diff options
Diffstat (limited to 'arch/x86')
| -rw-r--r-- | arch/x86/boot/Makefile | 1 | ||||
| -rw-r--r-- | arch/x86/crypto/Makefile | 2 | ||||
| -rw-r--r-- | arch/x86/crypto/aes_ctrby8_avx-x86_64.S | 46 | ||||
| -rw-r--r-- | arch/x86/include/asm/vgtod.h | 6 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/boot.c | 9 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/Makefile | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mkcapflags.sh | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore.h | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c | 17 | ||||
| -rw-r--r-- | arch/x86/kernel/perf_regs.c | 90 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu.c | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx.c | 88 | ||||
| -rw-r--r-- | arch/x86/lib/insn.c | 2 | ||||
| -rw-r--r-- | arch/x86/mm/init.c | 37 | ||||
| -rw-r--r-- | arch/x86/um/sys_call_table_32.c | 2 | ||||
| -rw-r--r-- | arch/x86/um/sys_call_table_64.c | 2 | ||||
| -rw-r--r-- | arch/x86/vdso/vma.c | 45 |
17 files changed, 249 insertions, 105 deletions
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 5b016e2498f3..3db07f30636f 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -51,6 +51,7 @@ targets += cpustr.h $(obj)/cpustr.h: $(obj)/mkcpustr FORCE $(call if_changed,cpustr) endif +clean-files += cpustr.h # --------------------------------------------------------------------------- diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index fd0f848938cc..5a4a089e8b1f 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -26,7 +26,6 @@ obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o -obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/ obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o @@ -46,6 +45,7 @@ endif ifeq ($(avx2_supported),yes) obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o + obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/ endif aes-i586-y := aes-i586-asm_32.o aes_glue.o diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S index 2df2a0298f5a..a916c4a61165 100644 --- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S +++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S @@ -208,7 +208,7 @@ ddq_add_8: .if (klen == KEY_128) .if (load_keys) - vmovdqa 3*16(p_keys), xkeyA + vmovdqa 3*16(p_keys), xkey4 .endif .else vmovdqa 3*16(p_keys), xkeyA @@ -224,7 +224,7 @@ ddq_add_8: add $(16*by), p_in .if (klen == KEY_128) - vmovdqa 4*16(p_keys), xkey4 + vmovdqa 4*16(p_keys), xkeyB .else .if (load_keys) vmovdqa 4*16(p_keys), xkey4 @@ -234,7 +234,12 @@ ddq_add_8: .set i, 0 .rept by club XDATA, i - vaesenc xkeyA, var_xdata, var_xdata /* key 3 */ + /* key 3 */ + .if (klen == KEY_128) + vaesenc xkey4, var_xdata, var_xdata + .else + vaesenc xkeyA, var_xdata, var_xdata + .endif .set i, (i +1) .endr @@ -243,13 +248,18 @@ ddq_add_8: .set i, 0 .rept by club XDATA, i - vaesenc xkey4, var_xdata, var_xdata /* key 4 */ + /* key 4 */ + .if (klen == KEY_128) + vaesenc xkeyB, var_xdata, var_xdata + .else + vaesenc xkey4, var_xdata, var_xdata + .endif .set i, (i +1) .endr .if (klen == KEY_128) .if (load_keys) - vmovdqa 6*16(p_keys), xkeyB + vmovdqa 6*16(p_keys), xkey8 .endif .else vmovdqa 6*16(p_keys), xkeyB @@ -267,12 +277,17 @@ ddq_add_8: .set i, 0 .rept by club XDATA, i - vaesenc xkeyB, var_xdata, var_xdata /* key 6 */ + /* key 6 */ + .if (klen == KEY_128) + vaesenc xkey8, var_xdata, var_xdata + .else + vaesenc xkeyB, var_xdata, var_xdata + .endif .set i, (i +1) .endr .if (klen == KEY_128) - vmovdqa 8*16(p_keys), xkey8 + vmovdqa 8*16(p_keys), xkeyB .else .if (load_keys) vmovdqa 8*16(p_keys), xkey8 @@ -288,7 +303,7 @@ ddq_add_8: .if (klen == KEY_128) .if (load_keys) - vmovdqa 9*16(p_keys), xkeyA + vmovdqa 9*16(p_keys), xkey12 .endif .else vmovdqa 9*16(p_keys), xkeyA @@ -297,7 +312,12 @@ ddq_add_8: .set i, 0 .rept by club XDATA, i - vaesenc xkey8, var_xdata, var_xdata /* key 8 */ + /* key 8 */ + .if (klen == KEY_128) + vaesenc xkeyB, var_xdata, var_xdata + .else + vaesenc xkey8, var_xdata, var_xdata + .endif .set i, (i +1) .endr @@ -306,7 +326,12 @@ ddq_add_8: .set i, 0 .rept by club XDATA, i - vaesenc xkeyA, var_xdata, var_xdata /* key 9 */ + /* key 9 */ + .if (klen == KEY_128) + vaesenc xkey12, var_xdata, var_xdata + .else + vaesenc xkeyA, var_xdata, var_xdata + .endif .set i, (i +1) .endr @@ -412,7 +437,6 @@ ddq_add_8: /* main body of aes ctr load */ .macro do_aes_ctrmain key_len - cmp $16, num_bytes jb .Ldo_return2\key_len diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index e7e9682a33e9..f556c4843aa1 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -80,9 +80,11 @@ static inline unsigned int __getcpu(void) /* * Load per CPU data from GDT. LSL is faster than RDTSCP and - * works on all CPUs. + * works on all CPUs. This is volatile so that it orders + * correctly wrt barrier() and to keep gcc from cleverly + * hoisting it out of the calling function. */ - asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); return p; } diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4433a4be8171..d1626364a28a 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -750,13 +750,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) +int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu) { return _acpi_map_lsapic(handle, physid, pcpu); } -EXPORT_SYMBOL(acpi_map_lsapic); +EXPORT_SYMBOL(acpi_map_cpu); -int acpi_unmap_lsapic(int cpu) +int acpi_unmap_cpu(int cpu) { #ifdef CONFIG_ACPI_NUMA set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); @@ -768,8 +768,7 @@ int acpi_unmap_lsapic(int cpu) return (0); } - -EXPORT_SYMBOL(acpi_unmap_lsapic); +EXPORT_SYMBOL(acpi_unmap_cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index e27b49d7c922..80091ae54c2b 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -66,3 +66,4 @@ targets += capflags.c $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE $(call if_changed,mkcapflags) endif +clean-files += capflags.c diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index e2b22df964cd..36d99a337b49 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -28,7 +28,7 @@ function dump_array() # If the /* comment */ starts with a quote string, grab that. VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')" [ -z "$VALUE" ] && VALUE="\"$NAME\"" - [ "$VALUE" == '""' ] && continue + [ "$VALUE" = '""' ] && continue # Name is uppercase, VALUE is all lowercase VALUE="$(echo "$VALUE" | tr A-Z a-z)" diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 18eb78bbdd10..863d9b02563e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -17,7 +17,7 @@ #define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) #define UNCORE_PCI_DEV_IDX(data) (data & 0xff) #define UNCORE_EXTRA_PCI_DEV 0xff -#define UNCORE_EXTRA_PCI_DEV_MAX 2 +#define UNCORE_EXTRA_PCI_DEV_MAX 3 /* support up to 8 sockets */ #define UNCORE_SOCKET_MAX 8 diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index 745b158e9a65..21af6149edf2 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -891,6 +891,7 @@ void snbep_uncore_cpu_init(void) enum { SNBEP_PCI_QPI_PORT0_FILTER, SNBEP_PCI_QPI_PORT1_FILTER, + HSWEP_PCI_PCU_3, }; static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) @@ -2026,6 +2027,17 @@ void hswep_uncore_cpu_init(void) { if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + + /* Detect 6-8 core systems with only two SBOXes */ + if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) { + u32 capid4; + + pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3], + 0x94, &capid4); + if (((capid4 >> 6) & 0x3) == 0) + hswep_uncore_sbox.num_boxes = 2; + } + uncore_msr_uncores = hswep_msr_uncores; } @@ -2287,6 +2299,11 @@ static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = { .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, SNBEP_PCI_QPI_PORT1_FILTER), }, + { /* PCU.3 (for Capability registers) */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + HSWEP_PCI_PCU_3), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index e309cc5c276e..781861cc5ee8 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task) { return PERF_SAMPLE_REGS_ABI_32; } + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} #else /* CONFIG_X86_64 */ #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ (1ULL << PERF_REG_X86_ES) | \ @@ -102,4 +110,86 @@ u64 perf_reg_abi(struct task_struct *task) else return PERF_SAMPLE_REGS_ABI_64; } + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + struct pt_regs *user_regs = task_pt_regs(current); + + /* + * If we're in an NMI that interrupted task_pt_regs setup, then + * we can't sample user regs at all. This check isn't really + * sufficient, though, as we could be in an NMI inside an interrupt + * that happened during task_pt_regs setup. + */ + if (regs->sp > (unsigned long)&user_regs->r11 && + regs->sp <= (unsigned long)(user_regs + 1)) { + regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; + regs_user->regs = NULL; + return; + } + + /* + * RIP, flags, and the argument registers are usually saved. + * orig_ax is probably okay, too. + */ + regs_user_copy->ip = user_regs->ip; + regs_user_copy->cx = user_regs->cx; + regs_user_copy->dx = user_regs->dx; + regs_user_copy->si = user_regs->si; + regs_user_copy->di = user_regs->di; + regs_user_copy->r8 = user_regs->r8; + regs_user_copy->r9 = user_regs->r9; + regs_user_copy->r10 = user_regs->r10; + regs_user_copy->r11 = user_regs->r11; + regs_user_copy->orig_ax = user_regs->orig_ax; + regs_user_copy->flags = user_regs->flags; + + /* + * Don't even try to report the "rest" regs. + */ + regs_user_copy->bx = -1; + regs_user_copy->bp = -1; + regs_user_copy->r12 = -1; + regs_user_copy->r13 = -1; + regs_user_copy->r14 = -1; + regs_user_copy->r15 = -1; + + /* + * For this to be at all useful, we need a reasonable guess for + * sp and the ABI. Be careful: we're in NMI context, and we're + * considering current to be the current task, so we should + * be careful not to look at any other percpu variables that might + * change during context switches. + */ + if (IS_ENABLED(CONFIG_IA32_EMULATION) && + task_thread_info(current)->status & TS_COMPAT) { + /* Easy case: we're in a compat syscall. */ + regs_user->abi = PERF_SAMPLE_REGS_ABI_32; + regs_user_copy->sp = user_regs->sp; + regs_user_copy->cs = user_regs->cs; + regs_user_copy->ss = user_regs->ss; + } else if (user_regs->orig_ax != -1) { + /* + * We're probably in a 64-bit syscall. + * Warning: this code is severely racy. At least it's better + * than just blindly copying user_regs. + */ + regs_user->abi = PERF_SAMPLE_REGS_ABI_64; + regs_user_copy->sp = this_cpu_read(old_rsp); + regs_user_copy->cs = __USER_CS; + regs_user_copy->ss = __USER_DS; + regs_user_copy->cx = -1; /* usually contains garbage */ + } else { + /* We're probably in an interrupt or exception. */ + regs_user->abi = user_64bit_mode(user_regs) ? + PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32; + regs_user_copy->sp = user_regs->sp; + regs_user_copy->cs = user_regs->cs; + regs_user_copy->ss = user_regs->ss; + } + + regs_user->regs = regs_user_copy; +} #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 10fbed126b11..f83fc6c5e0ba 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4448,7 +4448,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) * zap all shadow pages. */ if (unlikely(kvm_current_mmio_generation(kvm) == 0)) { - printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n"); + printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index feb852b04598..d4c58d884838 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5840,53 +5840,10 @@ static __init int hardware_setup(void) memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); - vmx_disable_intercept_for_msr(MSR_GS_BASE, false); - vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true); - - memcpy(vmx_msr_bitmap_legacy_x2apic, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic, - vmx_msr_bitmap_longmode, PAGE_SIZE); - - if (enable_apicv) { - for (msr = 0x800; msr <= 0x8ff; msr++) - vmx_disable_intercept_msr_read_x2apic(msr); - - /* According SDM, in x2apic mode, the whole id reg is used. - * But in KVM, it only use the highest eight bits. Need to - * intercept it */ - vmx_enable_intercept_msr_read_x2apic(0x802); - /* TMCCT */ - vmx_enable_intercept_msr_read_x2apic(0x839); - /* TPR */ - vmx_disable_intercept_msr_write_x2apic(0x808); - /* EOI */ - vmx_disable_intercept_msr_write_x2apic(0x80b); - /* SELF-IPI */ - vmx_disable_intercept_msr_write_x2apic(0x83f); - } - - if (enable_ept) { - kvm_mmu_set_mask_ptes(0ull, - (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, - (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, - 0ull, VMX_EPT_EXECUTABLE_MASK); - ept_set_mmio_spte_mask(); - kvm_enable_tdp(); - } else - kvm_disable_tdp(); - - update_ple_window_actual_max(); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; goto out7; - } + } if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); @@ -5945,6 +5902,49 @@ static __init int hardware_setup(void) if (nested) nested_vmx_setup_ctls_msrs(); + vmx_disable_intercept_for_msr(MSR_FS_BASE, false); + vmx_disable_intercept_for_msr(MSR_GS_BASE, false); + vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); + vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); + vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); + vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); + vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true); + + memcpy(vmx_msr_bitmap_legacy_x2apic, + vmx_msr_bitmap_legacy, PAGE_SIZE); + memcpy(vmx_msr_bitmap_longmode_x2apic, + vmx_msr_bitmap_longmode, PAGE_SIZE); + + if (enable_apicv) { + for (msr = 0x800; msr <= 0x8ff; msr++) + vmx_disable_intercept_msr_read_x2apic(msr); + + /* According SDM, in x2apic mode, the whole id reg is used. + * But in KVM, it only use the highest eight bits. Need to + * intercept it */ + vmx_enable_intercept_msr_read_x2apic(0x802); + /* TMCCT */ + vmx_enable_intercept_msr_read_x2apic(0x839); + /* TPR */ + vmx_disable_intercept_msr_write_x2apic(0x808); + /* EOI */ + vmx_disable_intercept_msr_write_x2apic(0x80b); + /* SELF-IPI */ + vmx_disable_intercept_msr_write_x2apic(0x83f); + } + + if (enable_ept) { + kvm_mmu_set_mask_ptes(0ull, + (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, + (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, + 0ull, VMX_EPT_EXECUTABLE_MASK); + ept_set_mmio_spte_mask(); + kvm_enable_tdp(); + } else + kvm_disable_tdp(); + + update_ple_window_actual_max(); + return alloc_kvm_area(); out7: diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 2480978b31cc..1313ae6b478b 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -28,7 +28,7 @@ /* Verify next sizeof(t) bytes can be on the same instruction */ #define validate_next(t, insn, n) \ - ((insn)->next_byte + sizeof(t) + n < (insn)->end_kaddr) + ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; }) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index a97ee0801475..08a7d313538a 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -438,20 +438,20 @@ static unsigned long __init init_range_memory_mapping( static unsigned long __init get_new_step_size(unsigned long step_size) { /* - * Explain why we shift by 5 and why we don't have to worry about - * 'step_size << 5' overflowing: - * - * initial mapped size is PMD_SIZE (2M). + * Initial mapped size is PMD_SIZE (2M). * We can not set step_size to be PUD_SIZE (1G) yet. * In worse case, when we cross the 1G boundary, and * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k) - * to map 1G range with PTE. Use 5 as shift for now. + * to map 1G range with PTE. Hence we use one less than the + * difference of page table level shifts. * - * Don't need to worry about overflow, on 32bit, when step_size - * is 0, round_down() returns 0 for start, and that turns it - * into 0x100000000ULL. + * Don't need to worry about overflow in the top-down case, on 32bit, + * when step_size is 0, round_down() returns 0 for start, and that + * turns it into 0x100000000ULL. + * In the bottom-up case, round_up(x, 0) returns 0 though too, which + * needs to be taken into consideration by the code below. */ - return step_size << 5; + return step_size << (PMD_SHIFT - PAGE_SHIFT - 1); } /** @@ -471,7 +471,6 @@ static void __init memory_map_top_down(unsigned long map_start, unsigned long step_size; unsigned long addr; unsigned long mapped_ram_size = 0; - unsigned long new_mapped_ram_size; /* xen has big range in reserved near end of ram, skip it at first.*/ addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE); @@ -496,14 +495,12 @@ static void __init memory_map_top_down(unsigned long map_start, start = map_start; } else start = map_start; - new_mapped_ram_size = init_range_memory_mapping(start, + mapped_ram_size += init_range_memory_mapping(start, last_start); last_start = start; min_pfn_mapped = last_start >> PAGE_SHIFT; - /* only increase step_size after big range get mapped */ - if (new_mapped_ram_size > mapped_ram_size) + if (mapped_ram_size >= step_size) step_size = get_new_step_size(step_size); - mapped_ram_size += new_mapped_ram_size; } if (real_end < map_end) @@ -524,7 +521,7 @@ static void __init memory_map_top_down(unsigned long map_start, static void __init memory_map_bottom_up(unsigned long map_start, unsigned long map_end) { - unsigned long next, new_mapped_ram_size, start; + unsigned long next, start; unsigned long mapped_ram_size = 0; /* step_size need to be small so pgt_buf from BRK could cover it */ unsigned long step_size = PMD_SIZE; @@ -539,19 +536,19 @@ static void __init memory_map_bottom_up(unsigned long map_start, * for page table. */ while (start < map_end) { - if (map_end - start > step_size) { + if (step_size && map_end - start > step_size) { next = round_up(start + 1, step_size); if (next > map_end) next = map_end; - } else + } else { next = map_end; + } - new_mapped_ram_size = init_range_memory_mapping(start, next); + mapped_ram_size += init_range_memory_mapping(start, next); start = next; - if (new_mapped_ram_size > mapped_ram_size) + if (mapped_ram_size >= step_size) step_size = get_new_step_size(step_size); - mapped_ram_size += new_mapped_ram_size; } } diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 531d4269e2e3..bd16d6c370ec 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -34,7 +34,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void); extern asmlinkage void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index 20c3649d0691..5cdfa9db2217 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -47,7 +47,7 @@ typedef void (*sys_call_ptr_t)(void); extern void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 009495b9ab4b..1c9f750c3859 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -41,12 +41,17 @@ void __init init_vdso_image(const struct vdso_image *image) struct linux_binprm; -/* Put the vdso above the (randomized) stack with another randomized offset. - This way there is no hole in the middle of address space. - To save memory make sure it is still in the same PTE as the stack top. - This doesn't give that many random bits. - - Only used for the 64-bit and x32 vdsos. */ +/* + * Put the vdso above the (randomized) stack with another randomized + * offset. This way there is no hole in the middle of address space. + * To save memory make sure it is still in the same PTE as the stack + * top. This doesn't give that many random bits. + * + * Note that this algorithm is imperfect: the distribution of the vdso + * start address within a PMD is biased toward the end. + * + * Only used for the 64-bit and x32 vdsos. + */ static unsigned long vdso_addr(unsigned long start, unsigned len) { #ifdef CONFIG_X86_32 @@ -54,22 +59,30 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) #else unsigned long addr, end; unsigned offset; - end = (start + PMD_SIZE - 1) & PMD_MASK; + + /* + * Round up the start address. It can start out unaligned as a result + * of stack start randomization. + */ + start = PAGE_ALIGN(start); + + /* Round the lowest possible end address up to a PMD boundary. */ + end = (start + len + PMD_SIZE - 1) & PMD_MASK; if (end >= TASK_SIZE_MAX) end = TASK_SIZE_MAX; end -= len; - /* This loses some more bits than a modulo, but is cheaper */ - offset = get_random_int() & (PTRS_PER_PTE - 1); - addr = start + (offset << PAGE_SHIFT); - if (addr >= end) - addr = end; + + if (end > start) { + offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + addr = start + (offset << PAGE_SHIFT); + } else { + addr = start; + } /* - * page-align it here so that get_unmapped_area doesn't - * align it wrongfully again to the next page. addr can come in 4K - * unaligned here as a result of stack start randomization. + * Forcibly align the final address in case we have a hardware + * issue that requires alignment for performance reasons. */ - addr = PAGE_ALIGN(addr); addr = align_vdso_addr(addr); return addr; |
