diff options
Diffstat (limited to 'arch/x86')
60 files changed, 1513 insertions, 998 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7399327d1eff..8910b09b5601 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -269,6 +269,7 @@ config X86 select HAVE_ARCH_KCSAN if X86_64 select X86_FEATURE_NAMES if PROC_FS select PROC_PID_ARCH_STATUS if PROC_FS + select HAVE_ARCH_NODE_DEV_GROUP if X86_SGX imply IMA_SECURE_AND_OR_TRUSTED_BOOT if EFI config INSTRUCTION_DECODER @@ -1523,16 +1524,20 @@ config X86_CPA_STATISTICS helps to determine the effectiveness of preserving large and huge page mappings when mapping protections are changed. +config X86_MEM_ENCRYPT + select ARCH_HAS_FORCE_DMA_UNENCRYPTED + select DYNAMIC_PHYSICAL_MASK + select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS + def_bool n + config AMD_MEM_ENCRYPT bool "AMD Secure Memory Encryption (SME) support" depends on X86_64 && CPU_SUP_AMD select DMA_COHERENT_POOL - select DYNAMIC_PHYSICAL_MASK select ARCH_USE_MEMREMAP_PROT - select ARCH_HAS_FORCE_DMA_UNENCRYPTED select INSTRUCTION_DECODER - select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS select ARCH_HAS_CC_PLATFORM + select X86_MEM_ENCRYPT help Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory @@ -1917,6 +1922,7 @@ config X86_SGX select SRCU select MMU_NOTIFIER select NUMA_KEEP_MEMINFO if NUMA + select XARRAY_MULTI help Intel(R) Software Guard eXtensions (SGX) is a set of CPU instructions that can be used by applications to set aside private regions of code @@ -1932,6 +1938,7 @@ config EFI depends on ACPI select UCS2_STRING select EFI_RUNTIME_WRAPPERS + select ARCH_USE_MEMREMAP_PROT help This enables the kernel to use EFI runtime services that are available (such as the EFI variable services). diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 670e998fe930..28bcf04c022e 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -122,7 +122,7 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, static bool early_setup_sev_es(void) { if (!sev_es_negotiate_protocol()) - sev_es_terminate(GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED); + sev_es_terminate(GHCB_SEV_ES_PROT_UNSUPPORTED); if (set_page_decrypted((unsigned long)&boot_ghcb_page)) return false; @@ -175,7 +175,7 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) enum es_result result; if (!boot_ghcb && !early_setup_sev_es()) - sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + sev_es_terminate(GHCB_SEV_ES_GEN_REQ); vc_ghcb_invalidate(boot_ghcb); result = vc_init_em_ctxt(&ctxt, regs, exit_code); @@ -202,5 +202,5 @@ finish: if (result == ES_OK) vc_finish_insn(&ctxt); else if (result != ES_RETRY) - sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + sev_es_terminate(GHCB_SEV_ES_GEN_REQ); } diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index e38a4cf795d9..97b1f84bb53f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -574,6 +574,10 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) ud2 1: #endif +#ifdef CONFIG_XEN_PV + ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV +#endif + POP_REGS pop_rdi=0 /* @@ -890,6 +894,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) .Lparanoid_entry_checkgs: /* EBX = 1 -> kernel GSBASE active, no restore required */ movl $1, %ebx + /* * The kernel-enforced convention is a negative GSBASE indicates * a kernel value. No SWAPGS needed on entry and exit. @@ -897,21 +902,14 @@ SYM_CODE_START_LOCAL(paranoid_entry) movl $MSR_GS_BASE, %ecx rdmsr testl %edx, %edx - jns .Lparanoid_entry_swapgs - ret + js .Lparanoid_kernel_gsbase -.Lparanoid_entry_swapgs: + /* EBX = 0 -> SWAPGS required on exit */ + xorl %ebx, %ebx swapgs +.Lparanoid_kernel_gsbase: - /* - * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an - * unconditional CR3 write, even in the PTI case. So do an lfence - * to prevent GS speculation, regardless of whether PTI is enabled. - */ FENCE_SWAPGS_KERNEL_ENTRY - - /* EBX = 0 -> SWAPGS required on exit */ - xorl %ebx, %ebx ret SYM_CODE_END(paranoid_entry) @@ -993,11 +991,6 @@ SYM_CODE_START_LOCAL(error_entry) pushq %r12 ret -.Lerror_entry_done_lfence: - FENCE_SWAPGS_KERNEL_ENTRY -.Lerror_entry_done: - ret - /* * There are two places in the kernel that can potentially fault with * usergs. Handle them here. B stepping K8s sometimes report a @@ -1020,8 +1013,14 @@ SYM_CODE_START_LOCAL(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS - FENCE_SWAPGS_USER_ENTRY - jmp .Lerror_entry_done + + /* + * Issue an LFENCE to prevent GS speculation, regardless of whether it is a + * kernel or user gsbase. + */ +.Lerror_entry_done_lfence: + FENCE_SWAPGS_KERNEL_ENTRY + ret .Lbstep_iret: /* Fix truncated RIP */ diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 38b2c779146f..68dea7ce6a22 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2476,7 +2476,7 @@ static int x86_pmu_event_init(struct perf_event *event) if (READ_ONCE(x86_pmu.attr_rdpmc) && !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS)) - event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED; + event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT; return err; } @@ -2510,7 +2510,7 @@ void perf_clear_dirty_counters(void) static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) { - if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) + if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) return; /* @@ -2531,7 +2531,7 @@ static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) { - if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) + if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) return; if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed)) @@ -2542,7 +2542,7 @@ static int x86_pmu_event_idx(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - if (!(hwc->flags & PERF_X86_EVENT_RDPMC_ALLOWED)) + if (!(hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT)) return 0; if (is_metric_idx(hwc->idx)) @@ -2725,7 +2725,7 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; userpg->cap_user_rdpmc = - !!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED); + !!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT); userpg->pmc_width = x86_pmu.cntval_bits; if (!using_native_sched_clock() || !sched_clock_stable()) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 5480db242083..9d376e528dfc 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -74,7 +74,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */ #define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */ #define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */ + #define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */ #define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ #define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 4d0b126835b8..63158fd55856 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -197,8 +197,6 @@ static inline bool efi_runtime_supported(void) extern void parse_efi_setup(u64 phys_addr, u32 data_len); -extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); - extern void efi_thunk_runtime_setup(void); efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size, unsigned long descriptor_size, diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5a0bcf8b78d7..048b6d5aff50 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -108,7 +108,7 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ -#define INTEL_FAM6_RAPTOR_LAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE 0xB7 /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 5c6a4af0b911..f6d91ecb8026 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -40,6 +40,7 @@ #include <linux/string.h> #include <linux/compiler.h> +#include <linux/cc_platform.h> #include <asm/page.h> #include <asm/early_ioremap.h> #include <asm/pgtable_types.h> @@ -256,21 +257,6 @@ static inline void slow_down_io(void) #endif -#ifdef CONFIG_AMD_MEM_ENCRYPT -#include <linux/jump_label.h> - -extern struct static_key_false sev_enable_key; -static inline bool sev_key_active(void) -{ - return static_branch_unlikely(&sev_enable_key); -} - -#else /* !CONFIG_AMD_MEM_ENCRYPT */ - -static inline bool sev_key_active(void) { return false; } - -#endif /* CONFIG_AMD_MEM_ENCRYPT */ - #define BUILDIO(bwl, bw, type) \ static inline void out##bwl(unsigned type value, int port) \ { \ @@ -301,7 +287,7 @@ static inline unsigned type in##bwl##_p(int port) \ \ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ { \ - if (sev_key_active()) { \ + if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ unsigned type *value = (unsigned type *)addr; \ while (count) { \ out##bwl(*value, port); \ @@ -317,7 +303,7 @@ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ \ static inline void ins##bwl(int port, void *addr, unsigned long count) \ { \ - if (sev_key_active()) { \ + if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ unsigned type *value = (unsigned type *)addr; \ while (count) { \ *value = in##bwl(port); \ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index c5ce9845c999..87761396e8cc 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -114,8 +114,6 @@ static __always_inline unsigned long arch_local_irq_save(void) #define SAVE_FLAGS pushfq; popq %rax #endif -#define INTERRUPT_RETURN jmp native_iret - #endif #endif /* __ASSEMBLY__ */ @@ -143,8 +141,13 @@ static __always_inline void arch_local_irq_restore(unsigned long flags) #ifdef CONFIG_X86_64 #ifdef CONFIG_XEN_PV #define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV +#define INTERRUPT_RETURN \ + ANNOTATE_RETPOLINE_SAFE; \ + ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);", \ + X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;") #else #define SWAPGS swapgs +#define INTERRUPT_RETURN jmp native_iret #endif #endif #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index cefe1d81e2e8..9e50da3ed01a 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -47,6 +47,7 @@ KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) KVM_X86_OP(set_rflags) +KVM_X86_OP(get_if_flag) KVM_X86_OP(tlb_flush_all) KVM_X86_OP(tlb_flush_current) KVM_X86_OP_NULL(tlb_remote_flush) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6ac61f85e07b..555f4de47ef2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -97,7 +97,7 @@ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) #define KVM_REQ_TLB_FLUSH_GUEST \ - KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP) + KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29) #define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ @@ -1036,6 +1036,7 @@ struct kvm_x86_msr_filter { #define APICV_INHIBIT_REASON_PIT_REINJ 4 #define APICV_INHIBIT_REASON_X2APIC 5 #define APICV_INHIBIT_REASON_BLOCKIRQ 6 +#define APICV_INHIBIT_REASON_ABSENT 7 struct kvm_arch { unsigned long n_used_mmu_pages; @@ -1348,6 +1349,7 @@ struct kvm_x86_ops { void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); + bool (*get_if_flag)(struct kvm_vcpu *vcpu); void (*tlb_flush_all)(struct kvm_vcpu *vcpu); void (*tlb_flush_current)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 21c4a694ca11..27d276232c80 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -752,11 +752,6 @@ extern void default_banner(void); #define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8) #define PARA_INDIRECT(addr) *addr(%rip) -#define INTERRUPT_RETURN \ - ANNOTATE_RETPOLINE_SAFE; \ - ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);", \ - X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;") - #ifdef CONFIG_DEBUG_ENTRY .macro PARA_IRQ_save_fl PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h index 4cd49afa0ca4..74f0a2d34ffd 100644 --- a/arch/x86/include/asm/pkru.h +++ b/arch/x86/include/asm/pkru.h @@ -4,8 +4,8 @@ #include <asm/cpufeature.h> -#define PKRU_AD_BIT 0x1 -#define PKRU_WD_BIT 0x2 +#define PKRU_AD_BIT 0x1u +#define PKRU_WD_BIT 0x2u #define PKRU_BITS_PER_PKEY 2 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 355d38c0cf60..2c5f12ae7d04 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -855,4 +855,12 @@ enum mds_mitigations { MDS_MITIGATION_VMWERV, }; +#ifdef CONFIG_X86_SGX +int arch_memory_failure(unsigned long pfn, int flags); +#define arch_memory_failure arch_memory_failure + +bool arch_is_platform_page(u64 paddr); +#define arch_is_platform_page arch_is_platform_page +#endif + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 872617542bbc..ff0f2d90338a 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_SET_MEMORY_H #define _ASM_X86_SET_MEMORY_H +#include <linux/mm.h> #include <asm/page.h> #include <asm-generic/set_memory.h> @@ -99,6 +100,9 @@ static inline int set_mce_nospec(unsigned long pfn, bool unmap) unsigned long decoy_addr; int rc; + /* SGX pages are not in the 1:1 map */ + if (arch_is_platform_page(pfn << PAGE_SHIFT)) + return 0; /* * We would like to just call: * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1); diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 2cef6c5a52c2..1b2fd32b42fe 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -18,20 +18,19 @@ /* SEV Information Request/Response */ #define GHCB_MSR_SEV_INFO_RESP 0x001 #define GHCB_MSR_SEV_INFO_REQ 0x002 -#define GHCB_MSR_VER_MAX_POS 48 -#define GHCB_MSR_VER_MAX_MASK 0xffff -#define GHCB_MSR_VER_MIN_POS 32 -#define GHCB_MSR_VER_MIN_MASK 0xffff -#define GHCB_MSR_CBIT_POS 24 -#define GHCB_MSR_CBIT_MASK 0xff -#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \ - ((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) | \ - (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) | \ - (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) | \ + +#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \ + /* GHCBData[63:48] */ \ + ((((_max) & 0xffff) << 48) | \ + /* GHCBData[47:32] */ \ + (((_min) & 0xffff) << 32) | \ + /* GHCBData[31:24] */ \ + (((_cbit) & 0xff) << 24) | \ GHCB_MSR_SEV_INFO_RESP) + #define GHCB_MSR_INFO(v) ((v) & 0xfffUL) -#define GHCB_MSR_PROTO_MAX(v) (((v) >> GHCB_MSR_VER_MAX_POS) & GHCB_MSR_VER_MAX_MASK) -#define GHCB_MSR_PROTO_MIN(v) (((v) >> GHCB_MSR_VER_MIN_POS) & GHCB_MSR_VER_MIN_MASK) +#define GHCB_MSR_PROTO_MAX(v) (((v) >> 48) & 0xffff) +#define GHCB_MSR_PROTO_MIN(v) (((v) >> 32) & 0xffff) /* CPUID Request/Response */ #define GHCB_MSR_CPUID_REQ 0x004 @@ -46,31 +45,48 @@ #define GHCB_CPUID_REQ_EBX 1 #define GHCB_CPUID_REQ_ECX 2 #define GHCB_CPUID_REQ_EDX 3 -#define GHCB_CPUID_REQ(fn, reg) \ - (GHCB_MSR_CPUID_REQ | \ - (((unsigned long)reg & GHCB_MSR_CPUID_REG_MASK) << GHCB_MSR_CPUID_REG_POS) | \ - (((unsigned long)fn) << GHCB_MSR_CPUID_FUNC_POS)) +#define GHCB_CPUID_REQ(fn, reg) \ + /* GHCBData[11:0] */ \ + (GHCB_MSR_CPUID_REQ | \ + /* GHCBData[31:12] */ \ + (((unsigned long)(reg) & 0x3) << 30) | \ + /* GHCBData[63:32] */ \ + (((unsigned long)fn) << 32)) /* AP Reset Hold */ -#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 -#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 +#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 +#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 /* GHCB Hypervisor Feature Request/Response */ -#define GHCB_MSR_HV_FT_REQ 0x080 -#define GHCB_MSR_HV_FT_RESP 0x081 +#define GHCB_MSR_HV_FT_REQ 0x080 +#define GHCB_MSR_HV_FT_RESP 0x081 #define GHCB_MSR_TERM_REQ 0x100 #define GHCB_MSR_TERM_REASON_SET_POS 12 #define GHCB_MSR_TERM_REASON_SET_MASK 0xf #define GHCB_MSR_TERM_REASON_POS 16 #define GHCB_MSR_TERM_REASON_MASK 0xff -#define GHCB_SEV_TERM_REASON(reason_set, reason_val) \ - (((((u64)reason_set) & GHCB_MSR_TERM_REASON_SET_MASK) << GHCB_MSR_TERM_REASON_SET_POS) | \ - ((((u64)reason_val) & GHCB_MSR_TERM_REASON_MASK) << GHCB_MSR_TERM_REASON_POS)) -#define GHCB_SEV_ES_REASON_GENERAL_REQUEST 0 -#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED 1 +#define GHCB_SEV_TERM_REASON(reason_set, reason_val) \ + /* GHCBData[15:12] */ \ + (((((u64)reason_set) & 0xf) << 12) | \ + /* GHCBData[23:16] */ \ + ((((u64)reason_val) & 0xff) << 16)) + +#define GHCB_SEV_ES_GEN_REQ 0 +#define GHCB_SEV_ES_PROT_UNSUPPORTED 1 #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) +/* + * Error codes related to GHCB input that can be communicated back to the guest + * by setting the lower 32-bits of the GHCB SW_EXITINFO1 field to 2. + */ +#define GHCB_ERR_NOT_REGISTERED 1 +#define GHCB_ERR_INVALID_USAGE 2 +#define GHCB_ERR_INVALID_SCRATCH_AREA 3 +#define GHCB_ERR_MISSING_INPUT 4 +#define GHCB_ERR_INVALID_INPUT 5 +#define GHCB_ERR_INVALID_EVENT 6 + #endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 2ff3e600f426..6aef9ee28a39 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -84,7 +84,7 @@ obj-$(CONFIG_IA32_EMULATION) += tls.o obj-y += step.o obj-$(CONFIG_INTEL_TXT) += tboot.o obj-$(CONFIG_ISA_DMA_API) += i8237.o -obj-$(CONFIG_STACKTRACE) += stacktrace.o +obj-y += stacktrace.o obj-y += cpu/ obj-y += acpi/ obj-y += reboot.o diff --git a/arch/x86/kernel/cc_platform.c b/arch/x86/kernel/cc_platform.c index 03bb2f343ddb..8a25b1c0d480 100644 --- a/arch/x86/kernel/cc_platform.c +++ b/arch/x86/kernel/cc_platform.c @@ -50,6 +50,14 @@ static bool amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_STATE_ENCRYPT: return sev_status & MSR_AMD64_SEV_ES_ENABLED; + /* + * With SEV, the rep string I/O instructions need to be unrolled + * but SEV-ES supports them through the #VC handler. + */ + case CC_ATTR_GUEST_UNROLL_STRING_IO: + return (sev_status & MSR_AMD64_SEV_ENABLED) && + !(sev_status & MSR_AMD64_SEV_ES_ENABLED); + default: return false; } diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index c9f0f3d63f75..eaf25a234ff5 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -282,7 +282,7 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) u64 shift = 64 - width, chunks; chunks = (cur_msr << shift) - (prev_msr << shift); - return chunks >>= shift; + return chunks >> shift; } static u64 __mon_event_count(u32 rmid, struct rmid_read *rr) diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 8471a8b9b48e..4b41efc9e367 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -6,11 +6,13 @@ #include <linux/highmem.h> #include <linux/kthread.h> #include <linux/miscdevice.h> +#include <linux/node.h> #include <linux/pagemap.h> #include <linux/ratelimit.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> +#include <linux/sysfs.h> #include <asm/sgx.h> #include "driver.h" #include "encl.h" @@ -20,6 +22,7 @@ struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS]; static int sgx_nr_epc_sections; static struct task_struct *ksgxd_tsk; static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq); +static DEFINE_XARRAY(sgx_epc_address_space); /* * These variables are part of the state of the reclaimer, and must be accessed @@ -60,6 +63,24 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list) page = list_first_entry(dirty_page_list, struct sgx_epc_page, list); + /* + * Checking page->poison without holding the node->lock + * is racy, but losing the race (i.e. poison is set just + * after the check) just means __eremove() will be uselessly + * called for a page that sgx_free_epc_page() will put onto + * the node->sgx_poison_page_list later. + */ + if (page->poison) { + struct sgx_epc_section *section = &sgx_epc_sections[page->section]; + struct sgx_numa_node *node = section->node; + + spin_lock(&node->lock); + list_move(&page->list, &node->sgx_poison_page_list); + spin_unlock(&node->lock); + + continue; + } + ret = __eremove(sgx_get_epc_virt_addr(page)); if (!ret) { /* @@ -471,6 +492,7 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid) page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list); list_del_init(&page->list); + page->flags = 0; spin_unlock(&node->lock); atomic_long_dec(&sgx_nr_free_pages); @@ -624,7 +646,12 @@ void sgx_free_epc_page(struct sgx_epc_page *page) spin_lock(&node->lock); - list_add_tail(&page->list, &node->free_page_list); + page->owner = NULL; + if (page->poison) + list_add(&page->list, &node->sgx_poison_page_list); + else + list_add_tail(&page->list, &node->free_page_list); + page->flags = SGX_EPC_PAGE_IS_FREE; spin_unlock(&node->lock); atomic_long_inc(&sgx_nr_free_pages); @@ -648,17 +675,102 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, } section->phys_addr = phys_addr; + xa_store_range(&sgx_epc_address_space, section->phys_addr, + phys_addr + size - 1, section, GFP_KERNEL); for (i = 0; i < nr_pages; i++) { section->pages[i].section = index; section->pages[i].flags = 0; section->pages[i].owner = NULL; + section->pages[i].poison = 0; list_add_tail(§ion->pages[i].list, &sgx_dirty_page_list); } return true; } +bool arch_is_platform_page(u64 paddr) +{ + return !!xa_load(&sgx_epc_address_space, paddr); +} +EXPORT_SYMBOL_GPL(arch_is_platform_page); + +static struct sgx_epc_page *sgx_paddr_to_page(u64 paddr) +{ + struct sgx_epc_section *section; + + section = xa_load(&sgx_epc_address_space, paddr); + if (!section) + return NULL; + + return §ion->pages[PFN_DOWN(paddr - section->phys_addr)]; +} + +/* + * Called in process context to handle a hardware reported + * error in an SGX EPC page. + * If the MF_ACTION_REQUIRED bit is set in flags, then the + * context is the task that consumed the poison data. Otherwise + * this is called from a kernel thread unrelated to the page. + */ +int arch_memory_failure(unsigned long pfn, int flags) +{ + struct sgx_epc_page *page = sgx_paddr_to_page(pfn << PAGE_SHIFT); + struct sgx_epc_section *section; + struct sgx_numa_node *node; + + /* + * mm/memory-failure.c calls this routine for all errors + * where there isn't a "struct page" for the address. But that + * includes other address ranges besides SGX. + */ + if (!page) + return -ENXIO; + + /* + * If poison was consumed synchronously. Send a SIGBUS to + * the task. Hardware has already exited the SGX enclave and + * will not allow re-entry to an enclave that has a memory + * error. The signal may help the task understand why the + * enclave is broken. + */ + if (flags & MF_ACTION_REQUIRED) + force_sig(SIGBUS); + + section = &sgx_epc_sections[page->section]; + node = section->node; + + spin_lock(&node->lock); + + /* Already poisoned? Nothing more to do */ + if (page->poison) + goto out; + + page->poison = 1; + + /* + * If the page is on a free list, move it to the per-node + * poison page list. + */ + if (page->flags & SGX_EPC_PAGE_IS_FREE) { + list_move(&page->list, &node->sgx_poison_page_list); + goto out; + } + + /* + * TBD: Add additional plumbing to enable pre-emptive + * action for asynchronous poison notification. Until + * then just hope that the poison: + * a) is not accessed - sgx_free_epc_page() will deal with it + * when the user gives it back + * b) results in a recoverable machine check rather than + * a fatal one + */ +out: + spin_unlock(&node->lock); + return 0; +} + /** * A section metric is concatenated in a way that @low bits 12-31 define the * bits 12-31 of the metric and @high bits 0-19 define the bits 32-51 of the @@ -670,6 +782,48 @@ static inline u64 __init sgx_calc_section_metric(u64 low, u64 high) ((high & GENMASK_ULL(19, 0)) << 32); } +#ifdef CONFIG_NUMA +static ssize_t sgx_total_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", sgx_numa_nodes[dev->id].size); +} +static DEVICE_ATTR_RO(sgx_total_bytes); + +static umode_t arch_node_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int idx) +{ + /* Make all x86/ attributes invisible when SGX is not initialized: */ + if (nodes_empty(sgx_numa_mask)) + return 0; + + return attr->mode; +} + +static struct attribute *arch_node_dev_attrs[] = { + &dev_attr_sgx_total_bytes.attr, + NULL, +}; + +const struct attribute_group arch_node_dev_group = { + .name = "x86", + .attrs = arch_node_dev_attrs, + .is_visible = arch_node_attr_is_visible, +}; + +static void __init arch_update_sysfs_visibility(int nid) +{ + struct node *node = node_devices[nid]; + int ret; + + ret = sysfs_update_group(&node->dev.kobj, &arch_node_dev_group); + + if (ret) + pr_err("sysfs update failed (%d), files may be invisible", ret); +} +#else /* !CONFIG_NUMA */ +static void __init arch_update_sysfs_visibility(int nid) {} +#endif + static bool __init sgx_page_cache_init(void) { u32 eax, ebx, ecx, edx, type; @@ -713,10 +867,16 @@ static bool __init sgx_page_cache_init(void) if (!node_isset(nid, sgx_numa_mask)) { spin_lock_init(&sgx_numa_nodes[nid].lock); INIT_LIST_HEAD(&sgx_numa_nodes[nid].free_page_list); + INIT_LIST_HEAD(&sgx_numa_nodes[nid].sgx_poison_page_list); node_set(nid, sgx_numa_mask); + sgx_numa_nodes[nid].size = 0; + + /* Make SGX-specific node sysfs files visible: */ + arch_update_sysfs_visibility(nid); } sgx_epc_sections[i].node = &sgx_numa_nodes[nid]; + sgx_numa_nodes[nid].size += size; sgx_nr_epc_sections++; } diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h index 4628acec0009..0f17def9fe6f 100644 --- a/arch/x86/kernel/cpu/sgx/sgx.h +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -26,9 +26,13 @@ /* Pages, which are being tracked by the page reclaimer. */ #define SGX_EPC_PAGE_RECLAIMER_TRACKED BIT(0) +/* Pages on free list */ +#define SGX_EPC_PAGE_IS_FREE BIT(1) + struct sgx_epc_page { unsigned int section; - unsigned int flags; + u16 flags; + u16 poison; struct sgx_encl_page *owner; struct list_head list; }; @@ -39,6 +43,8 @@ struct sgx_epc_page { */ struct sgx_numa_node { struct list_head free_page_list; + struct list_head sgx_poison_page_list; + unsigned long size; spinlock_t lock; }; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 8ea306b1bf8e..dd3777ac0443 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -99,6 +99,19 @@ bool irq_fpu_usable(void) EXPORT_SYMBOL(irq_fpu_usable); /* + * Track AVX512 state use because it is known to slow the max clock + * speed of the core. + */ +static void update_avx_timestamp(struct fpu *fpu) +{ + +#define AVX512_TRACKING_MASK (XFEATURE_MASK_ZMM_Hi256 | XFEATURE_MASK_Hi16_ZMM) + + if (fpu->fpstate->regs.xsave.header.xfeatures & AVX512_TRACKING_MASK) + fpu->avx512_timestamp = jiffies; +} + +/* * Save the FPU register state in fpu->fpstate->regs. The register state is * preserved. * @@ -116,13 +129,7 @@ void save_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { os_xsave(fpu->fpstate); - - /* - * AVX512 state is tracked here because its use is - * known to slow the max clock speed of the core. - */ - if (fpu->fpstate->regs.xsave.header.xfeatures & XFEATURE_MASK_AVX512) - fpu->avx512_timestamp = jiffies; + update_avx_timestamp(fpu); return; } diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index d5958278eba6..91d4b6de58ab 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -118,7 +118,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, struct fpstate *fpstate) { struct xregs_state __user *x = buf; - struct _fpx_sw_bytes sw_bytes; + struct _fpx_sw_bytes sw_bytes = {}; u32 xfeatures; int err; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f5e80a8377ad..de563db9cdcd 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -126,6 +126,36 @@ static bool __head check_la57_support(unsigned long physaddr) } #endif +static unsigned long sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd) +{ + unsigned long vaddr, vaddr_end; + int i; + + /* Encrypt the kernel and related (if SME is active) */ + sme_encrypt_kernel(bp); + + /* + * Clear the memory encryption mask from the .bss..decrypted section. + * The bss section will be memset to zero later in the initialization so + * there is no need to zero it after changing the memory encryption + * attribute. + */ + if (sme_get_me_mask()) { + vaddr = (unsigned long)__start_bss_decrypted; + vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + i = pmd_index(vaddr); + pmd[i] -= sme_get_me_mask(); + } + } + + /* + * Return the SME encryption mask (if SME is active) to be used as a + * modifier for the initial pgdir entry programmed into CR3. + */ + return sme_get_me_mask(); +} + /* Code in __startup_64() can be relocated during execution, but the compiler * doesn't have to generate PC-relative relocations when accessing globals from * that function. Clang actually does not generate them, which leads to @@ -135,7 +165,6 @@ static bool __head check_la57_support(unsigned long physaddr) unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { - unsigned long vaddr, vaddr_end; unsigned long load_delta, *p; unsigned long pgtable_flags; pgdval_t *pgd; @@ -276,34 +305,7 @@ unsigned long __head __startup_64(unsigned long physaddr, */ *fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask(); - /* Encrypt the kernel and related (if SME is active) */ - sme_encrypt_kernel(bp); - - /* - * Clear the memory encryption mask from the .bss..decrypted section. - * The bss section will be memset to zero later in the initialization so - * there is no need to zero it after changing the memory encryption - * attribute. - * - * This is early code, use an open coded check for SME instead of - * using cc_platform_has(). This eliminates worries about removing - * instrumentation or checking boot_cpu_data in the cc_platform_has() - * function. - */ - if (sme_get_me_mask()) { - vaddr = (unsigned long)__start_bss_decrypted; - vaddr_end = (unsigned long)__end_bss_decrypted; - for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { - i = pmd_index(vaddr); - pmd[i] -= sme_get_me_mask(); - } - } - - /* - * Return the SME encryption mask (if SME is active) to be used as a - * modifier for the initial pgdir entry programmed into CR3. - */ - return sme_get_me_mask(); + return sme_postprocess_startup(bp, pmd); } unsigned long __startup_secondary_64(void) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6a190c7f4d71..e04f5e6eb33f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -713,9 +713,6 @@ static void __init early_reserve_memory(void) early_reserve_initrd(); - if (efi_enabled(EFI_BOOT)) - efi_memblock_x86_reserve_range(); - memblock_x86_reserve_range_setup_data(); reserve_ibft_region(); @@ -742,28 +739,6 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } -static char * __init prepare_command_line(void) -{ -#ifdef CONFIG_CMDLINE_BOOL -#ifdef CONFIG_CMDLINE_OVERRIDE - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); -#else - if (builtin_cmdline[0]) { - /* append boot loader cmdline to builtin */ - strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); - strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); - } -#endif -#endif - - strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); - - parse_early_param(); - - return command_line; -} - /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -853,23 +828,6 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); /* - * x86_configure_nx() is called before parse_early_param() (called by - * prepare_command_line()) to detect whether hardware doesn't support - * NX (so that the early EHCI debug console setup can safely call - * set_fixmap()). It may then be called again from within noexec_setup() - * during parsing early parameters to honor the respective command line - * option. - */ - x86_configure_nx(); - - /* - * This parses early params and it needs to run before - * early_reserve_memory() because latter relies on such settings - * supplied as early params. - */ - *cmdline_p = prepare_command_line(); - - /* * Do some memory reservations *before* memory is added to memblock, so * memblock allocations won't overwrite it. * @@ -902,6 +860,36 @@ void __init setup_arch(char **cmdline_p) bss_resource.start = __pa_symbol(__bss_start); bss_resource.end = __pa_symbol(__bss_stop)-1; +#ifdef CONFIG_CMDLINE_BOOL +#ifdef CONFIG_CMDLINE_OVERRIDE + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); +#else + if (builtin_cmdline[0]) { + /* append boot loader cmdline to builtin */ + strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); + strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + } +#endif +#endif + + strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); + *cmdline_p = command_line; + + /* + * x86_configure_nx() is called before parse_early_param() to detect + * whether hardware doesn't support NX (so that the early EHCI debug + * console setup can safely call set_fixmap()). It may then be called + * again from within noexec_setup() during parsing early parameters + * to honor the respective command line option. + */ + x86_configure_nx(); + + parse_early_param(); + + if (efi_enabled(EFI_BOOT)) + efi_memblock_x86_reserve_range(); + #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 787dc5f568b5..ce987688bbc0 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -221,7 +221,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) fail: /* Terminate the guest */ - sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + sev_es_terminate(GHCB_SEV_ES_GEN_REQ); } static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 74f0ec955384..c9482f472ab6 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -26,6 +26,7 @@ #include <asm/fpu/xcr.h> #include <asm/processor.h> #include <asm/realmode.h> +#include <asm/setup.h> #include <asm/traps.h> #include <asm/svm.h> #include <asm/smp.h> @@ -86,9 +87,6 @@ struct ghcb_state { static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); -/* Needed in vc_early_forward_exception */ -void do_early_exception(struct pt_regs *regs, int trapnr); - static __always_inline bool on_vc_stack(struct pt_regs *regs) { unsigned long sp = regs->sp; @@ -209,9 +207,6 @@ static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state) return ghcb; } -/* Needed in vc_early_forward_exception */ -void do_early_exception(struct pt_regs *regs, int trapnr); - static inline u64 sev_es_rd_ghcb_msr(void) { return __rdmsr(MSR_AMD64_SEV_ES_GHCB); @@ -294,11 +289,6 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, char *dst, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT | X86_PF_WRITE; - char __user *target = (char __user *)dst; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __put_user() independent of whether kernel or user @@ -320,26 +310,42 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *target = (u8 __user *)dst; + memcpy(&d1, buf, 1); if (__put_user(d1, target)) goto fault; break; - case 2: + } + case 2: { + u16 d2; + u16 __user *target = (u16 __user *)dst; + memcpy(&d2, buf, 2); if (__put_user(d2, target)) goto fault; break; - case 4: + } + case 4: { + u32 d4; + u32 __user *target = (u32 __user *)dst; + memcpy(&d4, buf, 4); if (__put_user(d4, target)) goto fault; break; - case 8: + } + case 8: { + u64 d8; + u64 __user *target = (u64 __user *)dst; + memcpy(&d8, buf, 8); if (__put_user(d8, target)) goto fault; break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; @@ -362,11 +368,6 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, char *src, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT; - char __user *s = (char __user *)src; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __get_user() independent of whether kernel or user @@ -388,26 +389,41 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *s = (u8 __user *)src; + if (__get_user(d1, s)) goto fault; memcpy(buf, &d1, 1); break; - case 2: + } + case 2: { + u16 d2; + u16 __user *s = (u16 __user *)src; + if (__get_user(d2, s)) goto fault; memcpy(buf, &d2, 2); break; - case 4: + } + case 4: { + u32 d4; + u32 __user *s = (u32 __user *)src; + if (__get_user(d4, s)) goto fault; memcpy(buf, &d4, 4); break; - case 8: + } + case 8: { + u64 d8; + u64 __user *s = (u64 __user *)src; if (__get_user(d8, s)) goto fault; memcpy(buf, &d8, 8); break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; @@ -1411,7 +1427,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication) show_regs(regs); /* Ask hypervisor to sev_es_terminate */ - sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + sev_es_terminate(GHCB_SEV_ES_GEN_REQ); /* If that fails and we get here - just panic */ panic("Returned from Terminate-Request to Hypervisor\n"); @@ -1459,7 +1475,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) /* Do initial setup or terminate the guest */ if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb())) - sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + sev_es_terminate(GHCB_SEV_ES_GEN_REQ); vc_ghcb_invalidate(boot_ghcb); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ac2909f0cab3..617012f4619f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -579,6 +579,17 @@ static struct sched_domain_topology_level x86_numa_in_package_topology[] = { { NULL, }, }; +static struct sched_domain_topology_level x86_hybrid_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + static struct sched_domain_topology_level x86_topology[] = { #ifdef CONFIG_SCHED_SMT { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, @@ -1469,8 +1480,11 @@ void __init native_smp_cpus_done(unsigned int max_cpus) calculate_max_logical_packages(); + /* XXX for now assume numa-in-package and hybrid don't overlap */ if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); + if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) + set_sched_topology(x86_hybrid_topology); nmi_selftest(); impress_friends(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 2e076a459a0c..a698196377be 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1180,6 +1180,12 @@ void mark_tsc_unstable(char *reason) EXPORT_SYMBOL_GPL(mark_tsc_unstable); +static void __init tsc_disable_clocksource_watchdog(void) +{ + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; +} + static void __init check_system_tsc_reliable(void) { #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) @@ -1196,6 +1202,23 @@ static void __init check_system_tsc_reliable(void) #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; + + /* + * Disable the clocksource watchdog when the system has: + * - TSC running at constant frequency + * - TSC which does not stop in C-States + * - the TSC_ADJUST register which allows to detect even minimal + * modifications + * - not more than two sockets. As the number of sockets cannot be + * evaluated at the early boot stage where this has to be + * invoked, check the number of online memory nodes as a + * fallback solution which is an reasonable estimate. + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && + boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && + boot_cpu_has(X86_FEATURE_TSC_ADJUST) && + nr_online_nodes <= 2) + tsc_disable_clocksource_watchdog(); } /* @@ -1387,9 +1410,6 @@ static int __init init_tsc_clocksource(void) if (tsc_unstable) goto unreg; - if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; - if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; @@ -1527,7 +1547,7 @@ void __init tsc_init(void) } if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + tsc_disable_clocksource_watchdog(); clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 50a4515fe0ad..9452dc9664b5 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -30,6 +30,7 @@ struct tsc_adjust { }; static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust); +static struct timer_list tsc_sync_check_timer; /* * TSC's on different sockets may be reset asynchronously. @@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume) } } +/* + * Normally the tsc_sync will be checked every time system enters idle + * state, but there is still caveat that a system won't enter idle, + * either because it's too busy or configured purposely to not enter + * idle. + * + * So setup a periodic timer (every 10 minutes) to make sure the check + * is always on. + */ + +#define SYNC_CHECK_INTERVAL (HZ * 600) + +static void tsc_sync_check_timer_fn(struct timer_list *unused) +{ + int next_cpu; + + tsc_verify_tsc_adjust(false); + + /* Run the check for all onlined CPUs in turn */ + next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(cpu_online_mask); + + tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL; + add_timer_on(&tsc_sync_check_timer, next_cpu); +} + +static int __init start_sync_check_timer(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable) + return 0; + + timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0); + tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL; + add_timer(&tsc_sync_check_timer); + + return 0; +} +late_initcall(start_sync_check_timer); + static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, unsigned int cpu, bool bootcpu) { diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 54a83a744538..f33c804a922a 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -95,6 +95,9 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) unsigned int *log[KVM_NR_PAGE_SIZES], *cur; int i, j, k, l, ret; + if (!kvm_memslots_have_rmaps(kvm)) + return 0; + ret = -ENOMEM; memset(log, 0, sizeof(log)); for (i = 0; i < KVM_NR_PAGE_SIZES; i++) { diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 5e19e6e4c2ce..8d8c1cc7cb53 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1922,11 +1922,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; + if (all_cpus) + goto check_and_send_ipi; + if (!sparse_banks_len) goto ret_success; - if (!all_cpus && - kvm_read_guest(kvm, + if (kvm_read_guest(kvm, hc->ingpa + offsetof(struct hv_send_ipi_ex, vp_set.bank_contents), sparse_banks, @@ -1934,6 +1936,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool return HV_STATUS_INVALID_HYPERCALL_INPUT; } +check_and_send_ipi: if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return HV_STATUS_INVALID_HYPERCALL_INPUT; diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index e66e620c3bed..539333ac4b38 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -81,7 +81,6 @@ struct kvm_ioapic { unsigned long irq_states[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; - void (*ack_notifier)(void *opaque, int irq); spinlock_t lock; struct rtc_status rtc_status; struct delayed_work eoi_inject; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 650642b18d15..c2d7cfe82d00 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -56,7 +56,6 @@ struct kvm_pic { struct kvm_io_device dev_master; struct kvm_io_device dev_slave; struct kvm_io_device dev_elcr; - void (*ack_notifier)(void *opaque, int irq); unsigned long irq_states[PIC_NUM_PINS]; }; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 759952dd1222..f206fc35deff 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -707,7 +707,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; - if (apic->vcpu->arch.apicv_active) + if (kvm_x86_ops.sync_pir_to_irr) highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 3be9beea838d..fcdf3f8bb59a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1582,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp); if (is_tdp_mmu_enabled(kvm)) - flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); + flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); return flush; } @@ -1936,7 +1936,11 @@ static void mmu_audit_disable(void) { } static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { - return sp->role.invalid || + if (sp->role.invalid) + return true; + + /* TDP MMU pages due not use the MMU generation. */ + return !sp->tdp_mmu_page && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } @@ -2173,10 +2177,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato iterator->shadow_addr = root; iterator->level = vcpu->arch.mmu->shadow_root_level; - if (iterator->level == PT64_ROOT_4LEVEL && + if (iterator->level >= PT64_ROOT_4LEVEL && vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL && !vcpu->arch.mmu->direct_map) - --iterator->level; + iterator->level = PT32E_ROOT_LEVEL; if (iterator->level == PT32E_ROOT_LEVEL) { /* @@ -3976,6 +3980,34 @@ out_retry: return true; } +/* + * Returns true if the page fault is stale and needs to be retried, i.e. if the + * root was invalidated by a memslot update or a relevant mmu_notifier fired. + */ +static bool is_page_fault_stale(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, int mmu_seq) +{ + struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root_hpa); + + /* Special roots, e.g. pae_root, are not backed by shadow pages. */ + if (sp && is_obsolete_sp(vcpu->kvm, sp)) + return true; + + /* + * Roots without an associated shadow page are considered invalid if + * there is a pending request to free obsolete roots. The request is + * only a hint that the current root _may_ be obsolete and needs to be + * reloaded, e.g. if the guest frees a PGD that KVM is tracking as a + * previous root, then __kvm_mmu_prepare_zap_page() signals all vCPUs + * to reload even if no vCPU is actively using the root. + */ + if (!sp && kvm_test_request(KVM_REQ_MMU_RELOAD, vcpu)) + return true; + + return fault->slot && + mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva); +} + static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); @@ -4013,8 +4045,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault else write_lock(&vcpu->kvm->mmu_lock); - if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) + if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; + r = make_mmu_pages_available(vcpu); if (r) goto out_unlock; @@ -4855,7 +4888,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, struct kvm_mmu *context = &vcpu->arch.guest_mmu; struct kvm_mmu_role_regs regs = { .cr0 = cr0, - .cr4 = cr4, + .cr4 = cr4 & ~X86_CR4_PKE, .efer = efer, }; union kvm_mmu_role new_role; @@ -4919,7 +4952,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->direct_map = false; update_permission_bitmask(context, true); - update_pkru_bitmask(context); + context->pkru_mask = 0; reset_rsvds_bits_mask_ept(vcpu, context, execonly); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } @@ -5025,6 +5058,14 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) /* * Invalidate all MMU roles to force them to reinitialize as CPUID * information is factored into reserved bit calculations. + * + * Correctly handling multiple vCPU models with respect to paging and + * physical address properties) in a single VM would require tracking + * all relevant CPUID information in kvm_mmu_page_role. That is very + * undesirable as it would increase the memory requirements for + * gfn_track (see struct kvm_mmu_page_role comments). For now that + * problem is swept under the rug; KVM's CPUID API is horrific and + * it's all but impossible to solve it without introducing a new API. */ vcpu->arch.root_mmu.mmu_role.ext.valid = 0; vcpu->arch.guest_mmu.mmu_role.ext.valid = 0; @@ -5032,24 +5073,10 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); /* - * KVM does not correctly handle changing guest CPUID after KVM_RUN, as - * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't - * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page - * faults due to reusing SPs/SPTEs. Alert userspace, but otherwise - * sweep the problem under the rug. - * - * KVM's horrific CPUID ABI makes the problem all but impossible to - * solve, as correctly handling multiple vCPU models (with respect to - * paging and physical address properties) in a single VM would require - * tracking all relevant CPUID information in kvm_mmu_page_role. That - * is very undesirable as it would double the memory requirements for - * gfn_track (see struct kvm_mmu_page_role comments), and in practice - * no sane VMM mucks with the core vCPU model on the fly. + * Changing guest CPUID after KVM_RUN is forbidden, see the comment in + * kvm_arch_vcpu_ioctl(). */ - if (vcpu->arch.last_vmentry_cpu != -1) { - pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n"); - pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n"); - } + KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm); } void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) @@ -5369,7 +5396,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { - kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE); + kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); @@ -5854,8 +5881,6 @@ restart: void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) { - bool flush = false; - if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); /* @@ -5863,17 +5888,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, * logging at a 4k granularity and never creates collapsible * 2m SPTEs during dirty logging. */ - flush = slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true); - if (flush) + if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true)) kvm_arch_flush_remote_tlbs_memslot(kvm, slot); write_unlock(&kvm->mmu_lock); } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); - flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush); - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, slot); + kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); read_unlock(&kvm->mmu_lock); } } @@ -6182,23 +6204,46 @@ void kvm_mmu_module_exit(void) mmu_audit_disable(); } +/* + * Calculate the effective recovery period, accounting for '0' meaning "let KVM + * select a halving time of 1 hour". Returns true if recovery is enabled. + */ +static bool calc_nx_huge_pages_recovery_period(uint *period) +{ + /* + * Use READ_ONCE to get the params, this may be called outside of the + * param setters, e.g. by the kthread to compute its next timeout. + */ + bool enabled = READ_ONCE(nx_huge_pages); + uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + + if (!enabled || !ratio) + return false; + + *period = READ_ONCE(nx_huge_pages_recovery_period_ms); + if (!*period) { + /* Make sure the period is not less than one second. */ + ratio = min(ratio, 3600u); + *period = 60 * 60 * 1000 / ratio; + } + return true; +} + static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp) { bool was_recovery_enabled, is_recovery_enabled; uint old_period, new_period; int err; - was_recovery_enabled = nx_huge_pages_recovery_ratio; - old_period = nx_huge_pages_recovery_period_ms; + was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period); err = param_set_uint(val, kp); if (err) return err; - is_recovery_enabled = nx_huge_pages_recovery_ratio; - new_period = nx_huge_pages_recovery_period_ms; + is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period); - if (READ_ONCE(nx_huge_pages) && is_recovery_enabled && + if (is_recovery_enabled && (!was_recovery_enabled || old_period > new_period)) { struct kvm *kvm; @@ -6262,18 +6307,13 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) static long get_nx_lpage_recovery_timeout(u64 start_time) { - uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); - uint period = READ_ONCE(nx_huge_pages_recovery_period_ms); + bool enabled; + uint period; - if (!period && ratio) { - /* Make sure the period is not less than one second. */ - ratio = min(ratio, 3600u); - period = 60 * 60 * 1000 / ratio; - } + enabled = calc_nx_huge_pages_recovery_period(&period); - return READ_ONCE(nx_huge_pages) && ratio - ? start_time + msecs_to_jiffies(period) - get_jiffies_64() - : MAX_SCHEDULE_TIMEOUT; + return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; } static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index f87d36898c44..708a5d297fe1 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -911,7 +911,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) + + if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index b3ed302c1a35..caa96c270b95 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -26,6 +26,7 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level) */ void tdp_iter_restart(struct tdp_iter *iter) { + iter->yielded = false; iter->yielded_gfn = iter->next_last_level_gfn; iter->level = iter->root_level; @@ -160,6 +161,11 @@ static bool try_step_up(struct tdp_iter *iter) */ void tdp_iter_next(struct tdp_iter *iter) { + if (iter->yielded) { + tdp_iter_restart(iter); + return; + } + if (try_step_down(iter)) return; diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index b1748b988d3a..e19cabbcb65c 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -45,6 +45,12 @@ struct tdp_iter { * iterator walks off the end of the paging structure. */ bool valid; + /* + * True if KVM dropped mmu_lock and yielded in the middle of a walk, in + * which case tdp_iter_next() needs to restart the walk at the root + * level instead of advancing to the next entry. + */ + bool yielded; }; /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index a54c3491af42..1beb4ca90560 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt)); int level = sp->role.level; gfn_t base_gfn = sp->gfn; - u64 old_child_spte; - u64 *sptep; - gfn_t gfn; int i; trace_kvm_mmu_prepare_zap_page(sp); @@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, tdp_mmu_unlink_page(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - sptep = rcu_dereference(pt) + i; - gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 *sptep = rcu_dereference(pt) + i; + gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 old_child_spte; if (shared) { /* @@ -374,7 +372,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, shared); } - kvm_flush_remote_tlbs_with_address(kvm, gfn, + kvm_flush_remote_tlbs_with_address(kvm, base_gfn, KVM_PAGES_PER_HPAGE(level + 1)); call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -504,6 +502,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { + WARN_ON_ONCE(iter->yielded); + lockdep_assert_held_read(&kvm->mmu_lock); /* @@ -577,6 +577,8 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte, bool record_acc_track, bool record_dirty_log) { + WARN_ON_ONCE(iter->yielded); + lockdep_assert_held_write(&kvm->mmu_lock); /* @@ -642,18 +644,19 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm, * If this function should yield and flush is set, it will perform a remote * TLB flush before yielding. * - * If this function yields, it will also reset the tdp_iter's walk over the - * paging structure and the calling function should skip to the next - * iteration to allow the iterator to continue its traversal from the - * paging structure root. + * If this function yields, iter->yielded is set and the caller must skip to + * the next iteration, where tdp_iter_next() will reset the tdp_iter's walk + * over the paging structures to allow the iterator to continue its traversal + * from the paging structure root. * - * Return true if this function yielded and the iterator's traversal was reset. - * Return false if a yield was not needed. + * Returns true if this function yielded. */ -static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, - struct tdp_iter *iter, bool flush, - bool shared) +static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, + struct tdp_iter *iter, + bool flush, bool shared) { + WARN_ON(iter->yielded); + /* Ensure forward progress has been made before yielding. */ if (iter->next_last_level_gfn == iter->yielded_gfn) return false; @@ -673,12 +676,10 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, WARN_ON(iter->gfn > iter->next_last_level_gfn); - tdp_iter_restart(iter); - - return true; + iter->yielded = true; } - return false; + return iter->yielded; } /* @@ -1033,9 +1034,9 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, { struct kvm_mmu_page *root; - for_each_tdp_mmu_root(kvm, root, range->slot->as_id) - flush |= zap_gfn_range(kvm, root, range->start, range->end, - range->may_block, flush, false); + for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) + flush = zap_gfn_range(kvm, root, range->start, range->end, + range->may_block, flush, false); return flush; } @@ -1364,10 +1365,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, * Clear leaf entries which could be replaced by large mappings, for * GFNs within the slot. */ -static bool zap_collapsible_spte_range(struct kvm *kvm, +static void zap_collapsible_spte_range(struct kvm *kvm, struct kvm_mmu_page *root, - const struct kvm_memory_slot *slot, - bool flush) + const struct kvm_memory_slot *slot) { gfn_t start = slot->base_gfn; gfn_t end = start + slot->npages; @@ -1378,10 +1378,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm, tdp_root_for_each_pte(iter, root, start, end) { retry: - if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) { - flush = false; + if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - } if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) @@ -1393,6 +1391,7 @@ retry: pfn, PG_LEVEL_NUM)) continue; + /* Note, a successful atomic zap also does a remote TLB flush. */ if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) { /* * The iter must explicitly re-read the SPTE because @@ -1401,30 +1400,24 @@ retry: iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep)); goto retry; } - flush = true; } rcu_read_unlock(); - - return flush; } /* * Clear non-leaf entries (and free associated page tables) which could * be replaced by large mappings, for GFNs within the slot. */ -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot, - bool flush) +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, + const struct kvm_memory_slot *slot) { struct kvm_mmu_page *root; lockdep_assert_held_read(&kvm->mmu_lock); for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) - flush = zap_collapsible_spte_range(kvm, root, slot, flush); - - return flush; + zap_collapsible_spte_range(kvm, root, slot); } /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 476b133544dd..3899004a5d91 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -64,9 +64,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, unsigned long mask, bool wrprot); -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot, - bool flush); +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, + const struct kvm_memory_slot *slot); bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index affc0ea98d30..8f9af7b7dbbe 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -900,6 +900,7 @@ out: bool svm_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | @@ -989,16 +990,18 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) { struct vcpu_svm *svm = to_svm(vcpu); + int cpu = get_cpu(); + WARN_ON(cpu != vcpu->cpu); svm->avic_is_running = is_run; - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - if (is_run) - avic_vcpu_load(vcpu, vcpu->cpu); - else - avic_vcpu_put(vcpu); + if (kvm_vcpu_apicv_active(vcpu)) { + if (is_run) + avic_vcpu_load(vcpu, cpu); + else + avic_vcpu_put(vcpu); + } + put_cpu(); } void svm_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 871c426ec389..b4095dfeeee6 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -281,7 +281,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; - pmu->reserved_bits = 0xffffffff00200000ull; + pmu->reserved_bits = 0xfffffff000280000ull; pmu->version = 1; /* not applicable to AMD; but clean them to prevent any fall out */ pmu->counter_bitmask[KVM_PMC_FIXED] = 0; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 21ac0a5de4e0..be2883141220 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1543,28 +1543,50 @@ static bool is_cmd_allowed_from_mirror(u32 cmd_id) return false; } -static int sev_lock_for_migration(struct kvm *kvm) +static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; + int r = -EBUSY; + + if (dst_kvm == src_kvm) + return -EINVAL; /* - * Bail if this VM is already involved in a migration to avoid deadlock - * between two VMs trying to migrate to/from each other. + * Bail if these VMs are already involved in a migration to avoid + * deadlock between two VMs trying to migrate to/from each other. */ - if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1)) + if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1)) return -EBUSY; - mutex_lock(&kvm->lock); + if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1)) + goto release_dst; + r = -EINTR; + if (mutex_lock_killable(&dst_kvm->lock)) + goto release_src; + if (mutex_lock_killable_nested(&src_kvm->lock, SINGLE_DEPTH_NESTING)) + goto unlock_dst; return 0; + +unlock_dst: + mutex_unlock(&dst_kvm->lock); +release_src: + atomic_set_release(&src_sev->migration_in_progress, 0); +release_dst: + atomic_set_release(&dst_sev->migration_in_progress, 0); + return r; } -static void sev_unlock_after_migration(struct kvm *kvm) +static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; - mutex_unlock(&kvm->lock); - atomic_set_release(&sev->migration_in_progress, 0); + mutex_unlock(&dst_kvm->lock); + mutex_unlock(&src_kvm->lock); + atomic_set_release(&dst_sev->migration_in_progress, 0); + atomic_set_release(&src_sev->migration_in_progress, 0); } @@ -1607,14 +1629,15 @@ static void sev_migrate_from(struct kvm_sev_info *dst, dst->asid = src->asid; dst->handle = src->handle; dst->pages_locked = src->pages_locked; + dst->enc_context_owner = src->enc_context_owner; src->asid = 0; src->active = false; src->handle = 0; src->pages_locked = 0; + src->enc_context_owner = NULL; - INIT_LIST_HEAD(&dst->regions_list); - list_replace_init(&src->regions_list, &dst->regions_list); + list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); } static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) @@ -1666,15 +1689,6 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) bool charged = false; int ret; - ret = sev_lock_for_migration(kvm); - if (ret) - return ret; - - if (sev_guest(kvm)) { - ret = -EINVAL; - goto out_unlock; - } - source_kvm_file = fget(source_fd); if (!file_is_kvm(source_kvm_file)) { ret = -EBADF; @@ -1682,16 +1696,26 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) } source_kvm = source_kvm_file->private_data; - ret = sev_lock_for_migration(source_kvm); + ret = sev_lock_two_vms(kvm, source_kvm); if (ret) goto out_fput; - if (!sev_guest(source_kvm)) { + if (sev_guest(kvm) || !sev_guest(source_kvm)) { ret = -EINVAL; - goto out_source; + goto out_unlock; } src_sev = &to_kvm_svm(source_kvm)->sev_info; + + /* + * VMs mirroring src's encryption context rely on it to keep the + * ASID allocated, but below we are clearing src_sev->asid. + */ + if (src_sev->num_mirrored_vms) { + ret = -EBUSY; + goto out_unlock; + } + dst_sev->misc_cg = get_current_misc_cg(); cg_cleanup_sev = dst_sev; if (dst_sev->misc_cg != src_sev->misc_cg) { @@ -1728,13 +1752,11 @@ out_dst_cgroup: sev_misc_cg_uncharge(cg_cleanup_sev); put_misc_cg(cg_cleanup_sev->misc_cg); cg_cleanup_sev->misc_cg = NULL; -out_source: - sev_unlock_after_migration(source_kvm); +out_unlock: + sev_unlock_two_vms(kvm, source_kvm); out_fput: if (source_kvm_file) fput(source_kvm_file); -out_unlock: - sev_unlock_after_migration(kvm); return ret; } @@ -1953,76 +1975,60 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) { struct file *source_kvm_file; struct kvm *source_kvm; - struct kvm_sev_info source_sev, *mirror_sev; + struct kvm_sev_info *source_sev, *mirror_sev; int ret; source_kvm_file = fget(source_fd); if (!file_is_kvm(source_kvm_file)) { ret = -EBADF; - goto e_source_put; + goto e_source_fput; } source_kvm = source_kvm_file->private_data; - mutex_lock(&source_kvm->lock); - - if (!sev_guest(source_kvm)) { - ret = -EINVAL; - goto e_source_unlock; - } + ret = sev_lock_two_vms(kvm, source_kvm); + if (ret) + goto e_source_fput; - /* Mirrors of mirrors should work, but let's not get silly */ - if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) { + /* + * Mirrors of mirrors should work, but let's not get silly. Also + * disallow out-of-band SEV/SEV-ES init if the target is already an + * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being + * created after SEV/SEV-ES initialization, e.g. to init intercepts. + */ + if (sev_guest(kvm) || !sev_guest(source_kvm) || + is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) { ret = -EINVAL; - goto e_source_unlock; + goto e_unlock; } - memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info, - sizeof(source_sev)); - /* * The mirror kvm holds an enc_context_owner ref so its asid can't * disappear until we're done with it */ + source_sev = &to_kvm_svm(source_kvm)->sev_info; kvm_get_kvm(source_kvm); - - fput(source_kvm_file); - mutex_unlock(&source_kvm->lock); - mutex_lock(&kvm->lock); - - /* - * Disallow out-of-band SEV/SEV-ES init if the target is already an - * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being - * created after SEV/SEV-ES initialization, e.g. to init intercepts. - */ - if (sev_guest(kvm) || kvm->created_vcpus) { - ret = -EINVAL; - goto e_mirror_unlock; - } + source_sev->num_mirrored_vms++; /* Set enc_context_owner and copy its encryption context over */ mirror_sev = &to_kvm_svm(kvm)->sev_info; mirror_sev->enc_context_owner = source_kvm; mirror_sev->active = true; - mirror_sev->asid = source_sev.asid; - mirror_sev->fd = source_sev.fd; - mirror_sev->es_active = source_sev.es_active; - mirror_sev->handle = source_sev.handle; + mirror_sev->asid = source_sev->asid; + mirror_sev->fd = source_sev->fd; + mirror_sev->es_active = source_sev->es_active; + mirror_sev->handle = source_sev->handle; + INIT_LIST_HEAD(&mirror_sev->regions_list); + ret = 0; + /* * Do not copy ap_jump_table. Since the mirror does not share the same * KVM contexts as the original, and they may have different * memory-views. */ - mutex_unlock(&kvm->lock); - return 0; - -e_mirror_unlock: - mutex_unlock(&kvm->lock); - kvm_put_kvm(source_kvm); - return ret; -e_source_unlock: - mutex_unlock(&source_kvm->lock); -e_source_put: +e_unlock: + sev_unlock_two_vms(kvm, source_kvm); +e_source_fput: if (source_kvm_file) fput(source_kvm_file); return ret; @@ -2034,17 +2040,24 @@ void sev_vm_destroy(struct kvm *kvm) struct list_head *head = &sev->regions_list; struct list_head *pos, *q; + WARN_ON(sev->num_mirrored_vms); + if (!sev_guest(kvm)) return; /* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */ if (is_mirroring_enc_context(kvm)) { - kvm_put_kvm(sev->enc_context_owner); + struct kvm *owner_kvm = sev->enc_context_owner; + struct kvm_sev_info *owner_sev = &to_kvm_svm(owner_kvm)->sev_info; + + mutex_lock(&owner_kvm->lock); + if (!WARN_ON(!owner_sev->num_mirrored_vms)) + owner_sev->num_mirrored_vms--; + mutex_unlock(&owner_kvm->lock); + kvm_put_kvm(owner_kvm); return; } - mutex_lock(&kvm->lock); - /* * Ensure that all guest tagged cache entries are flushed before * releasing the pages back to the system for use. CLFLUSH will @@ -2064,8 +2077,6 @@ void sev_vm_destroy(struct kvm *kvm) } } - mutex_unlock(&kvm->lock); - sev_unbind_asid(kvm, sev->handle); sev_asid_free(sev); } @@ -2249,7 +2260,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) __free_page(virt_to_page(svm->sev_es.vmsa)); if (svm->sev_es.ghcb_sa_free) - kfree(svm->sev_es.ghcb_sa); + kvfree(svm->sev_es.ghcb_sa); } static void dump_ghcb(struct vcpu_svm *svm) @@ -2341,24 +2352,29 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } -static int sev_es_validate_vmgexit(struct vcpu_svm *svm) +static bool sev_es_validate_vmgexit(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu; struct ghcb *ghcb; - u64 exit_code = 0; + u64 exit_code; + u64 reason; ghcb = svm->sev_es.ghcb; - /* Only GHCB Usage code 0 is supported */ - if (ghcb->ghcb_usage) - goto vmgexit_err; - /* - * Retrieve the exit code now even though is may not be marked valid + * Retrieve the exit code now even though it may not be marked valid * as it could help with debugging. */ exit_code = ghcb_get_sw_exit_code(ghcb); + /* Only GHCB Usage code 0 is supported */ + if (ghcb->ghcb_usage) { + reason = GHCB_ERR_INVALID_USAGE; + goto vmgexit_err; + } + + reason = GHCB_ERR_MISSING_INPUT; + if (!ghcb_sw_exit_code_is_valid(ghcb) || !ghcb_sw_exit_info_1_is_valid(ghcb) || !ghcb_sw_exit_info_2_is_valid(ghcb)) @@ -2437,30 +2453,34 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; default: + reason = GHCB_ERR_INVALID_EVENT; goto vmgexit_err; } - return 0; + return true; vmgexit_err: vcpu = &svm->vcpu; - if (ghcb->ghcb_usage) { + if (reason == GHCB_ERR_INVALID_USAGE) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", ghcb->ghcb_usage); + } else if (reason == GHCB_ERR_INVALID_EVENT) { + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n", + exit_code); } else { - vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n", + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n", exit_code); dump_ghcb(svm); } - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_code; - vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + /* Clear the valid entries fields */ + memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); + + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, reason); - return -EINVAL; + return false; } void sev_es_unmap_ghcb(struct vcpu_svm *svm) @@ -2482,7 +2502,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) svm->sev_es.ghcb_sa_sync = false; } - kfree(svm->sev_es.ghcb_sa); + kvfree(svm->sev_es.ghcb_sa); svm->sev_es.ghcb_sa = NULL; svm->sev_es.ghcb_sa_free = false; } @@ -2530,14 +2550,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); - return false; + goto e_scratch; } scratch_gpa_end = scratch_gpa_beg + len; if (scratch_gpa_end < scratch_gpa_beg) { pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n", len, scratch_gpa_beg); - return false; + goto e_scratch; } if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) { @@ -2555,7 +2575,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) scratch_gpa_end > ghcb_scratch_end) { pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n", scratch_gpa_beg, scratch_gpa_end); - return false; + goto e_scratch; } scratch_va = (void *)svm->sev_es.ghcb; @@ -2568,18 +2588,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) if (len > GHCB_SCRATCH_AREA_LIMIT) { pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n", len, GHCB_SCRATCH_AREA_LIMIT); - return false; + goto e_scratch; } - scratch_va = kzalloc(len, GFP_KERNEL_ACCOUNT); + scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT); if (!scratch_va) - return false; + goto e_scratch; if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) { /* Unable to copy scratch area from guest */ pr_err("vmgexit: kvm_read_guest for scratch area failed\n"); - kfree(scratch_va); - return false; + kvfree(scratch_va); + goto e_scratch; } /* @@ -2596,6 +2616,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) svm->sev_es.ghcb_sa_len = len; return true; + +e_scratch: + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); + + return false; } static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, @@ -2646,7 +2672,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID); if (!ret) { - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ break; } @@ -2682,10 +2708,13 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) GHCB_MSR_TERM_REASON_POS); pr_info("SEV-ES guest requested termination: %#llx:%#llx\n", reason_set, reason_code); - fallthrough; + + ret = -EINVAL; + break; } default: - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ + break; } trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id, @@ -2709,14 +2738,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) if (!ghcb_gpa) { vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n"); - return -EINVAL; + + /* Without a GHCB, just return right back to the guest */ + return 1; } if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) { /* Unable to map GHCB from guest */ vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", ghcb_gpa); - return -EINVAL; + + /* Without a GHCB, just return right back to the guest */ + return 1; } svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; @@ -2726,15 +2759,14 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) exit_code = ghcb_get_sw_exit_code(ghcb); - ret = sev_es_validate_vmgexit(svm); - if (ret) - return ret; + if (!sev_es_validate_vmgexit(svm)) + return 1; sev_es_sync_from_ghcb(svm); ghcb_set_sw_exit_info_1(ghcb, 0); ghcb_set_sw_exit_info_2(ghcb, 0); - ret = -EINVAL; + ret = 1; switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: if (!setup_vmgexit_scratch(svm, true, control->exit_info_2)) @@ -2775,20 +2807,17 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) default: pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n", control->exit_info_1); - ghcb_set_sw_exit_info_1(ghcb, 1); - ghcb_set_sw_exit_info_2(ghcb, - X86_TRAP_UD | - SVM_EVTINJ_TYPE_EXEPT | - SVM_EVTINJ_VALID); + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT); } - ret = 1; break; } case SVM_VMGEXIT_UNSUPPORTED_EVENT: vcpu_unimpl(vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", control->exit_info_1, control->exit_info_2); + ret = -EINVAL; break; default: ret = svm_invoke_exit_handler(vcpu, exit_code); @@ -2810,7 +2839,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) return -EINVAL; if (!setup_vmgexit_scratch(svm, in, bytes)) - return -EINVAL; + return 1; return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa, count, in); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5630c241d5f6..5151efa424ac 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1585,6 +1585,15 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } +static bool svm_get_if_flag(struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = to_svm(vcpu)->vmcb; + + return sev_es_guest(vcpu->kvm) + ? vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK + : kvm_get_rflags(vcpu) & X86_EFLAGS_IF; +} + static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { switch (reg) { @@ -3568,14 +3577,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) if (!gif_set(svm)) return true; - if (sev_es_guest(vcpu->kvm)) { - /* - * SEV-ES guests to not expose RFLAGS. Use the VMCB interrupt mask - * bit to determine the state of the IF flag. - */ - if (!(vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK)) - return true; - } else if (is_guest_mode(vcpu)) { + if (is_guest_mode(vcpu)) { /* As long as interrupts are being delivered... */ if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) ? !(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF) @@ -3586,7 +3588,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) if (nested_exit_on_intr(svm)) return false; } else { - if (!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF)) + if (!svm_get_if_flag(vcpu)) return true; } @@ -4621,6 +4623,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, + .get_if_flag = svm_get_if_flag, .tlb_flush_all = svm_flush_tlb, .tlb_flush_current = svm_flush_tlb, @@ -4651,7 +4654,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, - .sync_pir_to_irr = kvm_lapic_find_highest_irr, .apicv_post_state_restore = avic_post_state_restore, .set_tss_addr = svm_set_tss_addr, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5faad3dc10e2..1c7306c370fa 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -79,6 +79,7 @@ struct kvm_sev_info { struct list_head regions_list; /* List of registered regions */ u64 ap_jump_table; /* SEV-ES AP Jump Table address */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ + unsigned long num_mirrored_vms; /* Number of VMs sharing this ASID */ struct misc_cg *misc_cg; /* For misc cgroup accounting */ atomic_t migration_in_progress; }; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1e2f66951566..9c941535f78c 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -1162,29 +1162,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, WARN_ON(!enable_vpid); /* - * If VPID is enabled and used by vmc12, but L2 does not have a unique - * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate - * a VPID for L2, flush the current context as the effective ASID is - * common to both L1 and L2. - * - * Defer the flush so that it runs after vmcs02.EPTP has been set by - * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid - * redundant flushes further down the nested pipeline. - * - * If a TLB flush isn't required due to any of the above, and vpid12 is - * changing then the new "virtual" VPID (vpid12) will reuse the same - * "real" VPID (vpid02), and so needs to be flushed. There's no direct - * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for - * all nested vCPUs. Remember, a flush on VM-Enter does not invalidate - * guest-physical mappings, so there is no need to sync the nEPT MMU. + * VPID is enabled and in use by vmcs12. If vpid12 is changing, then + * emulate a guest TLB flush as KVM does not track vpid12 history nor + * is the VPID incorporated into the MMU context. I.e. KVM must assume + * that the new vpid12 has never been used and thus represents a new + * guest ASID that cannot have entries in the TLB. */ - if (!nested_has_guest_tlb_tag(vcpu)) { - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } else if (is_vmenter && - vmcs12->virtual_processor_id != vmx->nested.last_vpid) { + if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; - vpid_sync_context(nested_get_vpid02(vcpu)); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + return; } + + /* + * If VPID is enabled, used by vmc12, and vpid12 is not changing but + * does not have a unique TLB tag (ASID), i.e. EPT is disabled and + * KVM was unable to allocate a VPID for L2, flush the current context + * as the effective ASID is common to both L1 and L2. + */ + if (!nested_has_guest_tlb_tag(vcpu)) + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) @@ -2594,8 +2591,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, - vmcs12->guest_ia32_perf_global_ctrl))) + vmcs12->guest_ia32_perf_global_ctrl))) { + *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; + } kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); @@ -3344,8 +3343,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, }; u32 failed_index; - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); + kvm_service_local_tlb_flush_requests(vcpu); evaluate_pending_interrupts = exec_controls_get(vmx) & (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); @@ -4502,9 +4500,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, (void)nested_get_evmcs_page(vcpu); } - /* Service the TLB flush request for L2 before switching to L1. */ - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); + /* Service pending TLB flush requests for L2 before switching to L1. */ + kvm_service_local_tlb_flush_requests(vcpu); /* * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between @@ -4857,6 +4854,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (!vmx->nested.cached_vmcs12) goto out_cached_vmcs12; + vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA; vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_shadow_vmcs12) goto out_cached_shadow_vmcs12; @@ -5289,8 +5287,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache; struct vmcs_hdr hdr; - if (ghc->gpa != vmptr && - kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { /* * Reads from an unbacked page return all 1s, * which means that the 32 bits located at the diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5f81ef092bd4..1c94783b5a54 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -5,6 +5,7 @@ #include <asm/cpu.h> #include "lapic.h" +#include "irq.h" #include "posted_intr.h" #include "trace.h" #include "vmx.h" @@ -77,13 +78,18 @@ after_clear_sn: pi_set_on(pi_desc); } +static bool vmx_can_use_vtd_pi(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm) && enable_apicv && + kvm_arch_has_assigned_device(kvm) && + irq_remapping_cap(IRQ_POSTING_CAP); +} + void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm)) return; /* Set SN when the vCPU is preempted */ @@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm)) return 0; WARN_ON(irqs_disabled()); @@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct vcpu_data vcpu_info; int idx, ret = 0; - if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(kvm->vcpus[0])) + if (!vmx_can_use_vtd_pi(kvm)) return 0; idx = srcu_read_lock(&kvm->irq_srcu); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ba66c171d951..0dbf94eb954f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1363,6 +1363,11 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmx->emulation_required = vmx_emulation_required(vcpu); } +static bool vmx_get_if_flag(struct kvm_vcpu *vcpu) +{ + return vmx_get_rflags(vcpu) & X86_EFLAGS_IF; +} + u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); @@ -2646,15 +2651,6 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); - - if (IS_ENABLED(CONFIG_HYPERV) && - static_branch_unlikely(&enable_evmcs) && - (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { - struct hv_enlightened_vmcs *evmcs = - (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs; - - evmcs->hv_enlightenments_control.msr_bitmap = 1; - } } memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); @@ -2918,6 +2914,13 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) } } +static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu)) + return nested_get_vpid02(vcpu); + return to_vmx(vcpu)->vpid; +} + static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; @@ -2930,31 +2933,29 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) if (enable_ept) ept_sync_context(construct_eptp(vcpu, root_hpa, mmu->shadow_root_level)); - else if (!is_guest_mode(vcpu)) - vpid_sync_context(to_vmx(vcpu)->vpid); else - vpid_sync_context(nested_get_vpid02(vcpu)); + vpid_sync_context(vmx_get_current_vpid(vcpu)); } static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* - * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in + * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in * vmx_flush_tlb_guest() for an explanation of why this is ok. */ - vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr); + vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* - * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0 - * or a vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit - * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is + * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a + * vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit are + * required to flush GVA->{G,H}PA mappings from the TLB if vpid is * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed), * i.e. no explicit INVVPID is necessary. */ - vpid_sync_context(to_vmx(vcpu)->vpid); + vpid_sync_context(vmx_get_current_vpid(vcpu)); } void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu) @@ -3963,8 +3964,7 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_on(&vmx->pi_desc)) return 0; - if (vcpu != kvm_get_running_vcpu() && - !kvm_vcpu_trigger_posted_interrupt(vcpu, false)) + if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); return 0; @@ -5881,18 +5881,14 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) vmx_flush_pml_buffer(vcpu); /* - * We should never reach this point with a pending nested VM-Enter, and - * more specifically emulation of L2 due to invalid guest state (see - * below) should never happen as that means we incorrectly allowed a - * nested VM-Enter with an invalid vmcs12. + * KVM should never reach this point with a pending nested VM-Enter. + * More specifically, short-circuiting VM-Entry to emulate L2 due to + * invalid guest state should never happen as that means KVM knowingly + * allowed a nested VM-Enter with an invalid vmcs12. More below. */ if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm)) return -EIO; - /* If guest state is invalid, start emulating */ - if (vmx->emulation_required) - return handle_invalid_guest_state(vcpu); - if (is_guest_mode(vcpu)) { /* * PML is never enabled when running L2, bail immediately if a @@ -5914,10 +5910,30 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) */ nested_mark_vmcs12_pages_dirty(vcpu); + /* + * Synthesize a triple fault if L2 state is invalid. In normal + * operation, nested VM-Enter rejects any attempt to enter L2 + * with invalid state. However, those checks are skipped if + * state is being stuffed via RSM or KVM_SET_NESTED_STATE. If + * L2 state is invalid, it means either L1 modified SMRAM state + * or userspace provided bad state. Synthesize TRIPLE_FAULT as + * doing so is architecturally allowed in the RSM case, and is + * the least awful solution for the userspace case without + * risking false positives. + */ + if (vmx->emulation_required) { + nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); + return 1; + } + if (nested_vmx_reflect_vmexit(vcpu)) return 1; } + /* If guest state is invalid, start emulating. L2 is handled above. */ + if (vmx->emulation_required) + return handle_invalid_guest_state(vcpu); + if (exit_reason.failed_vmentry) { dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; @@ -6262,9 +6278,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; - bool max_irr_updated; + bool got_posted_interrupt; - if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm)) + if (KVM_BUG_ON(!enable_apicv, vcpu->kvm)) return -EIO; if (pi_test_on(&vmx->pi_desc)) { @@ -6274,22 +6290,33 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); - max_irr_updated = + got_posted_interrupt = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr); - - /* - * If we are running L2 and L1 has a new pending interrupt - * which can be injected, this may cause a vmexit or it may - * be injected into L2. Either way, this interrupt will be - * processed via KVM_REQ_EVENT, not RVI, because we do not use - * virtual interrupt delivery to inject L1 interrupts into L2. - */ - if (is_guest_mode(vcpu) && max_irr_updated) - kvm_make_request(KVM_REQ_EVENT, vcpu); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); + got_posted_interrupt = false; } - vmx_hwapic_irr_update(vcpu, max_irr); + + /* + * Newly recognized interrupts are injected via either virtual interrupt + * delivery (RVI) or KVM_REQ_EVENT. Virtual interrupt delivery is + * disabled in two cases: + * + * 1) If L2 is running and the vCPU has a new pending interrupt. If L1 + * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a + * VM-Exit to L1. If L1 doesn't want to exit, the interrupt is injected + * into L2, but KVM doesn't use virtual interrupt delivery to inject + * interrupts into L2, and so KVM_REQ_EVENT is again needed. + * + * 2) If APICv is disabled for this vCPU, assigned devices may still + * attempt to post interrupts. The posted interrupt vector will cause + * a VM-Exit and the subsequent entry will call sync_pir_to_irr. + */ + if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu)) + vmx_set_rvi(max_irr); + else if (got_posted_interrupt) + kvm_make_request(KVM_REQ_EVENT, vcpu); + return max_irr; } @@ -6601,9 +6628,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) * consistency check VM-Exit due to invalid guest state and bail. */ if (unlikely(vmx->emulation_required)) { - - /* We don't emulate invalid state of a nested guest */ - vmx->fail = is_guest_mode(vcpu); + vmx->fail = 0; vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; vmx->exit_reason.failed_vmentry = 1; @@ -6826,6 +6851,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) if (err < 0) goto free_pml; + /* + * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a + * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the + * feature only for vmcs01, KVM currently isn't equipped to realize any + * performance benefits from enabling it for vmcs02. + */ + if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) && + (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + evmcs->hv_enlightenments_control.msr_bitmap = 1; + } + /* The MSR bitmap starts with all ones */ bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS); bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); @@ -7509,6 +7547,7 @@ static void hardware_unsetup(void) static bool vmx_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_BLOCKIRQ); @@ -7558,6 +7597,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, + .get_if_flag = vmx_get_if_flag, .tlb_flush_all = vmx_flush_tlb_all, .tlb_flush_current = vmx_flush_tlb_current, @@ -7761,10 +7801,10 @@ static __init int hardware_setup(void) ple_window_shrink = 0; } - if (!cpu_has_vmx_apicv()) { + if (!cpu_has_vmx_apicv()) enable_apicv = 0; + if (!enable_apicv) vmx_x86_ops.sync_pir_to_irr = NULL; - } if (cpu_has_vmx_tsc_scaling()) { kvm_has_tsc_control = true; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5a403d92833f..e50e97ac4408 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -890,7 +890,8 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu))) return 1; - if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + if (!(cr0 & X86_CR0_PG) && + (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))) return 1; static_call(kvm_x86_set_cr0)(vcpu, cr0); @@ -1330,7 +1331,7 @@ static const u32 msrs_to_save_all[] = { MSR_IA32_UMWAIT_CONTROL, MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, - MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, @@ -3258,6 +3259,29 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) static_call(kvm_x86_tlb_flush_guest)(vcpu); } + +static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + static_call(kvm_x86_tlb_flush_current)(vcpu); +} + +/* + * Service "local" TLB flush requests, which are specific to the current MMU + * context. In addition to the generic event handling in vcpu_enter_guest(), + * TLB flushes that are targeted at an MMU context also need to be serviced + * prior before nested VM-Enter/VM-Exit. + */ +void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu) +{ + if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) + kvm_vcpu_flush_tlb_current(vcpu); + + if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) + kvm_vcpu_flush_tlb_guest(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests); + static void record_steal_time(struct kvm_vcpu *vcpu) { struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; @@ -3389,7 +3413,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated) return 1; - if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM) && kvm_get_msr_feature(&msr_ent)) + if (kvm_get_msr_feature(&msr_ent)) return 1; if (data & ~msr_ent.data) return 1; @@ -4133,6 +4157,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SGX_ATTRIBUTE: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: @@ -4448,8 +4473,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); } @@ -5124,6 +5148,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; + /* + * KVM does not correctly handle changing guest CPUID after KVM_RUN, as + * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't + * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page + * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with + * the core vCPU model on the fly, so fail. + */ + r = -EINVAL; + if (vcpu->arch.last_vmentry_cpu != -1) + goto out; + r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5134,6 +5169,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; + /* + * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in + * KVM_SET_CPUID case above. + */ + r = -EINVAL; + if (vcpu->arch.last_vmentry_cpu != -1) + goto out; + r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5698,6 +5741,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; + kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); r = 0; split_irqchip_unlock: mutex_unlock(&kvm->lock); @@ -6078,6 +6122,7 @@ set_identity_unlock: /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; + kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -7077,7 +7122,13 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port, void *val, unsigned int count) { if (vcpu->arch.pio.count) { - /* Complete previous iteration. */ + /* + * Complete a previous iteration that required userspace I/O. + * Note, @count isn't guaranteed to match pio.count as userspace + * can modify ECX before rerunning the vCPU. Ignore any such + * shenanigans as KVM doesn't support modifying the rep count, + * and the emulator ensures @count doesn't overflow the buffer. + */ } else { int r = __emulator_pio_in(vcpu, size, port, count); if (!r) @@ -7086,7 +7137,6 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, /* Results already available, fall through. */ } - WARN_ON(count != vcpu->arch.pio.count); complete_emulator_pio_in(vcpu, val); return 1; } @@ -8776,10 +8826,9 @@ static void kvm_apicv_init(struct kvm *kvm) { init_rwsem(&kvm->arch.apicv_update_lock); - if (enable_apicv) - clear_bit(APICV_INHIBIT_REASON_DISABLE, - &kvm->arch.apicv_inhibit_reasons); - else + set_bit(APICV_INHIBIT_REASON_ABSENT, + &kvm->arch.apicv_inhibit_reasons); + if (!enable_apicv) set_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); } @@ -8952,14 +9001,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - /* - * if_flag is obsolete and useless, so do not bother - * setting it for SEV-ES guests. Userspace can just - * use kvm_run->ready_for_interrupt_injection. - */ - kvm_run->if_flag = !vcpu->arch.guest_state_protected - && (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - + kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu); kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); @@ -9528,8 +9570,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -9648,10 +9689,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* Flushing all ASIDs flushes the current ASID... */ kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); - if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) - kvm_vcpu_flush_tlb_guest(vcpu); + kvm_service_local_tlb_flush_requests(vcpu); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -9802,10 +9840,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* * This handles the case where a posted interrupt was - * notified with kvm_vcpu_kick. + * notified with kvm_vcpu_kick. Assigned devices can + * use the POSTED_INTR_VECTOR even if APICv is disabled, + * so do it even if APICv is disabled on this vCPU. */ - if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + if (kvm_lapic_enabled(vcpu)) + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; @@ -9849,8 +9889,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + if (kvm_lapic_enabled(vcpu)) + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 997669ae9caa..4abcd8d9836d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -103,6 +103,7 @@ static inline unsigned int __shrink_ple_window(unsigned int val, #define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL +void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) @@ -185,12 +186,6 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; } -static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.tlb_flush; - static_call(kvm_x86_tlb_flush_current)(vcpu); -} - static inline int is_pae(struct kvm_vcpu *vcpu) { return kvm_read_cr4_bits(vcpu, X86_CR4_PAE); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 5864219221ca..fe3d3061fc11 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -2,9 +2,11 @@ # Kernel does not boot with instrumentation of tlb.c and mem_encrypt*.c KCOV_INSTRUMENT_tlb.o := n KCOV_INSTRUMENT_mem_encrypt.o := n +KCOV_INSTRUMENT_mem_encrypt_amd.o := n KCOV_INSTRUMENT_mem_encrypt_identity.o := n KASAN_SANITIZE_mem_encrypt.o := n +KASAN_SANITIZE_mem_encrypt_amd.o := n KASAN_SANITIZE_mem_encrypt_identity.o := n # Disable KCSAN entirely, because otherwise we get warnings that some functions @@ -13,6 +15,7 @@ KCSAN_SANITIZE := n ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_mem_encrypt.o = -pg +CFLAGS_REMOVE_mem_encrypt_amd.o = -pg CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif @@ -52,6 +55,8 @@ obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o -obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o +obj-$(CONFIG_X86_MEM_ENCRYPT) += mem_encrypt.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_amd.o + obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_identity.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 35487305d8af..50d209939c66 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -1,419 +1,18 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * AMD Memory Encryption Support + * Memory Encryption Support Common Code * * Copyright (C) 2016 Advanced Micro Devices, Inc. * * Author: Tom Lendacky <thomas.lendacky@amd.com> */ -#define DISABLE_BRANCH_PROFILING - -#include <linux/linkage.h> -#include <linux/init.h> -#include <linux/mm.h> #include <linux/dma-direct.h> +#include <linux/dma-mapping.h> #include <linux/swiotlb.h> +#include <linux/cc_platform.h> #include <linux/mem_encrypt.h> -#include <linux/device.h> -#include <linux/kernel.h> -#include <linux/bitops.h> -#include <linux/dma-mapping.h> #include <linux/virtio_config.h> -#include <linux/cc_platform.h> - -#include <asm/tlbflush.h> -#include <asm/fixmap.h> -#include <asm/setup.h> -#include <asm/bootparam.h> -#include <asm/set_memory.h> -#include <asm/cacheflush.h> -#include <asm/processor-flags.h> -#include <asm/msr.h> -#include <asm/cmdline.h> - -#include "mm_internal.h" - -/* - * Since SME related variables are set early in the boot process they must - * reside in the .data section so as not to be zeroed out when the .bss - * section is later cleared. - */ -u64 sme_me_mask __section(".data") = 0; -u64 sev_status __section(".data") = 0; -u64 sev_check_data __section(".data") = 0; -EXPORT_SYMBOL(sme_me_mask); -DEFINE_STATIC_KEY_FALSE(sev_enable_key); -EXPORT_SYMBOL_GPL(sev_enable_key); - -/* Buffer used for early in-place encryption by BSP, no locking needed */ -static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE); - -/* - * This routine does not change the underlying encryption setting of the - * page(s) that map this memory. It assumes that eventually the memory is - * meant to be accessed as either encrypted or decrypted but the contents - * are currently not in the desired state. - * - * This routine follows the steps outlined in the AMD64 Architecture - * Programmer's Manual Volume 2, Section 7.10.8 Encrypt-in-Place. - */ -static void __init __sme_early_enc_dec(resource_size_t paddr, - unsigned long size, bool enc) -{ - void *src, *dst; - size_t len; - - if (!sme_me_mask) - return; - - wbinvd(); - - /* - * There are limited number of early mapping slots, so map (at most) - * one page at time. - */ - while (size) { - len = min_t(size_t, sizeof(sme_early_buffer), size); - - /* - * Create mappings for the current and desired format of - * the memory. Use a write-protected mapping for the source. - */ - src = enc ? early_memremap_decrypted_wp(paddr, len) : - early_memremap_encrypted_wp(paddr, len); - - dst = enc ? early_memremap_encrypted(paddr, len) : - early_memremap_decrypted(paddr, len); - - /* - * If a mapping can't be obtained to perform the operation, - * then eventual access of that area in the desired mode - * will cause a crash. - */ - BUG_ON(!src || !dst); - - /* - * Use a temporary buffer, of cache-line multiple size, to - * avoid data corruption as documented in the APM. - */ - memcpy(sme_early_buffer, src, len); - memcpy(dst, sme_early_buffer, len); - - early_memunmap(dst, len); - early_memunmap(src, len); - - paddr += len; - size -= len; - } -} - -void __init sme_early_encrypt(resource_size_t paddr, unsigned long size) -{ - __sme_early_enc_dec(paddr, size, true); -} - -void __init sme_early_decrypt(resource_size_t paddr, unsigned long size) -{ - __sme_early_enc_dec(paddr, size, false); -} - -static void __init __sme_early_map_unmap_mem(void *vaddr, unsigned long size, - bool map) -{ - unsigned long paddr = (unsigned long)vaddr - __PAGE_OFFSET; - pmdval_t pmd_flags, pmd; - - /* Use early_pmd_flags but remove the encryption mask */ - pmd_flags = __sme_clr(early_pmd_flags); - - do { - pmd = map ? (paddr & PMD_MASK) + pmd_flags : 0; - __early_make_pgtable((unsigned long)vaddr, pmd); - - vaddr += PMD_SIZE; - paddr += PMD_SIZE; - size = (size <= PMD_SIZE) ? 0 : size - PMD_SIZE; - } while (size); - - flush_tlb_local(); -} - -void __init sme_unmap_bootdata(char *real_mode_data) -{ - struct boot_params *boot_data; - unsigned long cmdline_paddr; - - if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) - return; - - /* Get the command line address before unmapping the real_mode_data */ - boot_data = (struct boot_params *)real_mode_data; - cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32); - - __sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), false); - - if (!cmdline_paddr) - return; - - __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, false); -} - -void __init sme_map_bootdata(char *real_mode_data) -{ - struct boot_params *boot_data; - unsigned long cmdline_paddr; - - if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) - return; - - __sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), true); - - /* Get the command line address after mapping the real_mode_data */ - boot_data = (struct boot_params *)real_mode_data; - cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32); - - if (!cmdline_paddr) - return; - - __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true); -} - -void __init sme_early_init(void) -{ - unsigned int i; - - if (!sme_me_mask) - return; - - early_pmd_flags = __sme_set(early_pmd_flags); - - __supported_pte_mask = __sme_set(__supported_pte_mask); - - /* Update the protection map with memory encryption mask */ - for (i = 0; i < ARRAY_SIZE(protection_map); i++) - protection_map[i] = pgprot_encrypted(protection_map[i]); - - if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) - swiotlb_force = SWIOTLB_FORCE; -} - -void __init sev_setup_arch(void) -{ - phys_addr_t total_mem = memblock_phys_mem_size(); - unsigned long size; - - if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) - return; - - /* - * For SEV, all DMA has to occur via shared/unencrypted pages. - * SEV uses SWIOTLB to make this happen without changing device - * drivers. However, depending on the workload being run, the - * default 64MB of SWIOTLB may not be enough and SWIOTLB may - * run out of buffers for DMA, resulting in I/O errors and/or - * performance degradation especially with high I/O workloads. - * - * Adjust the default size of SWIOTLB for SEV guests using - * a percentage of guest memory for SWIOTLB buffers. - * Also, as the SWIOTLB bounce buffer memory is allocated - * from low memory, ensure that the adjusted size is within - * the limits of low available memory. - * - * The percentage of guest memory used here for SWIOTLB buffers - * is more of an approximation of the static adjustment which - * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6% - */ - size = total_mem * 6 / 100; - size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G); - swiotlb_adjust_size(size); -} - -static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) -{ - unsigned long pfn = 0; - pgprot_t prot; - - switch (level) { - case PG_LEVEL_4K: - pfn = pte_pfn(*kpte); - prot = pte_pgprot(*kpte); - break; - case PG_LEVEL_2M: - pfn = pmd_pfn(*(pmd_t *)kpte); - prot = pmd_pgprot(*(pmd_t *)kpte); - break; - case PG_LEVEL_1G: - pfn = pud_pfn(*(pud_t *)kpte); - prot = pud_pgprot(*(pud_t *)kpte); - break; - default: - WARN_ONCE(1, "Invalid level for kpte\n"); - return 0; - } - - if (ret_prot) - *ret_prot = prot; - - return pfn; -} - -void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc) -{ -#ifdef CONFIG_PARAVIRT - unsigned long sz = npages << PAGE_SHIFT; - unsigned long vaddr_end = vaddr + sz; - - while (vaddr < vaddr_end) { - int psize, pmask, level; - unsigned long pfn; - pte_t *kpte; - - kpte = lookup_address(vaddr, &level); - if (!kpte || pte_none(*kpte)) { - WARN_ONCE(1, "kpte lookup for vaddr\n"); - return; - } - - pfn = pg_level_to_pfn(level, kpte, NULL); - if (!pfn) - continue; - - psize = page_level_size(level); - pmask = page_level_mask(level); - - notify_page_enc_status_changed(pfn, psize >> PAGE_SHIFT, enc); - - vaddr = (vaddr & pmask) + psize; - } -#endif -} - -static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) -{ - pgprot_t old_prot, new_prot; - unsigned long pfn, pa, size; - pte_t new_pte; - - pfn = pg_level_to_pfn(level, kpte, &old_prot); - if (!pfn) - return; - - new_prot = old_prot; - if (enc) - pgprot_val(new_prot) |= _PAGE_ENC; - else - pgprot_val(new_prot) &= ~_PAGE_ENC; - - /* If prot is same then do nothing. */ - if (pgprot_val(old_prot) == pgprot_val(new_prot)) - return; - - pa = pfn << PAGE_SHIFT; - size = page_level_size(level); - - /* - * We are going to perform in-place en-/decryption and change the - * physical page attribute from C=1 to C=0 or vice versa. Flush the - * caches to ensure that data gets accessed with the correct C-bit. - */ - clflush_cache_range(__va(pa), size); - - /* Encrypt/decrypt the contents in-place */ - if (enc) - sme_early_encrypt(pa, size); - else - sme_early_decrypt(pa, size); - - /* Change the page encryption mask. */ - new_pte = pfn_pte(pfn, new_prot); - set_pte_atomic(kpte, new_pte); -} - -static int __init early_set_memory_enc_dec(unsigned long vaddr, - unsigned long size, bool enc) -{ - unsigned long vaddr_end, vaddr_next, start; - unsigned long psize, pmask; - int split_page_size_mask; - int level, ret; - pte_t *kpte; - - start = vaddr; - vaddr_next = vaddr; - vaddr_end = vaddr + size; - - for (; vaddr < vaddr_end; vaddr = vaddr_next) { - kpte = lookup_address(vaddr, &level); - if (!kpte || pte_none(*kpte)) { - ret = 1; - goto out; - } - - if (level == PG_LEVEL_4K) { - __set_clr_pte_enc(kpte, level, enc); - vaddr_next = (vaddr & PAGE_MASK) + PAGE_SIZE; - continue; - } - - psize = page_level_size(level); - pmask = page_level_mask(level); - - /* - * Check whether we can change the large page in one go. - * We request a split when the address is not aligned and - * the number of pages to set/clear encryption bit is smaller - * than the number of pages in the large page. - */ - if (vaddr == (vaddr & pmask) && - ((vaddr_end - vaddr) >= psize)) { - __set_clr_pte_enc(kpte, level, enc); - vaddr_next = (vaddr & pmask) + psize; - continue; - } - - /* - * The virtual address is part of a larger page, create the next - * level page table mapping (4K or 2M). If it is part of a 2M - * page then we request a split of the large page into 4K - * chunks. A 1GB large page is split into 2M pages, resp. - */ - if (level == PG_LEVEL_2M) - split_page_size_mask = 0; - else - split_page_size_mask = 1 << PG_LEVEL_2M; - - /* - * kernel_physical_mapping_change() does not flush the TLBs, so - * a TLB flush is required after we exit from the for loop. - */ - kernel_physical_mapping_change(__pa(vaddr & pmask), - __pa((vaddr_end & pmask) + psize), - split_page_size_mask); - } - - ret = 0; - - notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc); -out: - __flush_tlb_all(); - return ret; -} - -int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) -{ - return early_set_memory_enc_dec(vaddr, size, false); -} - -int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) -{ - return early_set_memory_enc_dec(vaddr, size, true); -} - -void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) -{ - notify_range_enc_status_changed(vaddr, npages, enc); -} /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) @@ -441,30 +40,6 @@ bool force_dma_unencrypted(struct device *dev) return false; } -void __init mem_encrypt_free_decrypted_mem(void) -{ - unsigned long vaddr, vaddr_end, npages; - int r; - - vaddr = (unsigned long)__start_bss_decrypted_unused; - vaddr_end = (unsigned long)__end_bss_decrypted; - npages = (vaddr_end - vaddr) >> PAGE_SHIFT; - - /* - * The unused memory range was mapped decrypted, change the encryption - * attribute from decrypted to encrypted before freeing it. - */ - if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { - r = set_memory_encrypted(vaddr, npages); - if (r) { - pr_warn("failed to free unused decrypted pages\n"); - return; - } - } - - free_init_pages("unused decrypted", vaddr, vaddr_end); -} - static void print_mem_encrypt_feature_info(void) { pr_info("AMD Memory Encryption Features active:"); @@ -493,20 +68,12 @@ static void print_mem_encrypt_feature_info(void) /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void) { - if (!sme_me_mask) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return; /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ swiotlb_update_mem_attributes(); - /* - * With SEV, we need to unroll the rep string I/O instructions, - * but SEV-ES supports them through the #VC handler. - */ - if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) && - !cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) - static_branch_enable(&sev_enable_key); - print_mem_encrypt_feature_info(); } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c new file mode 100644 index 000000000000..2b2d018ea345 --- /dev/null +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -0,0 +1,438 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + */ + +#define DISABLE_BRANCH_PROFILING + +#include <linux/linkage.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/dma-direct.h> +#include <linux/swiotlb.h> +#include <linux/mem_encrypt.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/dma-mapping.h> +#include <linux/virtio_config.h> +#include <linux/cc_platform.h> + +#include <asm/tlbflush.h> +#include <asm/fixmap.h> +#include <asm/setup.h> +#include <asm/bootparam.h> +#include <asm/set_memory.h> +#include <asm/cacheflush.h> +#include <asm/processor-flags.h> +#include <asm/msr.h> +#include <asm/cmdline.h> + +#include "mm_internal.h" + +/* + * Since SME related variables are set early in the boot process they must + * reside in the .data section so as not to be zeroed out when the .bss + * section is later cleared. + */ +u64 sme_me_mask __section(".data") = 0; +u64 sev_status __section(".data") = 0; +u64 sev_check_data __section(".data") = 0; +EXPORT_SYMBOL(sme_me_mask); + +/* Buffer used for early in-place encryption by BSP, no locking needed */ +static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE); + +/* + * This routine does not change the underlying encryption setting of the + * page(s) that map this memory. It assumes that eventually the memory is + * meant to be accessed as either encrypted or decrypted but the contents + * are currently not in the desired state. + * + * This routine follows the steps outlined in the AMD64 Architecture + * Programmer's Manual Volume 2, Section 7.10.8 Encrypt-in-Place. + */ +static void __init __sme_early_enc_dec(resource_size_t paddr, + unsigned long size, bool enc) +{ + void *src, *dst; + size_t len; + + if (!sme_me_mask) + return; + + wbinvd(); + + /* + * There are limited number of early mapping slots, so map (at most) + * one page at time. + */ + while (size) { + len = min_t(size_t, sizeof(sme_early_buffer), size); + + /* + * Create mappings for the current and desired format of + * the memory. Use a write-protected mapping for the source. + */ + src = enc ? early_memremap_decrypted_wp(paddr, len) : + early_memremap_encrypted_wp(paddr, len); + + dst = enc ? early_memremap_encrypted(paddr, len) : + early_memremap_decrypted(paddr, len); + + /* + * If a mapping can't be obtained to perform the operation, + * then eventual access of that area in the desired mode + * will cause a crash. + */ + BUG_ON(!src || !dst); + + /* + * Use a temporary buffer, of cache-line multiple size, to + * avoid data corruption as documented in the APM. + */ + memcpy(sme_early_buffer, src, len); + memcpy(dst, sme_early_buffer, len); + + early_memunmap(dst, len); + early_memunmap(src, len); + + paddr += len; + size -= len; + } +} + +void __init sme_early_encrypt(resource_size_t paddr, unsigned long size) +{ + __sme_early_enc_dec(paddr, size, true); +} + +void __init sme_early_decrypt(resource_size_t paddr, unsigned long size) +{ + __sme_early_enc_dec(paddr, size, false); +} + +static void __init __sme_early_map_unmap_mem(void *vaddr, unsigned long size, + bool map) +{ + unsigned long paddr = (unsigned long)vaddr - __PAGE_OFFSET; + pmdval_t pmd_flags, pmd; + + /* Use early_pmd_flags but remove the encryption mask */ + pmd_flags = __sme_clr(early_pmd_flags); + + do { + pmd = map ? (paddr & PMD_MASK) + pmd_flags : 0; + __early_make_pgtable((unsigned long)vaddr, pmd); + + vaddr += PMD_SIZE; + paddr += PMD_SIZE; + size = (size <= PMD_SIZE) ? 0 : size - PMD_SIZE; + } while (size); + + flush_tlb_local(); +} + +void __init sme_unmap_bootdata(char *real_mode_data) +{ + struct boot_params *boot_data; + unsigned long cmdline_paddr; + + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) + return; + + /* Get the command line address before unmapping the real_mode_data */ + boot_data = (struct boot_params *)real_mode_data; + cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32); + + __sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), false); + + if (!cmdline_paddr) + return; + + __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, false); +} + +void __init sme_map_bootdata(char *real_mode_data) +{ + struct boot_params *boot_data; + unsigned long cmdline_paddr; + + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) + return; + + __sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), true); + + /* Get the command line address after mapping the real_mode_data */ + boot_data = (struct boot_params *)real_mode_data; + cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32); + + if (!cmdline_paddr) + return; + + __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true); +} + +void __init sme_early_init(void) +{ + unsigned int i; + + if (!sme_me_mask) + return; + + early_pmd_flags = __sme_set(early_pmd_flags); + + __supported_pte_mask = __sme_set(__supported_pte_mask); + + /* Update the protection map with memory encryption mask */ + for (i = 0; i < ARRAY_SIZE(protection_map); i++) + protection_map[i] = pgprot_encrypted(protection_map[i]); + + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + swiotlb_force = SWIOTLB_FORCE; +} + +void __init sev_setup_arch(void) +{ + phys_addr_t total_mem = memblock_phys_mem_size(); + unsigned long size; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + return; + + /* + * For SEV, all DMA has to occur via shared/unencrypted pages. + * SEV uses SWIOTLB to make this happen without changing device + * drivers. However, depending on the workload being run, the + * default 64MB of SWIOTLB may not be enough and SWIOTLB may + * run out of buffers for DMA, resulting in I/O errors and/or + * performance degradation especially with high I/O workloads. + * + * Adjust the default size of SWIOTLB for SEV guests using + * a percentage of guest memory for SWIOTLB buffers. + * Also, as the SWIOTLB bounce buffer memory is allocated + * from low memory, ensure that the adjusted size is within + * the limits of low available memory. + * + * The percentage of guest memory used here for SWIOTLB buffers + * is more of an approximation of the static adjustment which + * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6% + */ + size = total_mem * 6 / 100; + size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G); + swiotlb_adjust_size(size); +} + +static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) +{ + unsigned long pfn = 0; + pgprot_t prot; + + switch (level) { + case PG_LEVEL_4K: + pfn = pte_pfn(*kpte); + prot = pte_pgprot(*kpte); + break; + case PG_LEVEL_2M: + pfn = pmd_pfn(*(pmd_t *)kpte); + prot = pmd_pgprot(*(pmd_t *)kpte); + break; + case PG_LEVEL_1G: + pfn = pud_pfn(*(pud_t *)kpte); + prot = pud_pgprot(*(pud_t *)kpte); + break; + default: + WARN_ONCE(1, "Invalid level for kpte\n"); + return 0; + } + + if (ret_prot) + *ret_prot = prot; + + return pfn; +} + +void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc) +{ +#ifdef CONFIG_PARAVIRT + unsigned long sz = npages << PAGE_SHIFT; + unsigned long vaddr_end = vaddr + sz; + + while (vaddr < vaddr_end) { + int psize, pmask, level; + unsigned long pfn; + pte_t *kpte; + + kpte = lookup_address(vaddr, &level); + if (!kpte || pte_none(*kpte)) { + WARN_ONCE(1, "kpte lookup for vaddr\n"); + return; + } + + pfn = pg_level_to_pfn(level, kpte, NULL); + if (!pfn) + continue; + + psize = page_level_size(level); + pmask = page_level_mask(level); + + notify_page_enc_status_changed(pfn, psize >> PAGE_SHIFT, enc); + + vaddr = (vaddr & pmask) + psize; + } +#endif +} + +static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) +{ + pgprot_t old_prot, new_prot; + unsigned long pfn, pa, size; + pte_t new_pte; + + pfn = pg_level_to_pfn(level, kpte, &old_prot); + if (!pfn) + return; + + new_prot = old_prot; + if (enc) + pgprot_val(new_prot) |= _PAGE_ENC; + else + pgprot_val(new_prot) &= ~_PAGE_ENC; + + /* If prot is same then do nothing. */ + if (pgprot_val(old_prot) == pgprot_val(new_prot)) + return; + + pa = pfn << PAGE_SHIFT; + size = page_level_size(level); + + /* + * We are going to perform in-place en-/decryption and change the + * physical page attribute from C=1 to C=0 or vice versa. Flush the + * caches to ensure that data gets accessed with the correct C-bit. + */ + clflush_cache_range(__va(pa), size); + + /* Encrypt/decrypt the contents in-place */ + if (enc) + sme_early_encrypt(pa, size); + else + sme_early_decrypt(pa, size); + + /* Change the page encryption mask. */ + new_pte = pfn_pte(pfn, new_prot); + set_pte_atomic(kpte, new_pte); +} + +static int __init early_set_memory_enc_dec(unsigned long vaddr, + unsigned long size, bool enc) +{ + unsigned long vaddr_end, vaddr_next, start; + unsigned long psize, pmask; + int split_page_size_mask; + int level, ret; + pte_t *kpte; + + start = vaddr; + vaddr_next = vaddr; + vaddr_end = vaddr + size; + + for (; vaddr < vaddr_end; vaddr = vaddr_next) { + kpte = lookup_address(vaddr, &level); + if (!kpte || pte_none(*kpte)) { + ret = 1; + goto out; + } + + if (level == PG_LEVEL_4K) { + __set_clr_pte_enc(kpte, level, enc); + vaddr_next = (vaddr & PAGE_MASK) + PAGE_SIZE; + continue; + } + + psize = page_level_size(level); + pmask = page_level_mask(level); + + /* + * Check whether we can change the large page in one go. + * We request a split when the address is not aligned and + * the number of pages to set/clear encryption bit is smaller + * than the number of pages in the large page. + */ + if (vaddr == (vaddr & pmask) && + ((vaddr_end - vaddr) >= psize)) { + __set_clr_pte_enc(kpte, level, enc); + vaddr_next = (vaddr & pmask) + psize; + continue; + } + + /* + * The virtual address is part of a larger page, create the next + * level page table mapping (4K or 2M). If it is part of a 2M + * page then we request a split of the large page into 4K + * chunks. A 1GB large page is split into 2M pages, resp. + */ + if (level == PG_LEVEL_2M) + split_page_size_mask = 0; + else + split_page_size_mask = 1 << PG_LEVEL_2M; + + /* + * kernel_physical_mapping_change() does not flush the TLBs, so + * a TLB flush is required after we exit from the for loop. + */ + kernel_physical_mapping_change(__pa(vaddr & pmask), + __pa((vaddr_end & pmask) + psize), + split_page_size_mask); + } + + ret = 0; + + notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc); +out: + __flush_tlb_all(); + return ret; +} + +int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) +{ + return early_set_memory_enc_dec(vaddr, size, false); +} + +int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) +{ + return early_set_memory_enc_dec(vaddr, size, true); +} + +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) +{ + notify_range_enc_status_changed(vaddr, npages, enc); +} + +void __init mem_encrypt_free_decrypted_mem(void) +{ + unsigned long vaddr, vaddr_end, npages; + int r; + + vaddr = (unsigned long)__start_bss_decrypted_unused; + vaddr_end = (unsigned long)__end_bss_decrypted; + npages = (vaddr_end - vaddr) >> PAGE_SHIFT; + + /* + * The unused memory range was mapped decrypted, change the encryption + * attribute from decrypted to encrypted before freeing it. + */ + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { + r = set_memory_encrypted(vaddr, npages); + if (r) { + pr_warn("failed to free unused decrypted pages\n"); + return; + } + } + + free_init_pages("unused decrypted", vaddr, vaddr_end); +} diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 726700fabca6..bafe36e69227 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1252,19 +1252,54 @@ st: if (is_imm8(insn->off)) case BPF_LDX | BPF_MEM | BPF_DW: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { - /* test src_reg, src_reg */ - maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */ - EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg)); - /* jne start_of_ldx */ - EMIT2(X86_JNE, 0); + /* Though the verifier prevents negative insn->off in BPF_PROBE_MEM + * add abs(insn->off) to the limit to make sure that negative + * offset won't be an issue. + * insn->off is s16, so it won't affect valid pointers. + */ + u64 limit = TASK_SIZE_MAX + PAGE_SIZE + abs(insn->off); + u8 *end_of_jmp1, *end_of_jmp2; + + /* Conservatively check that src_reg + insn->off is a kernel address: + * 1. src_reg + insn->off >= limit + * 2. src_reg + insn->off doesn't become small positive. + * Cannot do src_reg + insn->off >= limit in one branch, + * since it needs two spare registers, but JIT has only one. + */ + + /* movabsq r11, limit */ + EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); + EMIT((u32)limit, 4); + EMIT(limit >> 32, 4); + /* cmp src_reg, r11 */ + maybe_emit_mod(&prog, src_reg, AUX_REG, true); + EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); + /* if unsigned '<' goto end_of_jmp2 */ + EMIT2(X86_JB, 0); + end_of_jmp1 = prog; + + /* mov r11, src_reg */ + emit_mov_reg(&prog, true, AUX_REG, src_reg); + /* add r11, insn->off */ + maybe_emit_1mod(&prog, AUX_REG, true); + EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); + /* jmp if not carry to start_of_ldx + * Otherwise ERR_PTR(-EINVAL) + 128 will be the user addr + * that has to be rejected. + */ + EMIT2(0x73 /* JNC */, 0); + end_of_jmp2 = prog; + /* xor dst_reg, dst_reg */ emit_mov_imm32(&prog, false, dst_reg, 0); /* jmp byte_after_ldx */ EMIT2(0xEB, 0); - /* populate jmp_offset for JNE above */ - temp[4] = prog - temp - 5 /* sizeof(test + jne) */; + /* populate jmp_offset for JB above to jump to xor dst_reg */ + end_of_jmp1[-1] = end_of_jmp2 - end_of_jmp1; + /* populate jmp_offset for JNC above to jump to start_of_ldx */ start_of_ldx = prog; + end_of_jmp2[-1] = start_of_ldx - end_of_jmp2; } emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { @@ -1305,7 +1340,7 @@ st: if (is_imm8(insn->off)) * End result: x86 insn "mov rbx, qword ptr [rax+0x14]" * of 4 bytes will be ignored and rbx will be zero inited. */ - ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8); + ex->fixup = (prog - start_of_ldx) | (reg2pt_regs[dst_reg] << 8); } break; diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts index 0ac3d4357136..65fa3d866226 100644 --- a/arch/x86/platform/ce4100/falconfalls.dts +++ b/arch/x86/platform/ce4100/falconfalls.dts @@ -249,7 +249,7 @@ gpio@26 { #gpio-cells = <2>; - compatible = "ti,pcf8575"; + compatible = "nxp,pcf8575"; reg = <0x26>; gpio-controller; }; @@ -263,7 +263,7 @@ gpio@26 { #gpio-cells = <2>; - compatible = "ti,pcf8575"; + compatible = "nxp,pcf8575"; reg = <0x26>; gpio-controller; }; diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index b15ebfe40a73..b0b848d6933a 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -277,7 +277,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } - new = early_memremap(data.phys_map, data.size); + new = early_memremap_prot(data.phys_map, data.size, + pgprot_val(pgprot_encrypted(FIXMAP_PAGE_NORMAL))); if (!new) { pr_err("Failed to map new boot services memmap\n"); return; diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 6d98609387ba..c5e29db02a46 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -98,6 +98,7 @@ static void __init setup_real_mode(void) #ifdef CONFIG_X86_64 u64 *trampoline_pgd; u64 efer; + int i; #endif base = (unsigned char *)real_mode_header; @@ -154,8 +155,17 @@ static void __init setup_real_mode(void) trampoline_header->flags = 0; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); + + /* Map the real mode stub as virtual == physical */ trampoline_pgd[0] = trampoline_pgd_entry.pgd; - trampoline_pgd[511] = init_top_pgt[511].pgd; + + /* + * Include the entirety of the kernel mapping into the trampoline + * PGD. This way, all mappings present in the normal kernel page + * tables are usable while running on trampoline_pgd. + */ + for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++) + trampoline_pgd[i] = init_top_pgt[i].pgd; #endif sme_sev_setup_real_mode(trampoline_header); diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index c736cf2ac76b..e2c5b296120d 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -68,7 +68,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "(__parainstructions|__alt_instructions)(_end)?|" "(__iommu_table|__apicdrivers|__smp_locks)(_end)?|" "__(start|end)_pci_.*|" -#if CONFIG_FW_LOADER_BUILTIN +#if CONFIG_FW_LOADER "__(start|end)_builtin_fw|" #endif "__(start|stop)___ksymtab(_gpl)?|" diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 220dd9678494..444d824775f6 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <../entry/calling.h> .pushsection .noinstr.text, "ax" /* @@ -193,6 +194,25 @@ SYM_CODE_START(xen_iret) SYM_CODE_END(xen_iret) /* + * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is + * also the kernel stack. Reusing swapgs_restore_regs_and_return_to_usermode() + * in XEN pv would cause %rsp to move up to the top of the kernel stack and + * leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI + * interrupts. And swapgs_restore_regs_and_return_to_usermode() pushing the IRET + * frame at the same address is useless. + */ +SYM_CODE_START(xenpv_restore_regs_and_return_to_usermode) + UNWIND_HINT_REGS + POP_REGS + + /* stackleak_erase() can work safely on the kernel stack. */ + STACKLEAK_ERASE_NOCLOBBER + + addq $8, %rsp /* skip regs->orig_ax */ + jmp xen_iret +SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode) + +/* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: * - kernel gs |