diff options
Diffstat (limited to 'arch/x86')
38 files changed, 1092 insertions, 175 deletions
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index e56dbc67e837..97c57b5f8d57 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -163,7 +163,8 @@ __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom) if (status != EFI_SUCCESS) goto free_struct; - memcpy(rom->romdata, pci->romimage, pci->romsize); + memcpy(rom->romdata, (void *)(unsigned long)pci->romimage, + pci->romsize); return status; free_struct: @@ -269,7 +270,8 @@ __setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom) if (status != EFI_SUCCESS) goto free_struct; - memcpy(rom->romdata, pci->romimage, pci->romsize); + memcpy(rom->romdata, (void *)(unsigned long)pci->romimage, + pci->romsize); return status; free_struct: diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 011a47b4587c..717c9219d00e 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1162,16 +1162,13 @@ int x86_perf_event_set_period(struct perf_event *event) per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; - if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) || - local64_read(&hwc->prev_count) != (u64)-left) { - /* - * The hw event starts counting from this event offset, - * mark it to be able to extra future deltas: - */ - local64_set(&hwc->prev_count, (u64)-left); + /* + * The hw event starts counting from this event offset, + * mark it to be able to extra future deltas: + */ + local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); - } + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* * Due to erratum on certan cpu we need diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 9b18a227fff7..6965ee8c4b8a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2201,16 +2201,23 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) int bit, loops; u64 status; int handled; + int pmu_enabled; cpuc = this_cpu_ptr(&cpu_hw_events); /* + * Save the PMU state. + * It needs to be restored when leaving the handler. + */ + pmu_enabled = cpuc->enabled; + /* * No known reason to not always do late ACK, * but just in case do it opt-in. */ if (!x86_pmu.late_ack) apic_write(APIC_LVTPC, APIC_DM_NMI); intel_bts_disable_local(); + cpuc->enabled = 0; __intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); handled += intel_bts_interrupt(); @@ -2320,7 +2327,8 @@ again: done: /* Only restore PMU state when it's active. See x86_pmu_disable(). */ - if (cpuc->enabled) + cpuc->enabled = pmu_enabled; + if (pmu_enabled) __intel_pmu_enable_all(0, true); intel_bts_enable_local(); @@ -3188,7 +3196,7 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, * Therefore the effective (average) period matches the requested period, * despite coarser hardware granularity. */ -static unsigned bdw_limit_period(struct perf_event *event, unsigned left) +static u64 bdw_limit_period(struct perf_event *event, u64 left) { if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0xc0, .umask=0x01)) { diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8156e47da7ba..10b39d44981c 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1150,6 +1150,7 @@ static void setup_pebs_sample_data(struct perf_event *event, if (pebs == NULL) return; + regs->flags &= ~PERF_EFLAGS_EXACT; sample_type = event->attr.sample_type; dsrc = sample_type & PERF_SAMPLE_DATA_SRC; @@ -1194,7 +1195,6 @@ static void setup_pebs_sample_data(struct perf_event *event, */ *regs = *iregs; regs->flags = pebs->flags; - set_linear_ip(regs, pebs->ip); if (sample_type & PERF_SAMPLE_REGS_INTR) { regs->ax = pebs->ax; @@ -1230,13 +1230,22 @@ static void setup_pebs_sample_data(struct perf_event *event, #endif } - if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { - regs->ip = pebs->real_ip; - regs->flags |= PERF_EFLAGS_EXACT; - } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs)) - regs->flags |= PERF_EFLAGS_EXACT; - else - regs->flags &= ~PERF_EFLAGS_EXACT; + if (event->attr.precise_ip > 1) { + /* Haswell and later have the eventing IP, so use it: */ + if (x86_pmu.intel_cap.pebs_format >= 2) { + set_linear_ip(regs, pebs->real_ip); + regs->flags |= PERF_EFLAGS_EXACT; + } else { + /* Otherwise use PEBS off-by-1 IP: */ + set_linear_ip(regs, pebs->ip); + + /* ... and try to fix it up using the LBR entries: */ + if (intel_pmu_pebs_fixup_ip(regs)) + regs->flags |= PERF_EFLAGS_EXACT; + } + } else + set_linear_ip(regs, pebs->ip); + if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) && x86_pmu.intel_cap.pebs_format >= 1) @@ -1303,17 +1312,84 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) return NULL; } +/* + * Special variant of intel_pmu_save_and_restart() for auto-reload. + */ +static int +intel_pmu_save_and_restart_reload(struct perf_event *event, int count) +{ + struct hw_perf_event *hwc = &event->hw; + int shift = 64 - x86_pmu.cntval_bits; + u64 period = hwc->sample_period; + u64 prev_raw_count, new_raw_count; + s64 new, old; + + WARN_ON(!period); + + /* + * drain_pebs() only happens when the PMU is disabled. + */ + WARN_ON(this_cpu_read(cpu_hw_events.enabled)); + + prev_raw_count = local64_read(&hwc->prev_count); + rdpmcl(hwc->event_base_rdpmc, new_raw_count); + local64_set(&hwc->prev_count, new_raw_count); + + /* + * Since the counter increments a negative counter value and + * overflows on the sign switch, giving the interval: + * + * [-period, 0] + * + * the difference between two consequtive reads is: + * + * A) value2 - value1; + * when no overflows have happened in between, + * + * B) (0 - value1) + (value2 - (-period)); + * when one overflow happened in between, + * + * C) (0 - value1) + (n - 1) * (period) + (value2 - (-period)); + * when @n overflows happened in between. + * + * Here A) is the obvious difference, B) is the extension to the + * discrete interval, where the first term is to the top of the + * interval and the second term is from the bottom of the next + * interval and C) the extension to multiple intervals, where the + * middle term is the whole intervals covered. + * + * An equivalent of C, by reduction, is: + * + * value2 - value1 + n * period + */ + new = ((s64)(new_raw_count << shift) >> shift); + old = ((s64)(prev_raw_count << shift) >> shift); + local64_add(new - old + count * period, &event->count); + + perf_event_update_userpage(event); + + return 0; +} + static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *base, void *top, int bit, int count) { + struct hw_perf_event *hwc = &event->hw; struct perf_sample_data data; struct pt_regs regs; void *at = get_next_pebs_record_by_bit(base, top, bit); - if (!intel_pmu_save_and_restart(event) && - !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)) + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + /* + * Now, auto-reload is only enabled in fixed period mode. + * The reload value is always hwc->sample_period. + * May need to change it, if auto-reload is enabled in + * freq mode later. + */ + intel_pmu_save_and_restart_reload(event, count); + } else if (!intel_pmu_save_and_restart(event)) return; while (count > 1) { @@ -1365,8 +1441,11 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) return; n = top - at; - if (n <= 0) + if (n <= 0) { + if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) + intel_pmu_save_and_restart_reload(event, 0); return; + } __intel_pmu_pebs_event(event, iregs, at, top, 0, n); } @@ -1389,8 +1468,22 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) ds->pebs_index = ds->pebs_buffer_base; - if (unlikely(base >= top)) + 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, + x86_pmu.max_pebs_events) { + event = cpuc->events[bit]; + if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) + intel_pmu_save_and_restart_reload(event, 0); + } return; + } for (at = base; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 8e4ea143ed96..dc4728eccfd8 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -556,7 +556,7 @@ struct x86_pmu { struct x86_pmu_quirk *quirks; int perfctr_second_write; bool late_ack; - unsigned (*limit_period)(struct perf_event *event, unsigned l); + u64 (*limit_period)(struct perf_event *event, u64 l); /* * sysfs attrs diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index cf5961ca8677..4cd6a3b71824 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -218,13 +218,11 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ output, input...) \ -{ \ asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ "call %P[new2]", feature2) \ : output, ASM_CALL_CONSTRAINT \ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ - [new2] "i" (newfunc2), ## input); \ -} + [new2] "i" (newfunc2), ## input) /* * use this macro(s) if you need more than one output parameter diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 23a65439c37c..403e97d5e243 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -198,7 +198,6 @@ #define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ #define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ - #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ @@ -207,11 +206,19 @@ #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ +#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ +#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ +#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ +#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */ +#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -272,9 +279,10 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ -#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ -#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -331,6 +339,7 @@ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ /* * BUG word(s) @@ -360,5 +369,6 @@ #define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ #define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ +#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4f8b80199672..174b9c41efce 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -908,7 +908,7 @@ struct kvm_x86_ops { int (*hardware_setup)(void); /* __init */ void (*hardware_unsetup)(void); /* __exit */ bool (*cpu_has_accelerated_tpr)(void); - bool (*cpu_has_high_real_mode_segbase)(void); + bool (*has_emulated_msr)(int index); void (*cpuid_update)(struct kvm_vcpu *vcpu); int (*vm_init)(struct kvm *kvm); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 1de72ce514cd..ed97ef3b48a7 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -192,7 +192,7 @@ static inline int init_new_context(struct task_struct *tsk, #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { - /* pkey 0 is the default and always allocated */ + /* pkey 0 is the default and allocated implicitly */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index eb83ff1bae8f..504b21692d32 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -42,6 +42,8 @@ #define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ #define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ #define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ +#define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ +#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ @@ -68,6 +70,11 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ +#define ARCH_CAP_SSB_NO (1 << 4) /* + * Not susceptible to Speculative Store Bypass + * attack, so no Speculative Store Bypass + * control required. + */ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e @@ -337,6 +344,8 @@ #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f928ad9b143f..8b38df98548e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -217,6 +217,14 @@ enum spectre_v2_mitigation { SPECTRE_V2_IBRS, }; +/* The Speculative Store Bypass disable variants */ +enum ssb_mitigation { + SPEC_STORE_BYPASS_NONE, + SPEC_STORE_BYPASS_DISABLE, + SPEC_STORE_BYPASS_PRCTL, + SPEC_STORE_BYPASS_SECCOMP, +}; + extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; @@ -241,22 +249,27 @@ static inline void vmexit_fill_RSB(void) #endif } -#define alternative_msr_write(_msr, _val, _feature) \ - asm volatile(ALTERNATIVE("", \ - "movl %[msr], %%ecx\n\t" \ - "movl %[val], %%eax\n\t" \ - "movl $0, %%edx\n\t" \ - "wrmsr", \ - _feature) \ - : : [msr] "i" (_msr), [val] "i" (_val) \ - : "eax", "ecx", "edx", "memory") +static __always_inline +void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) +{ + asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) + : : "c" (msr), + "a" ((u32)val), + "d" ((u32)(val >> 32)), + [feature] "i" (feature) + : "memory"); +} static inline void indirect_branch_prediction_barrier(void) { - alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, - X86_FEATURE_USE_IBPB); + u64 val = PRED_CMD_IBPB; + + alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); } +/* The Intel SPEC CTRL MSR base value cache */ +extern u64 x86_spec_ctrl_base; + /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. @@ -265,14 +278,18 @@ static inline void indirect_branch_prediction_barrier(void) */ #define firmware_restrict_branch_speculation_start() \ do { \ + u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS; \ + \ preempt_disable(); \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ X86_FEATURE_USE_IBRS_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \ + u64 val = x86_spec_ctrl_base; \ + \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index a0ba1ffda0df..851c04b7a092 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H +#define ARCH_DEFAULT_PKEY 0 + #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, @@ -15,7 +17,7 @@ extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { if (!boot_cpu_has(X86_FEATURE_OSPKE)) - return 0; + return ARCH_DEFAULT_PKEY; return __execute_only_pkey(mm); } @@ -49,13 +51,21 @@ bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { /* * "Allocated" pkeys are those that have been returned - * from pkey_alloc(). pkey 0 is special, and never - * returned from pkey_alloc(). + * from pkey_alloc() or pkey 0 which is allocated + * implicitly when the mm is created. */ - if (pkey <= 0) + if (pkey < 0) return false; if (pkey >= arch_max_pkey()) return false; + /* + * The exec-only pkey is set in the allocation map, but + * is not available to any of the user interfaces like + * mprotect_pkey(). + */ + if (pkey == mm->context.execute_only_pkey) + return false; + return mm_pkey_allocation_map(mm) & (1U << pkey); } diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h new file mode 100644 index 000000000000..ae7c2c5cd7f0 --- /dev/null +++ b/arch/x86/include/asm/spec-ctrl.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SPECCTRL_H_ +#define _ASM_X86_SPECCTRL_H_ + +#include <linux/thread_info.h> +#include <asm/nospec-branch.h> + +/* + * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR + * the guest has, while on VMEXIT we restore the host view. This + * would be easier if SPEC_CTRL were architecturally maskable or + * shadowable for guests but this is not (currently) the case. + * Takes the guest view of SPEC_CTRL MSR as a parameter and also + * the guest's version of VIRT_SPEC_CTRL, if emulated. + */ +extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest); + +/** + * x86_spec_ctrl_set_guest - Set speculation control registers for the guest + * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL + * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL + * (may get translated to MSR_AMD64_LS_CFG bits) + * + * Avoids writing to the MSR if the content/bits are the same + */ +static inline +void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +{ + x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true); +} + +/** + * x86_spec_ctrl_restore_host - Restore host speculation control registers + * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL + * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL + * (may get translated to MSR_AMD64_LS_CFG bits) + * + * Avoids writing to the MSR if the content/bits are the same + */ +static inline +void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +{ + x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false); +} + +/* AMD specific Speculative Store Bypass MSR data */ +extern u64 x86_amd_ls_cfg_base; +extern u64 x86_amd_ls_cfg_ssbd_mask; + +static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn) +{ + BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); + return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); +} + +static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl) +{ + BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); + return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); +} + +static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn) +{ + return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL; +} + +#ifdef CONFIG_SMP +extern void speculative_store_bypass_ht_init(void); +#else +static inline void speculative_store_bypass_ht_init(void) { } +#endif + +extern void speculative_store_bypass_update(unsigned long tif); + +static inline void speculative_store_bypass_update_current(void) +{ + speculative_store_bypass_update(current_thread_info()->flags); +} + +#endif diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 0242d91734ee..b1c9129f64fc 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -88,6 +88,7 @@ struct thread_info { #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ +#define TIF_SSBD 5 /* Reduced data speculation */ #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ @@ -115,6 +116,7 @@ struct thread_info { #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_SSBD (1 << TIF_SSBD) #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) @@ -155,7 +157,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP) + (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_SSBD) #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 704f31315dde..875ca99b82ee 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -131,7 +131,12 @@ static inline unsigned long build_cr3(pgd_t *pgd, u16 asid) static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) { VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); - VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID)); + /* + * Use boot_cpu_has() instead of this_cpu_has() as this function + * might be called during early boot. This should work even after + * boot because all CPU's the have same capabilities: + */ + VM_WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_PCID)); return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 5942aa5f569b..ebdcc368a2d3 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1481,7 +1481,7 @@ void setup_local_APIC(void) * TODO: set up through-local-APIC from through-I/O-APIC? --macro */ value = apic_read(APIC_LVT0) & APIC_LVT_MASKED; - if (!cpu && (pic_mode || !value)) { + if (!cpu && (pic_mode || !value || skip_ioapic_setup)) { value = APIC_DM_EXTINT; apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n", cpu); } else { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e7d5a7883632..90574f731c05 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -10,6 +10,7 @@ #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> +#include <asm/spec-ctrl.h> #include <asm/smp.h> #include <asm/pci-direct.h> #include <asm/delay.h> @@ -554,6 +555,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) rdmsrl(MSR_FAM10H_NODE_ID, value); nodes_per_socket = ((value >> 3) & 7) + 1; } + + if (c->x86 >= 0x15 && c->x86 <= 0x17) { + unsigned int bit; + + switch (c->x86) { + case 0x15: bit = 54; break; + case 0x16: bit = 33; break; + case 0x17: bit = 10; break; + default: return; + } + /* + * Try to cache the base value so further operations can + * avoid RMW. If that faults, do not enable SSBD. + */ + if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) { + setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD); + setup_force_cpu_cap(X86_FEATURE_SSBD); + x86_amd_ls_cfg_ssbd_mask = 1ULL << bit; + } + } } static void early_init_amd(struct cpuinfo_x86 *c) @@ -765,6 +786,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c) static void init_amd_zn(struct cpuinfo_x86 *c) { + set_cpu_cap(c, X86_FEATURE_ZEN); /* * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects * all up to and including B1. diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bfca937bdcc3..7416fc206b4a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -12,8 +12,10 @@ #include <linux/utsname.h> #include <linux/cpu.h> #include <linux/module.h> +#include <linux/nospec.h> +#include <linux/prctl.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> @@ -27,6 +29,27 @@ #include <asm/intel-family.h> static void __init spectre_v2_select_mitigation(void); +static void __init ssb_select_mitigation(void); + +/* + * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any + * writes to SPEC_CTRL contain whatever reserved bits have been set. + */ +u64 __ro_after_init x86_spec_ctrl_base; +EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); + +/* + * The vendor and possibly platform specific bits which can be modified in + * x86_spec_ctrl_base. + */ +static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; + +/* + * AMD specific MSR info for Speculative Store Bypass control. + * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu(). + */ +u64 __ro_after_init x86_amd_ls_cfg_base; +u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask; void __init check_bugs(void) { @@ -37,9 +60,27 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); } + /* + * Read the SPEC_CTRL MSR to account for reserved bits which may + * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD + * init code as it is not enumerated and depends on the family. + */ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + /* Allow STIBP in MSR_SPEC_CTRL if supported */ + if (boot_cpu_has(X86_FEATURE_STIBP)) + x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; + /* Select the proper spectre mitigation before patching alternatives */ spectre_v2_select_mitigation(); + /* + * Select proper mitigation for any exposure to the Speculative Store + * Bypass vulnerability. + */ + ssb_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -93,7 +134,76 @@ static const char *spectre_v2_strings[] = { #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt -static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = + SPECTRE_V2_NONE; + +void +x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) +{ + u64 msrval, guestval, hostval = x86_spec_ctrl_base; + struct thread_info *ti = current_thread_info(); + + /* Is MSR_SPEC_CTRL implemented ? */ + if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { + /* + * Restrict guest_spec_ctrl to supported values. Clear the + * modifiable bits in the host base value and or the + * modifiable bits from the guest value. + */ + guestval = hostval & ~x86_spec_ctrl_mask; + guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; + + /* SSBD controlled in MSR_SPEC_CTRL */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + hostval |= ssbd_tif_to_spec_ctrl(ti->flags); + + if (hostval != guestval) { + msrval = setguest ? guestval : hostval; + wrmsrl(MSR_IA32_SPEC_CTRL, msrval); + } + } + + /* + * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update + * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported. + */ + if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) && + !static_cpu_has(X86_FEATURE_VIRT_SSBD)) + return; + + /* + * If the host has SSBD mitigation enabled, force it in the host's + * virtual MSR value. If its not permanently enabled, evaluate + * current's TIF_SSBD thread flag. + */ + if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE)) + hostval = SPEC_CTRL_SSBD; + else + hostval = ssbd_tif_to_spec_ctrl(ti->flags); + + /* Sanitize the guest value */ + guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD; + + if (hostval != guestval) { + unsigned long tif; + + tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) : + ssbd_spec_ctrl_to_tif(hostval); + + speculative_store_bypass_update(tif); + } +} +EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl); + +static void x86_amd_ssb_disable(void) +{ + u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask; + + if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) + wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD); + else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + wrmsrl(MSR_AMD64_LS_CFG, msrval); +} #ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -312,32 +422,289 @@ retpoline_auto: } #undef pr_fmt +#define pr_fmt(fmt) "Speculative Store Bypass: " fmt + +static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE; + +/* The kernel command line selection */ +enum ssb_mitigation_cmd { + SPEC_STORE_BYPASS_CMD_NONE, + SPEC_STORE_BYPASS_CMD_AUTO, + SPEC_STORE_BYPASS_CMD_ON, + SPEC_STORE_BYPASS_CMD_PRCTL, + SPEC_STORE_BYPASS_CMD_SECCOMP, +}; + +static const char *ssb_strings[] = { + [SPEC_STORE_BYPASS_NONE] = "Vulnerable", + [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled", + [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl", + [SPEC_STORE_BYPASS_SECCOMP] = "Mitigation: Speculative Store Bypass disabled via prctl and seccomp", +}; + +static const struct { + const char *option; + enum ssb_mitigation_cmd cmd; +} ssb_mitigation_options[] = { + { "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 */ + { "prctl", SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */ + { "seccomp", SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */ +}; + +static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) +{ + enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO; + char arg[20]; + int ret, i; + + if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) { + return SPEC_STORE_BYPASS_CMD_NONE; + } else { + ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", + arg, sizeof(arg)); + if (ret < 0) + return SPEC_STORE_BYPASS_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) { + if (!match_option(arg, ret, ssb_mitigation_options[i].option)) + continue; + + cmd = ssb_mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(ssb_mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", arg); + return SPEC_STORE_BYPASS_CMD_AUTO; + } + } + + return cmd; +} + +static enum ssb_mitigation __init __ssb_select_mitigation(void) +{ + enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE; + enum ssb_mitigation_cmd cmd; + + if (!boot_cpu_has(X86_FEATURE_SSBD)) + return mode; + + cmd = ssb_parse_cmdline(); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) && + (cmd == SPEC_STORE_BYPASS_CMD_NONE || + cmd == SPEC_STORE_BYPASS_CMD_AUTO)) + return mode; + + switch (cmd) { + case SPEC_STORE_BYPASS_CMD_AUTO: + case SPEC_STORE_BYPASS_CMD_SECCOMP: + /* + * Choose prctl+seccomp as the default mode if seccomp is + * enabled. + */ + if (IS_ENABLED(CONFIG_SECCOMP)) + mode = SPEC_STORE_BYPASS_SECCOMP; + else + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_ON: + mode = SPEC_STORE_BYPASS_DISABLE; + break; + case SPEC_STORE_BYPASS_CMD_PRCTL: + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_NONE: + break; + } + + /* + * We have three CPU feature flags that are in play here: + * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. + * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass + * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation + */ + if (mode == SPEC_STORE_BYPASS_DISABLE) { + setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE); + /* + * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses + * a completely different MSR and bit dependent on family. + */ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + x86_spec_ctrl_base |= SPEC_CTRL_SSBD; + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + break; + case X86_VENDOR_AMD: + x86_amd_ssb_disable(); + break; + } + } + + return mode; +} + +static void ssb_select_mitigation(void) +{ + ssb_mode = __ssb_select_mitigation(); + + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + pr_info("%s\n", ssb_strings[ssb_mode]); +} + +#undef pr_fmt +#define pr_fmt(fmt) "Speculation prctl: " fmt + +static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + bool update; + + if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && + ssb_mode != SPEC_STORE_BYPASS_SECCOMP) + return -ENXIO; + + switch (ctrl) { + case PR_SPEC_ENABLE: + /* If speculation is force disabled, enable is not allowed */ + if (task_spec_ssb_force_disable(task)) + return -EPERM; + task_clear_spec_ssb_disable(task); + update = test_and_clear_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_DISABLE: + task_set_spec_ssb_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_FORCE_DISABLE: + task_set_spec_ssb_disable(task); + task_set_spec_ssb_force_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + default: + return -ERANGE; + } + + /* + * If being set on non-current task, delay setting the CPU + * mitigation until it is next scheduled. + */ + if (task == current && update) + speculative_store_bypass_update_current(); + + return 0; +} + +int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, + unsigned long ctrl) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_set(task, ctrl); + default: + return -ENODEV; + } +} + +#ifdef CONFIG_SECCOMP +void arch_seccomp_spec_mitigate(struct task_struct *task) +{ + if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) + ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); +} +#endif + +static int ssb_prctl_get(struct task_struct *task) +{ + switch (ssb_mode) { + case SPEC_STORE_BYPASS_DISABLE: + return PR_SPEC_DISABLE; + case SPEC_STORE_BYPASS_SECCOMP: + case SPEC_STORE_BYPASS_PRCTL: + if (task_spec_ssb_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + default: + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + return PR_SPEC_ENABLE; + return PR_SPEC_NOT_AFFECTED; + } +} + +int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_get(task); + default: + return -ENODEV; + } +} + +void x86_spec_ctrl_setup_ap(void) +{ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) + x86_amd_ssb_disable(); +} #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) + +static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, + char *buf, unsigned int bug) { - if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + if (!boot_cpu_has_bug(bug)) return sprintf(buf, "Not affected\n"); - if (boot_cpu_has(X86_FEATURE_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + + switch (bug) { + case X86_BUG_CPU_MELTDOWN: + if (boot_cpu_has(X86_FEATURE_PTI)) + return sprintf(buf, "Mitigation: PTI\n"); + + break; + + case X86_BUG_SPECTRE_V1: + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + + case X86_BUG_SPECTRE_V2: + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + spectre_v2_module_string()); + + case X86_BUG_SPEC_STORE_BYPASS: + return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + + default: + break; + } + return sprintf(buf, "Vulnerable\n"); } +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN); +} + ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { - if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) - return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1); } ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { - if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - return sprintf(buf, "Not affected\n"); + return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2); +} - return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - spectre_v2_module_string()); +ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS); } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cf6380200dc2..48e98964ecad 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -733,17 +733,32 @@ static void init_speculation_control(struct cpuinfo_x86 *c) * and they also have a different bit for STIBP support. Also, * a hypervisor might have set the individual AMD bits even on * Intel CPUs, for finer-grained selection of what's available. - * - * We use the AMD bits in 0x8000_0008 EBX as the generic hardware - * features, which are visible in /proc/cpuinfo and used by the - * kernel. So set those accordingly from the Intel bits. */ if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { set_cpu_cap(c, X86_FEATURE_IBRS); set_cpu_cap(c, X86_FEATURE_IBPB); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) set_cpu_cap(c, X86_FEATURE_STIBP); + + if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) || + cpu_has(c, X86_FEATURE_VIRT_SSBD)) + set_cpu_cap(c, X86_FEATURE_SSBD); + + if (cpu_has(c, X86_FEATURE_AMD_IBRS)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } + + if (cpu_has(c, X86_FEATURE_AMD_IBPB)) + set_cpu_cap(c, X86_FEATURE_IBPB); + + if (cpu_has(c, X86_FEATURE_AMD_STIBP)) { + set_cpu_cap(c, X86_FEATURE_STIBP); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } } void get_cpu_cap(struct cpuinfo_x86 *c) @@ -894,21 +909,55 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { {} }; -static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, + { X86_VENDOR_CENTAUR, 5, }, + { X86_VENDOR_INTEL, 5, }, + { X86_VENDOR_NSC, 5, }, + { X86_VENDOR_AMD, 0x12, }, + { X86_VENDOR_AMD, 0x11, }, + { X86_VENDOR_AMD, 0x10, }, + { X86_VENDOR_AMD, 0xf, }, + { X86_VENDOR_ANY, 4, }, + {} +}; + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; - if (x86_match_cpu(cpu_no_meltdown)) - return false; - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + if (!x86_match_cpu(cpu_no_spec_store_bypass) && + !(ia32_cap & ARCH_CAP_SSB_NO)) + setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); + + if (x86_match_cpu(cpu_no_speculation)) + return; + + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + + if (x86_match_cpu(cpu_no_meltdown)) + return; + /* Rogue Data Cache Load? No! */ if (ia32_cap & ARCH_CAP_RDCL_NO) - return false; + return; - return true; + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); } /* @@ -958,12 +1007,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); - if (!x86_match_cpu(cpu_no_speculation)) { - if (cpu_vulnerable_to_meltdown(c)) - setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - } + cpu_set_bug_bits(c); fpu__init_system(c); @@ -1322,6 +1366,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #endif mtrr_ap_init(); validate_apic_and_package_id(c); + x86_spec_ctrl_setup_ap(); } static __init int setup_noclflush(char *arg) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index e806b11a99af..37672d299e35 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -50,4 +50,6 @@ extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +extern void x86_spec_ctrl_setup_ap(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c3af167d0a70..c895f38a7a5e 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -188,7 +188,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_IBPB); setup_clear_cpu_cap(X86_FEATURE_STIBP); setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL); setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SSBD); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD); } /* diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 7be35b600299..2dae1b3c42fc 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -1657,6 +1657,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, if (ret < 0) goto out_common_fail; closid = ret; + ret = 0; rdtgrp->closid = closid; list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 76e07698e6d1..7fa0855e4b9a 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -12,6 +12,7 @@ #include <linux/of_address.h> #include <linux/of_platform.h> #include <linux/of_irq.h> +#include <linux/libfdt.h> #include <linux/slab.h> #include <linux/pci.h> #include <linux/of_pci.h> @@ -200,19 +201,22 @@ static struct of_ioapic_type of_ioapic_type[] = static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { - struct of_phandle_args *irq_data = (void *)arg; + struct irq_fwspec *fwspec = (struct irq_fwspec *)arg; struct of_ioapic_type *it; struct irq_alloc_info tmp; + int type_index; - if (WARN_ON(irq_data->args_count < 2)) + if (WARN_ON(fwspec->param_count < 2)) return -EINVAL; - if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type)) + + type_index = fwspec->param[1]; + if (type_index >= ARRAY_SIZE(of_ioapic_type)) return -EINVAL; - it = &of_ioapic_type[irq_data->args[1]]; + it = &of_ioapic_type[type_index]; ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity); tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain)); - tmp.ioapic_pin = irq_data->args[0]; + tmp.ioapic_pin = fwspec->param[0]; return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp); } @@ -276,14 +280,15 @@ static void __init x86_flattree_get_config(void) map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128); - initial_boot_params = dt = early_memremap(initial_dtb, map_len); - size = of_get_flat_dt_size(); + dt = early_memremap(initial_dtb, map_len); + size = fdt_totalsize(dt); if (map_len < size) { early_memunmap(dt, map_len); - initial_boot_params = dt = early_memremap(initial_dtb, size); + dt = early_memremap(initial_dtb, size); map_len = size; } + early_init_dt_verify(dt); unflatten_and_copy_device_tree(); early_memunmap(dt, map_len); } diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index edfede768688..5167f3f74136 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -57,12 +57,17 @@ static void load_segments(void) static void machine_kexec_free_page_tables(struct kimage *image) { free_page((unsigned long)image->arch.pgd); + image->arch.pgd = NULL; #ifdef CONFIG_X86_PAE free_page((unsigned long)image->arch.pmd0); + image->arch.pmd0 = NULL; free_page((unsigned long)image->arch.pmd1); + image->arch.pmd1 = NULL; #endif free_page((unsigned long)image->arch.pte0); + image->arch.pte0 = NULL; free_page((unsigned long)image->arch.pte1); + image->arch.pte1 = NULL; } static int machine_kexec_alloc_page_tables(struct kimage *image) @@ -79,7 +84,6 @@ static int machine_kexec_alloc_page_tables(struct kimage *image) !image->arch.pmd0 || !image->arch.pmd1 || #endif !image->arch.pte0 || !image->arch.pte1) { - machine_kexec_free_page_tables(image); return -ENOMEM; } return 0; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 3b7427aa7d85..5bce2a88e8a3 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -38,9 +38,13 @@ static struct kexec_file_ops *kexec_file_loaders[] = { static void free_transition_pgtable(struct kimage *image) { free_page((unsigned long)image->arch.p4d); + image->arch.p4d = NULL; free_page((unsigned long)image->arch.pud); + image->arch.pud = NULL; free_page((unsigned long)image->arch.pmd); + image->arch.pmd = NULL; free_page((unsigned long)image->arch.pte); + image->arch.pte = NULL; } static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) @@ -90,7 +94,6 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC)); return 0; err: - free_transition_pgtable(image); return result; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 8bd1d8292cf7..988a98f34c66 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -39,6 +39,7 @@ #include <asm/switch_to.h> #include <asm/desc.h> #include <asm/prctl.h> +#include <asm/spec-ctrl.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -279,6 +280,148 @@ static inline void switch_to_bitmap(struct tss_struct *tss, } } +#ifdef CONFIG_SMP + +struct ssb_state { + struct ssb_state *shared_state; + raw_spinlock_t lock; + unsigned int disable_state; + unsigned long local_state; +}; + +#define LSTATE_SSB 0 + +static DEFINE_PER_CPU(struct ssb_state, ssb_state); + +void speculative_store_bypass_ht_init(void) +{ + struct ssb_state *st = this_cpu_ptr(&ssb_state); + unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; + + st->local_state = 0; + + /* + * Shared state setup happens once on the first bringup + * of the CPU. It's not destroyed on CPU hotunplug. + */ + if (st->shared_state) + return; + + raw_spin_lock_init(&st->lock); + + /* + * Go over HT siblings and check whether one of them has set up the + * shared state pointer already. + */ + for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) { + if (cpu == this_cpu) + continue; + + if (!per_cpu(ssb_state, cpu).shared_state) + continue; + + /* Link it to the state of the sibling: */ + st->shared_state = per_cpu(ssb_state, cpu).shared_state; + return; + } + + /* + * First HT sibling to come up on the core. Link shared state of + * the first HT sibling to itself. The siblings on the same core + * which come up later will see the shared state pointer and link + * themself to the state of this CPU. + */ + st->shared_state = st; +} + +/* + * Logic is: First HT sibling enables SSBD for both siblings in the core + * and last sibling to disable it, disables it for the whole core. This how + * MSR_SPEC_CTRL works in "hardware": + * + * CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL + */ +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) +{ + struct ssb_state *st = this_cpu_ptr(&ssb_state); + u64 msr = x86_amd_ls_cfg_base; + + if (!static_cpu_has(X86_FEATURE_ZEN)) { + msr |= ssbd_tif_to_amd_ls_cfg(tifn); + wrmsrl(MSR_AMD64_LS_CFG, msr); + return; + } + + if (tifn & _TIF_SSBD) { + /* + * Since this can race with prctl(), block reentry on the + * same CPU. + */ + if (__test_and_set_bit(LSTATE_SSB, &st->local_state)) + return; + + msr |= x86_amd_ls_cfg_ssbd_mask; + + raw_spin_lock(&st->shared_state->lock); + /* First sibling enables SSBD: */ + if (!st->shared_state->disable_state) + wrmsrl(MSR_AMD64_LS_CFG, msr); + st->shared_state->disable_state++; + raw_spin_unlock(&st->shared_state->lock); + } else { + if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state)) + return; + + raw_spin_lock(&st->shared_state->lock); + st->shared_state->disable_state--; + if (!st->shared_state->disable_state) + wrmsrl(MSR_AMD64_LS_CFG, msr); + raw_spin_unlock(&st->shared_state->lock); + } +} +#else +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) +{ + u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn); + + wrmsrl(MSR_AMD64_LS_CFG, msr); +} +#endif + +static __always_inline void amd_set_ssb_virt_state(unsigned long tifn) +{ + /* + * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL, + * so ssbd_tif_to_spec_ctrl() just works. + */ + wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn)); +} + +static __always_inline void intel_set_ssb_state(unsigned long tifn) +{ + u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn); + + wrmsrl(MSR_IA32_SPEC_CTRL, msr); +} + +static __always_inline void __speculative_store_bypass_update(unsigned long tifn) +{ + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) + amd_set_ssb_virt_state(tifn); + else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + amd_set_core_ssb_state(tifn); + else + intel_set_ssb_state(tifn); +} + +void speculative_store_bypass_update(unsigned long tif) +{ + preempt_disable(); + __speculative_store_bypass_update(tif); + preempt_enable(); +} + void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss) { @@ -310,6 +453,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, if ((tifp ^ tifn) & _TIF_NOCPUID) set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); + + if ((tifp ^ tifn) & _TIF_SSBD) + __speculative_store_bypass_update(tifn); } /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9eb448c7859d..fa093b77689f 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -528,6 +528,7 @@ void set_personality_64bit(void) clear_thread_flag(TIF_X32); /* Pretend that this comes from a 64bit execve */ task_pt_regs(current)->orig_ax = __NR_execve; + current_thread_info()->status &= ~TS_COMPAT; /* Ensure the corresponding mm is not marked. */ if (current->mm) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6b841262b790..344d3c160f8d 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,6 +77,7 @@ #include <asm/i8259.h> #include <asm/realmode.h> #include <asm/misc.h> +#include <asm/spec-ctrl.h> /* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -245,6 +246,8 @@ static void notrace start_secondary(void *unused) */ check_tsc_sync_target(); + speculative_store_bypass_ht_init(); + /* * Lock vector_lock and initialize the vectors on this cpu * before setting the cpu online. We must set it online with @@ -1349,6 +1352,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_mtrr_aps_delayed_init(); smp_quirk_init_udelay(); + + speculative_store_bypass_ht_init(); } void arch_enable_nonboot_cpus_begin(void) @@ -1516,6 +1521,7 @@ static void remove_siblinginfo(int cpu) cpumask_clear(topology_core_cpumask(cpu)); c->phys_proc_id = 0; c->cpu_core_id = 0; + c->booted_cores = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 4f544f2a7b06..d1f5c744142b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -367,7 +367,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(IBPB) | F(IBRS); + F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD); /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = @@ -395,7 +395,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | - F(ARCH_CAPABILITIES); + F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -481,6 +481,11 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; cpuid_mask(&entry->edx, CPUID_7_EDX); + /* + * We emulate ARCH_CAPABILITIES in software even + * if the host doesn't support it. + */ + entry->edx |= F(ARCH_CAPABILITIES); } else { entry->ebx = 0; entry->ecx = 0; @@ -632,13 +637,20 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; - /* IBRS and IBPB aren't necessarily present in hardware cpuid */ - if (boot_cpu_has(X86_FEATURE_IBPB)) - entry->ebx |= F(IBPB); - if (boot_cpu_has(X86_FEATURE_IBRS)) - entry->ebx |= F(IBRS); + /* + * IBRS, IBPB and VIRT_SSBD aren't necessarily present in + * hardware cpuid + */ + if (boot_cpu_has(X86_FEATURE_AMD_IBPB)) + entry->ebx |= F(AMD_IBPB); + if (boot_cpu_has(X86_FEATURE_AMD_IBRS)) + entry->ebx |= F(AMD_IBRS); + if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) + entry->ebx |= F(VIRT_SSBD); entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + entry->ebx |= F(VIRT_SSBD); break; } case 0x80000019: diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index ddd83fb65da5..92f13ac70ad4 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -321,8 +321,16 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; + /* + * KVM emulates 82093AA datasheet (with in-kernel IOAPIC implementation) + * which doesn't have EOI register; Some buggy OSes (e.g. Windows with + * Hyper-V role) disable EOI broadcast in lapic not checking for IOAPIC + * version first and level-triggered interrupts never get EOIed in + * IOAPIC. + */ feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0); - if (feat && (feat->ecx & (1 << (X86_FEATURE_X2APIC & 31)))) + if (feat && (feat->ecx & (1 << (X86_FEATURE_X2APIC & 31))) && + !ioapic_in_kernel(vcpu->kvm)) v |= APIC_LVR_DIRECTED_EOI; kvm_lapic_set_reg(apic, APIC_LVR, v); } @@ -1467,11 +1475,23 @@ static bool set_target_expiration(struct kvm_lapic *apic) static void advance_periodic_target_expiration(struct kvm_lapic *apic) { - apic->lapic_timer.tscdeadline += - nsec_to_cycles(apic->vcpu, apic->lapic_timer.period); + ktime_t now = ktime_get(); + u64 tscl = rdtsc(); + ktime_t delta; + + /* + * Synchronize both deadlines to the same time source or + * differences in the periods (caused by differences in the + * underlying clocks or numerical approximation errors) will + * cause the two to drift apart over time as the errors + * accumulate. + */ apic->lapic_timer.target_expiration = ktime_add_ns(apic->lapic_timer.target_expiration, apic->lapic_timer.period); + delta = ktime_sub(apic->lapic_timer.target_expiration, now); + apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) + + nsec_to_cycles(apic->vcpu, delta); } static void start_sw_period(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 9fb0daf628cb..029aa1318874 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -46,7 +46,7 @@ #include <asm/kvm_para.h> #include <asm/irq_remapping.h> #include <asm/microcode.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/virtext.h> #include "trace.h" @@ -186,6 +186,12 @@ struct vcpu_svm { } host; u64 spec_ctrl; + /* + * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be + * translated into the appropriate L2_CFG bits on the host to + * perform speculative control. + */ + u64 virt_spec_ctrl; u32 *msrpm; @@ -1611,6 +1617,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 eax = 1; svm->spec_ctrl = 0; + svm->virt_spec_ctrl = 0; if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | @@ -3618,11 +3625,18 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) return 1; msr_info->data = svm->spec_ctrl; break; + case MSR_AMD64_VIRT_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + return 1; + + msr_info->data = svm->virt_spec_ctrl; + break; case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; @@ -3716,7 +3730,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_SPEC_CTRL: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) return 1; /* The STIBP bit doesn't fault even if it's not advertised */ @@ -3743,7 +3757,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_PRED_CMD: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBPB)) + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) return 1; if (data & ~PRED_CMD_IBPB) @@ -3757,6 +3771,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); break; + case MSR_AMD64_VIRT_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + return 1; + + if (data & ~SPEC_CTRL_SSBD) + return 1; + + svm->virt_spec_ctrl = data; + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -5015,8 +5039,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - if (svm->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl); asm volatile ( "push %%" _ASM_BP "; \n\t" @@ -5110,6 +5133,18 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + +#ifdef CONFIG_X86_64 + wrmsrl(MSR_GS_BASE, svm->host.gs_base); +#else + loadsegment(fs, svm->host.fs); +#ifndef CONFIG_X86_32_LAZY_GS + loadsegment(gs, svm->host.gs); +#endif +#endif + /* * We do not use IBRS in the kernel. If this vCPU has used the * SPEC_CTRL MSR it may have left it on; save the value and @@ -5128,20 +5163,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - if (svm->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); - - /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); - -#ifdef CONFIG_X86_64 - wrmsrl(MSR_GS_BASE, svm->host.gs_base); -#else - loadsegment(fs, svm->host.fs); -#ifndef CONFIG_X86_32_LAZY_GS - loadsegment(gs, svm->host.gs); -#endif -#endif + x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl); reload_tss(vcpu); @@ -5244,7 +5266,7 @@ static bool svm_cpu_has_accelerated_tpr(void) return false; } -static bool svm_has_high_real_mode_segbase(void) +static bool svm_has_emulated_msr(int index) { return true; } @@ -5551,7 +5573,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, - .cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase, + .has_emulated_msr = svm_has_emulated_msr, .vcpu_create = svm_create_vcpu, .vcpu_free = svm_free_vcpu, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bdd84ce4491e..4c88572d2b81 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -52,7 +52,7 @@ #include <asm/irq_remapping.h> #include <asm/mmu_context.h> #include <asm/microcode.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include "trace.h" #include "pmu.h" @@ -2583,6 +2583,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) return; } + WARN_ON_ONCE(vmx->emulation_required); + if (kvm_exception_is_soft(nr)) { vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmx->vcpu.arch.event_exit_inst_len); @@ -3293,7 +3295,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; @@ -3414,12 +3415,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) return 1; vmx->spec_ctrl = data; @@ -3445,7 +3445,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; @@ -6832,12 +6831,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) goto out; } - if (err != EMULATE_DONE) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - return 0; - } + if (err != EMULATE_DONE) + goto emulation_error; + + if (vmx->emulation_required && !vmx->rmode.vm86_active && + vcpu->arch.exception.pending) + goto emulation_error; if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; @@ -6853,6 +6852,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) out: return ret; + +emulation_error: + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return 0; } static int __grow_ple_window(int val) @@ -9217,9 +9222,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) } STACK_FRAME_NON_STANDARD(vmx_handle_external_intr); -static bool vmx_has_high_real_mode_segbase(void) +static bool vmx_has_emulated_msr(int index) { - return enable_unrestricted_guest || emulate_invalid_guest_state; + switch (index) { + case MSR_IA32_SMBASE: + /* + * We cannot do SMM unless we can run the guest in big + * real mode. + */ + return enable_unrestricted_guest || emulate_invalid_guest_state; + case MSR_AMD64_VIRT_SPEC_CTRL: + /* This is AMD only. */ + return false; + default: + return true; + } } static bool vmx_mpx_supported(void) @@ -9452,10 +9469,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - if (vmx->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0); vmx->__launched = vmx->loaded_vmcs->launched; + asm( /* Store host registers */ "push %%" _ASM_DX "; push %%" _ASM_BP ";" @@ -9591,8 +9608,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - if (vmx->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); + x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -11166,7 +11182,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (ret) return ret; - if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) + /* + * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken + * by event injection, halt vcpu. + */ + if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && + !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) return kvm_vcpu_halt(vcpu); vmx->nested.nested_run_pending = 1; @@ -12182,7 +12203,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .hardware_enable = hardware_enable, .hardware_disable = hardware_disable, .cpu_has_accelerated_tpr = report_flexpriority, - .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase, + .has_emulated_msr = vmx_has_emulated_msr, .vcpu_create = vmx_create_vcpu, .vcpu_free = vmx_free_vcpu, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ba5b6693fbe7..9fc1712523d7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1036,6 +1036,7 @@ static u32 emulated_msrs[] = { MSR_IA32_SMBASE, MSR_PLATFORM_INFO, MSR_MISC_FEATURES_ENABLES, + MSR_AMD64_VIRT_SPEC_CTRL, }; static unsigned num_emulated_msrs; @@ -2721,7 +2722,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * fringe case that is not enabled except via specific settings * of the module parameters. */ - r = kvm_x86_ops->cpu_has_high_real_mode_segbase(); + r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE); break; case KVM_CAP_VAPIC: r = !kvm_x86_ops->cpu_has_accelerated_tpr(); @@ -4324,14 +4325,8 @@ static void kvm_init_msr_list(void) num_msrs_to_save = j; for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { - switch (emulated_msrs[i]) { - case MSR_IA32_SMBASE: - if (!kvm_x86_ops->cpu_has_high_real_mode_segbase()) - continue; - break; - default: - break; - } + if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i])) + continue; if (j < i) emulated_msrs[j] = emulated_msrs[i]; @@ -7517,6 +7512,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, { struct msr_data apic_base_msr; int mmu_reset_needed = 0; + int cpuid_update_needed = 0; int pending_vec, max_bits, idx; struct desc_ptr dt; @@ -7554,8 +7550,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, vcpu->arch.cr0 = sregs->cr0; mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; + cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) & + (X86_CR4_OSXSAVE | X86_CR4_PKE)); kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE)) + if (cpuid_update_needed) kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 3ed9a08885c5..4085897fef64 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -298,9 +298,11 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, /* * The .rodata section needs to be read-only. Using the pfn - * catches all aliases. + * catches all aliases. This also includes __ro_after_init, + * so do not enforce until kernel_set_to_readonly is true. */ - if (within(pfn, __pa_symbol(__start_rodata) >> PAGE_SHIFT, + if (kernel_set_to_readonly && + within(pfn, __pa_symbol(__start_rodata) >> PAGE_SHIFT, __pa_symbol(__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 34cda7e0551b..c03c85e4fb6a 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/gfp.h> +#include <linux/hugetlb.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> #include <asm/tlb.h> @@ -636,6 +637,10 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) (mtrr != MTRR_TYPE_WRBACK)) return 0; + /* Bail out if we are we on a populated non-leaf entry: */ + if (pud_present(*pud) && !pud_huge(*pud)) + return 0; + prot = pgprot_4k_2_large(prot); set_pte((pte_t *)pud, pfn_pte( @@ -664,6 +669,10 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) return 0; } + /* Bail out if we are we on a populated non-leaf entry: */ + if (pmd_present(*pmd) && !pmd_huge(*pmd)) + return 0; + prot = pgprot_4k_2_large(prot); set_pte((pte_t *)pmd, pfn_pte( diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index d7bc0eea20a5..6e98e0a7c923 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -94,26 +94,27 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey */ if (pkey != -1) return pkey; - /* - * Look for a protection-key-drive execute-only mapping - * which is now being given permissions that are not - * execute-only. Move it back to the default pkey. - */ - if (vma_is_pkey_exec_only(vma) && - (prot & (PROT_READ|PROT_WRITE))) { - return 0; - } + /* * The mapping is execute-only. Go try to get the * execute-only protection key. If we fail to do that, * fall through as if we do not have execute-only - * support. + * support in this mm. */ if (prot == PROT_EXEC) { pkey = execute_only_pkey(vma->vm_mm); if (pkey > 0) return pkey; + } else if (vma_is_pkey_exec_only(vma)) { + /* + * Protections are *not* PROT_EXEC, but the mapping + * is using the exec-only pkey. This mapping was + * PROT_EXEC and will no longer be. Move back to + * the default pkey. + */ + return ARCH_DEFAULT_PKEY; } + /* * This is a vanilla, non-pkey mprotect (or we failed to * setup execute-only), inherit the pkey from the VMA we diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3e15345abfe7..de0263348f2d 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,13 +42,11 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr) } EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine); -static void xen_flush_tlb_all(void) +static noinline void xen_flush_tlb_all(void) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_all(0); - preempt_disable(); mcs = xen_mc_entry(sizeof(*op)); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 042e9c422b21..b3526a98a5a5 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1280,13 +1280,11 @@ unsigned long xen_read_cr2_direct(void) return this_cpu_read(xen_vcpu_info.arch.cr2); } -static void xen_flush_tlb(void) +static noinline void xen_flush_tlb(void) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb(0); - preempt_disable(); mcs = xen_mc_entry(sizeof(*op)); |