diff options
Diffstat (limited to 'arch/x86')
63 files changed, 1156 insertions, 828 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ae1654280c40..340e5468980e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2005,6 +2005,9 @@ config ARCH_SUPPORTS_KEXEC_BZIMAGE_VERIFY_SIG config ARCH_SUPPORTS_KEXEC_JUMP def_bool y +config ARCH_SUPPORTS_KEXEC_HANDOVER + def_bool X86_64 + config ARCH_SUPPORTS_CRASH_DUMP def_bool X86_64 || (X86_32 && HIGHMEM) diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index f03d59ea6e40..3b0948ad449f 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -760,6 +760,49 @@ static void process_e820_entries(unsigned long minimum, } } +/* + * If KHO is active, only process its scratch areas to ensure we are not + * stepping onto preserved memory. + */ +static bool process_kho_entries(unsigned long minimum, unsigned long image_size) +{ + struct kho_scratch *kho_scratch; + struct setup_data *ptr; + struct kho_data *kho; + int i, nr_areas = 0; + + if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER)) + return false; + + ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data; + while (ptr) { + if (ptr->type == SETUP_KEXEC_KHO) { + kho = (struct kho_data *)(unsigned long)ptr->data; + kho_scratch = (void *)(unsigned long)kho->scratch_addr; + nr_areas = kho->scratch_size / sizeof(*kho_scratch); + break; + } + + ptr = (struct setup_data *)(unsigned long)ptr->next; + } + + if (!nr_areas) + return false; + + for (i = 0; i < nr_areas; i++) { + struct kho_scratch *area = &kho_scratch[i]; + struct mem_vector region = { + .start = area->addr, + .size = area->size, + }; + + if (process_mem_region(®ion, minimum, image_size)) + break; + } + + return true; +} + static unsigned long find_random_phys_addr(unsigned long minimum, unsigned long image_size) { @@ -775,7 +818,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum, return 0; } - if (!process_efi_entries(minimum, image_size)) + /* + * During kexec handover only process KHO scratch areas that are known + * not to contain any data that must be preserved. + */ + if (!process_kho_entries(minimum, image_size) && + !process_efi_entries(minimum, image_size)) process_e820_entries(minimum, image_size); phys_addr = slots_fetch_random(); diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index fbc1215d2746..b6db4e0b936b 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -869,12 +869,12 @@ static void *snp_alloc_vmsa_page(int cpu) return page_address(p + 1); } -static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) +static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip, unsigned int cpu) { struct sev_es_save_area *cur_vmsa, *vmsa; struct svsm_ca *caa; u8 sipi_vector; - int cpu, ret; + int ret; u64 cr4; /* @@ -895,15 +895,6 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) /* Override start_ip with known protected guest start IP */ start_ip = real_mode_header->sev_es_trampoline_start; - - /* Find the logical CPU for the APIC ID */ - for_each_present_cpu(cpu) { - if (arch_match_cpu_phys_id(cpu, apic_id)) - break; - } - if (cpu >= nr_cpu_ids) - return -EINVAL; - cur_vmsa = per_cpu(sev_vmsa, cpu); /* diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 5d27194a2efa..3d1d3547095a 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -391,40 +391,6 @@ static void __init hv_stimer_setup_percpu_clockev(void) old_setup_percpu_clockev(); } -#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE) -static u8 __init get_vtl(void) -{ - u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS; - struct hv_input_get_vp_registers *input; - struct hv_output_get_vp_registers *output; - unsigned long flags; - u64 ret; - - local_irq_save(flags); - input = *this_cpu_ptr(hyperv_pcpu_input_arg); - output = *this_cpu_ptr(hyperv_pcpu_output_arg); - - memset(input, 0, struct_size(input, names, 1)); - input->partition_id = HV_PARTITION_ID_SELF; - input->vp_index = HV_VP_INDEX_SELF; - input->input_vtl.as_uint8 = 0; - input->names[0] = HV_REGISTER_VSM_VP_STATUS; - - ret = hv_do_hypercall(control, input, output); - if (hv_result_success(ret)) { - ret = output->values[0].reg8 & HV_X64_VTL_MASK; - } else { - pr_err("Failed to get VTL(error: %lld) exiting...\n", ret); - BUG(); - } - - local_irq_restore(flags); - return ret; -} -#else -static inline u8 get_vtl(void) { return 0; } -#endif - /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -707,3 +673,36 @@ 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_INDEX_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 4580936dcb03..042e8712d8de 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -56,7 +56,12 @@ static void __noreturn hv_vtl_restart(char __maybe_unused *cmd) void __init hv_vtl_init_platform(void) { - pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); + /* + * This function is a no-op if the VTL mode is not enabled. + * If it is, this function runs if and only the kernel boots in + * VTL2 which the x86 hv initialization path makes sure of. + */ + pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl); x86_platform.realmode_reserve = x86_init_noop; x86_platform.realmode_init = x86_init_noop; @@ -207,63 +212,23 @@ 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 = *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 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) +static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip, unsigned int cpu) { - int vp_id, cpu; - - /* Find the logical CPU for the APIC ID */ - for_each_present_cpu(cpu) { - if (arch_match_cpu_phys_id(cpu, apicid)) - break; - } - if (cpu >= nr_cpu_ids) - return -EINVAL; + int vp_index; 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/ivm.c b/arch/x86/hyperv/ivm.c index 09a165a3c41e..e93a2f488ff7 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -9,6 +9,7 @@ #include <linux/bitfield.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, unsigned int cpu) { struct sev_es_save_area *vmsa = (struct sev_es_save_area *) __get_free_page(GFP_KERNEL | __GFP_ZERO); @@ -298,10 +299,16 @@ 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 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; + native_store_gdt(&gdtr); vmsa->gdtr.base = gdtr.address; @@ -349,7 +356,7 @@ 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/apic.h b/arch/x86/include/asm/apic.h index 68e10e30fe9b..23d86c9750b9 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -313,9 +313,9 @@ struct apic { u32 (*get_apic_id)(u32 id); /* wakeup_secondary_cpu */ - int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu); /* wakeup secondary CPU using 64-bit wakeup point */ - int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu); char *name; }; @@ -333,8 +333,8 @@ struct apic_override { void (*send_IPI_self)(int vector); u64 (*icr_read)(void); void (*icr_write)(u32 low, u32 high); - int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip); - int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu); + int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu); }; /* diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 5b50e0e35129..ee176236c2be 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -336,6 +336,7 @@ #define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ #define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ #define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */ +#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/ #define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */ #define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */ @@ -378,6 +379,7 @@ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */ #define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */ +#define X86_FEATURE_BUS_LOCK_THRESHOLD (15*32+29) /* Bus lock threshold */ #define X86_FEATURE_IDLE_HLT (15*32+30) /* IDLE HLT intercept */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -446,6 +448,7 @@ #define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */ #define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */ #define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */ +#define X86_FEATURE_ALLOWED_SEV_FEATURES (19*32+27) /* Allowed SEV Features */ #define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ #define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ @@ -457,6 +460,7 @@ #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 */ +#define X86_FEATURE_PREFETCHI (20*32+20) /* Prefetch Data/Instruction to Cache Level */ #define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 79406bf07a1c..8d50e3e0a19b 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -127,7 +127,7 @@ KVM_X86_OP(leave_smm) KVM_X86_OP(enable_smi_window) #endif KVM_X86_OP_OPTIONAL(dev_get_attr) -KVM_X86_OP(mem_enc_ioctl) +KVM_X86_OP_OPTIONAL(mem_enc_ioctl) KVM_X86_OP_OPTIONAL(vcpu_mem_enc_ioctl) KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 67b464651c8d..b4a391929cdb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -126,7 +126,8 @@ KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_HV_TLB_FLUSH \ KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE KVM_ARCH_REQ(34) +#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE \ + KVM_ARCH_REQ_FLAGS(34, KVM_REQUEST_WAIT) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -412,7 +413,6 @@ struct kvm_rmap_head { }; struct kvm_pio_request { - unsigned long linear_rip; unsigned long count; int in; int port; @@ -918,6 +918,7 @@ struct kvm_vcpu_arch { bool emulate_regs_need_sync_to_vcpu; bool emulate_regs_need_sync_from_vcpu; int (*complete_userspace_io)(struct kvm_vcpu *vcpu); + unsigned long cui_linear_rip; gpa_t time; s8 pvclock_tsc_shift; @@ -1035,6 +1036,7 @@ struct kvm_vcpu_arch { int pending_ioapic_eoi; int pending_external_vector; + int highest_stale_pending_ioapic_eoi; /* be preempted when it's in kernel-mode(cpl=0) */ bool preempted_in_kernel; @@ -1942,6 +1944,7 @@ struct kvm_arch_async_pf { extern u32 __read_mostly kvm_nr_uret_msrs; extern bool __read_mostly allow_smaller_maxphyaddr; extern bool __read_mostly enable_apicv; +extern bool __read_mostly enable_device_posted_irqs; extern struct kvm_x86_ops kvm_x86_ops; #define kvm_x86_call(func) static_call(kvm_x86_##func) @@ -2445,7 +2448,7 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); static inline bool kvm_arch_has_irq_bypass(void) { - return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP); + return enable_device_posted_irqs; } #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 778444310cfb..e1752ba47e67 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -269,11 +269,12 @@ 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, unsigned int cpu); #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, + unsigned int cpu) { return 0; } #endif #if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) @@ -307,6 +308,7 @@ static __always_inline u64 hv_raw_get_msr(unsigned int reg) { return native_rdmsrq(reg); } +int hv_apicid_to_vp_index(u32 apic_id); #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} @@ -328,6 +330,7 @@ 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.h b/arch/x86/include/asm/msr.h index 4096b8af4ba7..9c2ea29e12a9 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -228,7 +228,7 @@ static __always_inline u64 rdpmc(int counter) #endif /* !CONFIG_PARAVIRT_XXL */ /* Instruction opcode for WRMSRNS supported in binutils >= 2.40 */ -#define WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6) +#define ASM_WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6) /* Non-serializing WRMSR, when available. Falls back to a serializing WRMSR. */ static __always_inline void wrmsrns(u32 msr, u64 val) @@ -237,7 +237,7 @@ static __always_inline void wrmsrns(u32 msr, u64 val) * WRMSR is 2 bytes. WRMSRNS is 3 bytes. Pad WRMSR with a redundant * DS prefix to avoid a trailing NOP. */ - asm volatile("1: " ALTERNATIVE("ds wrmsr", WRMSRNS, X86_FEATURE_WRMSRNS) + asm volatile("1: " ALTERNATIVE("ds wrmsr", ASM_WRMSRNS, X86_FEATURE_WRMSRNS) "2: " _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32))); } diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5ddba366d3b4..774430c3abff 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -777,6 +777,9 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot) static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + /* This bit combination is used to mark shadow stacks */ + WARN_ON_ONCE((pgprot_val(pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == + _PAGE_DIRTY); pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PTE_PFN_MASK; return __pte(pfn | check_pgprot(pgprot)); @@ -1073,22 +1076,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) */ #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) -/* - * Conversion functions: convert a page and protection to a page entry, - * and a page entry and page directory to the page they refer to. - * - * (Currently stuck as a macro because of indirect forward reference - * to linux/mm.h:page_to_nid()) - */ -#define mk_pte(page, pgprot) \ -({ \ - pgprot_t __pgprot = pgprot; \ - \ - WARN_ON_ONCE((pgprot_val(__pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == \ - _PAGE_DIRTY); \ - pfn_pte(page_to_pfn(page), __pgprot); \ -}) - static inline int pmd_bad(pmd_t pmd) { return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) != @@ -1353,8 +1340,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) -#define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) - #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h index bb107ebbe713..a5f761fbf45b 100644 --- a/arch/x86/include/asm/posted_intr.h +++ b/arch/x86/include/asm/posted_intr.h @@ -1,19 +1,24 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X86_POSTED_INTR_H #define _X86_POSTED_INTR_H + +#include <asm/cmpxchg.h> +#include <asm/rwonce.h> #include <asm/irq_vectors.h> +#include <linux/bitmap.h> + #define POSTED_INTR_ON 0 #define POSTED_INTR_SN 1 #define PID_TABLE_ENTRY_VALID 1 +#define NR_PIR_VECTORS 256 +#define NR_PIR_WORDS (NR_PIR_VECTORS / BITS_PER_LONG) + /* Posted-Interrupt Descriptor */ struct pi_desc { - union { - u32 pir[8]; /* Posted interrupt requested */ - u64 pir64[4]; - }; + unsigned long pir[NR_PIR_WORDS]; /* Posted interrupt requested */ union { struct { u16 notifications; /* Suppress and outstanding bits */ @@ -26,6 +31,65 @@ struct pi_desc { u32 rsvd[6]; } __aligned(64); +/* + * De-multiplexing posted interrupts is on the performance path, the code + * below is written to optimize the cache performance based on the following + * considerations: + * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently + * accessed by both CPU and IOMMU. + * 2.During software processing of posted interrupts, the CPU needs to do + * natural width read and xchg for checking and clearing posted interrupt + * request (PIR), a 256 bit field within the PID. + * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache + * line when posting interrupts and setting control bits. + * 4.The CPU can access the cache line a magnitude faster than the IOMMU. + * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID + * cache line. The cache line states after each operation are as follows, + * assuming a 64-bit kernel: + * CPU IOMMU PID Cache line state + * --------------------------------------------------------------- + *...read64 exclusive + *...lock xchg64 modified + *... post/atomic swap invalid + *...------------------------------------------------------------- + * + * To reduce L1 data cache miss, it is important to avoid contention with + * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used + * when processing posted interrupts in software, e.g. to dispatch interrupt + * handlers for posted MSIs, or to move interrupts from the PIR to the vIRR + * in KVM. + * + * In addition, the code is trying to keep the cache line state consistent + * as much as possible. e.g. when making a copy and clearing the PIR + * (assuming non-zero PIR bits are present in the entire PIR), it does: + * read, read, read, read, xchg, xchg, xchg, xchg + * instead of: + * read, xchg, read, xchg, read, xchg, read, xchg + */ +static __always_inline bool pi_harvest_pir(unsigned long *pir, + unsigned long *pir_vals) +{ + unsigned long pending = 0; + int i; + + for (i = 0; i < NR_PIR_WORDS; i++) { + pir_vals[i] = READ_ONCE(pir[i]); + pending |= pir_vals[i]; + } + + if (!pending) + return false; + + for (i = 0; i < NR_PIR_WORDS; i++) { + if (!pir_vals[i]) + continue; + + pir_vals[i] = arch_xchg(&pir[i], 0); + } + + return true; +} + static inline bool pi_test_and_set_on(struct pi_desc *pi_desc) { return test_and_set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); @@ -43,12 +107,12 @@ static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc) static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) { - return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); + return test_and_set_bit(vector, pi_desc->pir); } static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) { - return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); + return bitmap_empty(pi_desc->pir, NR_VECTORS); } static inline void pi_set_sn(struct pi_desc *pi_desc) @@ -110,7 +174,7 @@ static inline bool pi_pending_this_cpu(unsigned int vector) if (WARN_ON_ONCE(vector > NR_VECTORS || vector < FIRST_EXTERNAL_VECTOR)) return false; - return test_bit(vector, (unsigned long *)pid->pir); + return test_bit(vector, pid->pir); } extern void intel_posted_msi_init(void); diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 8d9f1c9aaa4c..61f56cdaccb5 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -4,6 +4,7 @@ #include <asm/page.h> #include <asm-generic/set_memory.h> +#include <asm/pgtable.h> #define set_memory_rox set_memory_rox int set_memory_rox(unsigned long addr, int numpages); @@ -37,6 +38,7 @@ int set_memory_rox(unsigned long addr, int numpages); * The caller is required to take care of these. */ +int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot); int _set_memory_uc(unsigned long addr, int numpages); int _set_memory_wc(unsigned long addr, int numpages); int _set_memory_wt(unsigned long addr, int numpages); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 6324f4c6c545..692af46603a1 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -68,6 +68,8 @@ extern void x86_ce4100_early_setup(void); static inline void x86_ce4100_early_setup(void) { } #endif +#include <linux/kexec_handover.h> + #ifndef _SETUP #include <asm/espfix.h> diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 9b7fa99ae951..ad954a1a6656 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -116,6 +116,7 @@ enum { INTERCEPT_INVPCID, INTERCEPT_MCOMMIT, INTERCEPT_TLBSYNC, + INTERCEPT_BUSLOCK, INTERCEPT_IDLE_HLT = 166, }; @@ -159,7 +160,12 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u64 avic_physical_id; /* Offset 0xf8 */ u8 reserved_7[8]; u64 vmsa_pa; /* Used for an SEV-ES guest */ - u8 reserved_8[720]; + u8 reserved_8[16]; + u16 bus_lock_counter; /* Offset 0x120 */ + u8 reserved_9[22]; + u64 allowed_sev_features; /* Offset 0x138 */ + u64 guest_sev_features; /* Offset 0x140 */ + u8 reserved_10[664]; /* * Offset 0x3e0, 32 bytes reserved * for use by hypervisor/software. @@ -291,6 +297,8 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_ #define SVM_SEV_FEAT_ALTERNATE_INJECTION BIT(4) #define SVM_SEV_FEAT_DEBUG_SWAP BIT(5) +#define VMCB_ALLOWED_SEV_FEATURES_VALID BIT_ULL(63) + struct vmcb_seg { u16 selector; u16 attrib; diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 7c488ff0c764..c10dbb74cd00 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -38,6 +38,13 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) return regs->orig_ax; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->orig_ax = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { @@ -90,6 +97,18 @@ static inline void syscall_get_arguments(struct task_struct *task, args[5] = regs->bp; } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + regs->bx = args[0]; + regs->cx = args[1]; + regs->dx = args[2]; + regs->si = args[3]; + regs->di = args[4]; + regs->bp = args[5]; +} + static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_I386; @@ -121,6 +140,30 @@ static inline void syscall_get_arguments(struct task_struct *task, } } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ +# ifdef CONFIG_IA32_EMULATION + if (task->thread_info.status & TS_COMPAT) { + regs->bx = *args++; + regs->cx = *args++; + regs->dx = *args++; + regs->si = *args++; + regs->di = *args++; + regs->bp = *args; + } else +# endif + { + regs->di = *args++; + regs->si = *args++; + regs->dx = *args++; + regs->r10 = *args++; + regs->r8 = *args++; + regs->r9 = *args; + } +} + static inline int syscall_get_arch(struct task_struct *task) { /* x32 tasks should be considered AUDIT_ARCH_X86_64. */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 225a12e0d5d6..6f3499507c5e 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -845,6 +845,7 @@ struct kvm_sev_snp_launch_start { }; /* Kept in sync with firmware values for simplicity. */ +#define KVM_SEV_PAGE_TYPE_INVALID 0x0 #define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1 #define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3 #define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4 diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h index 50c45ead4e7c..2671c4e1b3a0 100644 --- a/arch/x86/include/uapi/asm/setup_data.h +++ b/arch/x86/include/uapi/asm/setup_data.h @@ -13,7 +13,8 @@ #define SETUP_CC_BLOB 7 #define SETUP_IMA 8 #define SETUP_RNG_SEED 9 -#define SETUP_ENUM_MAX SETUP_RNG_SEED +#define SETUP_KEXEC_KHO 10 +#define SETUP_ENUM_MAX SETUP_KEXEC_KHO #define SETUP_INDIRECT (1<<31) #define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) @@ -78,6 +79,16 @@ struct ima_setup_data { __u64 size; } __attribute__((packed)); +/* + * Locations of kexec handover metadata + */ +struct kho_data { + __u64 fdt_addr; + __u64 fdt_size; + __u64 scratch_addr; + __u64 scratch_size; +} __attribute__((packed)); + #endif /* __ASSEMBLER__ */ #endif /* _UAPI_ASM_X86_SETUP_DATA_H */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index ec1321248dac..9c640a521a67 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -95,6 +95,7 @@ #define SVM_EXIT_CR14_WRITE_TRAP 0x09e #define SVM_EXIT_CR15_WRITE_TRAP 0x09f #define SVM_EXIT_INVPCID 0x0a2 +#define SVM_EXIT_BUS_LOCK 0x0a5 #define SVM_EXIT_IDLE_HLT 0x0a6 #define SVM_EXIT_NPF 0x400 #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 @@ -225,6 +226,7 @@ { SVM_EXIT_CR4_WRITE_TRAP, "write_cr4_trap" }, \ { SVM_EXIT_CR8_WRITE_TRAP, "write_cr8_trap" }, \ { SVM_EXIT_INVPCID, "invpcid" }, \ + { SVM_EXIT_BUS_LOCK, "buslock" }, \ { SVM_EXIT_IDLE_HLT, "idle-halt" }, \ { SVM_EXIT_NPF, "npf" }, \ { SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \ diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c index f36f28405dcc..6d7603511f52 100644 --- a/arch/x86/kernel/acpi/madt_wakeup.c +++ b/arch/x86/kernel/acpi/madt_wakeup.c @@ -126,7 +126,7 @@ static int __init acpi_mp_setup_reset(u64 reset_vector) return 0; } -static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip) +static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip, unsigned int cpu) { if (!acpi_mp_wake_mailbox_paddr) { pr_warn_once("No MADT mailbox: cannot bringup secondary CPUs. Booting with kexec?\n"); diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index b5bb7a2e8340..58abb941c45b 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -27,7 +27,13 @@ static void noop_send_IPI_allbutself(int vector) { } static void noop_send_IPI_all(int vector) { } static void noop_send_IPI_self(int vector) { } static void noop_apic_icr_write(u32 low, u32 id) { } -static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { return -1; } + +static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip, + unsigned int cpu) +{ + return -1; +} + static u64 noop_apic_icr_read(void) { return 0; } static u32 noop_get_apic_id(u32 apicid) { return 0; } static void noop_apic_eoi(void) { } diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index e272bc7fdc8e..5c5be2d58242 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -57,7 +57,7 @@ static void numachip2_apic_icr_write(int apicid, unsigned int val) numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val); } -static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip) +static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip, unsigned int cpu) { numachip_apic_icr_write(phys_apicid, APIC_DM_INIT); numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP | diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 7fef504ca508..15209f220e1f 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -667,7 +667,7 @@ static __init void build_uv_gr_table(void) } } -static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip) +static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip, unsigned int cpu) { unsigned long val; int pnode; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 0be61c45400c..bcb534688dfe 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -278,6 +278,7 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, unsigned long long mend) { unsigned long start, end; + int ret; cmem->ranges[0].start = mstart; cmem->ranges[0].end = mend; @@ -286,22 +287,43 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, /* Exclude elf header region */ start = image->elf_load_addr; end = start + image->elf_headers_sz - 1; - return crash_exclude_mem_range(cmem, start, end); + ret = crash_exclude_mem_range(cmem, start, end); + + if (ret) + return ret; + + /* Exclude dm crypt keys region */ + if (image->dm_crypt_keys_addr) { + start = image->dm_crypt_keys_addr; + end = start + image->dm_crypt_keys_sz - 1; + return crash_exclude_mem_range(cmem, start, end); + } + + return ret; } /* Prepare memory map for crash dump kernel */ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) { + unsigned int nr_ranges = 0; int i, ret = 0; unsigned long flags; struct e820_entry ei; struct crash_memmap_data cmd; struct crash_mem *cmem; - cmem = vzalloc(struct_size(cmem, ranges, 1)); + /* + * Using random kexec_buf for passing dm crypt keys may cause a range + * split. So use two slots here. + */ + nr_ranges = 2; + cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return -ENOMEM; + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; + memset(&cmd, 0, sizeof(struct crash_memmap_data)); cmd.params = params; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 9920122018a0..c3acbd26408b 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1300,6 +1300,24 @@ void __init e820__memblock_setup(void) } /* + * At this point memblock is only allowed to allocate from memory + * below 1M (aka ISA_END_ADDRESS) up until direct map is completely set + * up in init_mem_mapping(). + * + * KHO kernels are special and use only scratch memory for memblock + * allocations, but memory below 1M is ignored by kernel after early + * boot and cannot be naturally marked as scratch. + * + * To allow allocation of the real-mode trampoline and a few (if any) + * other very early allocations from below 1M forcibly mark the memory + * below 1M as scratch. + * + * After real mode trampoline is allocated, we clear that scratch + * marking. + */ + memblock_mark_kho_scratch(0, SZ_1M); + + /* * 32-bit systems are limited to 4BG of memory even with HIGHMEM and * to even less without it. * Discard memory after max_pfn - the actual limit detected at runtime. diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 81f9b78e0f7b..9ed29ff10e59 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -380,61 +380,18 @@ void intel_posted_msi_init(void) this_cpu_write(posted_msi_pi_desc.ndst, destination); } -/* - * De-multiplexing posted interrupts is on the performance path, the code - * below is written to optimize the cache performance based on the following - * considerations: - * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently - * accessed by both CPU and IOMMU. - * 2.During posted MSI processing, the CPU needs to do 64-bit read and xchg - * for checking and clearing posted interrupt request (PIR), a 256 bit field - * within the PID. - * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache - * line when posting interrupts and setting control bits. - * 4.The CPU can access the cache line a magnitude faster than the IOMMU. - * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID - * cache line. The cache line states after each operation are as follows: - * CPU IOMMU PID Cache line state - * --------------------------------------------------------------- - *...read64 exclusive - *...lock xchg64 modified - *... post/atomic swap invalid - *...------------------------------------------------------------- - * - * To reduce L1 data cache miss, it is important to avoid contention with - * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used - * to dispatch interrupt handlers. - * - * In addition, the code is trying to keep the cache line state consistent - * as much as possible. e.g. when making a copy and clearing the PIR - * (assuming non-zero PIR bits are present in the entire PIR), it does: - * read, read, read, read, xchg, xchg, xchg, xchg - * instead of: - * read, xchg, read, xchg, read, xchg, read, xchg - */ -static __always_inline bool handle_pending_pir(u64 *pir, struct pt_regs *regs) +static __always_inline bool handle_pending_pir(unsigned long *pir, struct pt_regs *regs) { - int i, vec = FIRST_EXTERNAL_VECTOR; - unsigned long pir_copy[4]; - bool handled = false; + unsigned long pir_copy[NR_PIR_WORDS]; + int vec = FIRST_EXTERNAL_VECTOR; - for (i = 0; i < 4; i++) - pir_copy[i] = pir[i]; - - for (i = 0; i < 4; i++) { - if (!pir_copy[i]) - continue; + if (!pi_harvest_pir(pir, pir_copy)) + return false; - pir_copy[i] = arch_xchg(&pir[i], 0); - handled = true; - } - - if (handled) { - for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR) - call_irq_handler(vec, regs); - } + for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR) + call_irq_handler(vec, regs); - return handled; + return true; } /* @@ -464,7 +421,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification) * MAX_POSTED_MSI_COALESCING_LOOP - 1 loops are executed here. */ while (++i < MAX_POSTED_MSI_COALESCING_LOOP) { - if (!handle_pending_pir(pid->pir64, regs)) + if (!handle_pending_pir(pid->pir, regs)) break; } @@ -479,7 +436,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification) * process PIR bits one last time such that handling the new interrupts * are not delayed until the next IRQ. */ - handle_pending_pir(pid->pir64, regs); + handle_pending_pir(pid->pir, regs); apic_eoi(); irq_exit(); diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 68530fad05f7..24a41f0e0cf1 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -27,6 +27,8 @@ #include <asm/kexec-bzimage64.h> #define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */ +#define MAX_DMCRYPTKEYS_STR_LEN 31 /* dmcryptkeys=0x<64bit-value> */ + /* * Defines lowest physical address for various segments. Not sure where @@ -76,6 +78,10 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params, if (image->type == KEXEC_TYPE_CRASH) { len = sprintf(cmdline_ptr, "elfcorehdr=0x%lx ", image->elf_load_addr); + + if (image->dm_crypt_keys_addr != 0) + len += sprintf(cmdline_ptr + len, + "dmcryptkeys=0x%lx ", image->dm_crypt_keys_addr); } memcpy(cmdline_ptr + len, cmdline, cmdline_len); cmdline_len += len; @@ -233,6 +239,32 @@ setup_ima_state(const struct kimage *image, struct boot_params *params, #endif /* CONFIG_IMA_KEXEC */ } +static void setup_kho(const struct kimage *image, struct boot_params *params, + unsigned long params_load_addr, + unsigned int setup_data_offset) +{ + struct setup_data *sd = (void *)params + setup_data_offset; + struct kho_data *kho = (void *)sd + sizeof(*sd); + + if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER)) + return; + + sd->type = SETUP_KEXEC_KHO; + sd->len = sizeof(struct kho_data); + + /* Only add if we have all KHO images in place */ + if (!image->kho.fdt || !image->kho.scratch) + return; + + /* Add setup data */ + kho->fdt_addr = image->kho.fdt; + kho->fdt_size = PAGE_SIZE; + kho->scratch_addr = image->kho.scratch->mem; + kho->scratch_size = image->kho.scratch->bufsz; + sd->next = params->hdr.setup_data; + params->hdr.setup_data = params_load_addr + setup_data_offset; +} + static int setup_boot_parameters(struct kimage *image, struct boot_params *params, unsigned long params_load_addr, @@ -312,6 +344,13 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, sizeof(struct ima_setup_data); } + if (IS_ENABLED(CONFIG_KEXEC_HANDOVER)) { + /* Setup space to store preservation metadata */ + setup_kho(image, params, params_load_addr, setup_data_offset); + setup_data_offset += sizeof(struct setup_data) + + sizeof(struct kho_data); + } + /* Setup RNG seed */ setup_rng_seed(params, params_load_addr, setup_data_offset); @@ -441,6 +480,19 @@ static void *bzImage64_load(struct kimage *image, char *kernel, ret = crash_load_segments(image); if (ret) return ERR_PTR(ret); + ret = crash_load_dm_crypt_keys(image); + if (ret == -ENOENT) { + kexec_dprintk("No dm crypt key to load\n"); + } else if (ret) { + pr_err("Failed to load dm crypt keys\n"); + return ERR_PTR(ret); + } + if (image->dm_crypt_keys_addr && + cmdline_len + MAX_ELFCOREHDR_STR_LEN + MAX_DMCRYPTKEYS_STR_LEN > + header->cmdline_size) { + pr_err("Appending dmcryptkeys=<addr> to command line exceeds maximum allowed length\n"); + return ERR_PTR(-EINVAL); + } } #endif @@ -468,6 +520,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, efi_map_sz = efi_get_runtime_map_size(); params_cmdline_sz = sizeof(struct boot_params) + cmdline_len + MAX_ELFCOREHDR_STR_LEN; + if (image->dm_crypt_keys_addr) + params_cmdline_sz += MAX_DMCRYPTKEYS_STR_LEN; params_cmdline_sz = ALIGN(params_cmdline_sz, 16); kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) + sizeof(struct setup_data) + @@ -479,6 +533,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel, kbuf.bufsz += sizeof(struct setup_data) + sizeof(struct ima_setup_data); + if (IS_ENABLED(CONFIG_KEXEC_HANDOVER)) + kbuf.bufsz += sizeof(struct setup_data) + + sizeof(struct kho_data); + params = kzalloc(kbuf.bufsz, GFP_KERNEL); if (!params) return ERR_PTR(-ENOMEM); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 949c9e4bfad2..697fb99406e6 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -630,13 +630,35 @@ static void kexec_mark_crashkres(bool protect) kexec_mark_range(control, crashk_res.end, protect); } +/* make the memory storing dm crypt keys in/accessible */ +static void kexec_mark_dm_crypt_keys(bool protect) +{ + unsigned long start_paddr, end_paddr; + unsigned int nr_pages; + + if (kexec_crash_image->dm_crypt_keys_addr) { + start_paddr = kexec_crash_image->dm_crypt_keys_addr; + end_paddr = start_paddr + kexec_crash_image->dm_crypt_keys_sz - 1; + nr_pages = (PAGE_ALIGN(end_paddr) - PAGE_ALIGN_DOWN(start_paddr))/PAGE_SIZE; + if (protect) + set_memory_np((unsigned long)phys_to_virt(start_paddr), nr_pages); + else + __set_memory_prot( + (unsigned long)phys_to_virt(start_paddr), + nr_pages, + __pgprot(_PAGE_PRESENT | _PAGE_NX | _PAGE_RW)); + } +} + void arch_kexec_protect_crashkres(void) { kexec_mark_crashkres(true); + kexec_mark_dm_crypt_keys(true); } void arch_kexec_unprotect_crashkres(void) { + kexec_mark_dm_crypt_keys(false); kexec_mark_crashkres(false); } #endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 7d9ed79a93c0..fb27be697128 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -282,8 +282,8 @@ static void __init cleanup_highmap(void) static void __init reserve_brk(void) { if (_brk_end > _brk_start) - memblock_reserve(__pa_symbol(_brk_start), - _brk_end - _brk_start); + memblock_reserve_kern(__pa_symbol(_brk_start), + _brk_end - _brk_start); /* Mark brk area as locked down and no longer taking any new allocations */ @@ -356,7 +356,7 @@ static void __init early_reserve_initrd(void) !ramdisk_image || !ramdisk_size) return; /* No initrd provided by bootloader */ - memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); + memblock_reserve_kern(ramdisk_image, ramdisk_end - ramdisk_image); } static void __init reserve_initrd(void) @@ -409,7 +409,7 @@ static void __init add_early_ima_buffer(u64 phys_addr) } if (data->size) { - memblock_reserve(data->addr, data->size); + memblock_reserve_kern(data->addr, data->size); ima_kexec_buffer_phys = data->addr; ima_kexec_buffer_size = data->size; } @@ -447,6 +447,29 @@ int __init ima_get_kexec_buffer(void **addr, size_t *size) } #endif +static void __init add_kho(u64 phys_addr, u32 data_len) +{ + struct kho_data *kho; + u64 addr = phys_addr + sizeof(struct setup_data); + u64 size = data_len - sizeof(struct setup_data); + + if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER)) { + pr_warn("Passed KHO data, but CONFIG_KEXEC_HANDOVER not set. Ignoring.\n"); + return; + } + + kho = early_memremap(addr, size); + if (!kho) { + pr_warn("setup: failed to memremap kho data (0x%llx, 0x%llx)\n", + addr, size); + return; + } + + kho_populate(kho->fdt_addr, kho->fdt_size, kho->scratch_addr, kho->scratch_size); + + early_memunmap(kho, size); +} + static void __init parse_setup_data(void) { struct setup_data *data; @@ -475,6 +498,9 @@ static void __init parse_setup_data(void) case SETUP_IMA: add_early_ima_buffer(pa_data); break; + case SETUP_KEXEC_KHO: + add_kho(pa_data, data_len); + break; case SETUP_RNG_SEED: data = early_memremap(pa_data, data_len); add_bootloader_randomness(data->data, data->len); @@ -549,7 +575,7 @@ static void __init memblock_x86_reserve_range_setup_data(void) len = sizeof(*data); pa_next = data->next; - memblock_reserve(pa_data, sizeof(*data) + data->len); + memblock_reserve_kern(pa_data, sizeof(*data) + data->len); if (data->type == SETUP_INDIRECT) { len += data->len; @@ -563,7 +589,7 @@ static void __init memblock_x86_reserve_range_setup_data(void) indirect = (struct setup_indirect *)data->data; if (indirect->type != SETUP_INDIRECT) - memblock_reserve(indirect->addr, indirect->len); + memblock_reserve_kern(indirect->addr, indirect->len); } pa_data = pa_next; @@ -766,8 +792,8 @@ static void __init early_reserve_memory(void) * __end_of_kernel_reserve symbol must be explicitly reserved with a * separate memblock_reserve() or they will be discarded. */ - memblock_reserve(__pa_symbol(_text), - (unsigned long)__end_of_kernel_reserve - (unsigned long)_text); + memblock_reserve_kern(__pa_symbol(_text), + (unsigned long)__end_of_kernel_reserve - (unsigned long)_text); /* * The first 4Kb of memory is a BIOS owned area, but generally it is diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 1ba92ac9441d..fc78c2325fd2 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -695,7 +695,7 @@ static void send_init_sequence(u32 phys_apicid) /* * Wake up AP by INIT, INIT, STARTUP sequence. */ -static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip) +static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip, unsigned int cpu) { unsigned long send_status = 0, accept_status = 0; int num_starts, j, maxlvt; @@ -842,7 +842,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle) * Returns zero if startup was successfully sent, else error code from * ->wakeup_secondary_cpu. */ -static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle) +static int do_boot_cpu(u32 apicid, unsigned int cpu, struct task_struct *idle) { unsigned long start_ip = real_mode_header->trampoline_start; int ret; @@ -896,11 +896,11 @@ static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle) * - Use an INIT boot APIC message */ if (apic->wakeup_secondary_cpu_64) - ret = apic->wakeup_secondary_cpu_64(apicid, start_ip); + ret = apic->wakeup_secondary_cpu_64(apicid, start_ip, cpu); else if (apic->wakeup_secondary_cpu) - ret = apic->wakeup_secondary_cpu(apicid, start_ip); + ret = apic->wakeup_secondary_cpu(apicid, start_ip, cpu); else - ret = wakeup_secondary_cpu_via_init(apicid, start_ip); + ret = wakeup_secondary_cpu_via_init(apicid, start_ip, cpu); /* If the wakeup mechanism failed, cleanup the warm reset vector */ if (ret) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 6569b453546b..b2d006756e02 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -978,6 +978,7 @@ void kvm_set_cpu_caps(void) F(FZRM), F(FSRS), F(FSRC), + F(WRMSRNS), F(AMX_FP16), F(AVX_IFMA), F(LAM), @@ -1093,6 +1094,7 @@ void kvm_set_cpu_caps(void) F(AMD_SSB_NO), F(AMD_STIBP), F(AMD_STIBP_ALWAYS_ON), + F(AMD_IBRS_SAME_MODE), F(AMD_PSFD), F(AMD_IBPB_RET), ); @@ -1150,6 +1152,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_init(CPUID_8000_0021_EAX, F(NO_NESTED_DATA_BP), + F(WRMSR_XX_BASE_NS), /* * Synthesize "LFENCE is serializing" into the AMD-defined entry * in KVM's supported CPUID, i.e. if the feature is reported as @@ -1163,10 +1166,13 @@ void kvm_set_cpu_caps(void) SYNTHESIZED_F(LFENCE_RDTSC), /* SmmPgCfgLock */ F(NULL_SEL_CLR_BASE), + /* UpperAddressIgnore */ F(AUTOIBRS), + F(PREFETCHI), EMULATED_F(NO_SMM_CTL_MSR), /* PrefetchCtlMsr */ - F(WRMSR_XX_BASE_NS), + /* GpOnUserCpuid */ + /* EPSF */ SYNTHESIZED_F(SBPB), SYNTHESIZED_F(IBPB_BRTYPE), SYNTHESIZED_F(SRSO_NO), diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 995eb5054360..45dae2d5d2f1 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -296,11 +296,8 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) index == RTC_GSI) { u16 dm = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); - if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, - e->fields.dest_id, dm) || - kvm_apic_pending_eoi(vcpu, e->fields.vector)) - __set_bit(e->fields.vector, - ioapic_handled_vectors); + kvm_scan_ioapic_irq(vcpu, e->fields.dest_id, dm, + e->fields.vector, ioapic_handled_vectors); } } spin_unlock(&ioapic->lock); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 539333ac4b38..aa8cb4ac0479 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -120,4 +120,6 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors); void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors); +void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode, + u8 vector, unsigned long *ioapic_handled_vectors); #endif diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 8136695f7b96..d6d792b5d1bd 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -402,6 +402,33 @@ void kvm_arch_post_irq_routing_update(struct kvm *kvm) kvm_make_scan_ioapic_request(kvm); } +void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode, + u8 vector, unsigned long *ioapic_handled_vectors) +{ + /* + * Intercept EOI if the vCPU is the target of the new IRQ routing, or + * the vCPU has a pending IRQ from the old routing, i.e. if the vCPU + * may receive a level-triggered IRQ in the future, or already received + * level-triggered IRQ. The EOI needs to be intercepted and forwarded + * to I/O APIC emulation so that the IRQ can be de-asserted. + */ + if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, dest_id, dest_mode)) { + __set_bit(vector, ioapic_handled_vectors); + } else if (kvm_apic_pending_eoi(vcpu, vector)) { + __set_bit(vector, ioapic_handled_vectors); + + /* + * Track the highest pending EOI for which the vCPU is NOT the + * target in the new routing. Only the EOI for the IRQ that is + * in-flight (for the old routing) needs to be intercepted, any + * future IRQs that arrive on this vCPU will be coincidental to + * the level-triggered routing and don't need to be intercepted. + */ + if ((int)vector > vcpu->arch.highest_stale_pending_ioapic_eoi) + vcpu->arch.highest_stale_pending_ioapic_eoi = vector; + } +} + void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) { @@ -424,11 +451,11 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.trig_mode && - (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, - irq.dest_id, irq.dest_mode) || - kvm_apic_pending_eoi(vcpu, irq.vector))) - __set_bit(irq.vector, ioapic_handled_vectors); + if (!irq.trig_mode) + continue; + + kvm_scan_ioapic_irq(vcpu, irq.dest_id, irq.dest_mode, + irq.vector, ioapic_handled_vectors); } } srcu_read_unlock(&kvm->irq_srcu, idx); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c9de81cc27e1..73418dc0ebb2 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -655,27 +655,29 @@ static u8 count_vectors(void *bitmap) return count; } -bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr) +bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr) { + unsigned long pir_vals[NR_PIR_WORDS]; + u32 *__pir = (void *)pir_vals; u32 i, vec; - u32 pir_val, irr_val, prev_irr_val; + u32 irr_val, prev_irr_val; int max_updated_irr; max_updated_irr = -1; *max_irr = -1; + if (!pi_harvest_pir(pir, pir_vals)) + return false; + for (i = vec = 0; i <= 7; i++, vec += 32) { u32 *p_irr = (u32 *)(regs + APIC_IRR + i * 0x10); - irr_val = *p_irr; - pir_val = READ_ONCE(pir[i]); - - if (pir_val) { - pir_val = xchg(&pir[i], 0); + irr_val = READ_ONCE(*p_irr); + if (__pir[i]) { prev_irr_val = irr_val; do { - irr_val = prev_irr_val | pir_val; + irr_val = prev_irr_val | __pir[i]; } while (prev_irr_val != irr_val && !try_cmpxchg(p_irr, &prev_irr_val, irr_val)); @@ -691,7 +693,7 @@ bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr) } EXPORT_SYMBOL_GPL(__kvm_apic_update_irr); -bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr) +bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr) { struct kvm_lapic *apic = vcpu->arch.apic; bool irr_updated = __kvm_apic_update_irr(pir, apic->regs, max_irr); @@ -1459,6 +1461,14 @@ static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) if (!kvm_ioapic_handles_vector(apic, vector)) return; + /* + * If the intercepted EOI is for an IRQ that was pending from previous + * routing, then re-scan the I/O APIC routes as EOIs for the IRQ likely + * no longer need to be intercepted. + */ + if (apic->vcpu->arch.highest_stale_pending_ioapic_eoi == vector) + kvm_make_request(KVM_REQ_SCAN_IOAPIC, apic->vcpu); + /* Request a KVM exit to inform the userspace IOAPIC. */ if (irqchip_split(apic->vcpu->kvm)) { apic->vcpu->arch.pending_ioapic_eoi = vector; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index e33c969439f7..4ce30db65828 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -103,8 +103,8 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int shorthand, unsigned int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec); -bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); -bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); +bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr); +bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7b3f1783ab3c..cbc84c6abc2e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3020,7 +3020,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } if (is_shadow_present_pte(*sptep)) { - if (prefetch) + if (prefetch && is_last_spte(*sptep, level) && + pfn == spte_to_pfn(*sptep)) return RET_PF_SPURIOUS; /* @@ -3034,7 +3035,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, child = spte_to_child_sp(pte); drop_parent_pte(vcpu->kvm, child, sptep); flush = true; - } else if (pfn != spte_to_pfn(*sptep)) { + } else if (WARN_ON_ONCE(pfn != spte_to_pfn(*sptep))) { drop_spte(vcpu->kvm, sptep); flush = true; } else diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 405874f4d088..7f3d7229b2c1 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -378,7 +378,7 @@ static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte, /* Zapping leaf spte is allowed only when write lock is held. */ lockdep_assert_held_write(&kvm->mmu_lock); /* Because write lock is held, operation should success. */ - ret = static_call(kvm_x86_remove_external_spte)(kvm, gfn, level, old_pfn); + ret = kvm_x86_call(remove_external_spte)(kvm, gfn, level, old_pfn); KVM_BUG_ON(ret, kvm); } @@ -485,8 +485,8 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) } if (is_mirror_sp(sp) && - WARN_ON(static_call(kvm_x86_free_external_spt)(kvm, base_gfn, sp->role.level, - sp->external_spt))) { + WARN_ON(kvm_x86_call(free_external_spt)(kvm, base_gfn, sp->role.level, + sp->external_spt))) { /* * Failed to free page table page in mirror page table and * there is nothing to do further. @@ -538,12 +538,12 @@ static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sp * external page table, or leaf. */ if (is_leaf) { - ret = static_call(kvm_x86_set_external_spte)(kvm, gfn, level, new_pfn); + ret = kvm_x86_call(set_external_spte)(kvm, gfn, level, new_pfn); } else { void *external_spt = get_external_spt(gfn, new_spte, level); KVM_BUG_ON(!external_spt, kvm); - ret = static_call(kvm_x86_link_external_spt)(kvm, gfn, level, external_spt); + ret = kvm_x86_call(link_external_spt)(kvm, gfn, level, external_spt); } if (ret) __kvm_tdp_mmu_write_spte(sptep, old_spte); @@ -1153,13 +1153,12 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, if (WARN_ON_ONCE(sp->role.level != fault->goal_level)) return RET_PF_RETRY; - if (fault->prefetch && is_shadow_present_pte(iter->old_spte)) - return RET_PF_SPURIOUS; - if (is_shadow_present_pte(iter->old_spte) && - is_access_allowed(fault, iter->old_spte) && - is_last_spte(iter->old_spte, iter->level)) + (fault->prefetch || is_access_allowed(fault, iter->old_spte)) && + is_last_spte(iter->old_spte, iter->level)) { + WARN_ON_ONCE(fault->pfn != spte_to_pfn(iter->old_spte)); return RET_PF_SPURIOUS; + } if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 834b67672d50..8427a48b8b7a 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -678,6 +678,33 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa; vmcb02->control.msrpm_base_pa = vmcb01->control.msrpm_base_pa; + /* + * Stash vmcb02's counter if the guest hasn't moved past the guilty + * instruction; otherwise, reset the counter to '0'. + * + * In order to detect if L2 has made forward progress or not, track the + * RIP at which a bus lock has occurred on a per-vmcb12 basis. If RIP + * is changed, guest has clearly made forward progress, bus_lock_counter + * still remained '1', so reset bus_lock_counter to '0'. Eg. In the + * scenario, where a buslock happened in L1 before VMRUN, the bus lock + * firmly happened on an instruction in the past. Even if vmcb01's + * counter is still '1', (because the guilty instruction got patched), + * the vCPU has clearly made forward progress and so KVM should reset + * vmcb02's counter to '0'. + * + * If the RIP hasn't changed, stash the bus lock counter at nested VMRUN + * to prevent the same guilty instruction from triggering a VM-Exit. Eg. + * if userspace rate-limits the vCPU, then it's entirely possible that + * L1's tick interrupt is pending by the time userspace re-runs the + * vCPU. If KVM unconditionally clears the counter on VMRUN, then when + * L1 re-enters L2, the same instruction will trigger a VM-Exit and the + * entire cycle start over. + */ + if (vmcb02->save.rip && (svm->nested.ctl.bus_lock_rip == vmcb02->save.rip)) + vmcb02->control.bus_lock_counter = 1; + else + vmcb02->control.bus_lock_counter = 0; + /* Done at vmrun: asid. */ /* Also overwritten later if necessary. */ @@ -1039,8 +1066,17 @@ int nested_svm_vmexit(struct vcpu_svm *svm) } + /* + * Invalidate bus_lock_rip unless KVM is still waiting for the guest + * to make forward progress before re-enabling bus lock detection. + */ + if (!vmcb02->control.bus_lock_counter) + svm->nested.ctl.bus_lock_rip = INVALID_GPA; + nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr); + kvm_nested_vmexit_handle_ibrs(vcpu); + svm_switch_vmcb(svm, &svm->vmcb01); /* diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 1aa0f07d3a63..5a69b657dae9 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -561,6 +561,8 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; + sev->policy = params.policy; + memset(&start, 0, sizeof(start)); dh_blob = NULL; @@ -1593,11 +1595,11 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* allocate memory for header and transport buffer */ ret = -ENOMEM; - hdr = kzalloc(params.hdr_len, GFP_KERNEL_ACCOUNT); + hdr = kzalloc(params.hdr_len, GFP_KERNEL); if (!hdr) goto e_unpin; - trans_data = kzalloc(params.trans_len, GFP_KERNEL_ACCOUNT); + trans_data = kzalloc(params.trans_len, GFP_KERNEL); if (!trans_data) goto e_free_hdr; @@ -1883,70 +1885,6 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) atomic_set_release(&src_sev->migration_in_progress, 0); } -/* vCPU mutex subclasses. */ -enum sev_migration_role { - SEV_MIGRATION_SOURCE = 0, - SEV_MIGRATION_TARGET, - SEV_NR_MIGRATION_ROLES, -}; - -static int sev_lock_vcpus_for_migration(struct kvm *kvm, - enum sev_migration_role role) -{ - struct kvm_vcpu *vcpu; - unsigned long i, j; - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (mutex_lock_killable_nested(&vcpu->mutex, role)) - goto out_unlock; - -#ifdef CONFIG_PROVE_LOCKING - if (!i) - /* - * Reset the role to one that avoids colliding with - * the role used for the first vcpu mutex. - */ - role = SEV_NR_MIGRATION_ROLES; - else - mutex_release(&vcpu->mutex.dep_map, _THIS_IP_); -#endif - } - - return 0; - -out_unlock: - - kvm_for_each_vcpu(j, vcpu, kvm) { - if (i == j) - break; - -#ifdef CONFIG_PROVE_LOCKING - if (j) - mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_); -#endif - - mutex_unlock(&vcpu->mutex); - } - return -EINTR; -} - -static void sev_unlock_vcpus_for_migration(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu; - unsigned long i; - bool first = true; - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (first) - first = false; - else - mutex_acquire(&vcpu->mutex.dep_map, - SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_); - - mutex_unlock(&vcpu->mutex); - } -} - static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) { struct kvm_sev_info *dst = to_kvm_sev_info(dst_kvm); @@ -2084,10 +2022,10 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) charged = true; } - ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE); + ret = kvm_lock_all_vcpus(kvm); if (ret) goto out_dst_cgroup; - ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET); + ret = kvm_lock_all_vcpus(source_kvm); if (ret) goto out_dst_vcpu; @@ -2101,9 +2039,9 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) ret = 0; out_source_vcpu: - sev_unlock_vcpus_for_migration(source_kvm); + kvm_unlock_all_vcpus(source_kvm); out_dst_vcpu: - sev_unlock_vcpus_for_migration(kvm); + kvm_unlock_all_vcpus(kvm); out_dst_cgroup: /* Operates on the source on success, on the destination on failure. */ if (charged) @@ -2200,6 +2138,8 @@ static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (params.policy & SNP_POLICY_MASK_SINGLE_SOCKET) return -EINVAL; + sev->policy = params.policy; + sev->snp_context = snp_context_create(kvm, argp); if (!sev->snp_context) return -ENOTTY; @@ -4007,10 +3947,8 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm) * Unless Creation is deferred until INIT, signal the vCPU to update * its state. */ - if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT) { - kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu); - kvm_vcpu_kick(target_vcpu); - } + if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT) + kvm_make_request_and_kick(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu); return 0; } @@ -4468,6 +4406,7 @@ void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) static void sev_es_init_vmcb(struct vcpu_svm *svm) { + struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm); struct vmcb *vmcb = svm->vmcb01.ptr; struct kvm_vcpu *vcpu = &svm->vcpu; @@ -4483,6 +4422,10 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa) svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); + if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES)) + svm->vmcb->control.allowed_sev_features = sev->vmsa_features | + VMCB_ALLOWED_SEV_FEATURES_VALID; + /* Can't intercept CR register access, HV can't modify CR registers */ svm_clr_intercept(svm, INTERCEPT_CR0_READ); svm_clr_intercept(svm, INTERCEPT_CR4_READ); @@ -4943,3 +4886,97 @@ int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) return level; } + +struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_save_area *vmsa; + struct kvm_sev_info *sev; + int error = 0; + int ret; + + if (!sev_es_guest(vcpu->kvm)) + return NULL; + + /* + * If the VMSA has not yet been encrypted, return a pointer to the + * current un-encrypted VMSA. + */ + if (!vcpu->arch.guest_state_protected) + return (struct vmcb_save_area *)svm->sev_es.vmsa; + + sev = to_kvm_sev_info(vcpu->kvm); + + /* Check if the SEV policy allows debugging */ + if (sev_snp_guest(vcpu->kvm)) { + if (!(sev->policy & SNP_POLICY_DEBUG)) + return NULL; + } else { + if (sev->policy & SEV_POLICY_NODBG) + return NULL; + } + + if (sev_snp_guest(vcpu->kvm)) { + struct sev_data_snp_dbg dbg = {0}; + + vmsa = snp_alloc_firmware_page(__GFP_ZERO); + if (!vmsa) + return NULL; + + dbg.gctx_paddr = __psp_pa(sev->snp_context); + dbg.src_addr = svm->vmcb->control.vmsa_pa; + dbg.dst_addr = __psp_pa(vmsa); + + ret = sev_do_cmd(SEV_CMD_SNP_DBG_DECRYPT, &dbg, &error); + + /* + * Return the target page to a hypervisor page no matter what. + * If this fails, the page can't be used, so leak it and don't + * try to use it. + */ + if (snp_page_reclaim(vcpu->kvm, PHYS_PFN(__pa(vmsa)))) + return NULL; + + if (ret) { + pr_err("SEV: SNP_DBG_DECRYPT failed ret=%d, fw_error=%d (%#x)\n", + ret, error, error); + free_page((unsigned long)vmsa); + + return NULL; + } + } else { + struct sev_data_dbg dbg = {0}; + struct page *vmsa_page; + + vmsa_page = alloc_page(GFP_KERNEL); + if (!vmsa_page) + return NULL; + + vmsa = page_address(vmsa_page); + + dbg.handle = sev->handle; + dbg.src_addr = svm->vmcb->control.vmsa_pa; + dbg.dst_addr = __psp_pa(vmsa); + dbg.len = PAGE_SIZE; + + ret = sev_do_cmd(SEV_CMD_DBG_DECRYPT, &dbg, &error); + if (ret) { + pr_err("SEV: SEV_CMD_DBG_DECRYPT failed ret=%d, fw_error=%d (0x%x)\n", + ret, error, error); + __free_page(vmsa_page); + + return NULL; + } + } + + return vmsa; +} + +void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa) +{ + /* If the VMSA has not yet been encrypted, nothing was allocated */ + if (!vcpu->arch.guest_state_protected || !vmsa) + return; + + free_page((unsigned long)vmsa); +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index ffb34dadff1c..ab9b947dbf4f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -29,6 +29,7 @@ #include <linux/cc_platform.h> #include <linux/smp.h> #include <linux/string_choices.h> +#include <linux/mutex.h> #include <asm/apic.h> #include <asm/msr.h> @@ -232,6 +233,8 @@ module_param(tsc_scaling, int, 0444); static bool avic; module_param(avic, bool, 0444); +module_param(enable_device_posted_irqs, bool, 0444); + bool __read_mostly dump_invalid_vmcb; module_param(dump_invalid_vmcb, bool, 0644); @@ -250,6 +253,8 @@ static unsigned long iopm_base; DEFINE_PER_CPU(struct svm_cpu_data, svm_data); +static DEFINE_MUTEX(vmcb_dump_mutex); + /* * Only MSR_TSC_AUX is switched via the user return hook. EFER is switched via * the VMCB, and the SYSCALL/SYSENTER MSRs are handled by VMLOAD/VMSAVE. @@ -1369,6 +1374,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK; } + if (vcpu->kvm->arch.bus_lock_detection_enabled) + svm_set_intercept(svm, INTERCEPT_BUSLOCK); + if (sev_guest(vcpu->kvm)) sev_init_vmcb(svm); @@ -1478,25 +1486,10 @@ out: return err; } -static void svm_clear_current_vmcb(struct vmcb *vmcb) -{ - int i; - - for_each_online_cpu(i) - cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL); -} - static void svm_vcpu_free(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - /* - * The vmcb page can be recycled, causing a false negative in - * svm_vcpu_load(). So, ensure that no logical CPU has this - * vmcb page recorded as its current vmcb. - */ - svm_clear_current_vmcb(svm->vmcb); - svm_leave_nested(vcpu); svm_free_nested(svm); @@ -1610,19 +1603,9 @@ static void svm_prepare_host_switch(struct kvm_vcpu *vcpu) static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - struct vcpu_svm *svm = to_svm(vcpu); - struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm)) shrink_ple_window(vcpu); - if (sd->current_vmcb != svm->vmcb) { - sd->current_vmcb = svm->vmcb; - - if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT) && - static_branch_likely(&switch_vcpu_ibpb)) - indirect_branch_prediction_barrier(); - } if (kvm_vcpu_apicv_active(vcpu)) avic_vcpu_load(vcpu, cpu); } @@ -3221,17 +3204,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) } /* - * AMD changed the architectural behavior of bits 5:2. On CPUs - * without BusLockTrap, bits 5:2 control "external pins", but - * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap - * and bits 5:3 are reserved-to-zero. Sadly, old KVM allowed - * the guest to set bits 5:2 despite not actually virtualizing - * Performance-Monitoring/Breakpoint external pins. Drop bits - * 5:2 for backwards compatibility. - */ - data &= ~GENMASK(5, 2); - - /* * Suppress BTF as KVM doesn't virtualize BTF, but there's no * way to communicate lack of support to the guest. */ @@ -3361,6 +3333,37 @@ static int invpcid_interception(struct kvm_vcpu *vcpu) return kvm_handle_invpcid(vcpu, type, gva); } +static inline int complete_userspace_buslock(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * If userspace has NOT changed RIP, then KVM's ABI is to let the guest + * execute the bus-locking instruction. Set the bus lock counter to '1' + * to effectively step past the bus lock. + */ + if (kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip)) + svm->vmcb->control.bus_lock_counter = 1; + + return 1; +} + +static int bus_lock_exit(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; + vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; + + vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.complete_userspace_io = complete_userspace_buslock; + + if (is_guest_mode(vcpu)) + svm->nested.ctl.bus_lock_rip = vcpu->arch.cui_linear_rip; + + return 0; +} + static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_READ_CR0] = cr_interception, [SVM_EXIT_READ_CR3] = cr_interception, @@ -3430,6 +3433,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_INVPCID] = invpcid_interception, [SVM_EXIT_IDLE_HLT] = kvm_emulate_halt, [SVM_EXIT_NPF] = npf_interception, + [SVM_EXIT_BUS_LOCK] = bus_lock_exit, [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, @@ -3444,14 +3448,21 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; struct vmcb_save_area *save01 = &svm->vmcb01.ptr->save; + char *vm_type; if (!dump_invalid_vmcb) { pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n"); return; } - pr_err("VMCB %p, last attempted VMRUN on CPU %d\n", - svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu); + guard(mutex)(&vmcb_dump_mutex); + + vm_type = sev_snp_guest(vcpu->kvm) ? "SEV-SNP" : + sev_es_guest(vcpu->kvm) ? "SEV-ES" : + sev_guest(vcpu->kvm) ? "SEV" : "SVM"; + + pr_err("%s vCPU%u VMCB %p, last attempted VMRUN on CPU %d\n", + vm_type, vcpu->vcpu_id, svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu); pr_err("VMCB Control Area:\n"); pr_err("%-20s%04x\n", "cr_read:", control->intercepts[INTERCEPT_CR] & 0xffff); pr_err("%-20s%04x\n", "cr_write:", control->intercepts[INTERCEPT_CR] >> 16); @@ -3489,6 +3500,17 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id); pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id); pr_err("%-20s%016llx\n", "vmsa_pa:", control->vmsa_pa); + pr_err("%-20s%016llx\n", "allowed_sev_features:", control->allowed_sev_features); + pr_err("%-20s%016llx\n", "guest_sev_features:", control->guest_sev_features); + + if (sev_es_guest(vcpu->kvm)) { + save = sev_decrypt_vmsa(vcpu); + if (!save) + goto no_vmsa; + + save01 = save; + } + pr_err("VMCB State Save Area:\n"); pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", "es:", @@ -3559,6 +3581,63 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) pr_err("%-15s %016llx %-13s %016llx\n", "excp_from:", save->last_excp_from, "excp_to:", save->last_excp_to); + + if (sev_es_guest(vcpu->kvm)) { + struct sev_es_save_area *vmsa = (struct sev_es_save_area *)save; + + pr_err("%-15s %016llx\n", + "sev_features", vmsa->sev_features); + + pr_err("%-15s %016llx %-13s %016llx\n", + "rax:", vmsa->rax, "rbx:", vmsa->rbx); + pr_err("%-15s %016llx %-13s %016llx\n", + "rcx:", vmsa->rcx, "rdx:", vmsa->rdx); + pr_err("%-15s %016llx %-13s %016llx\n", + "rsi:", vmsa->rsi, "rdi:", vmsa->rdi); + pr_err("%-15s %016llx %-13s %016llx\n", + "rbp:", vmsa->rbp, "rsp:", vmsa->rsp); + pr_err("%-15s %016llx %-13s %016llx\n", + "r8:", vmsa->r8, "r9:", vmsa->r9); + pr_err("%-15s %016llx %-13s %016llx\n", + "r10:", vmsa->r10, "r11:", vmsa->r11); + pr_err("%-15s %016llx %-13s %016llx\n", + "r12:", vmsa->r12, "r13:", vmsa->r13); + pr_err("%-15s %016llx %-13s %016llx\n", + "r14:", vmsa->r14, "r15:", vmsa->r15); + pr_err("%-15s %016llx %-13s %016llx\n", + "xcr0:", vmsa->xcr0, "xss:", vmsa->xss); + } else { + pr_err("%-15s %016llx %-13s %016lx\n", + "rax:", save->rax, "rbx:", + vcpu->arch.regs[VCPU_REGS_RBX]); + pr_err("%-15s %016lx %-13s %016lx\n", + "rcx:", vcpu->arch.regs[VCPU_REGS_RCX], + "rdx:", vcpu->arch.regs[VCPU_REGS_RDX]); + pr_err("%-15s %016lx %-13s %016lx\n", + "rsi:", vcpu->arch.regs[VCPU_REGS_RSI], + "rdi:", vcpu->arch.regs[VCPU_REGS_RDI]); + pr_err("%-15s %016lx %-13s %016llx\n", + "rbp:", vcpu->arch.regs[VCPU_REGS_RBP], + "rsp:", save->rsp); +#ifdef CONFIG_X86_64 + pr_err("%-15s %016lx %-13s %016lx\n", + "r8:", vcpu->arch.regs[VCPU_REGS_R8], + "r9:", vcpu->arch.regs[VCPU_REGS_R9]); + pr_err("%-15s %016lx %-13s %016lx\n", + "r10:", vcpu->arch.regs[VCPU_REGS_R10], + "r11:", vcpu->arch.regs[VCPU_REGS_R11]); + pr_err("%-15s %016lx %-13s %016lx\n", + "r12:", vcpu->arch.regs[VCPU_REGS_R12], + "r13:", vcpu->arch.regs[VCPU_REGS_R13]); + pr_err("%-15s %016lx %-13s %016lx\n", + "r14:", vcpu->arch.regs[VCPU_REGS_R14], + "r15:", vcpu->arch.regs[VCPU_REGS_R15]); +#endif + } + +no_vmsa: + if (sev_es_guest(vcpu->kvm)) + sev_free_decrypted_vmsa(vcpu, save); } static bool svm_check_exit_valid(u64 exit_code) @@ -3595,6 +3674,10 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code) return kvm_emulate_halt(vcpu); else if (exit_code == SVM_EXIT_NPF) return npf_interception(vcpu); +#ifdef CONFIG_KVM_AMD_SEV + else if (exit_code == SVM_EXIT_VMGEXIT) + return sev_handle_vmgexit(vcpu); +#endif #endif return svm_exit_handlers[exit_code](vcpu); } @@ -5356,6 +5439,9 @@ static __init void svm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK); } + if (cpu_feature_enabled(X86_FEATURE_BUS_LOCK_THRESHOLD)) + kvm_caps.has_bus_lock_exit = true; + /* CPUID 0x80000008 */ if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || boot_cpu_has(X86_FEATURE_AMD_SSBD)) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f16b068c4228..e6f3c6a153a0 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -98,6 +98,7 @@ struct kvm_sev_info { unsigned int asid; /* ASID used for this guest */ unsigned int handle; /* SEV firmware handle */ int fd; /* SEV device fd */ + unsigned long policy; unsigned long pages_locked; /* Number of pages locked */ struct list_head regions_list; /* List of registered regions */ u64 ap_jump_table; /* SEV-ES AP Jump Table address */ @@ -114,6 +115,9 @@ struct kvm_sev_info { struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */ }; +#define SEV_POLICY_NODBG BIT_ULL(0) +#define SNP_POLICY_DEBUG BIT_ULL(19) + struct kvm_svm { struct kvm kvm; @@ -169,6 +173,7 @@ struct vmcb_ctrl_area_cached { u64 nested_cr3; u64 virt_ext; u32 clean; + u64 bus_lock_rip; union { #if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV) struct hv_vmcb_enlightenments hv_enlightenments; @@ -340,8 +345,6 @@ struct svm_cpu_data { struct vmcb *save_area; unsigned long save_area_pa; - struct vmcb *current_vmcb; - /* index = sev_asid, value = vmcb pointer */ struct vmcb **sev_vmcbs; }; @@ -785,6 +788,8 @@ void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu); int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn); +struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu); +void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa); #else static inline struct page *snp_safe_alloc_page_node(int node, gfp_t gfp) { @@ -816,6 +821,11 @@ static inline int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) return 0; } +static inline struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu) +{ + return NULL; +} +static inline void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa) {} #endif /* vmenter.S */ diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h index 8f46a06e2c44..a0c5e8781c33 100644 --- a/arch/x86/kvm/vmx/common.h +++ b/arch/x86/kvm/vmx/common.h @@ -71,8 +71,8 @@ static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu) #else -static inline bool is_td(struct kvm *kvm) { return false; } -static inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; } +static __always_inline bool is_td(struct kvm *kvm) { return false; } +static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; } #endif diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 94d5d907d37b..d1e02e567b57 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -12,7 +12,6 @@ #ifdef CONFIG_KVM_INTEL_TDX static_assert(offsetof(struct vcpu_vmx, vt) == offsetof(struct vcpu_tdx, vt)); -#endif static void vt_disable_virtualization_cpu(void) { @@ -240,7 +239,7 @@ static int vt_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) if (is_td_vcpu(vcpu)) return tdx_complete_emulated_msr(vcpu, err); - return kvm_complete_insn_gp(vcpu, err); + return vmx_complete_emulated_msr(vcpu, err); } #ifdef CONFIG_KVM_SMM @@ -315,14 +314,6 @@ static void vt_set_virtual_apic_mode(struct kvm_vcpu *vcpu) return vmx_set_virtual_apic_mode(vcpu); } -static void vt_apicv_pre_state_restore(struct kvm_vcpu *vcpu) -{ - struct pi_desc *pi = vcpu_to_pi_desc(vcpu); - - pi_clear_on(pi); - memset(pi->pir, 0, sizeof(pi->pir)); -} - static void vt_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { if (is_td_vcpu(vcpu)) @@ -888,6 +879,13 @@ static int vt_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) return 0; } +#define vt_op(name) vt_##name +#define vt_op_tdx_only(name) vt_##name +#else /* CONFIG_KVM_INTEL_TDX */ +#define vt_op(name) vmx_##name +#define vt_op_tdx_only(name) NULL +#endif /* CONFIG_KVM_INTEL_TDX */ + #define VMX_REQUIRED_APICV_INHIBITS \ (BIT(APICV_INHIBIT_REASON_DISABLED) | \ BIT(APICV_INHIBIT_REASON_ABSENT) | \ @@ -905,113 +903,113 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .hardware_unsetup = vmx_hardware_unsetup, .enable_virtualization_cpu = vmx_enable_virtualization_cpu, - .disable_virtualization_cpu = vt_disable_virtualization_cpu, + .disable_virtualization_cpu = vt_op(disable_virtualization_cpu), .emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu, - .has_emulated_msr = vt_has_emulated_msr, + .has_emulated_msr = vt_op(has_emulated_msr), .vm_size = sizeof(struct kvm_vmx), - .vm_init = vt_vm_init, - .vm_pre_destroy = vt_vm_pre_destroy, - .vm_destroy = vt_vm_destroy, + .vm_init = vt_op(vm_init), + .vm_destroy = vt_op(vm_destroy), + .vm_pre_destroy = vt_op_tdx_only(vm_pre_destroy), - .vcpu_precreate = vt_vcpu_precreate, - .vcpu_create = vt_vcpu_create, - .vcpu_free = vt_vcpu_free, - .vcpu_reset = vt_vcpu_reset, + .vcpu_precreate = vt_op(vcpu_precreate), + .vcpu_create = vt_op(vcpu_create), + .vcpu_free = vt_op(vcpu_free), + .vcpu_reset = vt_op(vcpu_reset), - .prepare_switch_to_guest = vt_prepare_switch_to_guest, - .vcpu_load = vt_vcpu_load, - .vcpu_put = vt_vcpu_put, + .prepare_switch_to_guest = vt_op(prepare_switch_to_guest), + .vcpu_load = vt_op(vcpu_load), + .vcpu_put = vt_op(vcpu_put), - .update_exception_bitmap = vt_update_exception_bitmap, + .update_exception_bitmap = vt_op(update_exception_bitmap), .get_feature_msr = vmx_get_feature_msr, - .get_msr = vt_get_msr, - .set_msr = vt_set_msr, - - .get_segment_base = vt_get_segment_base, - .get_segment = vt_get_segment, - .set_segment = vt_set_segment, - .get_cpl = vt_get_cpl, - .get_cpl_no_cache = vt_get_cpl_no_cache, - .get_cs_db_l_bits = vt_get_cs_db_l_bits, - .is_valid_cr0 = vt_is_valid_cr0, - .set_cr0 = vt_set_cr0, - .is_valid_cr4 = vt_is_valid_cr4, - .set_cr4 = vt_set_cr4, - .set_efer = vt_set_efer, - .get_idt = vt_get_idt, - .set_idt = vt_set_idt, - .get_gdt = vt_get_gdt, - .set_gdt = vt_set_gdt, - .set_dr6 = vt_set_dr6, - .set_dr7 = vt_set_dr7, - .sync_dirty_debug_regs = vt_sync_dirty_debug_regs, - .cache_reg = vt_cache_reg, - .get_rflags = vt_get_rflags, - .set_rflags = vt_set_rflags, - .get_if_flag = vt_get_if_flag, - - .flush_tlb_all = vt_flush_tlb_all, - .flush_tlb_current = vt_flush_tlb_current, - .flush_tlb_gva = vt_flush_tlb_gva, - .flush_tlb_guest = vt_flush_tlb_guest, - - .vcpu_pre_run = vt_vcpu_pre_run, - .vcpu_run = vt_vcpu_run, - .handle_exit = vt_handle_exit, + .get_msr = vt_op(get_msr), + .set_msr = vt_op(set_msr), + + .get_segment_base = vt_op(get_segment_base), + .get_segment = vt_op(get_segment), + .set_segment = vt_op(set_segment), + .get_cpl = vt_op(get_cpl), + .get_cpl_no_cache = vt_op(get_cpl_no_cache), + .get_cs_db_l_bits = vt_op(get_cs_db_l_bits), + .is_valid_cr0 = vt_op(is_valid_cr0), + .set_cr0 = vt_op(set_cr0), + .is_valid_cr4 = vt_op(is_valid_cr4), + .set_cr4 = vt_op(set_cr4), + .set_efer = vt_op(set_efer), + .get_idt = vt_op(get_idt), + .set_idt = vt_op(set_idt), + .get_gdt = vt_op(get_gdt), + .set_gdt = vt_op(set_gdt), + .set_dr6 = vt_op(set_dr6), + .set_dr7 = vt_op(set_dr7), + .sync_dirty_debug_regs = vt_op(sync_dirty_debug_regs), + .cache_reg = vt_op(cache_reg), + .get_rflags = vt_op(get_rflags), + .set_rflags = vt_op(set_rflags), + .get_if_flag = vt_op(get_if_flag), + + .flush_tlb_all = vt_op(flush_tlb_all), + .flush_tlb_current = vt_op(flush_tlb_current), + .flush_tlb_gva = vt_op(flush_tlb_gva), + .flush_tlb_guest = vt_op(flush_tlb_guest), + + .vcpu_pre_run = vt_op(vcpu_pre_run), + .vcpu_run = vt_op(vcpu_run), + .handle_exit = vt_op(handle_exit), .skip_emulated_instruction = vmx_skip_emulated_instruction, .update_emulated_instruction = vmx_update_emulated_instruction, - .set_interrupt_shadow = vt_set_interrupt_shadow, - .get_interrupt_shadow = vt_get_interrupt_shadow, - .patch_hypercall = vt_patch_hypercall, - .inject_irq = vt_inject_irq, - .inject_nmi = vt_inject_nmi, - .inject_exception = vt_inject_exception, - .cancel_injection = vt_cancel_injection, - .interrupt_allowed = vt_interrupt_allowed, - .nmi_allowed = vt_nmi_allowed, - .get_nmi_mask = vt_get_nmi_mask, - .set_nmi_mask = vt_set_nmi_mask, - .enable_nmi_window = vt_enable_nmi_window, - .enable_irq_window = vt_enable_irq_window, - .update_cr8_intercept = vt_update_cr8_intercept, + .set_interrupt_shadow = vt_op(set_interrupt_shadow), + .get_interrupt_shadow = vt_op(get_interrupt_shadow), + .patch_hypercall = vt_op(patch_hypercall), + .inject_irq = vt_op(inject_irq), + .inject_nmi = vt_op(inject_nmi), + .inject_exception = vt_op(inject_exception), + .cancel_injection = vt_op(cancel_injection), + .interrupt_allowed = vt_op(interrupt_allowed), + .nmi_allowed = vt_op(nmi_allowed), + .get_nmi_mask = vt_op(get_nmi_mask), + .set_nmi_mask = vt_op(set_nmi_mask), + .enable_nmi_window = vt_op(enable_nmi_window), + .enable_irq_window = vt_op(enable_irq_window), + .update_cr8_intercept = vt_op(update_cr8_intercept), .x2apic_icr_is_split = false, - .set_virtual_apic_mode = vt_set_virtual_apic_mode, - .set_apic_access_page_addr = vt_set_apic_access_page_addr, - .refresh_apicv_exec_ctrl = vt_refresh_apicv_exec_ctrl, - .load_eoi_exitmap = vt_load_eoi_exitmap, - .apicv_pre_state_restore = vt_apicv_pre_state_restore, + .set_virtual_apic_mode = vt_op(set_virtual_apic_mode), + .set_apic_access_page_addr = vt_op(set_apic_access_page_addr), + .refresh_apicv_exec_ctrl = vt_op(refresh_apicv_exec_ctrl), + .load_eoi_exitmap = vt_op(load_eoi_exitmap), + .apicv_pre_state_restore = pi_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, - .hwapic_isr_update = vt_hwapic_isr_update, - .sync_pir_to_irr = vt_sync_pir_to_irr, - .deliver_interrupt = vt_deliver_interrupt, + .hwapic_isr_update = vt_op(hwapic_isr_update), + .sync_pir_to_irr = vt_op(sync_pir_to_irr), + .deliver_interrupt = vt_op(deliver_interrupt), .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, - .set_tss_addr = vt_set_tss_addr, - .set_identity_map_addr = vt_set_identity_map_addr, + .set_tss_addr = vt_op(set_tss_addr), + .set_identity_map_addr = vt_op(set_identity_map_addr), .get_mt_mask = vmx_get_mt_mask, - .get_exit_info = vt_get_exit_info, - .get_entry_info = vt_get_entry_info, + .get_exit_info = vt_op(get_exit_info), + .get_entry_info = vt_op(get_entry_info), - .vcpu_after_set_cpuid = vt_vcpu_after_set_cpuid, + .vcpu_after_set_cpuid = vt_op(vcpu_after_set_cpuid), .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .get_l2_tsc_offset = vt_get_l2_tsc_offset, - .get_l2_tsc_multiplier = vt_get_l2_tsc_multiplier, - .write_tsc_offset = vt_write_tsc_offset, - .write_tsc_multiplier = vt_write_tsc_multiplier, + .get_l2_tsc_offset = vt_op(get_l2_tsc_offset), + .get_l2_tsc_multiplier = vt_op(get_l2_tsc_multiplier), + .write_tsc_offset = vt_op(write_tsc_offset), + .write_tsc_multiplier = vt_op(write_tsc_multiplier), - .load_mmu_pgd = vt_load_mmu_pgd, + .load_mmu_pgd = vt_op(load_mmu_pgd), .check_intercept = vmx_check_intercept, .handle_exit_irqoff = vmx_handle_exit_irqoff, - .update_cpu_dirty_logging = vt_update_cpu_dirty_logging, + .update_cpu_dirty_logging = vt_op(update_cpu_dirty_logging), .nested_ops = &vmx_nested_ops, @@ -1019,38 +1017,38 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .pi_start_assignment = vmx_pi_start_assignment, #ifdef CONFIG_X86_64 - .set_hv_timer = vt_set_hv_timer, - .cancel_hv_timer = vt_cancel_hv_timer, + .set_hv_timer = vt_op(set_hv_timer), + .cancel_hv_timer = vt_op(cancel_hv_timer), #endif - .setup_mce = vt_setup_mce, + .setup_mce = vt_op(setup_mce), #ifdef CONFIG_KVM_SMM - .smi_allowed = vt_smi_allowed, - .enter_smm = vt_enter_smm, - .leave_smm = vt_leave_smm, - .enable_smi_window = vt_enable_smi_window, + .smi_allowed = vt_op(smi_allowed), + .enter_smm = vt_op(enter_smm), + .leave_smm = vt_op(leave_smm), + .enable_smi_window = vt_op(enable_smi_window), #endif - .check_emulate_instruction = vt_check_emulate_instruction, - .apic_init_signal_blocked = vt_apic_init_signal_blocked, + .check_emulate_instruction = vt_op(check_emulate_instruction), + .apic_init_signal_blocked = vt_op(apic_init_signal_blocked), .migrate_timers = vmx_migrate_timers, - .msr_filter_changed = vt_msr_filter_changed, - .complete_emulated_msr = vt_complete_emulated_msr, + .msr_filter_changed = vt_op(msr_filter_changed), + .complete_emulated_msr = vt_op(complete_emulated_msr), .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, .get_untagged_addr = vmx_get_untagged_addr, - .mem_enc_ioctl = vt_mem_enc_ioctl, - .vcpu_mem_enc_ioctl = vt_vcpu_mem_enc_ioctl, + .mem_enc_ioctl = vt_op_tdx_only(mem_enc_ioctl), + .vcpu_mem_enc_ioctl = vt_op_tdx_only(vcpu_mem_enc_ioctl), - .private_max_mapping_level = vt_gmem_private_max_mapping_level + .private_max_mapping_level = vt_op_tdx_only(gmem_private_max_mapping_level) }; struct kvm_x86_init_ops vt_init_ops __initdata = { - .hardware_setup = vt_hardware_setup, + .hardware_setup = vt_op(hardware_setup), .handle_intel_pt_intr = NULL, .runtime_ops = &vt_x86_ops, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 71701e2414a4..7211c71d4241 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -302,7 +302,7 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) cpu = get_cpu(); prev = vmx->loaded_vmcs; vmx->loaded_vmcs = vmcs; - vmx_vcpu_load_vmcs(vcpu, cpu, prev); + vmx_vcpu_load_vmcs(vcpu, cpu); vmx_sync_vmcs_host_state(vmx, prev); put_cpu(); @@ -825,12 +825,30 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, return 0; } +static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low, + vmx->nested.msrs.misc_high); + + return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER; +} + static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, u32 count, u64 addr) { if (count == 0) return 0; + /* + * Exceeding the limit results in architecturally _undefined_ behavior, + * i.e. KVM is allowed to do literally anything in response to a bad + * limit. Immediately generate a consistency check so that code that + * consumes the count doesn't need to worry about extreme edge cases. + */ + if (count > nested_vmx_max_atomic_switch_msrs(vcpu)) + return -EINVAL; + if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) || !kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1))) return -EINVAL; @@ -941,15 +959,6 @@ static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu, return 0; } -static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low, - vmx->nested.msrs.misc_high); - - return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER; -} - /* * Load guest's/host's msr at nested entry/exit. * return 0 for success, entry index for failure. @@ -966,7 +975,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); for (i = 0; i < count; i++) { - if (unlikely(i >= max_msr_list_size)) + if (WARN_ON_ONCE(i >= max_msr_list_size)) goto fail; if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), @@ -1054,7 +1063,7 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu); for (i = 0; i < count; i++) { - if (unlikely(i >= max_msr_list_size)) + if (WARN_ON_ONCE(i >= max_msr_list_size)) return -EINVAL; if (!read_and_check_msr_entry(vcpu, gpa, i, &e)) @@ -4521,12 +4530,12 @@ static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, cpu = get_cpu(); vmx->loaded_vmcs = &vmx->nested.vmcs02; - vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01); + vmx_vcpu_load_vmcs(vcpu, cpu); sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); vmx->loaded_vmcs = &vmx->vmcs01; - vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02); + vmx_vcpu_load_vmcs(vcpu, cpu); put_cpu(); } @@ -5021,16 +5030,7 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmx_switch_vmcs(vcpu, &vmx->vmcs01); - /* - * If IBRS is advertised to the vCPU, KVM must flush the indirect - * branch predictors when transitioning from L2 to L1, as L1 expects - * hardware (KVM in this case) to provide separate predictor modes. - * Bare metal isolates VMX root (host) from VMX non-root (guest), but - * doesn't isolate different VMCSs, i.e. in this case, doesn't provide - * separate modes for L2 vs L1. - */ - if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL)) - indirect_branch_prediction_barrier(); + kvm_nested_vmexit_handle_ibrs(vcpu); /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 99d1d599ff8c..5c615e5845bf 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -34,7 +34,7 @@ static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock); #define PI_LOCK_SCHED_OUT SINGLE_DEPTH_NESTING -struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) +static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) { return &(to_vt(vcpu)->pi_desc); } @@ -148,9 +148,8 @@ after_clear_sn: static bool vmx_can_use_vtd_pi(struct kvm *kvm) { - return irqchip_in_kernel(kvm) && enable_apicv && - kvm_arch_has_assigned_device(kvm) && - irq_remapping_cap(IRQ_POSTING_CAP); + return irqchip_in_kernel(kvm) && kvm_arch_has_irq_bypass() && + kvm_arch_has_assigned_device(kvm); } /* @@ -264,6 +263,14 @@ void __init pi_init_cpu(int cpu) raw_spin_lock_init(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu)); } +void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi = vcpu_to_pi_desc(vcpu); + + pi_clear_on(pi); + memset(pi->pir, 0, sizeof(pi->pir)); +} + bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -281,7 +288,7 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) */ void vmx_pi_start_assignment(struct kvm *kvm) { - if (!irq_remapping_cap(IRQ_POSTING_CAP)) + if (!kvm_arch_has_irq_bypass()) return; kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK); diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 68605ca7ef68..80499ea0e674 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -5,12 +5,11 @@ #include <linux/bitmap.h> #include <asm/posted_intr.h> -struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu); - void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu); void pi_wakeup_handler(void); void __init pi_init_cpu(int cpu); +void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu); bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu); int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); @@ -20,7 +19,7 @@ static inline int pi_find_highest_vector(struct pi_desc *pi_desc) { int vec; - vec = find_last_bit((unsigned long *)pi_desc->pir, 256); + vec = find_last_bit(pi_desc->pir, 256); return vec < 256 ? vec : -1; } diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index f6986dee6f8c..0a6cf5bff2aa 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -59,8 +59,7 @@ * without the explicit restore, thinks the stack is getting walloped. * Using an unwind hint is problematic due to x86-64's dynamic alignment. */ - mov %_ASM_BP, %_ASM_SP - pop %_ASM_BP + leave RET .endm diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index b12414108cbf..4953846cb30d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -117,6 +117,8 @@ module_param(enable_apicv, bool, 0444); bool __read_mostly enable_ipiv = true; module_param(enable_ipiv, bool, 0444); +module_param(enable_device_posted_irqs, bool, 0444); + /* * If nested=1, nested virtualization is supported, i.e., guests may use * VMX and be a hypervisor for its own guests. If nested=0, guests may not @@ -772,8 +774,11 @@ 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(); } @@ -1445,8 +1450,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) } } -void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, - struct loaded_vmcs *buddy) +void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool already_loaded = vmx->loaded_vmcs->cpu == cpu; @@ -1473,17 +1477,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, if (prev != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); - - /* - * No indirect branch prediction barrier needed when switching - * the active VMCS within a vCPU, unless IBRS is advertised to - * the vCPU. To minimize the number of IBPBs executed, KVM - * performs IBPB on nested VM-Exit (a single nested transition - * may switch the active VMCS multiple times). - */ - if (static_branch_likely(&switch_vcpu_ibpb) && - (!buddy || WARN_ON_ONCE(buddy->vmcs != prev))) - indirect_branch_prediction_barrier(); } if (!already_loaded) { @@ -1522,7 +1515,7 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm)) shrink_ple_window(vcpu); - vmx_vcpu_load_vmcs(vcpu, cpu, NULL); + vmx_vcpu_load_vmcs(vcpu, cpu); vmx_vcpu_pi_load(vcpu, cpu); } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 6d1e40ecc024..b5758c33c60f 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -354,8 +354,7 @@ static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) return vt->exit_intr_info; } -void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, - struct loaded_vmcs *buddy); +void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu); int allocate_vpid(void); void free_vpid(int vpid); void vmx_set_constant_host_state(struct vcpu_vmx *vmx); diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 6bf8be570b2e..b4596f651232 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -57,6 +57,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); int vmx_get_feature_msr(u32 msr, u64 *data); int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +#define vmx_complete_emulated_msr kvm_complete_insn_gp u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg); void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -163,71 +164,6 @@ void tdx_flush_tlb_current(struct kvm_vcpu *vcpu); void tdx_flush_tlb_all(struct kvm_vcpu *vcpu); void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn); -#else -static inline void tdx_disable_virtualization_cpu(void) {} -static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; } -static inline void tdx_mmu_release_hkid(struct kvm *kvm) {} -static inline void tdx_vm_destroy(struct kvm *kvm) {} -static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; } - -static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; } -static inline void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) {} -static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {} -static inline void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) {} -static inline int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; } -static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) -{ - return EXIT_FASTPATH_NONE; -} -static inline void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) {} -static inline void tdx_vcpu_put(struct kvm_vcpu *vcpu) {} -static inline bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) { return false; } -static inline int tdx_handle_exit(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion fastpath) { return 0; } - -static inline void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, - int trig_mode, int vector) {} -static inline void tdx_inject_nmi(struct kvm_vcpu *vcpu) {} -static inline void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, - u64 *info2, u32 *intr_info, u32 *error_code) {} -static inline bool tdx_has_emulated_msr(u32 index) { return false; } -static inline int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; } -static inline int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; } - -static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; } - -static inline int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, - enum pg_level level, - void *private_spt) -{ - return -EOPNOTSUPP; -} - -static inline int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, - enum pg_level level, - void *private_spt) -{ - return -EOPNOTSUPP; -} - -static inline int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, - kvm_pfn_t pfn) -{ - return -EOPNOTSUPP; -} - -static inline int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, - kvm_pfn_t pfn) -{ - return -EOPNOTSUPP; -} - -static inline void tdx_flush_tlb_current(struct kvm_vcpu *vcpu) {} -static inline void tdx_flush_tlb_all(struct kvm_vcpu *vcpu) {} -static inline void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) {} -static inline int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) { return 0; } #endif #endif /* __KVM_X86_VMX_X86_OPS_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 570e7f8cbf64..b58a74c1722d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -226,6 +226,9 @@ EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); bool __read_mostly enable_apicv = true; EXPORT_SYMBOL_GPL(enable_apicv); +bool __read_mostly enable_device_posted_irqs = true; +EXPORT_SYMBOL_GPL(enable_device_posted_irqs); + const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, mmu_shadow_zapped), @@ -4990,6 +4993,8 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) return kvm_arch_has_noncoherent_dma(vcpu->kvm); } +static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu); + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -5012,6 +5017,19 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_call(vcpu_load)(vcpu, cpu); + if (vcpu != per_cpu(last_vcpu, cpu)) { + /* + * Flush the branch predictor when switching vCPUs on the same + * physical CPU, as each vCPU needs its own branch prediction + * domain. No IBPB is needed when switching between L1 and L2 + * on the same vCPU unless IBRS is advertised to the vCPU; that + * is handled on the nested VM-Exit path. + */ + if (static_branch_likely(&switch_vcpu_ibpb)) + indirect_branch_prediction_barrier(); + per_cpu(last_vcpu, cpu) = vcpu; + } + /* Save host pkru register if supported */ vcpu->arch.host_pkru = read_pkru(); @@ -7326,10 +7344,13 @@ set_pit2_out: r = READ_ONCE(kvm->arch.default_tsc_khz); goto out; } - case KVM_MEMORY_ENCRYPT_OP: { + case KVM_MEMORY_ENCRYPT_OP: + r = -ENOTTY; + if (!kvm_x86_ops.mem_enc_ioctl) + goto out; + r = kvm_x86_call(mem_enc_ioctl)(kvm, argp); break; - } case KVM_MEMORY_ENCRYPT_REG_REGION: { struct kvm_enc_region region; @@ -8023,7 +8044,7 @@ static int emulator_read_write(struct x86_emulate_ctxt *ctxt, return rc; if (!vcpu->mmio_nr_fragments) - return rc; + return X86EMUL_CONTINUE; gpa = vcpu->mmio_fragments[0].gpa; @@ -9361,7 +9382,7 @@ static int complete_fast_pio_out(struct kvm_vcpu *vcpu) { vcpu->arch.pio.count = 0; - if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) return 1; return kvm_skip_emulated_instruction(vcpu); @@ -9386,7 +9407,7 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, complete_fast_pio_out_port_0x7e; kvm_skip_emulated_instruction(vcpu); } else { - vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_out; } return 0; @@ -9399,7 +9420,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) /* We should only ever be called with arch.pio.count equal to 1 */ BUG_ON(vcpu->arch.pio.count != 1); - if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) { + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) { vcpu->arch.pio.count = 0; return 1; } @@ -9428,7 +9449,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, return ret; } - vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_in; return 0; @@ -9811,6 +9832,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) if (r != 0) goto out_mmu_exit; + enable_device_posted_irqs &= enable_apicv && + irq_remapping_cap(IRQ_POSTING_CAP); + kvm_ops_update(ops); for_each_online_cpu(cpu) { @@ -10694,6 +10718,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) return; bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); + vcpu->arch.highest_stale_pending_ioapic_eoi = -1; kvm_x86_call(sync_pir_to_irr)(vcpu); @@ -12419,13 +12444,16 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - int idx; + int idx, cpu; kvm_clear_async_pf_completion_queue(vcpu); kvm_mmu_unload(vcpu); kvmclock_reset(vcpu); + for_each_possible_cpu(cpu) + cmpxchg(per_cpu_ptr(&last_vcpu, cpu), vcpu, NULL); + kvm_x86_call(vcpu_free)(vcpu); kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 88a9475899c8..832f0faf4779 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -121,6 +121,24 @@ static inline void kvm_leave_nested(struct kvm_vcpu *vcpu) kvm_x86_ops.nested_ops->leave_nested(vcpu); } +/* + * If IBRS is advertised to the vCPU, KVM must flush the indirect branch + * predictors when transitioning from L2 to L1, as L1 expects hardware (KVM in + * this case) to provide separate predictor modes. Bare metal isolates the host + * from the guest, but doesn't isolate different guests from one another (in + * this case L1 and L2). The exception is if bare metal supports same mode IBRS, + * which offers protection within the same mode, and hence protects L1 from L2. + */ +static inline void kvm_nested_vmexit_handle_ibrs(struct kvm_vcpu *vcpu) +{ + if (cpu_feature_enabled(X86_FEATURE_AMD_IBRS_SAME_MODE)) + return; + + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBRS)) + indirect_branch_prediction_barrier(); +} + static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu) { return vcpu->arch.last_vmentry_cpu != -1; diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 89079ea73e65..a4700ef6eb64 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -266,6 +266,32 @@ static void effective_prot(struct ptdump_state *pt_st, int level, u64 val) st->prot_levels[level] = effective; } +static void effective_prot_pte(struct ptdump_state *st, pte_t pte) +{ + effective_prot(st, 4, pte_val(pte)); +} + +static void effective_prot_pmd(struct ptdump_state *st, pmd_t pmd) +{ + effective_prot(st, 3, pmd_val(pmd)); +} + +static void effective_prot_pud(struct ptdump_state *st, pud_t pud) +{ + effective_prot(st, 2, pud_val(pud)); +} + +static void effective_prot_p4d(struct ptdump_state *st, p4d_t p4d) +{ + effective_prot(st, 1, p4d_val(p4d)); +} + +static void effective_prot_pgd(struct ptdump_state *st, pgd_t pgd) +{ + effective_prot(st, 0, pgd_val(pgd)); +} + + /* * This function gets called on a break in a continuous series * of PTE entries; the next one is different so we need to @@ -362,6 +388,38 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, } } +static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte) +{ + note_page(pt_st, addr, 4, pte_val(pte)); +} + +static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd) +{ + note_page(pt_st, addr, 3, pmd_val(pmd)); +} + +static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud) +{ + note_page(pt_st, addr, 2, pud_val(pud)); +} + +static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d) +{ + note_page(pt_st, addr, 1, p4d_val(p4d)); +} + +static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd) +{ + note_page(pt_st, addr, 0, pgd_val(pgd)); +} + +static void note_page_flush(struct ptdump_state *pt_st) +{ + pte_t pte_zero = {0}; + + note_page(pt_st, 0, -1, pte_val(pte_zero)); +} + bool ptdump_walk_pgd_level_core(struct seq_file *m, struct mm_struct *mm, pgd_t *pgd, bool checkwx, bool dmesg) @@ -378,8 +436,17 @@ bool ptdump_walk_pgd_level_core(struct seq_file *m, struct pg_state st = { .ptdump = { - .note_page = note_page, - .effective_prot = effective_prot, + .note_page_pte = note_page_pte, + .note_page_pmd = note_page_pmd, + .note_page_pud = note_page_pud, + .note_page_p4d = note_page_p4d, + .note_page_pgd = note_page_pgd, + .note_page_flush = note_page_flush, + .effective_prot_pte = effective_prot_pte, + .effective_prot_pmd = effective_prot_pmd, + .effective_prot_pud = effective_prot_pud, + .effective_prot_p4d = effective_prot_p4d, + .effective_prot_pgd = effective_prot_pgd, .range = ptdump_ranges }, .level = -1, diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 66330fe4e18c..ee66fae9ebcc 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1467,16 +1467,21 @@ static unsigned long probe_memory_block_size(void) } /* - * Use max block size to minimize overhead on bare metal, where - * alignment for memory hotplug isn't a concern. + * When hotplug alignment is not a concern, maximize blocksize + * to minimize overhead. Otherwise, align to the lesser of advice + * alignment and end of memory alignment. */ - if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + bz = memory_block_advised_max_size(); + if (!bz) { bz = MAX_BLOCK_SIZE; - goto done; + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + goto done; + } else { + bz = max(min(bz, MAX_BLOCK_SIZE), MIN_MEMORY_BLOCK_SIZE); } /* Find the largest allowed block size that aligns to memory end */ - for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) { + for (; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) { if (IS_ALIGNED(boot_mem_end, bz)) break; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 331e101bf801..12c8180ca1ba 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -71,7 +71,7 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, static unsigned int __ioremap_check_ram(struct resource *res) { unsigned long start_pfn, stop_pfn; - unsigned long i; + unsigned long pfn; if ((res->flags & IORESOURCE_SYSTEM_RAM) != IORESOURCE_SYSTEM_RAM) return 0; @@ -79,9 +79,8 @@ static unsigned int __ioremap_check_ram(struct resource *res) start_pfn = (res->start + PAGE_SIZE - 1) >> PAGE_SHIFT; stop_pfn = (res->end + 1) >> PAGE_SHIFT; if (stop_pfn > start_pfn) { - for (i = 0; i < (stop_pfn - start_pfn); ++i) - if (pfn_valid(start_pfn + i) && - !PageReserved(pfn_to_page(start_pfn + i))) + for_each_valid_pfn(pfn, start_pfn, stop_pfn) + if (!PageReserved(pfn_to_page(pfn))) return IORES_MAP_SYSTEM_RAM; } diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index c97b527c66fe..2e7923844afe 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -775,6 +775,12 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, return vma_prot; } +static inline void pgprot_set_cachemode(pgprot_t *prot, enum page_cache_mode pcm) +{ + *prot = __pgprot((pgprot_val(*prot) & ~_PAGE_CACHE_MASK) | + cachemode2protval(pcm)); +} + int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { @@ -789,8 +795,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, if (file->f_flags & O_DSYNC) pcm = _PAGE_CACHE_MODE_UC_MINUS; - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | - cachemode2protval(pcm)); + pgprot_set_cachemode(vma_prot, pcm); return 1; } @@ -831,8 +836,7 @@ int memtype_kernel_map_sync(u64 base, unsigned long size, * Reserved non RAM regions only and after successful memtype_reserve, * this func also keeps identity mapping (if any) in sync with this new prot. */ -static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, - int strict_prot) +static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot) { int is_ram = 0; int ret; @@ -858,9 +862,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, (unsigned long long)paddr, (unsigned long long)(paddr + size - 1), cattr_name(pcm)); - *vma_prot = __pgprot((pgprot_val(*vma_prot) & - (~_PAGE_CACHE_MASK)) | - cachemode2protval(pcm)); + pgprot_set_cachemode(vma_prot, pcm); } return 0; } @@ -870,8 +872,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, return ret; if (pcm != want_pcm) { - if (strict_prot || - !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) { + if (!is_new_memtype_allowed(paddr, size, want_pcm, pcm)) { memtype_free(paddr, paddr + size); pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n", current->comm, current->pid, @@ -881,13 +882,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, cattr_name(pcm)); return -EINVAL; } - /* - * We allow returning different type than the one requested in - * non strict case. - */ - *vma_prot = __pgprot((pgprot_val(*vma_prot) & - (~_PAGE_CACHE_MASK)) | - cachemode2protval(pcm)); + pgprot_set_cachemode(vma_prot, pcm); } if (memtype_kernel_map_sync(paddr, size, pcm) < 0) { @@ -910,124 +905,14 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } -static int follow_phys(struct vm_area_struct *vma, unsigned long *prot, - resource_size_t *phys) -{ - struct follow_pfnmap_args args = { .vma = vma, .address = vma->vm_start }; - - if (follow_pfnmap_start(&args)) - return -EINVAL; - - /* Never return PFNs of anon folios in COW mappings. */ - if (!args.special) { - follow_pfnmap_end(&args); - return -EINVAL; - } - - *prot = pgprot_val(args.pgprot); - *phys = (resource_size_t)args.pfn << PAGE_SHIFT; - follow_pfnmap_end(&args); - return 0; -} - -static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, - pgprot_t *pgprot) -{ - unsigned long prot; - - VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); - - /* - * We need the starting PFN and cachemode used for track_pfn_remap() - * that covered the whole VMA. For most mappings, we can obtain that - * information from the page tables. For COW mappings, we might now - * suddenly have anon folios mapped and follow_phys() will fail. - * - * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to - * detect the PFN. If we need the cachemode as well, we're out of luck - * for now and have to fail fork(). - */ - if (!follow_phys(vma, &prot, paddr)) { - if (pgprot) - *pgprot = __pgprot(prot); - return 0; - } - if (is_cow_mapping(vma->vm_flags)) { - if (pgprot) - return -EINVAL; - *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; - return 0; - } - WARN_ON_ONCE(1); - return -EINVAL; -} - -int track_pfn_copy(struct vm_area_struct *dst_vma, - struct vm_area_struct *src_vma, unsigned long *pfn) -{ - const unsigned long vma_size = src_vma->vm_end - src_vma->vm_start; - resource_size_t paddr; - pgprot_t pgprot; - int rc; - - if (!(src_vma->vm_flags & VM_PAT)) - return 0; - - /* - * Duplicate the PAT information for the dst VMA based on the src - * VMA. - */ - if (get_pat_info(src_vma, &paddr, &pgprot)) - return -EINVAL; - rc = reserve_pfn_range(paddr, vma_size, &pgprot, 1); - if (rc) - return rc; - - /* Reservation for the destination VMA succeeded. */ - vm_flags_set(dst_vma, VM_PAT); - *pfn = PHYS_PFN(paddr); - return 0; -} - -void untrack_pfn_copy(struct vm_area_struct *dst_vma, unsigned long pfn) -{ - untrack_pfn(dst_vma, pfn, dst_vma->vm_end - dst_vma->vm_start, true); - /* - * Reservation was freed, any copied page tables will get cleaned - * up later, but without getting PAT involved again. - */ -} - -/* - * prot is passed in as a parameter for the new mapping. If the vma has - * a linear pfn mapping for the entire range, or no vma is provided, - * reserve the entire pfn + size range with single reserve_pfn_range - * call. - */ -int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn, unsigned long addr, unsigned long size) +int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size, pgprot_t *prot) { resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT; enum page_cache_mode pcm; - /* reserve the whole chunk starting from paddr */ - if (!vma || (addr == vma->vm_start - && size == (vma->vm_end - vma->vm_start))) { - int ret; - - ret = reserve_pfn_range(paddr, size, prot, 0); - if (ret == 0 && vma) - vm_flags_set(vma, VM_PAT); - return ret; - } - if (!pat_enabled()) return 0; - /* - * For anything smaller than the vma size we set prot based on the - * lookup. - */ pcm = lookup_memtype(paddr); /* Check memtype for the remaining pages */ @@ -1038,70 +923,35 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, return -EINVAL; } - *prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) | - cachemode2protval(pcm)); - + pgprot_set_cachemode(prot, pcm); return 0; } -void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn) +int pfnmap_track(unsigned long pfn, unsigned long size, pgprot_t *prot) { - enum page_cache_mode pcm; + const resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT; - if (!pat_enabled()) - return; - - /* Set prot based on lookup */ - pcm = lookup_memtype(pfn_t_to_phys(pfn)); - *prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) | - cachemode2protval(pcm)); + return reserve_pfn_range(paddr, size, prot); } -/* - * untrack_pfn is called while unmapping a pfnmap for a region. - * untrack can be called for a specific region indicated by pfn and size or - * can be for the entire vma (in which case pfn, size are zero). - */ -void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, - unsigned long size, bool mm_wr_locked) +void pfnmap_untrack(unsigned long pfn, unsigned long size) { - resource_size_t paddr; - - if (vma && !(vma->vm_flags & VM_PAT)) - return; + const resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT; - /* free the chunk starting from pfn or the whole chunk */ - paddr = (resource_size_t)pfn << PAGE_SHIFT; - if (!paddr && !size) { - if (get_pat_info(vma, &paddr, NULL)) - return; - size = vma->vm_end - vma->vm_start; - } free_pfn_range(paddr, size); - if (vma) { - if (mm_wr_locked) - vm_flags_clear(vma, VM_PAT); - else - __vm_flags_mod(vma, 0, VM_PAT); - } -} - -void untrack_pfn_clear(struct vm_area_struct *vma) -{ - vm_flags_clear(vma, VM_PAT); } pgprot_t pgprot_writecombine(pgprot_t prot) { - return __pgprot(pgprot_val(prot) | - cachemode2protval(_PAGE_CACHE_MODE_WC)); + pgprot_set_cachemode(&prot, _PAGE_CACHE_MODE_WC); + return prot; } EXPORT_SYMBOL_GPL(pgprot_writecombine); pgprot_t pgprot_writethrough(pgprot_t prot) { - return __pgprot(pgprot_val(prot) | - cachemode2protval(_PAGE_CACHE_MODE_WT)); + pgprot_set_cachemode(&prot, _PAGE_CACHE_MODE_WT); + return prot; } EXPORT_SYMBOL_GPL(pgprot_writethrough); diff --git a/arch/x86/mm/pat/memtype_interval.c b/arch/x86/mm/pat/memtype_interval.c index 645613d59942..e5844ed1311e 100644 --- a/arch/x86/mm/pat/memtype_interval.c +++ b/arch/x86/mm/pat/memtype_interval.c @@ -49,32 +49,6 @@ INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end, static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED; -enum { - MEMTYPE_EXACT_MATCH = 0, - MEMTYPE_END_MATCH = 1 -}; - -static struct memtype *memtype_match(u64 start, u64 end, int match_type) -{ - struct memtype *entry_match; - - entry_match = interval_iter_first(&memtype_rbroot, start, end-1); - - while (entry_match != NULL && entry_match->start < end) { - if ((match_type == MEMTYPE_EXACT_MATCH) && - (entry_match->start == start) && (entry_match->end == end)) - return entry_match; - - if ((match_type == MEMTYPE_END_MATCH) && - (entry_match->start < start) && (entry_match->end == end)) - return entry_match; - - entry_match = interval_iter_next(entry_match, start, end-1); - } - - return NULL; /* Returns NULL if there is no match */ -} - static int memtype_check_conflict(u64 start, u64 end, enum page_cache_mode reqtype, enum page_cache_mode *newtype) @@ -130,35 +104,16 @@ int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *ret_ty struct memtype *memtype_erase(u64 start, u64 end) { - struct memtype *entry_old; - - /* - * Since the memtype_rbroot tree allows overlapping ranges, - * memtype_erase() checks with EXACT_MATCH first, i.e. free - * a whole node for the munmap case. If no such entry is found, - * it then checks with END_MATCH, i.e. shrink the size of a node - * from the end for the mremap case. - */ - entry_old = memtype_match(start, end, MEMTYPE_EXACT_MATCH); - if (!entry_old) { - entry_old = memtype_match(start, end, MEMTYPE_END_MATCH); - if (!entry_old) - return ERR_PTR(-EINVAL); + struct memtype *entry = interval_iter_first(&memtype_rbroot, start, end - 1); + + while (entry && entry->start < end) { + if (entry->start == start && entry->end == end) { + interval_remove(entry, &memtype_rbroot); + return entry; + } + entry = interval_iter_next(entry, start, end - 1); } - - if (entry_old->start == start) { - /* munmap: erase this node */ - interval_remove(entry_old, &memtype_rbroot); - } else { - /* mremap: update the end value of this node */ - interval_remove(entry_old, &memtype_rbroot); - entry_old->end = start; - interval_insert(entry_old, &memtype_rbroot); - - return NULL; - } - - return entry_old; + return ERR_PTR(-EINVAL); } struct memtype *memtype_lookup(u64 addr) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 30ab4aced761..46edc11726b7 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -2148,6 +2148,19 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages, CPA_PAGES_ARRAY, pages); } +/* + * __set_memory_prot is an internal helper for callers that have been passed + * a pgprot_t value from upper layers and a reservation has already been taken. + * If you want to set the pgprot to a specific page protocol, use the + * set_memory_xx() functions. + */ +int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot) +{ + return change_page_attr_set_clr(&addr, numpages, prot, + __pgprot(~pgprot_val(prot)), 0, 0, + NULL); +} + int _set_memory_uc(unsigned long addr, int numpages) { /* diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 62777ba4de1a..ddf248c3ee7d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -189,7 +189,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) if (!ptdesc) failed = true; - if (ptdesc && !pagetable_pmd_ctor(ptdesc)) { + if (ptdesc && !pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); ptdesc = NULL; failed = true; @@ -751,14 +751,13 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) for (i = 0; i < PTRS_PER_PMD; i++) { if (!pmd_none(pmd_sv[i])) { pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]); - free_page((unsigned long)pte); + pte_free_kernel(&init_mm, pte); } } free_page((unsigned long)pmd_sv); - pagetable_dtor(virt_to_ptdesc(pmd)); - free_page((unsigned long)pmd); + pmd_free(&init_mm, pmd); return 1; } @@ -781,7 +780,7 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); - free_page((unsigned long)pte); + pte_free_kernel(&init_mm, pte); return 1; } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index ed5c63c0b4e5..88be32026768 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -66,6 +66,8 @@ void __init reserve_real_mode(void) * setup_arch(). */ memblock_reserve(0, SZ_1M); + + memblock_clear_kho_scratch(0, SZ_1M); } static void __init sme_sev_setup_real_mode(struct trampoline_header *th) |