diff options
Diffstat (limited to 'arch/x86')
105 files changed, 2494 insertions, 1449 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c1f9b3cf437c..90e2640ade75 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -74,6 +74,7 @@ config X86 select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO + select ARCH_STACKWALK select ARCH_SUPPORTS_ACPI select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 @@ -183,7 +184,6 @@ config X86 select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if PARAVIRT - select HAVE_RCU_TABLE_INVALIDATE if HAVE_RCU_TABLE_FREE 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 @@ -268,9 +268,6 @@ config ARCH_MAY_HAVE_PC_FDC def_bool y depends on ISA_DMA_API -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config GENERIC_CALIBRATE_DELAY def_bool y @@ -783,14 +780,6 @@ config PARAVIRT_SPINLOCKS If you are unsure how to answer this question, answer Y. -config QUEUED_LOCK_STAT - bool "Paravirt queued spinlock statistics" - depends on PARAVIRT_SPINLOCKS && DEBUG_FS - ---help--- - Enable the collection of statistical data on the slowpath - behavior of paravirtualized queued spinlocks and report - them on debugfs. - source "arch/x86/xen/Kconfig" config KVM_GUEST @@ -1499,7 +1488,7 @@ config X86_CPA_STATISTICS depends on DEBUG_FS ---help--- Expose statistics about the Change Page Attribute mechanims, which - helps to determine the effectivness of preserving large and huge + helps to determine the effectiveness of preserving large and huge page mappings when mapping protections are changed. config ARCH_HAS_MEM_ENCRYPT @@ -2217,14 +2206,8 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING If unsure, leave at the default value. config HOTPLUG_CPU - bool "Support for hot-pluggable CPUs" + def_bool y depends on SMP - ---help--- - Say Y here to allow turning CPUs off and on. CPUs can be - controlled through /sys/devices/system/cpu. - ( Note: power management support will enable this option - automatically on SMP systems. ) - Say N if you want to disable CPU hotplug. config BOOTPARAM_HOTPLUG_CPU0 bool "Set default setting of cpu0_hotpluggable" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 2d8b9d8ca4f8..a587805c6687 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -219,8 +219,12 @@ ifdef CONFIG_RETPOLINE # Additionally, avoid generating expensive indirect jumps which # are subject to retpolines for small number of switch cases. # clang turns off jump table generation by default when under - # retpoline builds, however, gcc does not for x86. - KBUILD_CFLAGS += $(call cc-option,--param=case-values-threshold=20) + # retpoline builds, however, gcc does not for x86. This has + # only been fixed starting from gcc stable version 8.4.0 and + # onwards, but not for older ones. See gcc bug #86952. + ifndef CONFIG_CC_IS_CLANG + KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables) + endif endif archscripts: scripts_basic diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index c0d6c560df69..5a237e8dbf8d 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -352,7 +352,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, boot_params->hdr.loadflags &= ~KASLR_FLAG; /* Save RSDP address for later use. */ - boot_params->acpi_rsdp_addr = get_rsdp_addr(); + /* boot_params->acpi_rsdp_addr = get_rsdp_addr(); */ sanitize_boot_params(boot_params); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index fd13655e0f9b..d2f184165934 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -120,8 +120,6 @@ static inline void console_init(void) void set_sev_encryption_mask(void); -#endif - /* acpi.c */ #ifdef CONFIG_ACPI acpi_physical_address get_rsdp_addr(void); @@ -135,3 +133,5 @@ int count_immovable_mem_regions(void); #else static inline int count_immovable_mem_regions(void) { return 0; } #endif + +#endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 315a67b8896b..90154df8f125 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -13,8 +13,9 @@ */ #include <linux/types.h> -#include <linux/kernel.h> +#include <linux/compiler.h> #include <linux/errno.h> +#include <linux/limits.h> #include <asm/asm.h> #include "ctype.h" #include "string.h" diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S index 3b6e70d085da..8457cdd47f75 100644 --- a/arch/x86/crypto/poly1305-avx2-x86_64.S +++ b/arch/x86/crypto/poly1305-avx2-x86_64.S @@ -323,6 +323,12 @@ ENTRY(poly1305_4block_avx2) 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 @@ -361,16 +367,16 @@ ENTRY(poly1305_4block_avx2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S index e6add74d78a5..6f0be7a86964 100644 --- a/arch/x86/crypto/poly1305-sse2-x86_64.S +++ b/arch/x86/crypto/poly1305-sse2-x86_64.S @@ -253,16 +253,16 @@ ENTRY(poly1305_block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx @@ -524,6 +524,12 @@ ENTRY(poly1305_2block_sse2) 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 @@ -562,16 +568,16 @@ ENTRY(poly1305_2block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index d309f30cf7af..5fc76b755510 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -650,6 +650,7 @@ ENTRY(__switch_to_asm) pushl %ebx pushl %edi pushl %esi + pushfl /* switch stack */ movl %esp, TASK_threadsp(%eax) @@ -672,6 +673,7 @@ ENTRY(__switch_to_asm) #endif /* restore callee-saved registers */ + popfl popl %esi popl %edi popl %ebx diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 007b3fe9d727..98c7d12b945c 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -29,12 +29,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); extern time_t __vdso_time(time_t *t); #ifdef CONFIG_PARAVIRT_CLOCK -extern u8 pvclock_page +extern u8 pvclock_page[PAGE_SIZE] __attribute__((visibility("hidden"))); #endif #ifdef CONFIG_HYPERV_TSCPAGE -extern u8 hvclock_page +extern u8 hvclock_page[PAGE_SIZE] __attribute__((visibility("hidden"))); #endif diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 7d2d7c801dba..f15441b07dad 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -3,10 +3,14 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/delay.h> #include <asm/apicdef.h> +#include <asm/nmi.h> #include "../perf_event.h" +static DEFINE_PER_CPU(unsigned int, perf_nmi_counter); + static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -112,23 +116,144 @@ static __initconst const u64 amd_hw_cache_event_ids }, }; +static __initconst const u64 amd_hw_cache_event_ids_f17h + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { +[C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */ + [C(RESULT_MISS)] = 0xc860, /* L2$ access from DC Miss */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */ + [C(RESULT_MISS)] = 0, + }, +}, +[C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches */ + [C(RESULT_MISS)] = 0x0081, /* Instruction cache misses */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, +}, +[C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, +}, +[C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */ + [C(RESULT_MISS)] = 0xf045, /* L2 DTLB misses (PT walks) */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, +}, +[C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */ + [C(RESULT_MISS)] = 0xff85, /* L1 ITLB misses, L2 misses */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, +}, +[C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr. */ + [C(RESULT_MISS)] = 0x00c3, /* Retired Mispredicted BI */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, +}, +[C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, +}, +}; + /* - * AMD Performance Monitor K7 and later. + * AMD Performance Monitor K7 and later, up to and including Family 16h: */ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, - [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, + [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ +}; + +/* + * AMD Performance Monitor Family 17h and later: + */ +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_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, }; static u64 amd_pmu_event_map(int hw_event) { + if (boot_cpu_data.x86 >= 0x17) + return amd_f17h_perfmon_event_map[hw_event]; + return amd_perfmon_event_map[hw_event]; } @@ -429,6 +554,132 @@ static void amd_pmu_cpu_dead(int cpu) } } +/* + * When a PMC counter overflows, an NMI is used to process the event and + * reset the counter. NMI latency can result in the counter being updated + * before the NMI can run, which can result in what appear to be spurious + * NMIs. This function is intended to wait for the NMI to run and reset + * the counter to avoid possible unhandled NMI messages. + */ +#define OVERFLOW_WAIT_COUNT 50 + +static void amd_pmu_wait_on_overflow(int idx) +{ + unsigned int i; + u64 counter; + + /* + * Wait for the counter to be reset if it has overflowed. This loop + * should exit very, very quickly, but just in case, don't wait + * forever... + */ + for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) { + rdmsrl(x86_pmu_event_addr(idx), counter); + if (counter & (1ULL << (x86_pmu.cntval_bits - 1))) + break; + + /* Might be in IRQ context, so can't sleep */ + udelay(1); + } +} + +static void amd_pmu_disable_all(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int idx; + + x86_pmu_disable_all(); + + /* + * This shouldn't be called from NMI context, but add a safeguard here + * to return, since if we're in NMI context we can't wait for an NMI + * to reset an overflowed counter value. + */ + if (in_nmi()) + return; + + /* + * Check each counter for overflow and wait for it to be reset by the + * NMI if it has overflowed. This relies on the fact that all active + * counters are always enabled when this function is caled and + * ARCH_PERFMON_EVENTSEL_INT is always set. + */ + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + if (!test_bit(idx, cpuc->active_mask)) + continue; + + amd_pmu_wait_on_overflow(idx); + } +} + +static void amd_pmu_disable_event(struct perf_event *event) +{ + x86_pmu_disable_event(event); + + /* + * This can be called from NMI context (via x86_pmu_stop). The counter + * may have overflowed, but either way, we'll never see it get reset + * by the NMI if we're already in the NMI. And the NMI latency support + * below will take care of any pending NMI that might have been + * generated by the overflow. + */ + if (in_nmi()) + return; + + amd_pmu_wait_on_overflow(event->hw.idx); +} + +/* + * Because of NMI latency, if multiple PMC counters are active or other sources + * of NMIs are received, the perf NMI handler can handle one or more overflowed + * PMC counters outside of the NMI associated with the PMC overflow. If the NMI + * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel + * back-to-back NMI support won't be active. This PMC handler needs to take into + * account that this can occur, otherwise this could result in unknown NMI + * messages being issued. Examples of this is PMC overflow while in the NMI + * 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. + */ +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); + + /* 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 (handled) { + this_cpu_write(perf_nmi_counter, + min_t(unsigned int, 2, active)); + + return handled; + } + + if (!this_cpu_read(perf_nmi_counter)) + return NMI_DONE; + + this_cpu_dec(perf_nmi_counter); + + return NMI_HANDLED; +} + static struct event_constraint * amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -621,11 +872,11 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config) static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", - .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, + .handle_irq = amd_pmu_handle_irq, + .disable_all = amd_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, + .disable = amd_pmu_disable_event, .hw_config = amd_pmu_hw_config, .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, @@ -718,9 +969,10 @@ __init int amd_pmu_init(void) x86_pmu.amd_nb_constraints = 0; } - /* Events are common for all AMDs */ - memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, - sizeof(hw_cache_event_ids)); + if (boot_cpu_data.x86 >= 0x17) + memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids)); + else + memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids)); return 0; } @@ -732,7 +984,7 @@ void amd_pmu_enable_virt(void) cpuc->perf_ctr_virt_mask = 0; /* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); @@ -750,7 +1002,7 @@ void amd_pmu_disable_virt(void) cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; /* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_disable_virt); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index e2b1447192a8..f315425d8468 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -560,6 +560,21 @@ int x86_pmu_hw_config(struct perf_event *event) return -EINVAL; } + /* sample_regs_user never support XMM registers */ + if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS)) + return -EINVAL; + /* + * Besides the general purpose registers, XMM registers may + * be collected in PEBS on some platforms, e.g. Icelake + */ + if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) { + if (x86_pmu.pebs_no_xmm_regs) + return -EINVAL; + + if (!event->attr.precise_ip) + return -EINVAL; + } + return x86_setup_perfctr(event); } @@ -661,6 +676,10 @@ static inline int is_x86_event(struct perf_event *event) return event->pmu == &pmu; } +struct pmu *x86_get_pmu(void) +{ + return &pmu; +} /* * Event scheduler state: * @@ -849,18 +868,43 @@ 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 i, wmin, wmax, unsched = 0; + int n0, i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, X86_PMC_IDX_MAX); + /* + * Compute the number of events already present; see x86_pmu_add(), + * validate_group() and x86_pmu_commit_txn(). For the former two + * cpuc->n_events hasn't been updated yet, while for the latter + * cpuc->n_txn contains the number of events added in the current + * transaction. + */ + n0 = cpuc->n_events; + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) + n0 -= cpuc->n_txn; + if (x86_pmu.start_scheduling) x86_pmu.start_scheduling(cpuc); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { - cpuc->event_constraint[i] = NULL; - c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); - cpuc->event_constraint[i] = c; + c = cpuc->event_constraint[i]; + + /* + * Previously scheduled events should have a cached constraint, + * while new events should not have one. + */ + WARN_ON_ONCE((c && i >= n0) || (!c && i < n0)); + + /* + * Request constraints for new events; or for those events that + * have a dynamic constraint -- for those the constraint can + * change due to external factors (sibling state, allow_tfa). + */ + if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) { + c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); + cpuc->event_constraint[i] = c; + } wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); @@ -925,25 +969,20 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (!unsched && assign) { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; - e->hw.flags |= PERF_X86_EVENT_COMMITTED; if (x86_pmu.commit_scheduling) x86_pmu.commit_scheduling(cpuc, i, assign[i]); } } else { - for (i = 0; i < n; i++) { + for (i = n0; i < n; i++) { e = cpuc->event_list[i]; - /* - * do not put_constraint() on comitted events, - * because they are good to go - */ - if ((e->hw.flags & PERF_X86_EVENT_COMMITTED)) - continue; /* * release events that failed scheduling */ if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, e); + + cpuc->event_constraint[i] = NULL; } } @@ -1349,8 +1388,9 @@ void x86_pmu_stop(struct perf_event *event, int flags) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) { + if (test_bit(hwc->idx, cpuc->active_mask)) { x86_pmu.disable(event); + __clear_bit(hwc->idx, cpuc->active_mask); cpuc->events[hwc->idx] = NULL; WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; @@ -1372,11 +1412,6 @@ static void x86_pmu_del(struct perf_event *event, int flags) int i; /* - * event is descheduled - */ - event->hw.flags &= ~PERF_X86_EVENT_COMMITTED; - - /* * If we're called during a txn, we only need to undo x86_pmu.add. * The events never got scheduled and ->cancel_txn will truncate * the event_list. @@ -1412,6 +1447,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; } + cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; perf_event_update_userpage(event); @@ -1447,16 +1483,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs) apic_write(APIC_LVTPC, APIC_DM_NMI); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - if (!test_bit(idx, cpuc->active_mask)) { - /* - * Though we deactivated the counter some cpus - * might still deliver spurious interrupts still - * in flight. Catch them: - */ - if (__test_and_clear_bit(idx, cpuc->running)) - handled++; + if (!test_bit(idx, cpuc->active_mask)) continue; - } event = cpuc->events[idx]; @@ -2031,7 +2059,7 @@ static int validate_event(struct perf_event *event) if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); - c = x86_pmu.get_event_constraints(fake_cpuc, -1, event); + c = x86_pmu.get_event_constraints(fake_cpuc, 0, event); if (!c || !c->weight) ret = -EINVAL; @@ -2079,8 +2107,7 @@ static int validate_group(struct perf_event *event) if (n < 0) goto out; - fake_cpuc->n_events = n; - + fake_cpuc->n_events = 0; ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out: @@ -2355,6 +2382,15 @@ void arch_perf_update_userpage(struct perf_event *event, cyc2ns_read_end(); } +/* + * Determine whether the regs were taken from an irq/exception handler rather + * than from perf_arch_fetch_caller_regs(). + */ +static bool perf_hw_regs(struct pt_regs *regs) +{ + return regs->flags & X86_EFLAGS_FIXED; +} + void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { @@ -2366,11 +2402,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re return; } - if (perf_callchain_store(entry, regs->ip)) - return; + if (perf_hw_regs(regs)) { + if (perf_callchain_store(entry, regs->ip)) + return; + unwind_start(&state, current, regs, NULL); + } else { + unwind_start(&state, current, NULL, (void *)regs->sp); + } - for (unwind_start(&state, current, regs, NULL); !unwind_done(&state); - unwind_next_frame(&state)) { + for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || perf_callchain_store(entry, addr)) return; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 8baa441d8000..ef763f535e3a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -239,6 +239,35 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +static struct event_constraint intel_icl_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ + INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf), + INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */ + INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf), + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */ + INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.STALLS_MEM_ANY */ + INTEL_EVENT_CONSTRAINT(0xa3, 0xf), /* CYCLE_ACTIVITY.* */ + INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf), + INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg intel_icl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + EVENT_EXTRA_END +}; + EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); @@ -1827,6 +1856,45 @@ static __initconst const u64 glp_hw_cache_extra_regs }, }; +#define TNT_LOCAL_DRAM BIT_ULL(26) +#define TNT_DEMAND_READ GLM_DEMAND_DATA_RD +#define TNT_DEMAND_WRITE GLM_DEMAND_RFO +#define TNT_LLC_ACCESS GLM_ANY_RESPONSE +#define TNT_SNP_ANY (SNB_SNP_NOT_NEEDED|SNB_SNP_MISS| \ + SNB_NO_FWD|SNB_SNP_FWD|SNB_HITM) +#define TNT_LLC_MISS (TNT_SNP_ANY|SNB_NON_DRAM|TNT_LOCAL_DRAM) + +static __initconst const u64 tnt_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = TNT_DEMAND_READ| + TNT_LLC_ACCESS, + [C(RESULT_MISS)] = TNT_DEMAND_READ| + TNT_LLC_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = TNT_DEMAND_WRITE| + TNT_LLC_ACCESS, + [C(RESULT_MISS)] = TNT_DEMAND_WRITE| + TNT_LLC_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, +}; + +static struct extra_reg intel_tnt_extra_regs[] __read_mostly = { + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1), + EVENT_EXTRA_END +}; + #define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ #define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ #define KNL_MCDRAM_LOCAL BIT_ULL(21) @@ -2015,7 +2083,7 @@ static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int /* * We're going to use PMC3, make sure TFA is set before we touch it. */ - if (cntr == 3 && !cpuc->is_fake) + if (cntr == 3) intel_set_tfa(cpuc, true); } @@ -2091,15 +2159,19 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); cpuc->intel_cp_status &= ~(1ull << hwc->idx); - if (unlikely(event->attr.precise_ip)) - intel_pmu_pebs_disable(event); - if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_disable_fixed(hwc); return; } x86_pmu_disable_event(event); + + /* + * Needs to be called after x86_pmu_disable_event, + * so we don't trigger the event without PEBS bit set. + */ + if (unlikely(event->attr.precise_ip)) + intel_pmu_pebs_disable(event); } static void intel_pmu_del_event(struct perf_event *event) @@ -2145,6 +2217,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event) bits <<= (idx * 4); mask = 0xfULL << (idx * 4); + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) { + bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4); + mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4); + } + rdmsrl(hwc->config_base, ctrl_val); ctrl_val &= ~mask; ctrl_val |= bits; @@ -2688,7 +2765,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { - if ((event->hw.config & c->cmask) == c->code) { + if (constraint_match(c, event->hw.config)) { event->hw.flags |= c->flags; return c; } @@ -2838,7 +2915,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; struct intel_excl_states *xlo; int tid = cpuc->excl_thread_id; - int is_excl, i; + int is_excl, i, w; /* * validating a group does not require @@ -2894,36 +2971,40 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * SHARED : sibling counter measuring non-exclusive event * UNUSED : sibling counter unused */ + w = c->weight; for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) { /* * exclusive event in sibling counter * our corresponding counter cannot be used * regardless of our event */ - if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) + if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) { __clear_bit(i, c->idxmsk); + w--; + continue; + } /* * if measuring an exclusive event, sibling * measuring non-exclusive, then counter cannot * be used */ - if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) + if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) { __clear_bit(i, c->idxmsk); + w--; + continue; + } } /* - * recompute actual bit weight for scheduling algorithm - */ - c->weight = hweight64(c->idxmsk64); - - /* * if we return an empty mask, then switch * back to static empty constraint to avoid * the cost of freeing later on */ - if (c->weight == 0) + if (!w) c = &emptyconstraint; + c->weight = w; + return c; } @@ -2931,11 +3012,9 @@ static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { - struct event_constraint *c1 = NULL; - struct event_constraint *c2; + struct event_constraint *c1, *c2; - if (idx >= 0) /* fake does < 0 */ - c1 = cpuc->event_constraint[idx]; + c1 = cpuc->event_constraint[idx]; /* * first time only @@ -2943,7 +3022,8 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, * - dynamic constraint: handled by intel_get_excl_constraints() */ c2 = __intel_get_event_constraints(cpuc, idx, event); - if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) { + if (c1) { + WARN_ON_ONCE(!(c1->flags & PERF_X86_EVENT_DYNAMIC)); bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX); c1->weight = c2->weight; c2 = c1; @@ -3131,7 +3211,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event) flags &= ~PERF_SAMPLE_TIME; if (!event->attr.exclude_kernel) flags &= ~PERF_SAMPLE_REGS_USER; - if (event->attr.sample_regs_user & ~PEBS_REGS) + if (event->attr.sample_regs_user & ~PEBS_GP_REGS) flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR); return flags; } @@ -3185,7 +3265,7 @@ static int intel_pmu_hw_config(struct perf_event *event) return ret; if (event->attr.precise_ip) { - if (!event->attr.freq) { + if (!(event->attr.freq || event->attr.wakeup_events)) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & ~intel_pmu_large_pebs_flags(event))) @@ -3366,6 +3446,12 @@ static struct event_constraint counter0_constraint = static struct event_constraint counter2_constraint = EVENT_CONSTRAINT(0, 0x4, 0); +static struct event_constraint fixed0_constraint = + FIXED_EVENT_CONSTRAINT(0x00c0, 0); + +static struct event_constraint fixed0_counter0_constraint = + INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL); + static struct event_constraint * hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -3385,6 +3471,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, } static struct event_constraint * +icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + /* + * Fixed counter 0 has less skid. + * Force instruction:ppp in Fixed counter 0 + */ + if ((event->attr.precise_ip == 3) && + constraint_match(&fixed0_constraint, event->hw.config)) + return &fixed0_constraint; + + return hsw_get_event_constraints(cpuc, idx, event); +} + +static struct event_constraint * glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { @@ -3399,6 +3500,29 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return c; } +static struct event_constraint * +tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c; + + /* + * :ppp means to do reduced skid PEBS, + * which is available on PMC0 and fixed counter 0. + */ + if (event->attr.precise_ip == 3) { + /* Force instruction:ppp on PMC0 and Fixed counter 0 */ + if (constraint_match(&fixed0_constraint, event->hw.config)) + return &fixed0_counter0_constraint; + + return &counter0_constraint; + } + + c = intel_get_event_constraints(cpuc, idx, event); + + return c; +} + static bool allow_tsx_force_abort = true; static struct event_constraint * @@ -3410,7 +3534,7 @@ tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx, /* * Without TFA we must not use PMC3. */ - if (!allow_tsx_force_abort && test_bit(3, c->idxmsk) && idx >= 0) { + if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) { c = dyn_constraint(cpuc, c, idx); c->idxmsk64 &= ~(1ULL << 3); c->weight--; @@ -3507,6 +3631,8 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) { + cpuc->pebs_record_size = x86_pmu.pebs_record_size; + if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) @@ -3575,6 +3701,12 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; + if (x86_pmu.flags & PMU_FL_TFA) { + WARN_ON_ONCE(cpuc->tfa_shadow); + cpuc->tfa_shadow = ~0ULL; + intel_set_tfa(cpuc, false); + } + if (x86_pmu.version > 1) flip_smm_bit(&x86_pmu.attr_freeze_on_smi); @@ -4108,6 +4240,42 @@ static struct attribute *hsw_tsx_events_attrs[] = { NULL }; +EVENT_ATTR_STR(tx-capacity-read, tx_capacity_read, "event=0x54,umask=0x80"); +EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2"); +EVENT_ATTR_STR(el-capacity-read, el_capacity_read, "event=0x54,umask=0x80"); +EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2"); + +static struct attribute *icl_events_attrs[] = { + EVENT_PTR(mem_ld_hsw), + EVENT_PTR(mem_st_hsw), + NULL, +}; + +static struct attribute *icl_tsx_events_attrs[] = { + EVENT_PTR(tx_start), + EVENT_PTR(tx_abort), + EVENT_PTR(tx_commit), + EVENT_PTR(tx_capacity_read), + EVENT_PTR(tx_capacity_write), + EVENT_PTR(tx_conflict), + EVENT_PTR(el_start), + EVENT_PTR(el_abort), + EVENT_PTR(el_commit), + EVENT_PTR(el_capacity_read), + EVENT_PTR(el_capacity_write), + EVENT_PTR(el_conflict), + EVENT_PTR(cycles_t), + EVENT_PTR(cycles_ct), + NULL, +}; + +static __init struct attribute **get_icl_events_attrs(void) +{ + return boot_cpu_has(X86_FEATURE_RTM) ? + merge_attr(icl_events_attrs, icl_tsx_events_attrs) : + icl_events_attrs; +} + static ssize_t freeze_on_smi_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -4147,6 +4315,50 @@ done: return count; } +static void update_tfa_sched(void *ignored) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* + * check if PMC3 is used + * and if so force schedule out for all event types all contexts + */ + if (test_bit(3, cpuc->active_mask)) + perf_pmu_resched(x86_get_pmu()); +} + +static ssize_t show_sysctl_tfa(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, 40, "%d\n", allow_tsx_force_abort); +} + +static ssize_t set_sysctl_tfa(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + bool val; + ssize_t ret; + + ret = kstrtobool(buf, &val); + if (ret) + return ret; + + /* no change */ + if (val == allow_tsx_force_abort) + return count; + + allow_tsx_force_abort = val; + + get_online_cpus(); + on_each_cpu(update_tfa_sched, NULL, 1); + put_online_cpus(); + + return count; +} + + static DEVICE_ATTR_RW(freeze_on_smi); static ssize_t branches_show(struct device *cdev, @@ -4179,7 +4391,9 @@ static struct attribute *intel_pmu_caps_attrs[] = { NULL }; -static DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort); +static DEVICE_ATTR(allow_tsx_force_abort, 0644, + show_sysctl_tfa, + set_sysctl_tfa); static struct attribute *intel_pmu_attrs[] = { &dev_attr_freeze_on_smi.attr, @@ -4440,6 +4654,32 @@ __init int intel_pmu_init(void) name = "goldmont_plus"; break; + case INTEL_FAM6_ATOM_TREMONT_X: + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.extra_regs = intel_tnt_extra_regs; + /* + * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS + * for precise cycles. + */ + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.get_event_constraints = tnt_get_event_constraints; + extra_attr = slm_format_attr; + pr_cont("Tremont events, "); + name = "Tremont"; + break; + case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: @@ -4688,13 +4928,41 @@ __init int intel_pmu_init(void) x86_pmu.get_event_constraints = tfa_get_event_constraints; x86_pmu.enable_all = intel_tfa_pmu_enable_all; x86_pmu.commit_scheduling = intel_tfa_commit_scheduling; - intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr; + intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr; } pr_cont("Skylake events, "); name = "skylake"; break; + case INTEL_FAM6_ICELAKE_MOBILE: + 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)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_icl_event_constraints; + x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints; + x86_pmu.extra_regs = intel_icl_extra_regs; + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = icl_get_event_constraints; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; + extra_attr = merge_attr(extra_attr, skl_format_attr); + x86_pmu.cpu_events = get_icl_events_attrs(); + x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02); + x86_pmu.lbr_pt_coexist = true; + intel_pmu_pebs_data_source_skl(false); + pr_cont("Icelake events, "); + name = "icelake"; + break; + default: switch (x86_pmu.version) { case 1: diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 94a4b7fc75d0..6072f92cb8ea 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -76,15 +76,15 @@ * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 - * Available model: HSW ULT,CNL + * Available model: HSW ULT,KBL,CNL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 - * Available model: HSW ULT,CNL + * Available model: HSW ULT,KBL,CNL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT,GLM,CNL + * Available model: HSW ULT,KBL,GLM,CNL * Scope: Package (physical package) * */ @@ -566,8 +566,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, 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_CANNONLAKE_MOBILE, cnl_cstates), @@ -578,6 +578,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_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 10c99ce1fead..7a9f5dac5abe 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -849,6 +849,26 @@ struct event_constraint intel_skl_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_icl_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */ + + INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ + + INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + + /* + * Everything else is handled by PMU_FL_PEBS_ALL, because we + * need the full constraints from the main table. + */ + + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -858,7 +878,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) if (x86_pmu.pebs_constraints) { for_each_event_constraint(c, x86_pmu.pebs_constraints) { - if ((event->hw.config & c->cmask) == c->code) { + if (constraint_match(c, event->hw.config)) { event->hw.flags |= c->flags; return c; } @@ -906,17 +926,87 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) if (cpuc->n_pebs == cpuc->n_large_pebs) { threshold = ds->pebs_absolute_maximum - - reserved * x86_pmu.pebs_record_size; + reserved * cpuc->pebs_record_size; } else { - threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; + threshold = ds->pebs_buffer_base + cpuc->pebs_record_size; } ds->pebs_interrupt_threshold = threshold; } +static void adaptive_pebs_record_size_update(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 pebs_data_cfg = cpuc->pebs_data_cfg; + int sz = sizeof(struct pebs_basic); + + if (pebs_data_cfg & PEBS_DATACFG_MEMINFO) + sz += sizeof(struct pebs_meminfo); + if (pebs_data_cfg & PEBS_DATACFG_GP) + sz += sizeof(struct pebs_gprs); + if (pebs_data_cfg & PEBS_DATACFG_XMMS) + sz += sizeof(struct pebs_xmm); + if (pebs_data_cfg & PEBS_DATACFG_LBRS) + sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry); + + cpuc->pebs_record_size = sz; +} + +#define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \ + PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \ + PERF_SAMPLE_TRANSACTION) + +static u64 pebs_update_adaptive_cfg(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + u64 sample_type = attr->sample_type; + u64 pebs_data_cfg = 0; + bool gprs, tsx_weight; + + if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) && + attr->precise_ip > 1) + return pebs_data_cfg; + + if (sample_type & PERF_PEBS_MEMINFO_TYPE) + pebs_data_cfg |= PEBS_DATACFG_MEMINFO; + + /* + * We need GPRs when: + * + user requested them + * + precise_ip < 2 for the non event IP + * + For RTM TSX weight we need GPRs for the abort code. + */ + gprs = (sample_type & PERF_SAMPLE_REGS_INTR) && + (attr->sample_regs_intr & PEBS_GP_REGS); + + tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) && + ((attr->config & INTEL_ARCH_EVENT_MASK) == + x86_pmu.rtm_abort_event); + + if (gprs || (attr->precise_ip < 2) || tsx_weight) + pebs_data_cfg |= PEBS_DATACFG_GP; + + if ((sample_type & PERF_SAMPLE_REGS_INTR) && + (attr->sample_regs_intr & PEBS_XMM_REGS)) + pebs_data_cfg |= PEBS_DATACFG_XMMS; + + if (sample_type & PERF_SAMPLE_BRANCH_STACK) { + /* + * For now always log all LBRs. Could configure this + * later. + */ + pebs_data_cfg |= PEBS_DATACFG_LBRS | + ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT); + } + + return pebs_data_cfg; +} + static void -pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu) +pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, + struct perf_event *event, bool add) { + struct pmu *pmu = event->ctx->pmu; /* * Make sure we get updated with the first PEBS * event. It will trigger also during removal, but @@ -933,6 +1023,29 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu) update = true; } + /* + * The PEBS record doesn't shrink on pmu::del(). Doing so would require + * iterating all remaining PEBS events to reconstruct the config. + */ + if (x86_pmu.intel_cap.pebs_baseline && add) { + u64 pebs_data_cfg; + + /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */ + if (cpuc->n_pebs == 1) { + cpuc->pebs_data_cfg = 0; + cpuc->pebs_record_size = sizeof(struct pebs_basic); + } + + pebs_data_cfg = pebs_update_adaptive_cfg(event); + + /* Update pebs_record_size if new event requires more data. */ + if (pebs_data_cfg & ~cpuc->pebs_data_cfg) { + cpuc->pebs_data_cfg |= pebs_data_cfg; + adaptive_pebs_record_size_update(); + update = true; + } + } + if (update) pebs_update_threshold(cpuc); } @@ -947,7 +1060,7 @@ void intel_pmu_pebs_add(struct perf_event *event) if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs++; - pebs_update_state(needed_cb, cpuc, event->ctx->pmu); + pebs_update_state(needed_cb, cpuc, event, true); } void intel_pmu_pebs_enable(struct perf_event *event) @@ -960,11 +1073,19 @@ void intel_pmu_pebs_enable(struct perf_event *event) cpuc->pebs_enabled |= 1ULL << hwc->idx; - if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) + if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5)) cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled |= 1ULL << 63; + if (x86_pmu.intel_cap.pebs_baseline) { + hwc->config |= ICL_EVENTSEL_ADAPTIVE; + if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) { + wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg); + cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg; + } + } + /* * Use auto-reload if possible to save a MSR write in the PMI. * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD. @@ -991,7 +1112,7 @@ void intel_pmu_pebs_del(struct perf_event *event) if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs--; - pebs_update_state(needed_cb, cpuc, event->ctx->pmu); + pebs_update_state(needed_cb, cpuc, event, false); } void intel_pmu_pebs_disable(struct perf_event *event) @@ -1004,7 +1125,8 @@ void intel_pmu_pebs_disable(struct perf_event *event) cpuc->pebs_enabled &= ~(1ULL << hwc->idx); - if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) + if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && + (x86_pmu.version < 5)) cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32)); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); @@ -1125,34 +1247,57 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } -static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs) +static inline u64 intel_get_tsx_weight(u64 tsx_tuning) { - if (pebs->tsx_tuning) { - union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning }; + if (tsx_tuning) { + union hsw_tsx_tuning tsx = { .value = tsx_tuning }; return tsx.cycles_last_block; } return 0; } -static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs) +static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax) { - u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; + u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; /* For RTM XABORTs also log the abort code from AX */ - if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1)) - txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT; + if ((txn & PERF_TXN_TRANSACTION) && (ax & 1)) + txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT; return txn; } -static void setup_pebs_sample_data(struct perf_event *event, - struct pt_regs *iregs, void *__pebs, - struct perf_sample_data *data, - struct pt_regs *regs) +static inline u64 get_pebs_status(void *n) { + if (x86_pmu.intel_cap.pebs_format < 4) + return ((struct pebs_record_nhm *)n)->status; + return ((struct pebs_basic *)n)->applicable_counters; +} + #define PERF_X86_EVENT_PEBS_HSW_PREC \ (PERF_X86_EVENT_PEBS_ST_HSW | \ PERF_X86_EVENT_PEBS_LD_HSW | \ PERF_X86_EVENT_PEBS_NA_HSW) + +static u64 get_data_src(struct perf_event *event, u64 aux) +{ + u64 val = PERF_MEM_NA; + int fl = event->hw.flags; + bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); + + if (fl & PERF_X86_EVENT_PEBS_LDLAT) + val = load_latency_data(aux); + else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) + val = precise_datala_hsw(event, aux); + else if (fst) + val = precise_store_data(aux); + return val; +} + +static void setup_pebs_fixed_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) +{ /* * We cast to the biggest pebs_record but are careful not to * unconditionally access the 'extra' entries. @@ -1160,17 +1305,13 @@ static void setup_pebs_sample_data(struct perf_event *event, struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_record_skl *pebs = __pebs; u64 sample_type; - int fll, fst, dsrc; - int fl = event->hw.flags; + int fll; if (pebs == NULL) return; sample_type = event->attr.sample_type; - dsrc = sample_type & PERF_SAMPLE_DATA_SRC; - - fll = fl & PERF_X86_EVENT_PEBS_LDLAT; - fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); + fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; perf_sample_data_init(data, 0, event->hw.last_period); @@ -1185,16 +1326,8 @@ static void setup_pebs_sample_data(struct perf_event *event, /* * data.data_src encodes the data source */ - if (dsrc) { - u64 val = PERF_MEM_NA; - if (fll) - val = load_latency_data(pebs->dse); - else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) - val = precise_datala_hsw(event, pebs->dse); - else if (fst) - val = precise_store_data(pebs->dse); - data->data_src.val = val; - } + if (sample_type & PERF_SAMPLE_DATA_SRC) + data->data_src.val = get_data_src(event, pebs->dse); /* * We must however always use iregs for the unwinder to stay sane; the @@ -1281,10 +1414,11 @@ static void setup_pebs_sample_data(struct perf_event *event, if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data->weight = intel_hsw_weight(pebs); + data->weight = intel_get_tsx_weight(pebs->tsx_tuning); if (sample_type & PERF_SAMPLE_TRANSACTION) - data->txn = intel_hsw_transaction(pebs); + data->txn = intel_get_tsx_transaction(pebs->tsx_tuning, + pebs->ax); } /* @@ -1301,6 +1435,140 @@ static void setup_pebs_sample_data(struct perf_event *event, data->br_stack = &cpuc->lbr_stack; } +static void adaptive_pebs_save_regs(struct pt_regs *regs, + struct pebs_gprs *gprs) +{ + regs->ax = gprs->ax; + regs->bx = gprs->bx; + regs->cx = gprs->cx; + regs->dx = gprs->dx; + regs->si = gprs->si; + regs->di = gprs->di; + regs->bp = gprs->bp; + regs->sp = gprs->sp; +#ifndef CONFIG_X86_32 + regs->r8 = gprs->r8; + regs->r9 = gprs->r9; + regs->r10 = gprs->r10; + regs->r11 = gprs->r11; + regs->r12 = gprs->r12; + regs->r13 = gprs->r13; + regs->r14 = gprs->r14; + regs->r15 = gprs->r15; +#endif +} + +/* + * With adaptive PEBS the layout depends on what fields are configured. + */ + +static void setup_pebs_adaptive_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct pebs_basic *basic = __pebs; + void *next_record = basic + 1; + u64 sample_type; + u64 format_size; + struct pebs_meminfo *meminfo = NULL; + struct pebs_gprs *gprs = NULL; + struct x86_perf_regs *perf_regs; + + if (basic == NULL) + return; + + perf_regs = container_of(regs, struct x86_perf_regs, regs); + perf_regs->xmm_regs = NULL; + + sample_type = event->attr.sample_type; + format_size = basic->format_size; + perf_sample_data_init(data, 0, event->hw.last_period); + data->period = event->hw.last_period; + + if (event->attr.use_clockid == 0) + data->time = native_sched_clock_from_tsc(basic->tsc); + + /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happened between the record and + * PMI. + */ + if (sample_type & PERF_SAMPLE_CALLCHAIN) + data->callchain = perf_callchain(event, iregs); + + *regs = *iregs; + /* The ip in basic is EventingIP */ + set_linear_ip(regs, basic->ip); + regs->flags = PERF_EFLAGS_EXACT; + + /* + * The record for MEMINFO is in front of GP + * But PERF_SAMPLE_TRANSACTION needs gprs->ax. + * Save the pointer here but process later. + */ + if (format_size & PEBS_DATACFG_MEMINFO) { + meminfo = next_record; + next_record = meminfo + 1; + } + + if (format_size & PEBS_DATACFG_GP) { + gprs = next_record; + next_record = gprs + 1; + + if (event->attr.precise_ip < 2) { + set_linear_ip(regs, gprs->ip); + regs->flags &= ~PERF_EFLAGS_EXACT; + } + + if (sample_type & PERF_SAMPLE_REGS_INTR) + adaptive_pebs_save_regs(regs, gprs); + } + + if (format_size & PEBS_DATACFG_MEMINFO) { + if (sample_type & PERF_SAMPLE_WEIGHT) + data->weight = meminfo->latency ?: + intel_get_tsx_weight(meminfo->tsx_tuning); + + if (sample_type & PERF_SAMPLE_DATA_SRC) + data->data_src.val = get_data_src(event, meminfo->aux); + + if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) + data->addr = meminfo->address; + + if (sample_type & PERF_SAMPLE_TRANSACTION) + data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning, + gprs ? gprs->ax : 0); + } + + if (format_size & PEBS_DATACFG_XMMS) { + struct pebs_xmm *xmm = next_record; + + next_record = xmm + 1; + perf_regs->xmm_regs = xmm->xmm; + } + + if (format_size & PEBS_DATACFG_LBRS) { + struct pebs_lbr *lbr = next_record; + int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT) + & 0xff) + 1; + next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry); + + if (has_branch_stack(event)) { + intel_pmu_store_pebs_lbrs(lbr); + data->br_stack = &cpuc->lbr_stack; + } + } + + WARN_ONCE(next_record != __pebs + (format_size >> 48), + "PEBS record size %llu, expected %llu, config %llx\n", + format_size >> 48, + (u64)(next_record - __pebs), + basic->format_size); +} + static inline void * get_next_pebs_record_by_bit(void *base, void *top, int bit) { @@ -1318,19 +1586,19 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) if (base == NULL) return NULL; - for (at = base; at < top; at += x86_pmu.pebs_record_size) { - struct pebs_record_nhm *p = at; + for (at = base; at < top; at += cpuc->pebs_record_size) { + unsigned long status = get_pebs_status(at); - if (test_bit(bit, (unsigned long *)&p->status)) { + if (test_bit(bit, (unsigned long *)&status)) { /* PEBS v3 has accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) return at; - if (p->status == (1 << bit)) + if (status == (1 << bit)) return at; /* clear non-PEBS bit and re-check */ - pebs_status = p->status & cpuc->pebs_enabled; + pebs_status = status & cpuc->pebs_enabled; pebs_status &= PEBS_COUNTER_MASK; if (pebs_status == (1 << bit)) return at; @@ -1410,11 +1678,18 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *base, void *top, - int bit, int count) + int bit, int count, + void (*setup_sample)(struct perf_event *, + struct pt_regs *, + void *, + struct perf_sample_data *, + struct pt_regs *)) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; struct perf_sample_data data; - struct pt_regs regs; + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { @@ -1429,20 +1704,20 @@ static void __intel_pmu_pebs_event(struct perf_event *event, return; while (count > 1) { - setup_pebs_sample_data(event, iregs, at, &data, ®s); - perf_event_output(event, &data, ®s); - at += x86_pmu.pebs_record_size; + setup_sample(event, iregs, at, &data, regs); + perf_event_output(event, &data, regs); + at += cpuc->pebs_record_size; at = get_next_pebs_record_by_bit(at, top, bit); count--; } - setup_pebs_sample_data(event, iregs, at, &data, ®s); + setup_sample(event, iregs, at, &data, regs); /* * All but the last records are processed. * The last one is left to be able to call the overflow handler. */ - if (perf_event_overflow(event, &data, ®s)) { + if (perf_event_overflow(event, &data, regs)) { x86_pmu_stop(event, 0); return; } @@ -1483,7 +1758,27 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) return; } - __intel_pmu_pebs_event(event, iregs, at, top, 0, n); + __intel_pmu_pebs_event(event, iregs, at, top, 0, n, + setup_pebs_fixed_sample_data); +} + +static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size) +{ + struct perf_event *event; + int bit; + + /* + * The drain_pebs() could be called twice in a short period + * for auto-reload event in pmu::read(). There are no + * overflows have happened in between. + * It needs to call intel_pmu_save_and_restart_reload() to + * update the event->count for this case. + */ + for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) { + event = cpuc->events[bit]; + if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) + intel_pmu_save_and_restart_reload(event, 0); + } } static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) @@ -1513,19 +1808,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) } if (unlikely(base >= top)) { - /* - * The drain_pebs() could be called twice in a short period - * for auto-reload event in pmu::read(). There are no - * overflows have happened in between. - * It needs to call intel_pmu_save_and_restart_reload() to - * update the event->count for this case. - */ - for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, - size) { - event = cpuc->events[bit]; - if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) - intel_pmu_save_and_restart_reload(event, 0); - } + intel_pmu_pebs_event_update_no_drain(cpuc, size); return; } @@ -1538,8 +1821,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) /* PEBS v3 has more accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) { - for_each_set_bit(bit, (unsigned long *)&pebs_status, - size) + for_each_set_bit(bit, (unsigned long *)&pebs_status, size) counts[bit]++; continue; @@ -1578,8 +1860,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * If collision happened, the record will be dropped. */ if (p->status != (1ULL << bit)) { - for_each_set_bit(i, (unsigned long *)&pebs_status, - x86_pmu.max_pebs_events) + for_each_set_bit(i, (unsigned long *)&pebs_status, size) error[i]++; continue; } @@ -1587,7 +1868,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) counts[bit]++; } - for (bit = 0; bit < size; bit++) { + for_each_set_bit(bit, (unsigned long *)&mask, size) { if ((counts[bit] == 0) && (error[bit] == 0)) continue; @@ -1608,11 +1889,66 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) if (counts[bit]) { __intel_pmu_pebs_event(event, iregs, base, - top, bit, counts[bit]); + top, bit, counts[bit], + setup_pebs_fixed_sample_data); } } } +static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) +{ + short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct perf_event *event; + void *base, *at, *top; + int bit, size; + u64 mask; + + if (!x86_pmu.pebs_active) + return; + + base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_basic *)(unsigned long)ds->pebs_index; + + ds->pebs_index = ds->pebs_buffer_base; + + mask = ((1ULL << x86_pmu.max_pebs_events) - 1) | + (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED); + size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed; + + if (unlikely(base >= top)) { + intel_pmu_pebs_event_update_no_drain(cpuc, size); + return; + } + + for (at = base; at < top; at += cpuc->pebs_record_size) { + u64 pebs_status; + + pebs_status = get_pebs_status(at) & cpuc->pebs_enabled; + pebs_status &= mask; + + for_each_set_bit(bit, (unsigned long *)&pebs_status, size) + counts[bit]++; + } + + for_each_set_bit(bit, (unsigned long *)&mask, size) { + if (counts[bit] == 0) + continue; + + event = cpuc->events[bit]; + if (WARN_ON_ONCE(!event)) + continue; + + if (WARN_ON_ONCE(!event->attr.precise_ip)) + continue; + + __intel_pmu_pebs_event(event, iregs, base, + top, bit, counts[bit], + setup_pebs_adaptive_sample_data); + } +} + /* * BTS, PEBS probe and setup */ @@ -1628,12 +1964,18 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; - if (x86_pmu.version <= 4) + if (x86_pmu.version <= 4) { x86_pmu.pebs_no_isolation = 1; + x86_pmu.pebs_no_xmm_regs = 1; + } if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; + char *pebs_qual = ""; int format = x86_pmu.intel_cap.pebs_format; + if (format < 4) + x86_pmu.intel_cap.pebs_baseline = 0; + switch (format) { case 0: pr_cont("PEBS fmt0%c, ", pebs_type); @@ -1669,6 +2011,29 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; + case 4: + x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl; + x86_pmu.pebs_record_size = sizeof(struct pebs_basic); + if (x86_pmu.intel_cap.pebs_baseline) { + x86_pmu.large_pebs_flags |= + PERF_SAMPLE_BRANCH_STACK | + PERF_SAMPLE_TIME; + x86_pmu.flags |= PMU_FL_PEBS_ALL; + pebs_qual = "-baseline"; + } else { + /* Only basic record supported */ + x86_pmu.pebs_no_xmm_regs = 1; + x86_pmu.large_pebs_flags &= + ~(PERF_SAMPLE_ADDR | + PERF_SAMPLE_TIME | + PERF_SAMPLE_DATA_SRC | + PERF_SAMPLE_TRANSACTION | + PERF_SAMPLE_REGS_USER | + PERF_SAMPLE_REGS_INTR); + } + pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual); + break; + default: pr_cont("no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 580c1b91c454..6f814a27416b 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -488,6 +488,8 @@ void intel_pmu_lbr_add(struct perf_event *event) * be 'new'. Conversely, a new event can get installed through the * context switch path for the first time. */ + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0) + cpuc->lbr_pebs_users++; perf_sched_cb_inc(event->ctx->pmu); if (!cpuc->lbr_users++ && !event->total_time_running) intel_pmu_lbr_reset(); @@ -507,8 +509,11 @@ void intel_pmu_lbr_del(struct perf_event *event) task_ctx->lbr_callstack_users--; } + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0) + cpuc->lbr_pebs_users--; cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); + WARN_ON_ONCE(cpuc->lbr_pebs_users < 0); perf_sched_cb_dec(event->ctx->pmu); } @@ -658,7 +663,13 @@ void intel_pmu_lbr_read(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - if (!cpuc->lbr_users) + /* + * Don't read when all LBRs users are using adaptive PEBS. + * + * This could be smarter and actually check the event, + * but this simple approach seems to work for now. + */ + if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users) return; if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) @@ -1080,6 +1091,28 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) } } +void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int i; + + cpuc->lbr_stack.nr = x86_pmu.lbr_nr; + for (i = 0; i < x86_pmu.lbr_nr; i++) { + u64 info = lbr->lbr[i].info; + struct perf_branch_entry *e = &cpuc->lbr_entries[i]; + + e->from = lbr->lbr[i].from; + e->to = lbr->lbr[i].to; + e->mispred = !!(info & LBR_INFO_MISPRED); + e->predicted = !(info & LBR_INFO_MISPRED); + e->in_tx = !!(info & LBR_INFO_IN_TX); + e->abort = !!(info & LBR_INFO_ABORT); + e->cycles = info & LBR_INFO_CYCLES; + e->reserved = 0; + } + intel_pmu_lbr_filter(cpuc); +} + /* * Map interface branch filters onto LBR filters */ diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index fb3a2f13fc70..339d7628080c 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -1525,8 +1525,7 @@ static __init int pt_init(void) } if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) - pt_pmu.pmu.capabilities = - PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF; + pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG; pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE; pt_pmu.pmu.attr_groups = pt_attr_groups; diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 94dc564146ca..37ebf6fc5415 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -775,6 +775,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init), + + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init), {}, }; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 9fe64c01a2e5..fc40a1473058 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1367,6 +1367,11 @@ static const struct intel_uncore_init_fun skx_uncore_init __initconst = { .pci_init = skx_uncore_pci_init, }; +static const struct intel_uncore_init_fun icl_uncore_init __initconst = { + .cpu_init = icl_uncore_cpu_init, + .pci_init = skl_uncore_pci_init, +}; + static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init), @@ -1393,6 +1398,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { 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), {}, }; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 853a49a8ccf6..79eb2e21e4f0 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -512,6 +512,7 @@ int skl_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); +void icl_uncore_cpu_init(void); int snb_pci2phy_map_init(int devid); /* uncore_snbep.c */ diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 13493f43b247..f8431819b3e1 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -34,6 +34,8 @@ #define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33 #define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca #define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32 +#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02 +#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -93,6 +95,12 @@ #define SKL_UNC_PERF_GLOBAL_CTL 0xe01 #define SKL_UNC_GLOBAL_CTL_CORE_ALL ((1 << 5) - 1) +/* ICL Cbo register */ +#define ICL_UNC_CBO_CONFIG 0x396 +#define ICL_UNC_NUM_CBO_MASK 0xf +#define ICL_UNC_CBO_0_PER_CTR0 0x702 +#define ICL_UNC_CBO_MSR_OFFSET 0x8 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); @@ -280,6 +288,70 @@ void skl_uncore_cpu_init(void) snb_uncore_arb.ops = &skl_uncore_msr_ops; } +static struct intel_uncore_type icl_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .perf_ctr_bits = 44, + .perf_ctr = ICL_UNC_CBO_0_PER_CTR0, + .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = ICL_UNC_CBO_MSR_OFFSET, + .ops = &skl_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + +static struct uncore_event_desc icl_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"), + { /* end: all zeroes */ }, +}; + +static struct attribute *icl_uncore_clock_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group icl_uncore_clock_format_group = { + .name = "format", + .attrs = icl_uncore_clock_formats_attr, +}; + +static struct intel_uncore_type icl_uncore_clockbox = { + .name = "clock", + .num_counters = 1, + .num_boxes = 1, + .fixed_ctr_bits = 48, + .fixed_ctr = SNB_UNC_FIXED_CTR, + .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_CTL_EV_SEL_MASK, + .format_group = &icl_uncore_clock_format_group, + .ops = &skl_uncore_msr_ops, + .event_descs = icl_uncore_events, +}; + +static struct intel_uncore_type *icl_msr_uncores[] = { + &icl_uncore_cbox, + &snb_uncore_arb, + &icl_uncore_clockbox, + NULL, +}; + +static int icl_get_cbox_num(void) +{ + u64 num_boxes; + + rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes); + + return num_boxes & ICL_UNC_NUM_CBO_MASK; +} + +void icl_uncore_cpu_init(void) +{ + uncore_msr_uncores = icl_msr_uncores; + icl_uncore_cbox.num_boxes = icl_get_cbox_num(); + snb_uncore_arb.ops = &skl_uncore_msr_ops; +} + enum { SNB_PCI_UNCORE_IMC, }; @@ -668,6 +740,18 @@ static const struct pci_device_id skl_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id icl_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -693,6 +777,11 @@ static struct pci_driver skl_uncore_pci_driver = { .id_table = skl_uncore_pci_ids, }; +static struct pci_driver icl_uncore_pci_driver = { + .name = "icl_uncore", + .id_table = icl_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -732,6 +821,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */ IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */ IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */ + IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */ + IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */ { /* end marker */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index a878e6286e4a..f3f4c2263501 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -89,6 +89,7 @@ static bool test_intel(int idx) case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_KABYLAKE_MOBILE: case INTEL_FAM6_KABYLAKE_DESKTOP: + case INTEL_FAM6_ICELAKE_MOBILE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index a75955741c50..07fc84bb85c1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -49,28 +49,33 @@ struct event_constraint { unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; u64 idxmsk64; }; - u64 code; - u64 cmask; - int weight; - int overlap; - int flags; + u64 code; + u64 cmask; + int weight; + int overlap; + int flags; + unsigned int size; }; + +static inline bool constraint_match(struct event_constraint *c, u64 ecode) +{ + return ((ecode & c->cmask) - c->code) <= (u64)c->size; +} + /* * struct hw_perf_event.flags flags */ #define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */ #define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */ #define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */ -#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ -#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ -#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ -#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */ - +#define PERF_X86_EVENT_PEBS_LD_HSW 0x0008 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */ +#define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */ +#define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */ +#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */ +#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 */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -96,25 +101,43 @@ struct amd_nb { PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \ PERF_SAMPLE_PERIOD) -#define PEBS_REGS \ - (PERF_REG_X86_AX | \ - PERF_REG_X86_BX | \ - PERF_REG_X86_CX | \ - PERF_REG_X86_DX | \ - PERF_REG_X86_DI | \ - PERF_REG_X86_SI | \ - PERF_REG_X86_SP | \ - PERF_REG_X86_BP | \ - PERF_REG_X86_IP | \ - PERF_REG_X86_FLAGS | \ - PERF_REG_X86_R8 | \ - PERF_REG_X86_R9 | \ - PERF_REG_X86_R10 | \ - PERF_REG_X86_R11 | \ - PERF_REG_X86_R12 | \ - PERF_REG_X86_R13 | \ - PERF_REG_X86_R14 | \ - PERF_REG_X86_R15) +#define PEBS_GP_REGS \ + ((1ULL << PERF_REG_X86_AX) | \ + (1ULL << PERF_REG_X86_BX) | \ + (1ULL << PERF_REG_X86_CX) | \ + (1ULL << PERF_REG_X86_DX) | \ + (1ULL << PERF_REG_X86_DI) | \ + (1ULL << PERF_REG_X86_SI) | \ + (1ULL << PERF_REG_X86_SP) | \ + (1ULL << PERF_REG_X86_BP) | \ + (1ULL << PERF_REG_X86_IP) | \ + (1ULL << PERF_REG_X86_FLAGS) | \ + (1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15)) + +#define PEBS_XMM_REGS \ + ((1ULL << PERF_REG_X86_XMM0) | \ + (1ULL << PERF_REG_X86_XMM1) | \ + (1ULL << PERF_REG_X86_XMM2) | \ + (1ULL << PERF_REG_X86_XMM3) | \ + (1ULL << PERF_REG_X86_XMM4) | \ + (1ULL << PERF_REG_X86_XMM5) | \ + (1ULL << PERF_REG_X86_XMM6) | \ + (1ULL << PERF_REG_X86_XMM7) | \ + (1ULL << PERF_REG_X86_XMM8) | \ + (1ULL << PERF_REG_X86_XMM9) | \ + (1ULL << PERF_REG_X86_XMM10) | \ + (1ULL << PERF_REG_X86_XMM11) | \ + (1ULL << PERF_REG_X86_XMM12) | \ + (1ULL << PERF_REG_X86_XMM13) | \ + (1ULL << PERF_REG_X86_XMM14) | \ + (1ULL << PERF_REG_X86_XMM15)) /* * Per register state. @@ -207,10 +230,16 @@ struct cpu_hw_events { int n_pebs; int n_large_pebs; + /* Current super set of events hardware configuration */ + u64 pebs_data_cfg; + u64 active_pebs_data_cfg; + int pebs_record_size; + /* * Intel LBR bits */ int lbr_users; + int lbr_pebs_users; struct perf_branch_stack lbr_stack; struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; struct er_account *lbr_sel; @@ -257,18 +286,29 @@ struct cpu_hw_events { void *kfree_on_online[X86_PERF_KFREE_MAX]; }; -#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\ +#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \ { .idxmsk64 = (n) }, \ .code = (c), \ + .size = (e) - (c), \ .cmask = (m), \ .weight = (w), \ .overlap = (o), \ .flags = f, \ } +#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \ + __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f) + #define EVENT_CONSTRAINT(c, n, m) \ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0) +/* + * The constraint_match() function only works for 'simple' event codes + * and not for extended (AMD64_EVENTSEL_EVENT) events codes. + */ +#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \ + __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0) + #define INTEL_EXCLEVT_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\ 0, PERF_X86_EVENT_EXCL) @@ -304,6 +344,12 @@ struct cpu_hw_events { EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) /* + * Constraint on a range of Event codes + */ +#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT) + +/* * Constraint on the Event code + UMask + fixed-mask * * filter mask to validate fixed counter events. @@ -350,6 +396,9 @@ struct cpu_hw_events { #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) +#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) + /* Check only flags, but allow all event/umask */ #define INTEL_ALL_EVENT_CONSTRAINT(code, n) \ EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS) @@ -366,6 +415,11 @@ struct cpu_hw_events { ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \ + __EVENT_CONSTRAINT_RANGE(code, end, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \ __EVENT_CONSTRAINT(code, n, \ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ @@ -473,6 +527,7 @@ union perf_capabilities { * values > 32bit. */ u64 full_width_write:1; + u64 pebs_baseline:1; }; u64 capabilities; }; @@ -613,14 +668,16 @@ struct x86_pmu { pebs_broken :1, pebs_prec_dist :1, pebs_no_tlb :1, - pebs_no_isolation :1; + pebs_no_isolation :1, + pebs_no_xmm_regs :1; int pebs_record_size; int pebs_buffer_size; + int max_pebs_events; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); - int max_pebs_events; unsigned long large_pebs_flags; + u64 rtm_abort_event; /* * Intel LBR @@ -714,6 +771,7 @@ static struct perf_pmu_events_ht_attr event_attr_##v = { \ .event_str_ht = ht, \ } +struct pmu *x86_get_pmu(void); extern struct x86_pmu x86_pmu __read_mostly; static inline bool x86_pmu_has_lbr_callstack(void) @@ -941,6 +999,8 @@ extern struct event_constraint intel_bdw_pebs_event_constraints[]; extern struct event_constraint intel_skl_pebs_event_constraints[]; +extern struct event_constraint intel_icl_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_add(struct perf_event *event); @@ -959,6 +1019,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); void intel_pmu_auto_reload_read(struct perf_event *event); +void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 6461a16b4559..e4ba467a9fc6 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -103,9 +103,13 @@ static int hv_cpu_init(unsigned int cpu) u64 msr_vp_index; struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; void **input_arg; + struct page *pg; input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - *input_arg = page_address(alloc_page(GFP_KERNEL)); + pg = alloc_page(GFP_KERNEL); + if (unlikely(!pg)) + return -ENOMEM; + *input_arg = page_address(pg); hv_get_vp_index(msr_vp_index); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 321fe5f5d0e9..4d5fcd47ab75 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -61,9 +61,8 @@ } while (0) #define RELOAD_SEG(seg) { \ - unsigned int pre = GET_SEG(seg); \ + unsigned int pre = (seg) | 3; \ unsigned int cur = get_user_seg(seg); \ - pre |= 3; \ if (pre != cur) \ set_user_seg(seg, pre); \ } @@ -72,6 +71,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, struct sigcontext_32 __user *sc) { unsigned int tmpflags, err = 0; + u16 gs, fs, es, ds; void __user *buf; u32 tmp; @@ -79,16 +79,10 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, current->restart_block.fn = do_no_restart_syscall; get_user_try { - /* - * Reload fs and gs if they have changed in the signal - * handler. This does not handle long fs/gs base changes in - * the handler, but does not clobber them at least in the - * normal case. - */ - RELOAD_SEG(gs); - RELOAD_SEG(fs); - RELOAD_SEG(ds); - RELOAD_SEG(es); + gs = GET_SEG(gs); + fs = GET_SEG(fs); + ds = GET_SEG(ds); + es = GET_SEG(es); COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); COPY(dx); COPY(cx); COPY(ip); COPY(ax); @@ -106,6 +100,17 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, buf = compat_ptr(tmp); } get_user_catch(err); + /* + * Reload fs and gs if they have changed in the signal + * handler. This does not handle long fs/gs base changes in + * the handler, but does not clobber them at least in the + * normal case. + */ + RELOAD_SEG(gs); + RELOAD_SEG(fs); + RELOAD_SEG(ds); + RELOAD_SEG(es); + err |= fpu__restore_sig(buf, 1); force_iret(); diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index 31b627b43a8e..464034db299f 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -20,6 +20,17 @@ #endif /* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +.macro ANNOTATE_IGNORE_ALTERNATIVE + .Lannotate_\@: + .pushsection .discard.ignore_alts + .long .Lannotate_\@ - . + .popsection +.endm + +/* * Issue one struct alt_instr descriptor entry (need to put it into * the section .altinstructions, see below). This entry contains * enough information for the alternatives patching code to patch an diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 4c74073a19cc..094fbc9c0b1c 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -45,6 +45,16 @@ #define LOCK_PREFIX "" #endif +/* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +#define ANNOTATE_IGNORE_ALTERNATIVE \ + "999:\n\t" \ + ".pushsection .discard.ignore_alts\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" + struct alt_instr { s32 instr_offset; /* original instruction */ s32 repl_offset; /* offset to replacement instruction */ diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 6467757bb39f..3ff577c0b102 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -148,30 +148,6 @@ _ASM_PTR (entry); \ .popsection -.macro ALIGN_DESTINATION - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jz 102f /* already aligned */ - subl $8,%ecx - negl %ecx - subl %ecx,%edx -100: movb (%rsi),%al -101: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 100b -102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE_UA(100b, 103b) - _ASM_EXTABLE_UA(101b, 103b) - .endm - #else # define _EXPAND_EXTABLE_HANDLE(x) #x # define _ASM_EXTABLE_HANDLE(from, to, handler) \ diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index d153d570bb04..8e790ec219a5 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -36,16 +36,17 @@ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */ -#define BITOP_ADDR(x) "+m" (*(volatile long *) (x)) +#define RLONG_ADDR(x) "m" (*(volatile long *) (x)) +#define WBYTE_ADDR(x) "+m" (*(volatile char *) (x)) -#define ADDR BITOP_ADDR(addr) +#define ADDR RLONG_ADDR(addr) /* * 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) BITOP_ADDR((void *)(addr) + ((nr)>>3)) +#define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) /** @@ -73,7 +74,7 @@ set_bit(long nr, volatile unsigned long *addr) : "memory"); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" - : BITOP_ADDR(addr) : "Ir" (nr) : "memory"); + : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } @@ -88,7 +89,7 @@ set_bit(long nr, volatile unsigned long *addr) */ static __always_inline void __set_bit(long nr, volatile unsigned long *addr) { - asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory"); + asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } /** @@ -110,8 +111,7 @@ clear_bit(long nr, volatile unsigned long *addr) : "iq" ((u8)~CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" - : BITOP_ADDR(addr) - : "Ir" (nr)); + : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } @@ -131,7 +131,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) { - asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) @@ -139,7 +139,7 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile bool negative; asm volatile(LOCK_PREFIX "andb %2,%1" CC_SET(s) - : CC_OUT(s) (negative), ADDR + : CC_OUT(s) (negative), WBYTE_ADDR(addr) : "ir" ((char) ~(1 << nr)) : "memory"); return negative; } @@ -155,13 +155,9 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile * __clear_bit() is non-atomic and implies release semantics before the memory * operation. It can be used for an unlock if no other CPUs can concurrently * modify other bits in the word. - * - * No memory barrier is required here, because x86 cannot reorder stores past - * older loads. Same principle as spin_unlock. */ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) { - barrier(); __clear_bit(nr, addr); } @@ -176,7 +172,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long * */ static __always_inline void __change_bit(long nr, volatile unsigned long *addr) { - asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } /** @@ -196,8 +192,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) : "iq" ((u8)CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" - : BITOP_ADDR(addr) - : "Ir" (nr)); + : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } @@ -242,8 +237,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * asm(__ASM_SIZE(bts) " %2,%1" CC_SET(c) - : CC_OUT(c) (oldbit), ADDR - : "Ir" (nr)); + : CC_OUT(c) (oldbit) + : ADDR, "Ir" (nr) : "memory"); return oldbit; } @@ -282,8 +277,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long asm volatile(__ASM_SIZE(btr) " %2,%1" CC_SET(c) - : CC_OUT(c) (oldbit), ADDR - : "Ir" (nr)); + : CC_OUT(c) (oldbit) + : ADDR, "Ir" (nr) : "memory"); return oldbit; } @@ -294,8 +289,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon asm volatile(__ASM_SIZE(btc) " %2,%1" CC_SET(c) - : CC_OUT(c) (oldbit), ADDR - : "Ir" (nr) : "memory"); + : CC_OUT(c) (oldbit) + : ADDR, "Ir" (nr) : "memory"); return oldbit; } @@ -326,7 +321,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l asm volatile(__ASM_SIZE(bt) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) - : "m" (*(unsigned long *)addr), "Ir" (nr)); + : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); return oldbit; } diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index 3417110574c1..31c379c1da41 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CPU_DEVICE_ID -#define _CPU_DEVICE_ID 1 +#ifndef _ASM_X86_CPU_DEVICE_ID +#define _ASM_X86_CPU_DEVICE_ID /* * Declare drivers belonging to specific x86 CPUs @@ -9,8 +9,6 @@ #include <linux/mod_devicetable.h> -extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); - /* * Match specific microcode revisions. * @@ -22,21 +20,22 @@ extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); */ struct x86_cpu_desc { - __u8 x86_family; - __u8 x86_vendor; - __u8 x86_model; - __u8 x86_stepping; - __u32 x86_microcode_rev; + u8 x86_family; + u8 x86_vendor; + u8 x86_model; + u8 x86_stepping; + u32 x86_microcode_rev; }; -#define INTEL_CPU_DESC(mod, step, rev) { \ - .x86_family = 6, \ - .x86_vendor = X86_VENDOR_INTEL, \ - .x86_model = mod, \ - .x86_stepping = step, \ - .x86_microcode_rev = rev, \ +#define INTEL_CPU_DESC(model, stepping, revision) { \ + .x86_family = 6, \ + .x86_vendor = X86_VENDOR_INTEL, \ + .x86_model = (model), \ + .x86_stepping = (stepping), \ + .x86_microcode_rev = (revision), \ } +extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table); -#endif +#endif /* _ASM_X86_CPU_DEVICE_ID */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 6d6d5cc4302b..1d337c51f7e6 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -112,8 +112,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; test_cpu_cap(c, bit)) #define this_cpu_has(bit) \ - (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ - x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability)) + (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ + x86_this_cpu_test_bit(bit, \ + (unsigned long __percpu *)&cpu_info.x86_capability)) /* * This macro is for detection of features which need kernel diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h index ae26df1c2789..8380c3ddd4b2 100644 --- a/arch/x86/include/asm/intel_ds.h +++ b/arch/x86/include/asm/intel_ds.h @@ -8,7 +8,7 @@ /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS 8 -#define MAX_FIXED_PEBS_EVENTS 3 +#define MAX_FIXED_PEBS_EVENTS 4 /* * A debug store configuration. diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 93c4bf598fb0..feab24cac610 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -226,7 +226,9 @@ struct x86_emulate_ops { unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags); - int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase); + int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, + const char *smstate); + void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt); }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a5db4475e72d..c79abe7ca093 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -126,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) } #define KVM_PERMILLE_MMU_PAGES 20 -#define KVM_MIN_ALLOC_MMU_PAGES 64 +#define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 @@ -253,14 +253,14 @@ struct kvm_mmu_memory_cache { * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used * by indirect shadow page can not be more than 15 bits. * - * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access, + * Currently, we used 14 bits that are @level, @gpte_is_8_bytes, @quadrant, @access, * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; - unsigned cr4_pae:1; + unsigned gpte_is_8_bytes:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; @@ -295,6 +295,7 @@ union kvm_mmu_extended_role { unsigned int valid:1; unsigned int execonly:1; unsigned int cr0_pg:1; + unsigned int cr4_pae:1; unsigned int cr4_pse:1; unsigned int cr4_pke:1; unsigned int cr4_smap:1; @@ -350,6 +351,7 @@ struct kvm_mmu_page { }; struct kvm_pio_request { + unsigned long linear_rip; unsigned long count; int in; int port; @@ -568,6 +570,7 @@ struct kvm_vcpu_arch { bool tpr_access_reporting; u64 ia32_xss; u64 microcode_version; + u64 arch_capabilities; /* * Paging state of the vcpu @@ -842,9 +845,9 @@ enum kvm_irqchip_mode { }; struct kvm_arch { - unsigned int n_used_mmu_pages; - unsigned int n_requested_mmu_pages; - unsigned int n_max_mmu_pages; + unsigned long n_used_mmu_pages; + unsigned long n_requested_mmu_pages; + unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* @@ -1180,7 +1183,7 @@ struct kvm_x86_ops { int (*smi_allowed)(struct kvm_vcpu *vcpu); int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); - int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase); + int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); int (*enable_smi_window)(struct kvm_vcpu *vcpu); int (*mem_enc_op)(struct kvm *kvm, void __user *argp); @@ -1192,6 +1195,8 @@ struct kvm_x86_ops { int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu); + + bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { @@ -1252,8 +1257,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); -unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); +unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); bool pdptrs_changed(struct kvm_vcpu *vcpu); @@ -1588,4 +1593,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define put_smstate(type, buf, offset, val) \ *(type *)((buf) + (offset) - 0x7e00) = val +#define GET_SMSTATE(type, buf, offset) \ + (*(type *)((buf) + (offset) - 0x7e00)) + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ca5bc0eacb95..1378518cf63f 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -116,6 +116,7 @@ #define LBR_INFO_CYCLES 0xffff #define MSR_IA32_PEBS_ENABLE 0x000003f1 +#define MSR_PEBS_DATA_CFG 0x000003f2 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index dad12b767ba0..daf25b60c9e3 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -11,6 +11,15 @@ #include <asm/msr-index.h> /* + * This should be used immediately before a retpoline alternative. It tells + * objtool where the retpolines are so that it can make sense of the control + * flow by just reading the original instruction(s) and ignoring the + * alternatives. + */ +#define ANNOTATE_NOSPEC_ALTERNATIVE \ + ANNOTATE_IGNORE_ALTERNATIVE + +/* * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an @@ -57,19 +66,6 @@ #ifdef __ASSEMBLY__ /* - * This should be used immediately before a retpoline alternative. It tells - * objtool where the retpolines are so that it can make sense of the control - * flow by just reading the original instruction(s) and ignoring the - * alternatives. - */ -.macro ANNOTATE_NOSPEC_ALTERNATIVE - .Lannotate_\@: - .pushsection .discard.nospec - .long .Lannotate_\@ - . - .popsection -.endm - -/* * This should be used immediately before an indirect jump/call. It tells * objtool the subsequent indirect jump/call is vouched safe for retpoline * builds. @@ -152,12 +148,6 @@ #else /* __ASSEMBLY__ */ -#define ANNOTATE_NOSPEC_ALTERNATIVE \ - "999:\n\t" \ - ".pushsection .discard.nospec\n\t" \ - ".long 999b - .\n\t" \ - ".popsection\n\t" - #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8bdf74902293..1392d5e6e8d6 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -7,7 +7,7 @@ */ #define INTEL_PMC_MAX_GENERIC 32 -#define INTEL_PMC_MAX_FIXED 3 +#define INTEL_PMC_MAX_FIXED 4 #define INTEL_PMC_IDX_FIXED 32 #define X86_PMC_IDX_MAX 64 @@ -32,6 +32,8 @@ #define HSW_IN_TX (1ULL << 32) #define HSW_IN_TX_CHECKPOINTED (1ULL << 33) +#define ICL_EVENTSEL_ADAPTIVE (1ULL << 34) +#define ICL_FIXED_0_ADAPTIVE (1ULL << 32) #define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36) #define AMD64_EVENTSEL_GUESTONLY (1ULL << 40) @@ -87,6 +89,12 @@ #define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6 #define ARCH_PERFMON_EVENTS_COUNT 7 +#define PEBS_DATACFG_MEMINFO BIT_ULL(0) +#define PEBS_DATACFG_GP BIT_ULL(1) +#define PEBS_DATACFG_XMMS BIT_ULL(2) +#define PEBS_DATACFG_LBRS BIT_ULL(3) +#define PEBS_DATACFG_LBR_SHIFT 24 + /* * Intel "Architectural Performance Monitoring" CPUID * detection/enumeration details: @@ -177,6 +185,41 @@ struct x86_pmu_capability { #define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) /* + * Adaptive PEBS v4 + */ + +struct pebs_basic { + u64 format_size; + u64 ip; + u64 applicable_counters; + u64 tsc; +}; + +struct pebs_meminfo { + u64 address; + u64 aux; + u64 latency; + u64 tsx_tuning; +}; + +struct pebs_gprs { + u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di; + u64 r8, r9, r10, r11, r12, r13, r14, r15; +}; + +struct pebs_xmm { + u64 xmm[16*2]; /* two entries for each register */ +}; + +struct pebs_lbr_entry { + u64 from, to, info; +}; + +struct pebs_lbr { + struct pebs_lbr_entry lbr[0]; /* Variable length */ +}; + +/* * IBS cpuid feature detection */ @@ -248,6 +291,11 @@ extern void perf_events_lapic_init(void); #define PERF_EFLAGS_VM (1UL << 5) struct pt_regs; +struct x86_perf_regs { + struct pt_regs regs; + u64 *xmm_regs; +}; + extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) @@ -260,14 +308,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); */ #define perf_arch_fetch_caller_regs(regs, __ip) { \ (regs)->ip = (__ip); \ - (regs)->bp = caller_frame_pointer(); \ + (regs)->sp = (unsigned long)__builtin_frame_address(0); \ (regs)->cs = __KERNEL_CS; \ regs->flags = 0; \ - asm volatile( \ - _ASM_MOV "%%"_ASM_SP ", %0\n" \ - : "=m" ((regs)->sp) \ - :: "memory" \ - ); \ } struct perf_guest_switch_msr { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 2779ace16d23..50b3e2d963c9 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -46,7 +46,7 @@ void ptdump_walk_user_pgd_level_checkwx(void); */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __visible; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) +#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page)) extern spinlock_t pgd_lock; extern struct list_head pgd_list; diff --git a/arch/x86/include/asm/processor-cyrix.h b/arch/x86/include/asm/processor-cyrix.h index aaedd73ea2c6..df700a6cc869 100644 --- a/arch/x86/include/asm/processor-cyrix.h +++ b/arch/x86/include/asm/processor-cyrix.h @@ -3,19 +3,6 @@ * NSC/Cyrix CPU indexed register access. Must be inlined instead of * macros to ensure correct access ordering * Access order is always 0x22 (=offset), 0x23 (=value) - * - * When using the old macros a line like - * setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88); - * gets expanded to: - * do { - * outb((CX86_CCR2), 0x22); - * outb((({ - * outb((CX86_CCR2), 0x22); - * inb(0x23); - * }) | 0x88), 0x23); - * } while (0); - * - * which in fact violates the access order (= 0x22, 0x22, 0x23, 0x23). */ static inline u8 getCx86(u8 reg) @@ -29,11 +16,3 @@ static inline void setCx86(u8 reg, u8 data) outb(reg, 0x22); outb(data, 0x23); } - -#define getCx86_old(reg) ({ outb((reg), 0x22); inb(0x23); }) - -#define setCx86_old(reg, data) do { \ - outb((reg), 0x22); \ - outb((data), 0x23); \ -} while (0) - diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 63b3393bd98e..c53682303c9c 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -77,7 +77,11 @@ static inline size_t real_mode_size_needed(void) return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE); } -void set_real_mode_mem(phys_addr_t mem, size_t size); +static inline void set_real_mode_mem(phys_addr_t mem) +{ + real_mode_header = (struct real_mode_header *) __va(mem); +} + void reserve_real_mode(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h deleted file mode 100644 index 4c25cf6caefa..000000000000 --- a/arch/x86/include/asm/rwsem.h +++ /dev/null @@ -1,237 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+ - * - * Written by David Howells (dhowells@redhat.com). - * - * Derived from asm-x86/semaphore.h - * - * - * The MSW of the count is the negated number of active writers and waiting - * lockers, and the LSW is the total number of active locks - * - * The lock count is initialized to 0 (no active and no waiting lockers). - * - * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an - * uncontended lock. This can be determined because XADD returns the old value. - * Readers increment by 1 and see a positive value when uncontended, negative - * if there are writers (and maybe) readers waiting (in which case it goes to - * sleep). - * - * The value of WAITING_BIAS supports up to 32766 waiting processes. This can - * be extended to 65534 by manually checking the whole MSW rather than relying - * on the S flag. - * - * The value of ACTIVE_BIAS supports up to 65535 active processes. - * - * This should be totally fair - if anything is waiting, a process that wants a - * lock will go to the back of the queue. When the currently active lock is - * released, if there's a writer at the front of the queue, then that and only - * that will be woken up; if there's a bunch of consecutive readers at the - * front, then they'll all be woken up, but no other readers will be. - */ - -#ifndef _ASM_X86_RWSEM_H -#define _ASM_X86_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ -#include <asm/asm.h> - -/* - * The bias values and the counter type limits the number of - * potential readers/writers to 32767 for 32 bits and 2147483647 - * for 64 bits. - */ - -#ifdef CONFIG_X86_64 -# define RWSEM_ACTIVE_MASK 0xffffffffL -#else -# define RWSEM_ACTIVE_MASK 0x0000ffffL -#endif - -#define RWSEM_UNLOCKED_VALUE 0x00000000L -#define RWSEM_ACTIVE_BIAS 0x00000001L -#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -#define ____down_read(sem, slow_path) \ -({ \ - struct rw_semaphore* ret; \ - asm volatile("# beginning down_read\n\t" \ - LOCK_PREFIX _ASM_INC "(%[sem])\n\t" \ - /* adds 0x00000001 */ \ - " jns 1f\n" \ - " call " slow_path "\n" \ - "1:\n\t" \ - "# ending down_read\n\t" \ - : "+m" (sem->count), "=a" (ret), \ - ASM_CALL_CONSTRAINT \ - : [sem] "a" (sem) \ - : "memory", "cc"); \ - ret; \ -}) - -static inline void __down_read(struct rw_semaphore *sem) -{ - ____down_read(sem, "call_rwsem_down_read_failed"); -} - -static inline int __down_read_killable(struct rw_semaphore *sem) -{ - if (IS_ERR(____down_read(sem, "call_rwsem_down_read_failed_killable"))) - return -EINTR; - return 0; -} - -/* - * trylock for reading -- returns 1 if successful, 0 if contention - */ -static inline bool __down_read_trylock(struct rw_semaphore *sem) -{ - long result, tmp; - asm volatile("# beginning __down_read_trylock\n\t" - " mov %[count],%[result]\n\t" - "1:\n\t" - " mov %[result],%[tmp]\n\t" - " add %[inc],%[tmp]\n\t" - " jle 2f\n\t" - LOCK_PREFIX " cmpxchg %[tmp],%[count]\n\t" - " jnz 1b\n\t" - "2:\n\t" - "# ending __down_read_trylock\n\t" - : [count] "+m" (sem->count), [result] "=&a" (result), - [tmp] "=&r" (tmp) - : [inc] "i" (RWSEM_ACTIVE_READ_BIAS) - : "memory", "cc"); - return result >= 0; -} - -/* - * lock for writing - */ -#define ____down_write(sem, slow_path) \ -({ \ - long tmp; \ - struct rw_semaphore* ret; \ - \ - asm volatile("# beginning down_write\n\t" \ - LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" \ - /* adds 0xffff0001, returns the old value */ \ - " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \ - /* was the active mask 0 before? */\ - " jz 1f\n" \ - " call " slow_path "\n" \ - "1:\n" \ - "# ending down_write" \ - : "+m" (sem->count), [tmp] "=d" (tmp), \ - "=a" (ret), ASM_CALL_CONSTRAINT \ - : [sem] "a" (sem), "[tmp]" (RWSEM_ACTIVE_WRITE_BIAS) \ - : "memory", "cc"); \ - ret; \ -}) - -static inline void __down_write(struct rw_semaphore *sem) -{ - ____down_write(sem, "call_rwsem_down_write_failed"); -} - -static inline int __down_write_killable(struct rw_semaphore *sem) -{ - if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable"))) - return -EINTR; - - return 0; -} - -/* - * trylock for writing -- returns 1 if successful, 0 if contention - */ -static inline bool __down_write_trylock(struct rw_semaphore *sem) -{ - bool result; - long tmp0, tmp1; - asm volatile("# beginning __down_write_trylock\n\t" - " mov %[count],%[tmp0]\n\t" - "1:\n\t" - " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" - /* was the active mask 0 before? */ - " jnz 2f\n\t" - " mov %[tmp0],%[tmp1]\n\t" - " add %[inc],%[tmp1]\n\t" - LOCK_PREFIX " cmpxchg %[tmp1],%[count]\n\t" - " jnz 1b\n\t" - "2:\n\t" - CC_SET(e) - "# ending __down_write_trylock\n\t" - : [count] "+m" (sem->count), [tmp0] "=&a" (tmp0), - [tmp1] "=&r" (tmp1), CC_OUT(e) (result) - : [inc] "er" (RWSEM_ACTIVE_WRITE_BIAS) - : "memory"); - return result; -} - -/* - * unlock after reading - */ -static inline void __up_read(struct rw_semaphore *sem) -{ - long tmp; - asm volatile("# beginning __up_read\n\t" - LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" - /* subtracts 1, returns the old value */ - " jns 1f\n\t" - " call call_rwsem_wake\n" /* expects old value in %edx */ - "1:\n" - "# ending __up_read\n" - : "+m" (sem->count), [tmp] "=d" (tmp) - : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_READ_BIAS) - : "memory", "cc"); -} - -/* - * unlock after writing - */ -static inline void __up_write(struct rw_semaphore *sem) -{ - long tmp; - asm volatile("# beginning __up_write\n\t" - LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" - /* subtracts 0xffff0001, returns the old value */ - " jns 1f\n\t" - " call call_rwsem_wake\n" /* expects old value in %edx */ - "1:\n\t" - "# ending __up_write\n" - : "+m" (sem->count), [tmp] "=d" (tmp) - : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_WRITE_BIAS) - : "memory", "cc"); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - asm volatile("# beginning __downgrade_write\n\t" - LOCK_PREFIX _ASM_ADD "%[inc],(%[sem])\n\t" - /* - * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386) - * 0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64) - */ - " jns 1f\n\t" - " call call_rwsem_downgrade_wake\n" - "1:\n\t" - "# ending __downgrade_write\n" - : "+m" (sem->count) - : [sem] "a" (sem), [inc] "er" (-RWSEM_WAITING_BIAS) - : "memory", "cc"); -} - -#endif /* __KERNEL__ */ -#endif /* _ASM_X86_RWSEM_H */ diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index db333300bd4b..f94a7d0ddd49 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -13,13 +13,12 @@ #ifndef _ASM_X86_SMAP_H #define _ASM_X86_SMAP_H -#include <linux/stringify.h> #include <asm/nops.h> #include <asm/cpufeatures.h> /* "Raw" instruction opcodes */ -#define __ASM_CLAC .byte 0x0f,0x01,0xca -#define __ASM_STAC .byte 0x0f,0x01,0xcb +#define __ASM_CLAC ".byte 0x0f,0x01,0xca" +#define __ASM_STAC ".byte 0x0f,0x01,0xcb" #ifdef __ASSEMBLY__ @@ -28,10 +27,10 @@ #ifdef CONFIG_X86_SMAP #define ASM_CLAC \ - ALTERNATIVE "", __stringify(__ASM_CLAC), X86_FEATURE_SMAP + ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP #define ASM_STAC \ - ALTERNATIVE "", __stringify(__ASM_STAC), X86_FEATURE_SMAP + ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP #else /* CONFIG_X86_SMAP */ @@ -49,26 +48,46 @@ static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP); + alternative("", __ASM_CLAC, X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __stringify(__ASM_STAC), X86_FEATURE_SMAP); + alternative("", __ASM_STAC, X86_FEATURE_SMAP); +} + +static __always_inline unsigned long smap_save(void) +{ + unsigned long flags; + + asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC, + X86_FEATURE_SMAP) + : "=rm" (flags) : : "memory", "cc"); + + return flags; +} + +static __always_inline void smap_restore(unsigned long flags) +{ + asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP) + : : "g" (flags) : "memory", "cc"); } /* These macros can be used in asm() statements */ #define ASM_CLAC \ - ALTERNATIVE("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP) + ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP) #define ASM_STAC \ - ALTERNATIVE("", __stringify(__ASM_STAC), X86_FEATURE_SMAP) + ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) #else /* CONFIG_X86_SMAP */ static inline void clac(void) { } static inline void stac(void) { } +static inline unsigned long smap_save(void) { return 0; } +static inline void smap_restore(unsigned long flags) { } + #define ASM_CLAC #define ASM_STAC diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f335aad404a4..beef7ad9e43a 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -98,19 +98,6 @@ struct stack_frame_ia32 { u32 return_address; }; -static inline unsigned long caller_frame_pointer(void) -{ - struct stack_frame *frame; - - frame = __builtin_frame_address(0); - -#ifdef CONFIG_FRAME_POINTER - frame = frame->next_frame; -#endif - - return (unsigned long)frame; -} - void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 7cf1a270d891..18a4b6890fa8 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -46,6 +46,7 @@ struct inactive_task_frame { unsigned long r13; unsigned long r12; #else + unsigned long flags; unsigned long si; unsigned long di; #endif diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index d653139857af..4c305471ec33 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -91,11 +91,9 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - BUG_ON(i + n > 6); - memcpy(args, ®s->bx + i, n * sizeof(args[0])); + memcpy(args, ®s->bx, 6 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, @@ -116,124 +114,50 @@ static inline int syscall_get_arch(void) static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread_info.status & TS_COMPAT) - switch (i) { - case 0: - if (!n--) break; - *args++ = regs->bx; - case 1: - if (!n--) break; - *args++ = regs->cx; - case 2: - if (!n--) break; - *args++ = regs->dx; - case 3: - if (!n--) break; - *args++ = regs->si; - case 4: - if (!n--) break; - *args++ = regs->di; - case 5: - if (!n--) break; - *args++ = regs->bp; - case 6: - if (!n--) break; - default: - BUG(); - break; - } - else + if (task->thread_info.status & TS_COMPAT) { + *args++ = regs->bx; + *args++ = regs->cx; + *args++ = regs->dx; + *args++ = regs->si; + *args++ = regs->di; + *args = regs->bp; + } else # endif - switch (i) { - case 0: - if (!n--) break; - *args++ = regs->di; - case 1: - if (!n--) break; - *args++ = regs->si; - case 2: - if (!n--) break; - *args++ = regs->dx; - case 3: - if (!n--) break; - *args++ = regs->r10; - case 4: - if (!n--) break; - *args++ = regs->r8; - case 5: - if (!n--) break; - *args++ = regs->r9; - case 6: - if (!n--) break; - default: - BUG(); - break; - } + { + *args++ = regs->di; + *args++ = regs->si; + *args++ = regs->dx; + *args++ = regs->r10; + *args++ = regs->r8; + *args = regs->r9; + } } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread_info.status & TS_COMPAT) - switch (i) { - case 0: - if (!n--) break; - regs->bx = *args++; - case 1: - if (!n--) break; - regs->cx = *args++; - case 2: - if (!n--) break; - regs->dx = *args++; - case 3: - if (!n--) break; - regs->si = *args++; - case 4: - if (!n--) break; - regs->di = *args++; - case 5: - if (!n--) break; - regs->bp = *args++; - case 6: - if (!n--) break; - default: - BUG(); - break; - } - else + if (task->thread_info.status & TS_COMPAT) { + regs->bx = *args++; + regs->cx = *args++; + regs->dx = *args++; + regs->si = *args++; + regs->di = *args++; + regs->bp = *args; + } else # endif - switch (i) { - case 0: - if (!n--) break; - regs->di = *args++; - case 1: - if (!n--) break; - regs->si = *args++; - case 2: - if (!n--) break; - regs->dx = *args++; - case 3: - if (!n--) break; - regs->r10 = *args++; - case 4: - if (!n--) break; - regs->r8 = *args++; - case 5: - if (!n--) break; - regs->r9 = *args++; - case 6: - if (!n--) break; - default: - BUG(); - break; - } + { + regs->di = *args++; + regs->si = *args++; + regs->dx = *args++; + regs->r10 = *args++; + regs->r8 = *args++; + regs->r9 = *args; + } } static inline int syscall_get_arch(void) diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 404b8b1d44f5..f23e7aaff4cd 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -6,6 +6,7 @@ #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) +#define tlb_flush tlb_flush static inline void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a21f2a2f17bf..c82abd6e4ca3 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -427,10 +427,11 @@ do { \ ({ \ __label__ __pu_label; \ int __pu_err = -EFAULT; \ - __typeof__(*(ptr)) __pu_val; \ - __pu_val = x; \ + __typeof__(*(ptr)) __pu_val = (x); \ + __typeof__(ptr) __pu_ptr = (ptr); \ + __typeof__(size) __pu_size = (size); \ __uaccess_begin(); \ - __put_user_size(__pu_val, (ptr), (size), __pu_label); \ + __put_user_size(__pu_val, __pu_ptr, __pu_size, __pu_label); \ __pu_err = 0; \ __pu_label: \ __uaccess_end(); \ @@ -704,7 +705,7 @@ extern struct movsl_mask { * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ -static __must_check inline bool user_access_begin(const void __user *ptr, size_t len) +static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr,len))) return 0; @@ -714,6 +715,9 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t #define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() +#define user_access_save() smap_save() +#define user_access_restore(x) smap_restore(x) + #define unsafe_put_user(x, ptr, label) \ __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index a9d637bc301d..5cd1caa8bc65 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -208,9 +208,6 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) } unsigned long -copy_user_handle_tail(char *to, char *from, unsigned len); - -unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len); #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index de6f0d59a24f..d50c7b747d8b 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -206,6 +206,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); + if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) + return -EINVAL; + asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM : [thunk_target] "a" (&hypercall_page[call]) @@ -214,6 +217,22 @@ xen_single_call(unsigned int call, return (long)__res; } +static __always_inline void __xen_stac(void) +{ + /* + * Suppress objtool seeing the STAC/CLAC and getting confused about it + * calling random code with AC=1. + */ + asm volatile(ANNOTATE_IGNORE_ALTERNATIVE + ASM_STAC ::: "memory", "flags"); +} + +static __always_inline void __xen_clac(void) +{ + asm volatile(ANNOTATE_IGNORE_ALTERNATIVE + ASM_CLAC ::: "memory", "flags"); +} + static inline long privcmd_call(unsigned int call, unsigned long a1, unsigned long a2, @@ -222,9 +241,9 @@ privcmd_call(unsigned int call, { long res; - stac(); + __xen_stac(); res = xen_single_call(call, a1, a2, a3, a4, a5); - clac(); + __xen_clac(); return res; } @@ -421,9 +440,9 @@ HYPERVISOR_dm_op( domid_t dom, unsigned int nr_bufs, struct xen_dm_op_buf *bufs) { int ret; - stac(); + __xen_stac(); ret = _hypercall3(int, dm_op, dom, nr_bufs, bufs); - clac(); + __xen_clac(); return ret; } diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index dabfcf7c3941..7a0e64ccd6ff 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -381,6 +381,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h index f3329cabce5c..ac67bbea10ca 100644 --- a/arch/x86/include/uapi/asm/perf_regs.h +++ b/arch/x86/include/uapi/asm/perf_regs.h @@ -27,8 +27,29 @@ enum perf_event_x86_regs { PERF_REG_X86_R13, PERF_REG_X86_R14, PERF_REG_X86_R15, - + /* These are the limits for the GPRs. */ PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1, PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1, + + /* These all need two bits set because they are 128bit */ + PERF_REG_X86_XMM0 = 32, + PERF_REG_X86_XMM1 = 34, + PERF_REG_X86_XMM2 = 36, + PERF_REG_X86_XMM3 = 38, + PERF_REG_X86_XMM4 = 40, + PERF_REG_X86_XMM5 = 42, + PERF_REG_X86_XMM6 = 44, + PERF_REG_X86_XMM7 = 46, + PERF_REG_X86_XMM8 = 48, + PERF_REG_X86_XMM9 = 50, + PERF_REG_X86_XMM10 = 52, + PERF_REG_X86_XMM11 = 54, + PERF_REG_X86_XMM12 = 56, + PERF_REG_X86_XMM13 = 58, + PERF_REG_X86_XMM14 = 60, + PERF_REG_X86_XMM15 = 62, + + /* These include both GPRs and XMMX registers */ + PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2, }; #endif /* _ASM_X86_PERF_REGS_H */ diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index f0b0c90dd398..d213ec5c3766 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -146,6 +146,7 @@ #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 +#define VMX_ABORT_VMCS_CORRUPTED 3 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 58176b56354e..294ed4392a0e 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -14,6 +14,7 @@ #define pr_fmt(fmt) "AGP: " fmt #include <linux/kernel.h> +#include <linux/kcore.h> #include <linux/types.h> #include <linux/init.h> #include <linux/memblock.h> @@ -57,7 +58,7 @@ int fallback_aper_force __initdata; int fix_aperture __initdata = 1; -#ifdef CONFIG_PROC_VMCORE +#if defined(CONFIG_PROC_VMCORE) || defined(CONFIG_PROC_KCORE) /* * If the first kernel maps the aperture over e820 RAM, the kdump kernel will * use the same range because it will remain configured in the northbridge. @@ -66,20 +67,25 @@ int fix_aperture __initdata = 1; */ static unsigned long aperture_pfn_start, aperture_page_count; -static int gart_oldmem_pfn_is_ram(unsigned long pfn) +static int gart_mem_pfn_is_ram(unsigned long pfn) { return likely((pfn < aperture_pfn_start) || (pfn >= aperture_pfn_start + aperture_page_count)); } -static void exclude_from_vmcore(u64 aper_base, u32 aper_order) +static void __init exclude_from_core(u64 aper_base, u32 aper_order) { aperture_pfn_start = aper_base >> PAGE_SHIFT; aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT; - WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram)); +#ifdef CONFIG_PROC_VMCORE + WARN_ON(register_oldmem_pfn_is_ram(&gart_mem_pfn_is_ram)); +#endif +#ifdef CONFIG_PROC_KCORE + WARN_ON(register_mem_pfn_is_ram(&gart_mem_pfn_is_ram)); +#endif } #else -static void exclude_from_vmcore(u64 aper_base, u32 aper_order) +static void exclude_from_core(u64 aper_base, u32 aper_order) { } #endif @@ -474,7 +480,7 @@ out: * may have allocated the range over its e820 RAM * and fixed up the northbridge */ - exclude_from_vmcore(last_aper_base, last_aper_order); + exclude_from_core(last_aper_base, last_aper_order); return 1; } @@ -520,7 +526,7 @@ out: * overlap with the first kernel's memory. We can't access the * range through vmcore even though it should be part of the dump. */ - exclude_from_vmcore(aper_alloc, aper_order); + exclude_from_core(aper_alloc, aper_order); /* Fix up the north bridges */ for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) { diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b7bcdd781651..ab6af775f06c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -802,6 +802,24 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) return 0; } +static int __init lapic_init_clockevent(void) +{ + if (!lapic_timer_frequency) + return -1; + + /* Calculate the scaled math multiplication factor */ + lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR, + TICK_NSEC, lapic_clockevent.shift); + lapic_clockevent.max_delta_ns = + clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent); + lapic_clockevent.max_delta_ticks = 0x7FFFFFFF; + lapic_clockevent.min_delta_ns = + clockevent_delta2ns(0xF, &lapic_clockevent); + lapic_clockevent.min_delta_ticks = 0xF; + + return 0; +} + static int __init calibrate_APIC_clock(void) { struct clock_event_device *levt = this_cpu_ptr(&lapic_events); @@ -810,25 +828,21 @@ static int __init calibrate_APIC_clock(void) long delta, deltatsc; int pm_referenced = 0; - /** - * check if lapic timer has already been calibrated by platform - * specific routine, such as tsc calibration code. if so, we just fill + if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return 0; + + /* + * Check if lapic timer has already been calibrated by platform + * specific routine, such as tsc calibration code. If so just fill * in the clockevent structure and return. */ - - if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) { - return 0; - } else if (lapic_timer_frequency) { + if (!lapic_init_clockevent()) { apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n", - lapic_timer_frequency); - lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR, - TICK_NSEC, lapic_clockevent.shift); - lapic_clockevent.max_delta_ns = - clockevent_delta2ns(0x7FFFFF, &lapic_clockevent); - lapic_clockevent.max_delta_ticks = 0x7FFFFF; - lapic_clockevent.min_delta_ns = - clockevent_delta2ns(0xF, &lapic_clockevent); - lapic_clockevent.min_delta_ticks = 0xF; + lapic_timer_frequency); + /* + * Direct calibration methods must have an always running + * local APIC timer, no need for broadcast timer. + */ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; return 0; } @@ -869,17 +883,8 @@ static int __init calibrate_APIC_clock(void) pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1, &delta, &deltatsc); - /* Calculate the scaled math multiplication factor */ - lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS, - lapic_clockevent.shift); - lapic_clockevent.max_delta_ns = - clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent); - lapic_clockevent.max_delta_ticks = 0x7FFFFFFF; - lapic_clockevent.min_delta_ns = - clockevent_delta2ns(0xF, &lapic_clockevent); - lapic_clockevent.min_delta_ticks = 0xF; - lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; + lapic_init_clockevent(); apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta); apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 2da82eff0eb4..29630393f300 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -275,7 +275,7 @@ static const struct { const char *option; enum spectre_v2_user_cmd cmd; bool secure; -} v2_user_options[] __initdata = { +} v2_user_options[] __initconst = { { "auto", SPECTRE_V2_USER_CMD_AUTO, false }, { "off", SPECTRE_V2_USER_CMD_NONE, false }, { "on", SPECTRE_V2_USER_CMD_FORCE, true }, @@ -419,7 +419,7 @@ static const struct { const char *option; enum spectre_v2_mitigation_cmd cmd; bool secure; -} mitigation_options[] __initdata = { +} mitigation_options[] __initconst = { { "off", SPECTRE_V2_CMD_NONE, false }, { "on", SPECTRE_V2_CMD_FORCE, true }, { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, @@ -440,7 +440,8 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) char arg[20]; int ret, i; - if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") || + cpu_mitigations_off()) return SPECTRE_V2_CMD_NONE; ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); @@ -658,7 +659,7 @@ static const char * const ssb_strings[] = { static const struct { const char *option; enum ssb_mitigation_cmd cmd; -} ssb_mitigation_options[] __initdata = { +} ssb_mitigation_options[] __initconst = { { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ @@ -672,7 +673,8 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) char arg[20]; int ret, i; - if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) { + if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") || + cpu_mitigations_off()) { return SPEC_STORE_BYPASS_CMD_NONE; } else { ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", @@ -1008,6 +1010,11 @@ static void __init l1tf_select_mitigation(void) if (!boot_cpu_has_bug(X86_BUG_L1TF)) return; + if (cpu_mitigations_off()) + l1tf_mitigation = L1TF_MITIGATION_OFF; + else if (cpu_mitigations_auto_nosmt()) + l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT; + override_cache_bits(&boot_cpu_data); switch (l1tf_mitigation) { diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index d12226f60168..1d9b8aaea06c 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -124,7 +124,7 @@ static void set_cx86_reorder(void) setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ /* Load/Store Serialize to mem access disable (=reorder it) */ - setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80); + setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80); /* set load/store serialize from 1GB to 4GB */ ccr3 |= 0xe0; setCx86(CX86_CCR3, ccr3); @@ -135,11 +135,11 @@ static void set_cx86_memwb(void) pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n"); /* CCR2 bit 2: unlock NW bit */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04); /* set 'Not Write-through' */ write_cr0(read_cr0() | X86_CR0_NW); /* CCR2 bit 2: lock NW bit and set WT1 */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14); } /* @@ -153,14 +153,14 @@ static void geode_configure(void) local_irq_save(flags); /* Suspend on halt power saving and enable #SUSP pin */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88); ccr3 = getCx86(CX86_CCR3); setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ /* FPU fast, DTE cache, Mem bypass */ - setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38); + setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38); setCx86(CX86_CCR3, ccr3); /* disable MAPEN */ set_cx86_memwb(); @@ -296,7 +296,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* GXm supports extended cpuid levels 'ala' AMD */ if (c->cpuid_level == 2) { /* Enable cxMMX extensions (GX1 Datasheet 54) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1); /* * GXm : 0x30 ... 0x5f GXm datasheet 51 @@ -319,7 +319,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) if (dir1 > 7) { dir0_msn++; /* M II */ /* Enable MMX extensions (App note 108) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1); } else { /* A 6x86MX - it has the bug. */ set_cpu_bug(c, X86_BUG_COMA); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fc3c07fe7df5..3142fd7a9b32 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -611,8 +611,8 @@ static void init_intel_energy_perf(struct cpuinfo_x86 *c) if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE) return; - pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); - pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); + pr_info_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); + pr_info_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL; wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 97f9ada9ceda..5260185cbf7b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -608,6 +608,8 @@ static int microcode_reload_late(void) if (ret > 0) microcode_check(); + pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode); + return ret; } diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f33f11f69078..1573a0a6b525 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -501,11 +501,8 @@ out_unlock: void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) { unsigned long delay = msecs_to_jiffies(delay_ms); - struct rdt_resource *r; int cpu; - r = &rdt_resources_all[RDT_RESOURCE_L3]; - cpu = cpumask_any(&dom->cpu_mask); dom->cqm_work_cpu = cpu; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 399601eda8e4..85212a32b54d 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2039,14 +2039,14 @@ out: enum rdt_param { Opt_cdp, Opt_cdpl2, - Opt_mba_mpbs, + Opt_mba_mbps, nr__rdt_params }; static const struct fs_parameter_spec rdt_param_specs[] = { fsparam_flag("cdp", Opt_cdp), fsparam_flag("cdpl2", Opt_cdpl2), - fsparam_flag("mba_mpbs", Opt_mba_mpbs), + fsparam_flag("mba_MBps", Opt_mba_mbps), {} }; @@ -2072,7 +2072,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_cdpl2: ctx->enable_cdpl2 = true; return 0; - case Opt_mba_mpbs: + case Opt_mba_mbps: if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return -EINVAL; ctx->enable_mba_mbps = true; @@ -2610,9 +2610,10 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) rdt_last_cmd_puts("Failed to initialize allocations\n"); return ret; } - rdtgrp->mode = RDT_MODE_SHAREABLE; } + rdtgrp->mode = RDT_MODE_SHAREABLE; + return 0; } diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dfd3aca82c61..fb32925a2e62 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -905,6 +905,8 @@ int __init hpet_enable(void) return 0; hpet_set_mapping(); + if (!hpet_virt_address) + return 0; /* * Read the period and check for a sane value: diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index ff9bfd40429e..d73083021002 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -354,6 +354,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, #endif default: WARN_ON_ONCE(1); + return -EINVAL; } /* diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 31ab91c9c4e9..122548ad5c2e 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) unsigned long *sara = stack_addr(regs); ri->ret_addr = (kprobe_opcode_t *) *sara; + ri->fp = sara; /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; @@ -749,26 +750,48 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +static struct kprobe kretprobe_kprobe = { + .addr = (void *)kretprobe_trampoline, +}; + /* * Called from kretprobe_trampoline */ static __used void *trampoline_handler(struct pt_regs *regs) { + struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; kprobe_opcode_t *correct_ret_addr = NULL; + void *frame_pointer; + bool skipped = false; + + preempt_disable(); + + /* + * Set a dummy kprobe for avoiding kretprobe recursion. + * Since kretprobe never run in kprobe handler, kprobe must not + * be running at this point. + */ + kcb = get_kprobe_ctlblk(); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; + /* On x86-64, we use pt_regs->sp for return address holder. */ + frame_pointer = ®s->sp; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); regs->gs = 0; + /* On x86-32, we use pt_regs->flags for return address holder. */ + frame_pointer = ®s->flags; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; @@ -790,8 +813,25 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + /* + * Return probes must be pushed on this hash list correct + * order (same as return order) so that it can be poped + * correctly. However, if we find it is pushed it incorrect + * order, this means we find a function which should not be + * probed, because the wrong order entry is pushed on the + * path of processing other kretprobe itself. + */ + if (ri->fp != frame_pointer) { + if (!skipped) + pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); + skipped = true; + continue; + } orig_ret_address = (unsigned long)ri->ret_addr; + if (skipped) + pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", + ri->rp->kp.addr); if (orig_ret_address != trampoline_address) /* @@ -809,14 +849,15 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + if (ri->fp != frame_pointer) + continue; orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { __this_cpu_write(current_kprobe, &ri->rp->kp); - get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, NULL); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); } recycle_rp_inst(ri, &empty_rp); @@ -832,6 +873,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 3482460d984d..1bfe5c6e6cfe 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -598,8 +598,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) mpf_base = base; mpf_found = true; - pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n", - base, base + sizeof(*mpf) - 1, mpf); + pr_info("found SMP MP-table at [mem %#010lx-%#010lx]\n", + base, base + sizeof(*mpf) - 1); memblock_reserve(base, sizeof(*mpf)); if (mpf->physptr) diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index c06c4c16c6b6..07c30ee17425 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -59,18 +59,34 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = { u64 perf_reg_value(struct pt_regs *regs, int idx) { + struct x86_perf_regs *perf_regs; + + if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) { + perf_regs = container_of(regs, struct x86_perf_regs, regs); + if (!perf_regs->xmm_regs) + return 0; + return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0]; + } + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset))) return 0; return regs_get_register(regs, pt_regs_offset[idx]); } -#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL)) - #ifdef CONFIG_X86_32 +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15)) + int perf_reg_validate(u64 mask) { - if (!mask || mask & REG_RESERVED) + if (!mask || (mask & REG_NOSUPPORT)) return -EINVAL; return 0; @@ -96,10 +112,7 @@ void perf_get_regs_user(struct perf_regs *regs_user, int perf_reg_validate(u64 mask) { - if (!mask || mask & REG_RESERVED) - return -EINVAL; - - if (mask & REG_NOSUPPORT) + if (!mask || (mask & REG_NOSUPPORT)) return -EINVAL; return 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 16a7113e91c5..d1d312d012a6 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -426,6 +426,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, u64 msr = x86_spec_ctrl_base; bool updmsr = false; + lockdep_assert_irqs_disabled(); + /* * If TIF_SSBD is different, select the proper mitigation * method. Note that if SSBD mitigation is disabled or permanentely @@ -477,10 +479,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) void speculation_ctrl_update(unsigned long tif) { + unsigned long flags; + /* Forced update. Make sure all relevant TIF flags are different */ - preempt_disable(); + local_irq_save(flags); __speculation_ctrl_update(~tif, tif); - preempt_enable(); + local_irq_restore(flags); } /* Called from seccomp/prctl update */ diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index e471d8e6f0b2..70933193878c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -127,6 +127,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, 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; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6a62f4af9fcf..844a28b29967 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -392,6 +392,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, 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; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index d62ebbc5ec78..09d6bded3c1e 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -81,6 +81,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d) return 0; } +/* + * Some machines don't handle the default ACPI reboot method and + * require the EFI reboot method: + */ +static int __init set_efi_reboot(const struct dmi_system_id *d) +{ + if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) { + reboot_type = BOOT_EFI; + pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident); + } + return 0; +} + void __noreturn machine_real_restart(unsigned int type) { local_irq_disable(); @@ -166,6 +179,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"), }, }, + { /* Handle reboot issue on Acer TravelMate X514-51T */ + .callback = set_efi_reboot, + .ident = "Acer TravelMate X514-51T", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"), + }, + }, /* Apple */ { /* Handle problems with rebooting on Apple MacBook5 */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3d872a527cd9..3773905cd2c1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1005,13 +1005,11 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled(EFI_BOOT)) efi_init(); - dmi_scan_machine(); - dmi_memdev_walk(); - dmi_set_dump_stack_arch_desc(); + dmi_setup(); /* * VMware detection requires dmi to be available, so this - * needs to be done after dmi_scan_machine(), for the boot CPU. + * needs to be done after dmi_setup(), for the boot CPU. */ init_hypervisor_platform(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 08dfd4c1a4f9..dff90fb6a9af 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -132,16 +132,6 @@ static int restore_sigcontext(struct pt_regs *regs, COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); -#ifdef CONFIG_X86_64 - /* - * Fix up SS if needed for the benefit of old DOSEMU and - * CRIU. - */ - if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && - user_64bit_mode(regs))) - force_valid_ss(regs); -#endif - get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); regs->orig_ax = -1; /* disable syscall checks */ @@ -150,6 +140,15 @@ static int restore_sigcontext(struct pt_regs *regs, buf = (void __user *)buf_val; } get_user_catch(err); +#ifdef CONFIG_X86_64 + /* + * Fix up SS if needed for the benefit of old DOSEMU and + * CRIU. + */ + if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs))) + force_valid_ss(regs); +#endif + err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32)); force_iret(); @@ -461,6 +460,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, { struct rt_sigframe __user *frame; void __user *fp = NULL; + unsigned long uc_flags; int err = 0; frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp); @@ -473,9 +473,11 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, return -EFAULT; } + uc_flags = frame_uc_flags(regs); + put_user_try { /* Create the ucontext. */ - put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags); + put_user_ex(uc_flags, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); save_altstack_ex(&frame->uc.uc_stack, regs->sp); @@ -541,6 +543,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, { #ifdef CONFIG_X86_X32_ABI struct rt_sigframe_x32 __user *frame; + unsigned long uc_flags; void __user *restorer; int err = 0; void __user *fpstate = NULL; @@ -555,9 +558,11 @@ static int x32_setup_rt_frame(struct ksignal *ksig, return -EFAULT; } + uc_flags = frame_uc_flags(regs); + put_user_try { /* Create the ucontext. */ - put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags); + put_user_ex(uc_flags, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); @@ -688,10 +693,7 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) sigset_t *set = sigmask_to_save(); compat_sigset_t *cset = (compat_sigset_t *) set; - /* - * Increment event counter and perform fixup for the pre-signal - * frame. - */ + /* Perform fixup for the pre-signal frame. */ rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 5c2d71a1dc06..2abf27d7df6b 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -12,78 +12,31 @@ #include <asm/stacktrace.h> #include <asm/unwind.h> -static int save_stack_address(struct stack_trace *trace, unsigned long addr, - bool nosched) -{ - if (nosched && in_sched_functions(addr)) - return 0; - - if (trace->skip > 0) { - trace->skip--; - return 0; - } - - if (trace->nr_entries >= trace->max_entries) - return -1; - - trace->entries[trace->nr_entries++] = addr; - return 0; -} - -static void noinline __save_stack_trace(struct stack_trace *trace, - struct task_struct *task, struct pt_regs *regs, - bool nosched) +void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs) { struct unwind_state state; unsigned long addr; - if (regs) - save_stack_address(trace, regs->ip, nosched); + if (regs && !consume_entry(cookie, regs->ip, false)) + return; for (unwind_start(&state, task, regs, NULL); !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); - if (!addr || save_stack_address(trace, addr, nosched)) + if (!addr || !consume_entry(cookie, addr, false)) break; } - - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; } /* - * Save stack-backtrace addresses into a stack_trace buffer. + * This function returns an error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is reliable. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. */ -void save_stack_trace(struct stack_trace *trace) -{ - trace->skip++; - __save_stack_trace(trace, current, NULL, false); -} -EXPORT_SYMBOL_GPL(save_stack_trace); - -void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) -{ - __save_stack_trace(trace, current, regs, false); -} - -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) -{ - if (!try_get_task_stack(tsk)) - return; - - if (tsk == current) - trace->skip++; - __save_stack_trace(trace, tsk, NULL, true); - - put_task_stack(tsk); -} -EXPORT_SYMBOL_GPL(save_stack_trace_tsk); - -#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE - -static int __always_inline -__save_stack_trace_reliable(struct stack_trace *trace, - struct task_struct *task) +int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, + void *cookie, struct task_struct *task) { struct unwind_state state; struct pt_regs *regs; @@ -97,7 +50,7 @@ __save_stack_trace_reliable(struct stack_trace *trace, if (regs) { /* Success path for user tasks */ if (user_mode(regs)) - goto success; + return 0; /* * Kernel mode registers on the stack indicate an @@ -120,7 +73,7 @@ __save_stack_trace_reliable(struct stack_trace *trace, if (!addr) return -EINVAL; - if (save_stack_address(trace, addr, false)) + if (!consume_entry(cookie, addr, false)) return -EINVAL; } @@ -132,39 +85,9 @@ __save_stack_trace_reliable(struct stack_trace *trace, if (!(task->flags & (PF_KTHREAD | PF_IDLE))) return -EINVAL; -success: - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; - return 0; } -/* - * This function returns an error if it detects any unreliable features of the - * stack. Otherwise it guarantees that the stack trace is reliable. - * - * If the task is not 'current', the caller *must* ensure the task is inactive. - */ -int save_stack_trace_tsk_reliable(struct task_struct *tsk, - struct stack_trace *trace) -{ - int ret; - - /* - * If the task doesn't have a stack (e.g., a zombie), the stack is - * "reliably" empty. - */ - if (!try_get_task_stack(tsk)) - return 0; - - ret = __save_stack_trace_reliable(trace, tsk); - - put_task_stack(tsk); - - return ret; -} -#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */ - /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */ struct stack_frame_user { @@ -189,15 +112,15 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) return ret; } -static inline void __save_stack_trace_user(struct stack_trace *trace) +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs) { - const struct pt_regs *regs = task_pt_regs(current); const void __user *fp = (const void __user *)regs->bp; - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = regs->ip; + if (!consume_entry(cookie, regs->ip, false)) + return; - while (trace->nr_entries < trace->max_entries) { + while (1) { struct stack_frame_user frame; frame.next_fp = NULL; @@ -207,8 +130,8 @@ static inline void __save_stack_trace_user(struct stack_trace *trace) if ((unsigned long)fp < regs->sp) break; if (frame.ret_addr) { - trace->entries[trace->nr_entries++] = - frame.ret_addr; + if (!consume_entry(cookie, frame.ret_addr, false)) + return; } if (fp == frame.next_fp) break; @@ -216,14 +139,3 @@ static inline void __save_stack_trace_user(struct stack_trace *trace) } } -void save_stack_trace_user(struct stack_trace *trace) -{ - /* - * Trace user stack if we are not a kernel thread - */ - if (current->mm) { - __save_stack_trace_user(trace); - } - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; -} diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index bad8c51fee6e..a5127b2c195f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -362,7 +362,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) - *(.bss) + *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); __bss_stop = .; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c338984c850d..d0d5dd44b4f4 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2331,24 +2331,18 @@ 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); +#else + return false; +#endif } -#define GET_SMSTATE(type, smbase, offset) \ - ({ \ - type __val; \ - int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \ - sizeof(__val)); \ - if (r != X86EMUL_CONTINUE) \ - return X86EMUL_UNHANDLEABLE; \ - __val; \ - }) - static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) { desc->g = (flags >> 23) & 1; @@ -2361,27 +2355,30 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) desc->type = (flags >> 8) & 15; } -static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate, + int n) { struct desc_struct desc; int offset; u16 selector; - selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4); + selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4); if (n < 3) offset = 0x7f84 + n * 12; else offset = 0x7f2c + (n - 3) * 12; - set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset)); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8)); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset)); ctxt->ops->set_segment(ctxt, selector, &desc, 0, n); return X86EMUL_CONTINUE; } -static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +#ifdef CONFIG_X86_64 +static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate, + int n) { struct desc_struct desc; int offset; @@ -2390,15 +2387,16 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) offset = 0x7e00 + n * 16; - selector = GET_SMSTATE(u16, smbase, offset); - rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); - base3 = GET_SMSTATE(u32, smbase, offset + 12); + selector = GET_SMSTATE(u16, smstate, offset); + rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4)); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8)); + base3 = GET_SMSTATE(u32, smstate, offset + 12); ctxt->ops->set_segment(ctxt, selector, &desc, base3, n); return X86EMUL_CONTINUE; } +#endif static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, u64 cr0, u64 cr3, u64 cr4) @@ -2445,7 +2443,8 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, return X86EMUL_CONTINUE; } -static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) +static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, + const char *smstate) { struct desc_struct desc; struct desc_ptr dt; @@ -2453,53 +2452,55 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) u32 val, cr0, cr3, cr4; int i; - cr0 = GET_SMSTATE(u32, smbase, 0x7ffc); - cr3 = GET_SMSTATE(u32, smbase, 0x7ff8); - ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED; - ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0); + cr0 = GET_SMSTATE(u32, smstate, 0x7ffc); + cr3 = GET_SMSTATE(u32, smstate, 0x7ff8); + ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED; + ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0); for (i = 0; i < 8; i++) - *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4); + *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4); - val = GET_SMSTATE(u32, smbase, 0x7fcc); + val = GET_SMSTATE(u32, smstate, 0x7fcc); ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); - val = GET_SMSTATE(u32, smbase, 0x7fc8); + val = GET_SMSTATE(u32, smstate, 0x7fc8); ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); - selector = GET_SMSTATE(u32, smbase, 0x7fc4); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64)); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c)); + selector = GET_SMSTATE(u32, smstate, 0x7fc4); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64)); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c)); ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR); - selector = GET_SMSTATE(u32, smbase, 0x7fc0); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80)); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78)); + selector = GET_SMSTATE(u32, smstate, 0x7fc0); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80)); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78)); ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR); - dt.address = GET_SMSTATE(u32, smbase, 0x7f74); - dt.size = GET_SMSTATE(u32, smbase, 0x7f70); + dt.address = GET_SMSTATE(u32, smstate, 0x7f74); + dt.size = GET_SMSTATE(u32, smstate, 0x7f70); ctxt->ops->set_gdt(ctxt, &dt); - dt.address = GET_SMSTATE(u32, smbase, 0x7f58); - dt.size = GET_SMSTATE(u32, smbase, 0x7f54); + dt.address = GET_SMSTATE(u32, smstate, 0x7f58); + dt.size = GET_SMSTATE(u32, smstate, 0x7f54); ctxt->ops->set_idt(ctxt, &dt); for (i = 0; i < 6; i++) { - int r = rsm_load_seg_32(ctxt, smbase, i); + int r = rsm_load_seg_32(ctxt, smstate, i); if (r != X86EMUL_CONTINUE) return r; } - cr4 = GET_SMSTATE(u32, smbase, 0x7f14); + cr4 = GET_SMSTATE(u32, smstate, 0x7f14); - ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8)); + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8)); return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); } -static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) +#ifdef CONFIG_X86_64 +static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, + const char *smstate) { struct desc_struct desc; struct desc_ptr dt; @@ -2509,43 +2510,43 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) int i, r; for (i = 0; i < 16; i++) - *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8); + *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8); - ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78); - ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED; + ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78); + ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED; - val = GET_SMSTATE(u32, smbase, 0x7f68); + val = GET_SMSTATE(u32, smstate, 0x7f68); ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); - val = GET_SMSTATE(u32, smbase, 0x7f60); + val = GET_SMSTATE(u32, smstate, 0x7f60); ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); - cr0 = GET_SMSTATE(u64, smbase, 0x7f58); - cr3 = GET_SMSTATE(u64, smbase, 0x7f50); - cr4 = GET_SMSTATE(u64, smbase, 0x7f48); - ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00)); - val = GET_SMSTATE(u64, smbase, 0x7ed0); + cr0 = GET_SMSTATE(u64, smstate, 0x7f58); + cr3 = GET_SMSTATE(u64, smstate, 0x7f50); + cr4 = GET_SMSTATE(u64, smstate, 0x7f48); + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00)); + val = GET_SMSTATE(u64, smstate, 0x7ed0); ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA); - selector = GET_SMSTATE(u32, smbase, 0x7e90); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94)); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98)); - base3 = GET_SMSTATE(u32, smbase, 0x7e9c); + selector = GET_SMSTATE(u32, smstate, 0x7e90); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94)); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98)); + base3 = GET_SMSTATE(u32, smstate, 0x7e9c); ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR); - dt.size = GET_SMSTATE(u32, smbase, 0x7e84); - dt.address = GET_SMSTATE(u64, smbase, 0x7e88); + dt.size = GET_SMSTATE(u32, smstate, 0x7e84); + dt.address = GET_SMSTATE(u64, smstate, 0x7e88); ctxt->ops->set_idt(ctxt, &dt); - selector = GET_SMSTATE(u32, smbase, 0x7e70); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74)); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78)); - base3 = GET_SMSTATE(u32, smbase, 0x7e7c); + selector = GET_SMSTATE(u32, smstate, 0x7e70); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74)); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78)); + base3 = GET_SMSTATE(u32, smstate, 0x7e7c); ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR); - dt.size = GET_SMSTATE(u32, smbase, 0x7e64); - dt.address = GET_SMSTATE(u64, smbase, 0x7e68); + dt.size = GET_SMSTATE(u32, smstate, 0x7e64); + dt.address = GET_SMSTATE(u64, smstate, 0x7e68); ctxt->ops->set_gdt(ctxt, &dt); r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); @@ -2553,37 +2554,49 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) return r; for (i = 0; i < 6; i++) { - r = rsm_load_seg_64(ctxt, smbase, i); + r = rsm_load_seg_64(ctxt, smstate, i); if (r != X86EMUL_CONTINUE) return r; } return X86EMUL_CONTINUE; } +#endif static int em_rsm(struct x86_emulate_ctxt *ctxt) { unsigned long cr0, cr4, efer; + char buf[512]; u64 smbase; int ret; if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0) return emulate_ud(ctxt); + smbase = ctxt->ops->get_smbase(ctxt); + + ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf)); + if (ret != X86EMUL_CONTINUE) + return X86EMUL_UNHANDLEABLE; + + if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) + ctxt->ops->set_nmi_mask(ctxt, false); + + ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) & + ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK)); + /* * Get back to real mode, to prepare a safe state in which to load * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU * supports long mode. */ - cr4 = ctxt->ops->get_cr(ctxt, 4); if (emulator_has_longmode(ctxt)) { struct desc_struct cs_desc; /* Zero CR4.PCIDE before CR0.PG. */ - if (cr4 & X86_CR4_PCIDE) { + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PCIDE) ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); - cr4 &= ~X86_CR4_PCIDE; - } /* A 32-bit code segment is required to clear EFER.LMA. */ memset(&cs_desc, 0, sizeof(cs_desc)); @@ -2597,39 +2610,39 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) if (cr0 & X86_CR0_PE) ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); - /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */ - if (cr4 & X86_CR4_PAE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); - - /* And finally go back to 32-bit mode. */ - efer = 0; - ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + if (emulator_has_longmode(ctxt)) { + /* Clear CR4.PAE before clearing EFER.LME. */ + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PAE) + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); - smbase = ctxt->ops->get_smbase(ctxt); + /* And finally go back to 32-bit mode. */ + efer = 0; + ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + } /* * Give pre_leave_smm() a chance to make ISA-specific changes to the * vCPU state (e.g. enter guest mode) before loading state from the SMM * state-save area. */ - if (ctxt->ops->pre_leave_smm(ctxt, smbase)) + if (ctxt->ops->pre_leave_smm(ctxt, buf)) return X86EMUL_UNHANDLEABLE; +#ifdef CONFIG_X86_64 if (emulator_has_longmode(ctxt)) - ret = rsm_load_state_64(ctxt, smbase + 0x8000); + ret = rsm_load_state_64(ctxt, buf); else - ret = rsm_load_state_32(ctxt, smbase + 0x8000); +#endif + ret = rsm_load_state_32(ctxt, buf); if (ret != X86EMUL_CONTINUE) { /* FIXME: should triple fault */ return X86EMUL_UNHANDLEABLE; } - if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) - ctxt->ops->set_nmi_mask(ctxt, false); + ctxt->ops->post_leave_smm(ctxt); - ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) & - ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK)); return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 27c43525a05f..cc24b3a32c44 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -526,7 +526,9 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, new_config.enable = 0; stimer->config.as_uint64 = new_config.as_uint64; - stimer_mark_pending(stimer, false); + if (stimer->config.enable) + stimer_mark_pending(stimer, false); + return 0; } @@ -542,7 +544,10 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer->config.enable = 0; else if (stimer->config.auto_enable) stimer->config.enable = 1; - stimer_mark_pending(stimer, false); + + if (stimer->config.enable) + stimer_mark_pending(stimer, false); + return 0; } @@ -1366,7 +1371,16 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, valid_bank_mask = BIT_ULL(0); sparse_banks[0] = flush.processor_mask; - all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS; + + /* + * Work around possible WS2012 bug: it sends hypercalls + * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear, + * while also expecting us to flush something and crashing if + * we don't. Let's treat processor_mask == 0 same as + * HV_FLUSH_ALL_PROCESSORS. + */ + all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) || + flush.processor_mask == 0; } else { if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex, sizeof(flush_ex)))) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 991fdf7fc17f..bd13fdddbdc4 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -70,7 +70,6 @@ #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul -static bool lapic_timer_advance_adjust_done = false; #define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -138,6 +137,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, if (offset <= max_apic_id) { u8 cluster_size = min(max_apic_id - offset + 1, 16U); + offset = array_index_nospec(offset, map->max_apic_id + 1); *cluster = &map->phys_map[offset]; *mask = dest_id & (0xffff >> (16 - cluster_size)); } else { @@ -901,7 +901,8 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm, if (irq->dest_id > map->max_apic_id) { *bitmap = 0; } else { - *dst = &map->phys_map[irq->dest_id]; + u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1); + *dst = &map->phys_map[dest_id]; *bitmap = 1; } return true; @@ -1480,14 +1481,32 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) return false; } +static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles) +{ + u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns; + + /* + * If the guest TSC is running at a different ratio than the host, then + * convert the delay to nanoseconds to achieve an accurate delay. Note + * that __delay() uses delay_tsc whenever the hardware has TSC, thus + * always for VMX enabled hardware. + */ + if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) { + __delay(min(guest_cycles, + nsec_to_cycles(vcpu, timer_advance_ns))); + } else { + u64 delay_ns = guest_cycles * 1000000ULL; + do_div(delay_ns, vcpu->arch.virtual_tsc_khz); + ndelay(min_t(u32, delay_ns, timer_advance_ns)); + } +} + void wait_lapic_expire(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; + u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns; u64 guest_tsc, tsc_deadline, ns; - if (!lapic_in_kernel(vcpu)) - return; - if (apic->lapic_timer.expired_tscdeadline == 0) return; @@ -1499,33 +1518,37 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); - /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(min(tsc_deadline - guest_tsc, - nsec_to_cycles(vcpu, lapic_timer_advance_ns))); + __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - if (!lapic_timer_advance_adjust_done) { + if (!apic->lapic_timer.timer_advance_adjust_done) { /* too early */ if (guest_tsc < tsc_deadline) { ns = (tsc_deadline - guest_tsc) * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - lapic_timer_advance_ns -= min((unsigned int)ns, - lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns -= min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); } else { /* too late */ ns = (guest_tsc - tsc_deadline) * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - lapic_timer_advance_ns += min((unsigned int)ns, - lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns += min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); } if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) - lapic_timer_advance_adjust_done = true; + apic->lapic_timer.timer_advance_adjust_done = true; + if (unlikely(timer_advance_ns > 5000)) { + timer_advance_ns = 0; + apic->lapic_timer.timer_advance_adjust_done = true; + } + apic->lapic_timer.timer_advance_ns = timer_advance_ns; } } static void start_sw_tscdeadline(struct kvm_lapic *apic) { - u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; + struct kvm_timer *ktimer = &apic->lapic_timer; + u64 guest_tsc, tscdeadline = ktimer->tscdeadline; u64 ns = 0; ktime_t expire; struct kvm_vcpu *vcpu = apic->vcpu; @@ -1540,13 +1563,15 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) now = ktime_get(); guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); - if (likely(tscdeadline > guest_tsc)) { - ns = (tscdeadline - guest_tsc) * 1000000ULL; - do_div(ns, this_tsc_khz); + + ns = (tscdeadline - guest_tsc) * 1000000ULL; + do_div(ns, this_tsc_khz); + + if (likely(tscdeadline > guest_tsc) && + likely(ns > apic->lapic_timer.timer_advance_ns)) { expire = ktime_add_ns(now, ns); - expire = ktime_sub_ns(expire, lapic_timer_advance_ns); - hrtimer_start(&apic->lapic_timer.timer, - expire, HRTIMER_MODE_ABS_PINNED); + expire = ktime_sub_ns(expire, ktimer->timer_advance_ns); + hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_PINNED); } else apic_timer_expired(apic); @@ -2253,7 +2278,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } -int kvm_create_lapic(struct kvm_vcpu *vcpu) +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) { struct kvm_lapic *apic; @@ -2277,6 +2302,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); apic->lapic_timer.timer.function = apic_timer_fn; + if (timer_advance_ns == -1) { + apic->lapic_timer.timer_advance_ns = 1000; + apic->lapic_timer.timer_advance_adjust_done = false; + } else { + apic->lapic_timer.timer_advance_ns = timer_advance_ns; + apic->lapic_timer.timer_advance_adjust_done = true; + } + /* * APIC is created enabled. This will prevent kvm_lapic_set_base from diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index ff6ef9c3d760..d6d049ba3045 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -31,8 +31,10 @@ struct kvm_timer { u32 timer_mode_mask; u64 tscdeadline; u64 expired_tscdeadline; + u32 timer_advance_ns; atomic_t pending; /* accumulated triggered timers */ bool hv_timer_in_use; + bool timer_advance_adjust_done; }; struct kvm_lapic { @@ -62,7 +64,7 @@ struct kvm_lapic { struct dest_map; -int kvm_create_lapic(struct kvm_vcpu *vcpu); +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7837ab001d80..d9c7b45d231f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -182,7 +182,7 @@ struct kvm_shadow_walk_iterator { static const union kvm_mmu_page_role mmu_base_role_mask = { .cr0_wp = 1, - .cr4_pae = 1, + .gpte_is_8_bytes = 1, .nxe = 1, .smep_andnot_wp = 1, .smap_andnot_wp = 1, @@ -2007,7 +2007,7 @@ static int is_empty_shadow_page(u64 *spt) * aggregate version in order to make the slab shrinker * faster */ -static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr) +static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr) { kvm->arch.n_used_mmu_pages += nr; percpu_counter_add(&kvm_total_used_mmu_pages, nr); @@ -2205,6 +2205,7 @@ static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list); + #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) \ @@ -2215,12 +2216,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, for_each_valid_sp(_kvm, _sp, _gfn) \ if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else +static inline bool is_ept_sp(struct kvm_mmu_page *sp) +{ + return sp->role.cr0_wp && sp->role.smap_andnot_wp; +} + /* @sp->gfn should be write-protected at the call site */ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { - if (sp->role.cr4_pae != !!is_pae(vcpu) - || vcpu->arch.mmu->sync_page(vcpu, sp) == 0) { + if ((!is_ept_sp(sp) && sp->role.gpte_is_8_bytes != !!is_pae(vcpu)) || + vcpu->arch.mmu->sync_page(vcpu, sp) == 0) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return false; } @@ -2232,7 +2238,7 @@ static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm, struct list_head *invalid_list, bool remote_flush) { - if (!remote_flush && !list_empty(invalid_list)) + if (!remote_flush && list_empty(invalid_list)) return false; if (!list_empty(invalid_list)) @@ -2423,7 +2429,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role.level = level; role.direct = direct; if (role.direct) - role.cr4_pae = 0; + role.gpte_is_8_bytes = true; role.access = access; if (!vcpu->arch.mmu->direct_map && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) { @@ -2757,7 +2763,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, * Changing the number of mmu pages allocated to the vm * Note: if goal_nr_mmu_pages is too small, you will get dead lock */ -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) { LIST_HEAD(invalid_list); @@ -4775,6 +4781,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu) union kvm_mmu_extended_role ext = {0}; ext.cr0_pg = !!is_paging(vcpu); + ext.cr4_pae = !!is_pae(vcpu); ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); ext.cr4_pse = !!is_pse(vcpu); @@ -4794,7 +4801,6 @@ static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu, role.base.access = ACC_ALL; role.base.nxe = !!is_nx(vcpu); - role.base.cr4_pae = !!is_pae(vcpu); role.base.cr0_wp = is_write_protection(vcpu); role.base.smm = is_smm(vcpu); role.base.guest_mode = is_guest_mode(vcpu); @@ -4815,6 +4821,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) role.base.ad_disabled = (shadow_accessed_mask == 0); role.base.level = kvm_x86_ops->get_tdp_level(vcpu); role.base.direct = true; + role.base.gpte_is_8_bytes = true; return role; } @@ -4879,6 +4886,7 @@ kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) role.base.smap_andnot_wp = role.ext.cr4_smap && !is_write_protection(vcpu); role.base.direct = !is_paging(vcpu); + role.base.gpte_is_8_bytes = !!is_pae(vcpu); if (!is_long_mode(vcpu)) role.base.level = PT32E_ROOT_LEVEL; @@ -4918,18 +4926,26 @@ static union kvm_mmu_role kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, bool execonly) { - union kvm_mmu_role role; + union kvm_mmu_role role = {0}; - /* Base role is inherited from root_mmu */ - role.base.word = vcpu->arch.root_mmu.mmu_role.base.word; - role.ext = kvm_calc_mmu_role_ext(vcpu); + /* SMM flag is inherited from root_mmu */ + role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm; role.base.level = PT64_ROOT_4LEVEL; + role.base.gpte_is_8_bytes = true; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; role.base.guest_mode = true; role.base.access = ACC_ALL; + /* + * WP=1 and NOT_WP=1 is an impossible combination, use WP and the + * SMAP variation to denote shadow EPT entries. + */ + role.base.cr0_wp = true; + role.base.smap_andnot_wp = true; + + role.ext = kvm_calc_mmu_role_ext(vcpu); role.ext.execonly = execonly; return role; @@ -5179,7 +5195,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, gpa, bytes, sp->role.word); offset = offset_in_page(gpa); - pte_size = sp->role.cr4_pae ? 8 : 4; + pte_size = sp->role.gpte_is_8_bytes ? 8 : 4; /* * Sometimes, the OS only writes the last one bytes to update status @@ -5203,7 +5219,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) page_offset = offset_in_page(gpa); level = sp->role.level; *nspte = 1; - if (!sp->role.cr4_pae) { + if (!sp->role.gpte_is_8_bytes) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map @@ -5393,10 +5409,12 @@ emulate: * This can happen if a guest gets a page-fault on data access but the HW * table walker is not able to read the instruction page (e.g instruction * page is not present in memory). In those cases we simply restart the - * guest. + * guest, with the exception of AMD Erratum 1096 which is unrecoverable. */ - if (unlikely(insn && !insn_len)) - return 1; + if (unlikely(insn && !insn_len)) { + if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu)) + return 1; + } er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); @@ -5509,7 +5527,9 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { if (flush && lock_flush_tlb) { - kvm_flush_remote_tlbs(kvm); + kvm_flush_remote_tlbs_with_address(kvm, + start_gfn, + iterator.gfn - start_gfn + 1); flush = false; } cond_resched_lock(&kvm->mmu_lock); @@ -5517,7 +5537,8 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, } if (flush && lock_flush_tlb) { - kvm_flush_remote_tlbs(kvm); + kvm_flush_remote_tlbs_with_address(kvm, start_gfn, + end_gfn - start_gfn + 1); flush = false; } @@ -6011,10 +6032,10 @@ out: /* * Calculate mmu pages needed for kvm. */ -unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) +unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) { - unsigned int nr_mmu_pages; - unsigned int nr_pages = 0; + unsigned long nr_mmu_pages; + unsigned long nr_pages = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int i; @@ -6027,8 +6048,7 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) } nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; - nr_mmu_pages = max(nr_mmu_pages, - (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); + nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); return nr_mmu_pages; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index bbdc60f2fae8..54c2a377795b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -64,7 +64,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); -static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) +static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm) { if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages) return kvm->arch.n_max_mmu_pages - diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 9f6c855a0043..dd30dccd2ad5 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -29,10 +29,10 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gfn %llx l%u%s q%u%s %s%s" \ + trace_seq_printf(p, "sp gfn %llx l%u %u-byte q%u%s %s%s" \ " %snxe %sad root %u %s%c", \ __entry->gfn, role.level, \ - role.cr4_pae ? " pae" : "", \ + role.gpte_is_8_bytes ? 8 : 4, \ role.quadrant, \ role.direct ? " direct" : "", \ access_str[role.access], \ diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 58ead7db71a3..e39741997893 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -281,9 +281,13 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) { bool fast_mode = idx & (1u << 31); + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; u64 ctr_val; + if (!pmu->version) + return 1; + if (is_vmware_backdoor_pmc(idx)) return kvm_pmu_rdpmc_vmware(vcpu, idx, data); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b5b128a0a051..406b558abfef 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -262,6 +262,7 @@ struct amd_svm_iommu_ir { }; #define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 #define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) #define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) @@ -2692,6 +2693,7 @@ static int npf_interception(struct vcpu_svm *svm) static int db_interception(struct vcpu_svm *svm) { struct kvm_run *kvm_run = svm->vcpu.run; + struct kvm_vcpu *vcpu = &svm->vcpu; if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && @@ -2702,6 +2704,8 @@ static int db_interception(struct vcpu_svm *svm) if (svm->nmi_singlestep) { disable_nmi_singlestep(svm); + /* Make sure we check for pending NMIs upon entry */ + kvm_make_request(KVM_REQ_EVENT, vcpu); } if (svm->vcpu.guest_debug & @@ -4517,14 +4521,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) kvm_lapic_reg_write(apic, APIC_ICR, icrl); break; case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: { + int i; + struct kvm_vcpu *vcpu; + struct kvm *kvm = svm->vcpu.kvm; struct kvm_lapic *apic = svm->vcpu.arch.apic; /* - * Update ICR high and low, then emulate sending IPI, - * which is handled when writing APIC_ICR. + * At this point, we expect that the AVIC HW has already + * set the appropriate IRR bits on the valid target + * vcpus. So, we just need to kick the appropriate vcpu. */ - kvm_lapic_reg_write(apic, APIC_ICR2, icrh); - kvm_lapic_reg_write(apic, APIC_ICR, icrl); + kvm_for_each_vcpu(i, vcpu, kvm) { + bool m = kvm_apic_match_dest(vcpu, apic, + icrl & KVM_APIC_SHORT_MASK, + GET_APIC_DEST_FIELD(icrh), + icrl & KVM_APIC_DEST_MASK); + + if (m && !avic_vcpu_is_running(vcpu)) + kvm_vcpu_wake_up(vcpu); + } break; } case AVIC_IPI_FAILURE_INVALID_TARGET: @@ -4596,7 +4611,7 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat); if (entry) - WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK); + clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry); } static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) @@ -5621,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); + kvm_load_guest_xcr0(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -5766,6 +5782,7 @@ 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); stgi(); /* Any pending NMI will happen here */ @@ -6215,32 +6232,24 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) +static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *nested_vmcb; struct page *page; - struct { - u64 guest; - u64 vmcb; - } svm_state_save; - int ret; + u64 guest; + u64 vmcb; - ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save, - sizeof(svm_state_save)); - if (ret) - return ret; + guest = GET_SMSTATE(u64, smstate, 0x7ed8); + vmcb = GET_SMSTATE(u64, smstate, 0x7ee0); - if (svm_state_save.guest) { - vcpu->arch.hflags &= ~HF_SMM_MASK; - nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page); - if (nested_vmcb) - enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page); - else - ret = 1; - vcpu->arch.hflags |= HF_SMM_MASK; + if (guest) { + nested_vmcb = nested_svm_map(svm, vmcb, &page); + if (!nested_vmcb) + return 1; + enter_svm_guest_mode(svm, vmcb, nested_vmcb, page); } - return ret; + return 0; } static int enable_smi_window(struct kvm_vcpu *vcpu) @@ -6422,11 +6431,11 @@ e_free: return ret; } -static int get_num_contig_pages(int idx, struct page **inpages, - unsigned long npages) +static unsigned long get_num_contig_pages(unsigned long idx, + struct page **inpages, unsigned long npages) { unsigned long paddr, next_paddr; - int i = idx + 1, pages = 1; + unsigned long i = idx + 1, pages = 1; /* find the number of contiguous pages starting from idx */ paddr = __sme_page_pa(inpages[idx]); @@ -6445,12 +6454,12 @@ static int get_num_contig_pages(int idx, struct page **inpages, static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) { - unsigned long vaddr, vaddr_end, next_vaddr, npages, size; + unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i; struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct kvm_sev_launch_update_data params; struct sev_data_launch_update_data *data; struct page **inpages; - int i, ret, pages; + int ret; if (!sev_guest(kvm)) return -ENOTTY; @@ -6799,7 +6808,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) struct page **src_p, **dst_p; struct kvm_sev_dbg debug; unsigned long n; - int ret, size; + unsigned int size; + int ret; if (!sev_guest(kvm)) return -ENOTTY; @@ -6807,6 +6817,11 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) return -EFAULT; + if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr) + return -EINVAL; + if (!debug.dst_uaddr) + return -EINVAL; + vaddr = debug.src_uaddr; size = debug.len; vaddr_end = vaddr + size; @@ -6857,8 +6872,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) dst_vaddr, len, &argp->error); - sev_unpin_memory(kvm, src_p, 1); - sev_unpin_memory(kvm, dst_p, 1); + sev_unpin_memory(kvm, src_p, n); + sev_unpin_memory(kvm, dst_p, n); if (ret) goto err; @@ -7098,6 +7113,36 @@ static int nested_enable_evmcs(struct kvm_vcpu *vcpu, return -ENODEV; } +static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) +{ + bool is_user, smap; + + is_user = svm_get_cpl(vcpu) == 3; + smap = !kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); + + /* + * Detect and workaround Errata 1096 Fam_17h_00_0Fh + * + * In non SEV guest, hypervisor will be able to read the guest + * memory to decode the instruction pointer when insn_len is zero + * so we return true to indicate that decoding is possible. + * + * But in the SEV guest, the guest memory is encrypted with the + * guest specific key and hypervisor will not be able to decode the + * instruction pointer so we will not able to workaround it. Lets + * print the error and request to kill the guest. + */ + if (is_user && smap) { + if (!sev_guest(vcpu->kvm)) + return true; + + pr_err_ratelimited("KVM: Guest triggered AMD Erratum 1096\n"); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + } + + return false; +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -7231,6 +7276,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .nested_enable_evmcs = nested_enable_evmcs, .nested_get_evmcs_version = nested_get_evmcs_version, + + .need_emulation_on_page_fault = svm_need_emulation_on_page_fault, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 6432d08c7de7..4d47a2631d1f 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -438,13 +438,13 @@ TRACE_EVENT(kvm_apic_ipi, ); TRACE_EVENT(kvm_apic_accept_irq, - TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec), + TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec), TP_ARGS(apicid, dm, tm, vec), TP_STRUCT__entry( __field( __u32, apicid ) __field( __u16, dm ) - __field( __u8, tm ) + __field( __u16, tm ) __field( __u8, vec ) ), diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f24a2c225070..0c601d079cd2 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -500,6 +500,17 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } +static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + + msr_bitmap[word] = ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } +} + /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. @@ -541,39 +552,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, return false; msr_bitmap_l1 = (unsigned long *)kmap(page); - if (nested_cpu_has_apic_reg_virt(vmcs12)) { - /* - * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it - * just lets the processor take the value from the virtual-APIC page; - * take those 256 bits directly from the L1 bitmap. - */ - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap_l0[word] = msr_bitmap_l1[word]; - msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; - } - } else { - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap_l0[word] = ~0; - msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; - } - } - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_TASKPRI), - MSR_TYPE_W); + /* + * To keep the control flow simple, pay eight 8-byte writes (sixteen + * 4-byte writes on 32-bit systems) up front to enable intercepts for + * the x2APIC MSR range and selectively disable them below. + */ + enable_x2apic_msr_intercepts(msr_bitmap_l0); + + if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { + if (nested_cpu_has_apic_reg_virt(vmcs12)) { + /* + * L0 need not intercept reads for MSRs between 0x800 + * and 0x8ff, it just lets the processor take the value + * from the virtual-APIC page; take those 256 bits + * directly from the L1 bitmap. + */ + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + + msr_bitmap_l0[word] = msr_bitmap_l1[word]; + } + } - if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_EOI), - MSR_TYPE_W); nested_vmx_disable_intercept_for_msr( msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_SELF_IPI), - MSR_TYPE_W); + X2APIC_MSR(APIC_TASKPRI), + MSR_TYPE_R | MSR_TYPE_W); + + if (nested_cpu_has_vid(vmcs12)) { + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_EOI), + MSR_TYPE_W); + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_SELF_IPI), + MSR_TYPE_W); + } } if (spec_ctrl) @@ -2585,6 +2601,11 @@ static int nested_check_host_control_regs(struct kvm_vcpu *vcpu, !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) || !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)) + 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, @@ -2852,20 +2873,27 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) /* * If translation failed, VM entry will fail because * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull. - * Failing the vm entry is _not_ what the processor - * does but it's basically the only possibility we - * have. We could still enter the guest if CR8 load - * exits are enabled, CR8 store exits are enabled, and - * virtualize APIC access is disabled; in this case - * the processor would never use the TPR shadow and we - * could simply clear the bit from the execution - * control. But such a configuration is useless, so - * let's keep the code simple. */ if (!is_error_page(page)) { vmx->nested.virtual_apic_page = page; hpa = page_to_phys(vmx->nested.virtual_apic_page); vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa); + } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) && + nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) && + !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { + /* + * The processor will never use the TPR shadow, simply + * clear the bit from the execution control. Such a + * configuration is useless, but it happens in tests. + * For any other configuration, failing the vm entry is + * _not_ what the processor does but it's basically the + * only possibility we have. + */ + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_TPR_SHADOW); + } else { + printk("bad virtual-APIC page address\n"); + dump_vmcs(); } } @@ -3768,8 +3796,18 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW)); nested_ept_uninit_mmu_context(vcpu); - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + + /* + * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3 + * points to shadow pages! Fortunately we only get here after a WARN_ON + * if EPT is disabled, so a VMabort is perfectly fine. + */ + if (enable_ept) { + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + } else { + nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED); + } /* * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs @@ -5385,7 +5423,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return ret; /* Empty 'VMXON' state is permitted */ - if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12)) + if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) return 0; if (kvm_state->vmx.vmcs_pa != -1ull) { @@ -5429,7 +5467,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmcs12->vmcs_link_pointer != -1ull) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); - if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12)) + if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12)) return -EINVAL; if (copy_from_user(shadow_vmcs12, @@ -5717,6 +5755,14 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) { int i; + /* + * Without EPT it is not possible to restore L1's CR3 and PDPTR on + * VMfail, because they are not available in vmcs01. Just always + * use hardware checks. + */ + if (!enable_ept) + nested_early_check = 1; + if (!cpu_has_vmx_shadow_vmcs()) enable_shadow_vmcs = 0; if (enable_shadow_vmcs) { diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 7b272738c576..d4cb1945b2e3 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> +#include <asm/nospec-branch.h> #define WORD_SIZE (BITS_PER_LONG / 8) @@ -77,6 +78,17 @@ ENDPROC(vmx_vmenter) * referred to by VMCS.HOST_RIP. */ ENTRY(vmx_vmexit) +#ifdef CONFIG_RETPOLINE + ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE + /* Preserve guest's RAX, it's used to stuff the RSB. */ + push %_ASM_AX + + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + + pop %_ASM_AX +.Lvmexit_skip_rsb: +#endif ret ENDPROC(vmx_vmexit) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c73375e01ab8..0c955bb286ff 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1683,12 +1683,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = to_vmx(vcpu)->spec_ctrl; break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) - return 1; - msr_info->data = to_vmx(vcpu)->arch_capabilities; - break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -1895,11 +1889,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, MSR_TYPE_W); break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated) - return 1; - vmx->arch_capabilities = data; - break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -4088,8 +4077,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } - vmx->arch_capabilities = kvm_get_arch_capabilities(); - vm_exit_controls_init(vmx, vmx_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ @@ -5616,7 +5603,7 @@ static void vmx_dump_dtsel(char *name, uint32_t limit) vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); } -static void dump_vmcs(void) +void dump_vmcs(void) { u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); @@ -6423,6 +6410,8 @@ 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); + if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && vcpu->arch.pkru != vmx->host_pkru) @@ -6473,9 +6462,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); - /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); - /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) current_evmcs->hv_clean_fields |= @@ -6519,6 +6505,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } + kvm_put_guest_xcr0(vcpu); + vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; @@ -6865,6 +6853,30 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu) } } +static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *entry; + union cpuid10_eax eax; + + entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); + if (!entry) + return false; + + eax.full = entry->eax; + return (eax.split.version_id > 0); +} + +static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + bool pmu_enabled = guest_cpuid_has_pmu(vcpu); + + if (pmu_enabled) + vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING; + else + vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING; +} + static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6953,6 +6965,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (nested_vmx_allowed(vcpu)) { nested_vmx_cr_fixed1_bits_update(vcpu); nested_vmx_entry_exit_ctls_update(vcpu); + nested_vmx_procbased_ctls_update(vcpu); } if (boot_cpu_has(X86_FEATURE_INTEL_PT) && @@ -7016,6 +7029,7 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; + struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer; if (kvm_mwait_in_guest(vcpu->kvm)) return -EOPNOTSUPP; @@ -7024,7 +7038,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) tscl = rdtsc(); guest_tscl = kvm_read_l1_tsc(vcpu, tscl); delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; - lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns); + lapic_timer_advance_cycles = nsec_to_cycles(vcpu, + ktimer->timer_advance_ns); if (delta_tsc > lapic_timer_advance_cycles) delta_tsc -= lapic_timer_advance_cycles; @@ -7382,7 +7397,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) +static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -7393,9 +7408,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) } if (vmx->nested.smm.guest_mode) { - vcpu->arch.hflags &= ~HF_SMM_MASK; ret = nested_vmx_enter_non_root_mode(vcpu, false); - vcpu->arch.hflags |= HF_SMM_MASK; if (ret) return ret; @@ -7409,6 +7422,11 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) +{ + return 0; +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; @@ -7711,6 +7729,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .set_nested_state = NULL, .get_vmcs12_pages = NULL, .nested_enable_evmcs = NULL, + .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, }; static void vmx_cleanup_l1d_flush(void) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 1554cb45b393..f879529906b4 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -190,7 +190,6 @@ struct vcpu_vmx { u64 msr_guest_kernel_gs_base; #endif - u64 arch_capabilities; u64 spec_ctrl; u32 vm_entry_controls_shadow; @@ -518,4 +517,6 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx) vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); } +void dump_vmcs(void); + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 65e4559eef2f..b5edc8e3ce1d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -136,10 +136,14 @@ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); -/* lapic timer advance (tscdeadline mode only) in nanoseconds */ -unsigned int __read_mostly lapic_timer_advance_ns = 1000; +/* + * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables + * adaptive tuning starting from default advancment of 1000ns. '0' disables + * advancement entirely. Any other value is used as-is and disables adaptive + * tuning, i.e. allows priveleged userspace to set an exact advancement time. + */ +static int __read_mostly lapic_timer_advance_ns = -1; module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); -EXPORT_SYMBOL_GPL(lapic_timer_advance_ns); static bool __read_mostly vector_hashing = true; module_param(vector_hashing, bool, S_IRUGO); @@ -800,7 +804,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) { if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && !vcpu->guest_xcr0_loaded) { @@ -810,8 +814,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 1; } } +EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); -static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { if (vcpu->guest_xcr0_loaded) { if (vcpu->arch.xcr0 != host_xcr0) @@ -819,6 +824,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 0; } } +EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -1125,7 +1131,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES, + 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, MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, @@ -1158,6 +1164,7 @@ static u32 emulated_msrs[] = { MSR_IA32_TSC_ADJUST, MSR_IA32_TSCDEADLINE, + MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, @@ -2443,6 +2450,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (msr_info->host_initiated) vcpu->arch.microcode_version = data; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.arch_capabilities = data; + break; case MSR_EFER: return set_efer(vcpu, data); case MSR_K7_HWCR: @@ -2747,6 +2759,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return 1; + msr_info->data = vcpu->arch.arch_capabilities; + break; case MSR_IA32_TSC: msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; break; @@ -3081,7 +3099,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_NESTED_STATE: r = kvm_x86_ops->get_nested_state ? - kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0; + kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0; break; default: break; @@ -3516,7 +3534,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, memset(&events->reserved, 0, sizeof(events->reserved)); } -static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags); +static void kvm_smm_changed(struct kvm_vcpu *vcpu); static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) @@ -3576,12 +3594,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - u32 hflags = vcpu->arch.hflags; - if (events->smi.smm) - hflags |= HF_SMM_MASK; - else - hflags &= ~HF_SMM_MASK; - kvm_set_hflags(vcpu, hflags); + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { + if (events->smi.smm) + vcpu->arch.hflags |= HF_SMM_MASK; + else + vcpu->arch.hflags &= ~HF_SMM_MASK; + kvm_smm_changed(vcpu); + } vcpu->arch.smi_pending = events->smi.pending; @@ -4258,7 +4277,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, - u32 kvm_nr_mmu_pages) + unsigned long kvm_nr_mmu_pages) { if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; @@ -4272,7 +4291,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return 0; } -static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) +static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) { return kvm->arch.n_max_mmu_pages; } @@ -5946,12 +5965,18 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) { - kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags); + emul_to_vcpu(ctxt)->arch.hflags = emul_flags; } -static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase) +static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, + const char *smstate) { - return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase); + return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate); +} + +static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) +{ + kvm_smm_changed(emul_to_vcpu(ctxt)); } static const struct x86_emulate_ops emulate_ops = { @@ -5994,6 +6019,7 @@ static const struct x86_emulate_ops emulate_ops = { .get_hflags = emulator_get_hflags, .set_hflags = emulator_set_hflags, .pre_leave_smm = emulator_pre_leave_smm, + .post_leave_smm = emulator_post_leave_smm, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -6235,16 +6261,6 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); } -static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags) -{ - unsigned changed = vcpu->arch.hflags ^ emul_flags; - - vcpu->arch.hflags = emul_flags; - - if (changed & HF_SMM_MASK) - kvm_smm_changed(vcpu); -} - static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { @@ -6523,15 +6539,45 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); +static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pio.count = 0; + return 1; +} + +static int complete_fast_pio_out(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pio.count = 0; + + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) + return 1; + + return kvm_skip_emulated_instruction(vcpu); +} + static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, size, port, &val, 1); - /* do not return to emulator after return from userspace */ - vcpu->arch.pio.count = 0; - return ret; + if (ret) + return ret; + + /* + * Workaround userspace that relies on old KVM behavior of %rip being + * incremented prior to exiting to userspace to handle "OUT 0x7e". + */ + if (port == 0x7e && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) { + vcpu->arch.complete_userspace_io = + complete_fast_pio_out_port_0x7e; + kvm_skip_emulated_instruction(vcpu); + } else { + vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.complete_userspace_io = complete_fast_pio_out; + } + return 0; } static int complete_fast_pio_in(struct kvm_vcpu *vcpu) @@ -6541,6 +6587,11 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) /* We should only ever be called with arch.pio.count equal to 1 */ BUG_ON(vcpu->arch.pio.count != 1); + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) { + vcpu->arch.pio.count = 0; + return 1; + } + /* For size less than 4 we merge, else we zero extend */ val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0; @@ -6553,7 +6604,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) vcpu->arch.pio.port, &val, 1); kvm_register_write(vcpu, VCPU_REGS_RAX, val); - return 1; + return kvm_skip_emulated_instruction(vcpu); } static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, @@ -6572,6 +6623,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, return ret; } + vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_in; return 0; @@ -6579,16 +6631,13 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in) { - int ret = kvm_skip_emulated_instruction(vcpu); + int ret; - /* - * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ if (in) - return kvm_fast_pio_in(vcpu, size, port) && ret; + ret = kvm_fast_pio_in(vcpu, size, port); else - return kvm_fast_pio_out(vcpu, size, port) && ret; + ret = kvm_fast_pio_out(vcpu, size, port); + return ret && kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_fast_pio); @@ -7413,9 +7462,9 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase); } +#ifdef CONFIG_X86_64 static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) { -#ifdef CONFIG_X86_64 struct desc_ptr dt; struct kvm_segment seg; unsigned long val; @@ -7465,10 +7514,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) for (i = 0; i < 6; i++) enter_smm_save_seg_64(vcpu, buf, i); -#else - WARN_ON_ONCE(1); -#endif } +#endif static void enter_smm(struct kvm_vcpu *vcpu) { @@ -7479,9 +7526,11 @@ static void enter_smm(struct kvm_vcpu *vcpu) trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); memset(buf, 0, 512); +#ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) enter_smm_save_state_64(vcpu, buf); else +#endif enter_smm_save_state_32(vcpu, buf); /* @@ -7539,8 +7588,10 @@ static void enter_smm(struct kvm_vcpu *vcpu) kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); +#ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) kvm_x86_ops->set_efer(vcpu, 0); +#endif kvm_update_cpuid(vcpu); kvm_mmu_reset_context(vcpu); @@ -7837,15 +7888,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - kvm_load_guest_xcr0(vcpu); - if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_x86_ops->request_immediate_exit(vcpu); } trace_kvm_entry(vcpu->vcpu_id); - if (lapic_timer_advance_ns) + if (lapic_in_kernel(vcpu) && + vcpu->arch.apic->lapic_timer.timer_advance_ns) wait_lapic_expire(vcpu); guest_enter_irqoff(); @@ -7891,8 +7941,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_put_guest_xcr0(vcpu); - kvm_before_interrupt(vcpu); kvm_x86_ops->handle_external_intr(vcpu); kvm_after_interrupt(vcpu); @@ -8733,6 +8781,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, 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); vcpu_load(vcpu); @@ -9034,7 +9083,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) if (irqchip_in_kernel(vcpu->kvm)) { vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); - r = kvm_create_lapic(vcpu); + r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; } else @@ -9429,13 +9478,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - int nr_mmu_pages = 0; - if (!kvm->arch.n_requested_mmu_pages) - nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); - - if (nr_mmu_pages) - kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + kvm_mmu_change_mmu_pages(kvm, + kvm_mmu_calculate_default_mmu_pages(kvm)); /* * Dirty logging tracks sptes in 4k granularity, meaning that large diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 28406aa1136d..534d3f28bb01 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -294,8 +294,6 @@ extern u64 kvm_supported_xcr0(void); extern unsigned int min_timer_period_us; -extern unsigned int lapic_timer_advance_ns; - extern bool enable_vmware_backdoor; extern struct static_key kvm_no_apic_vcpu; @@ -347,4 +345,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) __this_cpu_write(current_vcpu, NULL); } +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 140e61843a07..5246db42de45 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -6,6 +6,18 @@ # Produces uninteresting flaky coverage. KCOV_INSTRUMENT_delay.o := n +# Early boot use of cmdline; don't instrument it +ifdef CONFIG_AMD_MEM_ENCRYPT +KCOV_INSTRUMENT_cmdline.o := n +KASAN_SANITIZE_cmdline.o := n + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_cmdline.o = -pg +endif + +CFLAGS_cmdline.o := $(call cc-option, -fno-stack-protector) +endif + inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt quiet_cmd_inat_tables = GEN $@ @@ -23,7 +35,6 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o -lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index db4e5aa0858b..b2f1822084ae 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -16,6 +16,30 @@ #include <asm/smap.h> #include <asm/export.h> +.macro ALIGN_DESTINATION + /* check for bad alignment of destination */ + movl %edi,%ecx + andl $7,%ecx + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +100: movb (%rsi),%al +101: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 100b +102: + .section .fixup,"ax" +103: addl %ecx,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous + + _ASM_EXTABLE_UA(100b, 103b) + _ASM_EXTABLE_UA(101b, 103b) + .endm + /* * copy_user_generic_unrolled - memory copy with exception handling. * This version is for CPUs like P4 that don't have efficient micro @@ -194,6 +218,30 @@ ENDPROC(copy_user_enhanced_fast_string) EXPORT_SYMBOL(copy_user_enhanced_fast_string) /* + * Try to copy last bytes and clear the rest if needed. + * Since protection fault in copy_from/to_user is not a normal situation, + * it is not necessary to optimize tail handling. + * + * Input: + * rdi destination + * rsi source + * rdx count + * + * Output: + * eax uncopied bytes or 0 if successful. + */ +ALIGN; +copy_user_handle_tail: + movl %edx,%ecx +1: rep movsb +2: mov %ecx,%eax + ASM_CLAC + ret + + _ASM_EXTABLE_UA(1b, 2b) +ENDPROC(copy_user_handle_tail) + +/* * copy_user_nocache - Uncached memory copy with exception handling * This will force destination out of cache for more performance. * diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index 9baca3e054be..e7925d668b68 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -94,7 +94,7 @@ static unsigned do_csum(const unsigned char *buff, unsigned len) : "m" (*(unsigned long *)buff), "r" (zero), "0" (result)); --count; - buff += 8; + buff += 8; } result = add32_with_carry(result>>32, result&0xffffffff); diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 3b24dc05251c..9d05572370ed 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -257,6 +257,7 @@ ENTRY(__memcpy_mcsafe) /* Copy successful. Return zero */ .L_done_memcpy_trap: xorl %eax, %eax +.L_done: ret ENDPROC(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) @@ -273,7 +274,7 @@ EXPORT_SYMBOL_GPL(__memcpy_mcsafe) addl %edx, %ecx .E_trailing_bytes: mov %ecx, %eax - ret + jmp .L_done /* * For write fault handling, given the destination is unaligned, diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S deleted file mode 100644 index dc2ab6ea6768..000000000000 --- a/arch/x86/lib/rwsem.S +++ /dev/null @@ -1,156 +0,0 @@ -/* - * x86 semaphore implementation. - * - * (C) Copyright 1999 Linus Torvalds - * - * Portions Copyright 1999 Red Hat, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org> - */ - -#include <linux/linkage.h> -#include <asm/alternative-asm.h> -#include <asm/frame.h> - -#define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg) -#define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l) - -#ifdef CONFIG_X86_32 - -/* - * The semaphore operations have a special calling sequence that - * allow us to do a simpler in-line version of them. These routines - * need to convert that sequence back into the C sequence when - * there is contention on the semaphore. - * - * %eax contains the semaphore pointer on entry. Save the C-clobbered - * registers (%eax, %edx and %ecx) except %eax which is either a return - * value or just gets clobbered. Same is true for %edx so make sure GCC - * reloads it after the slow path, by making it hold a temporary, for - * example see ____down_write(). - */ - -#define save_common_regs \ - pushl %ecx - -#define restore_common_regs \ - popl %ecx - - /* Avoid uglifying the argument copying x86-64 needs to do. */ - .macro movq src, dst - .endm - -#else - -/* - * x86-64 rwsem wrappers - * - * This interfaces the inline asm code to the slow-path - * C routines. We need to save the call-clobbered regs - * that the asm does not mark as clobbered, and move the - * argument from %rax to %rdi. - * - * NOTE! We don't need to save %rax, because the functions - * will always return the semaphore pointer in %rax (which - * is also the input argument to these helpers) - * - * The following can clobber %rdx because the asm clobbers it: - * call_rwsem_down_write_failed - * call_rwsem_wake - * but %rdi, %rsi, %rcx, %r8-r11 always need saving. - */ - -#define save_common_regs \ - pushq %rdi; \ - pushq %rsi; \ - pushq %rcx; \ - pushq %r8; \ - pushq %r9; \ - pushq %r10; \ - pushq %r11 - -#define restore_common_regs \ - popq %r11; \ - popq %r10; \ - popq %r9; \ - popq %r8; \ - popq %rcx; \ - popq %rsi; \ - popq %rdi - -#endif - -/* Fix up special calling conventions */ -ENTRY(call_rwsem_down_read_failed) - FRAME_BEGIN - save_common_regs - __ASM_SIZE(push,) %__ASM_REG(dx) - movq %rax,%rdi - call rwsem_down_read_failed - __ASM_SIZE(pop,) %__ASM_REG(dx) - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_read_failed) - -ENTRY(call_rwsem_down_read_failed_killable) - FRAME_BEGIN - save_common_regs - __ASM_SIZE(push,) %__ASM_REG(dx) - movq %rax,%rdi - call rwsem_down_read_failed_killable - __ASM_SIZE(pop,) %__ASM_REG(dx) - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_read_failed_killable) - -ENTRY(call_rwsem_down_write_failed) - FRAME_BEGIN - save_common_regs - movq %rax,%rdi - call rwsem_down_write_failed - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_write_failed) - -ENTRY(call_rwsem_down_write_failed_killable) - FRAME_BEGIN - save_common_regs - movq %rax,%rdi - call rwsem_down_write_failed_killable - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_write_failed_killable) - -ENTRY(call_rwsem_wake) - FRAME_BEGIN - /* do nothing if still outstanding active readers */ - __ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx) - jnz 1f - save_common_regs - movq %rax,%rdi - call rwsem_wake - restore_common_regs -1: FRAME_END - ret -ENDPROC(call_rwsem_wake) - -ENTRY(call_rwsem_downgrade_wake) - FRAME_BEGIN - save_common_regs - __ASM_SIZE(push,) %__ASM_REG(dx) - movq %rax,%rdi - call rwsem_downgrade_wake - __ASM_SIZE(pop,) %__ASM_REG(dx) - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_downgrade_wake) diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index ee42bb0cbeb3..9952a01cad24 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -55,26 +55,6 @@ unsigned long clear_user(void __user *to, unsigned long n) EXPORT_SYMBOL(clear_user); /* - * Try to copy last bytes and clear the rest if needed. - * Since protection fault in copy_from/to_user is not a normal situation, - * it is not necessary to optimize tail handling. - */ -__visible unsigned long -copy_user_handle_tail(char *to, char *from, unsigned len) -{ - for (; len; --len, to++) { - char c; - - if (__get_user_nocheck(c, from++, sizeof(char))) - break; - if (__put_user_nocheck(c, to, sizeof(char))) - break; - } - clac(); - return len; -} - -/* * Similar to copy_user_handle_tail, probe for the write fault point, * but reuse __memcpy_mcsafe in case a new read error is encountered. * clac() is handled in _copy_to_iter_mcsafe(). diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 7b71ac15b235..6a7302d1161f 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -259,7 +259,8 @@ static void note_wx(struct pg_state *st) #endif /* Account the WX pages */ st->wx_pages += npages; - WARN_ONCE(1, "x86/mm: Found insecure W+X mapping at address %pS\n", + WARN_ONCE(__supported_pte_mask & _PAGE_NX, + "x86/mm: Found insecure W+X mapping at address %pS\n", (void *)st->start_address); } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index f905a2371080..8dacdb96899e 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -5,6 +5,7 @@ #include <linux/memblock.h> #include <linux/swapfile.h> #include <linux/swapops.h> +#include <linux/kmemleak.h> #include <asm/set_memory.h> #include <asm/e820/api.h> @@ -766,6 +767,11 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end) if (debug_pagealloc_enabled()) { pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n", begin, end - 1); + /* + * Inform kmemleak about the hole in the memory since the + * corresponding pages will be unmapped. + */ + kmemleak_free_part((void *)begin, end - begin); set_memory_np(begin, (end - begin) >> PAGE_SHIFT); } else { /* diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0029604af8a4..dd73d5d74393 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -825,7 +825,7 @@ void __init __early_set_fixmap(enum fixed_addresses idx, pte = early_ioremap_pte(addr); /* Sanitize 'prot' against any unsupported bits: */ - pgprot_val(flags) &= __default_kernel_pte_mask; + pgprot_val(flags) &= __supported_pte_mask; if (pgprot_val(flags)) set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 3f452ffed7e9..d669c5e797e0 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -94,7 +94,7 @@ void __init kernel_randomize_memory(void) if (!kaslr_memory_enabled()) return; - kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT); + kaslr_regions[0].size_tb = 1 << (MAX_PHYSMEM_BITS - TB_SHIFT); kaslr_regions[1].size_tb = VMALLOC_SIZE_TB; /* diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index db3165714521..dc726e07d8ba 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -230,7 +230,7 @@ bool mmap_address_hint_valid(unsigned long addr, unsigned long len) /* Can we access it for direct reading/writing? Must be RAM: */ int valid_phys_addr_range(phys_addr_t addr, size_t count) { - return addr + count <= __pa(high_memory); + return addr + count - 1 <= __pa(high_memory - 1); } /* Can we access it through mmap? Must be a valid physical address: */ diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 8c9a54ebda60..9c2463bc158f 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -35,6 +35,7 @@ #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/uaccess.h> +#include <linux/cpu.h> #include <asm/cpufeature.h> #include <asm/hypervisor.h> @@ -77,7 +78,7 @@ static void __init pti_print_if_secure(const char *reason) pr_info("%s\n", reason); } -enum pti_mode { +static enum pti_mode { PTI_AUTO = 0, PTI_FORCE_OFF, PTI_FORCE_ON @@ -115,7 +116,8 @@ void __init pti_check_boottime_disable(void) } } - if (cmdline_find_option_bool(boot_command_line, "nopti")) { + if (cmdline_find_option_bool(boot_command_line, "nopti") || + cpu_mitigations_off()) { pti_mode = PTI_FORCE_OFF; pti_print_if_insecure("disabled on command line."); return; @@ -602,7 +604,7 @@ static void pti_clone_kernel_text(void) set_memory_global(start, (end_global - start) >> PAGE_SHIFT); } -void pti_set_kernel_image_nonglobal(void) +static void pti_set_kernel_image_nonglobal(void) { /* * The identity map is created with PMDs, regardless of the diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index bc4bc7b2f075..487b8474c01c 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -728,7 +728,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, { int cpu; - struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = { + struct flush_tlb_info info = { .mm = mm, .stride_shift = stride_shift, .freed_tables = freed_tables, diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 458a0e2bcc57..a25a9fd987a9 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -449,7 +449,7 @@ void __init efi_free_boot_services(void) */ rm_size = real_mode_size_needed(); if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) { - set_real_mode_mem(start, rm_size); + set_real_mode_mem(start); start += rm_size; size -= rm_size; } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index d10105825d57..7dce39c8c034 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -15,15 +15,6 @@ u32 *trampoline_cr4_features; /* Hold the pgd entry used on booting additional CPUs */ pgd_t trampoline_pgd_entry; -void __init set_real_mode_mem(phys_addr_t mem, size_t size) -{ - void *base = __va(mem); - - real_mode_header = (struct real_mode_header *) base; - printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", - base, (unsigned long long)mem, size); -} - void __init reserve_real_mode(void) { phys_addr_t mem; @@ -42,7 +33,7 @@ void __init reserve_real_mode(void) } memblock_reserve(mem, size); - set_real_mode_mem(mem, size); + set_real_mode_mem(mem); } static void __init setup_real_mode(void) diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index a9e80e44178c..a8985e1f7432 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -32,12 +32,6 @@ config ARCH_DEFCONFIG default "arch/um/configs/i386_defconfig" if X86_32 default "arch/um/configs/x86_64_defconfig" if X86_64 -config RWSEM_XCHGADD_ALGORITHM - def_bool 64BIT - -config RWSEM_GENERIC_SPINLOCK - def_bool !RWSEM_XCHGADD_ALGORITHM - config 3_LEVEL_PGTABLES bool "Three-level pagetables" if !64BIT default 64BIT diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 2d686ae54681..33c51c064c77 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -21,14 +21,12 @@ obj-y += checksum_32.o syscalls_32.o obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o -subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o else obj-y += syscalls_64.o vdso/ -subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \ - ../lib/rwsem.o +subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o endif |
