric Biederman and Andi Kleen. + * + * Basic principles: + * + * PAT is a CPU feature supported by all modern x86 CPUs, to allow the firmware and + * the kernel to set one of a handful of 'caching type' attributes for physical + * memory ranges: uncached, write-combining, write-through, write-protected, + * and the most commonly used and default attribute: write-back caching. + * + * PAT support supercedes and augments MTRR support in a compatible fashion: MTRR is + * a hardware interface to enumerate a limited number of physical memory ranges + * and set their caching attributes explicitly, programmed into the CPU via MSRs. + * Even modern CPUs have MTRRs enabled - but these are typically not touched + * by the kernel or by user-space (such as the X server), we rely on PAT for any + * additional cache attribute logic. + * + * PAT doesn't work via explicit memory ranges, but uses page table entries to add + * cache attribute information to the mapped memory range: there's 3 bits used, + * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT), with the 8 possible values mapped by the + * CPU to actual cache attributes via an MSR loaded into the CPU (MSR_IA32_CR_PAT). + * + * ( There's a metric ton of finer details, such as compatibility with CPU quirks + * that only support 4 types of PAT entries, and interaction with MTRRs, see + * below for details. ) */ #include <linux/seq_file.h> @@ -29,44 +52,48 @@ #include <asm/mtrr.h> #include <asm/page.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/io.h> -#include "pat_internal.h" -#include "mm_internal.h" +#include "memtype.h" +#include "../mm_internal.h" #undef pr_fmt #define pr_fmt(fmt) "" fmt -static bool __read_mostly boot_cpu_done; +static bool __read_mostly pat_bp_initialized; static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT); -static bool __read_mostly pat_initialized; -static bool __read_mostly init_cm_done; +static bool __read_mostly pat_bp_enabled; +static bool __read_mostly pat_cm_initialized; -void pat_disable(const char *reason) +/* + * PAT support is enabled by default, but can be disabled for + * various user-requested or hardware-forced reasons: + */ +void pat_disable(const char *msg_reason) { if (pat_disabled) return; - if (boot_cpu_done) { + if (pat_bp_initialized) { WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n"); return; } pat_disabled = true; - pr_info("x86/PAT: %s\n", reason); + pr_info("x86/PAT: %s\n", msg_reason); } static int __init nopat(char *str) { - pat_disable("PAT support disabled."); + pat_disable("PAT support disabled via boot option."); return 0; } early_param("nopat", nopat); bool pat_enabled(void) { - return pat_initialized; + return pat_bp_enabled; } EXPORT_SYMBOL_GPL(pat_enabled); @@ -197,6 +224,8 @@ static void __init_cache_modes(u64 pat) char pat_msg[33]; int i; + WARN_ON_ONCE(pat_cm_initialized); + pat_msg[32] = 0; for (i = 7; i >= 0; i--) { cache = pat_get_cache_mode((pat >> (i * 8)) & 7, @@ -205,28 +234,28 @@ static void __init_cache_modes(u64 pat) } pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg); - init_cm_done = true; + pat_cm_initialized = true; } #define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) -static void pat_bsp_init(u64 pat) +static void pat_bp_init(u64 pat) { u64 tmp_pat; if (!boot_cpu_has(X86_FEATURE_PAT)) { - pat_disable("PAT not supported by CPU."); + pat_disable("PAT not supported by the CPU."); return; } rdmsrl(MSR_IA32_CR_PAT, tmp_pat); if (!tmp_pat) { - pat_disable("PAT MSR is 0, disabled."); + pat_disable("PAT support disabled by the firmware."); return; } wrmsrl(MSR_IA32_CR_PAT, pat); - pat_initialized = true; + pat_bp_enabled = true; __init_cache_modes(pat); } @@ -248,7 +277,7 @@ void init_cache_modes(void) { u64 pat = 0; - if (init_cm_done) + if (pat_cm_initialized) return; if (boot_cpu_has(X86_FEATURE_PAT)) { @@ -291,7 +320,7 @@ void init_cache_modes(void) } /** - * pat_init - Initialize PAT MSR and PAT table + * pat_init - Initialize the PAT MSR and PAT table on the current CPU * * This function initializes PAT MSR and PAT table with an OS-defined value * to enable additional cache attributes, WC, WT and WP. @@ -305,6 +334,10 @@ void pat_init(void) u64 pat; struct cpuinfo_x86 *c = &boot_cpu_data; +#ifndef CONFIG_X86_PAT + pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n"); +#endif + if (pat_disabled) return; @@ -364,9 +397,9 @@ void pat_init(void) PAT(4, WB) | PAT(5, WP) | PAT(6, UC_MINUS) | PAT(7, WT); } - if (!boot_cpu_done) { - pat_bsp_init(pat); - boot_cpu_done = true; + if (!pat_bp_initialized) { + pat_bp_init(pat); + pat_bp_initialized = true; } else { pat_ap_init(pat); } @@ -542,10 +575,10 @@ static u64 sanitize_phys(u64 address) * available type in new_type in case of no error. In case of any error * it will return a negative return value. */ -int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, +int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_type, enum page_cache_mode *new_type) { - struct memtype *new; + struct memtype *entry_new; enum page_cache_mode actual_type; int is_range_ram; int err = 0; @@ -593,22 +626,22 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, return -EINVAL; } - new = kzalloc(sizeof(struct memtype), GFP_KERNEL); - if (!new) + entry_new = kzalloc(sizeof(struct memtype), GFP_KERNEL); + if (!entry_new) return -ENOMEM; - new->start = start; - new->end = end; - new->type = actual_type; + entry_new->start = start; + entry_new->end = end; + entry_new->type = actual_type; spin_lock(&memtype_lock); - err = rbt_memtype_check_insert(new, new_type); + err = memtype_check_insert(entry_new, new_type); if (err) { - pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n", + pr_info("x86/PAT: memtype_reserve failed [mem %#010Lx-%#010Lx], track %s, req %s\n", start, end - 1, - cattr_name(new->type), cattr_name(req_type)); - kfree(new); + cattr_name(entry_new->type), cattr_name(req_type)); + kfree(entry_new); spin_unlock(&memtype_lock); return err; @@ -616,18 +649,17 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, spin_unlock(&memtype_lock); - dprintk("reserve_memtype added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n", - start, end - 1, cattr_name(new->type), cattr_name(req_type), + dprintk("memtype_reserve added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n", + start, end - 1, cattr_name(entry_new->type), cattr_name(req_type), new_type ? cattr_name(*new_type) : "-"); return err; } -int free_memtype(u64 start, u64 end) +int memtype_free(u64 start, u64 end) { - int err = -EINVAL; int is_range_ram; - struct memtype *entry; + struct memtype *entry_old; if (!pat_enabled()) return 0; @@ -640,28 +672,24 @@ int free_memtype(u64 start, u64 end) return 0; is_range_ram = pat_pagerange_is_ram(start, end); - if (is_range_ram == 1) { - - err = free_ram_pages_type(start, end); - - return err; - } else if (is_range_ram < 0) { + if (is_range_ram == 1) + return free_ram_pages_type(start, end); + if (is_range_ram < 0) return -EINVAL; - } spin_lock(&memtype_lock); - entry = rbt_memtype_erase(start, end); + entry_old = memtype_erase(start, end); spin_unlock(&memtype_lock); - if (IS_ERR(entry)) { + if (IS_ERR(entry_old)) { pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, start, end - 1); return -EINVAL; } - kfree(entry); + kfree(entry_old); - dprintk("free_memtype request [mem %#010Lx-%#010Lx]\n", start, end - 1); + dprintk("memtype_free request [mem %#010Lx-%#010Lx]\n", start, end - 1); return 0; } @@ -693,13 +721,14 @@ static enum page_cache_mode lookup_memtype(u64 paddr) spin_lock(&memtype_lock); - entry = rbt_memtype_lookup(paddr); + entry = memtype_lookup(paddr); if (entry != NULL) rettype = entry->type; else rettype = _PAGE_CACHE_MODE_UC_MINUS; spin_unlock(&memtype_lock); + return rettype; } @@ -723,7 +752,7 @@ bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn) EXPORT_SYMBOL_GPL(pat_pfn_immune_to_uc_mtrr); /** - * io_reserve_memtype - Request a memory type mapping for a region of memory + * memtype_reserve_io - Request a memory type mapping for a region of memory * @start: start (physical address) of the region * @end: end (physical address) of the region * @type: A pointer to memtype, with requested type. On success, requested @@ -732,7 +761,7 @@ EXPORT_SYMBOL_GPL(pat_pfn_immune_to_uc_mtrr); * On success, returns 0 * On failure, returns non-zero */ -int io_reserve_memtype(resource_size_t start, resource_size_t end, +int memtype_reserve_io(resource_size_t start, resource_size_t end, enum page_cache_mode *type) { resource_size_t size = end - start; @@ -742,47 +771,47 @@ int io_reserve_memtype(resource_size_t start, resource_size_t end, WARN_ON_ONCE(iomem_map_sanity_check(start, size)); - ret = reserve_memtype(start, end, req_type, &new_type); + ret = memtype_reserve(start, end, req_type, &new_type); if (ret) goto out_err; if (!is_new_memtype_allowed(start, size, req_type, new_type)) goto out_free; - if (kernel_map_sync_memtype(start, size, new_type) < 0) + if (memtype_kernel_map_sync(start, size, new_type) < 0) goto out_free; *type = new_type; return 0; out_free: - free_memtype(start, end); + memtype_free(start, end); ret = -EBUSY; out_err: return ret; } /** - * io_free_memtype - Release a memory type mapping for a region of memory + * memtype_free_io - Release a memory type mapping for a region of memory * @start: start (physical address) of the region * @end: end (physical address) of the region */ -void io_free_memtype(resource_size_t start, resource_size_t end) +void memtype_free_io(resource_size_t start, resource_size_t end) { - free_memtype(start, end); + memtype_free(start, end); } int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size) { enum page_cache_mode type = _PAGE_CACHE_MODE_WC; - return io_reserve_memtype(start, start + size, &type); + return memtype_reserve_io(start, start + size, &type); } EXPORT_SYMBOL(arch_io_reserve_memtype_wc); void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size) { - io_free_memtype(start, start + size); + memtype_free_io(start, start + size); } EXPORT_SYMBOL(arch_io_free_memtype_wc); @@ -839,10 +868,10 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, } /* - * Change the memory type for the physial address range in kernel identity + * Change the memory type for the physical address range in kernel identity * mapping space if that range is a part of identity map. */ -int kernel_map_sync_memtype(u64 base, unsigned long size, +int memtype_kernel_map_sync(u64 base, unsigned long size, enum page_cache_mode pcm) { unsigned long id_sz; @@ -851,15 +880,14 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, return 0; /* - * some areas in the middle of the kernel identity range - * are not mapped, like the PCI space. + * Some areas in the middle of the kernel identity range + * are not mapped, for example the PCI space. */ if (!page_is_ram(base >> PAGE_SHIFT)) return 0; id_sz = (__pa(high_memory-1) <= base + size) ? - __pa(high_memory) - base : - size; + __pa(high_memory) - base : size; if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) { pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n", @@ -873,7 +901,7 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, /* * Internal interface to reserve a range of physical memory with prot. - * Reserved non RAM regions only and after successful reserve_memtype, + * Reserved non RAM regions only and after successful memtype_reserve, * this func also keeps identity mapping (if any) in sync with this new prot. */ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, @@ -910,14 +938,14 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, return 0; } - ret = reserve_memtype(paddr, paddr + size, want_pcm, &pcm); + ret = memtype_reserve(paddr, paddr + size, want_pcm, &pcm); if (ret) return ret; if (pcm != want_pcm) { if (strict_prot || !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) { - free_memtype(paddr, paddr + size); + memtype_free(paddr, paddr + size); pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n", current->comm, current->pid, cattr_name(want_pcm), @@ -935,8 +963,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, cachemode2protval(pcm)); } - if (kernel_map_sync_memtype(paddr, size, pcm) < 0) { - free_memtype(paddr, paddr + size); + if (memtype_kernel_map_sync(paddr, size, pcm) < 0) { + memtype_free(paddr, paddr + size); return -EINVAL; } return 0; @@ -952,7 +980,7 @@ static void free_pfn_range(u64 paddr, unsigned long size) is_ram = pat_pagerange_is_ram(paddr, paddr + size); if (is_ram == 0) - free_memtype(paddr, paddr + size); + memtype_free(paddr, paddr + size); } /* @@ -1099,25 +1127,30 @@ EXPORT_SYMBOL_GPL(pgprot_writethrough); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT) +/* + * We are allocating a temporary printout-entry to be passed + * between seq_start()/next() and seq_show(): + */ static struct memtype *memtype_get_idx(loff_t pos) { - struct memtype *print_entry; + struct memtype *entry_print; int ret; - print_entry = kzalloc(sizeof(struct memtype), GFP_KERNEL); - if (!print_entry) + entry_print = kzalloc(sizeof(struct memtype), GFP_KERNEL); + if (!entry_print) return NULL; spin_lock(&memtype_lock); - ret = rbt_memtype_copy_nth_element(print_entry, pos); + ret = memtype_copy_nth_element(entry_print, pos); spin_unlock(&memtype_lock); - if (!ret) { - return print_entry; - } else { - kfree(print_entry); + /* Free it on error: */ + if (ret) { + kfree(entry_print); return NULL; } + + return entry_print; } static void *memtype_seq_start(struct seq_file *seq, loff_t *pos) @@ -1142,11 +1175,14 @@ static void memtype_seq_stop(struct seq_file *seq, void *v) static int memtype_seq_show(struct seq_file *seq, void *v) { - struct memtype *print_entry = (struct memtype *)v; + struct memtype *entry_print = (struct memtype *)v; + + seq_printf(seq, "PAT: [mem 0x%016Lx-0x%016Lx] %s\n", + entry_print->start, + entry_print->end, + cattr_name(entry_print->type)); - seq_printf(seq, "%s @ 0x%Lx-0x%Lx\n", cattr_name(print_entry->type), - print_entry->start, print_entry->end); - kfree(print_entry); + kfree(entry_print); return 0; } @@ -1178,7 +1214,6 @@ static int __init pat_memtype_list_init(void) } return 0; } - late_initcall(pat_memtype_list_init); #endif /* CONFIG_DEBUG_FS && CONFIG_X86_PAT */ diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat/memtype.h index eeb5caeb089b..cacecdbceb55 100644 --- a/arch/x86/mm/pat_internal.h +++ b/arch/x86/mm/pat/memtype.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PAT_INTERNAL_H_ -#define __PAT_INTERNAL_H_ +#ifndef __MEMTYPE_H_ +#define __MEMTYPE_H_ extern int pat_debug_enable; @@ -29,21 +29,21 @@ static inline char *cattr_name(enum page_cache_mode pcm) } #ifdef CONFIG_X86_PAT -extern int rbt_memtype_check_insert(struct memtype *new, - enum page_cache_mode *new_type); -extern struct memtype *rbt_memtype_erase(u64 start, u64 end); -extern struct memtype *rbt_memtype_lookup(u64 addr); -extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos); +extern int memtype_check_insert(struct memtype *entry_new, + enum page_cache_mode *new_type); +extern struct memtype *memtype_erase(u64 start, u64 end); +extern struct memtype *memtype_lookup(u64 addr); +extern int memtype_copy_nth_element(struct memtype *entry_out, loff_t pos); #else -static inline int rbt_memtype_check_insert(struct memtype *new, - enum page_cache_mode *new_type) +static inline int memtype_check_insert(struct memtype *entry_new, + enum page_cache_mode *new_type) { return 0; } -static inline struct memtype *rbt_memtype_erase(u64 start, u64 end) +static inline struct memtype *memtype_erase(u64 start, u64 end) { return NULL; } -static inline struct memtype *rbt_memtype_lookup(u64 addr) +static inline struct memtype *memtype_lookup(u64 addr) { return NULL; } -static inline int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos) +static inline int memtype_copy_nth_element(struct memtype *out, loff_t pos) { return 0; } #endif -#endif /* __PAT_INTERNAL_H_ */ +#endif /* __MEMTYPE_H_ */ diff --git a/arch/x86/mm/pat/memtype_interval.c b/arch/x86/mm/pat/memtype_interval.c new file mode 100644 index 000000000000..a07e4882bf36 --- /dev/null +++ b/arch/x86/mm/pat/memtype_interval.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Handle caching attributes in page tables (PAT) + * + * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Suresh B Siddha <suresh.b.siddha@intel.com> + * + * Interval tree used to store the PAT memory type reservations. + */ + +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/kernel.h> +#include <linux/interval_tree_generic.h> +#include <linux/sched.h> +#include <linux/gfp.h> + +#include <asm/pgtable.h> +#include <asm/memtype.h> + +#include "memtype.h" + +/* + * The memtype tree keeps track of memory type for specific + * physical memory areas. Without proper tracking, conflicting memory + * types in different mappings can cause CPU cache corruption. + * + * The tree is an interval tree (augmented rbtree) which tree is ordered + * by the starting address. The tree can contain multiple entries for + * different regions which overlap. All the aliases have the same + * cache attributes of course, as enforced by the PAT logic. + * + * memtype_lock protects the rbtree. + */ + +static inline u64 interval_start(struct memtype *entry) +{ + return entry->start; +} + +static inline u64 interval_end(struct memtype *entry) +{ + return entry->end - 1; +} + +INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end, + interval_start, interval_end, + static, interval) + +static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED; + +enum { + MEMTYPE_EXACT_MATCH = 0, + MEMTYPE_END_MATCH = 1 +}; + +static struct memtype *memtype_match(u64 start, u64 end, int match_type) +{ + struct memtype *entry_match; + + entry_match = interval_iter_first(&memtype_rbroot, start, end-1); + + while (entry_match != NULL && entry_match->start < end) { + if ((match_type == MEMTYPE_EXACT_MATCH) && + (entry_match->start == start) && (entry_match->end == end)) + return entry_match; + + if ((match_type == MEMTYPE_END_MATCH) && + (entry_match->start < start) && (entry_match->end == end)) + return entry_match; + + entry_match = interval_iter_next(entry_match, start, end-1); + } + + return NULL; /* Returns NULL if there is no match */ +} + +static int memtype_check_conflict(u64 start, u64 end, + enum page_cache_mode reqtype, + enum page_cache_mode *newtype) +{ + struct memtype *entry_match; + enum page_cache_mode found_type = reqtype; + + entry_match = interval_iter_first(&memtype_rbroot, start, end-1); + if (entry_match == NULL) + goto success; + + if (entry_match->type != found_type && newtype == NULL) + goto failure; + + dprintk("Overlap at 0x%Lx-0x%Lx\n", entry_match->start, entry_match->end); + found_type = entry_match->type; + + entry_match = interval_iter_next(entry_match, start, end-1); + while (entry_match) { + if (entry_match->type != found_type) + goto failure; + + entry_match = interval_iter_next(entry_match, start, end-1); + } +success: + if (newtype) + *newtype = found_type; + + return 0; + +failure: + pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n", + current->comm, current->pid, start, end, + cattr_name(found_type), cattr_name(entry_match->type)); + + return -EBUSY; +} + +int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *ret_type) +{ + int err = 0; + + err = memtype_check_conflict(entry_new->start, entry_new->end, entry_new->type, ret_type); + if (err) + return err; + + if (ret_type) + entry_new->type = *ret_type; + + interval_insert(entry_new, &memtype_rbroot); + return 0; +} + +struct memtype *memtype_erase(u64 start, u64 end) +{ + struct memtype *entry_old; + + /* + * Since the memtype_rbroot tree allows overlapping ranges, + * memtype_erase() checks with EXACT_MATCH first, i.e. free + * a whole node for the munmap case. If no such entry is found, + * it then checks with END_MATCH, i.e. shrink the size of a node + * from the end for the mremap case. + */ + entry_old = memtype_match(start, end, MEMTYPE_EXACT_MATCH); + if (!entry_old) { + entry_old = memtype_match(start, end, MEMTYPE_END_MATCH); + if (!entry_old) + return ERR_PTR(-EINVAL); + } + + if (entry_old->start == start) { + /* munmap: erase this node */ + interval_remove(entry_old, &memtype_rbroot); + } else { + /* mremap: update the end value of this node */ + interval_remove(entry_old, &memtype_rbroot); + entry_old->end = start; + interval_insert(entry_old, &memtype_rbroot); + + return NULL; + } + + return entry_old; +} + +struct memtype *memtype_lookup(u64 addr) +{ + return interval_iter_first(&memtype_rbroot, addr, addr + PAGE_SIZE-1); +} + +/* + * Debugging helper, copy the Nth entry of the tree into a + * a copy for printout. This allows us to print out the tree + * via debugfs, without holding the memtype_lock too long: + */ +#ifdef CONFIG_DEBUG_FS +int memtype_copy_nth_element(struct memtype *entry_out, loff_t pos) +{ + struct memtype *entry_match; + int i = 1; + + entry_match = interval_iter_first(&memtype_rbroot, 0, ULONG_MAX); + + while (entry_match && pos != i) { + entry_match = interval_iter_next(entry_match, 0, ULONG_MAX); + i++; + } + + if (entry_match) { /* pos == i */ + *entry_out = *entry_match; + return 0; + } else { + return 1; + } +} +#endif diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pat/set_memory.c index 6a9a77a403c9..c4aedd00c1ba 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pat/set_memory.c @@ -24,10 +24,10 @@ #include <linux/uaccess.h> #include <asm/pgalloc.h> #include <asm/proto.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/set_memory.h> -#include "mm_internal.h" +#include "../mm_internal.h" /* * The current flushing context - we pass it instead of 5 arguments: @@ -331,7 +331,7 @@ static void cpa_flush_all(unsigned long cache) on_each_cpu(__cpa_flush_all, (void *) cache, 1); } -void __cpa_flush_tlb(void *data) +static void __cpa_flush_tlb(void *data) { struct cpa_data *cpa = data; unsigned int i; @@ -516,7 +516,7 @@ static inline void check_conflict(int warnlvl, pgprot_t prot, pgprotval_t val, */ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start, unsigned long pfn, unsigned long npg, - int warnlvl) + unsigned long lpsize, int warnlvl) { pgprotval_t forbidden, res; unsigned long end; @@ -535,9 +535,17 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start, check_conflict(warnlvl, prot, res, start, end, pfn, "Text NX"); forbidden = res; - res = protect_kernel_text_ro(start, end); - check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO"); - forbidden |= res; + /* + * Special case to preserve a large page. If the change spawns the + * full large page mapping then there is no point to split it + * up. Happens with ftrace and is going to be removed once ftrace + * switched to text_poke(). + */ + if (lpsize != (npg * PAGE_SIZE) || (start & (lpsize - 1))) { + res = protect_kernel_text_ro(start, end); + check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO"); + forbidden |= res; + } /* Check the PFN directly */ res = protect_pci_bios(pfn, pfn + npg - 1); @@ -610,6 +618,17 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) } EXPORT_SYMBOL_GPL(lookup_address); +/* + * Lookup the page table entry for a virtual address in a given mm. Return a + * pointer to the entry and the level of the mapping. + */ +pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, + unsigned int *level) +{ + return lookup_address_in_pgd(pgd_offset(mm, address), address, level); +} +EXPORT_SYMBOL_GPL(lookup_address_in_mm); + static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, unsigned int *level) { @@ -819,7 +838,7 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, * extra conditional required here. */ chk_prot = static_protections(old_prot, lpaddr, old_pfn, numpages, - CPA_CONFLICT); + psize, CPA_CONFLICT); if (WARN_ON_ONCE(pgprot_val(chk_prot) != pgprot_val(old_prot))) { /* @@ -855,7 +874,7 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, * protection requirement in the large page. */ new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages, - CPA_DETECT); + psize, CPA_DETECT); /* * If there is a conflict, split the large page. @@ -906,7 +925,8 @@ static void split_set_pte(struct cpa_data *cpa, pte_t *pte, unsigned long pfn, if (!cpa->force_static_prot) goto set; - prot = static_protections(ref_prot, address, pfn, npg, CPA_PROTECT); + /* Hand in lpsize = 0 to enforce the protection mechanism */ + prot = static_protections(ref_prot, address, pfn, npg, 0, CPA_PROTECT); if (pgprot_val(prot) == pgprot_val(ref_prot)) goto set; @@ -1503,7 +1523,8 @@ repeat: pgprot_val(new_prot) |= pgprot_val(cpa->mask_set); cpa_inc_4k_install(); - new_prot = static_protections(new_prot, address, pfn, 1, + /* Hand in lpsize = 0 to enforce the protection mechanism */ + new_prot = static_protections(new_prot, address, pfn, 1, 0, CPA_PROTECT); new_prot = pgprot_clear_protnone_bits(new_prot); @@ -1774,7 +1795,7 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages, int _set_memory_uc(unsigned long addr, int numpages) { /* - * for now UC MINUS. see comments in ioremap_nocache() + * for now UC MINUS. see comments in ioremap() * If you really need strong UC use ioremap_uc(), but note * that you cannot override IO areas with set_memory_*() as * these helpers cannot work with IO memory. @@ -1789,9 +1810,9 @@ int set_memory_uc(unsigned long addr, int numpages) int ret; /* - * for now UC MINUS. see comments in ioremap_nocache() + * for now UC MINUS. see comments in ioremap() */ - ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_MODE_UC_MINUS, NULL); if (ret) goto out_err; @@ -1803,69 +1824,12 @@ int set_memory_uc(unsigned long addr, int numpages) return 0; out_free: - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); out_err: return ret; } EXPORT_SYMBOL(set_memory_uc); -static int _set_memory_array(unsigned long *addr, int numpages, - enum page_cache_mode new_type) -{ - enum page_cache_mode set_type; - int i, j; - int ret; - - for (i = 0; i < numpages; i++) { - ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE, - new_type, NULL); - if (ret) - goto out_free; - } - - /* If WC, set to UC- first and then WC */ - set_type = (new_type == _PAGE_CACHE_MODE_WC) ? - _PAGE_CACHE_MODE_UC_MINUS : new_type; - - ret = change_page_attr_set(addr, numpages, - cachemode2pgprot(set_type), 1); - - if (!ret && new_type == _PAGE_CACHE_MODE_WC) - ret = change_page_attr_set_clr(addr, numpages, - cachemode2pgprot( - _PAGE_CACHE_MODE_WC), - __pgprot(_PAGE_CACHE_MASK), - 0, CPA_ARRAY, NULL); - if (ret) - goto out_free; - - return 0; - -out_free: - for (j = 0; j < i; j++) - free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE); - - return ret; -} - -int set_memory_array_uc(unsigned long *addr, int numpages) -{ - return _set_memory_array(addr, numpages, _PAGE_CACHE_MODE_UC_MINUS); -} -EXPORT_SYMBOL(set_memory_array_uc); - -int set_memory_array_wc(unsigned long *addr, int numpages) -{ - return _set_memory_array(addr, numpages, _PAGE_CACHE_MODE_WC); -} -EXPORT_SYMBOL(set_memory_array_wc); - -int set_memory_array_wt(unsigned long *addr, int numpages) -{ - return _set_memory_array(addr, numpages, _PAGE_CACHE_MODE_WT); -} -EXPORT_SYMBOL_GPL(set_memory_array_wt); - int _set_memory_wc(unsigned long addr, int numpages) { int ret; @@ -1886,14 +1850,14 @@ int set_memory_wc(unsigned long addr, int numpages) { int ret; - ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_MODE_WC, NULL); if (ret) return ret; ret = _set_memory_wc(addr, numpages); if (ret) - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); return ret; } @@ -1905,23 +1869,6 @@ int _set_memory_wt(unsigned long addr, int numpages) cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0); } -int set_memory_wt(unsigned long addr, int numpages) -{ - int ret; - - ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, - _PAGE_CACHE_MODE_WT, NULL); - if (ret) - return ret; - - ret = _set_memory_wt(addr, numpages); - if (ret) - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); - - return ret; -} -EXPORT_SYMBOL_GPL(set_memory_wt); - int _set_memory_wb(unsigned long addr, int numpages) { /* WB cache mode is hard wired to all cache attribute bits being 0 */ @@ -1937,29 +1884,11 @@ int set_memory_wb(unsigned long addr, int numpages) if (ret) return ret; - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); return 0; } EXPORT_SYMBOL(set_memory_wb); -int set_memory_array_wb(unsigned long *addr, int numpages) -{ - int i; - int ret; - - /* WB cache mode is hard wired to all cache attribute bits being 0 */ - ret = change_page_attr_clear(addr, numpages, - __pgprot(_PAGE_CACHE_MASK), 1); - if (ret) - return ret; - - for (i = 0; i < numpages; i++) - free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE); - - return 0; -} -EXPORT_SYMBOL(set_memory_array_wb); - int set_memory_x(unsigned long addr, int numpages) { if (!(__supported_pte_mask & _PAGE_NX)) @@ -1967,7 +1896,6 @@ int set_memory_x(unsigned long addr, int numpages) return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0); } -EXPORT_SYMBOL(set_memory_x); int set_memory_nx(unsigned long addr, int numpages) { @@ -1976,7 +1904,6 @@ int set_memory_nx(unsigned long addr, int numpages) return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0); } -EXPORT_SYMBOL(set_memory_nx); int set_memory_ro(unsigned long addr, int numpages) { @@ -2098,7 +2025,7 @@ static int _set_pages_array(struct page **pages, int numpages, continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; - if (reserve_memtype(start, end, new_type, NULL)) + if (memtype_reserve(start, end, new_type, NULL)) goto err_out; } @@ -2124,7 +2051,7 @@ err_out: continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; - free_memtype(start, end); + memtype_free(start, end); } return -EINVAL; } @@ -2173,29 +2100,13 @@ int set_pages_array_wb(struct page **pages, int numpages) continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; - free_memtype(start, end); + memtype_free(start, end); } return 0; } EXPORT_SYMBOL(set_pages_array_wb); -int set_pages_x(struct page *page, int numpages) -{ - unsigned long addr = (unsigned long)page_address(page); - - return set_memory_x(addr, numpages); -} -EXPORT_SYMBOL(set_pages_x); - -int set_pages_nx(struct page *page, int numpages) -{ - unsigned long addr = (unsigned long)page_address(page); - - return set_memory_nx(addr, numpages); -} -EXPORT_SYMBOL(set_pages_nx); - int set_pages_ro(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); @@ -2315,7 +2226,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(0), + .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)), .flags = 0, }; @@ -2324,12 +2235,6 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, if (!(__supported_pte_mask & _PAGE_NX)) goto out; - if (!(page_flags & _PAGE_NX)) - cpa.mask_clr = __pgprot(_PAGE_NX); - - if (!(page_flags & _PAGE_RW)) - cpa.mask_clr = __pgprot(_PAGE_RW); - if (!(page_flags & _PAGE_ENC)) cpa.mask_clr = pgprot_encrypted(cpa.mask_clr); @@ -2381,5 +2286,5 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, * be exposed to the rest of the kernel. Include these directly here. */ #ifdef CONFIG_CPA_DEBUG -#include "pageattr-test.c" +#include "cpa-test.c" #endif diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c deleted file mode 100644 index fa16036fa592..000000000000 --- a/arch/x86/mm/pat_rbtree.c +++ /dev/null @@ -1,281 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Handle caching attributes in page tables (PAT) - * - * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> - * Suresh B Siddha <suresh.b.siddha@intel.com> - * - * Interval tree (augmented rbtree) used to store the PAT memory type - * reservations. - */ - -#include <linux/seq_file.h> -#include <linux/debugfs.h> -#include <linux/kernel.h> -#include <linux/rbtree_augmented.h> -#include <linux/sched.h> -#include <linux/gfp.h> - -#include <asm/pgtable.h> -#include <asm/pat.h> - -#include "pat_internal.h" - -/* - * The memtype tree keeps track of memory type for specific - * physical memory areas. Without proper tracking, conflicting memory - * types in different mappings can cause CPU cache corruption. - * - * The tree is an interval tree (augmented rbtree) with tree ordered - * on starting address. Tree can contain multiple entries for - * different regions which overlap. All the aliases have the same - * cache attributes of course. - * - * memtype_lock protects the rbtree. - */ - -static struct rb_root memtype_rbroot = RB_ROOT; - -static int is_node_overlap(struct memtype *node, u64 start, u64 end) -{ - if (node->start >= end || node->end <= start) - return 0; - - return 1; -} - -static u64 get_subtree_max_end(struct rb_node *node) -{ - u64 ret = 0; - if (node) { - struct memtype *data = rb_entry(node, struct memtype, rb); - ret = data->subtree_max_end; - } - return ret; -} - -static u64 compute_subtree_max_end(struct memtype *data) -{ - u64 max_end = data->end, child_max_end; - - child_max_end = get_subtree_max_end(data->rb.rb_right); - if (child_max_end > max_end) - max_end = child_max_end; - - child_max_end = get_subtree_max_end(data->rb.rb_left); - if (child_max_end > max_end) - max_end = child_max_end; - - return max_end; -} - -RB_DECLARE_CALLBACKS(static, memtype_rb_augment_cb, struct memtype, rb, - u64, subtree_max_end, compute_subtree_max_end) - -/* Find the first (lowest start addr) overlapping range from rb tree */ -static struct memtype *memtype_rb_lowest_match(struct rb_root *root, - u64 start, u64 end) -{ - struct rb_node *node = root->rb_node; - struct memtype *last_lower = NULL; - - while (node) { - struct memtype *data = rb_entry(node, struct memtype, rb); - - if (get_subtree_max_end(node->rb_left) > start) { - /* Lowest overlap if any must be on left side */ - node = node->rb_left; - } else if (is_node_overlap(data, start, end)) { - last_lower = data; - break; - } else if (start >= data->start) { - /* Lowest overlap if any must be on right side */ - node = node->rb_right; - } else { - break; - } - } - return last_lower; /* Returns NULL if there is no overlap */ -} - -enum { - MEMTYPE_EXACT_MATCH = 0, - MEMTYPE_END_MATCH = 1 -}; - -static struct memtype *memtype_rb_match(struct rb_root *root, - u64 start, u64 end, int match_type) -{ - struct memtype *match; - - match = memtype_rb_lowest_match(root, start, end); - while (match != NULL && match->start < end) { - struct rb_node *node; - - if ((match_type == MEMTYPE_EXACT_MATCH) && - (match->start == start) && (match->end == end)) - return match; - - if ((match_type == MEMTYPE_END_MATCH) && - (match->start < start) && (match->end == end)) - return match; - - node = rb_next(&match->rb); - if (node) - match = rb_entry(node, struct memtype, rb); - else - match = NULL; - } - - return NULL; /* Returns NULL if there is no match */ -} - -static int memtype_rb_check_conflict(struct rb_root *root, - u64 start, u64 end, - enum page_cache_mode reqtype, - enum page_cache_mode *newtype) -{ - struct rb_node *node; - struct memtype *match; - enum page_cache_mode found_type = reqtype; - - match = memtype_rb_lowest_match(&memtype_rbroot, start, end); - if (match == NULL) - goto success; - - if (match->type != found_type && newtype == NULL) - goto failure; - - dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end); - found_type = match->type; - - node = rb_next(&match->rb); - while (node) { - match = rb_entry(node, struct memtype, rb); - - if (match->start >= end) /* Checked all possible matches */ - goto success; - - if (is_node_overlap(match, start, end) && - match->type != found_type) { - goto failure; - } - - node = rb_next(&match->rb); - } -success: - if (newtype) - *newtype = found_type; - - return 0; - -failure: - pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n", - current->comm, current->pid, start, end, - cattr_name(found_type), cattr_name(match->type)); - return -EBUSY; -} - -static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata) -{ - struct rb_node **node = &(root->rb_node); - struct rb_node *parent = NULL; - - while (*node) { - struct memtype *data = rb_entry(*node, struct memtype, rb); - - parent = *node; - if (data->subtree_max_end < newdata->end) - data->subtree_max_end = newdata->end; - if (newdata->start <= data->start) - node = &((*node)->rb_left); - else if (newdata->start > data->start) - node = &((*node)->rb_right); - } - - newdata->subtree_max_end = newdata->end; - rb_link_node(&newdata->rb, parent, node); - rb_insert_augmented(&newdata->rb, root, &memtype_rb_augment_cb); -} - -int rbt_memtype_check_insert(struct memtype *new, - enum page_cache_mode *ret_type) -{ - int err = 0; - - err = memtype_rb_check_conflict(&memtype_rbroot, new->start, new->end, - new->type, ret_type); - - if (!err) { - if (ret_type) - new->type = *ret_type; - - new->subtree_max_end = new->end; - memtype_rb_insert(&memtype_rbroot, new); - } - return err; -} - -struct memtype *rbt_memtype_erase(u64 start, u64 end) -{ - struct memtype *data; - - /* - * Since the memtype_rbroot tree allows overlapping ranges, - * rbt_memtype_erase() checks with EXACT_MATCH first, i.e. free - * a whole node for the munmap case. If no such entry is found, - * it then checks with END_MATCH, i.e. shrink the size of a node - * from the end for the mremap case. - */ - data = memtype_rb_match(&memtype_rbroot, start, end, - MEMTYPE_EXACT_MATCH); - if (!data) { - data = memtype_rb_match(&memtype_rbroot, start, end, - MEMTYPE_END_MATCH); - if (!data) - return ERR_PTR(-EINVAL); - } - - if (data->start == start) { - /* munmap: erase this node */ - rb_erase_augmented(&data->rb, &memtype_rbroot, - &memtype_rb_augment_cb); - } else { - /* mremap: update the end value of this node */ - rb_erase_augmented(&data->rb, &memtype_rbroot, - &memtype_rb_augment_cb); - data->end = start; - data->subtree_max_end = data->end; - memtype_rb_insert(&memtype_rbroot, data); - return NULL; - } - - return data; -} - -struct memtype *rbt_memtype_lookup(u64 addr) -{ - return memtype_rb_lowest_match(&memtype_rbroot, addr, addr + PAGE_SIZE); -} - -#if defined(CONFIG_DEBUG_FS) -int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos) -{ - struct rb_node *node; - int i = 1; - - node = rb_first(&memtype_rbroot); - while (node && pos != i) { - node = rb_next(node); - i++; - } - - if (node) { /* pos == i */ - struct memtype *this = rb_entry(node, struct memtype, rb); - *out = *this; - return 0; - } else { - return 1; - } -} -#endif diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 44816ff6411f..7bd2c3a52297 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -45,7 +45,7 @@ early_param("userpte", setup_userpte); void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { - pgtable_page_dtor(pte); + pgtable_pte_page_dtor(pte); paravirt_release_pte(page_to_pfn(pte)); paravirt_tlb_remove_table(tlb, pte); } @@ -357,7 +357,7 @@ static void pgd_prepopulate_user_pmd(struct mm_struct *mm, static struct kmem_cache *pgd_cache; -void __init pgd_cache_init(void) +void __init pgtable_cache_init(void) { /* * When PAE kernel is running as a Xen domain, it does not use @@ -402,10 +402,6 @@ static inline void _pgd_free(pgd_t *pgd) } #else -void __init pgd_cache_init(void) -{ -} - static inline pgd_t *_pgd_alloc(void) { return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, @@ -647,8 +643,8 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) fixmaps_set++; } -void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, - pgprot_t flags) +void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, + phys_addr_t phys, pgprot_t flags) { /* Sanitize 'prot' against any unsupported bits: */ pgprot_val(flags) &= __default_kernel_pte_mask; diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 9bb7f0ab9fe6..0e6700eaa4f9 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -18,6 +18,7 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/io.h> +#include <linux/vmalloc.h> unsigned int __VMALLOC_RESERVE = 128 << 20; diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index bdc98150d4db..fc3f3d3e2ef2 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -5,6 +5,7 @@ #include <linux/mm.h> #include <asm/page.h> +#include <linux/vmalloc.h> #include "physaddr.h" diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index b196524759ec..44a9f068eee0 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -330,13 +330,15 @@ pti_clone_pgtable(unsigned long start, unsigned long end, pud = pud_offset(p4d, addr); if (pud_none(*pud)) { - addr += PUD_SIZE; + WARN_ON_ONCE(addr & ~PUD_MASK); + addr = round_up(addr + 1, PUD_SIZE); continue; } pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { - addr += PMD_SIZE; + WARN_ON_ONCE(addr & ~PMD_MASK); + addr = round_up(addr + 1, PMD_SIZE); continue; } @@ -572,7 +574,7 @@ static void pti_clone_kernel_text(void) */ unsigned long start = PFN_ALIGN(_text); unsigned long end_clone = (unsigned long)__end_rodata_aligned; - unsigned long end_global = PFN_ALIGN((unsigned long)__stop___ex_table); + unsigned long end_global = PFN_ALIGN((unsigned long)_etext); if (!pti_kernel_image_global_ok()) return; @@ -666,6 +668,8 @@ void __init pti_init(void) */ void pti_finalize(void) { + if (!boot_cpu_has(X86_FEATURE_PTI)) + return; /* * We need to clone everything (again) that maps parts of the * kernel image. diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index 0881e1ff1e58..bda73cb7a044 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/io.h> #include <linux/mmiotrace.h> +#include <linux/security.h> static unsigned long mmio_address; module_param_hw(mmio_address, ulong, iomem, 0); @@ -78,7 +79,7 @@ static void do_read_far_test(void __iomem *p) static void do_test(unsigned long size) { - void __iomem *p = ioremap_nocache(mmio_address, size); + void __iomem *p = ioremap(mmio_address, size); if (!p) { pr_err("could not ioremap, aborting.\n"); return; @@ -103,7 +104,7 @@ static void do_test_bulk_ioremapping(void) int i; for (i = 0; i < 10; ++i) { - p = ioremap_nocache(mmio_address, PAGE_SIZE); + p = ioremap(mmio_address, PAGE_SIZE); if (p) iounmap(p); } @@ -115,6 +116,10 @@ static void do_test_bulk_ioremapping(void) static int __init init(void) { unsigned long size = (read_far) ? (8 << 20) : (16 << 10); + int ret = security_locked_down(LOCKDOWN_MMIOTRACE); + + if (ret) + return ret; if (mmio_address == 0) { pr_err("you have to use the module argument mmio_address.\n"); @@ -122,9 +127,9 @@ static int __init init(void) return -ENXIO; } - pr_warning("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, " - "and writing 16 kB of rubbish in there.\n", - size >> 10, mmio_address); + pr_warn("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, " + "and writing 16 kB of rubbish in there.\n", + size >> 10, mmio_address); do_test(size); do_test_bulk_ioremapping(); pr_info("All done.\n"); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 4de9704c4aaf..66f96f21a7b6 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -440,7 +440,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); if (next != real_prev) { - load_mm_cr4(next); + load_mm_cr4_irqsoff(next); switch_ldt(real_prev, next); } } @@ -708,7 +708,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, (void *)info, 1); else on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func_remote, - (void *)info, 1, GFP_ATOMIC, cpumask); + (void *)info, 1, cpumask); } /* diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 991549a1c5f3..9ba08e9abc09 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -9,9 +9,13 @@ #include <linux/filter.h> #include <linux/if_vlan.h> #include <linux/bpf.h> - +#include <linux/memory.h> +#include <linux/sort.h> +#include <asm/extable.h> #include <asm/set_memory.h> #include <asm/nospec-branch.h> +#include <asm/text-patching.h> +#include <asm/asm-prototypes.h> static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { @@ -96,6 +100,7 @@ static int bpf_size_to_x86_bytes(int bpf_size) /* Pick a register outside of BPF range for JIT internal work */ #define AUX_REG (MAX_BPF_JIT_REG + 1) +#define X86_REG_R9 (MAX_BPF_JIT_REG + 2) /* * The following table maps BPF registers to x86-64 registers. @@ -104,8 +109,8 @@ static int bpf_size_to_x86_bytes(int bpf_size) * register in load/store instructions, it always needs an * extra byte of encoding and is callee saved. * - * Also x86-64 register R9 is unused. x86-64 register R10 is - * used for blinding (if enabled). + * x86-64 register R9 is not used by BPF programs, but can be used by BPF + * trampoline. x86-64 register R10 is used for blinding (if enabled). */ static const int reg2hex[] = { [BPF_REG_0] = 0, /* RAX */ @@ -121,6 +126,20 @@ static const int reg2hex[] = { [BPF_REG_FP] = 5, /* RBP readonly */ [BPF_REG_AX] = 2, /* R10 temp register */ [AUX_REG] = 3, /* R11 temp register */ + [X86_REG_R9] = 1, /* R9 register, 6th function argument */ +}; + +static const int reg2pt_regs[] = { + [BPF_REG_0] = offsetof(struct pt_regs, ax), + [BPF_REG_1] = offsetof(struct pt_regs, di), + [BPF_REG_2] = offsetof(struct pt_regs, si), + [BPF_REG_3] = offsetof(struct pt_regs, dx), + [BPF_REG_4] = offsetof(struct pt_regs, cx), + [BPF_REG_5] = offsetof(struct pt_regs, r8), + [BPF_REG_6] = offsetof(struct pt_regs, bx), + [BPF_REG_7] = offsetof(struct pt_regs, r13), + [BPF_REG_8] = offsetof(struct pt_regs, r14), + [BPF_REG_9] = offsetof(struct pt_regs, r15), }; /* @@ -135,6 +154,7 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_7) | BIT(BPF_REG_8) | BIT(BPF_REG_9) | + BIT(X86_REG_R9) | BIT(BPF_REG_AX)); } @@ -186,7 +206,10 @@ struct jit_context { #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 -#define PROLOGUE_SIZE 20 +/* Number of bytes emit_patch() needs to generate instructions */ +#define X86_PATCH_SIZE 5 + +#define PROLOGUE_SIZE 25 /* * Emit x86-64 prologue code for BPF program and check its size. @@ -195,8 +218,13 @@ struct jit_context { static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) { u8 *prog = *pprog; - int cnt = 0; + int cnt = X86_PATCH_SIZE; + /* BPF trampoline can be made to work without these nops, + * but let's waste 5 bytes for now and optimize later + */ + memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt); + prog += cnt; EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ /* sub rsp, rounded_stack_depth */ @@ -213,6 +241,89 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) *pprog = prog; } +static int emit_patch(u8 **pprog, void *func, void *ip, u8 opcode) +{ + u8 *prog = *pprog; + int cnt = 0; + s64 offset; + + offset = func - (ip + X86_PATCH_SIZE); + if (!is_simm32(offset)) { + pr_err("Target call %p is out of range\n", func); + return -ERANGE; + } + EMIT1_off32(opcode, offset); + *pprog = prog; + return 0; +} + +static int emit_call(u8 **pprog, void *func, void *ip) +{ + return emit_patch(pprog, func, ip, 0xE8); +} + +static int emit_jump(u8 **pprog, void *func, void *ip) +{ + return emit_patch(pprog, func, ip, 0xE9); +} + +static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, + void *old_addr, void *new_addr, + const bool text_live) +{ + const u8 *nop_insn = ideal_nops[NOP_ATOMIC5]; + u8 old_insn[X86_PATCH_SIZE]; + u8 new_insn[X86_PATCH_SIZE]; + u8 *prog; + int ret; + + memcpy(old_insn, nop_insn, X86_PATCH_SIZE); + if (old_addr) { + prog = old_insn; + ret = t == BPF_MOD_CALL ? + emit_call(&prog, old_addr, ip) : + emit_jump(&prog, old_addr, ip); + if (ret) + return ret; + } + + memcpy(new_insn, nop_insn, X86_PATCH_SIZE); + if (new_addr) { + prog = new_insn; + ret = t == BPF_MOD_CALL ? + emit_call(&prog, new_addr, ip) : + emit_jump(&prog, new_addr, ip); + if (ret) + return ret; + } + + ret = -EBUSY; + mutex_lock(&text_mutex); + if (memcmp(ip, old_insn, X86_PATCH_SIZE)) + goto out; + if (memcmp(ip, new_insn, X86_PATCH_SIZE)) { + if (text_live) + text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL); + else + memcpy(ip, new_insn, X86_PATCH_SIZE); + } + ret = 0; +out: + mutex_unlock(&text_mutex); + return ret; +} + +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, + void *old_addr, void *new_addr) +{ + if (!is_kernel_text((long)ip) && + !is_bpf_text_address((long)ip)) + /* BPF poking in modules is not supported */ + return -EINVAL; + + return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true); +} + /* * Generate the following code: * @@ -227,7 +338,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) * goto *(prog->bpf_func + prologue_size); * out: */ -static void emit_bpf_tail_call(u8 **pprog) +static void emit_bpf_tail_call_indirect(u8 **pprog) { u8 *prog = *pprog; int label1, label2, label3; @@ -294,6 +405,68 @@ static void emit_bpf_tail_call(u8 **pprog) *pprog = prog; } +static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, + u8 **pprog, int addr, u8 *image) +{ + u8 *prog = *pprog; + int cnt = 0; + + /* + * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + */ + EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */ + EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ + EMIT2(X86_JA, 14); /* ja out */ + EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ + EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */ + + poke->ip = image + (addr - X86_PATCH_SIZE); + poke->adj_off = PROLOGUE_SIZE; + + memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE); + prog += X86_PATCH_SIZE; + /* out: */ + + *pprog = prog; +} + +static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) +{ + struct bpf_jit_poke_descriptor *poke; + struct bpf_array *array; + struct bpf_prog *target; + int i, ret; + + for (i = 0; i < prog->aux->size_poke_tab; i++) { + poke = &prog->aux->poke_tab[i]; + WARN_ON_ONCE(READ_ONCE(poke->ip_stable)); + + if (poke->reason != BPF_POKE_REASON_TAIL_CALL) + continue; + + array = container_of(poke->tail_call.map, struct bpf_array, map); + mutex_lock(&array->aux->poke_mutex); + target = array->ptrs[poke->tail_call.key]; + if (target) { + /* Plain memcpy is used when image is not live yet + * and still not locked as read-only. Once poke + * location is active (poke->ip_stable), any parallel + * bpf_arch_text_poke() might occur still on the + * read-write image until we finally locked it as + * read-only. Both modifications on the given image + * are under text_mutex to avoid interference. + */ + ret = __bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, NULL, + (u8 *)target->bpf_func + + poke->adj_off, false); + BUG_ON(ret < 0); + } + WRITE_ONCE(poke->ip_stable, true); + mutex_unlock(&array->aux->poke_mutex); + } +} + static void emit_mov_imm32(u8 **pprog, bool sign_propagate, u32 dst_reg, const u32 imm32) { @@ -377,6 +550,96 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg) *pprog = prog; } +/* LDX: dst_reg = *(u8*)(src_reg + off) */ +static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) +{ + u8 *prog = *pprog; + int cnt = 0; + + switch (size) { + case BPF_B: + /* Emit 'movzx rax, byte ptr [rax + off]' */ + EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6); + break; + case BPF_H: + /* Emit 'movzx rax, word ptr [rax + off]' */ + EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7); + break; + case BPF_W: + /* Emit 'mov eax, dword ptr [rax+0x14]' */ + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B); + else + EMIT1(0x8B); + break; + case BPF_DW: + /* Emit 'mov rax, qword ptr [rax+0x14]' */ + EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B); + break; + } + /* + * If insn->off == 0 we can save one extra byte, but + * special case of x86 R13 which always needs an offset + * is not worth the hassle + */ + if (is_imm8(off)) + EMIT2(add_2reg(0x40, src_reg, dst_reg), off); + else + EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), off); + *pprog = prog; +} + +/* STX: *(u8*)(dst_reg + off) = src_reg */ +static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) +{ + u8 *prog = *pprog; + int cnt = 0; + + switch (size) { + case BPF_B: + /* Emit 'mov byte ptr [rax + off], al' */ + if (is_ereg(dst_reg) || is_ereg(src_reg) || + /* We have to add extra byte for x86 SIL, DIL regs */ + src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); + else + EMIT1(0x88); + break; + case BPF_H: + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89); + else + EMIT2(0x66, 0x89); + break; + case BPF_W: + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89); + else + EMIT1(0x89); + break; + case BPF_DW: + EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89); + break; + } + if (is_imm8(off)) + EMIT2(add_2reg(0x40, dst_reg, src_reg), off); + else + EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), off); + *pprog = prog; +} + +static bool ex_handler_bpf(const struct exception_table_entry *x, + struct pt_regs *regs, int trapnr, + unsigned long error_code, unsigned long fault_addr) +{ + u32 reg = x->fixup >> 8; + + /* jump over faulting load and clear dest register */ + *(unsigned long *)((void *)regs + reg) = 0; + regs->ip += x->fixup & 0xff; + return true; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int oldproglen, struct jit_context *ctx) { @@ -384,7 +647,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int insn_cnt = bpf_prog->len; bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; - int i, cnt = 0; + int i, cnt = 0, excnt = 0; int proglen = 0; u8 *prog = temp; @@ -747,64 +1010,64 @@ st: if (is_imm8(insn->off)) /* STX: *(u8*)(dst_reg + off) = src_reg */ case BPF_STX | BPF_MEM | BPF_B: - /* Emit 'mov byte ptr [rax + off], al' */ - if (is_ereg(dst_reg) || is_ereg(src_reg) || - /* We have to add extra byte for x86 SIL, DIL regs */ - src_reg == BPF_REG_1 || src_reg == BPF_REG_2) - EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); - else - EMIT1(0x88); - goto stx; case BPF_STX | BPF_MEM | BPF_H: - if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89); - else - EMIT2(0x66, 0x89); - goto stx; case BPF_STX | BPF_MEM | BPF_W: - if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89); - else - EMIT1(0x89); - goto stx; case BPF_STX | BPF_MEM | BPF_DW: - EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89); -stx: if (is_imm8(insn->off)) - EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off); - else - EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), - insn->off); + emit_stx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); break; /* LDX: dst_reg = *(u8*)(src_reg + off) */ case BPF_LDX | BPF_MEM | BPF_B: - /* Emit 'movzx rax, byte ptr [rax + off]' */ - EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6); - goto ldx; + case BPF_LDX | BPF_PROBE_MEM | BPF_B: case BPF_LDX | BPF_MEM | BPF_H: - /* Emit 'movzx rax, word ptr [rax + off]' */ - EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7); - goto ldx; + case BPF_LDX | BPF_PROBE_MEM | BPF_H: case BPF_LDX | BPF_MEM | BPF_W: - /* Emit 'mov eax, dword ptr [rax+0x14]' */ - if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B); - else - EMIT1(0x8B); - goto ldx; + case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_MEM | BPF_DW: - /* Emit 'mov rax, qword ptr [rax+0x14]' */ - EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B); -ldx: /* - * If insn->off == 0 we can save one extra byte, but - * special case of x86 R13 which always needs an offset - * is not worth the hassle - */ - if (is_imm8(insn->off)) - EMIT2(add_2reg(0x40, src_reg, dst_reg), insn->off); - else - EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), - insn->off); + case BPF_LDX | BPF_PROBE_MEM | BPF_DW: + emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); + if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { + struct exception_table_entry *ex; + u8 *_insn = image + proglen; + s64 delta; + + if (!bpf_prog->aux->extable) + break; + + if (excnt >= bpf_prog->aux->num_exentries) { + pr_err("ex gen bug\n"); + return -EFAULT; + } + ex = &bpf_prog->aux->extable[excnt++]; + + delta = _insn - (u8 *)&ex->insn; + if (!is_simm32(delta)) { + pr_err("extable->insn doesn't fit into 32-bit\n"); + return -EFAULT; + } + ex->insn = delta; + + delta = (u8 *)ex_handler_bpf - (u8 *)&ex->handler; + if (!is_simm32(delta)) { + pr_err("extable->handler doesn't fit into 32-bit\n"); + return -EFAULT; + } + ex->handler = delta; + + if (dst_reg > BPF_REG_9) { + pr_err("verifier error\n"); + return -EFAULT; + } + /* + * Compute size of x86 insn and its target dest x86 register. + * ex_handler_bpf() will use lower 8 bits to adjust + * pt_regs->ip to jump over this x86 instruction + * and upper bits to figure out which pt_regs to zero out. + * End result: x86 insn "mov rbx, qword ptr [rax+0x14]" + * of 4 bytes will be ignored and rbx will be zero inited. + */ + ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8); + } break; /* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */ @@ -827,17 +1090,16 @@ xadd: if (is_imm8(insn->off)) /* call */ case BPF_JMP | BPF_CALL: func = (u8 *) __bpf_call_base + imm32; - jmp_offset = func - (image + addrs[i]); - if (!imm32 || !is_simm32(jmp_offset)) { - pr_err("unsupported BPF func %d addr %p image %p\n", - imm32, func, image); + if (!imm32 || emit_call(&prog, func, image + addrs[i - 1])) return -EINVAL; - } - EMIT1_off32(0xE8, jmp_offset); break; case BPF_JMP | BPF_TAIL_CALL: - emit_bpf_tail_call(&prog); + if (imm32) + emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1], + &prog, addrs[i], image); + else + emit_bpf_tail_call_indirect(&prog); break; /* cond jump */ @@ -909,6 +1171,16 @@ xadd: if (is_imm8(insn->off)) case BPF_JMP32 | BPF_JSLT | BPF_K: case BPF_JMP32 | BPF_JSGE | BPF_K: case BPF_JMP32 | BPF_JSLE | BPF_K: + /* test dst_reg, dst_reg to save one extra byte */ + if (imm32 == 0) { + if (BPF_CLASS(insn->code) == BPF_JMP) + EMIT1(add_2mod(0x48, dst_reg, dst_reg)); + else if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg)); + goto emit_cond_jmp; + } + /* cmp dst_reg, imm8/32 */ if (BPF_CLASS(insn->code) == BPF_JMP) EMIT1(add_1mod(0x48, dst_reg)); @@ -1048,9 +1320,364 @@ emit_jmp: addrs[i] = proglen; prog = temp; } + + if (image && excnt != bpf_prog->aux->num_exentries) { + pr_err("extable is not populated\n"); + return -EFAULT; + } return proglen; } +static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_args, + int stack_size) +{ + int i; + /* Store function arguments to stack. + * For a function that accepts two pointers the sequence will be: + * mov QWORD PTR [rbp-0x10],rdi + * mov QWORD PTR [rbp-0x8],rsi + */ + for (i = 0; i < min(nr_args, 6); i++) + emit_stx(prog, bytes_to_bpf_size(m->arg_size[i]), + BPF_REG_FP, + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + -(stack_size - i * 8)); +} + +static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, + int stack_size) +{ + int i; + + /* Restore function arguments from stack. + * For a function that accepts two pointers the sequence will be: + * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10] + * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8] + */ + for (i = 0; i < min(nr_args, 6); i++) + emit_ldx(prog, bytes_to_bpf_size(m->arg_size[i]), + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + BPF_REG_FP, + -(stack_size - i * 8)); +} + +static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, + struct bpf_prog **progs, int prog_cnt, int stack_size) +{ + u8 *prog = *pprog; + int cnt = 0, i; + + for (i = 0; i < prog_cnt; i++) { + if (emit_call(&prog, __bpf_prog_enter, prog)) + return -EINVAL; + /* remember prog start time returned by __bpf_prog_enter */ + emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); + + /* arg1: lea rdi, [rbp - stack_size] */ + EMIT4(0x48, 0x8D, 0x7D, -stack_size); + /* arg2: progs[i]->insnsi for interpreter */ + if (!progs[i]->jited) + emit_mov_imm64(&prog, BPF_REG_2, + (long) progs[i]->insnsi >> 32, + (u32) (long) progs[i]->insnsi); + /* call JITed bpf program or interpreter */ + if (emit_call(&prog, progs[i]->bpf_func, prog)) + return -EINVAL; + + /* arg1: mov rdi, progs[i] */ + emit_mov_imm64(&prog, BPF_REG_1, (long) progs[i] >> 32, + (u32) (long) progs[i]); + /* arg2: mov rsi, rbx <- start time in nsec */ + emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); + if (emit_call(&prog, __bpf_prog_exit, prog)) + return -EINVAL; + } + *pprog = prog; + return 0; +} + +/* Example: + * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); + * its 'struct btf_func_model' will be nr_args=2 + * The assembly code when eth_type_trans is executing after trampoline: + * + * push rbp + * mov rbp, rsp + * sub rsp, 16 // space for skb and dev + * push rbx // temp regs to pass start time + * mov qword ptr [rbp - 16], rdi // save skb pointer to stack + * mov qword ptr [rbp - 8], rsi // save dev pointer to stack + * call __bpf_prog_enter // rcu_read_lock and preempt_disable + * mov rbx, rax // remember start time in bpf stats are enabled + * lea rdi, [rbp - 16] // R1==ctx of bpf prog + * call addr_of_jited_FENTRY_prog + * movabsq rdi, 64bit_addr_of_struct_bpf_prog // unused if bpf stats are off + * mov rsi, rbx // prog start time + * call __bpf_prog_exit // rcu_read_unlock, preempt_enable and stats math + * mov rdi, qword ptr [rbp - 16] // restore skb pointer from stack + * mov rsi, qword ptr [rbp - 8] // restore dev pointer from stack + * pop rbx + * leave + * ret + * + * eth_type_trans has 5 byte nop at the beginning. These 5 bytes will be + * replaced with 'call generated_bpf_trampoline'. When it returns + * eth_type_trans will continue executing with original skb and dev pointers. + * + * The assembly code when eth_type_trans is called from trampoline: + * + * push rbp + * mov rbp, rsp + * sub rsp, 24 // space for skb, dev, return value + * push rbx // temp regs to pass start time + * mov qword ptr [rbp - 24], rdi // save skb pointer to stack + * mov qword ptr [rbp - 16], rsi // save dev pointer to stack + * call __bpf_prog_enter // rcu_read_lock and preempt_disable + * mov rbx, rax // remember start time if bpf stats are enabled + * lea rdi, [rbp - 24] // R1==ctx of bpf prog + * call addr_of_jited_FENTRY_prog // bpf prog can access skb and dev + * movabsq rdi, 64bit_addr_of_struct_bpf_prog // unused if bpf stats are off + * mov rsi, rbx // prog start time + * call __bpf_prog_exit // rcu_read_unlock, preempt_enable and stats math + * mov rdi, qword ptr [rbp - 24] // restore skb pointer from stack + * mov rsi, qword ptr [rbp - 16] // restore dev pointer from stack + * call eth_type_trans+5 // execute body of eth_type_trans + * mov qword ptr [rbp - 8], rax // save return value + * call __bpf_prog_enter // rcu_read_lock and preempt_disable + * mov rbx, rax // remember start time in bpf stats are enabled + * lea rdi, [rbp - 24] // R1==ctx of bpf prog + * call addr_of_jited_FEXIT_prog // bpf prog can access skb, dev, return value + * movabsq rdi, 64bit_addr_of_struct_bpf_prog // unused if bpf stats are off + * mov rsi, rbx // prog start time + * call __bpf_prog_exit // rcu_read_unlock, preempt_enable and stats math + * mov rax, qword ptr [rbp - 8] // restore eth_type_trans's return value + * pop rbx + * leave + * add rsp, 8 // skip eth_type_trans's frame + * ret // return to its caller + */ +int arch_prepare_bpf_trampoline(void *image, void *image_end, + const struct btf_func_model *m, u32 flags, + struct bpf_prog **fentry_progs, int fentry_cnt, + struct bpf_prog **fexit_progs, int fexit_cnt, + void *orig_call) +{ + int cnt = 0, nr_args = m->nr_args; + int stack_size = nr_args * 8; + u8 *prog; + + /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ + if (nr_args > 6) + return -ENOTSUPP; + + if ((flags & BPF_TRAMP_F_RESTORE_REGS) && + (flags & BPF_TRAMP_F_SKIP_FRAME)) + return -EINVAL; + + if (flags & BPF_TRAMP_F_CALL_ORIG) + stack_size += 8; /* room for return value of orig_call */ + + if (flags & BPF_TRAMP_F_SKIP_FRAME) + /* skip patched call instruction and point orig_call to actual + * body of the kernel function. + */ + orig_call += X86_PATCH_SIZE; + + prog = image; + + EMIT1(0x55); /* push rbp */ + EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ + EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ + EMIT1(0x53); /* push rbx */ + + save_regs(m, &prog, nr_args, stack_size); + + if (fentry_cnt) + if (invoke_bpf(m, &prog, fentry_progs, fentry_cnt, stack_size)) + return -EINVAL; + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + if (fentry_cnt) + restore_regs(m, &prog, nr_args, stack_size); + + /* call original function */ + if (emit_call(&prog, orig_call, prog)) + return -EINVAL; + /* remember return value in a stack for bpf prog to access */ + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + } + + if (fexit_cnt) + if (invoke_bpf(m, &prog, fexit_progs, fexit_cnt, stack_size)) + return -EINVAL; + + if (flags & BPF_TRAMP_F_RESTORE_REGS) + restore_regs(m, &prog, nr_args, stack_size); + + if (flags & BPF_TRAMP_F_CALL_ORIG) + /* restore original return value back into RAX */ + emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); + + EMIT1(0x5B); /* pop rbx */ + EMIT1(0xC9); /* leave */ + if (flags & BPF_TRAMP_F_SKIP_FRAME) + /* skip our return address and return to parent */ + EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ + EMIT1(0xC3); /* ret */ + /* Make sure the trampoline generation logic doesn't overflow */ + if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) + return -EFAULT; + return prog - (u8 *)image; +} + +static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) +{ + u8 *prog = *pprog; + int cnt = 0; + s64 offset; + + offset = func - (ip + 2 + 4); + if (!is_simm32(offset)) { + pr_err("Target %p is out of range\n", func); + return -EINVAL; + } + EMIT2_off32(0x0F, jmp_cond + 0x10, offset); + *pprog = prog; + return 0; +} + +static void emit_nops(u8 **pprog, unsigned int len) +{ + unsigned int i, noplen; + u8 *prog = *pprog; + int cnt = 0; + + while (len > 0) { + noplen = len; + + if (noplen > ASM_NOP_MAX) + noplen = ASM_NOP_MAX; + + for (i = 0; i < noplen; i++) + EMIT1(ideal_nops[noplen][i]); + len -= noplen; + } + + *pprog = prog; +} + +static int emit_fallback_jump(u8 **pprog) +{ + u8 *prog = *pprog; + int err = 0; + +#ifdef CONFIG_RETPOLINE + /* Note that this assumes the the compiler uses external + * thunks for indirect calls. Both clang and GCC use the same + * naming convention for external thunks. + */ + err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog); +#else + int cnt = 0; + + EMIT2(0xFF, 0xE2); /* jmp rdx */ +#endif + *pprog = prog; + return err; +} + +static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) +{ + u8 *jg_reloc, *jg_target, *prog = *pprog; + int pivot, err, jg_bytes = 1, cnt = 0; + s64 jg_offset; + + if (a == b) { + /* Leaf node of recursion, i.e. not a range of indices + * anymore. + */ + EMIT1(add_1mod(0x48, BPF_REG_3)); /* cmp rdx,func */ + if (!is_simm32(progs[a])) + return -1; + EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3), + progs[a]); + err = emit_cond_near_jump(&prog, /* je func */ + (void *)progs[a], prog, + X86_JE); + if (err) + return err; + + err = emit_fallback_jump(&prog); /* jmp thunk/indirect */ + if (err) + return err; + + *pprog = prog; + return 0; + } + + /* Not a leaf node, so we pivot, and recursively descend into + * the lower and upper ranges. + */ + pivot = (b - a) / 2; + EMIT1(add_1mod(0x48, BPF_REG_3)); /* cmp rdx,func */ + if (!is_simm32(progs[a + pivot])) + return -1; + EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3), progs[a + pivot]); + + if (pivot > 2) { /* jg upper_part */ + /* Require near jump. */ + jg_bytes = 4; + EMIT2_off32(0x0F, X86_JG + 0x10, 0); + } else { + EMIT2(X86_JG, 0); + } + jg_reloc = prog; + + err = emit_bpf_dispatcher(&prog, a, a + pivot, /* emit lower_part */ + progs); + if (err) + return err; + + /* From Intel 64 and IA-32 Architectures Optimization + * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler + * Coding Rule 11: All branch targets should be 16-byte + * aligned. + */ + jg_target = PTR_ALIGN(prog, 16); + if (jg_target != prog) + emit_nops(&prog, jg_target - prog); + jg_offset = prog - jg_reloc; + emit_code(jg_reloc - jg_bytes, jg_offset, jg_bytes); + + err = emit_bpf_dispatcher(&prog, a + pivot + 1, /* emit upper_part */ + b, progs); + if (err) + return err; + + *pprog = prog; + return 0; +} + +static int cmp_ips(const void *a, const void *b) +{ + const s64 *ipa = a; + const s64 *ipb = b; + + if (*ipa > *ipb) + return 1; + if (*ipa < *ipb) + return -1; + return 0; +} + +int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs) +{ + u8 *prog = image; + + sort(funcs, num_funcs, sizeof(funcs[0]), cmp_ips, NULL); + return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs); +} + struct x64_jit_data { struct bpf_binary_header *header; int *addrs; @@ -1148,12 +1775,24 @@ out_image: break; } if (proglen == oldproglen) { - header = bpf_jit_binary_alloc(proglen, &image, - 1, jit_fill_hole); + /* + * The number of entries in extable is the number of BPF_LDX + * insns that access kernel memory via "pointer to BTF type". + * The verifier changed their opcode from LDX|MEM|size + * to LDX|PROBE_MEM|size to make JITing easier. + */ + u32 align = __alignof__(struct exception_table_entry); + u32 extable_size = prog->aux->num_exentries * + sizeof(struct exception_table_entry); + + /* allocate module memory for x86 insns and extable */ + header = bpf_jit_binary_alloc(roundup(proglen, align) + extable_size, + &image, align, jit_fill_hole); if (!header) { prog = orig_prog; goto out_addrs; } + prog->aux->extable = (void *) image + roundup(proglen, align); } oldproglen = proglen; cond_resched(); @@ -1164,6 +1803,7 @@ out_image: if (image) { if (!prog->is_func || extra_pass) { + bpf_tail_call_direct_fixup(prog); bpf_jit_binary_lock_ro(header); } else { jit_data->addrs = addrs; diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h index 71e8a67337e2..276cf79b5d24 100644 --- a/arch/x86/oprofile/op_x86_model.h +++ b/arch/x86/oprofile/op_x86_model.h @@ -67,13 +67,13 @@ static inline void op_x86_warn_in_use(int counter) * cannot be monitored by any other counter, contact your * hardware or BIOS vendor. */ - pr_warning("oprofile: counter #%d on cpu #%d may already be used\n", - counter, smp_processor_id()); + pr_warn("oprofile: counter #%d on cpu #%d may already be used\n", + counter, smp_processor_id()); } static inline void op_x86_warn_reserved(int counter) { - pr_warning("oprofile: counter #%d is already reserved\n", counter); + pr_warn("oprofile: counter #%d is already reserved\n", counter); } extern u64 op_x86_get_ctrl(struct op_x86_model_spec const *model, diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index c806b57d3f22..48bcada5cabe 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -24,6 +24,4 @@ obj-y += bus_numa.o obj-$(CONFIG_AMD_NB) += amd_bus.o obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o -ifeq ($(CONFIG_PCI_DEBUG),y) -EXTRA_CFLAGS += -DDEBUG -endif +ccflags-$(CONFIG_PCI_DEBUG) += -DDEBUG diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 9acab6ac28f5..df1d95913d4e 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -135,7 +135,7 @@ static void pcibios_fixup_device_resources(struct pci_dev *dev) * resource so the kernel doesn't attempt to assign * it later on in pci_assign_unassigned_resources */ - for (bar = 0; bar <= PCI_STD_RESOURCE_END; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { bar_r = &dev->resource[bar]; if (bar_r->start == 0 && bar_r->end != 0) { bar_r->flags = 0; @@ -625,43 +625,6 @@ unsigned int pcibios_assign_all_busses(void) return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0; } -#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS) -static LIST_HEAD(dma_domain_list); -static DEFINE_SPINLOCK(dma_domain_list_lock); - -void add_dma_domain(struct dma_domain *domain) -{ - spin_lock(&dma_domain_list_lock); - list_add(&domain->node, &dma_domain_list); - spin_unlock(&dma_domain_list_lock); -} -EXPORT_SYMBOL_GPL(add_dma_domain); - -void del_dma_domain(struct dma_domain *domain) -{ - spin_lock(&dma_domain_list_lock); - list_del(&domain->node); - spin_unlock(&dma_domain_list_lock); -} -EXPORT_SYMBOL_GPL(del_dma_domain); - -static void set_dma_domain_ops(struct pci_dev *pdev) -{ - struct dma_domain *domain; - - spin_lock(&dma_domain_list_lock); - list_for_each_entry(domain, &dma_domain_list, node) { - if (pci_domain_nr(pdev->bus) == domain->domain_nr) { - pdev->dev.dma_ops = domain->dma_ops; - break; - } - } - spin_unlock(&dma_domain_list_lock); -} -#else -static void set_dma_domain_ops(struct pci_dev *pdev) {} -#endif - static void set_dev_domain_options(struct pci_dev *pdev) { if (is_vmd(pdev->bus)) @@ -697,7 +660,6 @@ int pcibios_add_device(struct pci_dev *dev) pa_data = data->next; memunmap(data); } - set_dma_domain_ops(dev); set_dev_domain_options(dev); return 0; } @@ -736,3 +698,13 @@ int pci_ext_cfg_avail(void) else return 0; } + +#if IS_ENABLED(CONFIG_VMD) +struct pci_dev *pci_real_dma_dev(struct pci_dev *dev) +{ + if (is_vmd(dev->bus)) + return to_pci_sysdata(dev->bus)->vmd_dev; + + return dev; +} +#endif diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 527e69b12002..e723559c386a 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -589,6 +589,17 @@ static void pci_fixup_amd_ehci_pme(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7808, pci_fixup_amd_ehci_pme); /* + * Device [1022:7914] + * When in D0, PME# doesn't get asserted when plugging USB 2.0 device. + */ +static void pci_fixup_amd_fch_xhci_pme(struct pci_dev *dev) +{ + dev_info(&dev->dev, "PME# does not work under D0, disabling it\n"); + dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7914, pci_fixup_amd_fch_xhci_pme); + +/* * Apple MacBook Pro: Avoid [mem 0x7fa00000-0x7fbfffff] * * Using the [mem 0x7fa00000-0x7fbfffff] region, e.g., by assigning it to diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 9df652d3d927..fa855bbaebaf 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -34,7 +34,7 @@ #include <linux/errno.h> #include <linux/memblock.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/e820/api.h> #include <asm/pci_x86.h> #include <asm/io_apic.h> diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 43867bc85368..00c62115f39c 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -382,7 +382,7 @@ static void pci_fixed_bar_fixup(struct pci_dev *dev) PCI_DEVFN(2, 2) == dev->devfn) return; - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { pci_read_config_dword(dev, offset + 8 + (i * 4), &size); dev->resource[i].end = dev->resource[i].start + size - 1; dev->resource[i].flags |= IORESOURCE_PCI_FIXED; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 7389db538c30..6fa42e9c4e6f 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -29,6 +29,7 @@ static bool pci_mmcfg_running_state; static bool pci_mmcfg_arch_init_failed; static DEFINE_MUTEX(pci_mmcfg_lock); +#define pci_mmcfg_lock_held() lock_is_held(&(pci_mmcfg_lock).dep_map) LIST_HEAD(pci_mmcfg_list); @@ -54,7 +55,7 @@ static void list_add_sorted(struct pci_mmcfg_region *new) struct pci_mmcfg_region *cfg; /* keep list sorted by segment and starting bus number */ - list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) { + list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held()) { if (cfg->segment > new->segment || (cfg->segment == new->segment && cfg->start_bus >= new->start_bus)) { @@ -118,7 +119,7 @@ struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus) { struct pci_mmcfg_region *cfg; - list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) + list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held()) if (cfg->segment == segment && cfg->start_bus <= bus && bus <= cfg->end_bus) return cfg; diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index 887d181b769b..0c7b6e66c644 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -105,7 +105,7 @@ static void __iomem *mcfg_ioremap(struct pci_mmcfg_region *cfg) start = cfg->address + PCI_MMCFG_BUS_OFFSET(cfg->start_bus); num_buses = cfg->end_bus - cfg->start_bus + 1; size = PCI_MMCFG_BUS_OFFSET(num_buses); - addr = ioremap_nocache(start, size); + addr = ioremap(start, size); if (addr) addr -= PCI_MMCFG_BUS_OFFSET(cfg->start_bus); return addr; diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c index 2e565e65c893..01a085d9135a 100644 --- a/arch/x86/pci/numachip.c +++ b/arch/x86/pci/numachip.c @@ -1,8 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * * Numascale NumaConnect-specific PCI code * * Copyright (C) 2012 Numascale AS. All rights reserved. diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 97bbc12dd6b2..c313d784efab 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * arch/x86/pci/sta2x11-fixup.c - * glue code for lib/swiotlb.c and DMA translation between STA2x11 - * AMBA memory mapping and the X86 memory mapping + * DMA translation between STA2x11 AMBA memory mapping and the x86 memory mapping * * ST Microelectronics ConneXt (STA2X11/STA2X10) * @@ -32,7 +30,6 @@ struct sta2x11_ahb_regs { /* saved during suspend */ }; struct sta2x11_mapping { - u32 amba_base; int is_suspended; struct sta2x11_ahb_regs regs[STA2X11_NR_FUNCS]; }; @@ -94,18 +91,6 @@ static int sta2x11_pdev_to_ep(struct pci_dev *pdev) return pdev->bus->number - instance->bus0; } -static struct sta2x11_mapping *sta2x11_pdev_to_mapping(struct pci_dev *pdev) -{ - struct sta2x11_instance *instance; - int ep; - - instance = sta2x11_pdev_to_instance(pdev); - if (!instance) - return NULL; - ep = sta2x11_pdev_to_ep(pdev); - return instance->map + ep; -} - /* This is exported, as some devices need to access the MFD registers */ struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev) { @@ -113,39 +98,6 @@ struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev) } EXPORT_SYMBOL(sta2x11_get_instance); - -/** - * p2a - Translate physical address to STA2x11 AMBA address, - * used for DMA transfers to STA2x11 - * @p: Physical address - * @pdev: PCI device (must be hosted within the connext) - */ -static dma_addr_t p2a(dma_addr_t p, struct pci_dev *pdev) -{ - struct sta2x11_mapping *map; - dma_addr_t a; - - map = sta2x11_pdev_to_mapping(pdev); - a = p + map->amba_base; - return a; -} - -/** - * a2p - Translate STA2x11 AMBA address to physical address - * used for DMA transfers from STA2x11 - * @a: STA2x11 AMBA address - * @pdev: PCI device (must be hosted within the connext) - */ -static dma_addr_t a2p(dma_addr_t a, struct pci_dev *pdev) -{ - struct sta2x11_mapping *map; - dma_addr_t p; - - map = sta2x11_pdev_to_mapping(pdev); - p = a - map->amba_base; - return p; -} - /* At setup time, we use our own ops if the device is a ConneXt one */ static void sta2x11_setup_pdev(struct pci_dev *pdev) { @@ -153,9 +105,6 @@ static void sta2x11_setup_pdev(struct pci_dev *pdev) if (!instance) /* either a sta2x11 bridge or another ST device */ return; - pci_set_consistent_dma_mask(pdev, STA2X11_AMBA_SIZE - 1); - pci_set_dma_mask(pdev, STA2X11_AMBA_SIZE - 1); - pdev->dev.archdata.is_sta2x11 = true; /* We must enable all devices as master, for audio DMA to work */ pci_set_master(pdev); @@ -163,61 +112,6 @@ static void sta2x11_setup_pdev(struct pci_dev *pdev) DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_setup_pdev); /* - * The following three functions are exported (used in swiotlb: FIXME) - */ -/** - * dma_capable - Check if device can manage DMA transfers (FIXME: kill it) - * @dev: device for a PCI device - * @addr: DMA address - * @size: DMA size - */ -bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ - struct sta2x11_mapping *map; - - if (!dev->archdata.is_sta2x11) { - if (!dev->dma_mask) - return false; - return addr + size - 1 <= *dev->dma_mask; - } - - map = sta2x11_pdev_to_mapping(to_pci_dev(dev)); - - if (!map || (addr < map->amba_base)) - return false; - if (addr + size >= map->amba_base + STA2X11_AMBA_SIZE) { - return false; - } - - return true; -} - -/** - * __phys_to_dma - Return the DMA AMBA address used for this STA2x11 device - * @dev: device for a PCI device - * @paddr: Physical address - */ -dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) -{ - if (!dev->archdata.is_sta2x11) - return paddr; - return p2a(paddr, to_pci_dev(dev)); -} - -/** - * dma_to_phys - Return the physical address used for this STA2x11 DMA address - * @dev: device for a PCI device - * @daddr: STA2x11 AMBA DMA address - */ -phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr) -{ - if (!dev->archdata.is_sta2x11) - return daddr; - return a2p(daddr, to_pci_dev(dev)); -} - - -/* * At boot we must set up the mappings for the pcie-to-amba bridge. * It involves device access, and the same happens at suspend/resume time */ @@ -236,12 +130,22 @@ phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr) /* At probe time, enable mapping for each endpoint, using the pdev */ static void sta2x11_map_ep(struct pci_dev *pdev) { - struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev); + struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev); + struct device *dev = &pdev->dev; + u32 amba_base, max_amba_addr; int i; - if (!map) + if (!instance) return; - pci_read_config_dword(pdev, AHB_BASE(0), &map->amba_base); + + pci_read_config_dword(pdev, AHB_BASE(0), &amba_base); + max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1; + + dev->dma_pfn_offset = PFN_DOWN(-amba_base); + + dev->bus_dma_limit = max_amba_addr; + pci_set_consistent_dma_mask(pdev, max_amba_addr); + pci_set_dma_mask(pdev, max_amba_addr); /* Configure AHB mapping */ pci_write_config_dword(pdev, AHB_PEXLBASE(0), 0); @@ -255,13 +159,24 @@ static void sta2x11_map_ep(struct pci_dev *pdev) dev_info(&pdev->dev, "sta2x11: Map EP %i: AMBA address %#8x-%#8x\n", - sta2x11_pdev_to_ep(pdev), map->amba_base, - map->amba_base + STA2X11_AMBA_SIZE - 1); + sta2x11_pdev_to_ep(pdev), amba_base, max_amba_addr); } DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_map_ep); #ifdef CONFIG_PM /* Some register values must be saved and restored */ +static struct sta2x11_mapping *sta2x11_pdev_to_mapping(struct pci_dev *pdev) +{ + struct sta2x11_instance *instance; + int ep; + + instance = sta2x11_pdev_to_instance(pdev); + if (!instance) + return NULL; + ep = sta2x11_pdev_to_ep(pdev); + return instance->map + ep; +} + static void suspend_mapping(struct pci_dev *pdev) { struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev); diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index fe29f3f5d384..84b09c230cbd 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y -OBJECT_FILES_NON_STANDARD_efi_stub_$(BITS).o := y +KASAN_SANITIZE := n +GCOV_PROFILE := n obj-$(CONFIG_EFI) += quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o obj-$(CONFIG_EFI_MIXED) += efi_thunk_$(BITS).o diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index a7189a3b4d70..ae923ee8e2b4 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -54,16 +54,39 @@ #include <asm/x86_init.h> #include <asm/uv/uv.h> -static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; +static u64 efi_systab_phys __initdata; static efi_config_table_type_t arch_tables[] __initdata = { #ifdef CONFIG_X86_UV - {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab}, + {UV_SYSTEM_TABLE_GUID, "UVsystab", &uv_systab_phys}, #endif {NULL_GUID, NULL, NULL}, }; +static const unsigned long * const efi_tables[] = { + &efi.mps, + &efi.acpi, + &efi.acpi20, + &efi.smbios, + &efi.smbios3, + &efi.boot_info, + &efi.hcdp, + &efi.uga, +#ifdef CONFIG_X86_UV + &uv_systab_phys, +#endif + &efi.fw_vendor, + &efi.runtime, + &efi.config_table, + &efi.esrt, + &efi.properties_table, + &efi.mem_attr_table, +#ifdef CONFIG_EFI_RCI2_TABLE + &rci2_table_phys, +#endif +}; + u64 efi_setup; /* efi setup_data physical address */ static int add_efi_memmap __initdata; @@ -74,37 +97,14 @@ static int __init setup_add_efi_memmap(char *arg) } early_param("add_efi_memmap", setup_add_efi_memmap); -static efi_status_t __init phys_efi_set_virtual_address_map( - unsigned long memory_map_size, - unsigned long descriptor_size, - u32 descriptor_version, - efi_memory_desc_t *virtual_map) -{ - efi_status_t status; - unsigned long flags; - pgd_t *save_pgd; - - save_pgd = efi_call_phys_prolog(); - if (!save_pgd) - return EFI_ABORTED; - - /* Disable interrupts around EFI calls: */ - local_irq_save(flags); - status = efi_call_phys(efi_phys.set_virtual_address_map, - memory_map_size, descriptor_size, - descriptor_version, virtual_map); - local_irq_restore(flags); - - efi_call_phys_epilog(save_pgd); - - return status; -} - void __init efi_find_mirror(void) { efi_memory_desc_t *md; u64 mirror_size = 0, total_size = 0; + if (!efi_enabled(EFI_MEMMAP)) + return; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; @@ -122,14 +122,18 @@ void __init efi_find_mirror(void) /* * Tell the kernel about the EFI memory map. This might include - * more than the max 128 entries that can fit in the e820 legacy - * (zeropage) memory map. + * more than the max 128 entries that can fit in the passed in e820 + * legacy (zeropage) memory map, but the kernel's e820 table can hold + * E820_MAX_ENTRIES. */ static void __init do_add_efi_memmap(void) { efi_memory_desc_t *md; + if (!efi_enabled(EFI_MEMMAP)) + return; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; @@ -141,7 +145,10 @@ static void __init do_add_efi_memmap(void) case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: - if (md->attribute & EFI_MEMORY_WB) + if (efi_soft_reserve_enabled() + && (md->attribute & EFI_MEMORY_SP)) + e820_type = E820_TYPE_SOFT_RESERVED; + else if (md->attribute & EFI_MEMORY_WB) e820_type = E820_TYPE_RAM; else e820_type = E820_TYPE_RESERVED; @@ -167,11 +174,36 @@ static void __init do_add_efi_memmap(void) e820_type = E820_TYPE_RESERVED; break; } + e820__range_add(start, size, e820_type); } e820__update_table(e820_table); } +/* + * Given add_efi_memmap defaults to 0 and there there is no alternative + * e820 mechanism for soft-reserved memory, import the full EFI memory + * map if soft reservations are present and enabled. Otherwise, the + * mechanism to disable the kernel's consideration of EFI_MEMORY_SP is + * the efi=nosoftreserve option. + */ +static bool do_efi_soft_reserve(void) +{ + efi_memory_desc_t *md; + + if (!efi_enabled(EFI_MEMMAP)) + return false; + + if (!efi_soft_reserve_enabled()) + return false; + + for_each_efi_memory_desc(md) + if (md->type == EFI_CONVENTIONAL_MEMORY && + (md->attribute & EFI_MEMORY_SP)) + return true; + return false; +} + int __init efi_memblock_x86_reserve_range(void) { struct efi_info *e = &boot_params.efi_info; @@ -201,9 +233,11 @@ int __init efi_memblock_x86_reserve_range(void) if (rv) return rv; - if (add_efi_memmap) + if (add_efi_memmap || do_efi_soft_reserve()) do_add_efi_memmap(); + efi_fake_memmap_early(); + WARN(efi.memmap.desc_version != 1, "Unexpected EFI_MEMORY_DESCRIPTOR version %ld", efi.memmap.desc_version); @@ -270,10 +304,16 @@ static void __init efi_clean_memmap(void) } if (n_removal > 0) { - u64 size = efi.memmap.nr_map - n_removal; + struct efi_memory_map_data data = { + .phys_map = efi.memmap.phys_map, + .desc_version = efi.memmap.desc_version, + .desc_size = efi.memmap.desc_size, + .size = efi.memmap.desc_size * (efi.memmap.nr_map - n_removal), + .flags = 0, + }; pr_warn("Removing %d invalid memory map entries.\n", n_removal); - efi_memmap_install(efi.memmap.phys_map, size); + efi_memmap_install(&data); } } @@ -293,89 +333,90 @@ void __init efi_print_memmap(void) } } -static int __init efi_systab_init(void *phys) +static int __init efi_systab_init(u64 phys) { + int size = efi_enabled(EFI_64BIT) ? sizeof(efi_system_table_64_t) + : sizeof(efi_system_table_32_t); + bool over4g = false; + void *p; + + p = early_memremap_ro(phys, size); + if (p == NULL) { + pr_err("Couldn't map the system table!\n"); + return -ENOMEM; + } + if (efi_enabled(EFI_64BIT)) { - efi_system_table_64_t *systab64; - struct efi_setup_data *data = NULL; - u64 tmp = 0; + const efi_system_table_64_t *systab64 = p; + + efi_systab.hdr = systab64->hdr; + efi_systab.fw_vendor = systab64->fw_vendor; + efi_systab.fw_revision = systab64->fw_revision; + efi_systab.con_in_handle = systab64->con_in_handle; + efi_systab.con_in = systab64->con_in; + efi_systab.con_out_handle = systab64->con_out_handle; + efi_systab.con_out = (void *)(unsigned long)systab64->con_out; + efi_systab.stderr_handle = systab64->stderr_handle; + efi_systab.stderr = systab64->stderr; + efi_systab.runtime = (void *)(unsigned long)systab64->runtime; + efi_systab.boottime = (void *)(unsigned long)systab64->boottime; + efi_systab.nr_tables = systab64->nr_tables; + efi_systab.tables = systab64->tables; + + over4g = systab64->con_in_handle > U32_MAX || + systab64->con_in > U32_MAX || + systab64->con_out_handle > U32_MAX || + systab64->con_out > U32_MAX || + systab64->stderr_handle > U32_MAX || + systab64->stderr > U32_MAX || + systab64->boottime > U32_MAX; if (efi_setup) { - data = early_memremap(efi_setup, sizeof(*data)); - if (!data) + struct efi_setup_data *data; + + data = early_memremap_ro(efi_setup, sizeof(*data)); + if (!data) { + early_memunmap(p, size); return -ENOMEM; - } - systab64 = early_memremap((unsigned long)phys, - sizeof(*systab64)); - if (systab64 == NULL) { - pr_err("Couldn't map the system table!\n"); - if (data) - early_memunmap(data, sizeof(*data)); - return -ENOMEM; - } + } + + efi_systab.fw_vendor = (unsigned long)data->fw_vendor; + efi_systab.runtime = (void *)(unsigned long)data->runtime; + efi_systab.tables = (unsigned long)data->tables; + + over4g |= data->fw_vendor > U32_MAX || + data->runtime > U32_MAX || + data->tables > U32_MAX; - efi_systab.hdr = systab64->hdr; - efi_systab.fw_vendor = data ? (unsigned long)data->fw_vendor : - systab64->fw_vendor; - tmp |= data ? data->fw_vendor : systab64->fw_vendor; - efi_systab.fw_revision = systab64->fw_revision; - efi_systab.con_in_handle = systab64->con_in_handle; - tmp |= systab64->con_in_handle; - efi_systab.con_in = systab64->con_in; - tmp |= systab64->con_in; - efi_systab.con_out_handle = systab64->con_out_handle; - tmp |= systab64->con_out_handle; - efi_systab.con_out = systab64->con_out; - tmp |= systab64->con_out; - efi_systab.stderr_handle = systab64->stderr_handle; - tmp |= systab64->stderr_handle; - efi_systab.stderr = systab64->stderr; - tmp |= systab64->stderr; - efi_systab.runtime = data ? - (void *)(unsigned long)data->runtime : - (void *)(unsigned long)systab64->runtime; - tmp |= data ? data->runtime : systab64->runtime; - efi_systab.boottime = (void *)(unsigned long)systab64->boottime; - tmp |= systab64->boottime; - efi_systab.nr_tables = systab64->nr_tables; - efi_systab.tables = data ? (unsigned long)data->tables : - systab64->tables; - tmp |= data ? data->tables : systab64->tables; - - early_memunmap(systab64, sizeof(*systab64)); - if (data) early_memunmap(data, sizeof(*data)); -#ifdef CONFIG_X86_32 - if (tmp >> 32) { - pr_err("EFI data located above 4GB, disabling EFI.\n"); - return -EINVAL; + } else { + over4g |= systab64->fw_vendor > U32_MAX || + systab64->runtime > U32_MAX || + systab64->tables > U32_MAX; } -#endif } else { - efi_system_table_32_t *systab32; - - systab32 = early_memremap((unsigned long)phys, - sizeof(*systab32)); - if (systab32 == NULL) { - pr_err("Couldn't map the system table!\n"); - return -ENOMEM; - } - - efi_systab.hdr = systab32->hdr; - efi_systab.fw_vendor = systab32->fw_vendor; - efi_systab.fw_revision = systab32->fw_revision; - efi_systab.con_in_handle = systab32->con_in_handle; - efi_systab.con_in = systab32->con_in; - efi_systab.con_out_handle = systab32->con_out_handle; - efi_systab.con_out = systab32->con_out; - efi_systab.stderr_handle = systab32->stderr_handle; - efi_systab.stderr = systab32->stderr; - efi_systab.runtime = (void *)(unsigned long)systab32->runtime; - efi_systab.boottime = (void *)(unsigned long)systab32->boottime; - efi_systab.nr_tables = systab32->nr_tables; - efi_systab.tables = systab32->tables; - - early_memunmap(systab32, sizeof(*systab32)); + const efi_system_table_32_t *systab32 = p; + + efi_systab.hdr = systab32->hdr; + efi_systab.fw_vendor = systab32->fw_vendor; + efi_systab.fw_revision = systab32->fw_revision; + efi_systab.con_in_handle = systab32->con_in_handle; + efi_systab.con_in = systab32->con_in; + efi_systab.con_out_handle = systab32->con_out_handle; + efi_systab.con_out = (void *)(unsigned long)systab32->con_out; + efi_systab.stderr_handle = systab32->stderr_handle; + efi_systab.stderr = systab32->stderr; + efi_systab.runtime = (void *)(unsigned long)systab32->runtime; + efi_systab.boottime = (void *)(unsigned long)systab32->boottime; + efi_systab.nr_tables = systab32->nr_tables; + efi_systab.tables = systab32->tables; + } + + early_memunmap(p, size); + + if (IS_ENABLED(CONFIG_X86_32) && over4g) { + pr_err("EFI data located above 4GB, disabling EFI.\n"); + return -EINVAL; } efi.systab = &efi_systab; @@ -395,108 +436,23 @@ static int __init efi_systab_init(void *phys) return 0; } -static int __init efi_runtime_init32(void) -{ - efi_runtime_services_32_t *runtime; - - runtime = early_memremap((unsigned long)efi.systab->runtime, - sizeof(efi_runtime_services_32_t)); - if (!runtime) { - pr_err("Could not map the runtime service table!\n"); - return -ENOMEM; - } - - /* - * We will only need *early* access to the SetVirtualAddressMap - * EFI runtime service. All other runtime services will be called - * via the virtual mapping. - */ - efi_phys.set_virtual_address_map = - (efi_set_virtual_address_map_t *) - (unsigned long)runtime->set_virtual_address_map; - early_memunmap(runtime, sizeof(efi_runtime_services_32_t)); - - return 0; -} - -static int __init efi_runtime_init64(void) -{ - efi_runtime_services_64_t *runtime; - - runtime = early_memremap((unsigned long)efi.systab->runtime, - sizeof(efi_runtime_services_64_t)); - if (!runtime) { - pr_err("Could not map the runtime service table!\n"); - return -ENOMEM; - } - - /* - * We will only need *early* access to the SetVirtualAddressMap - * EFI runtime service. All other runtime services will be called - * via the virtual mapping. - */ - efi_phys.set_virtual_address_map = - (efi_set_virtual_address_map_t *) - (unsigned long)runtime->set_virtual_address_map; - early_memunmap(runtime, sizeof(efi_runtime_services_64_t)); - - return 0; -} - -static int __init efi_runtime_init(void) -{ - int rv; - - /* - * Check out the runtime services table. We need to map - * the runtime services table so that we can grab the physical - * address of several of the EFI runtime functions, needed to - * set the firmware into virtual mode. - * - * When EFI_PARAVIRT is in force then we could not map runtime - * service memory region because we do not have direct access to it. - * However, runtime services are available through proxy functions - * (e.g. in case of Xen dom0 EFI implementation they call special - * hypercall which executes relevant EFI functions) and that is why - * they are always enabled. - */ - - if (!efi_enabled(EFI_PARAVIRT)) { - if (efi_enabled(EFI_64BIT)) - rv = efi_runtime_init64(); - else - rv = efi_runtime_init32(); - - if (rv) - return rv; - } - - set_bit(EFI_RUNTIME_SERVICES, &efi.flags); - - return 0; -} - void __init efi_init(void) { efi_char16_t *c16; char vendor[100] = "unknown"; int i = 0; - void *tmp; -#ifdef CONFIG_X86_32 - if (boot_params.efi_info.efi_systab_hi || - boot_params.efi_info.efi_memmap_hi) { + if (IS_ENABLED(CONFIG_X86_32) && + (boot_params.efi_info.efi_systab_hi || + boot_params.efi_info.efi_memmap_hi)) { pr_info("Table located above 4GB, disabling EFI.\n"); return; } - efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab; -#else - efi_phys.systab = (efi_system_table_t *) - (boot_params.efi_info.efi_systab | - ((__u64)boot_params.efi_info.efi_systab_hi<<32)); -#endif - if (efi_systab_init(efi_phys.systab)) + efi_systab_phys = boot_params.efi_info.efi_systab | + ((__u64)boot_params.efi_info.efi_systab_hi << 32); + + if (efi_systab_init(efi_systab_phys)) return; efi.config_table = (unsigned long)efi.systab->tables; @@ -506,14 +462,16 @@ void __init efi_init(void) /* * Show what we know for posterity */ - c16 = tmp = early_memremap(efi.systab->fw_vendor, 2); + c16 = early_memremap_ro(efi.systab->fw_vendor, + sizeof(vendor) * sizeof(efi_char16_t)); if (c16) { - for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i) - vendor[i] = *c16++; + for (i = 0; i < sizeof(vendor) - 1 && c16[i]; ++i) + vendor[i] = c16[i]; vendor[i] = '\0'; - } else + early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); + } else { pr_err("Could not map the firmware vendor!\n"); - early_memunmap(tmp, 2); + } pr_info("EFI v%u.%.02u by %s\n", efi.systab->hdr.revision >> 16, @@ -532,19 +490,21 @@ void __init efi_init(void) if (!efi_runtime_supported()) pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n"); - else { - if (efi_runtime_disabled() || efi_runtime_init()) { - efi_memmap_unmap(); - return; - } + + if (!efi_runtime_supported() || efi_runtime_disabled()) { + efi_memmap_unmap(); + return; } + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); efi_clean_memmap(); if (efi_enabled(EFI_DBG)) efi_print_memmap(); } +#if defined(CONFIG_X86_32) || defined(CONFIG_X86_UV) + void __init efi_set_executable(efi_memory_desc_t *md, bool executable) { u64 addr, npages; @@ -609,6 +569,8 @@ void __init old_map_region(efi_memory_desc_t *md) (unsigned long long)md->phys_addr); } +#endif + /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { @@ -647,7 +609,7 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md) size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; - systab = (u64)(unsigned long)efi_phys.systab; + systab = efi_systab_phys; if (md->phys_addr <= systab && systab < end) { systab += md->virt_addr - md->phys_addr; efi.systab = (efi_system_table_t *)(unsigned long)systab; @@ -707,7 +669,7 @@ static inline void *efi_map_next_entry_reverse(void *entry) */ static void *efi_map_next_entry(void *entry) { - if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) { + if (!efi_have_uv1_memmap() && efi_enabled(EFI_64BIT)) { /* * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE * config table feature requires us to map all entries @@ -756,10 +718,19 @@ static bool should_map_region(efi_memory_desc_t *md) return false; /* + * EFI specific purpose memory may be reserved by default + * depending on kernel config and boot options. + */ + if (md->type == EFI_CONVENTIONAL_MEMORY && + efi_soft_reserve_enabled() && + (md->attribute & EFI_MEMORY_SP)) + return false; + + /* * Map all of RAM so that we can access arguments in the 1:1 * mapping when making EFI runtime calls. */ - if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_is_native()) { + if (efi_is_mixed()) { if (md->type == EFI_CONVENTIONAL_MEMORY || md->type == EFI_LOADER_DATA || md->type == EFI_LOADER_CODE) @@ -830,11 +801,11 @@ static void __init kexec_enter_virtual_mode(void) /* * We don't do virtual mode, since we don't do runtime services, on - * non-native EFI. With efi=old_map, we don't do runtime services in + * non-native EFI. With the UV1 memmap, we don't do runtime services in * kexec kernel because in the initial boot something else might * have been mapped at these virtual addresses. */ - if (!efi_is_native() || efi_enabled(EFI_OLD_MEMMAP)) { + if (efi_is_mixed() || efi_have_uv1_memmap()) { efi_memmap_unmap(); clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); return; @@ -889,14 +860,6 @@ static void __init kexec_enter_virtual_mode(void) efi.runtime_version = efi_systab.hdr.revision; efi_native_runtime_setup(); - - efi.set_virtual_address_map = NULL; - - if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) - runtime_code_page_mkexec(); - - /* clean DUMMY object */ - efi_delete_dummy_variable(); #endif } @@ -908,9 +871,9 @@ static void __init kexec_enter_virtual_mode(void) * * The old method which used to update that memory descriptor with the * virtual address obtained from ioremap() is still supported when the - * kernel is booted with efi=old_map on its command line. Same old - * method enabled the runtime services to be called without having to - * thunk back into physical mode for every invocation. + * kernel is booted on SG1 UV1 hardware. Same old method enabled the + * runtime services to be called without having to thunk back into + * physical mode for every invocation. * * The new method does a pagetable switch in a preemption-safe manner * so that we're in a different address space when calling a runtime @@ -933,16 +896,14 @@ static void __init __efi_enter_virtual_mode(void) if (efi_alloc_page_tables()) { pr_err("Failed to allocate EFI page tables\n"); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; + goto err; } efi_merge_regions(); new_memmap = efi_map_regions(&count, &pg_shift); if (!new_memmap) { pr_err("Error reallocating memory, EFI runtime non-functional!\n"); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; + goto err; } pa = __pa(new_memmap); @@ -956,8 +917,7 @@ static void __init __efi_enter_virtual_mode(void) if (efi_memmap_init_late(pa, efi.memmap.desc_size * count)) { pr_err("Failed to remap late EFI memory map\n"); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; + goto err; } if (efi_enabled(EFI_DBG)) { @@ -965,34 +925,22 @@ static void __init __efi_enter_virtual_mode(void) efi_print_memmap(); } - BUG_ON(!efi.systab); + if (WARN_ON(!efi.systab)) + goto err; - if (efi_setup_page_tables(pa, 1 << pg_shift)) { - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; - } + if (efi_setup_page_tables(pa, 1 << pg_shift)) + goto err; efi_sync_low_kernel_mappings(); - if (efi_is_native()) { - status = phys_efi_set_virtual_address_map( - efi.memmap.desc_size * count, - efi.memmap.desc_size, - efi.memmap.desc_version, - (efi_memory_desc_t *)pa); - } else { - status = efi_thunk_set_virtual_address_map( - efi_phys.set_virtual_address_map, - efi.memmap.desc_size * count, - efi.memmap.desc_size, - efi.memmap.desc_version, - (efi_memory_desc_t *)pa); - } - + status = efi_set_virtual_address_map(efi.memmap.desc_size * count, + efi.memmap.desc_size, + efi.memmap.desc_version, + (efi_memory_desc_t *)pa); if (status != EFI_SUCCESS) { - pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n", - status); - panic("EFI call to SetVirtualAddressMap() failed!"); + pr_err("Unable to switch EFI into virtual mode (status=%lx)!\n", + status); + goto err; } efi_free_boot_services(); @@ -1005,13 +953,11 @@ static void __init __efi_enter_virtual_mode(void) */ efi.runtime_version = efi_systab.hdr.revision; - if (efi_is_native()) + if (!efi_is_mixed()) efi_native_runtime_setup(); else efi_thunk_runtime_setup(); - efi.set_virtual_address_map = NULL; - /* * Apply more restrictive page table mapping attributes now that * SVAM() has been called and the firmware has performed all @@ -1021,6 +967,10 @@ static void __init __efi_enter_virtual_mode(void) /* clean DUMMY object */ efi_delete_dummy_variable(); + return; + +err: + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); } void __init efi_enter_virtual_mode(void) @@ -1036,16 +986,16 @@ void __init efi_enter_virtual_mode(void) efi_dump_pagetable(); } -static int __init arch_parse_efi_cmdline(char *str) +bool efi_is_table_address(unsigned long phys_addr) { - if (!str) { - pr_warn("need at least one option\n"); - return -EINVAL; - } + unsigned int i; + + if (phys_addr == EFI_INVALID_TABLE_ADDR) + return false; - if (parse_option_str(str, "old_map")) - set_bit(EFI_OLD_MEMMAP, &efi.flags); + for (i = 0; i < ARRAY_SIZE(efi_tables); i++) + if (*(efi_tables[i]) == phys_addr) + return true; - return 0; + return false; } -early_param("efi", arch_parse_efi_cmdline); diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 9959657127f4..081d466002c9 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -49,7 +49,7 @@ void efi_sync_low_kernel_mappings(void) {} void __init efi_dump_pagetable(void) { #ifdef CONFIG_EFI_PGT_DUMP - ptdump_walk_pgd_level(NULL, swapper_pg_dir); + ptdump_walk_pgd_level(NULL, &init_mm); #endif } @@ -66,9 +66,17 @@ void __init efi_map_region(efi_memory_desc_t *md) void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} -pgd_t * __init efi_call_phys_prolog(void) +efi_status_t efi_call_svam(efi_set_virtual_address_map_t *__efiapi *, + u32, u32, u32, void *); + +efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map) { struct desc_ptr gdt_descr; + efi_status_t status; + unsigned long flags; pgd_t *save_pgd; /* Current pgd is swapper_pg_dir, we'll restore it later: */ @@ -80,14 +88,18 @@ pgd_t * __init efi_call_phys_prolog(void) gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); - return save_pgd; -} + /* Disable interrupts around EFI calls: */ + local_irq_save(flags); + status = efi_call_svam(&efi.systab->runtime->set_virtual_address_map, + memory_map_size, descriptor_size, + descriptor_version, virtual_map); + local_irq_restore(flags); -void __init efi_call_phys_epilog(pgd_t *save_pgd) -{ load_fixmap_gdt(0); load_cr3(save_pgd); __flush_tlb_all(); + + return status; } void __init efi_runtime_update_mappings(void) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 08ce8177c3af..fa8506e76bbe 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -57,142 +57,6 @@ static u64 efi_va = EFI_VA_START; struct efi_scratch efi_scratch; -static void __init early_code_mapping_set_exec(int executable) -{ - efi_memory_desc_t *md; - - if (!(__supported_pte_mask & _PAGE_NX)) - return; - - /* Make EFI service code area executable */ - for_each_efi_memory_desc(md) { - if (md->type == EFI_RUNTIME_SERVICES_CODE || - md->type == EFI_BOOT_SERVICES_CODE) - efi_set_executable(md, executable); - } -} - -pgd_t * __init efi_call_phys_prolog(void) -{ - unsigned long vaddr, addr_pgd, addr_p4d, addr_pud; - pgd_t *save_pgd, *pgd_k, *pgd_efi; - p4d_t *p4d, *p4d_k, *p4d_efi; - pud_t *pud; - - int pgd; - int n_pgds, i, j; - - if (!efi_enabled(EFI_OLD_MEMMAP)) { - efi_switch_mm(&efi_mm); - return efi_mm.pgd; - } - - early_code_mapping_set_exec(1); - - n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); - save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL); - if (!save_pgd) - return NULL; - - /* - * Build 1:1 identity mapping for efi=old_map usage. Note that - * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while - * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical - * address X, the pud_index(X) != pud_index(__va(X)), we can only copy - * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping. - * This means here we can only reuse the PMD tables of the direct mapping. - */ - for (pgd = 0; pgd < n_pgds; pgd++) { - addr_pgd = (unsigned long)(pgd * PGDIR_SIZE); - vaddr = (unsigned long)__va(pgd * PGDIR_SIZE); - pgd_efi = pgd_offset_k(addr_pgd); - save_pgd[pgd] = *pgd_efi; - - p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd); - if (!p4d) { - pr_err("Failed to allocate p4d table!\n"); - goto out; - } - - for (i = 0; i < PTRS_PER_P4D; i++) { - addr_p4d = addr_pgd + i * P4D_SIZE; - p4d_efi = p4d + p4d_index(addr_p4d); - - pud = pud_alloc(&init_mm, p4d_efi, addr_p4d); - if (!pud) { - pr_err("Failed to allocate pud table!\n"); - goto out; - } - - for (j = 0; j < PTRS_PER_PUD; j++) { - addr_pud = addr_p4d + j * PUD_SIZE; - - if (addr_pud > (max_pfn << PAGE_SHIFT)) - break; - - vaddr = (unsigned long)__va(addr_pud); - - pgd_k = pgd_offset_k(vaddr); - p4d_k = p4d_offset(pgd_k, vaddr); - pud[j] = *pud_offset(p4d_k, vaddr); - } - } - pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX; - } - - __flush_tlb_all(); - return save_pgd; -out: - efi_call_phys_epilog(save_pgd); - return NULL; -} - -void __init efi_call_phys_epilog(pgd_t *save_pgd) -{ - /* - * After the lock is released, the original page table is restored. - */ - int pgd_idx, i; - int nr_pgds; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - - if (!efi_enabled(EFI_OLD_MEMMAP)) { - efi_switch_mm(efi_scratch.prev_mm); - return; - } - - nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); - - for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) { - pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE); - set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]); - - if (!pgd_present(*pgd)) - continue; - - for (i = 0; i < PTRS_PER_P4D; i++) { - p4d = p4d_offset(pgd, - pgd_idx * PGDIR_SIZE + i * P4D_SIZE); - - if (!p4d_present(*p4d)) - continue; - - pud = (pud_t *)p4d_page_vaddr(*p4d); - pud_free(&init_mm, pud); - } - - p4d = (p4d_t *)pgd_page_vaddr(*pgd); - p4d_free(&init_mm, p4d); - } - - kfree(save_pgd); - - __flush_tlb_all(); - early_code_mapping_set_exec(0); -} - EXPORT_SYMBOL_GPL(efi_mm); /* @@ -211,7 +75,7 @@ int __init efi_alloc_page_tables(void) pud_t *pud; gfp_t gfp_mask; - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return 0; gfp_mask = GFP_KERNEL | __GFP_ZERO; @@ -252,7 +116,7 @@ void efi_sync_low_kernel_mappings(void) pud_t *pud_k, *pud_efi; pgd_t *efi_pgd = efi_mm.pgd; - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return; /* @@ -346,7 +210,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) unsigned npages; pgd_t *pgd = efi_mm.pgd; - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return 0; /* @@ -373,10 +237,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * as trim_bios_range() will reserve the first page and isolate it away * from memory allocators anyway. */ - pf = _PAGE_RW; - if (sev_active()) - pf |= _PAGE_ENC; - if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, pf)) { pr_err("Failed to create 1:1 mapping for the first page!\n"); return 1; @@ -388,21 +248,22 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * text and allocate a new stack because we can't rely on the * stack pointer being < 4GB. */ - if (!IS_ENABLED(CONFIG_EFI_MIXED) || efi_is_native()) + if (!efi_is_mixed()) return 0; page = alloc_page(GFP_KERNEL|__GFP_DMA32); - if (!page) - panic("Unable to allocate EFI runtime stack < 4GB\n"); + if (!page) { + pr_err("Unable to allocate EFI runtime stack < 4GB\n"); + return 1; + } - efi_scratch.phys_stack = virt_to_phys(page_address(page)); - efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */ + efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */ - npages = (_etext - _text) >> PAGE_SHIFT; + npages = (__end_rodata_aligned - _text) >> PAGE_SHIFT; text = __pa(_text); pfn = text >> PAGE_SHIFT; - pf = _PAGE_RW | _PAGE_ENC; + pf = _PAGE_ENC; if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, pf)) { pr_err("Failed to map kernel text 1:1\n"); return 1; @@ -417,6 +278,22 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) unsigned long pfn; pgd_t *pgd = efi_mm.pgd; + /* + * EFI_RUNTIME_SERVICES_CODE regions typically cover PE/COFF + * executable images in memory that consist of both R-X and + * RW- sections, so we cannot apply read-only or non-exec + * permissions just yet. However, modern EFI systems provide + * a memory attributes table that describes those sections + * with the appropriate restricted permissions, which are + * applied in efi_runtime_update_mappings() below. All other + * regions can be mapped non-executable at this point, with + * the exception of boot services code regions, but those will + * be unmapped again entirely in efi_free_boot_services(). + */ + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_RUNTIME_SERVICES_CODE) + flags |= _PAGE_NX; + if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; @@ -434,7 +311,7 @@ void __init efi_map_region(efi_memory_desc_t *md) unsigned long size = md->num_pages << PAGE_SHIFT; u64 pa = md->phys_addr; - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return old_map_region(md); /* @@ -449,7 +326,7 @@ void __init efi_map_region(efi_memory_desc_t *md) * booting in EFI mixed mode, because even though we may be * running a 64-bit kernel, the firmware may only be 32-bit. */ - if (!efi_is_native () && IS_ENABLED(CONFIG_EFI_MIXED)) { + if (efi_is_mixed()) { md->virt_addr = md->phys_addr; return; } @@ -491,26 +368,6 @@ void __init efi_map_region_fixed(efi_memory_desc_t *md) __map_region(md, md->virt_addr); } -void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size, - u32 type, u64 attribute) -{ - unsigned long last_map_pfn; - - if (type == EFI_MEMORY_MAPPED_IO) - return ioremap(phys_addr, size); - - last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); - if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) { - unsigned long top = last_map_pfn << PAGE_SHIFT; - efi_ioremap(top, size - (top - phys_addr), type, attribute); - } - - if (!(attribute & EFI_MEMORY_WB)) - efi_memory_uc((u64)(unsigned long)__va(phys_addr), size); - - return (void __iomem *)__va(phys_addr); -} - void __init parse_efi_setup(u64 phys_addr, u32 data_len) { efi_setup = phys_addr + sizeof(struct setup_data); @@ -559,7 +416,7 @@ void __init efi_runtime_update_mappings(void) { efi_memory_desc_t *md; - if (efi_enabled(EFI_OLD_MEMMAP)) { + if (efi_have_uv1_memmap()) { if (__supported_pte_mask & _PAGE_NX) runtime_code_page_mkexec(); return; @@ -613,10 +470,10 @@ void __init efi_runtime_update_mappings(void) void __init efi_dump_pagetable(void) { #ifdef CONFIG_EFI_PGT_DUMP - if (efi_enabled(EFI_OLD_MEMMAP)) - ptdump_walk_pgd_level(NULL, swapper_pg_dir); + if (efi_have_uv1_memmap()) + ptdump_walk_pgd_level(NULL, &init_mm); else - ptdump_walk_pgd_level(NULL, efi_mm.pgd); + ptdump_walk_pgd_level(NULL, &efi_mm); #endif } @@ -634,63 +491,74 @@ void efi_switch_mm(struct mm_struct *mm) switch_mm(efi_scratch.prev_mm, mm, NULL); } -#ifdef CONFIG_EFI_MIXED -extern efi_status_t efi64_thunk(u32, ...); - static DEFINE_SPINLOCK(efi_runtime_lock); -#define runtime_service32(func) \ -({ \ - u32 table = (u32)(unsigned long)efi.systab; \ - u32 *rt, *___f; \ - \ - rt = (u32 *)(table + offsetof(efi_system_table_32_t, runtime)); \ - ___f = (u32 *)(*rt + offsetof(efi_runtime_services_32_t, func)); \ - *___f; \ +/* + * DS and ES contain user values. We need to save them. + * The 32-bit EFI code needs a valid DS, ES, and SS. There's no + * need to save the old SS: __KERNEL_DS is always acceptable. + */ +#define __efi_thunk(func, ...) \ +({ \ + efi_runtime_services_32_t *__rt; \ + unsigned short __ds, __es; \ + efi_status_t ____s; \ + \ + __rt = (void *)(unsigned long)efi.systab->mixed_mode.runtime; \ + \ + savesegment(ds, __ds); \ + savesegment(es, __es); \ + \ + loadsegment(ss, __KERNEL_DS); \ + loadsegment(ds, __KERNEL_DS); \ + loadsegment(es, __KERNEL_DS); \ + \ + ____s = efi64_thunk(__rt->func, __VA_ARGS__); \ + \ + loadsegment(ds, __ds); \ + loadsegment(es, __es); \ + \ + ____s ^= (____s & BIT(31)) | (____s & BIT_ULL(31)) << 32; \ + ____s; \ }) /* * Switch to the EFI page tables early so that we can access the 1:1 * runtime services mappings which are not mapped in any other page - * tables. This function must be called before runtime_service32(). + * tables. * * Also, disable interrupts because the IDT points to 64-bit handlers, * which aren't going to function correctly when we switch to 32-bit. */ -#define efi_thunk(f, ...) \ +#define efi_thunk(func...) \ ({ \ efi_status_t __s; \ - u32 __func; \ \ arch_efi_call_virt_setup(); \ \ - __func = runtime_service32(f); \ - __s = efi64_thunk(__func, __VA_ARGS__); \ + __s = __efi_thunk(func); \ \ arch_efi_call_virt_teardown(); \ \ __s; \ }) -efi_status_t efi_thunk_set_virtual_address_map( - void *phys_set_virtual_address_map, - unsigned long memory_map_size, - unsigned long descriptor_size, - u32 descriptor_version, - efi_memory_desc_t *virtual_map) +static efi_status_t __init __no_sanitize_address +efi_thunk_set_virtual_address_map(unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map) { efi_status_t status; unsigned long flags; - u32 func; efi_sync_low_kernel_mappings(); local_irq_save(flags); efi_switch_mm(&efi_mm); - func = (u32)(unsigned long)phys_set_virtual_address_map; - status = efi64_thunk(func, memory_map_size, descriptor_size, - descriptor_version, virtual_map); + status = __efi_thunk(set_virtual_address_map, memory_map_size, + descriptor_size, descriptor_version, virtual_map); efi_switch_mm(efi_scratch.prev_mm); local_irq_restore(flags); @@ -993,8 +861,11 @@ efi_thunk_query_capsule_caps(efi_capsule_header_t **capsules, return EFI_UNSUPPORTED; } -void efi_thunk_runtime_setup(void) +void __init efi_thunk_runtime_setup(void) { + if (!IS_ENABLED(CONFIG_EFI_MIXED)) + return; + efi.get_time = efi_thunk_get_time; efi.set_time = efi_thunk_set_time; efi.get_wakeup_time = efi_thunk_get_wakeup_time; @@ -1010,4 +881,46 @@ void efi_thunk_runtime_setup(void) efi.update_capsule = efi_thunk_update_capsule; efi.query_capsule_caps = efi_thunk_query_capsule_caps; } -#endif /* CONFIG_EFI_MIXED */ + +efi_status_t __init __no_sanitize_address +efi_set_virtual_address_map(unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map) +{ + efi_status_t status; + unsigned long flags; + pgd_t *save_pgd = NULL; + + if (efi_is_mixed()) + return efi_thunk_set_virtual_address_map(memory_map_size, + descriptor_size, + descriptor_version, + virtual_map); + + if (efi_have_uv1_memmap()) { + save_pgd = efi_uv1_memmap_phys_prolog(); + if (!save_pgd) + return EFI_ABORTED; + } else { + efi_switch_mm(&efi_mm); + } + + kernel_fpu_begin(); + + /* Disable interrupts around EFI calls: */ + local_irq_save(flags); + status = efi_call(efi.systab->runtime->set_virtual_address_map, + memory_map_size, descriptor_size, + descriptor_version, virtual_map); + local_irq_restore(flags); + + kernel_fpu_end(); + + if (save_pgd) + efi_uv1_memmap_phys_epilog(save_pgd); + else + efi_switch_mm(efi_scratch.prev_mm); + + return status; +} diff --git a/arch/x86/platform/efi/efi_stub_32.S b/arch/x86/platform/efi/efi_stub_32.S index ab2e91e76894..75c46e7a809f 100644 --- a/arch/x86/platform/efi/efi_stub_32.S +++ b/arch/x86/platform/efi/efi_stub_32.S @@ -7,118 +7,43 @@ */ #include <linux/linkage.h> +#include <linux/init.h> #include <asm/page_types.h> -/* - * efi_call_phys(void *, ...) is a function with variable parameters. - * All the callers of this function assure that all the parameters are 4-bytes. - */ - -/* - * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save. - * So we'd better save all of them at the beginning of this function and restore - * at the end no matter how many we use, because we can not assure EFI runtime - * service functions will comply with gcc calling convention, too. - */ + __INIT +SYM_FUNC_START(efi_call_svam) + push 8(%esp) + push 8(%esp) + push %ecx + push %edx -.text -ENTRY(efi_call_phys) /* - * 0. The function can only be called in Linux kernel. So CS has been - * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found - * the values of these registers are the same. And, the corresponding - * GDT entries are identical. So I will do nothing about segment reg - * and GDT, but change GDT base register in prolog and epilog. - */ - - /* - * 1. Now I am running with EIP = <physical address> + PAGE_OFFSET. - * But to make it smoothly switch from virtual mode to flat mode. - * The mapping of lower virtual memory has been created in prolog and - * epilog. + * Switch to the flat mapped alias of this routine, by jumping to the + * address of label '1' after subtracting PAGE_OFFSET from it. */ movl $1f, %edx subl $__PAGE_OFFSET, %edx jmp *%edx 1: - /* - * 2. Now on the top of stack is the return - * address in the caller of efi_call_phys(), then parameter 1, - * parameter 2, ..., param n. To make things easy, we save the return - * address of efi_call_phys in a global variable. - */ - popl %edx - movl %edx, saved_return_addr - /* get the function pointer into ECX*/ - popl %ecx - movl %ecx, efi_rt_function_ptr - movl $2f, %edx - subl $__PAGE_OFFSET, %edx - pushl %edx - - /* - * 3. Clear PG bit in %CR0. - */ + /* disable paging */ movl %cr0, %edx andl $0x7fffffff, %edx movl %edx, %cr0 - jmp 1f -1: - /* - * 4. Adjust stack pointer. - */ + /* convert the stack pointer to a flat mapped address */ subl $__PAGE_OFFSET, %esp - /* - * 5. Call the physical function. - */ - jmp *%ecx + /* call the EFI routine */ + call *(%eax) -2: - /* - * 6. After EFI runtime service returns, control will return to - * following instruction. We'd better readjust stack pointer first. - */ - addl $__PAGE_OFFSET, %esp + /* convert ESP back to a kernel VA, and pop the outgoing args */ + addl $__PAGE_OFFSET + 16, %esp - /* - * 7. Restore PG bit - */ + /* re-enable paging */ movl %cr0, %edx orl $0x80000000, %edx movl %edx, %cr0 - jmp 1f -1: - /* - * 8. Now restore the virtual mode from flat mode by - * adding EIP with PAGE_OFFSET. - */ - movl $1f, %edx - jmp *%edx -1: - - /* - * 9. Balance the stack. And because EAX contain the return value, - * we'd better not clobber it. - */ - leal efi_rt_function_ptr, %edx - movl (%edx), %ecx - pushl %ecx - /* - * 10. Push the saved return address onto the stack and return. - */ - leal saved_return_addr, %edx - movl (%edx), %ecx - pushl %ecx ret -ENDPROC(efi_call_phys) -.previous - -.data -saved_return_addr: - .long 0 -efi_rt_function_ptr: - .long 0 +SYM_FUNC_END(efi_call_svam) diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 74628ec78f29..15da118f04f0 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -8,41 +8,12 @@ */ #include <linux/linkage.h> -#include <asm/segment.h> -#include <asm/msr.h> -#include <asm/processor-flags.h> -#include <asm/page_types.h> +#include <asm/nospec-branch.h> -#define SAVE_XMM \ - mov %rsp, %rax; \ - subq $0x70, %rsp; \ - and $~0xf, %rsp; \ - mov %rax, (%rsp); \ - mov %cr0, %rax; \ - clts; \ - mov %rax, 0x8(%rsp); \ - movaps %xmm0, 0x60(%rsp); \ - movaps %xmm1, 0x50(%rsp); \ - movaps %xmm2, 0x40(%rsp); \ - movaps %xmm3, 0x30(%rsp); \ - movaps %xmm4, 0x20(%rsp); \ - movaps %xmm5, 0x10(%rsp) - -#define RESTORE_XMM \ - movaps 0x60(%rsp), %xmm0; \ - movaps 0x50(%rsp), %xmm1; \ - movaps 0x40(%rsp), %xmm2; \ - movaps 0x30(%rsp), %xmm3; \ - movaps 0x20(%rsp), %xmm4; \ - movaps 0x10(%rsp), %xmm5; \ - mov 0x8(%rsp), %rsi; \ - mov %rsi, %cr0; \ - mov (%rsp), %rsp - -ENTRY(efi_call) +SYM_FUNC_START(__efi_call) pushq %rbp movq %rsp, %rbp - SAVE_XMM + and $~0xf, %rsp mov 16(%rbp), %rax subq $48, %rsp mov %r9, 32(%rsp) @@ -50,9 +21,7 @@ ENTRY(efi_call) mov %r8, %r9 mov %rcx, %r8 mov %rsi, %rcx - call *%rdi - addq $48, %rsp - RESTORE_XMM - popq %rbp + CALL_NOSPEC %rdi + leave ret -ENDPROC(efi_call) +SYM_FUNC_END(__efi_call) diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 46c58b08739c..26f0da238c1c 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -25,15 +25,16 @@ .text .code64 -ENTRY(efi64_thunk) +SYM_CODE_START(__efi64_thunk) push %rbp push %rbx /* * Switch to 1:1 mapped 32-bit stack pointer. */ - movq %rsp, efi_saved_sp(%rip) + movq %rsp, %rax movq efi_scratch(%rip), %rsp + push %rax /* * Calculate the physical address of the kernel text. @@ -41,113 +42,31 @@ ENTRY(efi64_thunk) movq $__START_KERNEL_map, %rax subq phys_base(%rip), %rax - /* - * Push some physical addresses onto the stack. This is easier - * to do now in a code64 section while the assembler can address - * 64-bit values. Note that all the addresses on the stack are - * 32-bit. - */ - subq $16, %rsp - leaq efi_exit32(%rip), %rbx - subq %rax, %rbx - movl %ebx, 8(%rsp) - - leaq __efi64_thunk(%rip), %rbx + leaq 1f(%rip), %rbp + leaq 2f(%rip), %rbx + subq %rax, %rbp subq %rax, %rbx - call *%rbx - - movq efi_saved_sp(%rip), %rsp - pop %rbx - pop %rbp - retq -ENDPROC(efi64_thunk) -/* - * We run this function from the 1:1 mapping. - * - * This function must be invoked with a 1:1 mapped stack. - */ -ENTRY(__efi64_thunk) - movl %ds, %eax - push %rax - movl %es, %eax - push %rax - movl %ss, %eax - push %rax - - subq $32, %rsp - movl %esi, 0x0(%rsp) - movl %edx, 0x4(%rsp) - movl %ecx, 0x8(%rsp) - movq %r8, %rsi - movl %esi, 0xc(%rsp) - movq %r9, %rsi - movl %esi, 0x10(%rsp) - - leaq 1f(%rip), %rbx - movq %rbx, func_rt_ptr(%rip) + subq $28, %rsp + movl %ebx, 0x0(%rsp) /* return address */ + movl %esi, 0x4(%rsp) + movl %edx, 0x8(%rsp) + movl %ecx, 0xc(%rsp) + movl %r8d, 0x10(%rsp) + movl %r9d, 0x14(%rsp) /* Switch to 32-bit descriptor */ pushq $__KERNEL32_CS - leaq efi_enter32(%rip), %rax - pushq %rax + pushq %rdi /* EFI runtime service address */ lretq -1: addq $32, %rsp - +1: movq 24(%rsp), %rsp pop %rbx - movl %ebx, %ss - pop %rbx - movl %ebx, %es - pop %rbx - movl %ebx, %ds - - /* - * Convert 32-bit status code into 64-bit. - */ - test %rax, %rax - jz 1f - movl %eax, %ecx - andl $0x0fffffff, %ecx - andl $0xf0000000, %eax - shl $32, %rax - or %rcx, %rax -1: - ret -ENDPROC(__efi64_thunk) - -ENTRY(efi_exit32) - movq func_rt_ptr(%rip), %rax - push %rax - mov %rdi, %rax - ret -ENDPROC(efi_exit32) + pop %rbp + retq .code32 -/* - * EFI service pointer must be in %edi. - * - * The stack should represent the 32-bit calling convention. - */ -ENTRY(efi_enter32) - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es - movl %eax, %ss - - call *%edi - - /* We must preserve return value */ - movl %eax, %edi - - movl 72(%esp), %eax - pushl $__KERNEL_CS - pushl %eax - +2: pushl $__KERNEL_CS + pushl %ebp lret -ENDPROC(efi_enter32) - - .data - .balign 8 -func_rt_ptr: .quad 0 -efi_saved_sp: .quad 0 +SYM_CODE_END(__efi64_thunk) diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 3b9fd679cea9..88d32c06cffa 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -16,6 +16,7 @@ #include <asm/efi.h> #include <asm/uv/uv.h> #include <asm/cpu_device_id.h> +#include <asm/realmode.h> #include <asm/reboot.h> #define EFI_MIN_RESERVE 5120 @@ -243,7 +244,7 @@ EXPORT_SYMBOL_GPL(efi_query_variable_store); */ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) { - phys_addr_t new_phys, new_size; + struct efi_memory_map_data data = { 0 }; struct efi_mem_range mr; efi_memory_desc_t md; int num_entries; @@ -260,10 +261,6 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } - /* No need to reserve regions that will never be freed. */ - if (md.attribute & EFI_MEMORY_RUNTIME) - return; - size += addr % EFI_PAGE_SIZE; size = round_up(size, EFI_PAGE_SIZE); addr = round_down(addr, EFI_PAGE_SIZE); @@ -275,24 +272,23 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) num_entries = efi_memmap_split_count(&md, &mr.range); num_entries += efi.memmap.nr_map; - new_size = efi.memmap.desc_size * num_entries; - - new_phys = efi_memmap_alloc(num_entries); - if (!new_phys) { + if (efi_memmap_alloc(num_entries, &data) != 0) { pr_err("Could not allocate boot services memmap\n"); return; } - new = early_memremap(new_phys, new_size); + new = early_memremap(data.phys_map, data.size); if (!new) { pr_err("Failed to map new boot services memmap\n"); return; } efi_memmap_insert(&efi.memmap, new, &mr); - early_memunmap(new, new_size); + early_memunmap(new, data.size); - efi_memmap_install(new_phys, num_entries); + efi_memmap_install(&data); + e820__range_update(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__update_table(e820_table); } /* @@ -320,6 +316,9 @@ void __init efi_reserve_boot_services(void) { efi_memory_desc_t *md; + if (!efi_enabled(EFI_MEMMAP)) + return; + for_each_efi_memory_desc(md) { u64 start = md->phys_addr; u64 size = md->num_pages << EFI_PAGE_SHIFT; @@ -383,10 +382,10 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md) /* * To Do: Remove this check after adding functionality to unmap EFI boot - * services code/data regions from direct mapping area because - * "efi=old_map" maps EFI regions in swapper_pg_dir. + * services code/data regions from direct mapping area because the UV1 + * memory map maps EFI regions in swapper_pg_dir. */ - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return; /* @@ -394,7 +393,7 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md) * EFI runtime calls, hence don't unmap EFI boot services code/data * regions. */ - if (!efi_is_native()) + if (efi_is_mixed()) return; if (kernel_unmap_pages_in_pgd(pgd, pa, md->num_pages)) @@ -406,7 +405,7 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md) void __init efi_free_boot_services(void) { - phys_addr_t new_phys, new_size; + struct efi_memory_map_data data = { 0 }; efi_memory_desc_t *md; int num_entries = 0; void *new, *new_md; @@ -461,14 +460,12 @@ void __init efi_free_boot_services(void) if (!num_entries) return; - new_size = efi.memmap.desc_size * num_entries; - new_phys = efi_memmap_alloc(num_entries); - if (!new_phys) { + if (efi_memmap_alloc(num_entries, &data) != 0) { pr_err("Failed to allocate new EFI memmap\n"); return; } - new = memremap(new_phys, new_size, MEMREMAP_WB); + new = memremap(data.phys_map, data.size, MEMREMAP_WB); if (!new) { pr_err("Failed to map new EFI memmap\n"); return; @@ -492,7 +489,7 @@ void __init efi_free_boot_services(void) memunmap(new); - if (efi_memmap_install(new_phys, num_entries)) { + if (efi_memmap_install(&data) != 0) { pr_err("Could not install new EFI memmap\n"); return; } @@ -557,7 +554,7 @@ out: return ret; } -static const struct dmi_system_id sgi_uv1_dmi[] = { +static const struct dmi_system_id sgi_uv1_dmi[] __initconst = { { NULL, "SGI UV1", { DMI_MATCH(DMI_PRODUCT_NAME, "Stoutland Platform"), DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), @@ -580,8 +577,15 @@ void __init efi_apply_memmap_quirks(void) } /* UV2+ BIOS has a fix for this issue. UV1 still needs the quirk. */ - if (dmi_check_system(sgi_uv1_dmi)) - set_bit(EFI_OLD_MEMMAP, &efi.flags); + if (dmi_check_system(sgi_uv1_dmi)) { + if (IS_ENABLED(CONFIG_X86_UV)) { + set_bit(EFI_UV1_MEMMAP, &efi.flags); + } else { + pr_warn("EFI runtime disabled, needs CONFIG_X86_UV=y on UV1\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + efi_memmap_unmap(); + } + } } /* @@ -719,7 +723,7 @@ void efi_recover_from_page_fault(unsigned long phys_addr) /* * Make sure that an efi runtime service caused the page fault. * "efi_mm" cannot be used to check if the page fault had occurred - * in the firmware context because efi=old_map doesn't use efi_pgd. + * in the firmware context because the UV1 memmap doesn't use efi_pgd. */ if (efi_rts_work.efi_rts_id == EFI_NONE) return; diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c index 44d1f884c3d3..139738bbdd36 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c @@ -6,21 +6,31 @@ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> */ -#include <linux/gpio.h> -#include <linux/platform_data/tc35876x.h> +#include <linux/gpio/machine.h> #include <asm/intel-mid.h> +static struct gpiod_lookup_table tc35876x_gpio_table = { + .dev_id = "i2c_disp_brig", + .table = { + GPIO_LOOKUP("0000:00:0c.0", -1, "bridge-reset", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("0000:00:0c.0", -1, "bl-en", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("0000:00:0c.0", -1, "vadd", GPIO_ACTIVE_HIGH), + { }, + }, +}; + /*tc35876x DSI_LVDS bridge chip and panel platform data*/ static void *tc35876x_platform_data(void *data) { - static struct tc35876x_platform_data pdata; + struct gpiod_lookup_table *table = &tc35876x_gpio_table; + struct gpiod_lookup *lookup = table->table; - /* gpio pins set to -1 will not be used by the driver */ - pdata.gpio_bridge_reset = get_gpio_by_name("LCMB_RXEN"); - pdata.gpio_panel_bl_en = get_gpio_by_name("6S6P_BL_EN"); - pdata.gpio_panel_vadd = get_gpio_by_name("EN_VREG_LCD_V3P3"); + lookup[0].chip_hwnum = get_gpio_by_name("LCMB_RXEN"); + lookup[1].chip_hwnum = get_gpio_by_name("6S6P_BL_EN"); + lookup[2].chip_hwnum = get_gpio_by_name("EN_VREG_LCD_V3P3"); + gpiod_add_lookup_table(table); - return &pdata; + return NULL; } static const struct devs_id tc35876x_dev_id __initconst = { diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index 6dd25dc5f027..e9d97d52475e 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -29,6 +29,8 @@ #include <asm/cpu_device_id.h> #include <asm/imr.h> #include <asm/iosf_mbi.h> +#include <asm/io.h> + #include <linux/debugfs.h> #include <linux/init.h> #include <linux/mm.h> diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c index 42f879b75f9b..4307830e1b6f 100644 --- a/arch/x86/platform/intel-quark/imr_selftest.c +++ b/arch/x86/platform/intel-quark/imr_selftest.c @@ -14,6 +14,8 @@ #include <asm-generic/sections.h> #include <asm/cpu_device_id.h> #include <asm/imr.h> +#include <asm/io.h> + #include <linux/init.h> #include <linux/mm.h> #include <linux/types.h> diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index 2e796b54cbde..9e2444500428 100644 --- a/arch/x86/platform/intel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -17,6 +17,7 @@ #include <linux/debugfs.h> #include <linux/capability.h> #include <linux/pm_qos.h> +#include <linux/wait.h> #include <asm/iosf_mbi.h> @@ -201,23 +202,45 @@ EXPORT_SYMBOL(iosf_mbi_available); #define PUNIT_SEMAPHORE_BIT BIT(0) #define PUNIT_SEMAPHORE_ACQUIRE BIT(1) -static DEFINE_MUTEX(iosf_mbi_punit_mutex); -static DEFINE_MUTEX(iosf_mbi_block_punit_i2c_access_count_mutex); +static DEFINE_MUTEX(iosf_mbi_pmic_access_mutex); static BLOCKING_NOTIFIER_HEAD(iosf_mbi_pmic_bus_access_notifier); -static u32 iosf_mbi_block_punit_i2c_access_count; +static DECLARE_WAIT_QUEUE_HEAD(iosf_mbi_pmic_access_waitq); +static u32 iosf_mbi_pmic_punit_access_count; +static u32 iosf_mbi_pmic_i2c_access_count; static u32 iosf_mbi_sem_address; static unsigned long iosf_mbi_sem_acquired; static struct pm_qos_request iosf_mbi_pm_qos; void iosf_mbi_punit_acquire(void) { - mutex_lock(&iosf_mbi_punit_mutex); + /* Wait for any I2C PMIC accesses from in kernel drivers to finish. */ + mutex_lock(&iosf_mbi_pmic_access_mutex); + while (iosf_mbi_pmic_i2c_access_count != 0) { + mutex_unlock(&iosf_mbi_pmic_access_mutex); + wait_event(iosf_mbi_pmic_access_waitq, + iosf_mbi_pmic_i2c_access_count == 0); + mutex_lock(&iosf_mbi_pmic_access_mutex); + } + /* + * We do not need to do anything to allow the PUNIT to safely access + * the PMIC, other then block in kernel accesses to the PMIC. + */ + iosf_mbi_pmic_punit_access_count++; + mutex_unlock(&iosf_mbi_pmic_access_mutex); } EXPORT_SYMBOL(iosf_mbi_punit_acquire); void iosf_mbi_punit_release(void) { - mutex_unlock(&iosf_mbi_punit_mutex); + bool do_wakeup; + + mutex_lock(&iosf_mbi_pmic_access_mutex); + iosf_mbi_pmic_punit_access_count--; + do_wakeup = iosf_mbi_pmic_punit_access_count == 0; + mutex_unlock(&iosf_mbi_pmic_access_mutex); + + if (do_wakeup) + wake_up(&iosf_mbi_pmic_access_waitq); } EXPORT_SYMBOL(iosf_mbi_punit_release); @@ -256,34 +279,32 @@ static void iosf_mbi_reset_semaphore(void) * already blocked P-Unit accesses because it wants them blocked over multiple * i2c-transfers, for e.g. read-modify-write of an I2C client register. * - * The P-Unit accesses already being blocked is tracked through the - * iosf_mbi_block_punit_i2c_access_count variable which is protected by the - * iosf_mbi_block_punit_i2c_access_count_mutex this mutex is hold for the - * entire duration of the function. - * - * If access is not blocked yet, this function takes the following steps: + * To allow safe PMIC i2c bus accesses this function takes the following steps: * * 1) Some code sends request to the P-Unit which make it access the PMIC * I2C bus. Testing has shown that the P-Unit does not check its internal * PMIC bus semaphore for these requests. Callers of these requests call * iosf_mbi_punit_acquire()/_release() around their P-Unit accesses, these - * functions lock/unlock the iosf_mbi_punit_mutex. - * As the first step we lock the iosf_mbi_punit_mutex, to wait for any in - * flight requests to finish and to block any new requests. + * functions increase/decrease iosf_mbi_pmic_punit_access_count, so first + * we wait for iosf_mbi_pmic_punit_access_count to become 0. + * + * 2) Check iosf_mbi_pmic_i2c_access_count, if access has already + * been blocked by another caller, we only need to increment + * iosf_mbi_pmic_i2c_access_count and we can skip the other steps. * - * 2) Some code makes such P-Unit requests from atomic contexts where it + * 3) Some code makes such P-Unit requests from atomic contexts where it * cannot call iosf_mbi_punit_acquire() as that may sleep. * As the second step we call a notifier chain which allows any code * needing P-Unit resources from atomic context to acquire them before * we take control over the PMIC I2C bus. * - * 3) When CPU cores enter C6 or C7 the P-Unit needs to talk to the PMIC + * 4) When CPU cores enter C6 or C7 the P-Unit needs to talk to the PMIC * if this happens while the kernel itself is accessing the PMIC I2C bus * the SoC hangs. * As the third step we call pm_qos_update_request() to disallow the CPU * to enter C6 or C7. * - * 4) The P-Unit has a PMIC bus semaphore which we can request to stop + * 5) The P-Unit has a PMIC bus semaphore which we can request to stop * autonomous P-Unit tasks from accessing the PMIC I2C bus while we hold it. * As the fourth and final step we request this semaphore and wait for our * request to be acknowledged. @@ -297,12 +318,18 @@ int iosf_mbi_block_punit_i2c_access(void) if (WARN_ON(!mbi_pdev || !iosf_mbi_sem_address)) return -ENXIO; - mutex_lock(&iosf_mbi_block_punit_i2c_access_count_mutex); + mutex_lock(&iosf_mbi_pmic_access_mutex); - if (iosf_mbi_block_punit_i2c_access_count > 0) + while (iosf_mbi_pmic_punit_access_count != 0) { + mutex_unlock(&iosf_mbi_pmic_access_mutex); + wait_event(iosf_mbi_pmic_access_waitq, + iosf_mbi_pmic_punit_access_count == 0); + mutex_lock(&iosf_mbi_pmic_access_mutex); + } + + if (iosf_mbi_pmic_i2c_access_count > 0) goto success; - mutex_lock(&iosf_mbi_punit_mutex); blocking_notifier_call_chain(&iosf_mbi_pmic_bus_access_notifier, MBI_PMIC_BUS_ACCESS_BEGIN, NULL); @@ -330,10 +357,6 @@ int iosf_mbi_block_punit_i2c_access(void) iosf_mbi_sem_acquired = jiffies; dev_dbg(&mbi_pdev->dev, "P-Unit semaphore acquired after %ums\n", jiffies_to_msecs(jiffies - start)); - /* - * Success, keep iosf_mbi_punit_mutex locked till - * iosf_mbi_unblock_punit_i2c_access() gets called. - */ goto success; } @@ -344,15 +367,13 @@ int iosf_mbi_block_punit_i2c_access(void) dev_err(&mbi_pdev->dev, "Error P-Unit semaphore timed out, resetting\n"); error: iosf_mbi_reset_semaphore(); - mutex_unlock(&iosf_mbi_punit_mutex); - if (!iosf_mbi_get_sem(&sem)) dev_err(&mbi_pdev->dev, "P-Unit semaphore: %d\n", sem); success: if (!WARN_ON(ret)) - iosf_mbi_block_punit_i2c_access_count++; + iosf_mbi_pmic_i2c_access_count++; - mutex_unlock(&iosf_mbi_block_punit_i2c_access_count_mutex); + mutex_unlock(&iosf_mbi_pmic_access_mutex); return ret; } @@ -360,17 +381,20 @@ EXPORT_SYMBOL(iosf_mbi_block_punit_i2c_access); void iosf_mbi_unblock_punit_i2c_access(void) { - mutex_lock(&iosf_mbi_block_punit_i2c_access_count_mutex); + bool do_wakeup = false; - iosf_mbi_block_punit_i2c_access_count--; - if (iosf_mbi_block_punit_i2c_access_count == 0) { + mutex_lock(&iosf_mbi_pmic_access_mutex); + iosf_mbi_pmic_i2c_access_count--; + if (iosf_mbi_pmic_i2c_access_count == 0) { iosf_mbi_reset_semaphore(); - mutex_unlock(&iosf_mbi_punit_mutex); dev_dbg(&mbi_pdev->dev, "punit semaphore held for %ums\n", jiffies_to_msecs(jiffies - iosf_mbi_sem_acquired)); + do_wakeup = true; } + mutex_unlock(&iosf_mbi_pmic_access_mutex); - mutex_unlock(&iosf_mbi_block_punit_i2c_access_count_mutex); + if (do_wakeup) + wake_up(&iosf_mbi_pmic_access_waitq); } EXPORT_SYMBOL(iosf_mbi_unblock_punit_i2c_access); @@ -379,10 +403,10 @@ int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb) int ret; /* Wait for the bus to go inactive before registering */ - mutex_lock(&iosf_mbi_punit_mutex); + iosf_mbi_punit_acquire(); ret = blocking_notifier_chain_register( &iosf_mbi_pmic_bus_access_notifier, nb); - mutex_unlock(&iosf_mbi_punit_mutex); + iosf_mbi_punit_release(); return ret; } @@ -403,9 +427,9 @@ int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb) int ret; /* Wait for the bus to go inactive before unregistering */ - mutex_lock(&iosf_mbi_punit_mutex); + iosf_mbi_punit_acquire(); ret = iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(nb); - mutex_unlock(&iosf_mbi_punit_mutex); + iosf_mbi_punit_release(); return ret; } @@ -413,7 +437,7 @@ EXPORT_SYMBOL(iosf_mbi_unregister_pmic_bus_access_notifier); void iosf_mbi_assert_punit_acquired(void) { - WARN_ON(!mutex_is_locked(&iosf_mbi_punit_mutex)); + WARN_ON(iosf_mbi_pmic_punit_access_count == 0); } EXPORT_SYMBOL(iosf_mbi_assert_punit_acquired); diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c index e1a32062a375..f067ac780ba7 100644 --- a/arch/x86/platform/olpc/olpc-xo1-pm.c +++ b/arch/x86/platform/olpc/olpc-xo1-pm.c @@ -12,7 +12,6 @@ #include <linux/platform_device.h> #include <linux/export.h> #include <linux/pm.h> -#include <linux/mfd/core.h> #include <linux/suspend.h> #include <linux/olpc-ec.h> @@ -120,16 +119,11 @@ static const struct platform_suspend_ops xo1_suspend_ops = { static int xo1_pm_probe(struct platform_device *pdev) { struct resource *res; - int err; /* don't run on non-XOs */ if (!machine_is_olpc()) return -ENODEV; - err = mfd_cell_enable(pdev); - if (err) - return err; - res = platform_get_resource(pdev, IORESOURCE_IO, 0); if (!res) { dev_err(&pdev->dev, "can't fetch device resource info\n"); @@ -152,8 +146,6 @@ static int xo1_pm_probe(struct platform_device *pdev) static int xo1_pm_remove(struct platform_device *pdev) { - mfd_cell_disable(pdev); - if (strcmp(pdev->name, "cs5535-pms") == 0) pms_base = 0; else if (strcmp(pdev->name, "olpc-xo1-pm-acpi") == 0) diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c index 25ce1b3b0732..933dd4fe3a97 100644 --- a/arch/x86/platform/olpc/olpc-xo1-sci.c +++ b/arch/x86/platform/olpc/olpc-xo1-sci.c @@ -15,7 +15,6 @@ #include <linux/platform_device.h> #include <linux/pm.h> #include <linux/pm_wakeup.h> -#include <linux/mfd/core.h> #include <linux/power_supply.h> #include <linux/suspend.h> #include <linux/workqueue.h> @@ -157,6 +156,12 @@ static ssize_t lid_wake_mode_set(struct device *dev, static DEVICE_ATTR(lid_wake_mode, S_IWUSR | S_IRUGO, lid_wake_mode_show, lid_wake_mode_set); +static struct attribute *lid_attrs[] = { + &dev_attr_lid_wake_mode.attr, + NULL, +}; +ATTRIBUTE_GROUPS(lid); + /* * Process all items in the EC's SCI queue. * @@ -510,17 +515,8 @@ static int setup_lid_switch(struct platform_device *pdev) goto err_register; } - r = device_create_file(&lid_switch_idev->dev, &dev_attr_lid_wake_mode); - if (r) { - dev_err(&pdev->dev, "failed to create wake mode attr: %d\n", r); - goto err_create_attr; - } - return 0; -err_create_attr: - input_unregister_device(lid_switch_idev); - lid_switch_idev = NULL; err_register: input_free_device(lid_switch_idev); return r; @@ -528,7 +524,6 @@ err_register: static void free_lid_switch(void) { - device_remove_file(&lid_switch_idev->dev, &dev_attr_lid_wake_mode); input_unregister_device(lid_switch_idev); } @@ -541,10 +536,6 @@ static int xo1_sci_probe(struct platform_device *pdev) if (!machine_is_olpc()) return -ENODEV; - r = mfd_cell_enable(pdev); - if (r) - return r; - res = platform_get_resource(pdev, IORESOURCE_IO, 0); if (!res) { dev_err(&pdev->dev, "can't fetch device resource info\n"); @@ -609,7 +600,6 @@ err_ebook: static int xo1_sci_remove(struct platform_device *pdev) { - mfd_cell_disable(pdev); free_irq(sci_irq, pdev); cancel_work_sync(&sci_work); free_ec_sci(); @@ -624,6 +614,7 @@ static int xo1_sci_remove(struct platform_device *pdev) static struct platform_driver xo1_sci_driver = { .driver = { .name = "olpc-xo1-sci-acpi", + .dev_groups = lid_groups, }, .probe = xo1_sci_probe, .remove = xo1_sci_remove, diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index 6d193bb36021..089413cd944e 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -39,7 +39,7 @@ static int set_lid_wake_behavior(bool wake_on_close) status = acpi_execute_simple_method(NULL, "\\_SB.PCI0.LID.LIDW", wake_on_close); if (ACPI_FAILURE(status)) { - pr_warning(PFX "failed to set lid behavior\n"); + pr_warn(PFX "failed to set lid behavior\n"); return 1; } diff --git a/arch/x86/platform/olpc/xo1-wakeup.S b/arch/x86/platform/olpc/xo1-wakeup.S index 5fee3a2c2fd4..75f4faff8468 100644 --- a/arch/x86/platform/olpc/xo1-wakeup.S +++ b/arch/x86/platform/olpc/xo1-wakeup.S @@ -90,7 +90,7 @@ restore_registers: ret -ENTRY(do_olpc_suspend_lowlevel) +SYM_CODE_START(do_olpc_suspend_lowlevel) call save_processor_state call save_registers @@ -110,6 +110,7 @@ ret_point: call restore_registers call restore_processor_state ret +SYM_CODE_END(do_olpc_suspend_lowlevel) .data saved_gdt: .long 0,0 diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index 1f8825bbaffb..43b4d864817e 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -50,7 +50,7 @@ #define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) #define PVH_CANARY_SEL (PVH_GDT_ENTRY_CANARY * 8) -ENTRY(pvh_start_xen) +SYM_CODE_START_LOCAL(pvh_start_xen) cld lgdt (_pa(gdt)) @@ -146,15 +146,16 @@ ENTRY(pvh_start_xen) ljmp $PVH_CS_SEL, $_pa(startup_32) #endif -END(pvh_start_xen) +SYM_CODE_END(pvh_start_xen) .section ".init.data","aw" .balign 8 -gdt: +SYM_DATA_START_LOCAL(gdt) .word gdt_end - gdt_start .long _pa(gdt_start) .word 0 -gdt_start: +SYM_DATA_END(gdt) +SYM_DATA_START_LOCAL(gdt_start) .quad 0x0000000000000000 /* NULL descriptor */ #ifdef CONFIG_X86_64 .quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* PVH_CS_SEL */ @@ -163,15 +164,14 @@ gdt_start: #endif .quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */ .quad GDT_ENTRY(0x4090, 0, 0x18) /* PVH_CANARY_SEL */ -gdt_end: +SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end) .balign 16 -canary: - .fill 48, 1, 0 +SYM_DATA_LOCAL(canary, .fill 48, 1, 0) -early_stack: +SYM_DATA_START_LOCAL(early_stack) .fill BOOT_STACK_SIZE, 1, 0 -early_stack_end: +SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end) ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY, _ASM_PTR (pvh_start_xen - __START_KERNEL_map)) diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c index bf6016f8db4e..6259563760f9 100644 --- a/arch/x86/platform/sfi/sfi.c +++ b/arch/x86/platform/sfi/sfi.c @@ -26,8 +26,7 @@ static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; static void __init mp_sfi_register_lapic(u8 id) { if (MAX_LOCAL_APIC - id <= 0) { - pr_warning("Processor #%d invalid (max %d)\n", - id, MAX_LOCAL_APIC); + pr_warn("Processor #%d invalid (max %d)\n", id, MAX_LOCAL_APIC); return; } diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 7c69652ffeea..607f58147311 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -14,6 +14,8 @@ #include <asm/uv/bios.h> #include <asm/uv/uv_hub.h> +unsigned long uv_systab_phys __ro_after_init = EFI_INVALID_TABLE_ADDR; + struct uv_systab *uv_systab; static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, @@ -29,13 +31,16 @@ static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, return BIOS_STATUS_UNIMPLEMENTED; /* - * If EFI_OLD_MEMMAP is set, we need to fall back to using our old EFI + * If EFI_UV1_MEMMAP is set, we need to fall back to using our old EFI * callback method, which uses efi_call() directly, with the kernel page tables: */ - if (unlikely(efi_enabled(EFI_OLD_MEMMAP))) + if (unlikely(efi_enabled(EFI_UV1_MEMMAP))) { + kernel_fpu_begin(); ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5); - else + kernel_fpu_end(); + } else { ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5); + } return ret; } @@ -182,20 +187,20 @@ int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus) } EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target); -void uv_bios_init(void) +int uv_bios_init(void) { uv_systab = NULL; - if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || - !efi.uv_systab || efi_runtime_disabled()) { + if ((uv_systab_phys == EFI_INVALID_TABLE_ADDR) || + !uv_systab_phys || efi_runtime_disabled()) { pr_crit("UV: UVsystab: missing\n"); - return; + return -EEXIST; } - uv_systab = ioremap(efi.uv_systab, sizeof(struct uv_systab)); + uv_systab = ioremap(uv_systab_phys, sizeof(struct uv_systab)); if (!uv_systab || strncmp(uv_systab->signature, UV_SYSTAB_SIG, 4)) { pr_err("UV: UVsystab: bad signature!\n"); iounmap(uv_systab); - return; + return -EINVAL; } /* Starting with UV4 the UV systab size is variable */ @@ -203,11 +208,172 @@ void uv_bios_init(void) int size = uv_systab->size; iounmap(uv_systab); - uv_systab = ioremap(efi.uv_systab, size); + uv_systab = ioremap(uv_systab_phys, size); if (!uv_systab) { pr_err("UV: UVsystab: ioremap(%d) failed!\n", size); - return; + return -EFAULT; } } pr_info("UV: UVsystab: Revision:%x\n", uv_systab->revision); + return 0; +} + +static void __init early_code_mapping_set_exec(int executable) +{ + efi_memory_desc_t *md; + + if (!(__supported_pte_mask & _PAGE_NX)) + return; + + /* Make EFI service code area executable */ + for_each_efi_memory_desc(md) { + if (md->type == EFI_RUNTIME_SERVICES_CODE || + md->type == EFI_BOOT_SERVICES_CODE) + efi_set_executable(md, executable); + } +} + +void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd) +{ + /* + * After the lock is released, the original page table is restored. + */ + int pgd_idx, i; + int nr_pgds; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + + nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); + + for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) { + pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE); + set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]); + + if (!pgd_present(*pgd)) + continue; + + for (i = 0; i < PTRS_PER_P4D; i++) { + p4d = p4d_offset(pgd, + pgd_idx * PGDIR_SIZE + i * P4D_SIZE); + + if (!p4d_present(*p4d)) + continue; + + pud = (pud_t *)p4d_page_vaddr(*p4d); + pud_free(&init_mm, pud); + } + + p4d = (p4d_t *)pgd_page_vaddr(*pgd); + p4d_free(&init_mm, p4d); + } + + kfree(save_pgd); + + __flush_tlb_all(); + early_code_mapping_set_exec(0); +} + +pgd_t * __init efi_uv1_memmap_phys_prolog(void) +{ + unsigned long vaddr, addr_pgd, addr_p4d, addr_pud; + pgd_t *save_pgd, *pgd_k, *pgd_efi; + p4d_t *p4d, *p4d_k, *p4d_efi; + pud_t *pud; + + int pgd; + int n_pgds, i, j; + + early_code_mapping_set_exec(1); + + n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); + save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL); + if (!save_pgd) + return NULL; + + /* + * Build 1:1 identity mapping for UV1 memmap usage. Note that + * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while + * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical + * address X, the pud_index(X) != pud_index(__va(X)), we can only copy + * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping. + * This means here we can only reuse the PMD tables of the direct mapping. + */ + for (pgd = 0; pgd < n_pgds; pgd++) { + addr_pgd = (unsigned long)(pgd * PGDIR_SIZE); + vaddr = (unsigned long)__va(pgd * PGDIR_SIZE); + pgd_efi = pgd_offset_k(addr_pgd); + save_pgd[pgd] = *pgd_efi; + + p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd); + if (!p4d) { + pr_err("Failed to allocate p4d table!\n"); + goto out; + } + + for (i = 0; i < PTRS_PER_P4D; i++) { + addr_p4d = addr_pgd + i * P4D_SIZE; + p4d_efi = p4d + p4d_index(addr_p4d); + + pud = pud_alloc(&init_mm, p4d_efi, addr_p4d); + if (!pud) { + pr_err("Failed to allocate pud table!\n"); + goto out; + } + + for (j = 0; j < PTRS_PER_PUD; j++) { + addr_pud = addr_p4d + j * PUD_SIZE; + + if (addr_pud > (max_pfn << PAGE_SHIFT)) + break; + + vaddr = (unsigned long)__va(addr_pud); + + pgd_k = pgd_offset_k(vaddr); + p4d_k = p4d_offset(pgd_k, vaddr); + pud[j] = *pud_offset(p4d_k, vaddr); + } + } + pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX; + } + + __flush_tlb_all(); + return save_pgd; +out: + efi_uv1_memmap_phys_epilog(save_pgd); + return NULL; +} + +void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size, + u32 type, u64 attribute) +{ + unsigned long last_map_pfn; + + if (type == EFI_MEMORY_MAPPED_IO) + return ioremap(phys_addr, size); + + last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); + if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) { + unsigned long top = last_map_pfn << PAGE_SHIFT; + efi_ioremap(top, size - (top - phys_addr), type, attribute); + } + + if (!(attribute & EFI_MEMORY_WB)) + efi_memory_uc((u64)(unsigned long)__va(phys_addr), size); + + return (void __iomem *)__va(phys_addr); +} + +static int __init arch_parse_efi_cmdline(char *str) +{ + if (!str) { + pr_warn("need at least one option\n"); + return -EINVAL; + } + + if (!efi_is_mixed() && parse_option_str(str, "old_map")) + set_bit(EFI_UV1_MEMMAP, &efi.flags); + + return 0; } +early_param("efi", arch_parse_efi_cmdline); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 20c389a91b80..1fd321f37f1b 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1668,12 +1668,12 @@ static int tunables_open(struct inode *inode, struct file *file) return 0; } -static const struct file_operations proc_uv_ptc_operations = { - .open = ptc_proc_open, - .read = seq_read, - .write = ptc_proc_write, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops uv_ptc_proc_ops = { + .proc_open = ptc_proc_open, + .proc_read = seq_read, + .proc_write = ptc_proc_write, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static const struct file_operations tunables_fops = { @@ -1691,7 +1691,7 @@ static int __init uv_ptc_init(void) return 0; proc_uv_ptc = proc_create(UV_PTC_BASENAME, 0444, NULL, - &proc_uv_ptc_operations); + &uv_ptc_proc_ops); if (!proc_uv_ptc) { pr_err("unable to create %s proc entry\n", UV_PTC_BASENAME); @@ -1804,9 +1804,9 @@ static void pq_init(int node, int pnode) plsize = (DEST_Q_SIZE + 1) * sizeof(struct bau_pq_entry); vp = kmalloc_node(plsize, GFP_KERNEL, node); - pqp = (struct bau_pq_entry *)vp; - BUG_ON(!pqp); + BUG_ON(!vp); + pqp = (struct bau_pq_entry *)vp; cp = (char *)pqp + 31; pqp = (struct bau_pq_entry *)(((unsigned long)cp >> 5) << 5); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 24b079e94bc2..915bb1639763 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -12,6 +12,7 @@ #include <linux/smp.h> #include <linux/perf_event.h> #include <linux/tboot.h> +#include <linux/dmi.h> #include <asm/pgtable.h> #include <asm/proto.h> @@ -23,7 +24,7 @@ #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/mmu_context.h> -#include <linux/dmi.h> +#include <asm/cpu_device_id.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -122,9 +123,6 @@ static void __save_processor_state(struct saved_context *ctxt) ctxt->cr2 = read_cr2(); ctxt->cr3 = __read_cr3(); ctxt->cr4 = __read_cr4(); -#ifdef CONFIG_X86_64 - ctxt->cr8 = read_cr8(); -#endif ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE, &ctxt->misc_enable); msr_save_context(ctxt); @@ -207,7 +205,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) #else /* CONFIG X86_64 */ wrmsrl(MSR_EFER, ctxt->efer); - write_cr8(ctxt->cr8); __write_cr4(ctxt->cr4); #endif write_cr3(ctxt->cr3); @@ -397,15 +394,14 @@ static int __init bsp_pm_check_init(void) core_initcall(bsp_pm_check_init); -static int msr_init_context(const u32 *msr_id, const int total_num) +static int msr_build_context(const u32 *msr_id, const int num) { - int i = 0; + struct saved_msrs *saved_msrs = &saved_context.saved_msrs; struct saved_msr *msr_array; + int total_num; + int i, j; - if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) { - pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n"); - return -EINVAL; - } + total_num = saved_msrs->num + num; msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL); if (!msr_array) { @@ -413,19 +409,30 @@ static int msr_init_context(const u32 *msr_id, const int total_num) return -ENOMEM; } - for (i = 0; i < total_num; i++) { - msr_array[i].info.msr_no = msr_id[i]; + if (saved_msrs->array) { + /* + * Multiple callbacks can invoke this function, so copy any + * MSR save requests from previous invocations. + */ + memcpy(msr_array, saved_msrs->array, + sizeof(struct saved_msr) * saved_msrs->num); + + kfree(saved_msrs->array); + } + + for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + msr_array[i].info.msr_no = msr_id[j]; msr_array[i].valid = false; msr_array[i].info.reg.q = 0; } - saved_context.saved_msrs.num = total_num; - saved_context.saved_msrs.array = msr_array; + saved_msrs->num = total_num; + saved_msrs->array = msr_array; return 0; } /* - * The following section is a quirk framework for problematic BIOSen: + * The following sections are a quirk framework for problematic BIOSen: * Sometimes MSRs are modified by the BIOSen after suspended to * RAM, this might cause unexpected behavior after wakeup. * Thus we save/restore these specified MSRs across suspend/resume @@ -440,7 +447,7 @@ static int msr_initialize_bdw(const struct dmi_system_id *d) u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL }; pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident); - return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); + return msr_build_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); } static const struct dmi_system_id msr_save_dmi_table[] = { @@ -455,9 +462,58 @@ static const struct dmi_system_id msr_save_dmi_table[] = { {} }; +static int msr_save_cpuid_features(const struct x86_cpu_id *c) +{ + u32 cpuid_msr_id[] = { + MSR_AMD64_CPUID_FN_1, + }; + + pr_info("x86/pm: family %#hx cpu detected, MSR saving is needed during suspending.\n", + c->family); + + return msr_build_context(cpuid_msr_id, ARRAY_SIZE(cpuid_msr_id)); +} + +static const struct x86_cpu_id msr_save_cpu_table[] = { + { + .vendor = X86_VENDOR_AMD, + .family = 0x15, + .model = X86_MODEL_ANY, + .feature = X86_FEATURE_ANY, + .driver_data = (kernel_ulong_t)msr_save_cpuid_features, + }, + { + .vendor = X86_VENDOR_AMD, + .family = 0x16, + .model = X86_MODEL_ANY, + .feature = X86_FEATURE_ANY, + .driver_data = (kernel_ulong_t)msr_save_cpuid_features, + }, + {} +}; + +typedef int (*pm_cpu_match_t)(const struct x86_cpu_id *); +static int pm_cpu_check(const struct x86_cpu_id *c) +{ + const struct x86_cpu_id *m; + int ret = 0; + + m = x86_match_cpu(msr_save_cpu_table); + if (m) { + pm_cpu_match_t fn; + + fn = (pm_cpu_match_t)m->driver_data; + ret = fn(m); + } + + return ret; +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); + pm_cpu_check(msr_save_cpu_table); + return 0; } diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S index 6fe383002125..8786653ad3c0 100644 --- a/arch/x86/power/hibernate_asm_32.S +++ b/arch/x86/power/hibernate_asm_32.S @@ -16,7 +16,7 @@ .text -ENTRY(swsusp_arch_suspend) +SYM_FUNC_START(swsusp_arch_suspend) movl %esp, saved_context_esp movl %ebx, saved_context_ebx movl %ebp, saved_context_ebp @@ -33,9 +33,9 @@ ENTRY(swsusp_arch_suspend) call swsusp_save FRAME_END ret -ENDPROC(swsusp_arch_suspend) +SYM_FUNC_END(swsusp_arch_suspend) -ENTRY(restore_image) +SYM_CODE_START(restore_image) /* prepare to jump to the image kernel */ movl restore_jump_address, %ebx movl restore_cr3, %ebp @@ -45,9 +45,10 @@ ENTRY(restore_image) /* jump to relocated restore code */ movl relocated_restore_code, %eax jmpl *%eax +SYM_CODE_END(restore_image) /* code below has been relocated to a safe page */ -ENTRY(core_restore_code) +SYM_CODE_START(core_restore_code) movl temp_pgt, %eax movl %eax, %cr3 @@ -77,10 +78,11 @@ copy_loop: done: jmpl *%ebx +SYM_CODE_END(core_restore_code) /* code below belongs to the image kernel */ .align PAGE_SIZE -ENTRY(restore_registers) +SYM_FUNC_START(restore_registers) /* go back to the original page tables */ movl %ebp, %cr3 movl mmu_cr4_features, %ecx @@ -107,4 +109,4 @@ ENTRY(restore_registers) movl %eax, in_suspend ret -ENDPROC(restore_registers) +SYM_FUNC_END(restore_registers) diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index a4d5eb0a7ece..7918b8415f13 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -22,7 +22,7 @@ #include <asm/processor-flags.h> #include <asm/frame.h> -ENTRY(swsusp_arch_suspend) +SYM_FUNC_START(swsusp_arch_suspend) movq $saved_context, %rax movq %rsp, pt_regs_sp(%rax) movq %rbp, pt_regs_bp(%rax) @@ -50,9 +50,9 @@ ENTRY(swsusp_arch_suspend) call swsusp_save FRAME_END ret -ENDPROC(swsusp_arch_suspend) +SYM_FUNC_END(swsusp_arch_suspend) -ENTRY(restore_image) +SYM_CODE_START(restore_image) /* prepare to jump to the image kernel */ movq restore_jump_address(%rip), %r8 movq restore_cr3(%rip), %r9 @@ -67,9 +67,10 @@ ENTRY(restore_image) /* jump to relocated restore code */ movq relocated_restore_code(%rip), %rcx jmpq *%rcx +SYM_CODE_END(restore_image) /* code below has been relocated to a safe page */ -ENTRY(core_restore_code) +SYM_CODE_START(core_restore_code) /* switch to temporary page tables */ movq %rax, %cr3 /* flush TLB */ @@ -97,10 +98,11 @@ ENTRY(core_restore_code) .Ldone: /* jump to the restore_registers address from the image header */ jmpq *%r8 +SYM_CODE_END(core_restore_code) /* code below belongs to the image kernel */ .align PAGE_SIZE -ENTRY(restore_registers) +SYM_FUNC_START(restore_registers) /* go back to the original page tables */ movq %r9, %cr3 @@ -142,4 +144,4 @@ ENTRY(restore_registers) movq %rax, in_suspend(%rip) ret -ENDPROC(restore_registers) +SYM_FUNC_END(restore_registers) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 8901a1f89cf5..fb4ee5444379 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -9,46 +9,52 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) $(obj)/string.o: $(srctree)/arch/x86/boot/compressed/string.c FORCE $(call if_changed_rule,cc_o_c) -$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE +$(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE $(call if_changed_rule,cc_o_c) +CFLAGS_sha256.o := -D__DISABLE_EXPORTS + LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib targets += purgatory.ro KASAN_SANITIZE := n KCOV_INSTRUMENT := n +# These are adjustments to the compiler flags used for objects that +# make up the standalone purgatory.ro + +PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel +PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss +PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) + # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That # in turn leaves some undefined symbols like __fentry__ in purgatory and not # sure how to relocate those. ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_sha256.o += $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_purgatory.o += $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_string.o += $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_kexec-purgatory.o += $(CC_FLAGS_FTRACE) +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_FTRACE) endif ifdef CONFIG_STACKPROTECTOR -CFLAGS_REMOVE_sha256.o += -fstack-protector -CFLAGS_REMOVE_purgatory.o += -fstack-protector -CFLAGS_REMOVE_string.o += -fstack-protector -CFLAGS_REMOVE_kexec-purgatory.o += -fstack-protector +PURGATORY_CFLAGS_REMOVE += -fstack-protector endif ifdef CONFIG_STACKPROTECTOR_STRONG -CFLAGS_REMOVE_sha256.o += -fstack-protector-strong -CFLAGS_REMOVE_purgatory.o += -fstack-protector-strong -CFLAGS_REMOVE_string.o += -fstack-protector-strong -CFLAGS_REMOVE_kexec-purgatory.o += -fstack-protector-strong +PURGATORY_CFLAGS_REMOVE += -fstack-protector-strong endif ifdef CONFIG_RETPOLINE -CFLAGS_REMOVE_sha256.o += $(RETPOLINE_CFLAGS) -CFLAGS_REMOVE_purgatory.o += $(RETPOLINE_CFLAGS) -CFLAGS_REMOVE_string.o += $(RETPOLINE_CFLAGS) -CFLAGS_REMOVE_kexec-purgatory.o += $(RETPOLINE_CFLAGS) +PURGATORY_CFLAGS_REMOVE += $(RETPOLINE_CFLAGS) endif +CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_purgatory.o += $(PURGATORY_CFLAGS) + +CFLAGS_REMOVE_sha256.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_sha256.o += $(PURGATORY_CFLAGS) + +CFLAGS_REMOVE_string.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_string.o += $(PURGATORY_CFLAGS) + $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) diff --git a/arch/x86/purgatory/entry64.S b/arch/x86/purgatory/entry64.S index 275a646d1048..0b4390ce586b 100644 --- a/arch/x86/purgatory/entry64.S +++ b/arch/x86/purgatory/entry64.S @@ -8,13 +8,13 @@ * This code has been taken from kexec-tools. */ +#include <linux/linkage.h> + .text .balign 16 .code64 - .globl entry64, entry64_regs - -entry64: +SYM_CODE_START(entry64) /* Setup a gdt that should be preserved */ lgdt gdt(%rip) @@ -54,10 +54,11 @@ new_cs_exit: /* Jump to the new code... */ jmpq *rip(%rip) +SYM_CODE_END(entry64) .section ".rodata" .balign 4 -entry64_regs: +SYM_DATA_START(entry64_regs) rax: .quad 0x0 rcx: .quad 0x0 rdx: .quad 0x0 @@ -75,13 +76,14 @@ r13: .quad 0x0 r14: .quad 0x0 r15: .quad 0x0 rip: .quad 0x0 - .size entry64_regs, . - entry64_regs +SYM_DATA_END(entry64_regs) /* GDT */ .section ".rodata" .balign 16 -gdt: - /* 0x00 unusable segment +SYM_DATA_START_LOCAL(gdt) + /* + * 0x00 unusable segment * 0x08 unused * so use them as gdt ptr */ @@ -94,6 +96,8 @@ gdt: /* 0x18 4GB flat data segment */ .word 0xFFFF, 0x0000, 0x9200, 0x00CF -gdt_end: -stack: .quad 0, 0 -stack_init: +SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) + +SYM_DATA_START_LOCAL(stack) + .quad 0, 0 +SYM_DATA_END_LABEL(stack, SYM_L_LOCAL, stack_init) diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c index b607bda786f6..2961234d0795 100644 --- a/arch/x86/purgatory/purgatory.c +++ b/arch/x86/purgatory/purgatory.c @@ -9,33 +9,15 @@ */ #include <linux/bug.h> -#include <linux/sha256.h> +#include <crypto/sha.h> #include <asm/purgatory.h> #include "../boot/string.h" -unsigned long purgatory_backup_dest __section(.kexec-purgatory); -unsigned long purgatory_backup_src __section(.kexec-purgatory); -unsigned long purgatory_backup_sz __section(.kexec-purgatory); - u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory); struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory); -/* - * On x86, second kernel requries first 640K of memory to boot. Copy - * first 640K to a backup region in reserved memory range so that second - * kernel can use first 640K. - */ -static int copy_backup_region(void) -{ - if (purgatory_backup_dest) { - memcpy((void *)purgatory_backup_dest, - (void *)purgatory_backup_src, purgatory_backup_sz); - } - return 0; -} - static int verify_sha256_digest(void) { struct kexec_sha_region *ptr, *end; @@ -66,7 +48,6 @@ void purgatory(void) for (;;) ; } - copy_backup_region(); } /* diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S index 321146be741d..89d9e9e53fcd 100644 --- a/arch/x86/purgatory/setup-x86_64.S +++ b/arch/x86/purgatory/setup-x86_64.S @@ -7,14 +7,14 @@ * * This code has been taken from kexec-tools. */ +#include <linux/linkage.h> #include <asm/purgatory.h> .text - .globl purgatory_start .balign 16 -purgatory_start: .code64 +SYM_CODE_START(purgatory_start) /* Load a gdt so I know what the segment registers are */ lgdt gdt(%rip) @@ -32,10 +32,12 @@ purgatory_start: /* Call the C code */ call purgatory jmp entry64 +SYM_CODE_END(purgatory_start) .section ".rodata" .balign 16 -gdt: /* 0x00 unusable segment +SYM_DATA_START_LOCAL(gdt) + /* 0x00 unusable segment * 0x08 unused * so use them as the gdt ptr */ @@ -48,10 +50,10 @@ gdt: /* 0x00 unusable segment /* 0x18 4GB flat data segment */ .word 0xFFFF, 0x0000, 0x9200, 0x00CF -gdt_end: +SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) .bss .balign 4096 -lstack: +SYM_DATA_START_LOCAL(lstack) .skip 4096 -lstack_end: +SYM_DATA_END_LABEL(lstack, SYM_L_LOCAL, lstack_end) diff --git a/arch/x86/purgatory/stack.S b/arch/x86/purgatory/stack.S index 8b1427422dfc..1ef507ca50a5 100644 --- a/arch/x86/purgatory/stack.S +++ b/arch/x86/purgatory/stack.S @@ -5,13 +5,14 @@ * Copyright (C) 2014 Red Hat Inc. */ +#include <linux/linkage.h> + /* A stack for the loaded kernel. * Separate and in the data section so it can be prepopulated. */ .data .balign 4096 - .globl stack, stack_end -stack: +SYM_DATA_START(stack) .skip 4096 -stack_end: +SYM_DATA_END_LABEL(stack, SYM_L_GLOBAL, stack_end) diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 7dce39c8c034..262f83cad355 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -8,6 +8,7 @@ #include <asm/pgtable.h> #include <asm/realmode.h> #include <asm/tlbflush.h> +#include <asm/crash.h> struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -34,6 +35,7 @@ void __init reserve_real_mode(void) memblock_reserve(mem, size); set_real_mode_mem(mem); + crash_reserve_low_1M(); } static void __init setup_real_mode(void) diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index f60501a384f9..99b6332ba540 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -12,7 +12,7 @@ OBJECT_FILES_NON_STANDARD := y # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n -always := realmode.bin realmode.relocs +always-y := realmode.bin realmode.relocs wakeup-objs := wakeup_asm.o wakemain.o video-mode.o wakeup-objs += copy.o bioscall.o regs.o diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index 30b0d30d861a..af04512c02d9 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -14,12 +14,11 @@ .section ".header", "a" .balign 16 -GLOBAL(real_mode_header) +SYM_DATA_START(real_mode_header) .long pa_text_start .long pa_ro_end /* SMP trampoline */ .long pa_trampoline_start - .long pa_trampoline_status .long pa_trampoline_header #ifdef CONFIG_X86_64 .long pa_trampoline_pgd; @@ -34,11 +33,9 @@ GLOBAL(real_mode_header) #ifdef CONFIG_X86_64 .long __KERNEL32_CS #endif -END(real_mode_header) +SYM_DATA_END(real_mode_header) /* End signature, used to verify integrity */ .section ".signature","a" .balign 4 -GLOBAL(end_signature) - .long REALMODE_END_SIGNATURE -END(end_signature) +SYM_DATA(end_signature, .long REALMODE_END_SIGNATURE) diff --git a/arch/x86/realmode/rm/realmode.lds.S b/arch/x86/realmode/rm/realmode.lds.S index 3bb980800c58..64d135d1ee63 100644 --- a/arch/x86/realmode/rm/realmode.lds.S +++ b/arch/x86/realmode/rm/realmode.lds.S @@ -11,6 +11,7 @@ OUTPUT_FORMAT("elf32-i386") OUTPUT_ARCH(i386) +ENTRY(pa_text_start) SECTIONS { diff --git a/arch/x86/realmode/rm/reboot.S b/arch/x86/realmode/rm/reboot.S index cd2f97b9623b..f10515b10e0a 100644 --- a/arch/x86/realmode/rm/reboot.S +++ b/arch/x86/realmode/rm/reboot.S @@ -19,7 +19,7 @@ */ .section ".text32", "ax" .code32 -ENTRY(machine_real_restart_asm) +SYM_CODE_START(machine_real_restart_asm) #ifdef CONFIG_X86_64 /* Switch to trampoline GDT as it is guaranteed < 4 GiB */ @@ -33,7 +33,7 @@ ENTRY(machine_real_restart_asm) movl %eax, %cr0 ljmpl $__KERNEL32_CS, $pa_machine_real_restart_paging_off -GLOBAL(machine_real_restart_paging_off) +SYM_INNER_LABEL(machine_real_restart_paging_off, SYM_L_GLOBAL) xorl %eax, %eax xorl %edx, %edx movl $MSR_EFER, %ecx @@ -63,6 +63,7 @@ GLOBAL(machine_real_restart_paging_off) movl %ecx, %gs movl %ecx, %ss ljmpw $8, $1f +SYM_CODE_END(machine_real_restart_asm) /* * This is 16-bit protected mode code to disable paging and the cache, @@ -127,13 +128,13 @@ bios: .section ".rodata", "a" .balign 16 -GLOBAL(machine_real_restart_idt) +SYM_DATA_START(machine_real_restart_idt) .word 0xffff /* Length - real mode default value */ .long 0 /* Base - real mode default value */ -END(machine_real_restart_idt) +SYM_DATA_END(machine_real_restart_idt) .balign 16 -GLOBAL(machine_real_restart_gdt) +SYM_DATA_START(machine_real_restart_gdt) /* Self-pointer */ .word 0xffff /* Length - real mode default value */ .long pa_machine_real_restart_gdt @@ -153,4 +154,4 @@ GLOBAL(machine_real_restart_gdt) * semantics we don't have to reload the segments once CR0.PE = 0. */ .quad GDT_ENTRY(0x0093, 0x100, 0xffff) -END(machine_real_restart_gdt) +SYM_DATA_END(machine_real_restart_gdt) diff --git a/arch/x86/realmode/rm/stack.S b/arch/x86/realmode/rm/stack.S index 8d4cb64799ea..0fca64061ad2 100644 --- a/arch/x86/realmode/rm/stack.S +++ b/arch/x86/realmode/rm/stack.S @@ -6,15 +6,13 @@ #include <linux/linkage.h> .data -GLOBAL(HEAP) - .long rm_heap -GLOBAL(heap_end) - .long rm_stack +SYM_DATA(HEAP, .long rm_heap) +SYM_DATA(heap_end, .long rm_stack) .bss .balign 16 -GLOBAL(rm_heap) - .space 2048 -GLOBAL(rm_stack) +SYM_DATA(rm_heap, .space 2048) + +SYM_DATA_START(rm_stack) .space 2048 -GLOBAL(rm_stack_end) +SYM_DATA_END_LABEL(rm_stack, SYM_L_GLOBAL, rm_stack_end) diff --git a/arch/x86/realmode/rm/trampoline_32.S b/arch/x86/realmode/rm/trampoline_32.S index 2dd866c9e21e..3fad907a179f 100644 --- a/arch/x86/realmode/rm/trampoline_32.S +++ b/arch/x86/realmode/rm/trampoline_32.S @@ -29,7 +29,7 @@ .code16 .balign PAGE_SIZE -ENTRY(trampoline_start) +SYM_CODE_START(trampoline_start) wbinvd # Needed for NUMA-Q should be harmless for others LJMPW_RM(1f) @@ -41,9 +41,6 @@ ENTRY(trampoline_start) movl tr_start, %eax # where we need to go - movl $0xA5A5A5A5, trampoline_status - # write marker for master knows we're running - /* * GDT tables in non default location kernel can be beyond 16MB and * lgdt will not be able to load the address as in real mode default @@ -57,18 +54,20 @@ ENTRY(trampoline_start) lmsw %dx # into protected mode ljmpl $__BOOT_CS, $pa_startup_32 +SYM_CODE_END(trampoline_start) .section ".text32","ax" .code32 -ENTRY(startup_32) # note: also used from wakeup_asm.S +SYM_CODE_START(startup_32) # note: also used from wakeup_asm.S jmp *%eax +SYM_CODE_END(startup_32) .bss .balign 8 -GLOBAL(trampoline_header) - tr_start: .space 4 - tr_gdt_pad: .space 2 - tr_gdt: .space 6 -END(trampoline_header) +SYM_DATA_START(trampoline_header) + SYM_DATA_LOCAL(tr_start, .space 4) + SYM_DATA_LOCAL(tr_gdt_pad, .space 2) + SYM_DATA_LOCAL(tr_gdt, .space 6) +SYM_DATA_END(trampoline_header) #include "trampoline_common.S" diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index 24bb7598774e..251758ed7443 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -38,7 +38,7 @@ .code16 .balign PAGE_SIZE -ENTRY(trampoline_start) +SYM_CODE_START(trampoline_start) cli # We should be safe anyway wbinvd @@ -49,9 +49,6 @@ ENTRY(trampoline_start) mov %ax, %es mov %ax, %ss - movl $0xA5A5A5A5, trampoline_status - # write marker for master knows we're running - # Setup stack movl $rm_stack_end, %esp @@ -81,12 +78,14 @@ ENTRY(trampoline_start) no_longmode: hlt jmp no_longmode +SYM_CODE_END(trampoline_start) + #include "../kernel/verify_cpu.S" .section ".text32","ax" .code32 .balign 4 -ENTRY(startup_32) +SYM_CODE_START(startup_32) movl %edx, %ss addl $pa_real_mode_base, %esp movl %edx, %ds @@ -140,38 +139,39 @@ ENTRY(startup_32) * the new gdt/idt that has __KERNEL_CS with CS.L = 1. */ ljmpl $__KERNEL_CS, $pa_startup_64 +SYM_CODE_END(startup_32) .section ".text64","ax" .code64 .balign 4 -ENTRY(startup_64) +SYM_CODE_START(startup_64) # Now jump into the kernel using virtual addresses jmpq *tr_start(%rip) +SYM_CODE_END(startup_64) .section ".rodata","a" # Duplicate the global descriptor table # so the kernel can live anywhere .balign 16 - .globl tr_gdt -tr_gdt: +SYM_DATA_START(tr_gdt) .short tr_gdt_end - tr_gdt - 1 # gdt limit .long pa_tr_gdt .short 0 .quad 0x00cf9b000000ffff # __KERNEL32_CS .quad 0x00af9b000000ffff # __KERNEL_CS .quad 0x00cf93000000ffff # __KERNEL_DS -tr_gdt_end: +SYM_DATA_END_LABEL(tr_gdt, SYM_L_LOCAL, tr_gdt_end) .bss .balign PAGE_SIZE -GLOBAL(trampoline_pgd) .space PAGE_SIZE +SYM_DATA(trampoline_pgd, .space PAGE_SIZE) .balign 8 -GLOBAL(trampoline_header) - tr_start: .space 8 - GLOBAL(tr_efer) .space 8 - GLOBAL(tr_cr4) .space 4 - GLOBAL(tr_flags) .space 4 -END(trampoline_header) +SYM_DATA_START(trampoline_header) + SYM_DATA_LOCAL(tr_start, .space 8) + SYM_DATA(tr_efer, .space 8) + SYM_DATA(tr_cr4, .space 4) + SYM_DATA(tr_flags, .space 4) +SYM_DATA_END(trampoline_header) #include "trampoline_common.S" diff --git a/arch/x86/realmode/rm/trampoline_common.S b/arch/x86/realmode/rm/trampoline_common.S index 7c706772ab59..5033e640f957 100644 --- a/arch/x86/realmode/rm/trampoline_common.S +++ b/arch/x86/realmode/rm/trampoline_common.S @@ -1,8 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ .section ".rodata","a" .balign 16 -tr_idt: .fill 1, 6, 0 - - .bss - .balign 4 -GLOBAL(trampoline_status) .space 4 +SYM_DATA_LOCAL(tr_idt, .fill 1, 6, 0) diff --git a/arch/x86/realmode/rm/wakeup_asm.S b/arch/x86/realmode/rm/wakeup_asm.S index 05ac9c17c811..02d0ba16ae33 100644 --- a/arch/x86/realmode/rm/wakeup_asm.S +++ b/arch/x86/realmode/rm/wakeup_asm.S @@ -17,7 +17,7 @@ .section ".data", "aw" .balign 16 -GLOBAL(wakeup_header) +SYM_DATA_START(wakeup_header) video_mode: .short 0 /* Video mode number */ pmode_entry: .long 0 pmode_cs: .short __KERNEL_CS @@ -31,13 +31,13 @@ GLOBAL(wakeup_header) realmode_flags: .long 0 real_magic: .long 0 signature: .long WAKEUP_HEADER_SIGNATURE -END(wakeup_header) +SYM_DATA_END(wakeup_header) .text .code16 .balign 16 -ENTRY(wakeup_start) +SYM_CODE_START(wakeup_start) cli cld @@ -73,7 +73,7 @@ ENTRY(wakeup_start) movw %ax, %fs movw %ax, %gs - lidtl wakeup_idt + lidtl .Lwakeup_idt /* Clear the EFLAGS */ pushl $0 @@ -135,6 +135,7 @@ ENTRY(wakeup_start) #else jmp trampoline_start #endif +SYM_CODE_END(wakeup_start) bogus_real_magic: 1: @@ -152,7 +153,7 @@ bogus_real_magic: */ .balign 16 -GLOBAL(wakeup_gdt) +SYM_DATA_START(wakeup_gdt) .word 3*8-1 /* Self-descriptor */ .long pa_wakeup_gdt .word 0 @@ -164,15 +165,15 @@ GLOBAL(wakeup_gdt) .word 0xffff /* 16-bit data segment @ real_mode_base */ .long 0x93000000 + pa_real_mode_base .word 0x008f /* big real mode */ -END(wakeup_gdt) +SYM_DATA_END(wakeup_gdt) .section ".rodata","a" .balign 8 /* This is the standard real-mode IDT */ .balign 16 -GLOBAL(wakeup_idt) +SYM_DATA_START_LOCAL(.Lwakeup_idt) .word 0xffff /* limit */ .long 0 /* address */ .word 0 -END(wakeup_idt) +SYM_DATA_END(.Lwakeup_idt) diff --git a/arch/x86/realmode/rmpiggy.S b/arch/x86/realmode/rmpiggy.S index c078dba40cef..c8fef76743f6 100644 --- a/arch/x86/realmode/rmpiggy.S +++ b/arch/x86/realmode/rmpiggy.S @@ -10,12 +10,10 @@ .balign PAGE_SIZE -GLOBAL(real_mode_blob) +SYM_DATA_START(real_mode_blob) .incbin "arch/x86/realmode/rm/realmode.bin" -END(real_mode_blob) +SYM_DATA_END_LABEL(real_mode_blob, SYM_L_GLOBAL, real_mode_blob_end) -GLOBAL(real_mode_blob_end); - -GLOBAL(real_mode_relocs) +SYM_DATA_START(real_mode_relocs) .incbin "arch/x86/realmode/rm/realmode.relocs" -END(real_mode_relocs) +SYM_DATA_END(real_mode_relocs) diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index 09af7ff53044..55b1ab378974 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -26,7 +26,7 @@ posttest: $(obj)/insn_decoder_test vmlinux $(obj)/insn_sanity $(call cmd,posttest) $(call cmd,sanitytest) -hostprogs-y += insn_decoder_test insn_sanity +hostprogs += insn_decoder_test insn_sanity # -I needed for generated C source and C source which in the kernel tree. HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/ @@ -39,7 +39,7 @@ $(obj)/insn_decoder_test.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/l $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c HOST_EXTRACFLAGS += -I$(srctree)/tools/include -hostprogs-y += relocs +hostprogs += relocs relocs-objs := relocs_32.o relocs_64.o relocs_common.o PHONY += relocs relocs: $(obj)/relocs diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index b02a36b2c14f..a42015b305f4 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -69,7 +69,7 @@ BEGIN { lprefix1_expr = "\\((66|!F3)\\)" lprefix2_expr = "\\(F3\\)" - lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)" + lprefix3_expr = "\\((F2|!F3|66&F2)\\)" lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 @@ -257,7 +257,7 @@ function convert_operands(count,opnd, i,j,imm,mod) return add_flags(imm, mod) } -/^[0-9a-f]+\:/ { +/^[0-9a-f]+:/ { if (NR == 1) next # get index diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index f31e5d903161..165be7f9a964 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -2,14 +2,7 @@ #ifndef _ASM_UM_BARRIER_H_ #define _ASM_UM_BARRIER_H_ -#include <asm/asm.h> -#include <asm/segment.h> -#include <asm/cpufeatures.h> -#include <asm/cmpxchg.h> -#include <asm/nops.h> - -#include <linux/kernel.h> -#include <linux/irqflags.h> +#include <asm/alternative.h> /* * Force strict CPU ordering. @@ -30,9 +23,6 @@ #endif /* CONFIG_X86_32 */ -#define dma_rmb() barrier() -#define dma_wmb() barrier() - #include <asm-generic/barrier.h> #endif diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index 5bd949da7a4a..ac8eee093f9c 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -215,14 +215,12 @@ static int set_tls_entry(struct task_struct* task, struct user_desc *info, return 0; } -int arch_copy_tls(struct task_struct *new) +int arch_set_tls(struct task_struct *new, unsigned long tls) { struct user_desc info; int idx, ret = -EFAULT; - if (copy_from_user(&info, - (void __user *) UPT_SI(&new->thread.regs.regs), - sizeof(info))) + if (copy_from_user(&info, (void __user *) tls, sizeof(info))) goto out; ret = -EINVAL; diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c index 3a621e0d3925..ebd3855d9b13 100644 --- a/arch/x86/um/tls_64.c +++ b/arch/x86/um/tls_64.c @@ -6,14 +6,13 @@ void clear_flushed_tls(struct task_struct *task) { } -int arch_copy_tls(struct task_struct *t) +int arch_set_tls(struct task_struct *t, unsigned long tls) { /* * If CLONE_SETTLS is set, we need to save the thread id - * (which is argument 5, child_tid, of clone) so it can be set - * during context switches. + * so it can be set during context switches. */ - t->thread.arch.fs = t->thread.regs.regs.gp[R8 / sizeof(long)]; + t->thread.arch.fs = tls; return 0; } diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c index ac9c02b9d92c..2112b8d14668 100644 --- a/arch/x86/um/vdso/um_vdso.c +++ b/arch/x86/um/vdso/um_vdso.c @@ -13,7 +13,7 @@ #include <linux/getcpu.h> #include <asm/unistd.h> -int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) +int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts) { long ret; @@ -22,10 +22,10 @@ int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) return ret; } -int clock_gettime(clockid_t, struct timespec *) +int clock_gettime(clockid_t, struct __kernel_old_timespec *) __attribute__((weak, alias("__vdso_clock_gettime"))); -int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { long ret; @@ -34,10 +34,10 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) return ret; } -int gettimeofday(struct timeval *, struct timezone *) +int gettimeofday(struct __kernel_old_timeval *, struct timezone *) __attribute__((weak, alias("__vdso_gettimeofday"))); -time_t __vdso_time(time_t *t) +__kernel_old_time_t __vdso_time(__kernel_old_time_t *t) { long secs; @@ -47,7 +47,7 @@ time_t __vdso_time(time_t *t) return secs; } -int time(time_t *t) __attribute__((weak, alias("__vdso_time"))); +__kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time"))); long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) diff --git a/arch/x86/um/vdso/vdso.S b/arch/x86/um/vdso/vdso.S index a4a3870dc059..a6eaf293a73b 100644 --- a/arch/x86/um/vdso/vdso.S +++ b/arch/x86/um/vdso/vdso.S @@ -1,11 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/init.h> +#include <linux/linkage.h> __INITDATA - .globl vdso_start, vdso_end -vdso_start: +SYM_DATA_START(vdso_start) .incbin "arch/x86/um/vdso/vdso.so" -vdso_end: +SYM_DATA_END_LABEL(vdso_start, SYM_L_GLOBAL, vdso_end) __FINIT diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index ba5a41828e9d..1aded63a95cb 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -62,10 +62,10 @@ config XEN_512GB boot parameter "xen_512gb_limit". config XEN_SAVE_RESTORE - bool - depends on XEN - select HIBERNATE_CALLBACKS - default y + bool + depends on XEN + select HIBERNATE_CALLBACKS + default y config XEN_DEBUG_FS bool "Enable Xen debug and tuning parameters in debugfs" diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index 0d3365cb64de..1abe455d926a 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -31,7 +31,7 @@ static efi_system_table_t efi_systab_xen __initdata = { .con_in_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ .con_in = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ .con_out_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ - .con_out = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ + .con_out = NULL, /* Not used under Xen. */ .stderr_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ .stderr = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ .runtime = (efi_runtime_services_t *)EFI_INVALID_TABLE_ADDR, @@ -57,19 +57,7 @@ static efi_system_table_t __init *xen_efi_probe(void) return NULL; /* Here we know that Xen runs on EFI platform. */ - - efi.get_time = xen_efi_get_time; - efi.set_time = xen_efi_set_time; - efi.get_wakeup_time = xen_efi_get_wakeup_time; - efi.set_wakeup_time = xen_efi_set_wakeup_time; - efi.get_variable = xen_efi_get_variable; - efi.get_next_variable = xen_efi_get_next_variable; - efi.set_variable = xen_efi_set_variable; - efi.query_variable_info = xen_efi_query_variable_info; - efi.update_capsule = xen_efi_update_capsule; - efi.query_capsule_caps = xen_efi_query_capsule_caps; - efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; - efi.reset_system = xen_efi_reset_system; + xen_efi_runtime_setup(); efi_systab_xen.tables = info->cfg.addr; efi_systab_xen.nr_tables = info->cfg.nent; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 750f46ad018a..205b1176084f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -269,19 +269,41 @@ void xen_reboot(int reason) BUG(); } +static int reboot_reason = SHUTDOWN_reboot; +static bool xen_legacy_crash; void xen_emergency_restart(void) { - xen_reboot(SHUTDOWN_reboot); + xen_reboot(reboot_reason); } static int xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { - if (!kexec_crash_loaded()) - xen_reboot(SHUTDOWN_crash); + if (!kexec_crash_loaded()) { + if (xen_legacy_crash) + xen_reboot(SHUTDOWN_crash); + + reboot_reason = SHUTDOWN_crash; + + /* + * If panic_timeout==0 then we are supposed to wait forever. + * However, to preserve original dom0 behavior we have to drop + * into hypervisor. (domU behavior is controlled by its + * config file) + */ + if (panic_timeout == 0) + panic_timeout = -1; + } return NOTIFY_DONE; } +static int __init parse_xen_legacy_crash(char *arg) +{ + xen_legacy_crash = true; + return 0; +} +early_param("xen_legacy_crash", parse_xen_legacy_crash); + static struct notifier_block xen_panic_block = { .notifier_call = xen_panic_event, .priority = INT_MIN diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 7ceb32821093..1f756ffffe8b 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -117,6 +117,14 @@ static void __init xen_banner(void) printk(KERN_INFO "Xen version: %d.%d%s%s\n", version >> 16, version & 0xffff, extra.extraversion, xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); + +#ifdef CONFIG_X86_32 + pr_warn("WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n" + "Support for running as 32-bit PV-guest under Xen will soon be removed\n" + "from the Linux kernel!\n" + "Please use either a 64-bit kernel or switch to HVM or PVH mode!\n" + "WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n"); +#endif } static void __init xen_pv_init_platform(void) @@ -829,15 +837,6 @@ static void xen_load_sp0(unsigned long sp0) this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } -void xen_set_iopl_mask(unsigned mask) -{ - struct physdev_set_iopl set_iopl; - - /* Force the change at ring 0. */ - set_iopl.iopl = (mask == 0) ? 1 : (mask >> 12) & 3; - HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); -} - static void xen_io_delay(void) { } @@ -877,16 +876,6 @@ static void xen_write_cr4(unsigned long cr4) native_write_cr4(cr4); } -#ifdef CONFIG_X86_64 -static inline unsigned long xen_read_cr8(void) -{ - return 0; -} -static inline void xen_write_cr8(unsigned long val) -{ - BUG_ON(val); -} -#endif static u64 xen_read_msr_safe(unsigned int msr, int *err) { @@ -1023,11 +1012,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .write_cr4 = xen_write_cr4, -#ifdef CONFIG_X86_64 - .read_cr8 = xen_read_cr8, - .write_cr8 = xen_write_cr8, -#endif - .wbinvd = native_wbinvd, .read_msr = xen_read_msr, @@ -1062,7 +1046,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .write_idt_entry = xen_write_idt_entry, .load_sp0 = xen_load_sp0, - .set_iopl_mask = xen_set_iopl_mask, .io_delay = xen_io_delay, /* Xen takes care of %gs when switching to usermode for us */ @@ -1222,6 +1205,7 @@ asmlinkage __visible void __init xen_start_kernel(void) x86_platform.get_nmi_reason = xen_get_nmi_reason; x86_init.resources.memory_setup = xen_memory_setup; + x86_init.irqs.intr_mode_select = x86_init_noop; x86_init.irqs.intr_mode_init = x86_init_noop; x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 26e8b326966d..bbba8b17829a 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -67,7 +67,7 @@ #include <asm/linkage.h> #include <asm/page.h> #include <asm/init.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/smp.h> #include <asm/tlb.h> @@ -2625,7 +2625,6 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, *dma_handle = virt_to_machine(vstart).maddr; return success ? 0 : -ENOMEM; } -EXPORT_SYMBOL_GPL(xen_create_contiguous_region); void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { @@ -2660,7 +2659,6 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) spin_unlock_irqrestore(&xen_reservation_lock, flags); } -EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region); static noinline void xen_flush_tlb_all(void) { diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 548d1e0a5ba1..33b0e20df7fc 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -412,7 +412,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk( remap_range_size = xen_find_pfn_range(&remap_pfn); if (!remap_range_size) { - pr_warning("Unable to find available pfn range, not remapping identity pages\n"); + pr_warn("Unable to find available pfn range, not remapping identity pages\n"); xen_set_identity_and_release_chunk(cur_pfn, cur_pfn + left, nr_pages); break; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index be104eef80be..508fe204520b 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -19,7 +19,7 @@ * event status with one and operation. If there are pending events, * then enter the hypervisor to get them handled. */ -ENTRY(xen_irq_enable_direct) +SYM_FUNC_START(xen_irq_enable_direct) FRAME_BEGIN /* Unmask events */ movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask @@ -38,17 +38,17 @@ ENTRY(xen_irq_enable_direct) 1: FRAME_END ret - ENDPROC(xen_irq_enable_direct) +SYM_FUNC_END(xen_irq_enable_direct) /* * Disabling events is simply a matter of making the event mask * non-zero. */ -ENTRY(xen_irq_disable_direct) +SYM_FUNC_START(xen_irq_disable_direct) movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask ret -ENDPROC(xen_irq_disable_direct) +SYM_FUNC_END(xen_irq_disable_direct) /* * (xen_)save_fl is used to get the current interrupt enable status. @@ -59,12 +59,12 @@ ENDPROC(xen_irq_disable_direct) * undefined. We need to toggle the state of the bit, because Xen and * x86 use opposite senses (mask vs enable). */ -ENTRY(xen_save_fl_direct) +SYM_FUNC_START(xen_save_fl_direct) testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask setz %ah addb %ah, %ah ret - ENDPROC(xen_save_fl_direct) +SYM_FUNC_END(xen_save_fl_direct) /* @@ -74,7 +74,7 @@ ENTRY(xen_save_fl_direct) * interrupt mask state, it checks for unmasked pending events and * enters the hypervisor to get them delivered if so. */ -ENTRY(xen_restore_fl_direct) +SYM_FUNC_START(xen_restore_fl_direct) FRAME_BEGIN #ifdef CONFIG_X86_64 testw $X86_EFLAGS_IF, %di @@ -95,14 +95,14 @@ ENTRY(xen_restore_fl_direct) 1: FRAME_END ret - ENDPROC(xen_restore_fl_direct) +SYM_FUNC_END(xen_restore_fl_direct) /* * Force an event check by making a hypercall, but preserve regs * before making the call. */ -ENTRY(check_events) +SYM_FUNC_START(check_events) FRAME_BEGIN #ifdef CONFIG_X86_32 push %eax @@ -135,19 +135,19 @@ ENTRY(check_events) #endif FRAME_END ret -ENDPROC(check_events) +SYM_FUNC_END(check_events) -ENTRY(xen_read_cr2) +SYM_FUNC_START(xen_read_cr2) FRAME_BEGIN _ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX _ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX FRAME_END ret - ENDPROC(xen_read_cr2); +SYM_FUNC_END(xen_read_cr2); -ENTRY(xen_read_cr2_direct) +SYM_FUNC_START(xen_read_cr2_direct) FRAME_BEGIN _ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX FRAME_END ret - ENDPROC(xen_read_cr2_direct); +SYM_FUNC_END(xen_read_cr2_direct); diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index c15db060a242..2712e9155306 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -56,7 +56,7 @@ _ASM_EXTABLE(1b,2b) .endm -ENTRY(xen_iret) +SYM_CODE_START(xen_iret) /* test eflags for special cases */ testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp) jnz hyper_iret @@ -122,14 +122,14 @@ xen_iret_end_crit: hyper_iret: /* put this out of line since its very rarely used */ jmp hypercall_page + __HYPERVISOR_iret * 32 +SYM_CODE_END(xen_iret) .globl xen_iret_start_crit, xen_iret_end_crit /* - * This is called by xen_hypervisor_callback in entry.S when it sees + * This is called by xen_hypervisor_callback in entry_32.S when it sees * that the EIP at the time of interrupt was between - * xen_iret_start_crit and xen_iret_end_crit. We're passed the EIP in - * %eax so we can do a more refined determination of what to do. + * xen_iret_start_crit and xen_iret_end_crit. * * The stack format at this point is: * ---------------- @@ -138,70 +138,46 @@ hyper_iret: * eflags } outer exception info * cs } * eip } - * ---------------- <- edi (copy dest) - * eax : outer eax if it hasn't been restored * ---------------- - * eflags } nested exception info - * cs } (no ss/esp because we're nested - * eip } from the same ring) - * orig_eax }<- esi (copy src) - * - - - - - - - - - * fs } - * es } - * ds } SAVE_ALL state - * eax } - * : : - * ebx }<- esp + * eax : outer eax if it hasn't been restored * ---------------- + * eflags } + * cs } nested exception info + * eip } + * return address : (into xen_hypervisor_callback) * - * In order to deliver the nested exception properly, we need to shift - * everything from the return addr up to the error code so it sits - * just under the outer exception info. This means that when we - * handle the exception, we do it in the context of the outer - * exception rather than starting a new one. + * In order to deliver the nested exception properly, we need to discard the + * nested exception frame such that when we handle the exception, we do it + * in the context of the outer exception rather than starting a new one. * - * The only caveat is that if the outer eax hasn't been restored yet - * (ie, it's still on stack), we need to insert its value into the - * SAVE_ALL state before going on, since it's usermode state which we - * eventually need to restore. + * The only caveat is that if the outer eax hasn't been restored yet (i.e. + * it's still on stack), we need to restore its value here. */ -ENTRY(xen_iret_crit_fixup) +SYM_CODE_START(xen_iret_crit_fixup) /* * Paranoia: Make sure we're really coming from kernel space. * One could imagine a case where userspace jumps into the * critical range address, but just before the CPU delivers a - * GP, it decides to deliver an interrupt instead. Unlikely? - * Definitely. Easy to avoid? Yes. The Intel documents - * explicitly say that the reported EIP for a bad jump is the - * jump instruction itself, not the destination, but some - * virtual environments get this wrong. + * PF, it decides to deliver an interrupt instead. Unlikely? + * Definitely. Easy to avoid? Yes. */ - movl PT_CS(%esp), %ecx - andl $SEGMENT_RPL_MASK, %ecx - cmpl $USER_RPL, %ecx - je 2f - - lea PT_ORIG_EAX(%esp), %esi - lea PT_EFLAGS(%esp), %edi + testb $2, 2*4(%esp) /* nested CS */ + jnz 2f /* * If eip is before iret_restore_end then stack * hasn't been restored yet. */ - cmp $iret_restore_end, %eax + cmpl $iret_restore_end, 1*4(%esp) jae 1f - movl 0+4(%edi), %eax /* copy EAX (just above top of frame) */ - movl %eax, PT_EAX(%esp) + movl 4*4(%esp), %eax /* load outer EAX */ + ret $4*4 /* discard nested EIP, CS, and EFLAGS as + * well as the just restored EAX */ - lea ESP_OFFSET(%edi), %edi /* move dest up over saved regs */ - - /* set up the copy */ -1: std - mov $PT_EIP / 4, %ecx /* saved regs up to orig_eax */ - rep movsl - cld - - lea 4(%edi), %esp /* point esp to new frame */ -2: jmp xen_do_upcall +1: + ret $3*4 /* discard nested EIP, CS, and EFLAGS */ +2: + ret +SYM_CODE_END(xen_iret_crit_fixup) diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index ebf610b49c06..0a0fd168683a 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -20,11 +20,11 @@ #include <linux/linkage.h> .macro xen_pv_trap name -ENTRY(xen_\name) +SYM_CODE_START(xen_\name) pop %rcx pop %r11 jmp \name -END(xen_\name) +SYM_CODE_END(xen_\name) _ASM_NOKPROBE(xen_\name) .endm @@ -57,7 +57,7 @@ xen_pv_trap entry_INT80_compat xen_pv_trap hypervisor_callback __INIT -ENTRY(xen_early_idt_handler_array) +SYM_CODE_START(xen_early_idt_handler_array) i = 0 .rept NUM_EXCEPTION_VECTORS pop %rcx @@ -66,7 +66,7 @@ ENTRY(xen_early_idt_handler_array) i = i + 1 .fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -END(xen_early_idt_handler_array) +SYM_CODE_END(xen_early_idt_handler_array) __FINIT hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 @@ -85,11 +85,12 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * r11 }<-- pushed by hypercall page * rsp->rax } */ -ENTRY(xen_iret) +SYM_CODE_START(xen_iret) pushq $0 jmp hypercall_iret +SYM_CODE_END(xen_iret) -ENTRY(xen_sysret64) +SYM_CODE_START(xen_sysret64) /* * We're already on the usermode stack at this point, but * still with the kernel gs, so we can easily switch back. @@ -107,6 +108,7 @@ ENTRY(xen_sysret64) pushq $VGCF_in_syscall jmp hypercall_iret +SYM_CODE_END(xen_sysret64) /* * Xen handles syscall callbacks much like ordinary exceptions, which @@ -124,7 +126,7 @@ ENTRY(xen_sysret64) */ /* Normal 64-bit system call target */ -ENTRY(xen_syscall_target) +SYM_FUNC_START(xen_syscall_target) popq %rcx popq %r11 @@ -137,12 +139,12 @@ ENTRY(xen_syscall_target) movq $__USER_CS, 1*8(%rsp) jmp entry_SYSCALL_64_after_hwframe -ENDPROC(xen_syscall_target) +SYM_FUNC_END(xen_syscall_target) #ifdef CONFIG_IA32_EMULATION /* 32-bit compat syscall target */ -ENTRY(xen_syscall32_target) +SYM_FUNC_START(xen_syscall32_target) popq %rcx popq %r11 @@ -155,25 +157,25 @@ ENTRY(xen_syscall32_target) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSCALL_compat_after_hwframe -ENDPROC(xen_syscall32_target) +SYM_FUNC_END(xen_syscall32_target) /* 32-bit compat sysenter target */ -ENTRY(xen_sysenter_target) +SYM_FUNC_START(xen_sysenter_target) mov 0*8(%rsp), %rcx mov 1*8(%rsp), %r11 mov 5*8(%rsp), %rsp jmp entry_SYSENTER_compat -ENDPROC(xen_sysenter_target) +SYM_FUNC_END(xen_sysenter_target) #else /* !CONFIG_IA32_EMULATION */ -ENTRY(xen_syscall32_target) -ENTRY(xen_sysenter_target) +SYM_FUNC_START_ALIAS(xen_syscall32_target) +SYM_FUNC_START(xen_sysenter_target) lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $0 jmp hypercall_iret -ENDPROC(xen_syscall32_target) -ENDPROC(xen_sysenter_target) +SYM_FUNC_END(xen_sysenter_target) +SYM_FUNC_END_ALIAS(xen_syscall32_target) #endif /* CONFIG_IA32_EMULATION */ diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index c1d8b90aa4e2..1d0cee3163e4 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -22,7 +22,7 @@ #ifdef CONFIG_XEN_PV __INIT -ENTRY(startup_xen) +SYM_CODE_START(startup_xen) UNWIND_HINT_EMPTY cld @@ -52,13 +52,13 @@ ENTRY(startup_xen) #endif jmp xen_start_kernel -END(startup_xen) +SYM_CODE_END(startup_xen) __FINIT #endif .pushsection .text .balign PAGE_SIZE -ENTRY(hypercall_page) +SYM_CODE_START(hypercall_page) .rept (PAGE_SIZE / 32) UNWIND_HINT_EMPTY .skip 32 @@ -69,7 +69,7 @@ ENTRY(hypercall_page) .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 #include <asm/xen-hypercalls.h> #undef HYPERCALL -END(hypercall_page) +SYM_CODE_END(hypercall_page) .popsection ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") |
