diff options
Diffstat (limited to 'arch/x86/kvm')
29 files changed, 1154 insertions, 788 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 65ed14b654..0ebdd088f2 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -7,7 +7,6 @@ source "virt/kvm/Kconfig" menuconfig VIRTUALIZATION bool "Virtualization" - depends on HAVE_KVM || X86 default y help Say Y here to get to see options for using your Linux host to run other @@ -20,7 +19,6 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support" - depends on HAVE_KVM depends on HIGH_RES_TIMERS depends on X86_LOCAL_APIC select KVM_COMMON @@ -29,9 +27,9 @@ config KVM select HAVE_KVM_PFNCACHE select HAVE_KVM_DIRTY_RING_TSO select HAVE_KVM_DIRTY_RING_ACQ_REL - select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING + select HAVE_KVM_READONLY_MEM select KVM_ASYNC_PF select USER_RETURN_NOTIFIER select KVM_MMIO @@ -120,10 +118,11 @@ config KVM_AMD will be called kvm-amd. config KVM_AMD_SEV - def_bool y bool "AMD Secure Encrypted Virtualization (SEV) support" + default y depends on KVM_AMD && X86_64 depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) + select ARCH_HAS_CC_PLATFORM help Provides support for launching Encrypted VMs (SEV) and Encrypted VMs with Encrypted State (SEV-ES) on AMD processors. diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 475b5fa917..addc44fc71 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -3,10 +3,6 @@ ccflags-y += -I $(srctree)/arch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror -ifeq ($(CONFIG_FRAME_POINTER),y) -OBJECT_FILES_NON_STANDARD_vmenter.o := y -endif - include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 3a02276899..b1002b7988 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -189,15 +189,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 return 0; } -static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, - const char *sig) +static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_entry2 *entries, + int nent, const char *sig) { struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; u32 base; for_each_possible_hypervisor_cpuid_base(base) { - entry = kvm_find_cpuid_entry(vcpu, base); + entry = cpuid_entry2_find(entries, nent, base, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (entry) { u32 signature[3]; @@ -217,22 +217,29 @@ static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcp return cpuid; } -static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu, - struct kvm_cpuid_entry2 *entries, int nent) +static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, + const char *sig) { - u32 base = vcpu->arch.kvm_cpuid.base; - - if (!base) - return NULL; + return __kvm_get_hypervisor_cpuid(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent, sig); +} - return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES, +static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_cpuid_entry2 *entries, + int nent, u32 kvm_cpuid_base) +{ + return cpuid_entry2_find(entries, nent, kvm_cpuid_base | KVM_CPUID_FEATURES, KVM_CPUID_INDEX_NOT_SIGNIFICANT); } static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) { - return __kvm_find_kvm_cpuid_features(vcpu, vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent); + u32 base = vcpu->arch.kvm_cpuid.base; + + if (!base) + return NULL; + + return __kvm_find_kvm_cpuid_features(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent, base); } void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) @@ -266,6 +273,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e int nent) { struct kvm_cpuid_entry2 *best; + struct kvm_hypervisor_cpuid kvm_cpuid; best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { @@ -292,10 +300,12 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent); - if (kvm_hlt_in_guest(vcpu->kvm) && best && - (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) - best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); + kvm_cpuid = __kvm_get_hypervisor_cpuid(entries, nent, KVM_SIGNATURE); + if (kvm_cpuid.base) { + best = __kvm_find_kvm_cpuid_features(entries, nent, kvm_cpuid.base); + if (kvm_hlt_in_guest(vcpu->kvm) && best) + best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); + } if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); @@ -1222,9 +1232,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = 0; break; case 0x80000008: { - unsigned g_phys_as = (entry->eax >> 16) & 0xff; - unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); - unsigned phys_as = entry->eax & 0xff; + unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned int phys_as; /* * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as @@ -1232,16 +1241,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * reductions in MAXPHYADDR for memory encryption affect shadow * paging, too. * - * If TDP is enabled but an explicit guest MAXPHYADDR is not - * provided, use the raw bare metal MAXPHYADDR as reductions to - * the HPAs do not affect GPAs. + * If TDP is enabled, use the raw bare metal MAXPHYADDR as + * reductions to the HPAs do not affect GPAs. */ - if (!tdp_enabled) - g_phys_as = boot_cpu_data.x86_phys_bits; - else if (!g_phys_as) - g_phys_as = phys_as; + if (!tdp_enabled) { + phys_as = boot_cpu_data.x86_phys_bits; + } else { + phys_as = entry->eax & 0xff; + } - entry->eax = g_phys_as | (virt_as << 8); + entry->eax = phys_as | (virt_as << 8); entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 95ea1a1f74..999227fc7c 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -189,9 +189,8 @@ static const struct file_operations mmu_rmaps_stat_fops = { .release = kvm_mmu_rmaps_stat_release, }; -int kvm_arch_create_vm_debugfs(struct kvm *kvm) +void kvm_arch_create_vm_debugfs(struct kvm *kvm) { debugfs_create_file("mmu_rmaps_stat", 0644, kvm->debugfs_dentry, kvm, &mmu_rmaps_stat_fops); - return 0; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index e223043ef5..5d4c861334 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1820,22 +1820,22 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) return X86EMUL_CONTINUE; } -static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes) +static int emulate_push(struct x86_emulate_ctxt *ctxt, const void *data, int len) { struct segmented_address addr; - rsp_increment(ctxt, -bytes); + rsp_increment(ctxt, -len); addr.ea = reg_read(ctxt, VCPU_REGS_RSP) & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; - return segmented_write(ctxt, addr, data, bytes); + return segmented_write(ctxt, addr, data, len); } static int em_push(struct x86_emulate_ctxt *ctxt) { /* Disable writeback. */ ctxt->dst.type = OP_NONE; - return push(ctxt, &ctxt->src.val, ctxt->op_bytes); + return emulate_push(ctxt, &ctxt->src.val, ctxt->op_bytes); } static int emulate_pop(struct x86_emulate_ctxt *ctxt, @@ -1863,7 +1863,8 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, void *dest, int len) { int rc; - unsigned long val, change_mask; + unsigned long val = 0; + unsigned long change_mask; int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; int cpl = ctxt->ops->cpl(ctxt); @@ -1920,7 +1921,7 @@ static int em_enter(struct x86_emulate_ctxt *ctxt) return X86EMUL_UNHANDLEABLE; rbp = reg_read(ctxt, VCPU_REGS_RBP); - rc = push(ctxt, &rbp, stack_size(ctxt)); + rc = emulate_push(ctxt, &rbp, stack_size(ctxt)); if (rc != X86EMUL_CONTINUE) return rc; assign_masked(reg_rmw(ctxt, VCPU_REGS_RBP), reg_read(ctxt, VCPU_REGS_RSP), @@ -1954,7 +1955,7 @@ static int em_push_sreg(struct x86_emulate_ctxt *ctxt) static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) { int seg = ctxt->src2.val; - unsigned long selector; + unsigned long selector = 0; int rc; rc = emulate_pop(ctxt, &selector, 2); @@ -2000,7 +2001,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; - u32 val; + u32 val = 0; while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { @@ -2229,7 +2230,7 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) static int em_ret(struct x86_emulate_ctxt *ctxt) { int rc; - unsigned long eip; + unsigned long eip = 0; rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) @@ -2241,7 +2242,8 @@ static int em_ret(struct x86_emulate_ctxt *ctxt) static int em_ret_far(struct x86_emulate_ctxt *ctxt) { int rc; - unsigned long eip, cs; + unsigned long eip = 0; + unsigned long cs = 0; int cpl = ctxt->ops->cpl(ctxt); struct desc_struct new_desc; @@ -3011,7 +3013,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ret = em_push(ctxt); } - ops->get_dr(ctxt, 7, &dr7); + dr7 = ops->get_dr(ctxt, 7); ops->set_dr(ctxt, 7, dr7 & ~(DR_LOCAL_ENABLE_MASK | DR_LOCAL_SLOWDOWN)); return ret; @@ -3184,7 +3186,7 @@ fail: static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) { int rc; - unsigned long eip; + unsigned long eip = 0; rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) @@ -3866,15 +3868,6 @@ static int check_cr_access(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int check_dr7_gd(struct x86_emulate_ctxt *ctxt) -{ - unsigned long dr7; - - ctxt->ops->get_dr(ctxt, 7, &dr7); - - return dr7 & DR7_GD; -} - static int check_dr_read(struct x86_emulate_ctxt *ctxt) { int dr = ctxt->modrm_reg; @@ -3887,10 +3880,10 @@ static int check_dr_read(struct x86_emulate_ctxt *ctxt) if ((cr4 & X86_CR4_DE) && (dr == 4 || dr == 5)) return emulate_ud(ctxt); - if (check_dr7_gd(ctxt)) { + if (ctxt->ops->get_dr(ctxt, 7) & DR7_GD) { ulong dr6; - ctxt->ops->get_dr(ctxt, 6, &dr6); + dr6 = ctxt->ops->get_dr(ctxt, 6); dr6 &= ~DR_TRAP_BITS; dr6 |= DR6_BD | DR6_ACTIVE_LOW; ctxt->ops->set_dr(ctxt, 6, dr6); @@ -3962,7 +3955,7 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt) * protected mode. */ if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) || - ctxt->ops->check_pmc(ctxt, rcx)) + ctxt->ops->check_rdpmc_early(ctxt, rcx)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; @@ -4505,11 +4498,11 @@ static const struct instr_dual instr_dual_0f_38_f1 = { }; static const struct gprefix three_byte_0f_38_f0 = { - ID(0, &instr_dual_0f_38_f0), N, N, N + ID(0, &instr_dual_0f_38_f0), ID(0, &instr_dual_0f_38_f0), N, N }; static const struct gprefix three_byte_0f_38_f1 = { - ID(0, &instr_dual_0f_38_f1), N, N, N + ID(0, &instr_dual_0f_38_f1), ID(0, &instr_dual_0f_38_f1), N, N }; /* @@ -5449,7 +5442,7 @@ twobyte_insn: ctxt->dst.val = ops->get_cr(ctxt, ctxt->modrm_reg); break; case 0x21: /* mov from dr to reg */ - ops->get_dr(ctxt, ctxt->modrm_reg, &ctxt->dst.val); + ctxt->dst.val = ops->get_dr(ctxt, ctxt->modrm_reg); break; case 0x40 ... 0x4f: /* cmov */ if (test_cc(ctxt->b, ctxt->eflags)) diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index e6d1498251..5382646162 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -203,12 +203,12 @@ struct x86_emulate_ops { ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr); int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val); int (*cpl)(struct x86_emulate_ctxt *ctxt); - void (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); + ulong (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); int (*set_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); - int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc); + int (*check_rdpmc_early)(struct x86_emulate_ctxt *ctxt, u32 pmc); int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata); void (*halt)(struct x86_emulate_ctxt *ctxt); void (*wbinvd)(struct x86_emulate_ctxt *ctxt); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 76fcee92b0..ebf41023be 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -125,6 +125,9 @@ static inline int __apic_test_and_clear_vector(int vec, void *bitmap) return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } +__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); +EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu); + __read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_hw_disabled, HZ); __read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_sw_disabled, HZ); @@ -2469,8 +2472,10 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!vcpu->arch.apic) + if (!vcpu->arch.apic) { + static_branch_dec(&kvm_has_noapic_vcpu); return; + } hrtimer_cancel(&apic->lapic_timer.timer); @@ -2813,13 +2818,21 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) ASSERT(vcpu != NULL); + if (!irqchip_in_kernel(vcpu->kvm)) { + static_branch_inc(&kvm_has_noapic_vcpu); + return 0; + } + apic = kzalloc(sizeof(*apic), GFP_KERNEL_ACCOUNT); if (!apic) goto nomem; vcpu->arch.apic = apic; - apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (kvm_x86_ops.alloc_apic_backing_page) + apic->regs = static_call(kvm_x86_alloc_apic_backing_page)(vcpu); + else + apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!apic->regs) { printk(KERN_ERR "malloc apic regs error for vcpu %x\n", vcpu->vcpu_id); @@ -2848,6 +2861,21 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */ kvm_iodevice_init(&apic->dev, &apic_mmio_ops); + /* + * Defer evaluating inhibits until the vCPU is first run, as this vCPU + * will not get notified of any changes until this vCPU is visible to + * other vCPUs (marked online and added to the set of vCPUs). + * + * Opportunistically mark APICv active as VMX in particularly is highly + * unlikely to have inhibits. Ignore the current per-VM APICv state so + * that vCPU creation is guaranteed to run with a deterministic value, + * the request will ensure the vCPU gets the correct state before VM-Entry. + */ + if (enable_apicv) { + apic->apicv_active = true; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } + return 0; nomem_free_apic: kfree(apic); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 982cf41e14..db007a4dff 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -47,18 +47,18 @@ #include <linux/kern_levels.h> #include <linux/kstrtox.h> #include <linux/kthread.h> +#include <linux/wordpart.h> #include <asm/page.h> #include <asm/memtype.h> #include <asm/cmpxchg.h> #include <asm/io.h> #include <asm/set_memory.h> +#include <asm/spec-ctrl.h> #include <asm/vmx.h> #include "trace.h" -extern bool itlb_multihit_kvm_mitigation; - static bool nx_hugepage_mitigation_hard_disabled; int __read_mostly nx_huge_pages = -1; @@ -263,7 +263,7 @@ static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu) static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { - if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) return kvm_read_cr3(vcpu); return mmu->get_guest_pgd(vcpu); @@ -3110,7 +3110,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, /* * Read each entry once. As above, a non-leaf entry can be promoted to * a huge page _during_ this walk. Re-reading the entry could send the - * walk into the weeks, e.g. p*d_large() returns false (sees the old + * walk into the weeks, e.g. p*d_leaf() returns false (sees the old * value) and then p*d_offset() walks into the target huge page instead * of the old page table (sees the new value). */ @@ -3135,7 +3135,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, if (pmd_none(pmd) || !pmd_present(pmd)) goto out; - if (pmd_large(pmd)) + if (pmd_leaf(pmd)) level = PG_LEVEL_2M; out: @@ -3575,10 +3575,14 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, if (WARN_ON_ONCE(!sp)) return; - if (is_tdp_mmu_page(sp)) + if (is_tdp_mmu_page(sp)) { + lockdep_assert_held_read(&kvm->mmu_lock); kvm_tdp_mmu_put_root(kvm, sp); - else if (!--sp->root_count && sp->role.invalid) - kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); + } else { + lockdep_assert_held_write(&kvm->mmu_lock); + if (!--sp->root_count && sp->role.invalid) + kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); + } *root_hpa = INVALID_PAGE; } @@ -3587,6 +3591,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free) { + bool is_tdp_mmu = tdp_mmu_enabled && mmu->root_role.direct; int i; LIST_HEAD(invalid_list); bool free_active_root; @@ -3609,7 +3614,10 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, return; } - write_lock(&kvm->mmu_lock); + if (is_tdp_mmu) + read_lock(&kvm->mmu_lock); + else + write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) @@ -3635,8 +3643,13 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, mmu->root.pgd = 0; } - kvm_mmu_commit_zap_page(kvm, &invalid_list); - write_unlock(&kvm->mmu_lock); + if (is_tdp_mmu) { + read_unlock(&kvm->mmu_lock); + WARN_ON_ONCE(!list_empty(&invalid_list)); + } else { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + write_unlock(&kvm->mmu_lock); + } } EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); @@ -3693,15 +3706,15 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) unsigned i; int r; + if (tdp_mmu_enabled) + return kvm_tdp_mmu_alloc_root(vcpu); + write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); if (r < 0) goto out_unlock; - if (tdp_mmu_enabled) { - root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu); - mmu->root.hpa = root; - } else if (shadow_root_level >= PT64_ROOT_4LEVEL) { + if (shadow_root_level >= PT64_ROOT_4LEVEL) { root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level); mmu->root.hpa = root; } else if (shadow_root_level == PT32E_ROOT_LEVEL) { @@ -5563,9 +5576,9 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ - vcpu->arch.root_mmu.root_role.word = 0; - vcpu->arch.guest_mmu.root_role.word = 0; - vcpu->arch.nested_mmu.root_role.word = 0; + vcpu->arch.root_mmu.root_role.invalid = 1; + vcpu->arch.guest_mmu.root_role.invalid = 1; + vcpu->arch.nested_mmu.root_role.invalid = 1; vcpu->arch.root_mmu.cpu_role.ext.valid = 0; vcpu->arch.guest_mmu.cpu_role.ext.valid = 0; vcpu->arch.nested_mmu.cpu_role.ext.valid = 0; @@ -7039,9 +7052,7 @@ int kvm_mmu_vendor_module_init(void) kvm_mmu_reset_all_pte_masks(); - pte_list_desc_cache = kmem_cache_create("pte_list_desc", - sizeof(struct pte_list_desc), - 0, SLAB_ACCOUNT, NULL); + pte_list_desc_cache = KMEM_CACHE(pte_list_desc, SLAB_ACCOUNT); if (!pte_list_desc_cache) goto out; diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 0669a8a668..5390a591a5 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -315,7 +315,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (!prefetch) vcpu->stat.pf_taken++; - if (IS_ENABLED(CONFIG_RETPOLINE) && fault.is_tdp) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && fault.is_tdp) r = kvm_tdp_page_fault(vcpu, &fault); else r = vcpu->arch.mmu->page_fault(vcpu, &fault); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index c87da11f3a..f6448284c1 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -20,10 +20,23 @@ #include "mmu_internal.h" #include "page_track.h" +static bool kvm_external_write_tracking_enabled(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING + /* + * Read external_write_tracking_enabled before related pointers. Pairs + * with the smp_store_release in kvm_page_track_write_tracking_enable(). + */ + return smp_load_acquire(&kvm->arch.external_write_tracking_enabled); +#else + return false; +#endif +} + bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) { - return IS_ENABLED(CONFIG_KVM_EXTERNAL_WRITE_TRACKING) || - !tdp_enabled || kvm_shadow_root_allocated(kvm); + return kvm_external_write_tracking_enabled(kvm) || + kvm_shadow_root_allocated(kvm) || !tdp_enabled; } void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) @@ -153,6 +166,50 @@ int kvm_page_track_init(struct kvm *kvm) return init_srcu_struct(&head->track_srcu); } +static int kvm_enable_external_write_tracking(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; + int r = 0, i, bkt; + + mutex_lock(&kvm->slots_arch_lock); + + /* + * Check for *any* write tracking user (not just external users) under + * lock. This avoids unnecessary work, e.g. if KVM itself is using + * write tracking, or if two external users raced when registering. + */ + if (kvm_page_track_write_tracking_enabled(kvm)) + goto out_success; + + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(slot, bkt, slots) { + /* + * Intentionally do NOT free allocations on failure to + * avoid having to track which allocations were made + * now versus when the memslot was created. The + * metadata is guaranteed to be freed when the slot is + * freed, and will be kept/used if userspace retries + * the failed ioctl() instead of killing the VM. + */ + r = kvm_page_track_write_tracking_alloc(slot); + if (r) + goto out_unlock; + } + } + +out_success: + /* + * Ensure that external_write_tracking_enabled becomes true strictly + * after all the related pointers are set. + */ + smp_store_release(&kvm->arch.external_write_tracking_enabled, true); +out_unlock: + mutex_unlock(&kvm->slots_arch_lock); + return r; +} + /* * register the notifier so that event interception for the tracked guest * pages can be received. @@ -161,10 +218,17 @@ int kvm_page_track_register_notifier(struct kvm *kvm, struct kvm_page_track_notifier_node *n) { struct kvm_page_track_notifier_head *head; + int r; if (!kvm || kvm->mm != current->mm) return -ESRCH; + if (!kvm_external_write_tracking_enabled(kvm)) { + r = kvm_enable_external_write_tracking(kvm); + if (r) + return r; + } + kvm_get_kvm(kvm); head = &kvm->arch.track_notifier_head; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 953082bf96..04c1f0957f 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -149,11 +149,11 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * If shared is set, this function is operating under the MMU lock in read * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid)\ - for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ - ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ - if (kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + if (_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) { \ } else #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ @@ -171,12 +171,19 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * Holding mmu_lock for write obviates the need for RCU protection as the list * is guaranteed to be stable. */ -#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ - list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ - if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ - kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _only_valid) \ + list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ + if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ + ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) || \ + ((_only_valid) && (_root)->role.invalid))) { \ } else +#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root(_kvm, _root, _as_id, false) + +#define for_each_valid_tdp_mmu_root(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root(_kvm, _root, _as_id, true) + static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu) { struct kvm_mmu_page *sp; @@ -216,22 +223,41 @@ static void tdp_mmu_init_child_sp(struct kvm_mmu_page *child_sp, tdp_mmu_init_sp(child_sp, iter->sptep, iter->gfn, role); } -hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) +int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) { - union kvm_mmu_page_role role = vcpu->arch.mmu->root_role; + struct kvm_mmu *mmu = vcpu->arch.mmu; + union kvm_mmu_page_role role = mmu->root_role; + int as_id = kvm_mmu_role_as_id(role); struct kvm *kvm = vcpu->kvm; struct kvm_mmu_page *root; - lockdep_assert_held_write(&kvm->mmu_lock); + /* + * Check for an existing root before acquiring the pages lock to avoid + * unnecessary serialization if multiple vCPUs are loading a new root. + * E.g. when bringing up secondary vCPUs, KVM will already have created + * a valid root on behalf of the primary vCPU. + */ + read_lock(&kvm->mmu_lock); + + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, as_id) { + if (root->role.word == role.word) + goto out_read_unlock; + } + + spin_lock(&kvm->arch.tdp_mmu_pages_lock); /* - * Check for an existing root before allocating a new one. Note, the - * role check prevents consuming an invalid root. + * Recheck for an existing root after acquiring the pages lock, another + * vCPU may have raced ahead and created a new usable root. Manually + * walk the list of roots as the standard macros assume that the pages + * lock is *not* held. WARN if grabbing a reference to a usable root + * fails, as the last reference to a root can only be put *after* the + * root has been invalidated, which requires holding mmu_lock for write. */ - for_each_tdp_mmu_root(kvm, root, kvm_mmu_role_as_id(role)) { + list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { if (root->role.word == role.word && - kvm_tdp_mmu_get_root(root)) - goto out; + !WARN_ON_ONCE(!kvm_tdp_mmu_get_root(root))) + goto out_spin_unlock; } root = tdp_mmu_alloc_sp(vcpu); @@ -245,13 +271,20 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots(). */ refcount_set(&root->tdp_mmu_root_count, 2); - - spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots); - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); -out: - return __pa(root->spt); +out_spin_unlock: + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); +out_read_unlock: + read_unlock(&kvm->mmu_lock); + /* + * Note, KVM_REQ_MMU_FREE_OBSOLETE_ROOTS will prevent entering the guest + * and actually consuming the root if it's invalidated after dropping + * mmu_lock, and the root can't be freed as this vCPU holds a reference. + */ + mmu->root.hpa = __pa(root->spt); + mmu->root.pgd = 0; + return 0; } static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, @@ -734,15 +767,26 @@ static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); /* - * To avoid RCU stalls due to recursively removing huge swaths of SPs, - * split the zap into two passes. On the first pass, zap at the 1gb - * level, and then zap top-level SPs on the second pass. "1gb" is not - * arbitrary, as KVM must be able to zap a 1gb shadow page without - * inducing a stall to allow in-place replacement with a 1gb hugepage. + * Zap roots in multiple passes of decreasing granularity, i.e. zap at + * 4KiB=>2MiB=>1GiB=>root, in order to better honor need_resched() (all + * preempt models) or mmu_lock contention (full or real-time models). + * Zapping at finer granularity marginally increases the total time of + * the zap, but in most cases the zap itself isn't latency sensitive. * - * Because zapping a SP recurses on its children, stepping down to - * PG_LEVEL_4K in the iterator itself is unnecessary. + * If KVM is configured to prove the MMU, skip the 4KiB and 2MiB zaps + * in order to mimic the page fault path, which can replace a 1GiB page + * table with an equivalent 1GiB hugepage, i.e. can get saddled with + * zapping a 1GiB region that's fully populated with 4KiB SPTEs. This + * allows verifying that KVM can safely zap 1GiB regions, e.g. without + * inducing RCU stalls, without relying on a relatively rare event + * (zapping roots is orders of magnitude more common). Note, because + * zapping a SP recurses on its children, stepping down to PG_LEVEL_4K + * in the iterator itself is unnecessary. */ + if (!IS_ENABLED(CONFIG_KVM_PROVE_MMU)) { + __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_4K); + __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_2M); + } __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_1G); __tdp_mmu_zap_root(kvm, root, shared, root->role.level); @@ -800,7 +844,13 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, continue; tdp_mmu_iter_set_spte(kvm, &iter, 0); - flush = true; + + /* + * Zappings SPTEs in invalid roots doesn't require a TLB flush, + * see kvm_tdp_mmu_zap_invalidated_roots() for details. + */ + if (!root->role.invalid) + flush = true; } rcu_read_unlock(); @@ -813,16 +863,16 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, } /* - * Zap leaf SPTEs for the range of gfns, [start, end), for all roots. Returns - * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or - * more SPTEs were zapped since the MMU lock was last acquired. + * Zap leaf SPTEs for the range of gfns, [start, end), for all *VALID** roots. + * Returns true if a TLB flush is needed before releasing the MMU lock, i.e. if + * one or more SPTEs were zapped since the MMU lock was last acquired. */ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; lockdep_assert_held_write(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, -1) flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; @@ -896,7 +946,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * the VM is being destroyed). * * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. - * See kvm_tdp_mmu_get_vcpu_root_hpa(). + * See kvm_tdp_mmu_alloc_root(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) { @@ -1508,13 +1558,6 @@ static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp) return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled(); } -/* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. - */ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { @@ -1551,11 +1594,9 @@ retry: } /* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. + * Clear the dirty status (D-bit or W-bit) of all the SPTEs mapping GFNs in the + * memslot. Returns true if an SPTE has been changed and the TLBs need to be + * flushed. */ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, const struct kvm_memory_slot *slot) @@ -1571,13 +1612,6 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, return spte_set; } -/* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. - */ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { @@ -1620,11 +1654,9 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, } /* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. + * Clear the dirty status (D-bit or W-bit) of all the 4k SPTEs mapping GFNs for + * which a bit is set in mask, starting at gfn. The given memslot is expected to + * contain all the GFNs represented by set bits in the mask. */ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -1633,7 +1665,7 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, { struct kvm_mmu_page *root; - for_each_tdp_mmu_root(kvm, root, slot->as_id) + for_each_valid_tdp_mmu_root(kvm, root, slot->as_id) clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot); } @@ -1751,7 +1783,7 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, bool spte_set = false; lockdep_assert_held_write(&kvm->mmu_lock); - for_each_tdp_mmu_root(kvm, root, slot->as_id) + for_each_valid_tdp_mmu_root(kvm, root, slot->as_id) spte_set |= write_protect_gfn(kvm, root, gfn, min_level); return spte_set; diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 20d97aa46c..6e1ea04ca8 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -10,7 +10,7 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); -hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); +int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) { diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 2ab2d5213f..a593b03c9a 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -29,6 +29,9 @@ struct x86_pmu_capability __read_mostly kvm_pmu_cap; EXPORT_SYMBOL_GPL(kvm_pmu_cap); +struct kvm_pmu_emulated_event_selectors __read_mostly kvm_pmu_eventsel; +EXPORT_SYMBOL_GPL(kvm_pmu_eventsel); + /* Precise Distribution of Instructions Retired (PDIR) */ static const struct x86_cpu_id vmx_pebs_pdir_cpu[] = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, NULL), @@ -67,7 +70,7 @@ static const struct x86_cpu_id vmx_pebs_pdist_cpu[] = { * all perf counters (both gp and fixed). The mapping relationship * between pmc and perf counters is as the following: * * Intel: [0 .. KVM_INTEL_PMC_MAX_GENERIC-1] <=> gp counters - * [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed + * [KVM_FIXED_PMC_BASE_IDX .. KVM_FIXED_PMC_BASE_IDX + 2] <=> fixed * * AMD: [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H * and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters */ @@ -411,7 +414,7 @@ static bool is_gp_event_allowed(struct kvm_x86_pmu_event_filter *f, static bool is_fixed_event_allowed(struct kvm_x86_pmu_event_filter *filter, int idx) { - int fixed_idx = idx - INTEL_PMC_IDX_FIXED; + int fixed_idx = idx - KVM_FIXED_PMC_BASE_IDX; if (filter->action == KVM_PMU_EVENT_DENY && test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap)) @@ -441,11 +444,10 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc) static bool pmc_event_is_allowed(struct kvm_pmc *pmc) { return pmc_is_globally_enabled(pmc) && pmc_speculative_in_use(pmc) && - static_call(kvm_x86_pmu_hw_event_available)(pmc) && check_pmu_event_filter(pmc); } -static void reprogram_counter(struct kvm_pmc *pmc) +static int reprogram_counter(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); u64 eventsel = pmc->eventsel; @@ -456,7 +458,7 @@ static void reprogram_counter(struct kvm_pmc *pmc) emulate_overflow = pmc_pause_counter(pmc); if (!pmc_event_is_allowed(pmc)) - goto reprogram_complete; + return 0; if (emulate_overflow) __kvm_perf_overflow(pmc, false); @@ -466,7 +468,7 @@ static void reprogram_counter(struct kvm_pmc *pmc) if (pmc_is_fixed(pmc)) { fixed_ctr_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, - pmc->idx - INTEL_PMC_IDX_FIXED); + pmc->idx - KVM_FIXED_PMC_BASE_IDX); if (fixed_ctr_ctrl & 0x1) eventsel |= ARCH_PERFMON_EVENTSEL_OS; if (fixed_ctr_ctrl & 0x2) @@ -477,43 +479,45 @@ static void reprogram_counter(struct kvm_pmc *pmc) } if (pmc->current_config == new_config && pmc_resume_counter(pmc)) - goto reprogram_complete; + return 0; pmc_release_perf_event(pmc); pmc->current_config = new_config; - /* - * If reprogramming fails, e.g. due to contention, leave the counter's - * regprogram bit set, i.e. opportunistically try again on the next PMU - * refresh. Don't make a new request as doing so can stall the guest - * if reprogramming repeatedly fails. - */ - if (pmc_reprogram_counter(pmc, PERF_TYPE_RAW, - (eventsel & pmu->raw_event_mask), - !(eventsel & ARCH_PERFMON_EVENTSEL_USR), - !(eventsel & ARCH_PERFMON_EVENTSEL_OS), - eventsel & ARCH_PERFMON_EVENTSEL_INT)) - return; - -reprogram_complete: - clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); + return pmc_reprogram_counter(pmc, PERF_TYPE_RAW, + (eventsel & pmu->raw_event_mask), + !(eventsel & ARCH_PERFMON_EVENTSEL_USR), + !(eventsel & ARCH_PERFMON_EVENTSEL_OS), + eventsel & ARCH_PERFMON_EVENTSEL_INT); } void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { + DECLARE_BITMAP(bitmap, X86_PMC_IDX_MAX); struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; int bit; - for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) { - struct kvm_pmc *pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, bit); + bitmap_copy(bitmap, pmu->reprogram_pmi, X86_PMC_IDX_MAX); - if (unlikely(!pmc)) { - clear_bit(bit, pmu->reprogram_pmi); - continue; - } + /* + * The reprogramming bitmap can be written asynchronously by something + * other than the task that holds vcpu->mutex, take care to clear only + * the bits that will actually processed. + */ + BUILD_BUG_ON(sizeof(bitmap) != sizeof(atomic64_t)); + atomic64_andnot(*(s64 *)bitmap, &pmu->__reprogram_pmi); - reprogram_counter(pmc); + kvm_for_each_pmc(pmu, pmc, bit, bitmap) { + /* + * If reprogramming fails, e.g. due to contention, re-set the + * regprogram bit set, i.e. opportunistically try again on the + * next PMU refresh. Don't make a new request as doing so can + * stall the guest if reprogramming repeatedly fails. + */ + if (reprogram_counter(pmc)) + set_bit(pmc->idx, pmu->reprogram_pmi); } /* @@ -525,10 +529,20 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) kvm_pmu_cleanup(vcpu); } -/* check if idx is a valid index to access PMU */ -bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +int kvm_pmu_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx) { - return static_call(kvm_x86_pmu_is_valid_rdpmc_ecx)(vcpu, idx); + /* + * On Intel, VMX interception has priority over RDPMC exceptions that + * aren't already handled by the emulator, i.e. there are no additional + * check needed for Intel PMUs. + * + * On AMD, _all_ exceptions on RDPMC have priority over SVM intercepts, + * i.e. an invalid PMC results in a #GP, not #VMEXIT. + */ + if (!kvm_pmu_ops.check_rdpmc_early) + return 0; + + return static_call(kvm_x86_pmu_check_rdpmc_early)(vcpu, idx); } bool is_vmware_backdoor_pmc(u32 pmc_idx) @@ -567,10 +581,9 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) { - bool fast_mode = idx & (1u << 31); struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; - u64 mask = fast_mode ? ~0u : ~0ull; + u64 mask = ~0ull; if (!pmu->version) return 1; @@ -716,11 +729,7 @@ static void kvm_pmu_reset(struct kvm_vcpu *vcpu) bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX); - for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { - pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); - if (!pmc) - continue; - + kvm_for_each_pmc(pmu, pmc, i, pmu->all_valid_pmc_idx) { pmc_stop_counter(pmc); pmc->counter = 0; pmc->emulated_counter = 0; @@ -804,10 +813,8 @@ void kvm_pmu_cleanup(struct kvm_vcpu *vcpu) bitmap_andnot(bitmask, pmu->all_valid_pmc_idx, pmu->pmc_in_use, X86_PMC_IDX_MAX); - for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) { - pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); - - if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc)) + kvm_for_each_pmc(pmu, pmc, i, bitmask) { + if (pmc->perf_event && !pmc_speculative_in_use(pmc)) pmc_stop_counter(pmc); } @@ -827,13 +834,6 @@ static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) kvm_pmu_request_counter_reprogram(pmc); } -static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc, - unsigned int perf_hw_id) -{ - return !((pmc->eventsel ^ perf_get_hw_event_config(perf_hw_id)) & - AMD64_RAW_EVENT_MASK_NB); -} - static inline bool cpl_is_matched(struct kvm_pmc *pmc) { bool select_os, select_user; @@ -845,29 +845,56 @@ static inline bool cpl_is_matched(struct kvm_pmc *pmc) select_user = config & ARCH_PERFMON_EVENTSEL_USR; } else { config = fixed_ctrl_field(pmc_to_pmu(pmc)->fixed_ctr_ctrl, - pmc->idx - INTEL_PMC_IDX_FIXED); + pmc->idx - KVM_FIXED_PMC_BASE_IDX); select_os = config & 0x1; select_user = config & 0x2; } + /* + * Skip the CPL lookup, which isn't free on Intel, if the result will + * be the same regardless of the CPL. + */ + if (select_os == select_user) + return select_os; + return (static_call(kvm_x86_get_cpl)(pmc->vcpu) == 0) ? select_os : select_user; } -void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) +void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 eventsel) { + DECLARE_BITMAP(bitmap, X86_PMC_IDX_MAX); struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; int i; - for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { - pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); + BUILD_BUG_ON(sizeof(pmu->global_ctrl) * BITS_PER_BYTE != X86_PMC_IDX_MAX); - if (!pmc || !pmc_event_is_allowed(pmc)) + if (!kvm_pmu_has_perf_global_ctrl(pmu)) + bitmap_copy(bitmap, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX); + else if (!bitmap_and(bitmap, pmu->all_valid_pmc_idx, + (unsigned long *)&pmu->global_ctrl, X86_PMC_IDX_MAX)) + return; + + kvm_for_each_pmc(pmu, pmc, i, bitmap) { + /* + * Ignore checks for edge detect (all events currently emulated + * but KVM are always rising edges), pin control (unsupported + * by modern CPUs), and counter mask and its invert flag (KVM + * doesn't emulate multiple events in a single clock cycle). + * + * Note, the uppermost nibble of AMD's mask overlaps Intel's + * IN_TX (bit 32) and IN_TXCP (bit 33), as well as two reserved + * bits (bits 35:34). Checking the "in HLE/RTM transaction" + * flags is correct as the vCPU can't be in a transaction if + * KVM is emulating an instruction. Checking the reserved bits + * might be wrong if they are defined in the future, but so + * could ignoring them, so do the simple thing for now. + */ + if (((pmc->eventsel ^ eventsel) & AMD64_RAW_EVENT_MASK_NB) || + !pmc_event_is_allowed(pmc) || !cpl_is_matched(pmc)) continue; - /* Ignore checks for edge detect, pin control, invert and CMASK bits */ - if (eventsel_match_perf_hw_id(pmc, perf_hw_id) && cpl_is_matched(pmc)) - kvm_pmu_incr_counter(pmc); + kvm_pmu_incr_counter(pmc); } } EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7caeb3d8d4..4d52b0b539 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -4,6 +4,8 @@ #include <linux/nospec.h> +#include <asm/kvm_host.h> + #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) @@ -18,13 +20,18 @@ #define VMWARE_BACKDOOR_PMC_REAL_TIME 0x10001 #define VMWARE_BACKDOOR_PMC_APPARENT_TIME 0x10002 +#define KVM_FIXED_PMC_BASE_IDX INTEL_PMC_IDX_FIXED + +struct kvm_pmu_emulated_event_selectors { + u64 INSTRUCTIONS_RETIRED; + u64 BRANCH_INSTRUCTIONS_RETIRED; +}; + struct kvm_pmu_ops { - bool (*hw_event_available)(struct kvm_pmc *pmc); - struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask); struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); - bool (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); + int (*check_rdpmc_early)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -55,6 +62,38 @@ static inline bool kvm_pmu_has_perf_global_ctrl(struct kvm_pmu *pmu) return pmu->version > 1; } +/* + * KVM tracks all counters in 64-bit bitmaps, with general purpose counters + * mapped to bits 31:0 and fixed counters mapped to 63:32, e.g. fixed counter 0 + * is tracked internally via index 32. On Intel, (AMD doesn't support fixed + * counters), this mirrors how fixed counters are mapped to PERF_GLOBAL_CTRL + * and similar MSRs, i.e. tracking fixed counters at base index 32 reduces the + * amounter of boilerplate needed to iterate over PMCs *and* simplifies common + * enabling/disable/reset operations. + * + * WARNING! This helper is only for lookups that are initiated by KVM, it is + * NOT safe for guest lookups, e.g. will do the wrong thing if passed a raw + * ECX value from RDPMC (fixed counters are accessed by setting bit 30 in ECX + * for RDPMC, not by adding 32 to the fixed counter index). + */ +static inline struct kvm_pmc *kvm_pmc_idx_to_pmc(struct kvm_pmu *pmu, int idx) +{ + if (idx < pmu->nr_arch_gp_counters) + return &pmu->gp_counters[idx]; + + idx -= KVM_FIXED_PMC_BASE_IDX; + if (idx >= 0 && idx < pmu->nr_arch_fixed_counters) + return &pmu->fixed_counters[idx]; + + return NULL; +} + +#define kvm_for_each_pmc(pmu, pmc, i, bitmap) \ + for_each_set_bit(i, bitmap, X86_PMC_IDX_MAX) \ + if (!(pmc = kvm_pmc_idx_to_pmc(pmu, i))) \ + continue; \ + else \ + static inline u64 pmc_bitmask(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -131,12 +170,13 @@ static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) if (pmc_is_fixed(pmc)) return fixed_ctrl_field(pmu->fixed_ctr_ctrl, - pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3; + pmc->idx - KVM_FIXED_PMC_BASE_IDX) & 0x3; return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE; } extern struct x86_pmu_capability kvm_pmu_cap; +extern struct kvm_pmu_emulated_event_selectors kvm_pmu_eventsel; static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) { @@ -178,6 +218,11 @@ static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) pmu_ops->MAX_NR_GP_COUNTERS); kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed, KVM_PMC_MAX_FIXED); + + kvm_pmu_eventsel.INSTRUCTIONS_RETIRED = + perf_get_hw_event_config(PERF_COUNT_HW_INSTRUCTIONS); + kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED = + perf_get_hw_event_config(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } static inline void kvm_pmu_request_counter_reprogram(struct kvm_pmc *pmc) @@ -216,7 +261,7 @@ static inline bool pmc_is_globally_enabled(struct kvm_pmc *pmc) void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); +int kvm_pmu_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -225,7 +270,7 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu); void kvm_pmu_cleanup(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp); -void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id); +void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 eventsel); bool is_vmware_backdoor_pmc(u32 pmc_idx); diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index dc3d95fdca..d06d43d8d2 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -184,7 +184,6 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_state_32 *smram) { struct desc_ptr dt; - unsigned long val; int i; smram->cr0 = kvm_read_cr0(vcpu); @@ -195,10 +194,8 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, for (i = 0; i < 8; i++) smram->gprs[i] = kvm_register_read_raw(vcpu, i); - kvm_get_dr(vcpu, 6, &val); - smram->dr6 = (u32)val; - kvm_get_dr(vcpu, 7, &val); - smram->dr7 = (u32)val; + smram->dr6 = (u32)vcpu->arch.dr6; + smram->dr7 = (u32)vcpu->arch.dr7; enter_smm_save_seg_32(vcpu, &smram->tr, &smram->tr_sel, VCPU_SREG_TR); enter_smm_save_seg_32(vcpu, &smram->ldtr, &smram->ldtr_sel, VCPU_SREG_LDTR); @@ -231,7 +228,6 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, struct kvm_smram_state_64 *smram) { struct desc_ptr dt; - unsigned long val; int i; for (i = 0; i < 16; i++) @@ -240,11 +236,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, smram->rip = kvm_rip_read(vcpu); smram->rflags = kvm_get_rflags(vcpu); - - kvm_get_dr(vcpu, 6, &val); - smram->dr6 = val; - kvm_get_dr(vcpu, 7, &val); - smram->dr7 = val; + smram->dr6 = vcpu->arch.dr6; + smram->dr7 = vcpu->arch.dr7; smram->cr0 = kvm_read_cr0(vcpu); smram->cr3 = kvm_read_cr3(vcpu); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index dee62362a3..55b9a6d96b 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1181,7 +1181,7 @@ int svm_allocate_nested(struct vcpu_svm *svm) if (svm->nested.initialized) return 0; - vmcb02_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmcb02_page = snp_safe_alloc_page(&svm->vcpu); if (!vmcb02_page) return -ENOMEM; svm->nested.vmcb02.ptr = page_address(vmcb02_page); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index b6a7ad4d69..dfcc38bd97 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -25,7 +25,7 @@ enum pmu_type { PMU_TYPE_EVNTSEL, }; -static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) +static struct kvm_pmc *amd_pmu_get_pmc(struct kvm_pmu *pmu, int pmc_idx) { unsigned int num_counters = pmu->nr_arch_gp_counters; @@ -70,28 +70,24 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, return NULL; } - return amd_pmc_idx_to_pmc(pmu, idx); + return amd_pmu_get_pmc(pmu, idx); } -static bool amd_hw_event_available(struct kvm_pmc *pmc) -{ - return true; -} - -static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +static int amd_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - idx &= ~(3u << 30); + if (idx >= pmu->nr_arch_gp_counters) + return -EINVAL; - return idx < pmu->nr_arch_gp_counters; + return 0; } /* idx is the ECX register of RDPMC instruction */ static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask) { - return amd_pmc_idx_to_pmc(vcpu_to_pmu(vcpu), idx & ~(3u << 30)); + return amd_pmu_get_pmc(vcpu_to_pmu(vcpu), idx); } static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) @@ -233,11 +229,9 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) } struct kvm_pmu_ops amd_pmu_ops __initdata = { - .hw_event_available = amd_hw_event_available, - .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, .rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = amd_msr_idx_to_pmc, - .is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx, + .check_rdpmc_early = amd_check_rdpmc_early, .is_valid_msr = amd_is_valid_msr, .get_msr = amd_pmu_get_msr, .set_msr = amd_pmu_set_msr, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 86088d1250..4471b4e08d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -186,7 +186,8 @@ again: mutex_unlock(&sev_bitmap_lock); - return asid; + sev->asid = asid; + return 0; e_uncharge: sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); @@ -253,23 +254,23 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - int asid, ret; + struct sev_platform_init_args init_args = {0}; + int ret; if (kvm->created_vcpus) return -EINVAL; - ret = -EBUSY; if (unlikely(sev->active)) - return ret; + return -EINVAL; sev->active = true; sev->es_active = argp->id == KVM_SEV_ES_INIT; - asid = sev_asid_new(sev); - if (asid < 0) + ret = sev_asid_new(sev); + if (ret) goto e_no_asid; - sev->asid = asid; - ret = sev_platform_init(&argp->error); + init_args.probe = false; + ret = sev_platform_init(&init_args); if (ret) goto e_free; @@ -281,6 +282,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) return 0; e_free: + argp->error = init_args.error; sev_asid_free(sev); sev->asid = 0; e_no_asid: @@ -432,7 +434,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) - pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT); else pages = kmalloc(size, GFP_KERNEL_ACCOUNT); @@ -664,6 +666,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, return ret; vcpu->arch.guest_state_protected = true; + + /* + * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it + * only after setting guest_state_protected because KVM_SET_MSRS allows + * dynamic toggling of LBRV (for performance reason) on write access to + * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set. + */ + svm_enable_lbrv(vcpu); return 0; } @@ -2267,6 +2277,12 @@ void __init sev_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_SEV_ES)) goto out; + if (!lbrv) { + WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV), + "LBRV must be present for SEV-ES support"); + goto out; + } + /* Has the system been allocated ASIDs for SEV-ES? */ if (min_sev_asid == 1) goto out; @@ -3032,7 +3048,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; - svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; /* * An SEV-ES guest requires a VMSA area that is a separate from the @@ -3084,10 +3099,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) /* Clear intercepts on selected MSRs */ set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); } void sev_init_vmcb(struct vcpu_svm *svm) @@ -3176,3 +3187,35 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); } + +struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) +{ + unsigned long pfn; + struct page *p; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + + /* + * Allocate an SNP-safe page to workaround the SNP erratum where + * the CPU will incorrectly signal an RMP violation #PF if a + * hugepage (2MB or 1GB) collides with the RMP entry of a + * 2MB-aligned VMCB, VMSA, or AVIC backing page. + * + * Allocate one extra page, choose a page which is not + * 2MB-aligned, and free the other. + */ + p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1); + if (!p) + return NULL; + + split_page(p, 1); + + pfn = page_to_pfn(p); + if (IS_ALIGNED(pfn, PTRS_PER_PMD)) + __free_page(p++); + else + __free_page(p + 1); + + return p; +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e90b429c84..4650153afa 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_SPEC_CTRL, .always = false }, { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_FLUSH_CMD, .always = false }, + { .index = MSR_IA32_DEBUGCTLMSR, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -215,7 +216,7 @@ int vgif = true; module_param(vgif, int, 0444); /* enable/disable LBR virtualization */ -static int lbrv = true; +int lbrv = true; module_param(lbrv, int, 0444); static int tsc_scaling = true; @@ -703,7 +704,7 @@ static int svm_cpu_init(int cpu) int ret = -ENOMEM; memset(sd, 0, sizeof(struct svm_cpu_data)); - sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); + sd->save_area = snp_safe_alloc_page(NULL); if (!sd->save_area) return ret; @@ -990,7 +991,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) vmcb_mark_dirty(to_vmcb, VMCB_LBR); } -static void svm_enable_lbrv(struct kvm_vcpu *vcpu) +void svm_enable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1000,6 +1001,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); + if (sev_es_guest(vcpu->kvm)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1); + /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ if (is_guest_mode(vcpu)) svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); @@ -1009,6 +1013,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); @@ -1421,7 +1427,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); err = -ENOMEM; - vmcb01_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmcb01_page = snp_safe_alloc_page(vcpu); if (!vmcb01_page) goto out; @@ -1430,7 +1436,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) * SEV-ES guests require a separate VMSA page used to contain * the encrypted register state of the guest. */ - vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmsa_page = snp_safe_alloc_page(vcpu); if (!vmsa_page) goto error_free_vmcb_page; @@ -1503,6 +1509,11 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } +static struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd) +{ + return page_address(sd->save_area) + 0x400; +} + static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1519,12 +1530,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * or subsequent vmload of host save area. */ vmsave(sd->save_area_pa); - if (sev_es_guest(vcpu->kvm)) { - struct sev_es_save_area *hostsa; - hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); - - sev_es_prepare_switch_to_guest(hostsa); - } + if (sev_es_guest(vcpu->kvm)) + sev_es_prepare_switch_to_guest(sev_es_host_save_area(sd)); if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); @@ -2735,7 +2742,6 @@ static int dr_interception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); int reg, dr; - unsigned long val; int err = 0; /* @@ -2763,11 +2769,9 @@ static int dr_interception(struct kvm_vcpu *vcpu) dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0; if (dr >= 16) { /* mov to DRn */ dr -= 16; - val = kvm_register_read(vcpu, reg); - err = kvm_set_dr(vcpu, dr, val); + err = kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)); } else { - kvm_get_dr(vcpu, dr, &val); - kvm_register_write(vcpu, reg, val); + kvm_register_write(vcpu, reg, kvm_get_dr(vcpu, dr)); } return kvm_complete_insn_gp(vcpu, err); @@ -3455,7 +3459,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code) if (!svm_check_exit_valid(exit_code)) return svm_handle_invalid_exit(vcpu, exit_code); -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE if (exit_code == SVM_EXIT_MSR) return msr_interception(vcpu); else if (exit_code == SVM_EXIT_VINTR) @@ -3845,16 +3849,27 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); /* - * KVM should never request an NMI window when vNMI is enabled, as KVM - * allows at most one to-be-injected NMI and one pending NMI, i.e. if - * two NMIs arrive simultaneously, KVM will inject one and set - * V_NMI_PENDING for the other. WARN, but continue with the standard - * single-step approach to try and salvage the pending NMI. + * If NMIs are outright masked, i.e. the vCPU is already handling an + * NMI, and KVM has not yet intercepted an IRET, then there is nothing + * more to do at this time as KVM has already enabled IRET intercepts. + * If KVM has already intercepted IRET, then single-step over the IRET, + * as NMIs aren't architecturally unmasked until the IRET completes. + * + * If vNMI is enabled, KVM should never request an NMI window if NMIs + * are masked, as KVM allows at most one to-be-injected NMI and one + * pending NMI. If two NMIs arrive simultaneously, KVM will inject one + * NMI and set V_NMI_PENDING for the other, but if and only if NMIs are + * unmasked. KVM _will_ request an NMI window in some situations, e.g. + * if the vCPU is in an STI shadow or if GIF=0, KVM can't immediately + * inject the NMI. In those situations, KVM needs to single-step over + * the STI shadow or intercept STGI. */ - WARN_ON_ONCE(is_vnmi_enabled(svm)); + if (svm_get_nmi_mask(vcpu)) { + WARN_ON_ONCE(is_vnmi_enabled(svm)); - if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion) - return; /* IRET will cause a vm exit */ + if (!svm->awaiting_iret_completion) + return; /* IRET will cause a vm exit */ + } /* * SEV-ES guests are responsible for signaling when a vCPU is ready to @@ -4092,6 +4107,9 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { + if (is_guest_mode(vcpu)) + return EXIT_FASTPATH_NONE; + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && to_svm(vcpu)->vmcb->control.exit_info_1) return handle_fastpath_set_msr_irqoff(vcpu); @@ -4101,6 +4119,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted) { + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); guest_state_enter_irqoff(); @@ -4108,19 +4127,21 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in amd_clear_divider(); if (sev_es_guest(vcpu->kvm)) - __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); + __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted, + sev_es_host_save_area(sd)); else __svm_vcpu_run(svm, spec_ctrl_intercepted); guest_state_exit_irqoff(); } -static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { struct vcpu_svm *svm = to_svm(vcpu); bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL); - trace_kvm_entry(vcpu); + trace_kvm_entry(vcpu, force_immediate_exit); svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; @@ -4139,9 +4160,12 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) * is enough to force an immediate vmexit. */ disable_nmi_singlestep(svm); - smp_send_reschedule(vcpu->cpu); + force_immediate_exit = true; } + if (force_immediate_exit) + smp_send_reschedule(vcpu->cpu); + pre_svm_run(vcpu); sync_lapic_to_cr8(vcpu); @@ -4237,9 +4261,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) svm_complete_interrupts(vcpu); - if (is_guest_mode(vcpu)) - return EXIT_FASTPATH_NONE; - return svm_exit_handlers_fastpath(vcpu); } @@ -4900,6 +4921,16 @@ static int svm_vm_init(struct kvm *kvm) return 0; } +static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu) +{ + struct page *page = snp_safe_alloc_page(vcpu); + + if (!page) + return NULL; + + return page_address(page); +} + static struct kvm_x86_ops svm_x86_ops __initdata = { .name = KBUILD_MODNAME, @@ -4997,8 +5028,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .check_intercept = svm_check_intercept, .handle_exit_irqoff = svm_handle_exit_irqoff, - .request_immediate_exit = __kvm_request_immediate_exit, - .sched_in = svm_sched_in, .nested_ops = &svm_nested_ops, @@ -5031,6 +5060,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, .vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons, + .alloc_apic_backing_page = svm_alloc_apic_backing_page, }; /* @@ -5236,6 +5266,12 @@ static __init int svm_hardware_setup(void) nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS); + if (lbrv) { + if (!boot_cpu_has(X86_FEATURE_LBRV)) + lbrv = false; + else + pr_info("LBR virtualization supported\n"); + } /* * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which * may be modified by svm_adjust_mmio_mask()), as well as nrips. @@ -5289,14 +5325,6 @@ static __init int svm_hardware_setup(void) svm_x86_ops.set_vnmi_pending = NULL; } - - if (lbrv) { - if (!boot_cpu_has(X86_FEATURE_LBRV)) - lbrv = false; - else - pr_info("LBR virtualization supported\n"); - } - if (!enable_pmu) pr_info("PMU virtualization is disabled\n"); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 8ef95139cd..2ed3015e03 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -30,7 +30,7 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 47 +#define MAX_DIRECT_ACCESS_MSRS 48 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; @@ -39,6 +39,7 @@ extern int vgif; extern bool intercept_smi; extern bool x2avic_enabled; extern bool vnmi; +extern int lbrv; /* * Clean bits in VMCB. @@ -543,6 +544,7 @@ u32 *svm_vcpu_alloc_msrpm(void); void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); void svm_vcpu_free_msrpm(u32 *msrpm); void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb); +void svm_enable_lbrv(struct kvm_vcpu *vcpu); void svm_update_lbrv(struct kvm_vcpu *vcpu); int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); @@ -694,10 +696,12 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); void sev_es_unmap_ghcb(struct vcpu_svm *svm); +struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu); /* vmenter.S */ -void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted, + struct sev_es_save_area *hostsa); void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); #define DEFINE_KVM_GHCB_ACCESSORS(field) \ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 9499f9c6b0..a0c8eb37d3 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/asm-offsets.h> #include <asm/bitsperlong.h> +#include <asm/frame.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> #include "kvm-asm-offsets.h" @@ -67,7 +68,7 @@ "", X86_FEATURE_V_SPEC_CTRL 901: .endm -.macro RESTORE_HOST_SPEC_CTRL_BODY +.macro RESTORE_HOST_SPEC_CTRL_BODY spec_ctrl_intercepted:req 900: /* Same for after vmexit. */ mov $MSR_IA32_SPEC_CTRL, %ecx @@ -76,7 +77,7 @@ * Load the value that the guest had written into MSR_IA32_SPEC_CTRL, * if it was not intercepted during guest execution. */ - cmpb $0, (%_ASM_SP) + cmpb $0, \spec_ctrl_intercepted jnz 998f rdmsr movl %eax, SVM_spec_ctrl(%_ASM_DI) @@ -99,6 +100,7 @@ */ SYM_FUNC_START(__svm_vcpu_run) push %_ASM_BP + mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 push %r15 push %r14 @@ -207,7 +209,7 @@ SYM_FUNC_START(__svm_vcpu_run) 7: vmload %_ASM_AX 8: -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif @@ -268,7 +270,7 @@ SYM_FUNC_START(__svm_vcpu_run) RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY (%_ASM_SP) 10: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b @@ -290,66 +292,68 @@ SYM_FUNC_START(__svm_vcpu_run) SYM_FUNC_END(__svm_vcpu_run) +#ifdef CONFIG_KVM_AMD_SEV + + +#ifdef CONFIG_X86_64 +#define SEV_ES_GPRS_BASE 0x300 +#define SEV_ES_RBX (SEV_ES_GPRS_BASE + __VCPU_REGS_RBX * WORD_SIZE) +#define SEV_ES_RBP (SEV_ES_GPRS_BASE + __VCPU_REGS_RBP * WORD_SIZE) +#define SEV_ES_RSI (SEV_ES_GPRS_BASE + __VCPU_REGS_RSI * WORD_SIZE) +#define SEV_ES_RDI (SEV_ES_GPRS_BASE + __VCPU_REGS_RDI * WORD_SIZE) +#define SEV_ES_R12 (SEV_ES_GPRS_BASE + __VCPU_REGS_R12 * WORD_SIZE) +#define SEV_ES_R13 (SEV_ES_GPRS_BASE + __VCPU_REGS_R13 * WORD_SIZE) +#define SEV_ES_R14 (SEV_ES_GPRS_BASE + __VCPU_REGS_R14 * WORD_SIZE) +#define SEV_ES_R15 (SEV_ES_GPRS_BASE + __VCPU_REGS_R15 * WORD_SIZE) +#endif + /** * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode * @svm: struct vcpu_svm * * @spec_ctrl_intercepted: bool */ SYM_FUNC_START(__svm_sev_es_vcpu_run) - push %_ASM_BP -#ifdef CONFIG_X86_64 - push %r15 - push %r14 - push %r13 - push %r12 -#else - push %edi - push %esi -#endif - push %_ASM_BX + FRAME_BEGIN /* - * Save variables needed after vmexit on the stack, in inverse - * order compared to when they are needed. + * Save non-volatile (callee-saved) registers to the host save area. + * Except for RAX and RSP, all GPRs are restored on #VMEXIT, but not + * saved on VMRUN. */ + mov %rbp, SEV_ES_RBP (%rdx) + mov %r15, SEV_ES_R15 (%rdx) + mov %r14, SEV_ES_R14 (%rdx) + mov %r13, SEV_ES_R13 (%rdx) + mov %r12, SEV_ES_R12 (%rdx) + mov %rbx, SEV_ES_RBX (%rdx) - /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */ - push %_ASM_ARG2 - - /* Save @svm. */ - push %_ASM_ARG1 - -.ifnc _ASM_ARG1, _ASM_DI /* - * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX - * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL. + * Save volatile registers that hold arguments that are needed after + * #VMEXIT (RDI=@svm and RSI=@spec_ctrl_intercepted). */ - mov %_ASM_ARG1, %_ASM_DI -.endif + mov %rdi, SEV_ES_RDI (%rdx) + mov %rsi, SEV_ES_RSI (%rdx) - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX (@hostsa). */ RESTORE_GUEST_SPEC_CTRL /* Get svm->current_vmcb->pa into RAX. */ - mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX - mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX + mov SVM_current_vmcb(%rdi), %rax + mov KVM_VMCB_pa(%rax), %rax /* Enter guest mode */ sti -1: vmrun %_ASM_AX +1: vmrun %rax 2: cli - /* Pop @svm to RDI, guest registers have been saved already. */ - pop %_ASM_DI - -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */ RESTORE_HOST_SPEC_CTRL /* @@ -361,30 +365,17 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) */ UNTRAIN_RET_VM - /* "Pop" @spec_ctrl_intercepted. */ - pop %_ASM_BX - - pop %_ASM_BX - -#ifdef CONFIG_X86_64 - pop %r12 - pop %r13 - pop %r14 - pop %r15 -#else - pop %esi - pop %edi -#endif - pop %_ASM_BP + FRAME_END RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY %sil -3: cmpb $0, _ASM_RIP(kvm_rebooting) +3: cmpb $0, kvm_rebooting(%rip) jne 2b ud2 _ASM_EXTABLE(1b, 3b) SYM_FUNC_END(__svm_sev_es_vcpu_run) +#endif /* CONFIG_KVM_AMD_SEV */ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index b82e6ed4f0..c6b4b17280 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -15,20 +15,23 @@ * Tracepoint for guest mode entry. */ TRACE_EVENT(kvm_entry, - TP_PROTO(struct kvm_vcpu *vcpu), - TP_ARGS(vcpu), + TP_PROTO(struct kvm_vcpu *vcpu, bool force_immediate_exit), + TP_ARGS(vcpu, force_immediate_exit), TP_STRUCT__entry( __field( unsigned int, vcpu_id ) __field( unsigned long, rip ) + __field( bool, immediate_exit ) ), TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; __entry->rip = kvm_rip_read(vcpu); + __entry->immediate_exit = force_immediate_exit; ), - TP_printk("vcpu %u, rip 0x%lx", __entry->vcpu_id, __entry->rip) + TP_printk("vcpu %u, rip 0x%lx%s", __entry->vcpu_id, __entry->rip, + __entry->immediate_exit ? "[immediate exit]" : "") ); /* diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 6329a30685..d05ddf7514 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3606,7 +3606,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return 1; } - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); + kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED); if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) return nested_vmx_failInvalid(vcpu); @@ -4433,7 +4433,7 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) - kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7); + vmcs12->guest_dr7 = vcpu->arch.dr7; if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) vmcs12->guest_ia32_efer = vcpu->arch.efer; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 600a021ae9..be40474de6 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -20,53 +20,19 @@ #include "nested.h" #include "pmu.h" -#define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) - -enum intel_pmu_architectural_events { - /* - * The order of the architectural events matters as support for each - * event is enumerated via CPUID using the index of the event. - */ - INTEL_ARCH_CPU_CYCLES, - INTEL_ARCH_INSTRUCTIONS_RETIRED, - INTEL_ARCH_REFERENCE_CYCLES, - INTEL_ARCH_LLC_REFERENCES, - INTEL_ARCH_LLC_MISSES, - INTEL_ARCH_BRANCHES_RETIRED, - INTEL_ARCH_BRANCHES_MISPREDICTED, - - NR_REAL_INTEL_ARCH_EVENTS, - - /* - * Pseudo-architectural event used to implement IA32_FIXED_CTR2, a.k.a. - * TSC reference cycles. The architectural reference cycles event may - * or may not actually use the TSC as the reference, e.g. might use the - * core crystal clock or the bus clock (yeah, "architectural"). - */ - PSEUDO_ARCH_REFERENCE_CYCLES = NR_REAL_INTEL_ARCH_EVENTS, - NR_INTEL_ARCH_EVENTS, -}; +/* + * Perf's "BASE" is wildly misleading, architectural PMUs use bits 31:16 of ECX + * to encode the "type" of counter to read, i.e. this is not a "base". And to + * further confuse things, non-architectural PMUs use bit 31 as a flag for + * "fast" reads, whereas the "type" is an explicit value. + */ +#define INTEL_RDPMC_GP 0 +#define INTEL_RDPMC_FIXED INTEL_PMC_FIXED_RDPMC_BASE -static struct { - u8 eventsel; - u8 unit_mask; -} const intel_arch_events[] = { - [INTEL_ARCH_CPU_CYCLES] = { 0x3c, 0x00 }, - [INTEL_ARCH_INSTRUCTIONS_RETIRED] = { 0xc0, 0x00 }, - [INTEL_ARCH_REFERENCE_CYCLES] = { 0x3c, 0x01 }, - [INTEL_ARCH_LLC_REFERENCES] = { 0x2e, 0x4f }, - [INTEL_ARCH_LLC_MISSES] = { 0x2e, 0x41 }, - [INTEL_ARCH_BRANCHES_RETIRED] = { 0xc4, 0x00 }, - [INTEL_ARCH_BRANCHES_MISPREDICTED] = { 0xc5, 0x00 }, - [PSEUDO_ARCH_REFERENCE_CYCLES] = { 0x00, 0x03 }, -}; +#define INTEL_RDPMC_TYPE_MASK GENMASK(31, 16) +#define INTEL_RDPMC_INDEX_MASK GENMASK(15, 0) -/* mapping between fixed pmc index and intel_arch_events array */ -static int fixed_pmc_events[] = { - [0] = INTEL_ARCH_INSTRUCTIONS_RETIRED, - [1] = INTEL_ARCH_CPU_CYCLES, - [2] = PSEUDO_ARCH_REFERENCE_CYCLES, -}; +#define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { @@ -84,77 +50,61 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i); - __set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use); + __set_bit(KVM_FIXED_PMC_BASE_IDX + i, pmu->pmc_in_use); kvm_pmu_request_counter_reprogram(pmc); } } -static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) -{ - if (pmc_idx < INTEL_PMC_IDX_FIXED) { - return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + pmc_idx, - MSR_P6_EVNTSEL0); - } else { - u32 idx = pmc_idx - INTEL_PMC_IDX_FIXED; - - return get_fixed_pmc(pmu, idx + MSR_CORE_PERF_FIXED_CTR0); - } -} - -static bool intel_hw_event_available(struct kvm_pmc *pmc) -{ - struct kvm_pmu *pmu = pmc_to_pmu(pmc); - u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; - u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; - int i; - - BUILD_BUG_ON(ARRAY_SIZE(intel_arch_events) != NR_INTEL_ARCH_EVENTS); - - /* - * Disallow events reported as unavailable in guest CPUID. Note, this - * doesn't apply to pseudo-architectural events. - */ - for (i = 0; i < NR_REAL_INTEL_ARCH_EVENTS; i++) { - if (intel_arch_events[i].eventsel != event_select || - intel_arch_events[i].unit_mask != unit_mask) - continue; - - return pmu->available_event_types & BIT(i); - } - - return true; -} - -static bool intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fixed = idx & (1u << 30); - - idx &= ~(3u << 30); - - return fixed ? idx < pmu->nr_arch_fixed_counters - : idx < pmu->nr_arch_gp_counters; -} - static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask) { + unsigned int type = idx & INTEL_RDPMC_TYPE_MASK; struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fixed = idx & (1u << 30); struct kvm_pmc *counters; unsigned int num_counters; + u64 bitmask; + + /* + * The encoding of ECX for RDPMC is different for architectural versus + * non-architecturals PMUs (PMUs with version '0'). For architectural + * PMUs, bits 31:16 specify the PMC type and bits 15:0 specify the PMC + * index. For non-architectural PMUs, bit 31 is a "fast" flag, and + * bits 30:0 specify the PMC index. + * + * Yell and reject attempts to read PMCs for a non-architectural PMU, + * as KVM doesn't support such PMUs. + */ + if (WARN_ON_ONCE(!pmu->version)) + return NULL; - idx &= ~(3u << 30); - if (fixed) { + /* + * General Purpose (GP) PMCs are supported on all PMUs, and fixed PMCs + * are supported on all architectural PMUs, i.e. on all virtual PMUs + * supported by KVM. Note, KVM only emulates fixed PMCs for PMU v2+, + * but the type itself is still valid, i.e. let RDPMC fail due to + * accessing a non-existent counter. Reject attempts to read all other + * types, which are unknown/unsupported. + */ + switch (type) { + case INTEL_RDPMC_FIXED: counters = pmu->fixed_counters; num_counters = pmu->nr_arch_fixed_counters; - } else { + bitmask = pmu->counter_bitmask[KVM_PMC_FIXED]; + break; + case INTEL_RDPMC_GP: counters = pmu->gp_counters; num_counters = pmu->nr_arch_gp_counters; + bitmask = pmu->counter_bitmask[KVM_PMC_GP]; + break; + default: + return NULL; } + + idx &= INTEL_RDPMC_INDEX_MASK; if (idx >= num_counters) return NULL; - *mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP]; + + *mask &= bitmask; return &counters[array_index_nospec(idx, num_counters)]; } @@ -464,20 +414,38 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -static void setup_fixed_pmc_eventsel(struct kvm_pmu *pmu) +/* + * Map fixed counter events to architectural general purpose event encodings. + * Perf doesn't provide APIs to allow KVM to directly program a fixed counter, + * and so KVM instead programs the architectural event to effectively request + * the fixed counter. Perf isn't guaranteed to use a fixed counter and may + * instead program the encoding into a general purpose counter, e.g. if a + * different perf_event is already utilizing the requested counter, but the end + * result is the same (ignoring the fact that using a general purpose counter + * will likely exacerbate counter contention). + * + * Forcibly inlined to allow asserting on @index at build time, and there should + * never be more than one user. + */ +static __always_inline u64 intel_get_fixed_pmc_eventsel(unsigned int index) { - int i; - - BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_events) != KVM_PMC_MAX_FIXED); + const enum perf_hw_id fixed_pmc_perf_ids[] = { + [0] = PERF_COUNT_HW_INSTRUCTIONS, + [1] = PERF_COUNT_HW_CPU_CYCLES, + [2] = PERF_COUNT_HW_REF_CPU_CYCLES, + }; + u64 eventsel; - for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { - int index = array_index_nospec(i, KVM_PMC_MAX_FIXED); - struct kvm_pmc *pmc = &pmu->fixed_counters[index]; - u32 event = fixed_pmc_events[index]; + BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_perf_ids) != KVM_PMC_MAX_FIXED); + BUILD_BUG_ON(index >= KVM_PMC_MAX_FIXED); - pmc->eventsel = (intel_arch_events[event].unit_mask << 8) | - intel_arch_events[event].eventsel; - } + /* + * Yell if perf reports support for a fixed counter but perf doesn't + * have a known encoding for the associated general purpose event. + */ + eventsel = perf_get_hw_event_config(fixed_pmc_perf_ids[index]); + WARN_ON_ONCE(!eventsel && index < kvm_pmu_cap.num_counters_fixed); + return eventsel; } static void intel_pmu_refresh(struct kvm_vcpu *vcpu) @@ -531,13 +499,12 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) kvm_pmu_cap.bit_width_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; - setup_fixed_pmc_eventsel(pmu); } for (i = 0; i < pmu->nr_arch_fixed_counters; i++) pmu->fixed_ctr_ctrl_mask &= ~(0xbull << (i * 4)); counter_mask = ~(((1ull << pmu->nr_arch_gp_counters) - 1) | - (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED)); + (((1ull << pmu->nr_arch_fixed_counters) - 1) << KVM_FIXED_PMC_BASE_IDX)); pmu->global_ctrl_mask = counter_mask; /* @@ -568,7 +535,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) perf_capabilities = vcpu_get_perf_capabilities(vcpu); if (cpuid_model_is_consistent(vcpu) && (perf_capabilities & PMU_CAP_LBR_FMT)) - x86_perf_get_lbr(&lbr_desc->records); + memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps)); else lbr_desc->records.nr = 0; @@ -581,7 +548,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->reserved_bits &= ~ICL_EVENTSEL_ADAPTIVE; for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { pmu->fixed_ctr_ctrl_mask &= - ~(1ULL << (INTEL_PMC_IDX_FIXED + i * 4)); + ~(1ULL << (KVM_FIXED_PMC_BASE_IDX + i * 4)); } pmu->pebs_data_cfg_mask = ~0xff00000full; } else { @@ -607,8 +574,9 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) for (i = 0; i < KVM_PMC_MAX_FIXED; i++) { pmu->fixed_counters[i].type = KVM_PMC_FIXED; pmu->fixed_counters[i].vcpu = vcpu; - pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; + pmu->fixed_counters[i].idx = i + KVM_FIXED_PMC_BASE_IDX; pmu->fixed_counters[i].current_config = 0; + pmu->fixed_counters[i].eventsel = intel_get_fixed_pmc_eventsel(i); } lbr_desc->records.nr = 0; @@ -736,11 +704,8 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu) struct kvm_pmc *pmc = NULL; int bit, hw_idx; - for_each_set_bit(bit, (unsigned long *)&pmu->global_ctrl, - X86_PMC_IDX_MAX) { - pmc = intel_pmc_idx_to_pmc(pmu, bit); - - if (!pmc || !pmc_speculative_in_use(pmc) || + kvm_for_each_pmc(pmu, pmc, bit, (unsigned long *)&pmu->global_ctrl) { + if (!pmc_speculative_in_use(pmc) || !pmc_is_globally_enabled(pmc) || !pmc->perf_event) continue; @@ -755,11 +720,8 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu) } struct kvm_pmu_ops intel_pmu_ops __initdata = { - .hw_event_available = intel_hw_event_available, - .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, .rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = intel_msr_idx_to_pmc, - .is_valid_rdpmc_ecx = intel_is_valid_rdpmc_ecx, .is_valid_msr = intel_is_valid_msr, .get_msr = intel_pmu_get_msr, .set_msr = intel_pmu_set_msr, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 784f2ecca5..22411f4aff 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -38,6 +38,7 @@ #include <asm/desc.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> +#include <asm/fred.h> #include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> @@ -49,6 +50,8 @@ #include <asm/spec-ctrl.h> #include <asm/vmx.h> +#include <trace/events/ipi.h> + #include "capabilities.h" #include "cpuid.h" #include "hyperv.h" @@ -159,7 +162,7 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); /* * List of MSRs that can be directly passed to the guest. - * In addition to these x2apic and PT MSRs are handled specially. + * In addition to these x2apic, PT and LBR MSRs are handled specially. */ static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { MSR_IA32_SPEC_CTRL, @@ -215,6 +218,8 @@ module_param(ple_window_max, uint, 0444); int __read_mostly pt_mode = PT_MODE_SYSTEM; module_param(pt_mode, int, S_IRUGO); +struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; + static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); static DEFINE_MUTEX(vmx_l1d_flush_mutex); @@ -667,25 +672,14 @@ static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) return flexpriority_enabled && lapic_in_kernel(vcpu); } -static int possible_passthrough_msr_slot(u32 msr) -{ - u32 i; - - for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) - if (vmx_possible_passthrough_msrs[i] == msr) - return i; - - return -ENOENT; -} - -static bool is_valid_passthrough_msr(u32 msr) +static int vmx_get_passthrough_msr_slot(u32 msr) { - bool r; + int i; switch (msr) { case 0x800 ... 0x8ff: /* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */ - return true; + return -ENOENT; case MSR_IA32_RTIT_STATUS: case MSR_IA32_RTIT_OUTPUT_BASE: case MSR_IA32_RTIT_OUTPUT_MASK: @@ -700,14 +694,16 @@ static bool is_valid_passthrough_msr(u32 msr) case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8: case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8: /* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */ - return true; + return -ENOENT; } - r = possible_passthrough_msr_slot(msr) != -ENOENT; - - WARN(!r, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr); + for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) { + if (vmx_possible_passthrough_msrs[i] == msr) + return i; + } - return r; + WARN(1, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr); + return -ENOENT; } struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) @@ -1290,8 +1286,6 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) u16 fs_sel, gs_sel; int i; - vmx->req_immediate_exit = false; - /* * Note that guest MSRs to be saved/restored can also be changed * when guest state is loaded. This happens when guest transitions @@ -3963,6 +3957,7 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + int idx; if (!cpu_has_vmx_msr_bitmap()) return; @@ -3972,16 +3967,13 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) /* * Mark the desired intercept state in shadow bitmap, this is needed * for resync when the MSR filters change. - */ - if (is_valid_passthrough_msr(msr)) { - int idx = possible_passthrough_msr_slot(msr); - - if (idx != -ENOENT) { - if (type & MSR_TYPE_R) - clear_bit(idx, vmx->shadow_msr_intercept.read); - if (type & MSR_TYPE_W) - clear_bit(idx, vmx->shadow_msr_intercept.write); - } + */ + idx = vmx_get_passthrough_msr_slot(msr); + if (idx >= 0) { + if (type & MSR_TYPE_R) + clear_bit(idx, vmx->shadow_msr_intercept.read); + if (type & MSR_TYPE_W) + clear_bit(idx, vmx->shadow_msr_intercept.write); } if ((type & MSR_TYPE_R) && @@ -4007,6 +3999,7 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + int idx; if (!cpu_has_vmx_msr_bitmap()) return; @@ -4016,16 +4009,13 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) /* * Mark the desired intercept state in shadow bitmap, this is needed * for resync when the MSR filter changes. - */ - if (is_valid_passthrough_msr(msr)) { - int idx = possible_passthrough_msr_slot(msr); - - if (idx != -ENOENT) { - if (type & MSR_TYPE_R) - set_bit(idx, vmx->shadow_msr_intercept.read); - if (type & MSR_TYPE_W) - set_bit(idx, vmx->shadow_msr_intercept.write); - } + */ + idx = vmx_get_passthrough_msr_slot(msr); + if (idx >= 0) { + if (type & MSR_TYPE_R) + set_bit(idx, vmx->shadow_msr_intercept.read); + if (type & MSR_TYPE_W) + set_bit(idx, vmx->shadow_msr_intercept.write); } if (type & MSR_TYPE_R) @@ -4136,6 +4126,9 @@ static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 i; + if (!cpu_has_vmx_msr_bitmap()) + return; + /* * Redo intercept permissions for MSRs that KVM is passing through to * the guest. Disabling interception will check the new MSR filter and @@ -5575,10 +5568,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) reg = DEBUG_REG_ACCESS_REG(exit_qualification); if (exit_qualification & TYPE_MOV_FROM_DR) { - unsigned long val; - - kvm_get_dr(vcpu, dr, &val); - kvm_register_write(vcpu, reg, val); + kvm_register_write(vcpu, reg, kvm_get_dr(vcpu, dr)); err = 0; } else { err = kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)); @@ -6000,22 +5990,46 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) return 1; } -static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu) +static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx->req_immediate_exit && - !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) { - kvm_lapic_expired_hv_timer(vcpu); + /* + * In the *extremely* unlikely scenario that this is a spurious VM-Exit + * due to the timer expiring while it was "soft" disabled, just eat the + * exit and re-enter the guest. + */ + if (unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) return EXIT_FASTPATH_REENTER_GUEST; - } - return EXIT_FASTPATH_NONE; + /* + * If the timer expired because KVM used it to force an immediate exit, + * then mission accomplished. + */ + if (force_immediate_exit) + return EXIT_FASTPATH_EXIT_HANDLED; + + /* + * If L2 is active, go down the slow path as emulating the guest timer + * expiration likely requires synthesizing a nested VM-Exit. + */ + if (is_guest_mode(vcpu)) + return EXIT_FASTPATH_NONE; + + kvm_lapic_expired_hv_timer(vcpu); + return EXIT_FASTPATH_REENTER_GUEST; } static int handle_preemption_timer(struct kvm_vcpu *vcpu) { - handle_fastpath_preemption_timer(vcpu); + /* + * This non-fastpath handler is reached if and only if the preemption + * timer was being used to emulate a guest timer while L2 is active. + * All other scenarios are supposed to be handled in the fastpath. + */ + WARN_ON_ONCE(!is_guest_mode(vcpu)); + kvm_lapic_expired_hv_timer(vcpu); return 1; } @@ -6518,7 +6532,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; vcpu->run->internal.data[0] = vectoring_info; vcpu->run->internal.data[1] = exit_reason.full; - vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; + vcpu->run->internal.data[2] = vmx_get_exit_qual(vcpu); if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { vcpu->run->internal.data[ndata++] = vmcs_read64(GUEST_PHYSICAL_ADDRESS); @@ -6552,7 +6566,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (exit_reason.basic >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE if (exit_reason.basic == EXIT_REASON_MSR_WRITE) return kvm_emulate_wrmsr(vcpu); else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) @@ -6969,14 +6983,16 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) { u32 intr_info = vmx_get_intr_info(vcpu); unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; - gate_desc *desc = (gate_desc *)host_idt_base + vector; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); - vmx_do_interrupt_irqoff(gate_offset(desc)); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector); + else + vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector)); kvm_after_interrupt(vcpu); vcpu->arch.at_instruction_boundary = true; @@ -7155,13 +7171,13 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) +static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc; - if (vmx->req_immediate_exit) { + if (force_immediate_exit) { vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0); vmx->loaded_vmcs->hv_timer_soft_disabled = false; } else if (vmx->hv_deadline_tsc != -1) { @@ -7214,13 +7230,22 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, barrier_nospec(); } -static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) +static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { + /* + * If L2 is active, some VMX preemption timer exits can be handled in + * the fastpath even, all other exits must use the slow path. + */ + if (is_guest_mode(vcpu) && + to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_PREEMPTION_TIMER) + return EXIT_FASTPATH_NONE; + switch (to_vmx(vcpu)->exit_reason.basic) { case EXIT_REASON_MSR_WRITE: return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: - return handle_fastpath_preemption_timer(vcpu); + return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); default: return EXIT_FASTPATH_NONE; } @@ -7272,7 +7297,10 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI && is_nmi(vmx_get_intr_info(vcpu))) { kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); - vmx_do_nmi_irqoff(); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); + else + vmx_do_nmi_irqoff(); kvm_after_interrupt(vcpu); } @@ -7280,7 +7308,7 @@ out: guest_state_exit_irqoff(); } -static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) +static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; @@ -7307,7 +7335,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) return EXIT_FASTPATH_NONE; } - trace_kvm_entry(vcpu); + trace_kvm_entry(vcpu, force_immediate_exit); if (vmx->ple_window_dirty) { vmx->ple_window_dirty = false; @@ -7366,7 +7394,9 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_passthrough_lbr_msrs(vcpu); if (enable_preemption_timer) - vmx_update_hv_timer(vcpu); + vmx_update_hv_timer(vcpu, force_immediate_exit); + else if (force_immediate_exit) + smp_send_reschedule(vcpu->cpu); kvm_wait_lapic_expire(vcpu); @@ -7430,10 +7460,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); - if (is_guest_mode(vcpu)) - return EXIT_FASTPATH_NONE; - - return vmx_exit_handlers_fastpath(vcpu); + return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit); } static void vmx_vcpu_free(struct kvm_vcpu *vcpu) @@ -7837,10 +7864,9 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_update_exception_bitmap(vcpu); } -static u64 vmx_get_perf_capabilities(void) +static __init u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PMU_CAP_FW_WRITES; - struct x86_pmu_lbr lbr; u64 host_perf_cap = 0; if (!enable_pmu) @@ -7850,8 +7876,16 @@ static u64 vmx_get_perf_capabilities(void) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { - x86_perf_get_lbr(&lbr); - if (lbr.nr) + x86_perf_get_lbr(&vmx_lbr_caps); + + /* + * KVM requires LBR callstack support, as the overhead due to + * context switching LBRs without said support is too high. + * See intel_pmu_create_guest_lbr_event() for more info. + */ + if (!vmx_lbr_caps.has_callstack) + memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps)); + else if (vmx_lbr_caps.nr) perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; } @@ -7933,11 +7967,6 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); } -static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - to_vmx(vcpu)->req_immediate_exit = true; -} - static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, struct x86_instruction_info *info) { @@ -8390,8 +8419,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .check_intercept = vmx_check_intercept, .handle_exit_irqoff = vmx_handle_exit_irqoff, - .request_immediate_exit = vmx_request_immediate_exit, - .sched_in = vmx_sched_in, .cpu_dirty_log_size = PML_ENTITY_NUM, @@ -8651,7 +8678,6 @@ static __init int hardware_setup(void) if (!enable_preemption_timer) { vmx_x86_ops.set_hv_timer = NULL; vmx_x86_ops.cancel_hv_timer = NULL; - vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; } kvm_caps.supported_mce_cap |= MCG_LMCE_P; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index e3b0985bb7..90f9e44346 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -15,6 +15,7 @@ #include "vmx_ops.h" #include "../cpuid.h" #include "run_flags.h" +#include "../mmu.h" #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 @@ -109,6 +110,8 @@ struct lbr_desc { bool msr_passthrough; }; +extern struct x86_pmu_lbr vmx_lbr_caps; + /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -332,8 +335,6 @@ struct vcpu_vmx { unsigned int ple_window; bool ple_window_dirty; - bool req_immediate_exit; - /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; @@ -721,7 +722,8 @@ static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) if (!enable_ept) return true; - return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; + return allow_smaller_maxphyaddr && + cpuid_maxphyaddr(vcpu) < kvm_get_shadow_phys_bits(); } static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c84927216f..4dbd9d99f9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1399,22 +1399,19 @@ int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) } EXPORT_SYMBOL_GPL(kvm_set_dr); -void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr) { size_t size = ARRAY_SIZE(vcpu->arch.db); switch (dr) { case 0 ... 3: - *val = vcpu->arch.db[array_index_nospec(dr, size)]; - break; + return vcpu->arch.db[array_index_nospec(dr, size)]; case 4: case 6: - *val = vcpu->arch.dr6; - break; + return vcpu->arch.dr6; case 5: default: /* 7 */ - *val = vcpu->arch.dr7; - break; + return vcpu->arch.dr7; } } EXPORT_SYMBOL_GPL(kvm_get_dr); @@ -2860,7 +2857,11 @@ static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, return v * clock->mult; } -static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) +/* + * As with get_kvmclock_base_ns(), this counts from boot time, at the + * frequency of CLOCK_MONOTONIC_RAW (hence adding gtos->offs_boot). + */ +static int do_kvmclock_base(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -2879,6 +2880,29 @@ static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) return mode; } +/* + * This calculates CLOCK_MONOTONIC at the time of the TSC snapshot, with + * no boot time offset. + */ +static int do_monotonic(s64 *t, u64 *tsc_timestamp) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + unsigned long seq; + int mode; + u64 ns; + + do { + seq = read_seqcount_begin(>od->seq); + ns = gtod->clock.base_cycles; + ns += vgettsc(>od->clock, tsc_timestamp, &mode); + ns >>= gtod->clock.shift; + ns += ktime_to_ns(gtod->clock.offset); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + *t = ns; + + return mode; +} + static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; @@ -2900,18 +2924,42 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) return mode; } -/* returns true if host is using TSC based clocksource */ +/* + * Calculates the kvmclock_base_ns (CLOCK_MONOTONIC_RAW + boot time) and + * reports the TSC value from which it do so. Returns true if host is + * using TSC based clocksource. + */ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) { /* checked again under seqlock below */ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns, - tsc_timestamp)); + return gtod_is_based_on_tsc(do_kvmclock_base(kernel_ns, + tsc_timestamp)); +} + +/* + * Calculates CLOCK_MONOTONIC and reports the TSC value from which it did + * so. Returns true if host is using TSC based clocksource. + */ +bool kvm_get_monotonic_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) +{ + /* checked again under seqlock below */ + if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) + return false; + + return gtod_is_based_on_tsc(do_monotonic(kernel_ns, + tsc_timestamp)); } -/* returns true if host is using TSC based clocksource */ +/* + * Calculates CLOCK_REALTIME and reports the TSC value from which it did + * so. Returns true if host is using TSC based clocksource. + * + * DO NOT USE this for anything related to migration. You want CLOCK_TAI + * for that. + */ static bool kvm_get_walltime_and_clockread(struct timespec64 *ts, u64 *tsc_timestamp) { @@ -3158,7 +3206,7 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, guest_hv_clock->version = ++vcpu->hv_clock.version; - mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); + kvm_gpc_mark_dirty_in_slot(gpc); read_unlock_irqrestore(&gpc->lock, flags); trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); @@ -4680,7 +4728,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | KVM_XEN_HVM_CONFIG_EVTCHN_SEND | - KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE | + KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; @@ -5064,8 +5113,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) int idx; if (vcpu->preempted) { - if (!vcpu->arch.guest_state_protected) - vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); + vcpu->arch.preempted_in_kernel = kvm_arch_vcpu_in_kernel(vcpu); /* * Take the srcu lock as memslots will be accessed to check the gfn @@ -5512,18 +5560,23 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { - unsigned long val; + unsigned int i; memset(dbgregs, 0, sizeof(*dbgregs)); - memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); - kvm_get_dr(vcpu, 6, &val); - dbgregs->dr6 = val; + + BUILD_BUG_ON(ARRAY_SIZE(vcpu->arch.db) != ARRAY_SIZE(dbgregs->db)); + for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) + dbgregs->db[i] = vcpu->arch.db[i]; + + dbgregs->dr6 = vcpu->arch.dr6; dbgregs->dr7 = vcpu->arch.dr7; } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { + unsigned int i; + if (dbgregs->flags) return -EINVAL; @@ -5532,7 +5585,9 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, if (!kvm_dr7_valid(dbgregs->dr7)) return -EINVAL; - memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) + vcpu->arch.db[i] = dbgregs->db[i]; + kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; vcpu->arch.dr7 = dbgregs->dr7; @@ -8180,10 +8235,9 @@ static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -static void emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long *dest) +static unsigned long emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr) { - kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); + return kvm_get_dr(emul_to_vcpu(ctxt), dr); } static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, @@ -8405,12 +8459,9 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); } -static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, - u32 pmc) +static int emulator_check_rdpmc_early(struct x86_emulate_ctxt *ctxt, u32 pmc) { - if (kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc)) - return 0; - return -EINVAL; + return kvm_pmu_check_rdpmc_early(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -8542,7 +8593,7 @@ static const struct x86_emulate_ops emulate_ops = { .set_msr_with_filter = emulator_set_msr_with_filter, .get_msr_with_filter = emulator_get_msr_with_filter, .get_msr = emulator_get_msr, - .check_pmc = emulator_check_pmc, + .check_rdpmc_early = emulator_check_rdpmc_early, .read_pmc = emulator_read_pmc, .halt = emulator_halt, .wbinvd = emulator_wbinvd, @@ -8803,31 +8854,24 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_release_pfn_clean(pfn); - /* The instructions are well-emulated on direct mmu. */ - if (vcpu->arch.mmu->root_role.direct) { - unsigned int indirect_shadow_pages; - - write_lock(&vcpu->kvm->mmu_lock); - indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; - write_unlock(&vcpu->kvm->mmu_lock); - - if (indirect_shadow_pages) - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); - - return true; - } - /* - * if emulation was due to access to shadowed page table - * and it failed try to unshadow page and re-enter the - * guest to let CPU execute the instruction. + * If emulation may have been triggered by a write to a shadowed page + * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the + * guest to let the CPU re-execute the instruction in the hope that the + * CPU can cleanly execute the instruction that KVM failed to emulate. */ - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + if (vcpu->kvm->arch.indirect_shadow_pages) + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); /* - * If the access faults on its page table, it can not - * be fixed by unprotecting shadow page and it should - * be reported to userspace. + * If the failed instruction faulted on an access to page tables that + * are used to translate any part of the instruction, KVM can't resolve + * the issue by unprotecting the gfn, as zapping the shadow page will + * result in the instruction taking a !PRESENT page fault and thus put + * the vCPU into an infinite loop of page faults. E.g. KVM will create + * a SPTE and write-protect the gfn to resolve the !PRESENT fault, and + * then zap the SPTE to unprotect the gfn, and then do it all over + * again. Report the error to userspace. */ return !(emulation_type & EMULTYPE_WRITE_PF_TO_SP); } @@ -8922,7 +8966,7 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) if (unlikely(!r)) return 0; - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED); /* * rflags is the old, "raw" value of the flags. The new value has @@ -9235,9 +9279,9 @@ writeback: */ if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED); if (ctxt->is_branch) - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); + kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED); kvm_rip_write(vcpu, ctxt->eip); if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) r = kvm_vcpu_do_singlestep(vcpu); @@ -9648,11 +9692,13 @@ static void kvm_x86_check_cpu_compat(void *ret) *(int *)ret = kvm_x86_check_processor_compatibility(); } -static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { u64 host_pat; int r, cpu; + guard(mutex)(&vendor_module_lock); + if (kvm_x86_ops.hardware_enable) { pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; @@ -9782,17 +9828,6 @@ out_free_x86_emulator_cache: kmem_cache_destroy(x86_emulator_cache); return r; } - -int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) -{ - int r; - - mutex_lock(&vendor_module_lock); - r = __kvm_x86_vendor_init(ops); - mutex_unlock(&vendor_module_lock); - - return r; -} EXPORT_SYMBOL_GPL(kvm_x86_vendor_init); void kvm_x86_vendor_exit(void) @@ -10642,13 +10677,12 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); + if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); - else { - static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); - if (ioapic_in_kernel(vcpu->kvm)) - kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); - } + else if (ioapic_in_kernel(vcpu->kvm)) + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); if (is_guest_mode(vcpu)) vcpu->arch.load_eoi_exitmap_pending = true; @@ -10689,12 +10723,6 @@ static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) static_call_cond(kvm_x86_set_apic_access_page_addr)(vcpu); } -void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - smp_send_reschedule(vcpu->cpu); -} -EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); - /* * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without @@ -10944,10 +10972,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - if (req_immediate_exit) { + if (req_immediate_exit) kvm_make_request(KVM_REQ_EVENT, vcpu); - static_call(kvm_x86_request_immediate_exit)(vcpu); - } fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) @@ -10978,7 +11004,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED)); - exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu); + exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu, req_immediate_exit); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; @@ -12065,7 +12091,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; - kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm, vcpu, KVM_HOST_USES_PFN); + kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm); if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -12076,27 +12102,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (r < 0) return r; - if (irqchip_in_kernel(vcpu->kvm)) { - r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); - if (r < 0) - goto fail_mmu_destroy; - - /* - * Defer evaluating inhibits until the vCPU is first run, as - * this vCPU will not get notified of any changes until this - * vCPU is visible to other vCPUs (marked online and added to - * the set of vCPUs). Opportunistically mark APICv active as - * VMX in particularly is highly unlikely to have inhibits. - * Ignore the current per-VM APICv state so that vCPU creation - * is guaranteed to run with a deterministic value, the request - * will ensure the vCPU gets the correct state before VM-Entry. - */ - if (enable_apicv) { - vcpu->arch.apic->apicv_active = true; - kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); - } - } else - static_branch_inc(&kvm_has_noapic_vcpu); + r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); + if (r < 0) + goto fail_mmu_destroy; r = -ENOMEM; @@ -12217,8 +12225,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); kvfree(vcpu->arch.cpuid_entries); - if (!lapic_in_kernel(vcpu)) - static_branch_dec(&kvm_has_noapic_vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -12495,9 +12501,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; } -__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); -EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu); - void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -13100,11 +13103,13 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_apicv_active(vcpu) && - static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu)) - return true; + return kvm_vcpu_apicv_active(vcpu) && + static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu); +} - return false; +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.preempted_in_kernel; } bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) @@ -13127,9 +13132,6 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_state_protected) return true; - if (vcpu != kvm_get_running_vcpu()) - return vcpu->arch.preempted_in_kernel; - return static_call(kvm_x86_get_cpl)(vcpu) == 0; } @@ -13924,9 +13926,6 @@ module_init(kvm_x86_init); static void __exit kvm_x86_exit(void) { - /* - * If module_init() is implemented, module_exit() must also be - * implemented to allow module unload. - */ + WARN_ON_ONCE(static_branch_unlikely(&kvm_has_noapic_vcpu)); } module_exit(kvm_x86_exit); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 2f7e191666..a8b7180377 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -294,6 +294,7 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); u64 get_kvmclock_ns(struct kvm *kvm); uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm); +bool kvm_get_monotonic_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp); int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, @@ -431,12 +432,6 @@ static inline bool kvm_notify_vmexit_enabled(struct kvm *kvm) return kvm->arch.notify_vmexit_flags & KVM_X86_NOTIFY_VMEXIT_ENABLED; } -enum kvm_intr_type { - /* Values are arbitrary, but must be non-zero. */ - KVM_HANDLING_IRQ = 1, - KVM_HANDLING_NMI, -}; - static __always_inline void kvm_before_interrupt(struct kvm_vcpu *vcpu, enum kvm_intr_type intr) { diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index b0212ba2d8..f65b35a05d 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -10,7 +10,7 @@ #include "x86.h" #include "xen.h" #include "hyperv.h" -#include "lapic.h" +#include "irq.h" #include <linux/eventfd.h> #include <linux/kvm_host.h> @@ -24,6 +24,7 @@ #include <xen/interface/sched.h> #include <asm/xen/cpuid.h> +#include <asm/pvclock.h> #include "cpuid.h" #include "trace.h" @@ -34,41 +35,32 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r); DEFINE_STATIC_KEY_DEFERRED_FALSE(kvm_xen_enabled, HZ); -static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) +static int kvm_xen_shared_info_init(struct kvm *kvm) { struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache; struct pvclock_wall_clock *wc; - gpa_t gpa = gfn_to_gpa(gfn); u32 *wc_sec_hi; u32 wc_version; u64 wall_nsec; int ret = 0; int idx = srcu_read_lock(&kvm->srcu); - if (gfn == KVM_XEN_INVALID_GFN) { - kvm_gpc_deactivate(gpc); - goto out; - } + read_lock_irq(&gpc->lock); + while (!kvm_gpc_check(gpc, PAGE_SIZE)) { + read_unlock_irq(&gpc->lock); - do { - ret = kvm_gpc_activate(gpc, gpa, PAGE_SIZE); + ret = kvm_gpc_refresh(gpc, PAGE_SIZE); if (ret) goto out; - /* - * This code mirrors kvm_write_wall_clock() except that it writes - * directly through the pfn cache and doesn't mark the page dirty. - */ - wall_nsec = kvm_get_wall_clock_epoch(kvm); - - /* It could be invalid again already, so we need to check */ read_lock_irq(&gpc->lock); + } - if (gpc->valid) - break; - - read_unlock_irq(&gpc->lock); - } while (1); + /* + * This code mirrors kvm_write_wall_clock() except that it writes + * directly through the pfn cache and doesn't mark the page dirty. + */ + wall_nsec = kvm_get_wall_clock_epoch(kvm); /* Paranoia checks on the 32-bit struct layout */ BUILD_BUG_ON(offsetof(struct compat_shared_info, wc) != 0x900); @@ -158,8 +150,93 @@ static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer) return HRTIMER_NORESTART; } -static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, s64 delta_ns) +static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, + bool linux_wa) { + int64_t kernel_now, delta; + uint64_t guest_now; + + /* + * The guest provides the requested timeout in absolute nanoseconds + * of the KVM clock — as *it* sees it, based on the scaled TSC and + * the pvclock information provided by KVM. + * + * The kernel doesn't support hrtimers based on CLOCK_MONOTONIC_RAW + * so use CLOCK_MONOTONIC. In the timescales covered by timers, the + * difference won't matter much as there is no cumulative effect. + * + * Calculate the time for some arbitrary point in time around "now" + * in terms of both kvmclock and CLOCK_MONOTONIC. Calculate the + * delta between the kvmclock "now" value and the guest's requested + * timeout, apply the "Linux workaround" described below, and add + * the resulting delta to the CLOCK_MONOTONIC "now" value, to get + * the absolute CLOCK_MONOTONIC time at which the timer should + * fire. + */ + if (vcpu->arch.hv_clock.version && vcpu->kvm->arch.use_master_clock && + static_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + uint64_t host_tsc, guest_tsc; + + if (!IS_ENABLED(CONFIG_64BIT) || + !kvm_get_monotonic_and_clockread(&kernel_now, &host_tsc)) { + /* + * Don't fall back to get_kvmclock_ns() because it's + * broken; it has a systemic error in its results + * because it scales directly from host TSC to + * nanoseconds, and doesn't scale first to guest TSC + * and *then* to nanoseconds as the guest does. + * + * There is a small error introduced here because time + * continues to elapse between the ktime_get() and the + * subsequent rdtsc(). But not the systemic drift due + * to get_kvmclock_ns(). + */ + kernel_now = ktime_get(); /* This is CLOCK_MONOTONIC */ + host_tsc = rdtsc(); + } + + /* Calculate the guest kvmclock as the guest would do it. */ + guest_tsc = kvm_read_l1_tsc(vcpu, host_tsc); + guest_now = __pvclock_read_cycles(&vcpu->arch.hv_clock, + guest_tsc); + } else { + /* + * Without CONSTANT_TSC, get_kvmclock_ns() is the only option. + * + * Also if the guest PV clock hasn't been set up yet, as is + * likely to be the case during migration when the vCPU has + * not been run yet. It would be possible to calculate the + * scaling factors properly in that case but there's not much + * point in doing so. The get_kvmclock_ns() drift accumulates + * over time, so it's OK to use it at startup. Besides, on + * migration there's going to be a little bit of skew in the + * precise moment at which timers fire anyway. Often they'll + * be in the "past" by the time the VM is running again after + * migration. + */ + guest_now = get_kvmclock_ns(vcpu->kvm); + kernel_now = ktime_get(); + } + + delta = guest_abs - guest_now; + + /* + * Xen has a 'Linux workaround' in do_set_timer_op() which checks for + * negative absolute timeout values (caused by integer overflow), and + * for values about 13 days in the future (2^50ns) which would be + * caused by jiffies overflow. For those cases, Xen sets the timeout + * 100ms in the future (not *too* soon, since if a guest really did + * set a long timeout on purpose we don't want to keep churning CPU + * time by waking it up). Emulate Xen's workaround when starting the + * timer in response to __HYPERVISOR_set_timer_op. + */ + if (linux_wa && + unlikely((int64_t)guest_abs < 0 || + (delta > 0 && (uint32_t) (delta >> 50) != 0))) { + delta = 100 * NSEC_PER_MSEC; + guest_abs = guest_now + delta; + } + /* * Avoid races with the old timer firing. Checking timer_expires * to avoid calling hrtimer_cancel() will only have false positives @@ -171,14 +248,12 @@ static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, s64 delta_ atomic_set(&vcpu->arch.xen.timer_pending, 0); vcpu->arch.xen.timer_expires = guest_abs; - if (delta_ns <= 0) { + if (delta <= 0) xen_timer_callback(&vcpu->arch.xen.timer); - } else { - ktime_t ktime_now = ktime_get(); + else hrtimer_start(&vcpu->arch.xen.timer, - ktime_add_ns(ktime_now, delta_ns), + ktime_add_ns(kernel_now, delta), HRTIMER_MODE_ABS_HARD); - } } static void kvm_xen_stop_timer(struct kvm_vcpu *vcpu) @@ -452,14 +527,13 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) smp_wmb(); } - if (user_len2) + if (user_len2) { + kvm_gpc_mark_dirty_in_slot(gpc2); read_unlock(&gpc2->lock); + } + kvm_gpc_mark_dirty_in_slot(gpc1); read_unlock_irqrestore(&gpc1->lock, flags); - - mark_page_dirty_in_slot(v->kvm, gpc1->memslot, gpc1->gpa >> PAGE_SHIFT); - if (user_len2) - mark_page_dirty_in_slot(v->kvm, gpc2->memslot, gpc2->gpa >> PAGE_SHIFT); } void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) @@ -496,7 +570,6 @@ void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) { struct kvm_lapic_irq irq = { }; - int r; irq.dest_id = v->vcpu_id; irq.vector = v->arch.xen.upcall_vector; @@ -505,8 +578,7 @@ void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) irq.delivery_mode = APIC_DM_FIXED; irq.level = 1; - /* The fast version will always work for physical unicast */ - WARN_ON_ONCE(!kvm_irq_delivery_to_apic_fast(v->kvm, NULL, &irq, &r, NULL)); + kvm_irq_delivery_to_apic(v->kvm, NULL, &irq, NULL); } /* @@ -565,13 +637,13 @@ void kvm_xen_inject_pending_events(struct kvm_vcpu *v) : "0" (evtchn_pending_sel32)); WRITE_ONCE(vi->evtchn_upcall_pending, 1); } + + kvm_gpc_mark_dirty_in_slot(gpc); read_unlock_irqrestore(&gpc->lock, flags); /* For the per-vCPU lapic vector, deliver it as MSI. */ if (v->arch.xen.upcall_vector) kvm_xen_inject_vcpu_vector(v); - - mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); } int __kvm_xen_has_interrupt(struct kvm_vcpu *v) @@ -635,17 +707,59 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) } else { mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.long_mode = !!data->u.long_mode; + + /* + * Re-initialize shared_info to put the wallclock in the + * correct place. Whilst it's not necessary to do this + * unless the mode is actually changed, it does no harm + * to make the call anyway. + */ + r = kvm->arch.xen.shinfo_cache.active ? + kvm_xen_shared_info_init(kvm) : 0; mutex_unlock(&kvm->arch.xen.xen_lock); - r = 0; } break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: + case KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA: { + int idx; + mutex_lock(&kvm->arch.xen.xen_lock); - r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn); + + idx = srcu_read_lock(&kvm->srcu); + + if (data->type == KVM_XEN_ATTR_TYPE_SHARED_INFO) { + gfn_t gfn = data->u.shared_info.gfn; + + if (gfn == KVM_XEN_INVALID_GFN) { + kvm_gpc_deactivate(&kvm->arch.xen.shinfo_cache); + r = 0; + } else { + r = kvm_gpc_activate(&kvm->arch.xen.shinfo_cache, + gfn_to_gpa(gfn), PAGE_SIZE); + } + } else { + void __user * hva = u64_to_user_ptr(data->u.shared_info.hva); + + if (!PAGE_ALIGNED(hva) || !access_ok(hva, PAGE_SIZE)) { + r = -EINVAL; + } else if (!hva) { + kvm_gpc_deactivate(&kvm->arch.xen.shinfo_cache); + r = 0; + } else { + r = kvm_gpc_activate_hva(&kvm->arch.xen.shinfo_cache, + (unsigned long)hva, PAGE_SIZE); + } + } + + srcu_read_unlock(&kvm->srcu, idx); + + if (!r && kvm->arch.xen.shinfo_cache.active) + r = kvm_xen_shared_info_init(kvm); + mutex_unlock(&kvm->arch.xen.xen_lock); break; - + } case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: if (data->u.vector && data->u.vector < 0x10) r = -EINVAL; @@ -699,13 +813,21 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - if (kvm->arch.xen.shinfo_cache.active) + if (kvm_gpc_is_gpa_active(&kvm->arch.xen.shinfo_cache)) data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa); else data->u.shared_info.gfn = KVM_XEN_INVALID_GFN; r = 0; break; + case KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA: + if (kvm_gpc_is_hva_active(&kvm->arch.xen.shinfo_cache)) + data->u.shared_info.hva = kvm->arch.xen.shinfo_cache.uhva; + else + data->u.shared_info.hva = 0; + r = 0; + break; + case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: data->u.vector = kvm->arch.xen.upcall_vector; r = 0; @@ -742,20 +864,33 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) switch (data->type) { case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA: /* No compat necessary here. */ BUILD_BUG_ON(sizeof(struct vcpu_info) != sizeof(struct compat_vcpu_info)); BUILD_BUG_ON(offsetof(struct vcpu_info, time) != offsetof(struct compat_vcpu_info, time)); - if (data->u.gpa == KVM_XEN_INVALID_GPA) { - kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); - r = 0; - break; + if (data->type == KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { + kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); + r = 0; + break; + } + + r = kvm_gpc_activate(&vcpu->arch.xen.vcpu_info_cache, + data->u.gpa, sizeof(struct vcpu_info)); + } else { + if (data->u.hva == 0) { + kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); + r = 0; + break; + } + + r = kvm_gpc_activate_hva(&vcpu->arch.xen.vcpu_info_cache, + data->u.hva, sizeof(struct vcpu_info)); } - r = kvm_gpc_activate(&vcpu->arch.xen.vcpu_info_cache, - data->u.gpa, sizeof(struct vcpu_info)); if (!r) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -944,9 +1079,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) /* Start the timer if the new value has a valid vector+expiry. */ if (data->u.timer.port && data->u.timer.expires_ns) - kvm_xen_start_timer(vcpu, data->u.timer.expires_ns, - data->u.timer.expires_ns - - get_kvmclock_ns(vcpu->kvm)); + kvm_xen_start_timer(vcpu, data->u.timer.expires_ns, false); r = 0; break; @@ -977,13 +1110,21 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) switch (data->type) { case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: - if (vcpu->arch.xen.vcpu_info_cache.active) + if (kvm_gpc_is_gpa_active(&vcpu->arch.xen.vcpu_info_cache)) data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa; else data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA: + if (kvm_gpc_is_hva_active(&vcpu->arch.xen.vcpu_info_cache)) + data->u.hva = vcpu->arch.xen.vcpu_info_cache.uhva; + else + data->u.hva = 0; + r = 0; + break; + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: if (vcpu->arch.xen.vcpu_time_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa; @@ -1093,9 +1234,24 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) u32 page_num = data & ~PAGE_MASK; u64 page_addr = data & PAGE_MASK; bool lm = is_long_mode(vcpu); + int r = 0; + + mutex_lock(&kvm->arch.xen.xen_lock); + if (kvm->arch.xen.long_mode != lm) { + kvm->arch.xen.long_mode = lm; + + /* + * Re-initialize shared_info to put the wallclock in the + * correct place. + */ + if (kvm->arch.xen.shinfo_cache.active && + kvm_xen_shared_info_init(kvm)) + r = 1; + } + mutex_unlock(&kvm->arch.xen.xen_lock); - /* Latch long_mode for shared_info pages etc. */ - vcpu->kvm->arch.xen.long_mode = lm; + if (r) + return r; /* * If Xen hypercall intercept is enabled, fill the hypercall @@ -1396,7 +1552,6 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, { struct vcpu_set_singleshot_timer oneshot; struct x86_exception e; - s64 delta; if (!kvm_xen_timer_enabled(vcpu)) return false; @@ -1430,9 +1585,7 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, return true; } - /* A delta <= 0 results in an immediate callback, which is what we want */ - delta = oneshot.timeout_abs_ns - get_kvmclock_ns(vcpu->kvm); - kvm_xen_start_timer(vcpu, oneshot.timeout_abs_ns, delta); + kvm_xen_start_timer(vcpu, oneshot.timeout_abs_ns, false); *r = 0; return true; @@ -1455,29 +1608,10 @@ static bool kvm_xen_hcall_set_timer_op(struct kvm_vcpu *vcpu, uint64_t timeout, if (!kvm_xen_timer_enabled(vcpu)) return false; - if (timeout) { - uint64_t guest_now = get_kvmclock_ns(vcpu->kvm); - int64_t delta = timeout - guest_now; - - /* Xen has a 'Linux workaround' in do_set_timer_op() which - * checks for negative absolute timeout values (caused by - * integer overflow), and for values about 13 days in the - * future (2^50ns) which would be caused by jiffies - * overflow. For those cases, it sets the timeout 100ms in - * the future (not *too* soon, since if a guest really did - * set a long timeout on purpose we don't want to keep - * churning CPU time by waking it up). - */ - if (unlikely((int64_t)timeout < 0 || - (delta > 0 && (uint32_t) (delta >> 50) != 0))) { - delta = 100 * NSEC_PER_MSEC; - timeout = guest_now + delta; - } - - kvm_xen_start_timer(vcpu, timeout, delta); - } else { + if (timeout) + kvm_xen_start_timer(vcpu, timeout, true); + else kvm_xen_stop_timer(vcpu); - } *r = 0; return true; @@ -1621,9 +1755,6 @@ int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe, struct kvm *kvm) WRITE_ONCE(xe->vcpu_idx, vcpu->vcpu_idx); } - if (!vcpu->arch.xen.vcpu_info_cache.active) - return -EINVAL; - if (xe->port >= max_evtchn_port(kvm)) return -EINVAL; @@ -1731,8 +1862,6 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) mm_borrowed = true; } - mutex_lock(&kvm->arch.xen.xen_lock); - /* * It is theoretically possible for the page to be unmapped * and the MMU notifier to invalidate the shared_info before @@ -1760,8 +1889,6 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) srcu_read_unlock(&kvm->srcu, idx); } while(!rc); - mutex_unlock(&kvm->arch.xen.xen_lock); - if (mm_borrowed) kthread_unuse_mm(kvm->mm); @@ -2109,14 +2236,10 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu) timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0); - kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm, NULL, - KVM_HOST_USES_PFN); - kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm, NULL, - KVM_HOST_USES_PFN); - kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache, vcpu->kvm, NULL, - KVM_HOST_USES_PFN); - kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache, vcpu->kvm, NULL, - KVM_HOST_USES_PFN); + kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm); + kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm); + kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache, vcpu->kvm); + kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache, vcpu->kvm); } void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) @@ -2159,7 +2282,7 @@ void kvm_xen_init_vm(struct kvm *kvm) { mutex_init(&kvm->arch.xen.xen_lock); idr_init(&kvm->arch.xen.evtchn_ports); - kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN); + kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm); } void kvm_xen_destroy_vm(struct kvm *kvm) |