diff options
Diffstat (limited to 'arch/x86')
66 files changed, 992 insertions, 298 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 15425c9bdc2b..2df0ae2a5e5d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -137,7 +137,7 @@ config X86 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_NO_INSTR select ARCH_WANT_GENERAL_HUGETLB - select ARCH_WANT_HUGE_PMD_SHARE + select ARCH_WANT_HUGE_PMD_SHARE if X86_64 select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if X86_64 select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64 @@ -2760,6 +2760,15 @@ config MITIGATION_ITS disabled, mitigation cannot be enabled via cmdline. See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst> +config MITIGATION_TSA + bool "Mitigate Transient Scheduler Attacks" + depends on CPU_SUP_AMD + default y + help + Enable mitigation for Transient Scheduler Attacks. TSA is a hardware + security vulnerability on AMD CPUs which can lead to forwarding of + invalid info to subsequent instructions and thus can affect their + timing and thereby cause a leakage. endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index d75237ba7ce9..5660d3229d29 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -115,5 +115,18 @@ void get_cpuflags(void) cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6], &cpu.flags[1]); } + + if (max_amd_level >= 0x8000001f) { + u32 ebx; + + /* + * The X86_FEATURE_COHERENCY_SFW_NO feature bit is in + * the virtualization flags entry (word 8) and set by + * scattered.c, so the bit needs to be explicitly set. + */ + cpuid(0x8000001f, &ignored, &ebx, &ignored, &ignored); + if (ebx & BIT(31)) + set_bit(X86_FEATURE_COHERENCY_SFW_NO, cpu.flags); + } } } diff --git a/arch/x86/coco/sev/shared.c b/arch/x86/coco/sev/shared.c index 71de53194089..f5936da235c7 100644 --- a/arch/x86/coco/sev/shared.c +++ b/arch/x86/coco/sev/shared.c @@ -1243,6 +1243,24 @@ static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svs __pval_terminate(pfn, action, page_size, ret, svsm_ret); } +static inline void sev_evict_cache(void *va, int npages) +{ + volatile u8 val __always_unused; + u8 *bytes = va; + int page_idx; + + /* + * For SEV guests, a read from the first/last cache-lines of a 4K page + * using the guest key is sufficient to cause a flush of all cache-lines + * associated with that 4K page without incurring all the overhead of a + * full CLFLUSH sequence. + */ + for (page_idx = 0; page_idx < npages; page_idx++) { + val = bytes[page_idx * PAGE_SIZE]; + val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; + } +} + static void svsm_pval_4k_page(unsigned long paddr, bool validate) { struct svsm_pvalidate_call *pc; @@ -1295,6 +1313,13 @@ static void pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, bool val if (ret) __pval_terminate(PHYS_PFN(paddr), validate, RMP_PG_SIZE_4K, ret, 0); } + + /* + * If validating memory (making it private) and affected by the + * cache-coherency vulnerability, perform the cache eviction mitigation. + */ + if (validate && !has_cpuflag(X86_FEATURE_COHERENCY_SFW_NO)) + sev_evict_cache((void *)vaddr, 1); } static void pval_pages(struct snp_psc_desc *desc) @@ -1479,10 +1504,31 @@ static void svsm_pval_pages(struct snp_psc_desc *desc) static void pvalidate_pages(struct snp_psc_desc *desc) { + struct psc_entry *e; + unsigned int i; + if (snp_vmpl) svsm_pval_pages(desc); else pval_pages(desc); + + /* + * If not affected by the cache-coherency vulnerability there is no need + * to perform the cache eviction mitigation. + */ + if (cpu_feature_enabled(X86_FEATURE_COHERENCY_SFW_NO)) + return; + + for (i = 0; i <= desc->hdr.end_entry; i++) { + e = &desc->entries[i]; + + /* + * If validating memory (making it private) perform the cache + * eviction mitigation. + */ + if (e->operation == SNP_PAGE_STATE_PRIVATE) + sev_evict_cache(pfn_to_kaddr(e->gfn), e->pagesize ? 512 : 1); + } } static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 5b96249734ad..b0d5ab951231 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -33,20 +33,20 @@ EXPORT_SYMBOL_GPL(entry_ibpb); /* * Define the VERW operand that is disguised as entry code so that - * it can be referenced with KPTI enabled. This ensure VERW can be + * it can be referenced with KPTI enabled. This ensures VERW can be * used late in exit-to-user path after page tables are switched. */ .pushsection .entry.text, "ax" .align L1_CACHE_BYTES, 0xcc -SYM_CODE_START_NOALIGN(mds_verw_sel) +SYM_CODE_START_NOALIGN(x86_verw_sel) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR .word __KERNEL_DS .align L1_CACHE_BYTES, 0xcc -SYM_CODE_END(mds_verw_sel); +SYM_CODE_END(x86_verw_sel); /* For KVM */ -EXPORT_SYMBOL_GPL(mds_verw_sel); +EXPORT_SYMBOL_GPL(x86_verw_sel); .popsection diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 95eada2994e1..239f612816e6 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -730,3 +730,36 @@ bool hv_is_hyperv_initialized(void) return hypercall_msr.enable; } EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized); + +int hv_apicid_to_vp_index(u32 apic_id) +{ + u64 control; + u64 status; + unsigned long irq_flags; + struct hv_get_vp_from_apic_id_in *input; + u32 *output, ret; + + local_irq_save(irq_flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + memset(input, 0, sizeof(*input)); + input->partition_id = HV_PARTITION_ID_SELF; + input->apic_ids[0] = apic_id; + + output = *this_cpu_ptr(hyperv_pcpu_output_arg); + + control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID; + status = hv_do_hypercall(control, input, output); + ret = output[0]; + + local_irq_restore(irq_flags); + + if (!hv_result_success(status)) { + pr_err("failed to get vp index from apic id %d, status %#llx\n", + apic_id, status); + return -EINVAL; + } + + return ret; +} +EXPORT_SYMBOL_GPL(hv_apicid_to_vp_index); diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index d04ccd4b3b4a..2510e91b29b0 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -175,41 +175,9 @@ free_lock: return ret; } -static int hv_vtl_apicid_to_vp_id(u32 apic_id) -{ - u64 control; - u64 status; - unsigned long irq_flags; - struct hv_get_vp_from_apic_id_in *input; - u32 *output, ret; - - local_irq_save(irq_flags); - - input = *this_cpu_ptr(hyperv_pcpu_input_arg); - memset(input, 0, sizeof(*input)); - input->partition_id = HV_PARTITION_ID_SELF; - input->apic_ids[0] = apic_id; - - output = (u32 *)input; - - control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID; - status = hv_do_hypercall(control, input, output); - ret = output[0]; - - local_irq_restore(irq_flags); - - if (!hv_result_success(status)) { - pr_err("failed to get vp id from apic id %d, status %#llx\n", - apic_id, status); - return -EINVAL; - } - - return ret; -} - static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { - int vp_id, cpu; + int vp_index, cpu; /* Find the logical CPU for the APIC ID */ for_each_present_cpu(cpu) { @@ -220,18 +188,18 @@ static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) return -EINVAL; pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid); - vp_id = hv_vtl_apicid_to_vp_id(apicid); + vp_index = hv_apicid_to_vp_index(apicid); - if (vp_id < 0) { + if (vp_index < 0) { pr_err("Couldn't find CPU with APIC ID %d\n", apicid); return -EINVAL; } - if (vp_id > ms_hyperv.max_vp_index) { - pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid); + if (vp_index > ms_hyperv.max_vp_index) { + pr_err("Invalid CPU id %d for APIC ID %d\n", vp_index, apicid); return -EINVAL; } - return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip); + return hv_vtl_bringup_vcpu(vp_index, cpu, start_eip); } int __init hv_vtl_early_init(void) diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c index 3215a4a07408..939b7081c5ab 100644 --- a/arch/x86/hyperv/irqdomain.c +++ b/arch/x86/hyperv/irqdomain.c @@ -192,7 +192,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_dev *dev; struct hv_interrupt_entry out_entry, *stored_entry; struct irq_cfg *cfg = irqd_cfg(data); - const cpumask_t *affinity; int cpu; u64 status; @@ -204,8 +203,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; } - affinity = irq_data_get_effective_affinity_mask(data); - cpu = cpumask_first_and(affinity, cpu_online_mask); + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data)); if (data->chip_data) { /* diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 4065f5ef3ae0..af87f440bc2a 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -10,6 +10,7 @@ #include <linux/hyperv.h> #include <linux/types.h> #include <linux/slab.h> +#include <linux/cpu.h> #include <asm/svm.h> #include <asm/sev.h> #include <asm/io.h> @@ -289,7 +290,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) free_page((unsigned long)vmsa); } -int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) +int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip) { struct sev_es_save_area *vmsa = (struct sev_es_save_area *) __get_free_page(GFP_KERNEL | __GFP_ZERO); @@ -298,10 +299,27 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) u64 ret, retry = 5; struct hv_enable_vp_vtl *start_vp_input; unsigned long flags; + int cpu, vp_index; if (!vmsa) return -ENOMEM; + /* Find the Hyper-V VP index which might be not the same as APIC ID */ + vp_index = hv_apicid_to_vp_index(apic_id); + if (vp_index < 0 || vp_index > ms_hyperv.max_vp_index) + return -EINVAL; + + /* + * Find the Linux CPU number for addressing the per-CPU data, and it + * might not be the same as APIC ID. + */ + for_each_present_cpu(cpu) { + if (arch_match_cpu_phys_id(cpu, apic_id)) + break; + } + if (cpu >= nr_cpu_ids) + return -EINVAL; + native_store_gdt(&gdtr); vmsa->gdtr.base = gdtr.address; @@ -349,7 +367,7 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) start_vp_input = (struct hv_enable_vp_vtl *)ap_start_input_arg; memset(start_vp_input, 0, sizeof(*start_vp_input)); start_vp_input->partition_id = -1; - start_vp_input->vp_index = cpu; + start_vp_input->vp_index = vp_index; start_vp_input->target_vtl.target_vtl = ms_hyperv.vtl; *(u64 *)&start_vp_input->vp_context = __pa(vmsa) | 1; diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index aa30fd8cad7f..b6099456477c 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -69,4 +69,16 @@ int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type); extern struct cpumask cpus_stop_mask; +union zen_patch_rev { + struct { + __u32 rev : 8, + stepping : 4, + model : 4, + __reserved : 4, + ext_model : 4, + ext_fam : 8; + }; + __u32 ucode_rev; +}; + #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 308e7d97135c..98e72c1391f2 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -227,6 +227,7 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ +#define X86_FEATURE_COHERENCY_SFW_NO ( 8*32+ 4) /* SNP cache coherency software work around not needed */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ @@ -455,6 +456,7 @@ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ #define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ #define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_VERW_CLEAR (20*32+ 5) /* The memory form of VERW mitigates TSA */ #define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */ #define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */ #define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */ @@ -477,6 +479,10 @@ #define X86_FEATURE_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ #define X86_FEATURE_INDIRECT_THUNK_ITS (21*32 + 6) /* Use thunk for indirect branches in lower half of cacheline */ +#define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */ +#define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */ +#define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */ + /* * BUG word(s) */ @@ -529,4 +535,5 @@ #define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #define X86_BUG_ITS X86_BUG(1*32 + 5) /* "its" CPU is affected by Indirect Target Selection */ #define X86_BUG_ITS_NATIVE_ONLY X86_BUG(1*32 + 6) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ +#define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index fdbbbfec745a..820b4aeabd0c 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -9,6 +9,14 @@ #include <asm/cpufeature.h> #include <asm/msr.h> +/* + * Define bits that are always set to 1 in DR7, only bit 10 is + * architecturally reserved to '1'. + * + * This is also the init/reset value for DR7. + */ +#define DR7_FIXED_1 0x00000400 + DECLARE_PER_CPU(unsigned long, cpu_dr7); #ifndef CONFIG_PARAVIRT_XXL @@ -100,8 +108,8 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value) static inline void hw_breakpoint_disable(void) { - /* Zero the control register for HW Breakpoint */ - set_debugreg(0UL, 7); + /* Reset the control register for HW Breakpoint */ + set_debugreg(DR7_FIXED_1, 7); /* Zero-out the individual HW breakpoint address registers */ set_debugreg(0UL, 0); @@ -125,9 +133,12 @@ static __always_inline unsigned long local_db_save(void) return 0; get_debugreg(dr7, 7); - dr7 &= ~0x400; /* architecturally set bit */ + + /* Architecturally set bit */ + dr7 &= ~DR7_FIXED_1; if (dr7) - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); + /* * Ensure the compiler doesn't lower the above statements into * the critical section; disabling breakpoints late would not diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index edebf1020e04..6bb3d9a86abe 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -92,8 +92,6 @@ struct irq_cfg { extern struct irq_cfg *irq_cfg(unsigned int irq); extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data); -extern void lock_vector_lock(void); -extern void unlock_vector_lock(void); #ifdef CONFIG_SMP extern void vector_schedule_cleanup(struct irq_cfg *); extern void irq_complete_move(struct irq_cfg *cfg); @@ -101,12 +99,16 @@ extern void irq_complete_move(struct irq_cfg *cfg); static inline void vector_schedule_cleanup(struct irq_cfg *c) { } static inline void irq_complete_move(struct irq_cfg *c) { } #endif - extern void apic_ack_edge(struct irq_data *data); -#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ + +#ifdef CONFIG_X86_LOCAL_APIC +extern void lock_vector_lock(void); +extern void unlock_vector_lock(void); +#else static inline void lock_vector_lock(void) {} static inline void unlock_vector_lock(void) {} -#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +#endif /* Statistics */ extern atomic_t irq_err_count; diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 1c2db11a2c3c..2b75fe80fcb2 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -44,13 +44,13 @@ static __always_inline void native_irq_enable(void) static __always_inline void native_safe_halt(void) { - mds_idle_clear_cpu_buffers(); + x86_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static __always_inline void native_halt(void) { - mds_idle_clear_cpu_buffers(); + x86_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index cfb22f8c451a..861d080ed4c6 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -47,7 +47,6 @@ KVM_X86_OP(set_idt) KVM_X86_OP(get_gdt) KVM_X86_OP(set_gdt) KVM_X86_OP(sync_dirty_debug_regs) -KVM_X86_OP(set_dr6) KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e4dd840e0bec..d27df86aa62c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -31,6 +31,7 @@ #include <asm/apic.h> #include <asm/pvclock-abi.h> +#include <asm/debugreg.h> #include <asm/desc.h> #include <asm/mtrr.h> #include <asm/msr-index.h> @@ -246,7 +247,6 @@ enum x86_intercept_stage; #define DR7_BP_EN_MASK 0x000000ff #define DR7_GE (1 << 9) #define DR7_GD (1 << 13) -#define DR7_FIXED_1 0x00000400 #define DR7_VOLATILE 0xffff2bff #define KVM_GUESTDBG_VALID_MASK \ @@ -1627,6 +1627,12 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; } +enum kvm_x86_run_flags { + KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0), + KVM_RUN_LOAD_GUEST_DR6 = BIT(1), + KVM_RUN_LOAD_DEBUGCTL = BIT(2), +}; + struct kvm_x86_ops { const char *name; @@ -1654,6 +1660,12 @@ struct kvm_x86_ops { void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); + /* + * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to + * match the host's value even while the guest is active. + */ + const u64 HOST_OWNED_DEBUGCTL; + void (*update_exception_bitmap)(struct kvm_vcpu *vcpu); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); @@ -1675,7 +1687,6 @@ struct kvm_x86_ops { void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); - void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); @@ -1706,7 +1717,7 @@ struct kvm_x86_ops { int (*vcpu_pre_run)(struct kvm_vcpu *vcpu); enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu, - bool force_immediate_exit); + u64 run_flags); int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5f0bc6a6d025..a42439c2ed24 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -275,11 +275,11 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry); #ifdef CONFIG_AMD_MEM_ENCRYPT bool hv_ghcb_negotiate_protocol(void); void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason); -int hv_snp_boot_ap(u32 cpu, unsigned long start_ip); +int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip); #else static inline bool hv_ghcb_negotiate_protocol(void) { return false; } static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {} -static inline int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { return 0; } +static inline int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip) { return 0; } #endif #if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) @@ -313,6 +313,7 @@ static __always_inline u64 hv_raw_get_msr(unsigned int reg) { return __rdmsr(reg); } +int hv_apicid_to_vp_index(u32 apic_id); #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} @@ -334,6 +335,7 @@ static inline void hv_set_msr(unsigned int reg, u64 value) { } static inline u64 hv_get_msr(unsigned int reg) { return 0; } static inline void hv_set_non_nested_msr(unsigned int reg, u64 value) { } static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; } +static inline int hv_apicid_to_vp_index(u32 apic_id) { return -EINVAL; } #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ac25f9eb5912..2b6e3127ef4e 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -417,6 +417,7 @@ #define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI (1UL << 12) #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 #define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) +#define DEBUGCTLMSR_RTM_DEBUG BIT(15) #define MSR_PEBS_FRONTEND 0x000003f7 @@ -621,6 +622,7 @@ #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 #define MSR_AMD_PPIN 0xc00102f1 +#define MSR_AMD64_CPUID_FN_7 0xc0011002 #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 3e4e85f71a6a..7f9a97c572fe 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -44,8 +44,6 @@ static __always_inline void __monitorx(const void *eax, unsigned long ecx, static __always_inline void __mwait(unsigned long eax, unsigned long ecx) { - mds_idle_clear_cpu_buffers(); - /* "mwait %eax, %ecx;" */ asm volatile(".byte 0x0f, 0x01, 0xc9;" :: "a" (eax), "c" (ecx)); @@ -80,7 +78,7 @@ static __always_inline void __mwait(unsigned long eax, unsigned long ecx) static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx, unsigned long ecx) { - /* No MDS buffer clear as this is AMD/HYGON only */ + /* No need for TSA buffer clearing on AMD */ /* "mwaitx %eax, %ebx, %ecx;" */ asm volatile(".byte 0x0f, 0x01, 0xfb;" @@ -98,7 +96,7 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx, */ static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx) { - mds_idle_clear_cpu_buffers(); + /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" :: "a" (eax), "c" (ecx)); @@ -116,21 +114,29 @@ static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx) */ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) { + if (need_resched()) + return; + + x86_idle_clear_cpu_buffers(); + if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) { const void *addr = ¤t_thread_info()->flags; alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr)); __monitor(addr, 0, 0); - if (!need_resched()) { - if (ecx & 1) { - __mwait(eax, ecx); - } else { - __sti_mwait(eax, ecx); - raw_local_irq_disable(); - } + if (need_resched()) + goto out; + + if (ecx & 1) { + __mwait(eax, ecx); + } else { + __sti_mwait(eax, ecx); + raw_local_irq_disable(); } } + +out: current_clr_polling(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f7bb0016d7d9..331f6a05535d 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,25 +315,31 @@ .endm /* - * Macro to execute VERW instruction that mitigate transient data sampling - * attacks such as MDS. On affected systems a microcode update overloaded VERW - * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. - * + * Macro to execute VERW insns that mitigate transient data sampling + * attacks such as MDS or TSA. On affected systems a microcode update + * overloaded VERW insns to also clear the CPU buffers. VERW clobbers + * CFLAGS.ZF. * Note: Only the memory operand variant of VERW clears the CPU buffers. */ -.macro CLEAR_CPU_BUFFERS +.macro __CLEAR_CPU_BUFFERS feature #ifdef CONFIG_X86_64 - ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF + ALTERNATIVE "", "verw x86_verw_sel(%rip)", \feature #else /* * In 32bit mode, the memory operand must be a %cs reference. The data * segments may not be usable (vm86 mode), and the stack segment may not * be flat (ESPFIX32). */ - ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF + ALTERNATIVE "", "verw %cs:x86_verw_sel", \feature #endif .endm +#define CLEAR_CPU_BUFFERS \ + __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF + +#define VM_CLEAR_CPU_BUFFERS \ + __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF_VM + #ifdef CONFIG_X86_64 .macro CLEAR_BRANCH_HISTORY ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP @@ -582,24 +588,24 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -DECLARE_STATIC_KEY_FALSE(mds_idle_clear); +DECLARE_STATIC_KEY_FALSE(cpu_buf_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); -extern u16 mds_verw_sel; +extern u16 x86_verw_sel; #include <asm/segment.h> /** - * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability + * x86_clear_cpu_buffers - Buffer clearing support for different x86 CPU vulns * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ -static __always_inline void mds_clear_cpu_buffers(void) +static __always_inline void x86_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; @@ -616,14 +622,15 @@ static __always_inline void mds_clear_cpu_buffers(void) } /** - * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability + * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS + * and TSA vulnerabilities. * * Clear CPU buffers if the corresponding static key is enabled */ -static __always_inline void mds_idle_clear_cpu_buffers(void) +static __always_inline void x86_idle_clear_cpu_buffers(void) { - if (static_branch_likely(&mds_idle_clear)) - mds_clear_cpu_buffers(); + if (static_branch_likely(&cpu_buf_idle_clear)) + x86_clear_cpu_buffers(); } #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index b5b633294061..2d13ef1f4b05 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -97,7 +97,7 @@ void tdx_init(void); typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args); -static inline u64 sc_retry(sc_func_t func, u64 fn, +static __always_inline u64 sc_retry(sc_func_t func, u64 fn, struct tdx_module_args *args) { int retry = RDRAND_RETRY_LOOPS; diff --git a/arch/x86/include/uapi/asm/debugreg.h b/arch/x86/include/uapi/asm/debugreg.h index 0007ba077c0c..41da492dfb01 100644 --- a/arch/x86/include/uapi/asm/debugreg.h +++ b/arch/x86/include/uapi/asm/debugreg.h @@ -15,7 +15,26 @@ which debugging register was responsible for the trap. The other bits are either reserved or not of interest to us. */ -/* Define reserved bits in DR6 which are always set to 1 */ +/* + * Define bits in DR6 which are set to 1 by default. + * + * This is also the DR6 architectural value following Power-up, Reset or INIT. + * + * Note, with the introduction of Bus Lock Detection (BLD) and Restricted + * Transactional Memory (RTM), the DR6 register has been modified: + * + * 1) BLD flag (bit 11) is no longer reserved to 1 if the CPU supports + * Bus Lock Detection. The assertion of a bus lock could clear it. + * + * 2) RTM flag (bit 16) is no longer reserved to 1 if the CPU supports + * restricted transactional memory. #DB occurred inside an RTM region + * could clear it. + * + * Apparently, DR6.BLD and DR6.RTM are active low bits. + * + * As a result, DR6_RESERVED is an incorrect name now, but it is kept for + * compatibility. + */ #define DR6_RESERVED (0xFFFF0FF0) #define DR_TRAP0 (0x1) /* db0 */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e432910859cb..4810271302d0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -368,6 +368,66 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c) #endif } +static bool amd_check_tsa_microcode(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + union zen_patch_rev p; + u32 min_rev = 0; + + p.ext_fam = c->x86 - 0xf; + p.model = c->x86_model; + p.ext_model = c->x86_model >> 4; + p.stepping = c->x86_stepping; + /* reserved bits are expected to be 0 in test below */ + p.__reserved = 0; + + if (cpu_has(c, X86_FEATURE_ZEN3) || + cpu_has(c, X86_FEATURE_ZEN4)) { + switch (p.ucode_rev >> 8) { + case 0xa0011: min_rev = 0x0a0011d7; break; + case 0xa0012: min_rev = 0x0a00123b; break; + case 0xa0082: min_rev = 0x0a00820d; break; + case 0xa1011: min_rev = 0x0a10114c; break; + case 0xa1012: min_rev = 0x0a10124c; break; + case 0xa1081: min_rev = 0x0a108109; break; + case 0xa2010: min_rev = 0x0a20102e; break; + case 0xa2012: min_rev = 0x0a201211; break; + case 0xa4041: min_rev = 0x0a404108; break; + case 0xa5000: min_rev = 0x0a500012; break; + case 0xa6012: min_rev = 0x0a60120a; break; + case 0xa7041: min_rev = 0x0a704108; break; + case 0xa7052: min_rev = 0x0a705208; break; + case 0xa7080: min_rev = 0x0a708008; break; + case 0xa70c0: min_rev = 0x0a70c008; break; + case 0xaa002: min_rev = 0x0aa00216; break; + default: + pr_debug("%s: ucode_rev: 0x%x, current revision: 0x%x\n", + __func__, p.ucode_rev, c->microcode); + return false; + } + } + + if (!min_rev) + return false; + + return c->microcode >= min_rev; +} + +static void tsa_init(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return; + + if (cpu_has(c, X86_FEATURE_ZEN3) || + cpu_has(c, X86_FEATURE_ZEN4)) { + if (amd_check_tsa_microcode()) + setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR); + } else { + setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO); + setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO); + } +} + static void bsp_init_amd(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -475,6 +535,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) } bsp_determine_snp(c); + + tsa_init(c); + return; warn: @@ -916,6 +979,13 @@ static void init_amd_zen2(struct cpuinfo_x86 *c) init_spectral_chicken(c); fix_erratum_1386(c); zen2_zenbleed_check(c); + + /* Disable RDSEED on AMD Cyan Skillfish because of an error. */ + if (c->x86_model == 0x47 && c->x86_stepping == 0x0) { + clear_cpu_cap(c, X86_FEATURE_RDSEED); + msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18); + pr_emerg("RDSEED is not reliable on this platform; disabling.\n"); + } } static void init_amd_zen3(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0e9ab0b9a494..31b4b73e5405 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -50,6 +50,7 @@ static void __init l1d_flush_select_mitigation(void); static void __init srso_select_mitigation(void); static void __init gds_select_mitigation(void); static void __init its_select_mitigation(void); +static void __init tsa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -70,10 +71,9 @@ void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; static void __init set_return_thunk(void *thunk) { - if (x86_return_thunk != __x86_return_thunk) - pr_warn("x86/bugs: return thunk changed\n"); - x86_return_thunk = thunk; + + pr_info("active return thunk: %ps\n", thunk); } /* Update SPEC_CTRL MSR and its cached copy unconditionally */ @@ -122,9 +122,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -/* Control MDS CPU buffer clear before idling (halt, mwait) */ -DEFINE_STATIC_KEY_FALSE(mds_idle_clear); -EXPORT_SYMBOL_GPL(mds_idle_clear); +/* Control CPU buffer clear before idling (halt, mwait) */ +DEFINE_STATIC_KEY_FALSE(cpu_buf_idle_clear); +EXPORT_SYMBOL_GPL(cpu_buf_idle_clear); /* * Controls whether l1d flush based mitigations are enabled, @@ -185,6 +185,7 @@ void __init cpu_select_mitigations(void) srso_select_mitigation(); gds_select_mitigation(); its_select_mitigation(); + tsa_select_mitigation(); } /* @@ -448,7 +449,7 @@ static void __init mmio_select_mitigation(void) * is required irrespective of SMT state. */ if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) - static_branch_enable(&mds_idle_clear); + static_branch_enable(&cpu_buf_idle_clear); /* * Check if the system has the right microcode. @@ -2092,10 +2093,10 @@ static void update_mds_branch_idle(void) return; if (sched_smt_active()) { - static_branch_enable(&mds_idle_clear); + static_branch_enable(&cpu_buf_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { - static_branch_disable(&mds_idle_clear); + static_branch_disable(&cpu_buf_idle_clear); } } @@ -2103,6 +2104,94 @@ static void update_mds_branch_idle(void) #define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" #define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n" +#undef pr_fmt +#define pr_fmt(fmt) "Transient Scheduler Attacks: " fmt + +enum tsa_mitigations { + TSA_MITIGATION_NONE, + TSA_MITIGATION_UCODE_NEEDED, + TSA_MITIGATION_USER_KERNEL, + TSA_MITIGATION_VM, + TSA_MITIGATION_FULL, +}; + +static const char * const tsa_strings[] = { + [TSA_MITIGATION_NONE] = "Vulnerable", + [TSA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TSA_MITIGATION_USER_KERNEL] = "Mitigation: Clear CPU buffers: user/kernel boundary", + [TSA_MITIGATION_VM] = "Mitigation: Clear CPU buffers: VM", + [TSA_MITIGATION_FULL] = "Mitigation: Clear CPU buffers", +}; + +static enum tsa_mitigations tsa_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_TSA) ? TSA_MITIGATION_FULL : TSA_MITIGATION_NONE; + +static int __init tsa_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + tsa_mitigation = TSA_MITIGATION_NONE; + else if (!strcmp(str, "on")) + tsa_mitigation = TSA_MITIGATION_FULL; + else if (!strcmp(str, "user")) + tsa_mitigation = TSA_MITIGATION_USER_KERNEL; + else if (!strcmp(str, "vm")) + tsa_mitigation = TSA_MITIGATION_VM; + else + pr_err("Ignoring unknown tsa=%s option.\n", str); + + return 0; +} +early_param("tsa", tsa_parse_cmdline); + +static void __init tsa_select_mitigation(void) +{ + if (tsa_mitigation == TSA_MITIGATION_NONE) + return; + + if (cpu_mitigations_off() || !boot_cpu_has_bug(X86_BUG_TSA)) { + tsa_mitigation = TSA_MITIGATION_NONE; + return; + } + + if (!boot_cpu_has(X86_FEATURE_VERW_CLEAR)) + tsa_mitigation = TSA_MITIGATION_UCODE_NEEDED; + + switch (tsa_mitigation) { + case TSA_MITIGATION_USER_KERNEL: + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + break; + + case TSA_MITIGATION_VM: + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM); + break; + + case TSA_MITIGATION_UCODE_NEEDED: + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) + goto out; + + pr_notice("Forcing mitigation on in a VM\n"); + + /* + * On the off-chance that microcode has been updated + * on the host, enable the mitigation in the guest just + * in case. + */ + fallthrough; + case TSA_MITIGATION_FULL: + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM); + break; + default: + break; + } + +out: + pr_info("%s\n", tsa_strings[tsa_mitigation]); +} + void cpu_bugs_smt_update(void) { mutex_lock(&spec_ctrl_mutex); @@ -2156,6 +2245,24 @@ void cpu_bugs_smt_update(void) break; } + switch (tsa_mitigation) { + case TSA_MITIGATION_USER_KERNEL: + case TSA_MITIGATION_VM: + case TSA_MITIGATION_FULL: + case TSA_MITIGATION_UCODE_NEEDED: + /* + * TSA-SQ can potentially lead to info leakage between + * SMT threads. + */ + if (sched_smt_active()) + static_branch_enable(&cpu_buf_idle_clear); + else + static_branch_disable(&cpu_buf_idle_clear); + break; + case TSA_MITIGATION_NONE: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -3084,6 +3191,11 @@ static ssize_t gds_show_state(char *buf) return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); } +static ssize_t tsa_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -3145,6 +3257,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_ITS: return its_show_state(buf); + case X86_BUG_TSA: + return tsa_show_state(buf); + default: break; } @@ -3229,6 +3344,11 @@ ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_att { return cpu_show_common(dev, attr, buf, X86_BUG_ITS); } + +ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TSA); +} #endif void __warn_thunk(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b48775445523..976545ec8fdc 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1233,6 +1233,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define ITS BIT(8) /* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */ #define ITS_NATIVE_ONLY BIT(9) +/* CPU is affected by Transient Scheduler Attacks */ +#define TSA BIT(10) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(INTEL_IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1280,7 +1282,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x16, RETBLEED), VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), - VULNBL_AMD(0x19, SRSO), + VULNBL_AMD(0x19, SRSO | TSA), {} }; @@ -1490,6 +1492,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY); } + if (c->x86_vendor == X86_VENDOR_AMD) { + if (!cpu_has(c, X86_FEATURE_TSA_SQ_NO) || + !cpu_has(c, X86_FEATURE_TSA_L1_NO)) { + if (cpu_matches(cpu_vuln_blacklist, TSA) || + /* Enable bug on Zen guests to allow for live migration. */ + (cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_ZEN))) + setup_force_cpu_bug(X86_BUG_TSA); + } + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -2145,20 +2157,16 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard); #endif /* CONFIG_X86_64 */ -/* - * Clear all 6 debug registers: - */ -static void clear_all_debug_regs(void) +static void initialize_debug_regs(void) { - int i; - - for (i = 0; i < 8; i++) { - /* Ignore db4, db5 */ - if ((i == 4) || (i == 5)) - continue; - - set_debugreg(0, i); - } + /* Control register first -- to make sure everything is disabled. */ + set_debugreg(DR7_FIXED_1, 7); + set_debugreg(DR6_RESERVED, 6); + /* dr5 and dr4 don't exist */ + set_debugreg(0, 3); + set_debugreg(0, 2); + set_debugreg(0, 1); + set_debugreg(0, 0); } #ifdef CONFIG_KGDB @@ -2319,7 +2327,7 @@ void cpu_init(void) load_mm_ldt(&init_mm); - clear_all_debug_regs(); + initialize_debug_regs(); dbg_restore_debug_regs(); doublefault_init_cpu_tss(); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 14bf8c232e45..dac4564e1d7c 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -327,7 +327,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu) struct thresh_restart { struct threshold_block *b; - int reset; int set_lvt_off; int lvt_off; u16 old_limit; @@ -422,13 +421,13 @@ static void threshold_restart_bank(void *_tr) rdmsr(tr->b->address, lo, hi); - if (tr->b->threshold_limit < (hi & THRESHOLD_MAX)) - tr->reset = 1; /* limit cannot be lower than err count */ - - if (tr->reset) { /* reset err count and overflow bit */ - hi = - (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) | - (THRESHOLD_MAX - tr->b->threshold_limit); + /* + * Reset error count and overflow bit. + * This is done during init or after handling an interrupt. + */ + if (hi & MASK_OVERFLOW_HI || tr->set_lvt_off) { + hi &= ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI); + hi |= THRESHOLD_MAX - tr->b->threshold_limit; } else if (tr->old_limit) { /* change limit w/o reset */ int new_count = (hi & THRESHOLD_MAX) + (tr->old_limit - tr->b->threshold_limit); @@ -1099,13 +1098,20 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol } bank_type = smca_get_bank_type(cpu, bank); - if (bank_type >= N_SMCA_BANK_TYPES) - return NULL; if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) return smca_umc_block_names[b->block]; - return NULL; + } + + if (b && b->block) { + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_block_%u", b->block); + return buf_mcatype; + } + + if (bank_type >= N_SMCA_BANK_TYPES) { + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_bank_%u", bank); + return buf_mcatype; } if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2a938f429c4d..d8f3d9af8acf 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1688,6 +1688,11 @@ static void mc_poll_banks_default(void) void (*mc_poll_banks)(void) = mc_poll_banks_default; +static bool should_enable_timer(unsigned long iv) +{ + return !mca_cfg.ignore_ce && iv; +} + static void mce_timer_fn(struct timer_list *t) { struct timer_list *cpu_t = this_cpu_ptr(&mce_timer); @@ -1711,7 +1716,7 @@ static void mce_timer_fn(struct timer_list *t) if (mce_get_storm_mode()) { __start_timer(t, HZ); - } else { + } else if (should_enable_timer(iv)) { __this_cpu_write(mce_next_interval, iv); __start_timer(t, iv); } @@ -2111,11 +2116,10 @@ static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; - if (mca_cfg.ignore_ce || !iv) - return; - - this_cpu_write(mce_next_interval, iv); - __start_timer(t, iv); + if (should_enable_timer(iv)) { + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); + } } static void __mcheck_cpu_setup_timer(void) @@ -2756,15 +2760,9 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { struct timer_list *t = this_cpu_ptr(&mce_timer); - int ret; mce_device_create(cpu); - - ret = mce_threshold_create_device(cpu); - if (ret) { - mce_device_remove(cpu); - return ret; - } + mce_threshold_create_device(cpu); mce_reenable_cpu(); mce_start_timer(t); return 0; diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index f6103e6bf69a..bb0a60b1ed63 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -477,6 +477,7 @@ void mce_intel_feature_init(struct cpuinfo_x86 *c) void mce_intel_feature_clear(struct cpuinfo_x86 *c) { intel_clear_lmce(); + cmci_clear(); } bool intel_filter_mce(struct mce *m) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 2f84164b20e0..765b4646648f 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -94,18 +94,6 @@ static struct equiv_cpu_table { struct equiv_cpu_entry *entry; } equiv_table; -union zen_patch_rev { - struct { - __u32 rev : 8, - stepping : 4, - model : 4, - __reserved : 4, - ext_model : 4, - ext_fam : 8; - }; - __u32 ucode_rev; -}; - union cpuid_1_eax { struct { __u32 stepping : 4, diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c index 2a1655b1fdd8..1fd349cfc802 100644 --- a/arch/x86/kernel/cpu/microcode/amd_shas.c +++ b/arch/x86/kernel/cpu/microcode/amd_shas.c @@ -231,6 +231,13 @@ static const struct patch_digest phashes[] = { 0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21, } }, + { 0xa0011d7, { + 0x35,0x07,0xcd,0x40,0x94,0xbc,0x81,0x6b, + 0xfc,0x61,0x56,0x1a,0xe2,0xdb,0x96,0x12, + 0x1c,0x1c,0x31,0xb1,0x02,0x6f,0xe5,0xd2, + 0xfe,0x1b,0x04,0x03,0x2c,0x8f,0x4c,0x36, + } + }, { 0xa001223, { 0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8, 0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4, @@ -294,6 +301,13 @@ static const struct patch_digest phashes[] = { 0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59, } }, + { 0xa00123b, { + 0xef,0xa1,0x1e,0x71,0xf1,0xc3,0x2c,0xe2, + 0xc3,0xef,0x69,0x41,0x7a,0x54,0xca,0xc3, + 0x8f,0x62,0x84,0xee,0xc2,0x39,0xd9,0x28, + 0x95,0xa7,0x12,0x49,0x1e,0x30,0x71,0x72, + } + }, { 0xa00820c, { 0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3, 0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63, @@ -301,6 +315,13 @@ static const struct patch_digest phashes[] = { 0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2, } }, + { 0xa00820d, { + 0xf9,0x2a,0xc0,0xf4,0x9e,0xa4,0x87,0xa4, + 0x7d,0x87,0x00,0xfd,0xab,0xda,0x19,0xca, + 0x26,0x51,0x32,0xc1,0x57,0x91,0xdf,0xc1, + 0x05,0xeb,0x01,0x7c,0x5a,0x95,0x21,0xb7, + } + }, { 0xa10113e, { 0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10, 0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0, @@ -322,6 +343,13 @@ static const struct patch_digest phashes[] = { 0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4, } }, + { 0xa10114c, { + 0x9e,0xb6,0xa2,0xd9,0x87,0x38,0xc5,0x64, + 0xd8,0x88,0xfa,0x78,0x98,0xf9,0x6f,0x74, + 0x39,0x90,0x1b,0xa5,0xcf,0x5e,0xb4,0x2a, + 0x02,0xff,0xd4,0x8c,0x71,0x8b,0xe2,0xc0, + } + }, { 0xa10123e, { 0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18, 0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d, @@ -343,6 +371,13 @@ static const struct patch_digest phashes[] = { 0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75, } }, + { 0xa10124c, { + 0x29,0xea,0xf1,0x2c,0xb2,0xe4,0xef,0x90, + 0xa4,0xcd,0x1d,0x86,0x97,0x17,0x61,0x46, + 0xfc,0x22,0xcb,0x57,0x75,0x19,0xc8,0xcc, + 0x0c,0xf5,0xbc,0xac,0x81,0x9d,0x9a,0xd2, + } + }, { 0xa108108, { 0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9, 0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6, @@ -350,6 +385,13 @@ static const struct patch_digest phashes[] = { 0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16, } }, + { 0xa108109, { + 0x85,0xb4,0xbd,0x7c,0x49,0xa7,0xbd,0xfa, + 0x49,0x36,0x80,0x81,0xc5,0xb7,0x39,0x1b, + 0x9a,0xaa,0x50,0xde,0x9b,0xe9,0x32,0x35, + 0x42,0x7e,0x51,0x4f,0x52,0x2c,0x28,0x59, + } + }, { 0xa20102d, { 0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11, 0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89, @@ -357,6 +399,13 @@ static const struct patch_digest phashes[] = { 0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4, } }, + { 0xa20102e, { + 0xbe,0x1f,0x32,0x04,0x0d,0x3c,0x9c,0xdd, + 0xe1,0xa4,0xbf,0x76,0x3a,0xec,0xc2,0xf6, + 0x11,0x00,0xa7,0xaf,0x0f,0xe5,0x02,0xc5, + 0x54,0x3a,0x1f,0x8c,0x16,0xb5,0xff,0xbe, + } + }, { 0xa201210, { 0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe, 0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9, @@ -364,6 +413,13 @@ static const struct patch_digest phashes[] = { 0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41, } }, + { 0xa201211, { + 0x69,0xa1,0x17,0xec,0xd0,0xf6,0x6c,0x95, + 0xe2,0x1e,0xc5,0x59,0x1a,0x52,0x0a,0x27, + 0xc4,0xed,0xd5,0x59,0x1f,0xbf,0x00,0xff, + 0x08,0x88,0xb5,0xe1,0x12,0xb6,0xcc,0x27, + } + }, { 0xa404107, { 0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45, 0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0, @@ -371,6 +427,13 @@ static const struct patch_digest phashes[] = { 0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99, } }, + { 0xa404108, { + 0x69,0x67,0x43,0x06,0xf8,0x0c,0x62,0xdc, + 0xa4,0x21,0x30,0x4f,0x0f,0x21,0x2c,0xcb, + 0xcc,0x37,0xf1,0x1c,0xc3,0xf8,0x2f,0x19, + 0xdf,0x53,0x53,0x46,0xb1,0x15,0xea,0x00, + } + }, { 0xa500011, { 0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4, 0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1, @@ -378,6 +441,13 @@ static const struct patch_digest phashes[] = { 0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74, } }, + { 0xa500012, { + 0xeb,0x74,0x0d,0x47,0xa1,0x8e,0x09,0xe4, + 0x93,0x4c,0xad,0x03,0x32,0x4c,0x38,0x16, + 0x10,0x39,0xdd,0x06,0xaa,0xce,0xd6,0x0f, + 0x62,0x83,0x9d,0x8e,0x64,0x55,0xbe,0x63, + } + }, { 0xa601209, { 0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32, 0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30, @@ -385,6 +455,13 @@ static const struct patch_digest phashes[] = { 0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d, } }, + { 0xa60120a, { + 0x0c,0x8b,0x3d,0xfd,0x52,0x52,0x85,0x7d, + 0x20,0x3a,0xe1,0x7e,0xa4,0x21,0x3b,0x7b, + 0x17,0x86,0xae,0xac,0x13,0xb8,0x63,0x9d, + 0x06,0x01,0xd0,0xa0,0x51,0x9a,0x91,0x2c, + } + }, { 0xa704107, { 0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6, 0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93, @@ -392,6 +469,13 @@ static const struct patch_digest phashes[] = { 0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39, } }, + { 0xa704108, { + 0xd7,0x55,0x15,0x2b,0xfe,0xc4,0xbc,0x93, + 0xec,0x91,0xa0,0xae,0x45,0xb7,0xc3,0x98, + 0x4e,0xff,0x61,0x77,0x88,0xc2,0x70,0x49, + 0xe0,0x3a,0x1d,0x84,0x38,0x52,0xbf,0x5a, + } + }, { 0xa705206, { 0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4, 0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7, @@ -399,6 +483,13 @@ static const struct patch_digest phashes[] = { 0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc, } }, + { 0xa705208, { + 0x30,0x1d,0x55,0x24,0xbc,0x6b,0x5a,0x19, + 0x0c,0x7d,0x1d,0x74,0xaa,0xd1,0xeb,0xd2, + 0x16,0x62,0xf7,0x5b,0xe1,0x1f,0x18,0x11, + 0x5c,0xf0,0x94,0x90,0x26,0xec,0x69,0xff, + } + }, { 0xa708007, { 0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3, 0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2, @@ -406,6 +497,13 @@ static const struct patch_digest phashes[] = { 0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93, } }, + { 0xa708008, { + 0x08,0x6e,0xf0,0x22,0x4b,0x8e,0xc4,0x46, + 0x58,0x34,0xe6,0x47,0xa2,0x28,0xfd,0xab, + 0x22,0x3d,0xdd,0xd8,0x52,0x9e,0x1d,0x16, + 0xfa,0x01,0x68,0x14,0x79,0x3e,0xe8,0x6b, + } + }, { 0xa70c005, { 0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b, 0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f, @@ -413,6 +511,13 @@ static const struct patch_digest phashes[] = { 0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13, } }, + { 0xa70c008, { + 0x0f,0xdb,0x37,0xa1,0x10,0xaf,0xd4,0x21, + 0x94,0x0d,0xa4,0xa2,0xe9,0x86,0x6c,0x0e, + 0x85,0x7c,0x36,0x30,0xa3,0x3a,0x78,0x66, + 0x18,0x10,0x60,0x0d,0x78,0x3d,0x44,0xd0, + } + }, { 0xaa00116, { 0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63, 0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5, @@ -441,4 +546,11 @@ static const struct patch_digest phashes[] = { 0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef, } }, + { 0xaa00216, { + 0x79,0xfb,0x5b,0x9f,0xb6,0xe6,0xa8,0xf5, + 0x4e,0x7c,0x4f,0x8e,0x1d,0xad,0xd0,0x08, + 0xc2,0x43,0x7c,0x8b,0xe6,0xdb,0xd0,0xd2, + 0xe8,0x39,0x26,0xc1,0xe5,0x5a,0x48,0xf1, + } + }, }; diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index c84c30188fdf..c463363ae1d4 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -47,8 +47,11 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, + { X86_FEATURE_COHERENCY_SFW_NO, CPUID_EBX, 31, 0x8000001f, 0 }, { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, + { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 }, + { X86_FEATURE_TSA_L1_NO, CPUID_ECX, 2, 0x80000021, 0 }, { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 }, diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 9ace84486499..147ea26dfdad 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -719,6 +719,8 @@ int arch_memory_failure(unsigned long pfn, int flags) goto out; } + sgx_unmark_page_reclaimable(page); + /* * TBD: Add additional plumbing to enable pre-emptive * action for asynchronous poison notification. Until diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 8f62e0666dea..8abe60919e2f 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -119,7 +119,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, { struct xregs_state __user *x = buf; struct _fpx_sw_bytes sw_bytes = {}; - u32 xfeatures; int err; /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ @@ -133,12 +132,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, (__u32 __user *)(buf + fpstate->user_size)); /* - * Read the xfeatures which we copied (directly from the cpu or - * from the state in task struct) to the user buffers. - */ - err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures); - - /* * For legacy compatible, we always set FP/SSE bits in the bit * vector while saving the state to the user context. This will * enable us capturing any changes(during sigreturn) to @@ -149,9 +142,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, * header as well as change any contents in the memory layout. * xrestore as part of sigreturn will capture all the changes. */ - xfeatures |= XFEATURE_MASK_FPSSE; - - err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures); + err |= set_xfeature_in_sigframe(x, XFEATURE_MASK_FPSSE); return !err; } diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index aa16f1a1bbcf..f7d8f3d73599 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -69,21 +69,31 @@ static inline u64 xfeatures_mask_independent(void) return fpu_kernel_cfg.independent_features; } +static inline int set_xfeature_in_sigframe(struct xregs_state __user *xbuf, u64 mask) +{ + u64 xfeatures; + int err; + + /* Read the xfeatures value already saved in the user buffer */ + err = __get_user(xfeatures, &xbuf->header.xfeatures); + xfeatures |= mask; + err |= __put_user(xfeatures, &xbuf->header.xfeatures); + + return err; +} + /* * Update the value of PKRU register that was already pushed onto the signal frame. */ -static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru) +static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru) { - u64 xstate_bv; int err; if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE))) return 0; /* Mark PKRU as in-use so that it is restored correctly. */ - xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU; - - err = __put_user(xstate_bv, &buf->header.xfeatures); + err = set_xfeature_in_sigframe(buf, XFEATURE_MASK_PKRU); if (err) return err; @@ -304,7 +314,7 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkr clac(); if (!err) - err = update_pkru_in_sigframe(buf, mask, pkru); + err = update_pkru_in_sigframe(buf, pkru); return err; } diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 85fa2db38dc4..9400730e538e 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -251,26 +251,59 @@ static __always_inline void handle_irq(struct irq_desc *desc, __handle_irq(desc, regs); } -static __always_inline int call_irq_handler(int vector, struct pt_regs *regs) +static struct irq_desc *reevaluate_vector(int vector) { - struct irq_desc *desc; - int ret = 0; + struct irq_desc *desc = __this_cpu_read(vector_irq[vector]); + + if (!IS_ERR_OR_NULL(desc)) + return desc; + + if (desc == VECTOR_UNUSED) + pr_emerg_ratelimited("No irq handler for %d.%u\n", smp_processor_id(), vector); + else + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + return NULL; +} + +static __always_inline bool call_irq_handler(int vector, struct pt_regs *regs) +{ + struct irq_desc *desc = __this_cpu_read(vector_irq[vector]); - desc = __this_cpu_read(vector_irq[vector]); if (likely(!IS_ERR_OR_NULL(desc))) { handle_irq(desc, regs); - } else { - ret = -EINVAL; - if (desc == VECTOR_UNUSED) { - pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n", - __func__, smp_processor_id(), - vector); - } else { - __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); - } + return true; } - return ret; + /* + * Reevaluate with vector_lock held to prevent a race against + * request_irq() setting up the vector: + * + * CPU0 CPU1 + * interrupt is raised in APIC IRR + * but not handled + * free_irq() + * per_cpu(vector_irq, CPU1)[vector] = VECTOR_SHUTDOWN; + * + * request_irq() common_interrupt() + * d = this_cpu_read(vector_irq[vector]); + * + * per_cpu(vector_irq, CPU1)[vector] = desc; + * + * if (d == VECTOR_SHUTDOWN) + * this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + * + * This requires that the same vector on the same target CPU is + * handed out or that a spurious interrupt hits that CPU/vector. + */ + lock_vector_lock(); + desc = reevaluate_vector(vector); + unlock_vector_lock(); + + if (!desc) + return false; + + handle_irq(desc, regs); + return true; } /* @@ -284,7 +317,7 @@ DEFINE_IDTENTRY_IRQ(common_interrupt) /* entry code tells RCU that we're not quiescent. Check it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU"); - if (unlikely(call_irq_handler(vector, regs))) + if (unlikely(!call_irq_handler(vector, regs))) apic_eoi(); set_irq_regs(old_regs); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 9c9faa1634fb..e5faeec20b1f 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -385,7 +385,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs) struct perf_event *bp; /* Disable hardware debugging while we are in kgdb: */ - set_debugreg(0UL, 7); + set_debugreg(DR7_FIXED_1, 7); for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 1dbd7a34645c..4c9c98c5deab 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -911,16 +911,24 @@ static __init bool prefer_mwait_c1_over_halt(void) */ static __cpuidle void mwait_idle(void) { + if (need_resched()) + return; + + x86_idle_clear_cpu_buffers(); + if (!current_set_polling_and_test()) { const void *addr = ¤t_thread_info()->flags; alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr)); __monitor(addr, 0, 0); - if (!need_resched()) { - __sti_mwait(0, 0); - raw_local_irq_disable(); - } + if (need_resched()) + goto out; + + __sti_mwait(0, 0); + raw_local_irq_disable(); } + +out: __current_clr_polling(); } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 0917c7f25720..f10c14cb6ef8 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, /* Only print out debug registers if they are in their non-default state. */ if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && - (d6 == DR6_RESERVED) && (d7 == 0x400)) + (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1)) return; printk("%sDR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 226472332a70..266366a945ed 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -132,7 +132,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, /* Only print out debug registers if they are in their non-default state. */ if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && - (d6 == DR6_RESERVED) && (d7 == 0x400))) { + (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) { printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n", log_lvl, d0, d1, d2); printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n", diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b18fc7539b8d..243f3bc9b4dc 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -977,24 +977,32 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) #endif } -static __always_inline unsigned long debug_read_clear_dr6(void) +static __always_inline unsigned long debug_read_reset_dr6(void) { unsigned long dr6; + get_debugreg(dr6, 6); + dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ + /* * The Intel SDM says: * - * Certain debug exceptions may clear bits 0-3. The remaining - * contents of the DR6 register are never cleared by the - * processor. To avoid confusion in identifying debug - * exceptions, debug handlers should clear the register before - * returning to the interrupted task. + * Certain debug exceptions may clear bits 0-3 of DR6. + * + * BLD induced #DB clears DR6.BLD and any other debug + * exception doesn't modify DR6.BLD. * - * Keep it simple: clear DR6 immediately. + * RTM induced #DB clears DR6.RTM and any other debug + * exception sets DR6.RTM. + * + * To avoid confusion in identifying debug exceptions, + * debug handlers should set DR6.BLD and DR6.RTM, and + * clear other DR6 bits before returning. + * + * Keep it simple: write DR6 with its architectural reset + * value 0xFFFF0FF0, defined as DR6_RESERVED, immediately. */ - get_debugreg(dr6, 6); set_debugreg(DR6_RESERVED, 6); - dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ return dr6; } @@ -1194,13 +1202,13 @@ out: /* IST stack entry */ DEFINE_IDTENTRY_DEBUG(exc_debug) { - exc_debug_kernel(regs, debug_read_clear_dr6()); + exc_debug_kernel(regs, debug_read_reset_dr6()); } /* User entry, runs on regular task stack */ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) { - exc_debug_user(regs, debug_read_clear_dr6()); + exc_debug_user(regs, debug_read_reset_dr6()); } #ifdef CONFIG_X86_FRED @@ -1219,7 +1227,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug) { /* * FRED #DB stores DR6 on the stack in the format which - * debug_read_clear_dr6() returns for the IDT entry points. + * debug_read_reset_dr6() returns for the IDT entry points. */ unsigned long dr6 = fred_event_data(regs); @@ -1234,7 +1242,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug) /* 32 bit does not have separate entry points. */ DEFINE_IDTENTRY_RAW(exc_debug) { - unsigned long dr6 = debug_read_clear_dr6(); + unsigned long dr6 = debug_read_reset_dr6(); if (user_mode(regs)) exc_debug_user(regs, dr6); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c92e43f2d0c4..8f587c5bb6bc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -814,6 +814,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_8000_0021_EAX, F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | + F(VERW_CLEAR) | F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ | F(WRMSR_XX_BASE_NS) ); @@ -821,11 +822,19 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB); kvm_cpu_cap_check_and_set(X86_FEATURE_IBPB_BRTYPE); kvm_cpu_cap_check_and_set(X86_FEATURE_SRSO_NO); + kvm_cpu_cap_check_and_set(X86_FEATURE_VERW_CLEAR); kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, F(PERFMON_V2) ); + kvm_cpu_cap_init_kvm_defined(CPUID_8000_0021_ECX, + F(TSA_SQ_NO) | F(TSA_L1_NO) + ); + + kvm_cpu_cap_check_and_set(X86_FEATURE_TSA_SQ_NO); + kvm_cpu_cap_check_and_set(X86_FEATURE_TSA_L1_NO); + /* * Synthesize "LFENCE is serializing" into the AMD-defined entry in * KVM's supported CPUID if the feature is reported as supported by the @@ -1376,8 +1385,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; case 0x80000021: - entry->ebx = entry->ecx = entry->edx = 0; + entry->ebx = entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0021_EAX); + cpuid_entry_override(entry, CPUID_8000_0021_ECX); break; /* AMD Extended Performance Monitoring and Debug */ case 0x80000022: { diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index ad479cfb91bc..f16a7b2c2adc 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -2,7 +2,6 @@ #ifndef ARCH_X86_KVM_CPUID_H #define ARCH_X86_KVM_CPUID_H -#include "x86.h" #include "reverse_cpuid.h" #include <asm/cpu.h> #include <asm/processor.h> diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index e72aed25d721..60986f67c35a 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -651,9 +651,10 @@ static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt) } static inline bool emul_is_noncanonical_address(u64 la, - struct x86_emulate_ctxt *ctxt) + struct x86_emulate_ctxt *ctxt, + unsigned int flags) { - return !__is_canonical_address(la, ctxt_virt_addr_bits(ctxt)); + return !ctxt->ops->is_canonical_addr(ctxt, la, flags); } /* @@ -1733,7 +1734,8 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (ret != X86EMUL_CONTINUE) return ret; if (emul_is_noncanonical_address(get_desc_base(&seg_desc) | - ((u64)base3 << 32), ctxt)) + ((u64)base3 << 32), ctxt, + X86EMUL_F_DT_LOAD)) return emulate_gp(ctxt, err_code); } @@ -2516,8 +2518,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ss_sel = cs_sel + 8; cs.d = 0; cs.l = 1; - if (emul_is_noncanonical_address(rcx, ctxt) || - emul_is_noncanonical_address(rdx, ctxt)) + if (emul_is_noncanonical_address(rcx, ctxt, 0) || + emul_is_noncanonical_address(rdx, ctxt, 0)) return emulate_gp(ctxt, 0); break; } @@ -3494,7 +3496,8 @@ static int em_lgdt_lidt(struct x86_emulate_ctxt *ctxt, bool lgdt) if (rc != X86EMUL_CONTINUE) return rc; if (ctxt->mode == X86EMUL_MODE_PROT64 && - emul_is_noncanonical_address(desc_ptr.address, ctxt)) + emul_is_noncanonical_address(desc_ptr.address, ctxt, + X86EMUL_F_DT_LOAD)) return emulate_gp(ctxt, 0); if (lgdt) ctxt->ops->set_gdt(ctxt, &desc_ptr); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 44c88537448c..79d06a8a5b7d 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1980,6 +1980,9 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY) goto out_flush_all; + if (is_noncanonical_invlpg_address(entries[i], vcpu)) + continue; + /* * Lower 12 bits of 'address' encode the number of additional * pages to flush. diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 55a18e2f2dcd..10495fffb890 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -94,6 +94,8 @@ struct x86_instruction_info { #define X86EMUL_F_FETCH BIT(1) #define X86EMUL_F_IMPLICIT BIT(2) #define X86EMUL_F_INVLPG BIT(3) +#define X86EMUL_F_MSR BIT(4) +#define X86EMUL_F_DT_LOAD BIT(5) struct x86_emulate_ops { void (*vm_bugged)(struct x86_emulate_ctxt *ctxt); @@ -235,6 +237,9 @@ struct x86_emulate_ops { gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr, unsigned int flags); + + bool (*is_canonical_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr, + unsigned int flags); }; /* Type, address-of, and value of an instruction's operand. */ diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 9dc5dd43ae7f..e9322358678b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -4,6 +4,7 @@ #include <linux/kvm_host.h> #include "kvm_cache_regs.h" +#include "x86.h" #include "cpuid.h" extern bool __read_mostly enable_mmio_caching; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4607610ef062..8edfb4e4a73d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6234,7 +6234,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, /* It's actually a GPA for vcpu->arch.guest_mmu. */ if (mmu != &vcpu->arch.guest_mmu) { /* INVLPG on a non-canonical address is a NOP according to the SDM. */ - if (is_noncanonical_address(addr, vcpu)) + if (is_noncanonical_invlpg_address(addr, vcpu)) return; kvm_x86_call(flush_tlb_gva)(vcpu, addr); diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 05490b9d8a43..6f74e2b27c1e 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -19,6 +19,7 @@ #include <asm/mtrr.h> #include "cpuid.h" +#include "x86.h" static u64 *find_mtrr(struct kvm_vcpu *vcpu, unsigned int msr) { diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 0d17d6b70639..0ea847b82354 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -18,6 +18,7 @@ enum kvm_only_cpuid_leafs { CPUID_8000_0022_EAX, CPUID_7_2_EDX, CPUID_24_0_EBX, + CPUID_8000_0021_ECX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -68,6 +69,10 @@ enum kvm_only_cpuid_leafs { /* CPUID level 0x80000022 (EAX) */ #define KVM_X86_FEATURE_PERFMON_V2 KVM_X86_FEATURE(CPUID_8000_0022_EAX, 0) +/* CPUID level 0x80000021 (ECX) */ +#define KVM_X86_FEATURE_TSA_SQ_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 1) +#define KVM_X86_FEATURE_TSA_L1_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 2) + struct cpuid_reg { u32 function; u32 index; @@ -98,6 +103,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, [CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX}, + [CPUID_8000_0021_ECX] = {0x80000021, 0, CPUID_ECX}, }; /* @@ -137,6 +143,8 @@ static __always_inline u32 __feature_translate(int x86_feature) KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); + KVM_X86_TRANSLATE_FEATURE(TSA_SQ_NO); + KVM_X86_TRANSLATE_FEATURE(TSA_L1_NO); default: return x86_feature; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6154cb450b44..c4ae73541fc5 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2058,6 +2058,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src) struct kvm_vcpu *src_vcpu; unsigned long i; + if (src->created_vcpus != atomic_read(&src->online_vcpus) || + dst->created_vcpus != atomic_read(&dst->online_vcpus)) + return -EBUSY; + if (!sev_es_guest(src)) return 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7cbacd043921..800f781475c0 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1483,7 +1483,7 @@ static void svm_clear_current_vmcb(struct vmcb *vmcb) { int i; - for_each_online_cpu(i) + for_each_possible_cpu(i) cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL); } @@ -4226,9 +4226,9 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in guest_state_exit_irqoff(); } -static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, - bool force_immediate_exit) +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { + bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT; struct vcpu_svm *svm = to_svm(vcpu); bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL); @@ -4270,10 +4270,13 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, svm_hv_update_vp_id(svm->vmcb, vcpu); /* - * Run with all-zero DR6 unless needed, so that we can get the exact cause - * of a #DB. + * Run with all-zero DR6 unless the guest can write DR6 freely, so that + * KVM can get the exact cause of a #DB. Note, loading guest DR6 from + * KVM's snapshot is only necessary when DR accesses won't exit. */ - if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) + if (unlikely(run_flags & KVM_RUN_LOAD_GUEST_DR6)) + svm_set_dr6(vcpu, vcpu->arch.dr6); + else if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) svm_set_dr6(vcpu, DR6_ACTIVE_LOW); clgi(); @@ -5084,7 +5087,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, - .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 0c61153b275f..235c4af6b692 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -169,6 +169,9 @@ SYM_FUNC_START(__svm_vcpu_run) #endif mov VCPU_RDI(%_ASM_DI), %_ASM_DI + /* Clobbers EFLAGS.ZF */ + VM_CLEAR_CPU_BUFFERS + /* Enter guest mode */ 3: vmrun %_ASM_AX 4: @@ -335,6 +338,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) mov SVM_current_vmcb(%rdi), %rax mov KVM_VMCB_pa(%rax), %rax + /* Clobbers EFLAGS.ZF */ + VM_CLEAR_CPU_BUFFERS + /* Enter guest mode */ 1: vmrun %rax 2: diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index fab6a1ad98dc..fa41d036acd4 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -4,6 +4,7 @@ #include <linux/errno.h> #include <linux/smp.h> +#include "x86.h" #include "../cpuid.h" #include "hyperv.h" #include "nested.h" diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 47476fcc179a..3f83e36a657b 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -42,6 +42,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, + .HOST_OWNED_DEBUGCTL = DEBUGCTLMSR_FREEZE_IN_SMM, + .update_exception_bitmap = vmx_update_exception_bitmap, .get_feature_msr = vmx_get_feature_msr, .get_msr = vmx_get_msr, @@ -60,7 +62,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, - .set_dr6 = vmx_set_dr6, .set_dr7 = vmx_set_dr7, .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, .cache_reg = vmx_cache_reg, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 22bee8a71144..60bd2791d933 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -7,6 +7,7 @@ #include <asm/debugreg.h> #include <asm/mmu_context.h> +#include "x86.h" #include "cpuid.h" #include "hyperv.h" #include "mmu.h" @@ -16,7 +17,6 @@ #include "sgx.h" #include "trace.h" #include "vmx.h" -#include "x86.h" #include "smm.h" static bool __read_mostly enable_shadow_vmcs = 1; @@ -2653,10 +2653,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); + vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl & + vmx_get_supported_debugctl(vcpu, false)); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl); + vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl); } if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -3020,8 +3021,8 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3))) return -EINVAL; - if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))) + if (CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || + CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_eip, vcpu))) return -EINVAL; if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) && @@ -3055,12 +3056,12 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(vmcs12->host_ss_selector == 0 && !ia32e)) return -EINVAL; - if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_rip, vcpu))) + if (CC(is_noncanonical_base_address(vmcs12->host_fs_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_gs_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_gdtr_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_idtr_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_tr_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_rip, vcpu, 0))) return -EINVAL; /* @@ -3135,7 +3136,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && - CC(!kvm_dr7_valid(vmcs12->guest_dr7))) + (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || + CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false)))) return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && @@ -3178,7 +3180,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) && - (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || + (CC(is_noncanonical_msr_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))) return -EINVAL; @@ -3525,7 +3527,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) - vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read(); if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -4576,6 +4578,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); + /* + * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02. + * Writes to DEBUGCTL that aren't intercepted by L1 are immediately + * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into + * vmcs02 doesn't strictly track vmcs12. + */ if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) vmcs12->guest_dr7 = vcpu->arch.dr7; @@ -4766,7 +4774,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, __vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR); kvm_set_dr(vcpu, 7, 0x400); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + vmx_guest_debugctl_write(vcpu, 0); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -4821,6 +4829,9 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7))); } + /* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */ + vmx_reload_guest_debugctl(vcpu); + /* * Note that calling vmx_set_{efer,cr0,cr4} is important as they * handle a variety of side effects to KVM's software model. @@ -5172,7 +5183,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, * non-canonical form. This is the only check on the memory * destination for long mode! */ - exn = is_noncanonical_address(*ret, vcpu); + exn = is_noncanonical_address(*ret, vcpu, 0); } else { /* * When not in long mode, the virtual/linear address is @@ -5983,7 +5994,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) * invalidation. */ if (!operand.vpid || - is_noncanonical_address(operand.gla, vcpu)) + is_noncanonical_invlpg_address(operand.gla, vcpu)) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); vpid_sync_vcpu_addr(vpid02, operand.gla); diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 83382a4d1d66..a5edc623166a 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -365,7 +365,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; case MSR_IA32_DS_AREA: - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; pmu->ds_area = data; @@ -605,11 +605,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) */ static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu) { - u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL); + u64 data = vmx_guest_debugctl_read(); if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) { data &= ~DEBUGCTLMSR_LBR; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); } } @@ -679,7 +679,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) if (!lbr_desc->event) { vmx_disable_lbr_msrs_passthrough(vcpu); - if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) + if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR) goto warn; if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use)) goto warn; @@ -701,7 +701,7 @@ warn: static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) { - if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)) + if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)) intel_pmu_release_guest_lbr_event(vcpu); } diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index a3c3d2a51f47..b352a3ba7354 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -4,12 +4,11 @@ #include <asm/sgx.h> -#include "cpuid.h" +#include "x86.h" #include "kvm_cache_regs.h" #include "nested.h" #include "sgx.h" #include "vmx.h" -#include "x86.h" bool __read_mostly enable_sgx = 1; module_param_named(sgx, enable_sgx, bool, 0444); @@ -38,7 +37,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset, fault = true; } else if (likely(is_64_bit_mode(vcpu))) { *gva = vmx_get_untagged_addr(vcpu, *gva, 0); - fault = is_noncanonical_address(*gva, vcpu); + fault = is_noncanonical_address(*gva, vcpu, 0); } else { *gva &= 0xffffffff; fault = (s.unusable) || diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a3d45b01dbad..6c185a260c5b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -770,8 +770,11 @@ void vmx_emergency_disable_virtualization_cpu(void) return; list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) + loaded_vmcss_on_cpu_link) { vmcs_clear(v->vmcs); + if (v->shadow_vmcs) + vmcs_clear(v->shadow_vmcs); + } kvm_cpu_vmxoff(); } @@ -2145,7 +2148,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; case MSR_IA32_DEBUGCTLMSR: - msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); + msr_info->data = vmx_guest_debugctl_read(); break; default: find_uret_msr: @@ -2170,7 +2173,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } -static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) +u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { u64 debugctl = 0; @@ -2182,9 +2185,25 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; + if (boot_cpu_has(X86_FEATURE_RTM) && + (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_RTM))) + debugctl |= DEBUGCTLMSR_RTM_DEBUG; + return debugctl; } +bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated) +{ + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated); + if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) { + kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data); + invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR); + } + return !invalid; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -2253,35 +2272,28 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } vmcs_writel(GUEST_SYSENTER_ESP, data); break; - case MSR_IA32_DEBUGCTLMSR: { - u64 invalid; - - invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); - if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); - data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - } - - if (invalid) + case MSR_IA32_DEBUGCTLMSR: + if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated)) return 1; + data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); + if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); + if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); return 0; - } case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) return 1; - if (is_noncanonical_address(data & PAGE_MASK, vcpu) || + if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) || (data & MSR_IA32_BNDCFGS_RSVD)) return 1; @@ -2446,7 +2458,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; if (index >= 2 * vmx->pt_desc.num_address_ranges) return 1; - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; @@ -4820,7 +4832,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write32(GUEST_SYSENTER_CS, 0); vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + + vmx_guest_debugctl_write(&vmx->vcpu, 0); if (cpu_has_vmx_tpr_shadow()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); @@ -5627,12 +5640,6 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } -void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) -{ - lockdep_assert_irqs_disabled(); - set_debugreg(vcpu->arch.dr6, 6); -} - void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); @@ -7310,7 +7317,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vmx_l1d_flush(vcpu); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) - mds_clear_cpu_buffers(); + x86_clear_cpu_buffers(); vmx_disable_fb_clear(vmx); @@ -7350,8 +7357,9 @@ out: guest_state_exit_irqoff(); } -fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { + bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT; struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; @@ -7396,6 +7404,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0; + if (run_flags & KVM_RUN_LOAD_GUEST_DR6) + set_debugreg(vcpu->arch.dr6, 6); + + if (run_flags & KVM_RUN_LOAD_DEBUGCTL) + vmx_reload_guest_debugctl(vcpu); + /* * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index cf57fbf12104..a7e2de50d27f 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -435,6 +435,32 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated); +bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated); + +static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val) +{ + WARN_ON_ONCE(val & DEBUGCTLMSR_FREEZE_IN_SMM); + + val |= vcpu->arch.host_debugctl & DEBUGCTLMSR_FREEZE_IN_SMM; + vmcs_write64(GUEST_IA32_DEBUGCTL, val); +} + +static inline u64 vmx_guest_debugctl_read(void) +{ + return vmcs_read64(GUEST_IA32_DEBUGCTL) & ~DEBUGCTLMSR_FREEZE_IN_SMM; +} + +static inline void vmx_reload_guest_debugctl(struct kvm_vcpu *vcpu) +{ + u64 val = vmcs_read64(GUEST_IA32_DEBUGCTL); + + if (!((val ^ vcpu->arch.host_debugctl) & DEBUGCTLMSR_FREEZE_IN_SMM)) + return; + + vmx_guest_debugctl_write(vcpu, val & ~DEBUGCTLMSR_FREEZE_IN_SMM); +} + /* * Note, early Intel manuals have the write-low and read-high bitmap offsets * the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 4aba200f435d..5e4ce13ab305 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -21,7 +21,7 @@ void vmx_vm_destroy(struct kvm *kvm); int vmx_vcpu_precreate(struct kvm *kvm); int vmx_vcpu_create(struct kvm_vcpu *vcpu); int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu); -fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit); +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags); void vmx_vcpu_free(struct kvm_vcpu *vcpu); void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f378d479fea3..dbd295ef3eba 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1845,7 +1845,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, case MSR_KERNEL_GS_BASE: case MSR_CSTAR: case MSR_LSTAR: - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; break; case MSR_IA32_SYSENTER_EIP: @@ -1862,7 +1862,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, * value, and that something deterministic happens if the guest * invokes 64-bit SYSENTER. */ - data = __canonical_address(data, vcpu_virt_addr_bits(vcpu)); + data = __canonical_address(data, max_host_virt_addr_bits()); break; case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) @@ -8608,6 +8608,12 @@ static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt, addr, flags); } +static bool emulator_is_canonical_addr(struct x86_emulate_ctxt *ctxt, + gva_t addr, unsigned int flags) +{ + return !is_noncanonical_address(addr, emul_to_vcpu(ctxt), flags); +} + static const struct x86_emulate_ops emulate_ops = { .vm_bugged = emulator_vm_bugged, .read_gpr = emulator_read_gpr, @@ -8654,6 +8660,7 @@ static const struct x86_emulate_ops emulate_ops = { .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, .get_untagged_addr = emulator_get_untagged_addr, + .is_canonical_addr = emulator_is_canonical_addr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -10704,6 +10711,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); fastpath_t exit_fastpath; + u64 run_flags, debug_ctl; bool req_immediate_exit = false; @@ -10948,8 +10956,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - if (req_immediate_exit) + run_flags = 0; + if (req_immediate_exit) { + run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT; kvm_make_request(KVM_REQ_EVENT, vcpu); + } fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) @@ -10959,19 +10970,29 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); if (unlikely(vcpu->arch.switch_db_regs)) { - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); set_debugreg(vcpu->arch.eff_db[0], 0); set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6); + run_flags |= KVM_RUN_LOAD_GUEST_DR6; } else if (unlikely(hw_breakpoint_active())) { - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); } - vcpu->arch.host_debugctl = get_debugctlmsr(); + /* + * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL + * can be modified in IRQ context, e.g. via SMP function calls. Inform + * vendor code if any host-owned bits were changed, e.g. so that the + * value loaded into hardware while running the guest can be updated. + */ + debug_ctl = get_debugctlmsr(); + if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL && + !vcpu->arch.guest_state_protected) + run_flags |= KVM_RUN_LOAD_DEBUGCTL; + vcpu->arch.host_debugctl = debug_ctl; guest_timing_enter_irqoff(); @@ -10985,8 +11006,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED)); - exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, - req_immediate_exit); + exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; @@ -10998,6 +11018,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) break; } + run_flags = 0; + /* Note, VM-Exits that go down the "slow" path are accounted below. */ ++vcpu->stat.exits; } @@ -12888,11 +12910,11 @@ void kvm_arch_destroy_vm(struct kvm *kvm) mutex_unlock(&kvm->slots_lock); } kvm_unload_vcpu_mmus(kvm); + kvm_destroy_vcpus(kvm); kvm_x86_call(vm_destroy)(kvm); kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); - kvm_destroy_vcpus(kvm); kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); @@ -13756,7 +13778,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) * invalidation. */ if ((!pcid_enabled && (operand.pcid != 0)) || - is_noncanonical_address(operand.gla, vcpu)) { + is_noncanonical_invlpg_address(operand.gla, vcpu)) { kvm_inject_gp(vcpu, 0); return 1; } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a84c48ef5278..ec623d23d13d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -8,6 +8,7 @@ #include <asm/pvclock.h> #include "kvm_cache_regs.h" #include "kvm_emulate.h" +#include "cpuid.h" struct kvm_caps { /* control of guest tsc rate supported? */ @@ -233,9 +234,52 @@ static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu) return kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 57 : 48; } -static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu) +static inline u8 max_host_virt_addr_bits(void) { - return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu)); + return kvm_cpu_cap_has(X86_FEATURE_LA57) ? 57 : 48; +} + +/* + * x86 MSRs which contain linear addresses, x86 hidden segment bases, and + * IDT/GDT bases have static canonicality checks, the size of which depends + * only on the CPU's support for 5-level paging, rather than on the state of + * CR4.LA57. This applies to both WRMSR and to other instructions that set + * their values, e.g. SGDT. + * + * KVM passes through most of these MSRS and also doesn't intercept the + * instructions that set the hidden segment bases. + * + * Because of this, to be consistent with hardware, even if the guest doesn't + * have LA57 enabled in its CPUID, perform canonicality checks based on *host* + * support for 5 level paging. + * + * Finally, instructions which are related to MMU invalidation of a given + * linear address, also have a similar static canonical check on address. + * This allows for example to invalidate 5-level addresses of a guest from a + * host which uses 4-level paging. + */ +static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu, + unsigned int flags) +{ + if (flags & (X86EMUL_F_INVLPG | X86EMUL_F_MSR | X86EMUL_F_DT_LOAD)) + return !__is_canonical_address(la, max_host_virt_addr_bits()); + else + return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu)); +} + +static inline bool is_noncanonical_msr_address(u64 la, struct kvm_vcpu *vcpu) +{ + return is_noncanonical_address(la, vcpu, X86EMUL_F_MSR); +} + +static inline bool is_noncanonical_base_address(u64 la, struct kvm_vcpu *vcpu) +{ + return is_noncanonical_address(la, vcpu, X86EMUL_F_DT_LOAD); +} + +static inline bool is_noncanonical_invlpg_address(u64 la, struct kvm_vcpu *vcpu) +{ + return is_noncanonical_address(la, vcpu, X86EMUL_F_INVLPG); } static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 622fe24da910..1fc2035df404 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1472,7 +1472,7 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports, sched_poll.nr_ports * sizeof(*ports), &e)) { *r = -EFAULT; - return true; + goto out; } for (i = 0; i < sched_poll.nr_ports; i++) { @@ -1916,8 +1916,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm, { struct kvm_vcpu *vcpu; - if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm)) - return -EINVAL; + /* + * Don't check for the port being within range of max_evtchn_port(). + * Userspace can configure what ever targets it likes; events just won't + * be delivered if/while the target is invalid, just like userspace can + * configure MSIs which target non-existent APICs. + * + * This allow on Live Migration and Live Update, the IRQ routing table + * can be restored *independently* of other things like creating vCPUs, + * without imposing an ordering dependency on userspace. In this + * particular case, the problematic ordering would be with setting the + * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096 + * instead of 1024 event channels. + */ /* We only support 2 level event channels for now */ if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 51986e8a9d35..52e22d3e1a82 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -122,13 +122,12 @@ static bool ex_handler_sgx(const struct exception_table_entry *fixup, static bool ex_handler_fprestore(const struct exception_table_entry *fixup, struct pt_regs *regs) { - regs->ip = ex_fixup_addr(fixup); - WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); fpu_reset_from_exception_fixup(); - return true; + + return ex_handler_default(fixup, regs); } /* diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c index 472540aeabc2..08cd913cbd4e 100644 --- a/arch/x86/tools/insn_decoder_test.c +++ b/arch/x86/tools/insn_decoder_test.c @@ -10,8 +10,7 @@ #include <assert.h> #include <unistd.h> #include <stdarg.h> - -#define unlikely(cond) (cond) +#include <linux/kallsyms.h> #include <asm/insn.h> #include <inat.c> @@ -106,7 +105,7 @@ static void parse_args(int argc, char **argv) } } -#define BUFSIZE 256 +#define BUFSIZE (256 + KSYM_NAME_LEN) int main(int argc, char **argv) { diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h index b07824500363..ddc144657efa 100644 --- a/arch/x86/um/asm/checksum.h +++ b/arch/x86/um/asm/checksum.h @@ -20,6 +20,9 @@ */ extern __wsum csum_partial(const void *buff, int len, __wsum sum); +/* Do not call this directly. Declared for export type visibility. */ +extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len); + /** * csum_fold - Fold and invert a 32bit checksum. * sum: 32bit unfolded sum diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c index 4e2b2e2ac9f9..eb91bc5448de 100644 --- a/arch/x86/virt/vmx/tdx/tdx.c +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -69,8 +69,9 @@ static inline void seamcall_err_ret(u64 fn, u64 err, args->r9, args->r10, args->r11); } -static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func, - u64 fn, struct tdx_module_args *args) +static __always_inline int sc_retry_prerr(sc_func_t func, + sc_err_func_t err_func, + u64 fn, struct tdx_module_args *args) { u64 sret = sc_retry(func, fn, args); |