diff options
Diffstat (limited to 'arch/x86')
30 files changed, 276 insertions, 161 deletions
diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 7854685c5f25..bafbd905e6e7 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -286,10 +286,6 @@ vdso_install: archprepare: checkbin checkbin: -ifndef CONFIG_CC_HAS_ASM_GOTO - @echo Compiler lacks asm-goto support. - @exit 1 -endif ifdef CONFIG_RETPOLINE ifeq ($(RETPOLINE_CFLAGS),) @echo "You are building kernel with non-retpoline compiler." >&2 diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config index d9fc7139fd46..581296255b39 100644 --- a/arch/x86/configs/xen.config +++ b/arch/x86/configs/xen.config @@ -14,7 +14,6 @@ CONFIG_CPU_FREQ=y # x86 xen specific config options CONFIG_XEN_PVH=y -CONFIG_XEN_MAX_DOMAIN_MEMORY=500 CONFIG_XEN_SAVE_RESTORE=y # CONFIG_XEN_DEBUG_FS is not set CONFIG_XEN_MCE_LOG=y diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 973c6bd17f98..0fe9de58af31 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -207,6 +207,20 @@ static __always_inline bool constant_test_bit(long nr, const volatile unsigned l (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } +static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr) +{ + bool oldbit; + + asm volatile("testb %2,%1" + CC_SET(nz) + : CC_OUT(nz) (oldbit) + : "m" (((unsigned char *)addr)[nr >> 3]), + "i" (1 << (nr & 7)) + :"memory"); + + return oldbit; +} + static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; @@ -226,6 +240,13 @@ arch_test_bit(unsigned long nr, const volatile unsigned long *addr) variable_test_bit(nr, addr); } +static __always_inline bool +arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) : + variable_test_bit(nr, addr); +} + /** * __ffs - find first set bit in word * @word: The word to search diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ea34cc31b047..1a85e1fb0922 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -155,20 +155,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) -#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO) - -/* - * Workaround for the sake of BPF compilation which utilizes kernel - * headers, but clang does not support ASM GOTO and fails the build. - */ -#ifndef __BPF_TRACING__ -#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments" -#endif - -#define static_cpu_has(bit) boot_cpu_has(bit) - -#else - /* * Static testing of CPU features. Used the same as boot_cpu_has(). It * statically patches the target code for additional performance. Use @@ -208,7 +194,6 @@ t_no: boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) -#endif #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h index 503622627400..991e31cfde94 100644 --- a/arch/x86/include/asm/extable_fixup_types.h +++ b/arch/x86/include/asm/extable_fixup_types.h @@ -64,4 +64,6 @@ #define EX_TYPE_UCOPY_LEN4 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4)) #define EX_TYPE_UCOPY_LEN8 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8)) +#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */ + #endif diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h index 689880eca9ba..9b08082a5d9f 100644 --- a/arch/x86/include/asm/ibt.h +++ b/arch/x86/include/asm/ibt.h @@ -31,6 +31,16 @@ #define __noendbr __attribute__((nocf_check)) +/* + * Create a dummy function pointer reference to prevent objtool from marking + * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by + * apply_ibt_endbr()). + */ +#define IBT_NOSEAL(fname) \ + ".pushsection .discard.ibt_endbr_noseal\n\t" \ + _ASM_PTR fname "\n\t" \ + ".popsection\n\t" + static inline __attribute_const__ u32 gen_endbr(void) { u32 endbr; @@ -84,6 +94,7 @@ extern __noendbr void ibt_restore(u64 save); #ifndef __ASSEMBLY__ #define ASM_ENDBR +#define IBT_NOSEAL(name) #define __noendbr diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e8281d64a431..2c96c43c313a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -53,7 +53,7 @@ #define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) /* memory slots that are not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 3 +#define KVM_INTERNAL_MEM_SLOTS 3 #define KVM_HALT_POLL_NS_DEFAULT 200000 @@ -1704,7 +1704,7 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) #define kvm_arch_pmi_in_guest(vcpu) \ ((vcpu) && (vcpu)->arch.handling_intr_from_guest) -void kvm_mmu_x86_module_init(void); +void __init kvm_mmu_x86_module_init(void); int kvm_mmu_vendor_module_init(void); void kvm_mmu_vendor_module_exit(void); diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 8a9eba191516..7fa611216417 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -11,7 +11,7 @@ #define __CLOBBERS_MEM(clb...) "memory", ## clb -#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CONFIG_CC_HAS_ASM_GOTO) +#ifndef __GCC_ASM_FLAG_OUTPUTS__ /* Use asm goto */ @@ -27,7 +27,7 @@ cc_label: c = true; \ c; \ }) -#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */ +#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) */ /* Use flags output or a set instruction */ @@ -40,7 +40,7 @@ cc_label: c = true; \ c; \ }) -#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */ +#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) */ #define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \ __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h index 8338b0432b50..46b4f1f7f354 100644 --- a/arch/x86/include/asm/word-at-a-time.h +++ b/arch/x86/include/asm/word-at-a-time.h @@ -77,58 +77,18 @@ static inline unsigned long find_zero(unsigned long mask) * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ -#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT - static inline unsigned long load_unaligned_zeropad(const void *addr) { - unsigned long offset, data; unsigned long ret; - asm_volatile_goto( + asm volatile( "1: mov %[mem], %[ret]\n" - - _ASM_EXTABLE(1b, %l[do_exception]) - - : [ret] "=r" (ret) - : [mem] "m" (*(unsigned long *)addr) - : : do_exception); - - return ret; - -do_exception: - offset = (unsigned long)addr & (sizeof(long) - 1); - addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1)); - data = *(unsigned long *)addr; - ret = data >> offset * 8; - - return ret; -} - -#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ - -static inline unsigned long load_unaligned_zeropad(const void *addr) -{ - unsigned long offset, data; - unsigned long ret, err = 0; - - asm( "1: mov %[mem], %[ret]\n" "2:\n" - - _ASM_EXTABLE_FAULT(1b, 2b) - - : [ret] "=&r" (ret), "+a" (err) + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD) + : [ret] "=r" (ret) : [mem] "m" (*(unsigned long *)addr)); - if (unlikely(err)) { - offset = (unsigned long)addr & (sizeof(long) - 1); - addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1)); - data = *(unsigned long *)addr; - ret = data >> offset * 8; - } - return ret; } -#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ - #endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h index 78e667a31d6c..6daa9b0c8d11 100644 --- a/arch/x86/include/asm/xen/cpuid.h +++ b/arch/x86/include/asm/xen/cpuid.h @@ -107,6 +107,8 @@ * ID field from 8 to 15 bits, allowing to target APIC IDs up 32768. */ #define XEN_HVM_CPUID_EXT_DEST_ID (1u << 5) +/* Per-vCPU event channel upcalls */ +#define XEN_HVM_CPUID_UPCALL_VECTOR (1u << 6) /* * Leaf 6 (0x40000x05) diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h index 068d9b067c83..62bdceb594f1 100644 --- a/arch/x86/include/asm/xen/events.h +++ b/arch/x86/include/asm/xen/events.h @@ -23,7 +23,7 @@ static inline int xen_irqs_disabled(struct pt_regs *regs) /* No need for a barrier -- XCHG is a barrier on x86. */ #define xchg_xen_ulong(ptr, val) xchg((ptr), (val)) -extern int xen_have_vector_callback; +extern bool xen_have_vector_callback; /* * Events delivered via platform PCI interrupts are always @@ -34,4 +34,5 @@ static inline bool xen_support_evtchn_rebind(void) return (!xen_hvm_domain() || xen_have_vector_callback); } +extern bool xen_percpu_upcall; #endif /* _ASM_X86_XEN_EVENTS_H */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 9f7e751b91df..510d85261132 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -152,7 +152,7 @@ void __init check_bugs(void) /* * spectre_v2_user_select_mitigation() relies on the state set by * retbleed_select_mitigation(); specifically the STIBP selection is - * forced for UNRET. + * forced for UNRET or IBPB. */ spectre_v2_user_select_mitigation(); ssb_select_mitigation(); @@ -1179,7 +1179,8 @@ spectre_v2_user_select_mitigation(void) boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) mode = SPECTRE_V2_USER_STRICT_PREFERRED; - if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET) { + if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || + retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { if (mode != SPECTRE_V2_USER_STRICT && mode != SPECTRE_V2_USER_STRICT_PREFERRED) pr_info("Selecting STIBP always-on mode to complement retbleed mitigation\n"); @@ -2360,10 +2361,11 @@ static ssize_t srbds_show_state(char *buf) static ssize_t retbleed_show_state(char *buf) { - if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET) { + if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || + retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) - return sprintf(buf, "Vulnerable: untrained return thunk on non-Zen uarch\n"); + return sprintf(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); return sprintf(buf, "%s; SMT %s\n", retbleed_strings[retbleed_mitigation], diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 047c583596bb..d5ec3a2ed5a4 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -326,7 +326,8 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); ".align " __stringify(FASTOP_SIZE) " \n\t" \ ".type " name ", @function \n\t" \ name ":\n\t" \ - ASM_ENDBR + ASM_ENDBR \ + IBT_NOSEAL(name) #define FOP_FUNC(name) \ __FOP_FUNC(#name) @@ -446,27 +447,12 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); FOP_END /* Special case for SETcc - 1 instruction per cc */ - -/* - * Depending on .config the SETcc functions look like: - * - * ENDBR [4 bytes; CONFIG_X86_KERNEL_IBT] - * SETcc %al [3 bytes] - * RET | JMP __x86_return_thunk [1,5 bytes; CONFIG_RETHUNK] - * INT3 [1 byte; CONFIG_SLS] - */ -#define SETCC_ALIGN 16 - #define FOP_SETCC(op) \ - ".align " __stringify(SETCC_ALIGN) " \n\t" \ - ".type " #op ", @function \n\t" \ - #op ": \n\t" \ - ASM_ENDBR \ + FOP_FUNC(op) \ #op " %al \n\t" \ - __FOP_RET(#op) \ - ".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t" + FOP_RET(op) -__FOP_START(setcc, SETCC_ALIGN) +FOP_START(setcc) FOP_SETCC(seto) FOP_SETCC(setno) FOP_SETCC(setc) @@ -493,7 +479,7 @@ FOP_END; /* * XXX: inoutclob user must know where the argument is being expanded. - * Relying on CONFIG_CC_HAS_ASM_GOTO would allow us to remove _fault. + * Using asm goto would allow us to remove _fault. */ #define asm_safe(insn, inoutclob...) \ ({ \ @@ -1079,7 +1065,7 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt) static __always_inline u8 test_cc(unsigned int condition, unsigned long flags) { u8 rc; - void (*fop)(void) = (void *)em_setcc + SETCC_ALIGN * (condition & 0xf); + void (*fop)(void) = (void *)em_setcc + FASTOP_SIZE * (condition & 0xf); flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; asm("push %[flags]; popf; " CALL_NOSPEC @@ -4578,6 +4564,10 @@ static const struct mode_dual mode_dual_63 = { N, I(DstReg | SrcMem32 | ModRM | Mov, em_movsxd) }; +static const struct instr_dual instr_dual_8d = { + D(DstReg | SrcMem | ModRM | NoAccess), N +}; + static const struct opcode opcode_table[256] = { /* 0x00 - 0x07 */ F6ALU(Lock, em_add), @@ -4634,7 +4624,7 @@ static const struct opcode opcode_table[256] = { I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov), I2bv(DstReg | SrcMem | ModRM | Mov, em_mov), I(DstMem | SrcNone | ModRM | Mov | PageTable, em_mov_rm_sreg), - D(ModRM | SrcMem | NoAccess | DstReg), + ID(0, &instr_dual_8d), I(ImplicitOps | SrcMem16 | ModRM, em_mov_sreg_rm), G(0, group1A), /* 0x90 - 0x97 */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e2ce3556915e..9dda989a1cf0 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2284,10 +2284,12 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) struct kvm_lapic *apic = vcpu->arch.apic; u64 val; - if (apic_x2apic_mode(apic)) - kvm_lapic_msr_read(apic, offset, &val); - else + if (apic_x2apic_mode(apic)) { + if (KVM_BUG_ON(kvm_lapic_msr_read(apic, offset, &val), vcpu->kvm)) + return; + } else { val = kvm_lapic_get_reg(apic, offset); + } /* * ICR is a single 64-bit register when x2APIC is enabled. For legacy diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index a99acec925eb..6bdaacb6faa0 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -6,6 +6,8 @@ #include "kvm_cache_regs.h" #include "cpuid.h" +extern bool __read_mostly enable_mmio_caching; + #define PT_WRITABLE_SHIFT 1 #define PT_USER_SHIFT 2 diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 06ac8c7cef67..126fa9aec64c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2914,7 +2914,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) * If addresses are being invalidated, skip prefetching to avoid * accidentally prefetching those addresses. */ - if (unlikely(vcpu->kvm->mmu_notifier_count)) + if (unlikely(vcpu->kvm->mmu_invalidate_in_progress)) return; __direct_pte_prefetch(vcpu, sp, sptep); @@ -2928,7 +2928,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) * * There are several ways to safely use this helper: * - * - Check mmu_notifier_retry_hva() after grabbing the mapping level, before + * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before * consuming it. In this case, mmu_lock doesn't need to be held during the * lookup, but it does need to be held while checking the MMU notifier. * @@ -3056,7 +3056,7 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return; /* - * mmu_notifier_retry() was successful and mmu_lock is held, so + * mmu_invalidate_retry() was successful and mmu_lock is held, so * the pmd can't be split from under us. */ fault->goal_level = fault->req_level; @@ -4164,7 +4164,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) { trace_kvm_try_async_get_page(fault->addr, fault->gfn); if (kvm_find_async_pf_gfn(vcpu, fault->gfn)) { - trace_kvm_async_pf_doublefault(fault->addr, fault->gfn); + trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return RET_PF_RETRY; } else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) { @@ -4203,7 +4203,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, return true; return fault->slot && - mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva); + mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) @@ -4227,7 +4227,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r) return r; - mmu_seq = vcpu->kvm->mmu_notifier_seq; + mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); r = kvm_faultin_pfn(vcpu, fault); @@ -6055,7 +6055,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) write_lock(&kvm->mmu_lock); - kvm_inc_notifier_count(kvm, gfn_start, gfn_end); + kvm_mmu_invalidate_begin(kvm, gfn_start, gfn_end); flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); @@ -6069,7 +6069,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end - gfn_start); - kvm_dec_notifier_count(kvm, gfn_start, gfn_end); + kvm_mmu_invalidate_end(kvm, gfn_start, gfn_end); write_unlock(&kvm->mmu_lock); } @@ -6697,11 +6697,15 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) /* * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as * its default value of -1 is technically undefined behavior for a boolean. + * Forward the module init call to SPTE code so that it too can handle module + * params that need to be resolved/snapshot. */ -void kvm_mmu_x86_module_init(void) +void __init kvm_mmu_x86_module_init(void) { if (nx_huge_pages == -1) __set_nx_huge_pages(get_nx_auto_mode()); + + kvm_mmu_spte_module_init(); } /* diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index f5958071220c..39e0205e7300 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -589,7 +589,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, * If addresses are being invalidated, skip prefetching to avoid * accidentally prefetching those addresses. */ - if (unlikely(vcpu->kvm->mmu_notifier_count)) + if (unlikely(vcpu->kvm->mmu_invalidate_in_progress)) return; if (sp->role.direct) @@ -838,7 +838,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault else fault->max_level = walker.level; - mmu_seq = vcpu->kvm->mmu_notifier_seq; + mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); r = kvm_faultin_pfn(vcpu, fault); diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 7314d27d57a4..2e08b2a45361 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -20,7 +20,9 @@ #include <asm/vmx.h> bool __read_mostly enable_mmio_caching = true; +static bool __ro_after_init allow_mmio_caching; module_param_named(mmio_caching, enable_mmio_caching, bool, 0444); +EXPORT_SYMBOL_GPL(enable_mmio_caching); u64 __read_mostly shadow_host_writable_mask; u64 __read_mostly shadow_mmu_writable_mask; @@ -43,6 +45,18 @@ u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; u8 __read_mostly shadow_phys_bits; +void __init kvm_mmu_spte_module_init(void) +{ + /* + * Snapshot userspace's desire to allow MMIO caching. Whether or not + * KVM can actually enable MMIO caching depends on vendor-specific + * hardware capabilities and other module params that can't be resolved + * until the vendor module is loaded, i.e. enable_mmio_caching can and + * will change when the vendor module is (re)loaded. + */ + allow_mmio_caching = enable_mmio_caching; +} + static u64 generation_mmio_spte_mask(u64 gen) { u64 mask; @@ -340,10 +354,24 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask) BUG_ON((u64)(unsigned)access_mask != access_mask); WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask); + /* + * Reset to the original module param value to honor userspace's desire + * to (dis)allow MMIO caching. Update the param itself so that + * userspace can see whether or not KVM is actually using MMIO caching. + */ + enable_mmio_caching = allow_mmio_caching; if (!enable_mmio_caching) mmio_value = 0; /* + * The mask must contain only bits that are carved out specifically for + * the MMIO SPTE mask, e.g. to ensure there's no overlap with the MMIO + * generation. + */ + if (WARN_ON(mmio_mask & ~SPTE_MMIO_ALLOWED_MASK)) + mmio_value = 0; + + /* * Disable MMIO caching if the MMIO value collides with the bits that * are used to hold the relocated GFN when the L1TF mitigation is * enabled. This should never fire as there is no known hardware that diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index cabe3fbb4f39..f3744eea45f5 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -5,8 +5,6 @@ #include "mmu_internal.h" -extern bool __read_mostly enable_mmio_caching; - /* * A MMU present SPTE is backed by actual memory and may or may not be present * in hardware. E.g. MMIO SPTEs are not considered present. Use bit 11, as it @@ -125,6 +123,20 @@ static_assert(!(EPT_SPTE_MMU_WRITABLE & SHADOW_ACC_TRACK_SAVED_MASK)); static_assert(!(SPTE_MMU_PRESENT_MASK & (MMIO_SPTE_GEN_LOW_MASK | MMIO_SPTE_GEN_HIGH_MASK))); +/* + * The SPTE MMIO mask must NOT overlap the MMIO generation bits or the + * MMU-present bit. The generation obviously co-exists with the magic MMIO + * mask/value, and MMIO SPTEs are considered !MMU-present. + * + * The SPTE MMIO mask is allowed to use hardware "present" bits (i.e. all EPT + * RWX bits), all physical address bits (legal PA bits are used for "fast" MMIO + * and so they're off-limits for generation; additional checks ensure the mask + * doesn't overlap legal PA bits), and bit 63 (carved out for future usage). + */ +#define SPTE_MMIO_ALLOWED_MASK (BIT_ULL(63) | GENMASK_ULL(51, 12) | GENMASK_ULL(2, 0)) +static_assert(!(SPTE_MMIO_ALLOWED_MASK & + (SPTE_MMU_PRESENT_MASK | MMIO_SPTE_GEN_LOW_MASK | MMIO_SPTE_GEN_HIGH_MASK))); + #define MMIO_SPTE_GEN_LOW_BITS (MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1) #define MMIO_SPTE_GEN_HIGH_BITS (MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1) @@ -450,6 +462,7 @@ static inline u64 restore_acc_track_spte(u64 spte) u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn); +void __init kvm_mmu_spte_module_init(void); void kvm_mmu_reset_all_pte_masks(void); #endif diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index b0e793e7d85c..28064060413a 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -22,6 +22,7 @@ #include <asm/trapnr.h> #include <asm/fpu/xcr.h> +#include "mmu.h" #include "x86.h" #include "svm.h" #include "svm_ops.h" @@ -2221,6 +2222,15 @@ void __init sev_hardware_setup(void) if (!sev_es_enabled) goto out; + /* + * SEV-ES requires MMIO caching as KVM doesn't have access to the guest + * instruction stream, i.e. can't emulate in response to a #NPF and + * instead relies on #NPF(RSVD) being reflected into the guest as #VC + * (the guest can then do a #VMGEXIT to request MMIO emulation). + */ + if (!enable_mmio_caching) + goto out; + /* Does the CPU support SEV-ES? */ if (!boot_cpu_has(X86_FEATURE_SEV_ES)) goto out; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 38f873cb6f2c..f3813dbacb9f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -5034,13 +5034,16 @@ static __init int svm_hardware_setup(void) /* Setup shadow_me_value and shadow_me_mask */ kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask); - /* Note, SEV setup consumes npt_enabled. */ + svm_adjust_mmio_mask(); + + /* + * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which + * may be modified by svm_adjust_mmio_mask()). + */ sev_hardware_setup(); svm_hv_hardware_setup(); - svm_adjust_mmio_mask(); - for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 862c1a4d971b..c399637a3a79 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -171,13 +171,6 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr) return get_gp_pmc(pmu, msr, MSR_IA32_PMC0); } -bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu) -{ - struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu); - - return lbr->nr && (vcpu_get_perf_capabilities(vcpu) & PMU_CAP_LBR_FMT); -} - static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index) { struct x86_pmu_lbr *records = vcpu_to_lbr_records(vcpu); @@ -592,7 +585,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) bitmap_set(pmu->all_valid_pmc_idx, INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters); - if (cpuid_model_is_consistent(vcpu)) + perf_capabilities = vcpu_get_perf_capabilities(vcpu); + if (cpuid_model_is_consistent(vcpu) && + (perf_capabilities & PMU_CAP_LBR_FMT)) x86_perf_get_lbr(&lbr_desc->records); else lbr_desc->records.nr = 0; @@ -600,7 +595,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) if (lbr_desc->records.nr) bitmap_set(pmu->all_valid_pmc_idx, INTEL_PMC_IDX_FIXED_VLBR, 1); - perf_capabilities = vcpu_get_perf_capabilities(vcpu); if (perf_capabilities & PERF_CAP_PEBS_FORMAT) { if (perf_capabilities & PERF_CAP_PEBS_BASELINE) { pmu->pebs_enable_mask = counter_mask; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index fb8e3480a9d7..24d58c2ffaa3 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -6,6 +6,7 @@ #include <asm/kvm.h> #include <asm/intel_pt.h> +#include <asm/perf_event.h> #include "capabilities.h" #include "../kvm_cache_regs.h" @@ -104,15 +105,6 @@ static inline bool intel_pmu_has_perf_global_ctrl(struct kvm_pmu *pmu) return pmu->version > 1; } -#define vcpu_to_lbr_desc(vcpu) (&to_vmx(vcpu)->lbr_desc) -#define vcpu_to_lbr_records(vcpu) (&to_vmx(vcpu)->lbr_desc.records) - -void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu); -bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu); - -int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); -void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu); - struct lbr_desc { /* Basic info about guest LBR records. */ struct x86_pmu_lbr records; @@ -542,6 +534,25 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_vmx, vcpu); } +static inline struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu) +{ + return &to_vmx(vcpu)->lbr_desc; +} + +static inline struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu) +{ + return &vcpu_to_lbr_desc(vcpu)->records; +} + +static inline bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu) +{ + return !!vcpu_to_lbr_records(vcpu)->nr; +} + +void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu); +int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); +void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu); + static inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 79a8a74b6b2a..205ebdc2b11b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3413,6 +3413,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu) struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; struct kvm_steal_time __user *st; struct kvm_memslots *slots; + gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; u64 steal; u32 version; @@ -3430,13 +3431,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu) slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || + gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { - gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; - /* We rely on the fact that it fits in a single page. */ BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) || + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st)) || kvm_is_error_hva(ghc->hva) || !ghc->memslot) return; } @@ -3545,9 +3545,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.perf_capabilities = data; - + kvm_pmu_refresh(vcpu); return 0; - } + } case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: @@ -4714,6 +4714,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) struct kvm_steal_time __user *st; struct kvm_memslots *slots; static const u8 preempted = KVM_VCPU_PREEMPTED; + gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; /* * The vCPU can be marked preempted if and only if the VM-Exit was on @@ -4741,6 +4742,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || + gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) return; @@ -13019,6 +13021,7 @@ void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_c fault.error_code = error_code; fault.nested_page_fault = false; fault.address = gva; + fault.async_page_fault = false; } vcpu->arch.walk_mmu->inject_page_fault(vcpu, &fault); } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index a0c05ccbf4b1..280cb5dc7341 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -707,23 +707,24 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; case KVM_XEN_VCPU_ATTR_TYPE_TIMER: - if (data->u.timer.port) { - if (data->u.timer.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) { - r = -EINVAL; - break; - } - vcpu->arch.xen.timer_virq = data->u.timer.port; + if (data->u.timer.port && + data->u.timer.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) { + r = -EINVAL; + break; + } + + if (!vcpu->arch.xen.timer.function) kvm_xen_init_timer(vcpu); - /* Restart the timer if it's set */ - if (data->u.timer.expires_ns) - kvm_xen_start_timer(vcpu, data->u.timer.expires_ns, - data->u.timer.expires_ns - - get_kvmclock_ns(vcpu->kvm)); - } else if (kvm_xen_timer_enabled(vcpu)) { - kvm_xen_stop_timer(vcpu); - vcpu->arch.xen.timer_virq = 0; - } + /* Stop the timer (if it's running) before changing the vector */ + kvm_xen_stop_timer(vcpu); + vcpu->arch.xen.timer_virq = data->u.timer.port; + + /* Start the timer if the new value has a valid vector+expiry. */ + if (data->u.timer.port && data->u.timer.expires_ns) + kvm_xen_start_timer(vcpu, data->u.timer.expires_ns, + data->u.timer.expires_ns - + get_kvmclock_ns(vcpu->kvm)); r = 0; break; diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 331310c29349..60814e110a54 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -41,6 +41,59 @@ static bool ex_handler_default(const struct exception_table_entry *e, return true; } +/* + * This is the *very* rare case where we do a "load_unaligned_zeropad()" + * and it's a page crosser into a non-existent page. + * + * This happens when we optimistically load a pathname a word-at-a-time + * and the name is less than the full word and the next page is not + * mapped. Typically that only happens for CONFIG_DEBUG_PAGEALLOC. + * + * NOTE! The faulting address is always a 'mov mem,reg' type instruction + * of size 'long', and the exception fixup must always point to right + * after the instruction. + */ +static bool ex_handler_zeropad(const struct exception_table_entry *e, + struct pt_regs *regs, + unsigned long fault_addr) +{ + struct insn insn; + const unsigned long mask = sizeof(long) - 1; + unsigned long offset, addr, next_ip, len; + unsigned long *reg; + + next_ip = ex_fixup_addr(e); + len = next_ip - regs->ip; + if (len > MAX_INSN_SIZE) + return false; + + if (insn_decode(&insn, (void *) regs->ip, len, INSN_MODE_KERN)) + return false; + if (insn.length != len) + return false; + + if (insn.opcode.bytes[0] != 0x8b) + return false; + if (insn.opnd_bytes != sizeof(long)) + return false; + + addr = (unsigned long) insn_get_addr_ref(&insn, regs); + if (addr == ~0ul) + return false; + + offset = addr & mask; + addr = addr & ~mask; + if (fault_addr != addr + sizeof(long)) + return false; + + reg = insn_get_modrm_reg_ptr(&insn, regs); + if (!reg) + return false; + + *reg = *(unsigned long *)addr >> (offset * 8); + return ex_handler_default(e, regs); +} + static bool ex_handler_fault(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { @@ -217,6 +270,8 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, return ex_handler_sgx(e, regs, trapnr); case EX_TYPE_UCOPY_LEN: return ex_handler_ucopy_len(e, regs, trapnr, reg, imm); + case EX_TYPE_ZEROPAD: + return ex_handler_zeropad(e, regs, fault_addr); } BUG(); } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 39c5246964a9..0fe690ebc269 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -645,7 +645,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, pages++; spin_lock(&init_mm.page_table_lock); - prot = __pgprot(pgprot_val(prot) | __PAGE_KERNEL_LARGE); + prot = __pgprot(pgprot_val(prot) | _PAGE_PSE); set_pte_init((pte_t *)pud, pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT, diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 30c6e986a6cd..b8db2148c07d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(xen_start_info); struct shared_info xen_dummy_shared_info; -__read_mostly int xen_have_vector_callback; +__read_mostly bool xen_have_vector_callback = true; EXPORT_SYMBOL_GPL(xen_have_vector_callback); /* diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 28762f800596..1c1ac418484b 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -8,6 +8,8 @@ #include <xen/features.h> #include <xen/events.h> +#include <xen/hvm.h> +#include <xen/interface/hvm/hvm_op.h> #include <xen/interface/memory.h> #include <asm/apic.h> @@ -31,6 +33,9 @@ static unsigned long shared_info_pfn; +__ro_after_init bool xen_percpu_upcall; +EXPORT_SYMBOL_GPL(xen_percpu_upcall); + void xen_hvm_init_shared_info(void) { struct xen_add_to_physmap xatp; @@ -126,6 +131,9 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_xen_hvm_callback) { struct pt_regs *old_regs = set_irq_regs(regs); + if (xen_percpu_upcall) + ack_APIC_irq(); + inc_irq_stat(irq_hv_callback_count); xen_hvm_evtchn_do_upcall(); @@ -169,6 +177,15 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) if (!xen_have_vector_callback) return 0; + if (xen_percpu_upcall) { + rc = xen_set_upcall_vector(cpu); + if (rc) { + WARN(1, "HVMOP_set_evtchn_upcall_vector" + " for CPU %d failed: %d\n", cpu, rc); + return rc; + } + } + if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); @@ -189,8 +206,6 @@ static int xen_cpu_dead_hvm(unsigned int cpu) return 0; } -static bool no_vector_callback __initdata; - static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -213,9 +228,6 @@ static void __init xen_hvm_guest_init(void) xen_panic_handler_init(); - if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector)) - xen_have_vector_callback = 1; - xen_hvm_smp_init(); WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_hvm, xen_cpu_dead_hvm)); xen_unplug_emulated_devices(); @@ -241,7 +253,7 @@ early_param("xen_nopv", xen_parse_nopv); static __init int xen_parse_no_vector_callback(char *arg) { - no_vector_callback = true; + xen_have_vector_callback = false; return 0; } early_param("xen_no_vector_callback", xen_parse_no_vector_callback); diff --git a/arch/x86/xen/suspend_hvm.c b/arch/x86/xen/suspend_hvm.c index 9d548b0c772f..0c4f7554b7cc 100644 --- a/arch/x86/xen/suspend_hvm.c +++ b/arch/x86/xen/suspend_hvm.c @@ -5,6 +5,7 @@ #include <xen/hvm.h> #include <xen/features.h> #include <xen/interface/features.h> +#include <xen/events.h> #include "xen-ops.h" @@ -14,6 +15,13 @@ void xen_hvm_post_suspend(int suspend_cancelled) xen_hvm_init_shared_info(); xen_vcpu_restore(); } - xen_setup_callback_vector(); + if (xen_percpu_upcall) { + unsigned int cpu; + + for_each_online_cpu(cpu) + BUG_ON(xen_set_upcall_vector(cpu)); + } else { + xen_setup_callback_vector(); + } xen_unplug_emulated_devices(); } |