diff options
Diffstat (limited to 'arch/x86/include')
62 files changed, 771 insertions, 499 deletions
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index de690c2d2e33..a0ab9ab61c75 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -8,5 +8,6 @@ generated-y += xen-hypercalls.h generic-y += dma-contiguous.h generic-y += early_ioremap.h +generic-y += export.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 74a9e06b6cfd..130e81e10fc7 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -10,6 +10,7 @@ #include <asm/fixmap.h> #include <asm/mpspec.h> #include <asm/msr.h> +#include <asm/hardirq.h> #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -502,12 +503,19 @@ extern int default_check_phys_apicid_present(int phys_apicid); #endif /* CONFIG_X86_LOCAL_APIC */ +#ifdef CONFIG_SMP +bool apic_id_is_primary_thread(unsigned int id); +#else +static inline bool apic_id_is_primary_thread(unsigned int id) { return false; } +#endif + extern void irq_enter(void); extern void irq_exit(void); static inline void entering_irq(void) { irq_enter(); + kvm_set_cpu_l1tf_flush_l1d(); } static inline void entering_ack_irq(void) @@ -520,6 +528,7 @@ static inline void ipi_entering_ack_irq(void) { irq_enter(); ack_APIC_irq(); + kvm_set_cpu_l1tf_flush_l1d(); } static inline void exiting_irq(void) diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 0db6bec95489..b143717b92b3 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,6 +80,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); @@ -91,6 +92,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" @@ -103,6 +105,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" @@ -117,6 +120,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); @@ -130,6 +134,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); @@ -144,6 +149,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); @@ -173,9 +179,6 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) return arch_atomic_add_return(-i, v); } -#define arch_atomic_inc_return(v) (arch_atomic_add_return(1, v)) -#define arch_atomic_dec_return(v) (arch_atomic_sub_return(1, v)) - static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); @@ -199,7 +202,7 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n static inline int arch_atomic_xchg(atomic_t *v, int new) { - return xchg(&v->counter, new); + return arch_xchg(&v->counter, new); } static inline void arch_atomic_and(int i, atomic_t *v) @@ -253,27 +256,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v) return val; } -/** - * __arch_atomic_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns the old value of @v. - */ -static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); - - return c; -} - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 92212bf0484f..ef959f02d070 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -158,6 +158,7 @@ static inline long long arch_atomic64_inc_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_inc_return arch_atomic64_inc_return static inline long long arch_atomic64_dec_return(atomic64_t *v) { @@ -166,6 +167,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v) "S" (v) : "memory", "ecx"); return a; } +#define arch_atomic64_dec_return arch_atomic64_dec_return /** * arch_atomic64_add - add integer to atomic64 variable @@ -198,25 +200,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) } /** - * arch_atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer to type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v) -{ - return arch_atomic64_sub_return(i, v) == 0; -} - -/** * arch_atomic64_inc - increment atomic64 variable * @v: pointer to type atomic64_t * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, @@ -229,6 +218,7 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, @@ -236,46 +226,6 @@ static inline void arch_atomic64_dec(atomic64_t *v) } /** - * arch_atomic64_dec_and_test - decrement and test - * @v: pointer to type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static inline int arch_atomic64_dec_and_test(atomic64_t *v) -{ - return arch_atomic64_dec_return(v) == 0; -} - -/** - * atomic64_inc_and_test - increment and test - * @v: pointer to type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static inline int arch_atomic64_inc_and_test(atomic64_t *v) -{ - return arch_atomic64_inc_return(v) == 0; -} - -/** - * arch_atomic64_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer to type atomic64_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static inline int arch_atomic64_add_negative(long long i, atomic64_t *v) -{ - return arch_atomic64_add_return(i, v) < 0; -} - -/** * arch_atomic64_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... @@ -295,7 +245,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } - +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; @@ -304,6 +254,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 6106b59d3260..4343d9b4f30e 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,6 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); @@ -82,6 +83,7 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ +#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" @@ -95,6 +97,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ +#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" @@ -110,6 +113,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); @@ -123,6 +127,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); @@ -137,6 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ +#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); @@ -169,9 +175,6 @@ static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v) return xadd(&v->counter, -i); } -#define arch_atomic64_inc_return(v) (arch_atomic64_add_return(1, (v))) -#define arch_atomic64_dec_return(v) (arch_atomic64_sub_return(1, (v))) - static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new) { return arch_cmpxchg(&v->counter, old, new); @@ -185,46 +188,7 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, l static inline long arch_atomic64_xchg(atomic64_t *v, long new) { - return xchg(&v->counter, new); -} - -/** - * arch_atomic64_add_unless - add unless the number is a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. - */ -static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u) -{ - s64 c = arch_atomic64_read(v); - do { - if (unlikely(c == u)) - return false; - } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); - return true; -} - -#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0) - -/* - * arch_atomic64_dec_if_positive - decrement by 1 if old value positive - * @v: pointer of type atomic_t - * - * The function returns the old value of *v minus 1, even if - * the atomic variable, v, was not decremented. - */ -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) -{ - s64 dec, c = arch_atomic64_read(v); - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); - return dec; + return arch_xchg(&v->counter, new); } static inline void arch_atomic64_and(long i, atomic64_t *v) diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index e3efd8a06066..a55d79b233d3 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -75,7 +75,7 @@ extern void __add_wrong_size(void) * use "asm volatile" and "memory" clobbers to prevent gcc from moving * information around. */ -#define xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") +#define arch_xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") /* * Atomic compare and exchange. Compare OLD with MEM, if identical, diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index bfca3b346c74..072e5459fe2f 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -10,13 +10,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) #define arch_cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg((ptr), (o), (n)); \ + arch_cmpxchg((ptr), (o), (n)); \ }) #define arch_cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg_local((ptr), (o), (n)); \ + arch_cmpxchg_local((ptr), (o), (n)); \ }) #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 5701f5cecd31..89a048c2faec 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -219,6 +219,8 @@ #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) */ +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ +#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -229,7 +231,7 @@ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ - +#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -341,6 +343,7 @@ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #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_FLUSH_L1D (18*32+28) /* Flush L1D cache */ #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 */ @@ -373,5 +376,6 @@ #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 */ +#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index 0ab2ab27ad1f..b825cb201251 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -4,8 +4,8 @@ #include <linux/compiler.h> #include <linux/init.h> +#include <linux/io.h> -#include <asm/io.h> #include <asm/setup.h> static __always_inline __init void *dmi_alloc(unsigned len) diff --git a/arch/x86/include/asm/export.h b/arch/x86/include/asm/export.h deleted file mode 100644 index 2a51d66689c5..000000000000 --- a/arch/x86/include/asm/export.h +++ /dev/null @@ -1,5 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifdef CONFIG_64BIT -#define KSYM_ALIGN 16 -#endif -#include <asm-generic/export.h> diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 740a428acf1e..d9069bb26c7f 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -3,10 +3,12 @@ #define _ASM_X86_HARDIRQ_H #include <linux/threads.h> -#include <linux/irq.h> typedef struct { - unsigned int __softirq_pending; + u16 __softirq_pending; +#if IS_ENABLED(CONFIG_KVM_INTEL) + u8 kvm_cpu_l1tf_flush_l1d; +#endif unsigned int __nmi_count; /* arch dependent */ #ifdef CONFIG_X86_LOCAL_APIC unsigned int apic_timer_irqs; /* arch dependent */ @@ -58,4 +60,24 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu); extern u64 arch_irq_stat(void); #define arch_irq_stat arch_irq_stat + +#if IS_ENABLED(CONFIG_KVM_INTEL) +static inline void kvm_set_cpu_l1tf_flush_l1d(void) +{ + __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1); +} + +static inline void kvm_clear_cpu_l1tf_flush_l1d(void) +{ + __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 0); +} + +static inline bool kvm_get_cpu_l1tf_flush_l1d(void) +{ + return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d); +} +#else /* !IS_ENABLED(CONFIG_KVM_INTEL) */ +static inline void kvm_set_cpu_l1tf_flush_l1d(void) { } +#endif /* IS_ENABLED(CONFIG_KVM_INTEL) */ + #endif /* _ASM_X86_HARDIRQ_H */ diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index f59c39835a5a..a1f0e90d0818 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -49,11 +49,14 @@ static inline int hw_breakpoint_slots(int type) return HBP_NUM; } +struct perf_event_attr; struct perf_event; struct pmu; -extern int arch_check_bp_in_kernelspace(struct perf_event *bp); -extern int arch_validate_hwbkpt_settings(struct perf_event *bp); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, unsigned long val, void *data); diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index b8c89265baf0..e977b6b3a538 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -35,9 +35,9 @@ /* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */ #define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0) /* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/ -#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1) +#define HV_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1) /* Partition reference TSC MSR is available */ -#define HV_X64_MSR_REFERENCE_TSC_AVAILABLE (1 << 9) +#define HV_MSR_REFERENCE_TSC_AVAILABLE (1 << 9) /* A partition's reference time stamp counter (TSC) page */ #define HV_X64_MSR_REFERENCE_TSC 0x40000021 @@ -60,7 +60,7 @@ * Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through * HV_X64_MSR_STIMER3_COUNT) available */ -#define HV_X64_MSR_SYNTIMER_AVAILABLE (1 << 3) +#define HV_MSR_SYNTIMER_AVAILABLE (1 << 3) /* * APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR) * are available @@ -86,7 +86,7 @@ #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10) /* stimer Direct Mode is available */ -#define HV_X64_STIMER_DIRECT_MODE_AVAILABLE (1 << 19) +#define HV_STIMER_DIRECT_MODE_AVAILABLE (1 << 19) /* * Feature identification: EBX indicates which flags were specified at @@ -160,9 +160,9 @@ #define HV_X64_RELAXED_TIMING_RECOMMENDED (1 << 5) /* - * Virtual APIC support + * Recommend not using Auto End-Of-Interrupt feature */ -#define HV_X64_DEPRECATING_AEOI_RECOMMENDED (1 << 9) +#define HV_DEPRECATING_AEOI_RECOMMENDED (1 << 9) /* * Recommend using cluster IPI hypercalls. @@ -176,9 +176,10 @@ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED (1 << 14) /* - * Crash notification flag. + * Crash notification flags. */ -#define HV_CRASH_CTL_CRASH_NOTIFY (1ULL << 63) +#define HV_CRASH_CTL_CRASH_NOTIFY_MSG BIT_ULL(62) +#define HV_CRASH_CTL_CRASH_NOTIFY BIT_ULL(63) /* MSR used to identify the guest OS. */ #define HV_X64_MSR_GUEST_OS_ID 0x40000000 @@ -309,6 +310,7 @@ struct ms_hyperv_tsc_page { #define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 /* Nested features (CPUID 0x4000000A) EAX */ +#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) #define HV_X64_NESTED_MSR_BITMAP BIT(19) struct hv_reenlightenment_control { @@ -350,6 +352,7 @@ struct hv_tsc_emulation_status { #define HVCALL_SEND_IPI_EX 0x0015 #define HVCALL_POST_MESSAGE 0x005c #define HVCALL_SIGNAL_EVENT 0x005d +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 @@ -741,6 +744,12 @@ struct ipi_arg_ex { struct hv_vpset vp_set; }; +/* HvFlushGuestPhysicalAddressSpace hypercalls */ +struct hv_guest_mapping_flush { + u64 address_space; + u64 flags; +}; + /* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ struct hv_tlb_flush { u64 address_space; diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h index 5cdcdbd4d892..89789e8c80f6 100644 --- a/arch/x86/include/asm/i8259.h +++ b/arch/x86/include/asm/i8259.h @@ -3,6 +3,7 @@ #define _ASM_X86_I8259_H #include <linux/delay.h> +#include <asm/io.h> extern unsigned int cached_irq_mask; diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index cf090e584202..7ed08a7c3398 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -76,4 +76,17 @@ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ #define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */ +/* Useful macros */ +#define INTEL_CPU_FAM_ANY(_family, _model, _driver_data) \ +{ \ + .vendor = X86_VENDOR_INTEL, \ + .family = _family, \ + .model = _model, \ + .feature = X86_FEATURE_ANY, \ + .driver_data = (kernel_ulong_t)&_driver_data \ +} + +#define INTEL_CPU_FAM6(_model, _driver_data) \ + INTEL_CPU_FAM_ANY(6, INTEL_FAM6_##_model, _driver_data) + #endif /* _ASM_X86_INTEL_FAMILY_H */ diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index fe04491130ae..52f815a80539 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -80,35 +80,6 @@ enum intel_mid_cpu_type { extern enum intel_mid_cpu_type __intel_mid_cpu_chip; -/** - * struct intel_mid_ops - Interface between intel-mid & sub archs - * @arch_setup: arch_setup function to re-initialize platform - * structures (x86_init, x86_platform_init) - * - * This structure can be extended if any new interface is required - * between intel-mid & its sub arch files. - */ -struct intel_mid_ops { - void (*arch_setup)(void); -}; - -/* Helper API's for INTEL_MID_OPS_INIT */ -#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid) \ - [cpuid] = get_##cpuname##_ops - -/* Maximum number of CPU ops */ -#define MAX_CPU_OPS(a) (sizeof(a)/sizeof(void *)) - -/* - * For every new cpu addition, a weak get_<cpuname>_ops() function needs be - * declared in arch/x86/platform/intel_mid/intel_mid_weak_decls.h. - */ -#define INTEL_MID_OPS_INIT { \ - DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL), \ - DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW), \ - DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER) \ -}; - #ifdef CONFIG_X86_INTEL_MID static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void) @@ -136,20 +107,6 @@ enum intel_mid_timer_options { extern enum intel_mid_timer_options intel_mid_timer_options; -/* - * Penwell uses spread spectrum clock, so the freq number is not exactly - * the same as reported by MSR based on SDM. - */ -#define FSB_FREQ_83SKU 83200 -#define FSB_FREQ_100SKU 99840 -#define FSB_FREQ_133SKU 133000 - -#define FSB_FREQ_167SKU 167000 -#define FSB_FREQ_200SKU 200000 -#define FSB_FREQ_267SKU 267000 -#define FSB_FREQ_333SKU 333000 -#define FSB_FREQ_400SKU 400000 - /* Bus Select SoC Fuse value */ #define BSEL_SOC_FUSE_MASK 0x7 /* FSB 133MHz */ diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h index 62a9f4966b42..ae26df1c2789 100644 --- a/arch/x86/include/asm/intel_ds.h +++ b/arch/x86/include/asm/intel_ds.h @@ -8,6 +8,7 @@ /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS 8 +#define MAX_FIXED_PEBS_EVENTS 3 /* * A debug store configuration. @@ -23,7 +24,7 @@ struct debug_store { u64 pebs_index; u64 pebs_absolute_maximum; u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; + u64 pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS]; } __aligned(PAGE_SIZE); DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 023b4a9fc846..5f26962eff42 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -33,6 +33,11 @@ enum irq_remap_cap { IRQ_POSTING_CAP = 0, }; +enum { + IRQ_REMAP_XAPIC_MODE, + IRQ_REMAP_X2APIC_MODE, +}; + struct vcpu_data { u64 pi_desc_addr; /* Physical address of PI Descriptor */ u32 vector; /* Guest vector of the interrupt */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index c4fc17220df9..c14f2a74b2be 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -13,6 +13,8 @@ * Interrupt control: */ +/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ +extern inline unsigned long native_save_fl(void); extern inline unsigned long native_save_fl(void) { unsigned long flags; diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 367d99cff426..c8cec1b39b88 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -78,7 +78,7 @@ struct arch_specific_insn { * boostable = true: This instruction has been boosted: we have * added a relative jump after the instruction copy in insn, * so no single-step and fixup are needed (unless there's - * a post_handler or break_handler). + * a post_handler). */ bool boostable; bool if_modifier; @@ -111,9 +111,6 @@ struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_old_flags; unsigned long kprobe_saved_flags; - unsigned long *jprobe_saved_sp; - struct pt_regs jprobe_saved_regs; - kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE]; struct prev_kprobe prev_kprobe; }; diff --git a/arch/x86/include/asm/kvm_guest.h b/arch/x86/include/asm/kvm_guest.h deleted file mode 100644 index 46185263d9c2..000000000000 --- a/arch/x86/include/asm/kvm_guest.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_KVM_GUEST_H -#define _ASM_X86_KVM_GUEST_H - -int kvm_setup_vsyscall_timeinfo(void); - -#endif /* _ASM_X86_KVM_GUEST_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c13cd28d9d1b..00ddb0c9e612 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -17,6 +17,7 @@ #include <linux/tracepoint.h> #include <linux/cpumask.h> #include <linux/irq_work.h> +#include <linux/irq.h> #include <linux/kvm.h> #include <linux/kvm_para.h> @@ -54,6 +55,7 @@ #define KVM_REQ_TRIPLE_FAULT KVM_ARCH_REQ(2) #define KVM_REQ_MMU_SYNC KVM_ARCH_REQ(3) #define KVM_REQ_CLOCK_UPDATE KVM_ARCH_REQ(4) +#define KVM_REQ_LOAD_CR3 KVM_ARCH_REQ(5) #define KVM_REQ_EVENT KVM_ARCH_REQ(6) #define KVM_REQ_APF_HALT KVM_ARCH_REQ(7) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(8) @@ -75,13 +77,13 @@ #define KVM_REQ_HV_EXIT KVM_ARCH_REQ(21) #define KVM_REQ_HV_STIMER KVM_ARCH_REQ(22) #define KVM_REQ_LOAD_EOI_EXITMAP KVM_ARCH_REQ(23) +#define KVM_REQ_GET_VMCS12_PAGES KVM_ARCH_REQ(24) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) -#define CR3_PCID_INVD BIT_64(63) #define CR4_RESERVED_BITS \ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ @@ -325,6 +327,16 @@ struct rsvd_bits_validate { u64 bad_mt_xwr; }; +struct kvm_mmu_root_info { + gpa_t cr3; + hpa_t hpa; +}; + +#define KVM_MMU_ROOT_INFO_INVALID \ + ((struct kvm_mmu_root_info) { .cr3 = INVALID_PAGE, .hpa = INVALID_PAGE }) + +#define KVM_MMU_NUM_PREV_ROOTS 3 + /* * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit, * and 2-level 32-bit). The kvm_mmu structure abstracts the details of the @@ -344,7 +356,7 @@ struct kvm_mmu { struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); - void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva); + void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, const void *pte); hpa_t root_hpa; @@ -353,6 +365,7 @@ struct kvm_mmu { u8 shadow_root_level; u8 ept_ad; bool direct_map; + struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS]; /* * Bitmap; bit set = permission fault @@ -713,6 +726,9 @@ struct kvm_vcpu_arch { /* be preempted when it's in kernel-mode(cpl=0) */ bool preempted_in_kernel; + + /* Flush the L1 Data cache for L1TF mitigation on VMENTER */ + bool l1tf_flush_l1d; }; struct kvm_lpage_info { @@ -881,6 +897,7 @@ struct kvm_vcpu_stat { u64 signal_exits; u64 irq_window_exits; u64 nmi_window_exits; + u64 l1d_flush; u64 halt_exits; u64 halt_successful_poll; u64 halt_attempted_poll; @@ -973,6 +990,15 @@ struct kvm_x86_ops { void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa); + int (*tlb_remote_flush)(struct kvm *kvm); + + /* + * Flush any TLB entries associated with the given GVA. + * Does not need to flush GPA->HPA mappings. + * Can potentially get non-canonical addresses through INVLPGs, which + * the implementation may choose to ignore if appropriate. + */ + void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr); void (*run)(struct kvm_vcpu *vcpu); int (*handle_exit)(struct kvm_vcpu *vcpu); @@ -1085,6 +1111,14 @@ struct kvm_x86_ops { void (*setup_mce)(struct kvm_vcpu *vcpu); + int (*get_nested_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + unsigned user_data_size); + int (*set_nested_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + struct kvm_nested_state *kvm_state); + void (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); + int (*smi_allowed)(struct kvm_vcpu *vcpu); int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase); @@ -1117,6 +1151,16 @@ static inline void kvm_arch_free_vm(struct kvm *kvm) return kvm_x86_ops->vm_free(kvm); } +#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB +static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) +{ + if (kvm_x86_ops->tlb_remote_flush && + !kvm_x86_ops->tlb_remote_flush(kvm)) + return 0; + else + return -ENOTSUPP; +} + int kvm_mmu_module_init(void); void kvm_mmu_module_exit(void); @@ -1268,6 +1312,10 @@ static inline int __kvm_irq_line_state(unsigned long *irq_state, return !!(*irq_state); } +#define KVM_MMU_ROOT_CURRENT BIT(0) +#define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i) +#define KVM_MMU_ROOTS_ALL (~0UL) + int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level); void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); @@ -1279,7 +1327,7 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu); -void kvm_mmu_free_roots(struct kvm_vcpu *vcpu); +void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free); gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, @@ -1298,7 +1346,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); -void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu); +void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); +void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush); void kvm_enable_tdp(void); void kvm_disable_tdp(void); @@ -1413,6 +1462,11 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); +int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, + unsigned long ipi_bitmap_high, int min, + unsigned long icr, int op_64_bit); + +u64 kvm_get_arch_capabilities(void); void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 3aea2658323a..4c723632c036 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -7,7 +7,6 @@ #include <uapi/asm/kvm_para.h> extern void kvmclock_init(void); -extern int kvm_register_clock(char *txt); #ifdef CONFIG_KVM_GUEST bool kvm_check_and_clear_guest_paused(void); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 8c7b3e5a2d01..3a17107594c8 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -148,6 +148,7 @@ enum mce_notifier_prios { MCE_PRIO_LOWEST = 0, }; +struct notifier_block; extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index bbc796eb0a3b..eeeb9289c764 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -71,12 +71,7 @@ struct ldt_struct { static inline void *ldt_slot_va(int slot) { -#ifdef CONFIG_X86_64 return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); -#else - BUG(); - return (void *)fix_to_virt(FIX_HOLE); -#endif } /* diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5a7375ed5f7c..f37704497d8f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -76,8 +76,10 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) } } -#define hv_init_timer(timer, tick) wrmsrl(timer, tick) -#define hv_init_timer_config(config, val) wrmsrl(config, val) +#define hv_init_timer(timer, tick) \ + wrmsrl(HV_X64_MSR_STIMER0_COUNT + (2*timer), tick) +#define hv_init_timer_config(timer, val) \ + wrmsrl(HV_X64_MSR_STIMER0_CONFIG + (2*timer), val) #define hv_get_simp(val) rdmsrl(HV_X64_MSR_SIMP, val) #define hv_set_simp(val) wrmsrl(HV_X64_MSR_SIMP, val) @@ -90,8 +92,13 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) #define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index) -#define hv_get_synint_state(int_num, val) rdmsrl(int_num, val) -#define hv_set_synint_state(int_num, val) wrmsrl(int_num, val) +#define hv_get_synint_state(int_num, val) \ + rdmsrl(HV_X64_MSR_SINT0 + int_num, val) +#define hv_set_synint_state(int_num, val) \ + wrmsrl(HV_X64_MSR_SINT0 + int_num, val) + +#define hv_get_crash_ctl(val) \ + rdmsrl(HV_X64_MSR_CRASH_CTL, val) void hyperv_callback_vector(void); void hyperv_reenlightenment_vector(void); @@ -194,6 +201,40 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) return hv_status; } +/* Fast hypercall with 16 bytes of input */ +static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) +{ + u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; + +#ifdef CONFIG_X86_64 + { + __asm__ __volatile__("mov %4, %%r8\n" + CALL_NOSPEC + : "=a" (hv_status), ASM_CALL_CONSTRAINT, + "+c" (control), "+d" (input1) + : "r" (input2), + THUNK_TARGET(hv_hypercall_pg) + : "cc", "r8", "r9", "r10", "r11"); + } +#else + { + u32 input1_hi = upper_32_bits(input1); + u32 input1_lo = lower_32_bits(input1); + u32 input2_hi = upper_32_bits(input2); + u32 input2_lo = lower_32_bits(input2); + + __asm__ __volatile__ (CALL_NOSPEC + : "=A"(hv_status), + "+c"(input1_lo), ASM_CALL_CONSTRAINT + : "A" (control), "b" (input1_hi), + "D"(input2_hi), "S"(input2_lo), + THUNK_TARGET(hv_hypercall_pg) + : "cc"); + } +#endif + return hv_status; +} + /* * Rep hypercalls. Callers of this functions are supposed to ensure that * rep_count and varhead_size comply with Hyper-V hypercall definition. @@ -298,6 +339,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, void __init hyperv_init(void); void hyperv_setup_mmu_ops(void); void hyperv_report_panic(struct pt_regs *regs, long err); +void hyperv_report_panic_msg(phys_addr_t pa, size_t size); bool hv_is_hyperv_initialized(void); void hyperv_cleanup(void); @@ -305,6 +347,7 @@ void hyperv_reenlightenment_intr(struct pt_regs *regs); void set_hv_tscchange_cb(void (*cb)(void)); void clear_hv_tscchange_cb(void); void hyperv_stop_tsc_emulation(void); +int hyperv_flush_guest_mapping(u64 as); #ifdef CONFIG_X86_64 void hv_apic_init(void); @@ -324,6 +367,7 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) { return NULL; } +static inline int hyperv_flush_guest_mapping(u64 as) { return -1; } #endif /* CONFIG_HYPERV */ #ifdef CONFIG_HYPERV_TSCPAGE diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 68b2c3150de1..4731f0cf97c5 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -70,12 +70,19 @@ #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_SKIP_VMENTRY_L1DFLUSH (1 << 3) /* Skip L1D flush on vmentry */ #define ARCH_CAP_SSB_NO (1 << 4) /* * Not susceptible to Speculative Store Bypass * attack, so no Speculative Store Bypass * control required. */ +#define MSR_IA32_FLUSH_CMD 0x0000010b +#define L1D_FLUSH (1 << 0) /* + * Writeback and invalidate the + * L1 data cache. + */ + #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f6f6c63da62f..fd2a8c1b88bc 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -214,7 +214,7 @@ enum spectre_v2_mitigation { SPECTRE_V2_RETPOLINE_MINIMAL_AMD, SPECTRE_V2_RETPOLINE_GENERIC, SPECTRE_V2_RETPOLINE_AMD, - SPECTRE_V2_IBRS, + SPECTRE_V2_IBRS_ENHANCED, }; /* The Speculative Store Bypass disable variants */ diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h index 9c9dc579bd7d..46f516dd80ce 100644 --- a/arch/x86/include/asm/orc_types.h +++ b/arch/x86/include/asm/orc_types.h @@ -88,6 +88,7 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned end:1; } __packed; /* @@ -101,6 +102,7 @@ struct unwind_hint { s16 sp_offset; u8 sp_reg; u8 type; + u8 end; }; #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index aa30c3241ea7..0d5c739eebd7 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -29,8 +29,13 @@ #define N_EXCEPTION_STACKS 1 #ifdef CONFIG_X86_PAE -/* 44=32+12, the limit we can fit into an unsigned long pfn */ -#define __PHYSICAL_MASK_SHIFT 44 +/* + * This is beyond the 44 bit limit imposed by the 32bit long pfns, + * but we need the full mask to make sure inverted PROT_NONE + * entries have all the host bits set in a guest. + * The real limit is still 44 bits. + */ +#define __PHYSICAL_MASK_SHIFT 52 #define __VIRTUAL_MASK_SHIFT 32 #else /* !CONFIG_X86_PAE */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index d49bbf4bb5c8..e375d4266b53 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -309,6 +309,11 @@ static inline void flush_tlb_others(const struct cpumask *cpumask, PVOP_VCALL2(pv_mmu_ops.flush_tlb_others, cpumask, info); } +static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + PVOP_VCALL2(pv_mmu_ops.tlb_remove_table, tlb, table); +} + static inline int paravirt_pgd_alloc(struct mm_struct *mm) { return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 180bc0bff0fb..4b75acc23b30 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -54,6 +54,7 @@ struct desc_struct; struct task_struct; struct cpumask; struct flush_tlb_info; +struct mmu_gather; /* * Wrapper type for pointers to code which uses the non-standard @@ -222,6 +223,8 @@ struct pv_mmu_ops { void (*flush_tlb_others)(const struct cpumask *cpus, const struct flush_tlb_info *info); + void (*tlb_remove_table)(struct mmu_gather *tlb, void *table); + /* Hooks for allocating and freeing a pagetable top-level */ int (*pgd_alloc)(struct mm_struct *mm); void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd); diff --git a/arch/x86/include/asm/pci-direct.h b/arch/x86/include/asm/pci-direct.h index e1084f71a295..94597a3cf3d0 100644 --- a/arch/x86/include/asm/pci-direct.h +++ b/arch/x86/include/asm/pci-direct.h @@ -15,8 +15,4 @@ extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val); extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val); extern int early_pci_allowed(void); - -extern unsigned int pci_early_dump_regs; -extern void early_dump_pci_device(u8 bus, u8 slot, u8 func); -extern void early_dump_pci_devices(void); #endif /* _ASM_X86_PCI_DIRECT_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a06b07399d17..e9202a0de8f0 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -450,9 +450,10 @@ do { \ bool __ret; \ typeof(pcp1) __o1 = (o1), __n1 = (n1); \ typeof(pcp2) __o2 = (o2), __n2 = (n2); \ - asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t" \ - : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \ - : "b" (__n1), "c" (__n2), "a" (__o1)); \ + asm volatile("cmpxchg8b "__percpu_arg(1) \ + CC_SET(z) \ + : CC_OUT(z) (__ret), "+m" (pcp1), "+m" (pcp2), "+a" (__o1), "+d" (__o2) \ + : "b" (__n1), "c" (__n2)); \ __ret; \ }) diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 685ffe8a0eaf..24c6cf5f16b7 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -19,6 +19,9 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd); +#endif *pmdp = pmd; } @@ -58,6 +61,9 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp) #ifdef CONFIG_SMP static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0)); +#endif return __pmd(xchg((pmdval_t *)xp, 0)); } #else @@ -67,6 +73,9 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #ifdef CONFIG_SMP static inline pud_t native_pudp_get_and_clear(pud_t *xp) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0)); +#endif return __pud(xchg((pudval_t *)xp, 0)); } #else @@ -95,4 +104,21 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi #define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low }) #define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val }) +/* No inverted PFNs on 2 level page tables */ + +static inline u64 protnone_mask(u64 val) +{ + return 0; +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) +{ + return val; +} + +static inline bool __pte_needs_invert(u64 val) +{ + return false; +} + #endif /* _ASM_X86_PGTABLE_2LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h index f982ef808e7e..6deb6cd236e3 100644 --- a/arch/x86/include/asm/pgtable-2level_types.h +++ b/arch/x86/include/asm/pgtable-2level_types.h @@ -35,4 +35,7 @@ typedef union { #define PTRS_PER_PTE 1024 +/* This covers all VMSPLIT_* and VMSPLIT_*_OPT variants */ +#define PGD_KERNEL_START (CONFIG_PAGE_OFFSET >> PGDIR_SHIFT) + #endif /* _ASM_X86_PGTABLE_2LEVEL_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index f24df59c40b2..a564084c6141 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -98,6 +98,9 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) static inline void native_set_pud(pud_t *pudp, pud_t pud) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd); +#endif set_64bit((unsigned long long *)(pudp), native_pud_val(pud)); } @@ -229,6 +232,10 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) { union split_pud res, *orig = (union split_pud *)pudp; +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pti_set_user_pgtbl(&pudp->p4d.pgd, __pgd(0)); +#endif + /* xchg acts as a barrier before setting of the high bits */ res.pud_low = xchg(&orig->pud_low, 0); res.pud_high = orig->pud_high; @@ -241,12 +248,43 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) #endif /* Encode and de-code a swap entry */ +#define SWP_TYPE_BITS 5 + +#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) + +/* We always extract/encode the offset by shifting it all the way up, and then down again */ +#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS) + #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5) #define __swp_type(x) (((x).val) & 0x1f) #define __swp_offset(x) ((x).val >> 5) #define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << 5}) -#define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high }) -#define __swp_entry_to_pte(x) ((pte_t){ { .pte_high = (x).val } }) + +/* + * Normally, __swp_entry() converts from arch-independent swp_entry_t to + * arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result + * to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the + * whole 64 bits. Thus, we shift the "real" arch-dependent conversion to + * __swp_entry_to_pte() through the following helper macro based on 64bit + * __swp_entry(). + */ +#define __swp_pteval_entry(type, offset) ((pteval_t) { \ + (~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ + | ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) }) + +#define __swp_entry_to_pte(x) ((pte_t){ .pte = \ + __swp_pteval_entry(__swp_type(x), __swp_offset(x)) }) +/* + * Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent + * swp_entry_t, but also has to convert it from 64bit to the 32bit + * intermediate representation, using the following macros based on 64bit + * __swp_type() and __swp_offset(). + */ +#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS))) +#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)) + +#define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \ + __pteval_swp_offset(pte))) #define gup_get_pte gup_get_pte /* @@ -295,4 +333,6 @@ static inline pte_t gup_get_pte(pte_t *ptep) return pte; } +#include <asm/pgtable-invert.h> + #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h index 6a59a6d0cc50..858358a82b14 100644 --- a/arch/x86/include/asm/pgtable-3level_types.h +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -21,9 +21,10 @@ typedef union { #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_PARAVIRT -#define SHARED_KERNEL_PMD (pv_info.shared_kernel_pmd) +#define SHARED_KERNEL_PMD ((!static_cpu_has(X86_FEATURE_PTI) && \ + (pv_info.shared_kernel_pmd))) #else -#define SHARED_KERNEL_PMD 1 +#define SHARED_KERNEL_PMD (!static_cpu_has(X86_FEATURE_PTI)) #endif /* @@ -45,5 +46,6 @@ typedef union { #define PTRS_PER_PTE 512 #define MAX_POSSIBLE_PHYSMEM_BITS 36 +#define PGD_KERNEL_START (CONFIG_PAGE_OFFSET >> PGDIR_SHIFT) #endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h new file mode 100644 index 000000000000..a0c1525f1b6f --- /dev/null +++ b/arch/x86/include/asm/pgtable-invert.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_PGTABLE_INVERT_H +#define _ASM_PGTABLE_INVERT_H 1 + +#ifndef __ASSEMBLY__ + +/* + * A clear pte value is special, and doesn't get inverted. + * + * Note that even users that only pass a pgprot_t (rather + * than a full pte) won't trigger the special zero case, + * because even PAGE_NONE has _PAGE_PROTNONE | _PAGE_ACCESSED + * set. So the all zero case really is limited to just the + * cleared page table entry case. + */ +static inline bool __pte_needs_invert(u64 val) +{ + return val && !(val & _PAGE_PRESENT); +} + +/* Get a mask to xor with the page table entry to get the correct pfn. */ +static inline u64 protnone_mask(u64 val) +{ + return __pte_needs_invert(val) ? ~0ull : 0; +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) +{ + /* + * When a PTE transitions from NONE to !NONE or vice-versa + * invert the PFN part to stop speculation. + * pte_pfn undoes this when needed. + */ + if (__pte_needs_invert(oldval) != __pte_needs_invert(val)) + val = (val & ~mask) | (~val & mask); + return val; +} + +#endif /* __ASSEMBLY__ */ + +#endif diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5715647fc4fe..e4ffa565a69f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -30,11 +30,14 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user); void ptdump_walk_pgd_level_checkwx(void); +void ptdump_walk_user_pgd_level_checkwx(void); #ifdef CONFIG_DEBUG_WX -#define debug_checkwx() ptdump_walk_pgd_level_checkwx() +#define debug_checkwx() ptdump_walk_pgd_level_checkwx() +#define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() #else -#define debug_checkwx() do { } while (0) +#define debug_checkwx() do { } while (0) +#define debug_checkwx_user() do { } while (0) #endif /* @@ -185,19 +188,29 @@ static inline int pte_special(pte_t pte) return pte_flags(pte) & _PAGE_SPECIAL; } +/* Entries that were set to PROT_NONE are inverted */ + +static inline u64 protnone_mask(u64 val); + static inline unsigned long pte_pfn(pte_t pte) { - return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT; + phys_addr_t pfn = pte_val(pte); + pfn ^= protnone_mask(pfn); + return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline unsigned long pmd_pfn(pmd_t pmd) { - return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; + phys_addr_t pfn = pmd_val(pmd); + pfn ^= protnone_mask(pfn); + return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } static inline unsigned long pud_pfn(pud_t pud) { - return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT; + phys_addr_t pfn = pud_val(pud); + pfn ^= protnone_mask(pfn); + return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } static inline unsigned long p4d_pfn(p4d_t p4d) @@ -400,11 +413,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_RW); } -static inline pmd_t pmd_mknotpresent(pmd_t pmd) -{ - return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE); -} - static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); @@ -459,11 +467,6 @@ static inline pud_t pud_mkwrite(pud_t pud) return pud_set_flags(pud, _PAGE_RW); } -static inline pud_t pud_mknotpresent(pud_t pud) -{ - return pud_clear_flags(pud, _PAGE_PRESENT | _PAGE_PROTNONE); -} - #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { @@ -545,25 +548,45 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot) static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { - return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) | - check_pgprot(pgprot)); + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PTE_PFN_MASK; + return __pte(pfn | check_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { - return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) | - check_pgprot(pgprot)); + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PMD_PAGE_MASK; + return __pmd(pfn | check_pgprot(pgprot)); } static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) { - return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) | - check_pgprot(pgprot)); + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PUD_PAGE_MASK; + return __pud(pfn | check_pgprot(pgprot)); +} + +static inline pmd_t pmd_mknotpresent(pmd_t pmd) +{ + return pfn_pmd(pmd_pfn(pmd), + __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); +} + +static inline pud_t pud_mknotpresent(pud_t pud) +{ + return pfn_pud(pud_pfn(pud), + __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - pteval_t val = pte_val(pte); + pteval_t val = pte_val(pte), oldval = val; /* * Chop off the NX bit (if present), and add the NX portion of @@ -571,17 +594,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) */ val &= _PAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; - + val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); return __pte(val); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmdval_t val = pmd_val(pmd); + pmdval_t val = pmd_val(pmd), oldval = val; val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; - + val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); return __pmd(val); } @@ -640,8 +663,31 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); + +/* + * Take a PGD location (pgdp) and a pgd value that needs to be set there. + * Populates the user and returns the resulting PGD that must be set in + * the kernel copy of the page tables. + */ +static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) +{ + if (!static_cpu_has(X86_FEATURE_PTI)) + return pgd; + return __pti_set_user_pgtbl(pgdp, pgd); +} +#else /* CONFIG_PAGE_TABLE_ISOLATION */ +static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) +{ + return pgd; +} +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ + #endif /* __ASSEMBLY__ */ + #ifdef CONFIG_X86_32 # include <asm/pgtable_32.h> #else @@ -1154,6 +1200,70 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, } } #endif +/* + * Page table pages are page-aligned. The lower half of the top + * level is used for userspace and the top half for the kernel. + * + * Returns true for parts of the PGD that map userspace and + * false for the parts that map the kernel. + */ +static inline bool pgdp_maps_userspace(void *__ptr) +{ + unsigned long ptr = (unsigned long)__ptr; + + return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); +} + +static inline int pgd_large(pgd_t pgd) { return 0; } + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages + * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and + * the user one is in the last 4k. To switch between them, you + * just need to flip the 12th bit in their addresses. + */ +#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT + +/* + * This generates better code than the inline assembly in + * __set_bit(). + */ +static inline void *ptr_set_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr |= BIT(bit); + return (void *)__ptr; +} +static inline void *ptr_clear_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr &= ~BIT(bit); + return (void *)__ptr; +} + +static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) +{ + return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) +{ + return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) +{ + return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) +{ + return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); @@ -1320,6 +1430,14 @@ static inline bool pud_access_permitted(pud_t pud, bool write) return __pte_access_permitted(pud_val(pud), write); } +#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 +extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); + +static inline bool arch_has_pfn_modify_check(void) +{ + return boot_cpu_has_bug(X86_BUG_L1TF); +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 88a056b01db4..b3ec519e3982 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -34,8 +34,6 @@ static inline void check_pgt_cache(void) { } void paging_init(void); void sync_initial_page_table(void); -static inline int pgd_large(pgd_t pgd) { return 0; } - /* * Define this if things work differently on an i386 and an i486: * it will (on an i486) warn about kernel memory accesses that are diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index d9a001a4a872..b0bc0fff5f1f 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -50,13 +50,18 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \ & PMD_MASK) -#define PKMAP_BASE \ +#define LDT_BASE_ADDR \ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) +#define LDT_END_ADDR (LDT_BASE_ADDR + PMD_SIZE) + +#define PKMAP_BASE \ + ((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK) + #ifdef CONFIG_HIGHMEM # define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) #else -# define VMALLOC_END (CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE) +# define VMALLOC_END (LDT_BASE_ADDR - 2 * PAGE_SIZE) #endif #define MODULES_VADDR VMALLOC_START diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 3c5385f9a88f..f773d5e6c8cc 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -132,90 +132,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp) #endif } -#ifdef CONFIG_PAGE_TABLE_ISOLATION -/* - * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages - * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and - * the user one is in the last 4k. To switch between them, you - * just need to flip the 12th bit in their addresses. - */ -#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT - -/* - * This generates better code than the inline assembly in - * __set_bit(). - */ -static inline void *ptr_set_bit(void *ptr, int bit) -{ - unsigned long __ptr = (unsigned long)ptr; - - __ptr |= BIT(bit); - return (void *)__ptr; -} -static inline void *ptr_clear_bit(void *ptr, int bit) -{ - unsigned long __ptr = (unsigned long)ptr; - - __ptr &= ~BIT(bit); - return (void *)__ptr; -} - -static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) -{ - return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); -} - -static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) -{ - return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); -} - -static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) -{ - return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); -} - -static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) -{ - return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); -} -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ - -/* - * Page table pages are page-aligned. The lower half of the top - * level is used for userspace and the top half for the kernel. - * - * Returns true for parts of the PGD that map userspace and - * false for the parts that map the kernel. - */ -static inline bool pgdp_maps_userspace(void *__ptr) -{ - unsigned long ptr = (unsigned long)__ptr; - - return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2); -} - -#ifdef CONFIG_PAGE_TABLE_ISOLATION -pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd); - -/* - * Take a PGD location (pgdp) and a pgd value that needs to be set there. - * Populates the user and returns the resulting PGD that must be set in - * the kernel copy of the page tables. - */ -static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) -{ - if (!static_cpu_has(X86_FEATURE_PTI)) - return pgd; - return __pti_set_user_pgd(pgdp, pgd); -} -#else -static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) -{ - return pgd; -} -#endif - static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; @@ -226,7 +142,7 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) } pgd = native_make_pgd(native_p4d_val(p4d)); - pgd = pti_set_user_pgd((pgd_t *)p4dp, pgd); + pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); *p4dp = native_make_p4d(native_pgd_val(pgd)); } @@ -237,7 +153,7 @@ static inline void native_p4d_clear(p4d_t *p4d) static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pti_set_user_pgd(pgdp, pgd); + *pgdp = pti_set_user_pgtbl(pgdp, pgd); } static inline void native_pgd_clear(pgd_t *pgd) @@ -255,7 +171,6 @@ extern void sync_global_pgds(unsigned long start, unsigned long end); /* * Level 4 access. */ -static inline int pgd_large(pgd_t pgd) { return 0; } #define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE) /* PUD - Level3 access */ @@ -273,7 +188,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names - * | OFFSET (14->63) | TYPE (9-13) |0|0|X|X| X| X|X|SD|0| <- swp entry + * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|X|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above @@ -286,20 +201,34 @@ static inline int pgd_large(pgd_t pgd) { return 0; } * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. + * + * The offset is inverted by a binary not operation to make the high + * physical bits set. */ -#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) -#define SWP_TYPE_BITS 5 -/* Place the offset above the type: */ -#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS) +#define SWP_TYPE_BITS 5 + +#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) + +/* We always extract/encode the offset by shifting it all the way up, and then down again */ +#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) -#define __swp_type(x) (((x).val >> (SWP_TYPE_FIRST_BIT)) \ - & ((1U << SWP_TYPE_BITS) - 1)) -#define __swp_offset(x) ((x).val >> SWP_OFFSET_FIRST_BIT) -#define __swp_entry(type, offset) ((swp_entry_t) { \ - ((type) << (SWP_TYPE_FIRST_BIT)) \ - | ((offset) << SWP_OFFSET_FIRST_BIT) }) +/* Extract the high bits for type */ +#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) + +/* Shift up (to get rid of type), then down to get value */ +#define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) + +/* + * Shift the offset up "too far" by TYPE bits, then down again + * The offset is inverted by a binary not operation to make the high + * physical bits set. + */ +#define __swp_entry(type, offset) ((swp_entry_t) { \ + (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ + | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) + #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) #define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val }) @@ -343,5 +272,7 @@ static inline bool gup_fast_permitted(unsigned long start, int nr_pages, return true; } +#include <asm/pgtable-invert.h> + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 054765ab2da2..04edd2d58211 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -115,6 +115,7 @@ extern unsigned int ptrs_per_p4d; #define LDT_PGD_ENTRY_L5 -112UL #define LDT_PGD_ENTRY (pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) +#define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE) #define __VMALLOC_BASE_L4 0xffffc90000000000UL #define __VMALLOC_BASE_L5 0xffa0000000000000UL @@ -153,4 +154,6 @@ extern unsigned int ptrs_per_p4d; #define EARLY_DYNAMIC_PAGE_TABLES 64 +#define PGD_KERNEL_START ((PAGE_SIZE / 2) / sizeof(pgd_t)) + #endif /* _ASM_X86_PGTABLE_64_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 99fff853c944..b64acb08a62b 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -50,6 +50,7 @@ #define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) #define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) #define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2) +#define _PAGE_SOFTW3 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW3) #define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) @@ -266,14 +267,37 @@ typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; typedef struct { pgdval_t pgd; } pgd_t; +#ifdef CONFIG_X86_PAE + +/* + * PHYSICAL_PAGE_MASK might be non-constant when SME is compiled in, so we can't + * use it here. + */ + +#define PGD_PAE_PAGE_MASK ((signed long)PAGE_MASK) +#define PGD_PAE_PHYS_MASK (((1ULL << __PHYSICAL_MASK_SHIFT)-1) & PGD_PAE_PAGE_MASK) + +/* + * PAE allows Base Address, P, PWT, PCD and AVL bits to be set in PGD entries. + * All other bits are Reserved MBZ + */ +#define PGD_ALLOWED_BITS (PGD_PAE_PHYS_MASK | _PAGE_PRESENT | \ + _PAGE_PWT | _PAGE_PCD | \ + _PAGE_SOFTW1 | _PAGE_SOFTW2 | _PAGE_SOFTW3) + +#else +/* No need to mask any bits for !PAE */ +#define PGD_ALLOWED_BITS (~0ULL) +#endif + static inline pgd_t native_make_pgd(pgdval_t val) { - return (pgd_t) { val }; + return (pgd_t) { val & PGD_ALLOWED_BITS }; } static inline pgdval_t native_pgd_val(pgd_t pgd) { - return pgd.pgd; + return pgd.pgd & PGD_ALLOWED_BITS; } static inline pgdval_t pgd_flags(pgd_t pgd) diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 625a52a5594f..02c2cbda4a74 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -39,10 +39,6 @@ #define CR3_PCID_MASK 0xFFFull #define CR3_NOFLUSH BIT_ULL(63) -#ifdef CONFIG_PAGE_TABLE_ISOLATION -# define X86_CR3_PTI_PCID_USER_BIT 11 -#endif - #else /* * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save @@ -53,4 +49,8 @@ #define CR3_NOFLUSH 0 #endif +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define X86_CR3_PTI_PCID_USER_BIT 11 +#endif + #endif /* _ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index cfd29ee8c3da..c24297268ebc 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -181,6 +181,11 @@ extern const struct seq_operations cpuinfo_op; extern void cpu_detect(struct cpuinfo_x86 *c); +static inline unsigned long long l1tf_pfn_limit(void) +{ + return BIT_ULL(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT); +} + extern void early_cpu_init(void); extern void identify_boot_cpu(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); @@ -966,6 +971,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) extern unsigned long arch_align_stack(unsigned long sp); extern void free_init_pages(char *what, unsigned long begin, unsigned long end); +extern void free_kernel_image_pages(void *begin, void *end); void default_idle(void); #ifdef CONFIG_XEN @@ -977,4 +983,16 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); void microcode_check(void); + +enum l1tf_mitigations { + L1TF_MITIGATION_OFF, + L1TF_MITIGATION_FLUSH_NOWARN, + L1TF_MITIGATION_FLUSH, + L1TF_MITIGATION_FLUSH_NOSMT, + L1TF_MITIGATION_FULL, + L1TF_MITIGATION_FULL_FORCE +}; + +extern enum l1tf_mitigations l1tf_mitigation; + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h index 38a17f1d5c9d..5df09a0b80b8 100644 --- a/arch/x86/include/asm/pti.h +++ b/arch/x86/include/asm/pti.h @@ -6,10 +6,9 @@ #ifdef CONFIG_PAGE_TABLE_ISOLATION extern void pti_init(void); extern void pti_check_boottime_disable(void); -extern void pti_clone_kernel_text(void); +extern void pti_finalize(void); #else static inline void pti_check_boottime_disable(void) { } -static inline void pti_clone_kernel_text(void) { } #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 4cf11d88d3b3..19b90521954c 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -5,6 +5,7 @@ * PaX/grsecurity. */ #include <linux/refcount.h> +#include <asm/bug.h> /* * This is the first portion of the refcount error handling, which lives in diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 5c019d23d06b..4a911a382ade 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -7,6 +7,7 @@ extern char __brk_base[], __brk_limit[]; extern struct exception_table_entry __stop___ex_table[]; +extern char __end_rodata_aligned[]; #if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index bd090367236c..07a25753e85c 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -46,6 +46,7 @@ int set_memory_np(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); +int set_memory_np_noalias(unsigned long addr, int numpages); int set_memory_array_uc(unsigned long *addr, int addrinarray); int set_memory_array_wc(unsigned long *addr, int addrinarray); @@ -88,4 +89,46 @@ extern int kernel_set_to_readonly; void set_kernel_text_rw(void); void set_kernel_text_ro(void); +#ifdef CONFIG_X86_64 +static inline int set_mce_nospec(unsigned long pfn) +{ + unsigned long decoy_addr; + int rc; + + /* + * Mark the linear address as UC to make sure we don't log more + * errors because of speculative access to the page. + * We would like to just call: + * set_memory_uc((unsigned long)pfn_to_kaddr(pfn), 1); + * but doing that would radically increase the odds of a + * speculative access to the poison page because we'd have + * the virtual address of the kernel 1:1 mapping sitting + * around in registers. + * Instead we get tricky. We create a non-canonical address + * that looks just like the one we want, but has bit 63 flipped. + * This relies on set_memory_uc() properly sanitizing any __pa() + * results with __PHYSICAL_MASK or PTE_PFN_MASK. + */ + decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); + + rc = set_memory_uc(decoy_addr, 1); + if (rc) + pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); + return rc; +} +#define set_mce_nospec set_mce_nospec + +/* Restore full speculative operation to the pfn. */ +static inline int clear_mce_nospec(unsigned long pfn) +{ + return set_memory_wb((unsigned long) pfn_to_kaddr(pfn), 1); +} +#define clear_mce_nospec clear_mce_nospec +#else +/* + * Few people would run a 32-bit kernel on a machine that supports + * recoverable errors because they have too much memory to boot 32-bit. + */ +#endif + #endif /* _ASM_X86_SET_MEMORY_H */ diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index eb5f7999a893..36bd243843d6 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -87,15 +87,25 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread) #endif /* This is used when switching tasks or entering/exiting vm86 mode. */ -static inline void update_sp0(struct task_struct *task) +static inline void update_task_stack(struct task_struct *task) { - /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */ + /* sp0 always points to the entry trampoline stack, which is constant: */ #ifdef CONFIG_X86_32 - load_sp0(task->thread.sp0); + if (static_cpu_has(X86_FEATURE_XENPV)) + load_sp0(task->thread.sp0); + else + this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0); #else + /* + * x86-64 updates x86_tss.sp1 via cpu_current_top_of_stack. That + * doesn't work on x86-32 because sp1 and + * cpu_current_top_of_stack have different values (because of + * the non-zero stack-padding on 32bit). + */ if (static_cpu_has(X86_FEATURE_XENPV)) load_sp0(task_top_of_stack(task)); #endif + } #endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 2ecd34e2d46c..e85ff65c43c3 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -37,5 +37,6 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len); extern void *text_poke(void *addr, const void *opcode, size_t len); extern int poke_int3_handler(struct pt_regs *regs); extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); +extern int after_bootmem; #endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6690cd3fc8b1..29c9da6c62fc 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -552,6 +552,9 @@ extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); #ifndef CONFIG_PARAVIRT #define flush_tlb_others(mask, info) \ native_flush_tlb_others(mask, info) + +#define paravirt_tlb_remove_table(tlb, page) \ + tlb_remove_page(tlb, (void *)(page)) #endif #endif /* _ASM_X86_TLBFLUSH_H */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index c1d2a9892352..453cf38a1c33 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -123,13 +123,17 @@ static inline int topology_max_smt_threads(void) } int topology_update_package_map(unsigned int apicid, unsigned int cpu); -extern int topology_phys_to_logical_pkg(unsigned int pkg); +int topology_phys_to_logical_pkg(unsigned int pkg); +bool topology_is_primary_thread(unsigned int cpu); +bool topology_smt_supported(void); #else #define topology_max_packages() (1) static inline int topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; } static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } static inline int topology_max_smt_threads(void) { return 1; } +static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } +static inline bool topology_smt_supported(void) { return false; } #endif static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h index 4253bca99989..2e6245a023ef 100644 --- a/arch/x86/include/asm/trace/hyperv.h +++ b/arch/x86/include/asm/trace/hyperv.h @@ -28,6 +28,35 @@ TRACE_EVENT(hyperv_mmu_flush_tlb_others, __entry->addr, __entry->end) ); +TRACE_EVENT(hyperv_nested_flush_guest_mapping, + TP_PROTO(u64 as, int ret), + TP_ARGS(as, ret), + + TP_STRUCT__entry( + __field(u64, as) + __field(int, ret) + ), + TP_fast_assign(__entry->as = as; + __entry->ret = ret; + ), + TP_printk("address space %llx ret %d", __entry->as, __entry->ret) + ); + +TRACE_EVENT(hyperv_send_ipi_mask, + TP_PROTO(const struct cpumask *cpus, + int vector), + TP_ARGS(cpus, vector), + TP_STRUCT__entry( + __field(unsigned int, ncpus) + __field(int, vector) + ), + TP_fast_assign(__entry->ncpus = cpumask_weight(cpus); + __entry->vector = vector; + ), + TP_printk("ncpus %d vector %x", + __entry->ncpus, __entry->vector) + ); + #endif /* CONFIG_HYPERV */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 2701d221583a..eb5bbfeccb66 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -33,13 +33,13 @@ static inline cycles_t get_cycles(void) extern struct system_counterval_t convert_art_to_tsc(u64 art); extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns); -extern void tsc_early_delay_calibrate(void); +extern void tsc_early_init(void); extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); extern void mark_tsc_async_resets(char *reason); -extern unsigned long native_calibrate_cpu(void); +extern unsigned long native_calibrate_cpu_early(void); extern unsigned long native_calibrate_tsc(void); extern unsigned long long native_sched_clock_from_tsc(u64 tsc); diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index bae46fc6b9de..0bcdb1279361 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -26,7 +26,7 @@ * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL +.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0 #ifdef CONFIG_STACK_VALIDATION .Lunwind_hint_ip_\@: .pushsection .discard.unwind_hints @@ -35,12 +35,14 @@ .short \sp_offset .byte \sp_reg .byte \type + .byte \end + .balign 4 .popsection #endif .endm .macro UNWIND_HINT_EMPTY - UNWIND_HINT sp_reg=ORC_REG_UNDEFINED + UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1 .endm .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0 @@ -86,19 +88,21 @@ #else /* !__ASSEMBLY__ */ -#define UNWIND_HINT(sp_reg, sp_offset, type) \ +#define UNWIND_HINT(sp_reg, sp_offset, type, end) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ ".long 987b - .\n\t" \ - ".short " __stringify(sp_offset) "\n\t" \ + ".short " __stringify(sp_offset) "\n\t" \ ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ + ".byte " __stringify(end) "\n\t" \ + ".balign 4 \n\t" \ ".popsection\n\t" -#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE) +#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0) -#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE) +#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 6aa8499e1f62..9527ba5d62da 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -74,6 +74,7 @@ #define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000 #define SECONDARY_EXEC_ENABLE_VMFUNC 0x00002000 #define SECONDARY_EXEC_SHADOW_VMCS 0x00004000 +#define SECONDARY_EXEC_ENCLS_EXITING 0x00008000 #define SECONDARY_EXEC_RDSEED_EXITING 0x00010000 #define SECONDARY_EXEC_ENABLE_PML 0x00020000 #define SECONDARY_EXEC_XSAVES 0x00100000 @@ -213,6 +214,8 @@ enum vmcs_field { VMWRITE_BITMAP_HIGH = 0x00002029, XSS_EXIT_BITMAP = 0x0000202C, XSS_EXIT_BITMAP_HIGH = 0x0000202D, + ENCLS_EXITING_BITMAP = 0x0000202E, + ENCLS_EXITING_BITMAP_HIGH = 0x0000202F, TSC_MULTIPLIER = 0x00002032, TSC_MULTIPLIER_HIGH = 0x00002033, GUEST_PHYSICAL_ADDRESS = 0x00002400, @@ -576,4 +579,15 @@ enum vm_instruction_error_number { VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID = 28, }; +enum vmx_l1d_flush_state { + VMENTER_L1D_FLUSH_AUTO, + VMENTER_L1D_FLUSH_NEVER, + VMENTER_L1D_FLUSH_COND, + VMENTER_L1D_FLUSH_ALWAYS, + VMENTER_L1D_FLUSH_EPT_DISABLED, + VMENTER_L1D_FLUSH_NOT_REQUIRED, +}; + +extern enum vmx_l1d_flush_state l1tf_vmx_mitigation; + #endif diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index bfd882617613..ef05bea7010d 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -197,36 +197,38 @@ extern struct { char _entry[32]; } hypercall_page[]; (type)__res; \ }) -#define _hypercall5(type, name, a1, a2, a3, a4, a5) \ -({ \ - __HYPERCALL_DECLS; \ - __HYPERCALL_5ARG(a1, a2, a3, a4, a5); \ - asm volatile (__HYPERCALL \ - : __HYPERCALL_5PARAM \ - : __HYPERCALL_ENTRY(name) \ - : __HYPERCALL_CLOBBER5); \ - (type)__res; \ -}) - static inline long -privcmd_call(unsigned call, - unsigned long a1, unsigned long a2, - unsigned long a3, unsigned long a4, - unsigned long a5) +xen_single_call(unsigned int call, + unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, + unsigned long a5) { __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - stac(); asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM : [thunk_target] "a" (&hypercall_page[call]) : __HYPERCALL_CLOBBER5); - clac(); return (long)__res; } +static inline long +privcmd_call(unsigned int call, + unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, + unsigned long a5) +{ + long res; + + stac(); + res = xen_single_call(call, a1, a2, a3, a4, a5); + clac(); + + return res; +} + static inline int HYPERVISOR_set_trap_table(struct trap_info *table) { @@ -254,47 +256,12 @@ HYPERVISOR_set_gdt(unsigned long *frame_list, int entries) } static inline int -HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp) -{ - return _hypercall2(int, stack_switch, ss, esp); -} - -#ifdef CONFIG_X86_32 -static inline int -HYPERVISOR_set_callbacks(unsigned long event_selector, - unsigned long event_address, - unsigned long failsafe_selector, - unsigned long failsafe_address) -{ - return _hypercall4(int, set_callbacks, - event_selector, event_address, - failsafe_selector, failsafe_address); -} -#else /* CONFIG_X86_64 */ -static inline int -HYPERVISOR_set_callbacks(unsigned long event_address, - unsigned long failsafe_address, - unsigned long syscall_address) -{ - return _hypercall3(int, set_callbacks, - event_address, failsafe_address, - syscall_address); -} -#endif /* CONFIG_X86_{32,64} */ - -static inline int HYPERVISOR_callback_op(int cmd, void *arg) { return _hypercall2(int, callback_op, cmd, arg); } static inline int -HYPERVISOR_fpu_taskswitch(int set) -{ - return _hypercall1(int, fpu_taskswitch, set); -} - -static inline int HYPERVISOR_sched_op(int cmd, void *arg) { return _hypercall2(int, sched_op, cmd, arg); @@ -406,19 +373,6 @@ HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count) } static inline int -HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, pte_t new_val, - unsigned long flags, domid_t domid) -{ - if (sizeof(new_val) == sizeof(long)) - return _hypercall4(int, update_va_mapping_otherdomain, va, - new_val.pte, flags, domid); - else - return _hypercall5(int, update_va_mapping_otherdomain, va, - new_val.pte, new_val.pte >> 32, - flags, domid); -} - -static inline int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type) { return _hypercall2(int, vm_assist, cmd, type); @@ -452,12 +406,6 @@ HYPERVISOR_suspend(unsigned long start_info_mfn) return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn); } -static inline int -HYPERVISOR_nmi_op(unsigned long op, unsigned long arg) -{ - return _hypercall2(int, nmi_op, op, arg); -} - static inline unsigned long __must_check HYPERVISOR_hvm_op(int op, void *arg) { @@ -516,39 +464,6 @@ MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, } static inline void -MULTI_grant_table_op(struct multicall_entry *mcl, unsigned int cmd, - void *uop, unsigned int count) -{ - mcl->op = __HYPERVISOR_grant_table_op; - mcl->args[0] = cmd; - mcl->args[1] = (unsigned long)uop; - mcl->args[2] = count; - - trace_xen_mc_entry(mcl, 3); -} - -static inline void -MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long va, - pte_t new_val, unsigned long flags, - domid_t domid) -{ - mcl->op = __HYPERVISOR_update_va_mapping_otherdomain; - mcl->args[0] = va; - if (sizeof(new_val) == sizeof(long)) { - mcl->args[1] = new_val.pte; - mcl->args[2] = flags; - mcl->args[3] = domid; - } else { - mcl->args[1] = new_val.pte; - mcl->args[2] = new_val.pte >> 32; - mcl->args[3] = flags; - mcl->args[4] = domid; - } - - trace_xen_mc_entry(mcl, sizeof(new_val) == sizeof(long) ? 4 : 5); -} - -static inline void MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, struct desc_struct desc) { @@ -569,16 +484,6 @@ MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, } static inline void -MULTI_memory_op(struct multicall_entry *mcl, unsigned int cmd, void *arg) -{ - mcl->op = __HYPERVISOR_memory_op; - mcl->args[0] = cmd; - mcl->args[1] = (unsigned long)arg; - - trace_xen_mc_entry(mcl, 2); -} - -static inline void MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, int count, int *success_count, domid_t domid) { @@ -605,16 +510,6 @@ MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count, } static inline void -MULTI_set_gdt(struct multicall_entry *mcl, unsigned long *frames, int entries) -{ - mcl->op = __HYPERVISOR_set_gdt; - mcl->args[0] = (unsigned long)frames; - mcl->args[1] = entries; - - trace_xen_mc_entry(mcl, 2); -} - -static inline void MULTI_stack_switch(struct multicall_entry *mcl, unsigned long ss, unsigned long esp) { diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index c535c2fdea13..86299efa804a 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -378,4 +378,41 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_STATE_NESTED_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_RUN_PENDING 0x00000002 + +#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_SMM_VMXON 0x00000002 + +struct kvm_vmx_nested_state { + __u64 vmxon_pa; + __u64 vmcs_pa; + + struct { + __u16 flags; + } smm; +}; + +/* for KVM_CAP_NESTED_STATE */ +struct kvm_nested_state { + /* KVM_STATE_* flags */ + __u16 flags; + + /* 0 for VMX, 1 for SVM. */ + __u16 format; + + /* 128 for SVM, 128 + VMCS size for VMX. */ + __u32 size; + + union { + /* VMXON, VMCS */ + struct kvm_vmx_nested_state vmx; + + /* Pad the header to 128 bytes. */ + __u8 pad[120]; + }; + + __u8 data[0]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 0ede697c3961..19980ec1a316 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -28,6 +28,7 @@ #define KVM_FEATURE_PV_UNHALT 7 #define KVM_FEATURE_PV_TLB_FLUSH 9 #define KVM_FEATURE_ASYNC_PF_VMEXIT 10 +#define KVM_FEATURE_PV_SEND_IPI 11 #define KVM_HINTS_REALTIME 0 |