diff options
48 files changed, 528 insertions, 346 deletions
diff --git a/Documentation/virt/kvm/mmu.txt b/Documentation/virt/kvm/mmu.txt index 1b9880dfba0a..dadb29e8738f 100644 --- a/Documentation/virt/kvm/mmu.txt +++ b/Documentation/virt/kvm/mmu.txt @@ -294,7 +294,7 @@ Handling a page fault is performed as follows: - walk shadow page table - check for valid generation number in the spte (see "Fast invalidation of MMIO sptes" below) - - cache the information to vcpu->arch.mmio_gva, vcpu->arch.access and + - cache the information to vcpu->arch.mmio_gva, vcpu->arch.mmio_access and vcpu->arch.mmio_gfn, and call the emulator - If both P bit and R/W bit of error code are set, this could possibly be handled as a "fast page fault" (fixed without taking the MMU lock). See @@ -304,7 +304,7 @@ Handling a page fault is performed as follows: - if permissions are insufficient, reflect the fault back to the guest - determine the host page - if this is an mmio request, there is no host page; cache the info to - vcpu->arch.mmio_gva, vcpu->arch.access and vcpu->arch.mmio_gfn + vcpu->arch.mmio_gva, vcpu->arch.mmio_access and vcpu->arch.mmio_gfn - walk the shadow page table to find the spte for the translation, instantiating missing intermediate page tables as necessary - If this is an mmio request, cache the mmio info to the spte and set some diff --git a/MAINTAINERS b/MAINTAINERS index 6426db5198f0..1dd30ccf5136 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8819,14 +8819,6 @@ F: virt/kvm/* F: tools/kvm/ F: tools/testing/selftests/kvm/ -KERNEL VIRTUAL MACHINE FOR AMD-V (KVM/amd) -M: Joerg Roedel <joro@8bytes.org> -L: kvm@vger.kernel.org -W: http://www.linux-kvm.org/ -S: Maintained -F: arch/x86/include/asm/svm.h -F: arch/x86/kvm/svm.c - KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64) M: Marc Zyngier <maz@kernel.org> R: James Morse <james.morse@arm.com> @@ -8869,7 +8861,7 @@ M: Christian Borntraeger <borntraeger@de.ibm.com> M: Janosch Frank <frankja@linux.ibm.com> R: David Hildenbrand <david@redhat.com> R: Cornelia Huck <cohuck@redhat.com> -L: linux-s390@vger.kernel.org +L: kvm@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git S: Supported @@ -8884,6 +8876,11 @@ F: tools/testing/selftests/kvm/*/s390x/ KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86) M: Paolo Bonzini <pbonzini@redhat.com> M: Radim Krčmář <rkrcmar@redhat.com> +R: Sean Christopherson <sean.j.christopherson@intel.com> +R: Vitaly Kuznetsov <vkuznets@redhat.com> +R: Wanpeng Li <wanpengli@tencent.com> +R: Jim Mattson <jmattson@google.com> +R: Joerg Roedel <joro@8bytes.org> L: kvm@vger.kernel.org W: http://www.linux-kvm.org T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git @@ -8891,8 +8888,12 @@ S: Supported F: arch/x86/kvm/ F: arch/x86/kvm/*/ F: arch/x86/include/uapi/asm/kvm* +F: arch/x86/include/uapi/asm/vmx.h +F: arch/x86/include/uapi/asm/svm.h F: arch/x86/include/asm/kvm* F: arch/x86/include/asm/pvclock-abi.h +F: arch/x86/include/asm/svm.h +F: arch/x86/include/asm/vmx.h F: arch/x86/kernel/kvm.c F: arch/x86/kernel/kvmclock.c diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index d2806bcff8bb..07745ee022a1 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -651,13 +651,22 @@ int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run) } static void reset_coproc_regs(struct kvm_vcpu *vcpu, - const struct coproc_reg *table, size_t num) + const struct coproc_reg *table, size_t num, + unsigned long *bmap) { unsigned long i; for (i = 0; i < num; i++) - if (table[i].reset) + if (table[i].reset) { + int reg = table[i].reg; + table[i].reset(vcpu, &table[i]); + if (reg > 0 && reg < NR_CP15_REGS) { + set_bit(reg, bmap); + if (table[i].is_64bit) + set_bit(reg + 1, bmap); + } + } } static struct coproc_params decode_32bit_hsr(struct kvm_vcpu *vcpu) @@ -1432,17 +1441,15 @@ void kvm_reset_coprocs(struct kvm_vcpu *vcpu) { size_t num; const struct coproc_reg *table; - - /* Catch someone adding a register without putting in reset entry. */ - memset(vcpu->arch.ctxt.cp15, 0x42, sizeof(vcpu->arch.ctxt.cp15)); + DECLARE_BITMAP(bmap, NR_CP15_REGS) = { 0, }; /* Generic chip reset first (so target could override). */ - reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs)); + reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs), bmap); table = get_target_table(vcpu->arch.target, &num); - reset_coproc_regs(vcpu, table, num); + reset_coproc_regs(vcpu, table, num, bmap); for (num = 1; num < NR_CP15_REGS; num++) - WARN(vcpu_cp15(vcpu, num) == 0x42424242, + WARN(!test_bit(num, bmap), "Didn't reset vcpu_cp15(vcpu, %zi)", num); } diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index a8b205e5c4a8..ddf9d762ac62 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -316,9 +316,10 @@ #define kvm_arm_exception_class \ ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \ - ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(CP14_64), ECN(SVC64), \ - ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(IMP_DEF), ECN(IABT_LOW), \ - ECN(IABT_CUR), ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \ + ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(PAC), ECN(CP14_64), \ + ECN(SVC64), ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(SVE), \ + ECN(IMP_DEF), ECN(IABT_LOW), ECN(IABT_CUR), \ + ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \ ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \ ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \ ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index d3313797cca9..32893b3d9164 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -733,6 +733,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_CP14_LS] = "CP14 LDC/STC", [ESR_ELx_EC_FP_ASIMD] = "ASIMD", [ESR_ELx_EC_CP10_ID] = "CP10 MRC/VMRS", + [ESR_ELx_EC_PAC] = "PAC", [ESR_ELx_EC_CP14_64] = "CP14 MCRR/MRRC", [ESR_ELx_EC_ILL] = "PSTATE.IL", [ESR_ELx_EC_SVC32] = "SVC (AArch32)", diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c index 26781da3ad3e..0fc9872a1467 100644 --- a/arch/arm64/kvm/hyp/debug-sr.c +++ b/arch/arm64/kvm/hyp/debug-sr.c @@ -18,40 +18,70 @@ #define save_debug(ptr,reg,nr) \ switch (nr) { \ case 15: ptr[15] = read_debug(reg, 15); \ + /* Fall through */ \ case 14: ptr[14] = read_debug(reg, 14); \ + /* Fall through */ \ case 13: ptr[13] = read_debug(reg, 13); \ + /* Fall through */ \ case 12: ptr[12] = read_debug(reg, 12); \ + /* Fall through */ \ case 11: ptr[11] = read_debug(reg, 11); \ + /* Fall through */ \ case 10: ptr[10] = read_debug(reg, 10); \ + /* Fall through */ \ case 9: ptr[9] = read_debug(reg, 9); \ + /* Fall through */ \ case 8: ptr[8] = read_debug(reg, 8); \ + /* Fall through */ \ case 7: ptr[7] = read_debug(reg, 7); \ + /* Fall through */ \ case 6: ptr[6] = read_debug(reg, 6); \ + /* Fall through */ \ case 5: ptr[5] = read_debug(reg, 5); \ + /* Fall through */ \ case 4: ptr[4] = read_debug(reg, 4); \ + /* Fall through */ \ case 3: ptr[3] = read_debug(reg, 3); \ + /* Fall through */ \ case 2: ptr[2] = read_debug(reg, 2); \ + /* Fall through */ \ case 1: ptr[1] = read_debug(reg, 1); \ + /* Fall through */ \ default: ptr[0] = read_debug(reg, 0); \ } #define restore_debug(ptr,reg,nr) \ switch (nr) { \ case 15: write_debug(ptr[15], reg, 15); \ + /* Fall through */ \ case 14: write_debug(ptr[14], reg, 14); \ + /* Fall through */ \ case 13: write_debug(ptr[13], reg, 13); \ + /* Fall through */ \ case 12: write_debug(ptr[12], reg, 12); \ + /* Fall through */ \ case 11: write_debug(ptr[11], reg, 11); \ + /* Fall through */ \ case 10: write_debug(ptr[10], reg, 10); \ + /* Fall through */ \ case 9: write_debug(ptr[9], reg, 9); \ + /* Fall through */ \ case 8: write_debug(ptr[8], reg, 8); \ + /* Fall through */ \ case 7: write_debug(ptr[7], reg, 7); \ + /* Fall through */ \ case 6: write_debug(ptr[6], reg, 6); \ + /* Fall through */ \ case 5: write_debug(ptr[5], reg, 5); \ + /* Fall through */ \ case 4: write_debug(ptr[4], reg, 4); \ + /* Fall through */ \ case 3: write_debug(ptr[3], reg, 3); \ + /* Fall through */ \ case 2: write_debug(ptr[2], reg, 2); \ + /* Fall through */ \ case 1: write_debug(ptr[1], reg, 1); \ + /* Fall through */ \ default: write_debug(ptr[0], reg, 0); \ } diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c index 0d60e4f0af66..a900181e3867 100644 --- a/arch/arm64/kvm/regmap.c +++ b/arch/arm64/kvm/regmap.c @@ -178,13 +178,18 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v) switch (spsr_idx) { case KVM_SPSR_SVC: write_sysreg_el1(v, SYS_SPSR); + break; case KVM_SPSR_ABT: write_sysreg(v, spsr_abt); + break; case KVM_SPSR_UND: write_sysreg(v, spsr_und); + break; case KVM_SPSR_IRQ: write_sysreg(v, spsr_irq); + break; case KVM_SPSR_FIQ: write_sysreg(v, spsr_fiq); + break; } } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index f26e181d881c..2071260a275b 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -632,7 +632,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) */ val = ((pmcr & ~ARMV8_PMU_PMCR_MASK) | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E); - __vcpu_sys_reg(vcpu, PMCR_EL0) = val; + __vcpu_sys_reg(vcpu, r->reg) = val; } static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) @@ -981,13 +981,13 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ - trap_bvr, reset_bvr, n, 0, get_bvr, set_bvr }, \ + trap_bvr, reset_bvr, 0, 0, get_bvr, set_bvr }, \ { SYS_DESC(SYS_DBGBCRn_EL1(n)), \ - trap_bcr, reset_bcr, n, 0, get_bcr, set_bcr }, \ + trap_bcr, reset_bcr, 0, 0, get_bcr, set_bcr }, \ { SYS_DESC(SYS_DBGWVRn_EL1(n)), \ - trap_wvr, reset_wvr, n, 0, get_wvr, set_wvr }, \ + trap_wvr, reset_wvr, 0, 0, get_wvr, set_wvr }, \ { SYS_DESC(SYS_DBGWCRn_EL1(n)), \ - trap_wcr, reset_wcr, n, 0, get_wcr, set_wcr } + trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr } /* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ @@ -1540,7 +1540,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, - { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, }, + { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 }, { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, NULL, PMCNTENSET_EL0 }, { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, NULL, PMOVSSET_EL0 }, @@ -2254,13 +2254,19 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, } static void reset_sys_reg_descs(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *table, size_t num) + const struct sys_reg_desc *table, size_t num, + unsigned long *bmap) { unsigned long i; for (i = 0; i < num; i++) - if (table[i].reset) + if (table[i].reset) { + int reg = table[i].reg; + table[i].reset(vcpu, &table[i]); + if (reg > 0 && reg < NR_SYS_REGS) + set_bit(reg, bmap); + } } /** @@ -2774,18 +2780,16 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) { size_t num; const struct sys_reg_desc *table; - - /* Catch someone adding a register without putting in reset entry. */ - memset(&vcpu->arch.ctxt.sys_regs, 0x42, sizeof(vcpu->arch.ctxt.sys_regs)); + DECLARE_BITMAP(bmap, NR_SYS_REGS) = { 0, }; /* Generic chip reset first (so target could override). */ - reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); + reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs), bmap); table = get_target_table(vcpu->arch.target, true, &num); - reset_sys_reg_descs(vcpu, table, num); + reset_sys_reg_descs(vcpu, table, num, bmap); for (num = 1; num < NR_SYS_REGS; num++) { - if (WARN(__vcpu_sys_reg(vcpu, num) == 0x4242424242424242, + if (WARN(!test_bit(num, bmap), "Didn't reset __vcpu_sys_reg(%zi)\n", num)) break; } diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 2cfe839f0b3a..1109924560d8 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -150,16 +150,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } -bool kvm_arch_has_vcpu_debugfs(void) -{ - return false; -} - -int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) -{ - return 0; -} - void kvm_mips_free_vcpus(struct kvm *kvm) { unsigned int i; diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index b5a848a55504..00649ca5fa9a 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -440,6 +440,9 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm, struct kvm_vcpu *vcpu; int err; + BUILD_BUG_ON_MSG(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0, + "struct kvm_vcpu must be at offset 0 for arch usercopy region"); + vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); if (!vcpu_e500) { err = -ENOMEM; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 7012dd709787..3a77bb643452 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -50,6 +50,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) return !!(v->arch.pending_exceptions) || kvm_request_pending(v); } +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_arch_vcpu_runnable(vcpu); +} + bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { return false; @@ -452,16 +457,6 @@ err_out: return -EINVAL; } -bool kvm_arch_has_vcpu_debugfs(void) -{ - return false; -} - -int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) -{ - return 0; -} - void kvm_arch_destroy_vm(struct kvm *kvm) { unsigned int i; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3f520cd837fb..f329dcb3f44c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2516,16 +2516,6 @@ out_err: return rc; } -bool kvm_arch_has_vcpu_debugfs(void) -{ - return false; -} - -int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) -{ - return 0; -} - void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 3, "%s", "free cpu"); diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index feab24cac610..77cf6c11f66b 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -229,7 +229,7 @@ struct x86_emulate_ops { int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate); void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt); - + int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); }; typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -429,6 +429,7 @@ enum x86_intercept { x86_intercept_ins, x86_intercept_out, x86_intercept_outs, + x86_intercept_xsetbv, nr_x86_intercepts }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7b0a4ee77313..5b14aa1fbeeb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -35,6 +35,8 @@ #include <asm/kvm_vcpu_regs.h> #include <asm/hyperv-tlfs.h> +#define __KVM_HAVE_ARCH_VCPU_DEBUGFS + #define KVM_MAX_VCPUS 288 #define KVM_SOFT_MAX_VCPUS 240 #define KVM_MAX_VCPU_ID 1023 @@ -715,7 +717,7 @@ struct kvm_vcpu_arch { /* Cache MMIO info */ u64 mmio_gva; - unsigned access; + unsigned mmio_access; gfn_t mmio_gfn; u64 mmio_gen; @@ -1068,7 +1070,7 @@ struct kvm_x86_ops { void (*run)(struct kvm_vcpu *vcpu); int (*handle_exit)(struct kvm_vcpu *vcpu); - void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, @@ -1175,6 +1177,7 @@ struct kvm_x86_ops { int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); + bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, bool *expired); @@ -1578,6 +1581,13 @@ bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, struct kvm_lapic_irq *irq); +static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) +{ + /* We can only post Fixed and LowPrio IRQs */ + return (irq->delivery_mode == dest_Fixed || + irq->delivery_mode == dest_LowestPrio); +} + static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { if (kvm_x86_ops->vcpu_blocking) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b7f34fe2171e..4ab377c9fffe 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -308,9 +308,6 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val) static void kvm_guest_cpu_init(void) { - if (!kvm_para_available()) - return; - if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) { u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); @@ -625,9 +622,6 @@ static void __init kvm_guest_init(void) { int i; - if (!kvm_para_available()) - return; - paravirt_ops_setup(); register_reboot_notifier(&kvm_pv_reboot_nb); for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) @@ -848,8 +842,6 @@ asm( */ void __init kvm_spinlock_init(void) { - if (!kvm_para_available()) - return; /* Does host kernel support KVM_FEATURE_PV_UNHALT? */ if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 22c2720cd948..dd5985eb61b4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -392,6 +392,12 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) entry->edx &= kvm_cpuid_7_0_edx_x86_features; cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even * if the host doesn't support it. @@ -729,18 +735,23 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); /* - * IBRS, IBPB and VIRT_SSBD aren't necessarily present in - * hardware cpuid + * AMD has separate bits for each SPEC_CTRL bit. + * arch/x86/kernel/cpu/bugs.c is kind enough to + * record that in cpufeatures so use them. */ - if (boot_cpu_has(X86_FEATURE_AMD_IBPB)) + if (boot_cpu_has(X86_FEATURE_IBPB)) entry->ebx |= F(AMD_IBPB); - if (boot_cpu_has(X86_FEATURE_AMD_IBRS)) + if (boot_cpu_has(X86_FEATURE_IBRS)) entry->ebx |= F(AMD_IBRS); - if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) - entry->ebx |= F(VIRT_SSBD); - entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->ebx |= F(AMD_STIBP); + if (boot_cpu_has(X86_FEATURE_SSBD)) + entry->ebx |= F(AMD_SSBD); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + entry->ebx |= F(AMD_SSB_NO); /* * The preference is to use SPEC CTRL MSR instead of the * VIRT_SPEC MSR. diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 329361b69d5e..018aebce33ff 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -8,11 +8,6 @@ #include <linux/debugfs.h> #include "lapic.h" -bool kvm_arch_has_vcpu_debugfs(void) -{ - return true; -} - static int vcpu_get_timer_advance_ns(void *data, u64 *val) { struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data; @@ -48,37 +43,22 @@ static int vcpu_get_tsc_scaling_frac_bits(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_frac_fops, vcpu_get_tsc_scaling_frac_bits, NULL, "%llu\n"); -int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) { - struct dentry *ret; - - ret = debugfs_create_file("tsc-offset", 0444, - vcpu->debugfs_dentry, - vcpu, &vcpu_tsc_offset_fops); - if (!ret) - return -ENOMEM; + debugfs_create_file("tsc-offset", 0444, vcpu->debugfs_dentry, vcpu, + &vcpu_tsc_offset_fops); - if (lapic_in_kernel(vcpu)) { - ret = debugfs_create_file("lapic_timer_advance_ns", 0444, - vcpu->debugfs_dentry, - vcpu, &vcpu_timer_advance_ns_fops); - if (!ret) - return -ENOMEM; - } + if (lapic_in_kernel(vcpu)) + debugfs_create_file("lapic_timer_advance_ns", 0444, + vcpu->debugfs_dentry, vcpu, + &vcpu_timer_advance_ns_fops); if (kvm_has_tsc_control) { - ret = debugfs_create_file("tsc-scaling-ratio", 0444, - vcpu->debugfs_dentry, - vcpu, &vcpu_tsc_scaling_fops); - if (!ret) - return -ENOMEM; - ret = debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444, - vcpu->debugfs_dentry, - vcpu, &vcpu_tsc_scaling_frac_fops); - if (!ret) - return -ENOMEM; - + debugfs_create_file("tsc-scaling-ratio", 0444, + vcpu->debugfs_dentry, vcpu, + &vcpu_tsc_scaling_fops); + debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444, + vcpu->debugfs_dentry, vcpu, + &vcpu_tsc_scaling_frac_fops); } - - return 0; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 718f7d9afedc..bef3c3c695d7 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4156,6 +4156,20 @@ out: return rc; } +static int em_xsetbv(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ecx, edx; + + eax = reg_read(ctxt, VCPU_REGS_RAX); + edx = reg_read(ctxt, VCPU_REGS_RDX); + ecx = reg_read(ctxt, VCPU_REGS_RCX); + + if (ctxt->ops->set_xcr(ctxt, ecx, ((u64)edx << 32) | eax)) + return emulate_gp(ctxt, 0); + + return X86EMUL_CONTINUE; +} + static bool valid_cr(int nr) { switch (nr) { @@ -4409,6 +4423,12 @@ static const struct opcode group7_rm1[] = { N, N, N, N, N, N, }; +static const struct opcode group7_rm2[] = { + N, + II(ImplicitOps | Priv, em_xsetbv, xsetbv), + N, N, N, N, N, N, +}; + static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), II(SrcNone | Prot | EmulateOnUD, em_hypercall, vmmcall), @@ -4498,7 +4518,8 @@ static const struct group_dual group7 = { { }, { EXT(0, group7_rm0), EXT(0, group7_rm1), - N, EXT(0, group7_rm3), + EXT(0, group7_rm2), + EXT(0, group7_rm3), II(SrcNone | DstMem | Mov, em_smsw, smsw), N, II(SrcMem16 | Mov | Priv, em_lmsw, lmsw), EXT(0, group7_rm7), @@ -5144,7 +5165,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) else { rc = __do_insn_fetch_bytes(ctxt, 1); if (rc != X86EMUL_CONTINUE) - return rc; + goto done; } switch (mode) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0aa158657f20..e904ff06a83d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -216,6 +216,9 @@ static void recalculate_apic_map(struct kvm *kvm) if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) new->phys_map[xapic_id] = apic; + if (!kvm_apic_sw_enabled(apic)) + continue; + ldr = kvm_lapic_get_reg(apic, APIC_LDR); if (apic_x2apic_mode(apic)) { @@ -258,6 +261,8 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) static_key_slow_dec_deferred(&apic_sw_disabled); else static_key_slow_inc(&apic_sw_disabled.key); + + recalculate_apic_map(apic->vcpu->kvm); } } @@ -1548,7 +1553,6 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic) static void apic_timer_expired(struct kvm_lapic *apic) { struct kvm_vcpu *vcpu = apic->vcpu; - struct swait_queue_head *q = &vcpu->wq; struct kvm_timer *ktimer = &apic->lapic_timer; if (atomic_read(&apic->lapic_timer.pending)) @@ -1566,13 +1570,6 @@ static void apic_timer_expired(struct kvm_lapic *apic) atomic_inc(&apic->lapic_timer.pending); kvm_set_pending_timer(vcpu); - - /* - * For x86, the atomic_inc() is serialized, thus - * using swait_active() is safe. - */ - if (swait_active(q)) - swake_up_one(q); } static void start_sw_tscdeadline(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 24843cf49579..4c45ff0cfbd0 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -214,6 +214,7 @@ static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_mmio_value; +static u64 __read_mostly shadow_mmio_access_mask; static u64 __read_mostly shadow_present_mask; static u64 __read_mostly shadow_me_mask; @@ -299,14 +300,21 @@ static void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask) { + BUG_ON((u64)(unsigned)access_mask != access_mask); BUG_ON((mmio_mask & mmio_value) != mmio_value); shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; + shadow_mmio_access_mask = access_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +static bool is_mmio_spte(u64 spte) +{ + return (spte & shadow_mmio_mask) == shadow_mmio_value; +} + static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) { return sp->role.ad_disabled; @@ -314,19 +322,19 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) static inline bool spte_ad_enabled(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return !(spte & shadow_acc_track_value); } static inline u64 spte_shadow_accessed_mask(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return spte_ad_enabled(spte) ? shadow_accessed_mask : 0; } static inline u64 spte_shadow_dirty_mask(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return spte_ad_enabled(spte) ? shadow_dirty_mask : 0; } @@ -389,7 +397,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, u64 mask = generation_mmio_spte_mask(gen); u64 gpa = gfn << PAGE_SHIFT; - access &= ACC_WRITE_MASK | ACC_USER_MASK; + access &= shadow_mmio_access_mask; mask |= shadow_mmio_value | access; mask |= gpa | shadow_nonpresent_or_rsvd_mask; mask |= (gpa & shadow_nonpresent_or_rsvd_mask) @@ -401,11 +409,6 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, mmu_spte_set(sptep, mask); } -static bool is_mmio_spte(u64 spte) -{ - return (spte & shadow_mmio_mask) == shadow_mmio_value; -} - static gfn_t get_mmio_spte_gfn(u64 spte) { u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask; @@ -418,8 +421,7 @@ static gfn_t get_mmio_spte_gfn(u64 spte) static unsigned get_mmio_spte_access(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_SPTE_GEN_MASK) | shadow_mmio_mask; - return (spte & ~mask) & ~PAGE_MASK; + return spte & shadow_mmio_access_mask; } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, @@ -3290,7 +3292,8 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, } if (unlikely(is_noslot_pfn(pfn))) - vcpu_cache_mmio_info(vcpu, gva, gfn, access); + vcpu_cache_mmio_info(vcpu, gva, gfn, + access & shadow_mmio_access_mask); return false; } @@ -5653,38 +5656,7 @@ static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, struct kvm_page_track_notifier_node *node) { - struct kvm_mmu_page *sp; - LIST_HEAD(invalid_list); - unsigned long i; - bool flush; - gfn_t gfn; - - spin_lock(&kvm->mmu_lock); - - if (list_empty(&kvm->arch.active_mmu_pages)) - goto out_unlock; - - flush = slot_handle_all_level(kvm, slot, kvm_zap_rmapp, false); - - for (i = 0; i < slot->npages; i++) { - gfn = slot->base_gfn + i; - - for_each_valid_sp(kvm, sp, gfn) { - if (sp->gfn != gfn) - continue; - - kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - } - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); - flush = false; - cond_resched_lock(&kvm->mmu_lock); - } - } - kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); - -out_unlock: - spin_unlock(&kvm->mmu_lock); + kvm_mmu_zap_all(kvm); } void kvm_mmu_init_vm(struct kvm *kvm) @@ -6028,7 +6000,7 @@ static void kvm_set_mmio_spte_mask(void) if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52) mask &= ~1ull; - kvm_mmu_set_mmio_spte_mask(mask, mask); + kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); } int kvm_mmu_module_init(void) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 54c2a377795b..11f8ec89433b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -51,7 +51,7 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value); +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 7eafc6907861..f5b03d0c9bc6 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -68,10 +68,8 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 -#define SVM_FEATURE_NPT (1 << 0) #define SVM_FEATURE_LBRV (1 << 1) #define SVM_FEATURE_SVML (1 << 2) -#define SVM_FEATURE_NRIP (1 << 3) #define SVM_FEATURE_TSC_RATE (1 << 4) #define SVM_FEATURE_VMCB_CLEAN (1 << 5) #define SVM_FEATURE_FLUSH_ASID (1 << 6) @@ -770,7 +768,7 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) } -static void skip_emulated_instruction(struct kvm_vcpu *vcpu) +static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -779,18 +777,17 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) svm->next_rip = svm->vmcb->control.next_rip; } - if (!svm->next_rip) { - if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) != - EMULATE_DONE) - printk(KERN_DEBUG "%s: NOP\n", __func__); - return; - } + if (!svm->next_rip) + return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP); + if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE) printk(KERN_ERR "%s: ip 0x%lx next 0x%llx\n", __func__, kvm_rip_read(vcpu), svm->next_rip); kvm_rip_write(vcpu, svm->next_rip); svm_set_interrupt_shadow(vcpu, 0); + + return EMULATE_DONE; } static void svm_queue_exception(struct kvm_vcpu *vcpu) @@ -821,7 +818,7 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu) * raises a fault that is not intercepted. Still better than * failing in all cases. */ - skip_emulated_instruction(&svm->vcpu); + (void)skip_emulated_instruction(&svm->vcpu); rip = kvm_rip_read(&svm->vcpu); svm->int3_rip = rip + svm->vmcb->save.cs.base; svm->int3_injected = rip - old_rip; @@ -1714,7 +1711,6 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) if (!entry) return -EINVAL; - new_entry = READ_ONCE(*entry); new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); @@ -2137,6 +2133,9 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) struct page *nested_msrpm_pages; int err; + BUILD_BUG_ON_MSG(offsetof(struct vcpu_svm, vcpu) != 0, + "struct kvm_vcpu must be at offset 0 for arch usercopy region"); + svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!svm) { err = -ENOMEM; @@ -2904,13 +2903,11 @@ static int nop_on_interception(struct vcpu_svm *svm) static int halt_interception(struct vcpu_svm *svm) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; return kvm_emulate_halt(&svm->vcpu); } static int vmmcall_interception(struct vcpu_svm *svm) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; return kvm_emulate_hypercall(&svm->vcpu); } @@ -3589,9 +3586,9 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, mark_all_dirty(svm->vmcb); } -static bool nested_svm_vmrun(struct vcpu_svm *svm) +static int nested_svm_vmrun(struct vcpu_svm *svm) { - int rc; + int ret; struct vmcb *nested_vmcb; struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; @@ -3600,13 +3597,16 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) vmcb_gpa = svm->vmcb->save.rax; - rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); - if (rc) { - if (rc == -EINVAL) - kvm_inject_gp(&svm->vcpu, 0); - return false; + ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); + if (ret == EINVAL) { + kvm_inject_gp(&svm->vcpu, 0); + return 1; + } else if (ret) { + return kvm_skip_emulated_instruction(&svm->vcpu); } + ret = kvm_skip_emulated_instruction(&svm->vcpu); + nested_vmcb = map.hva; if (!nested_vmcb_checks(nested_vmcb)) { @@ -3617,7 +3617,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) kvm_vcpu_unmap(&svm->vcpu, &map, true); - return false; + return ret; } trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa, @@ -3661,7 +3661,16 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map); - return true; + if (!nested_svm_vmrun_msrpm(svm)) { + svm->vmcb->control.exit_code = SVM_EXIT_ERR; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + nested_svm_vmexit(svm); + } + + return ret; } static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) @@ -3698,7 +3707,6 @@ static int vmload_interception(struct vcpu_svm *svm) nested_vmcb = map.hva; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(nested_vmcb, svm->vmcb); @@ -3725,7 +3733,6 @@ static int vmsave_interception(struct vcpu_svm *svm) nested_vmcb = map.hva; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(svm->vmcb, nested_vmcb); @@ -3739,27 +3746,7 @@ static int vmrun_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - /* Save rip after vmrun instruction */ - kvm_rip_write(&svm->vcpu, kvm_rip_read(&svm->vcpu) + 3); - - if (!nested_svm_vmrun(svm)) - return 1; - - if (!nested_svm_vmrun_msrpm(svm)) - goto failed; - - return 1; - -failed: - - svm->vmcb->control.exit_code = SVM_EXIT_ERR; - svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - - nested_svm_vmexit(svm); - - return 1; + return nested_svm_vmrun(svm); } static int stgi_interception(struct vcpu_svm *svm) @@ -3776,7 +3763,6 @@ static int stgi_interception(struct vcpu_svm *svm) if (vgif_enabled(svm)) clr_intercept(svm, INTERCEPT_STGI); - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); @@ -3792,7 +3778,6 @@ static int clgi_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; ret = kvm_skip_emulated_instruction(&svm->vcpu); disable_gif(svm); @@ -3817,7 +3802,6 @@ static int invlpga_interception(struct vcpu_svm *svm) /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ kvm_mmu_invlpg(vcpu, kvm_rax_read(&svm->vcpu)); - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; return kvm_skip_emulated_instruction(&svm->vcpu); } @@ -3840,7 +3824,6 @@ static int xsetbv_interception(struct vcpu_svm *svm) u32 index = kvm_rcx_read(&svm->vcpu); if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; return kvm_skip_emulated_instruction(&svm->vcpu); } @@ -3899,25 +3882,29 @@ static int task_switch_interception(struct vcpu_svm *svm) if (reason != TASK_SWITCH_GATE || int_type == SVM_EXITINTINFO_TYPE_SOFT || (int_type == SVM_EXITINTINFO_TYPE_EXEPT && - (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) - skip_emulated_instruction(&svm->vcpu); + (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) { + if (skip_emulated_instruction(&svm->vcpu) != EMULATE_DONE) + goto fail; + } if (int_type != SVM_EXITINTINFO_TYPE_SOFT) int_vec = -1; if (kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason, - has_error_code, error_code) == EMULATE_FAIL) { - svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - svm->vcpu.run->internal.ndata = 0; - return 0; - } + has_error_code, error_code) == EMULATE_FAIL) + goto fail; + return 1; + +fail: + svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + svm->vcpu.run->internal.ndata = 0; + return 0; } static int cpuid_interception(struct vcpu_svm *svm) { - svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; return kvm_emulate_cpuid(&svm->vcpu); } @@ -4247,7 +4234,6 @@ static int rdmsr_interception(struct vcpu_svm *svm) kvm_rax_write(&svm->vcpu, msr_info.data & 0xffffffff); kvm_rdx_write(&svm->vcpu, msr_info.data >> 32); - svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; return kvm_skip_emulated_instruction(&svm->vcpu); } } @@ -4447,7 +4433,6 @@ static int wrmsr_interception(struct vcpu_svm *svm) msr.index = ecx; msr.host_initiated = false; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; if (kvm_set_msr(&svm->vcpu, &msr)) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); @@ -5190,6 +5175,11 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) kvm_vcpu_wake_up(vcpu); } +static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return false; +} + static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) { unsigned long flags; @@ -5270,7 +5260,8 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, kvm_set_msi_irq(kvm, e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || + !kvm_irq_is_postable(&irq)) { pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n", __func__, irq.vector); return -1; @@ -5324,6 +5315,7 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * 1. When cannot target interrupt to a specific vcpu. * 2. Unsetting posted interrupt. * 3. APIC virtialization is disabled for the vcpu. + * 4. IRQ has incompatible delivery mode (SMI, INIT, etc) */ if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && kvm_vcpu_apicv_active(&svm->vcpu)) { @@ -5929,6 +5921,8 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC); } +#define F(x) bit(X86_FEATURE_##x) + static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { switch (func) { @@ -5940,6 +5934,11 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) if (nested) entry->ecx |= (1 << 2); /* Set SVM bit */ break; + case 0x80000008: + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->ebx |= F(VIRT_SSBD); + break; case 0x8000000A: entry->eax = 1; /* SVM revision 1 */ entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper @@ -5950,11 +5949,11 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) /* Support next_rip if host supports it */ if (boot_cpu_has(X86_FEATURE_NRIPS)) - entry->edx |= SVM_FEATURE_NRIP; + entry->edx |= F(NRIPS); /* Support NPT for the guest if enabled */ if (npt_enabled) - entry->edx |= SVM_FEATURE_NPT; + entry->edx |= F(NPT); break; case 0x8000001F: @@ -6063,6 +6062,7 @@ static const struct __x86_intercept { [x86_intercept_ins] = POST_EX(SVM_EXIT_IOIO), [x86_intercept_out] = POST_EX(SVM_EXIT_IOIO), [x86_intercept_outs] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_xsetbv] = PRE_EX(SVM_EXIT_XSETBV), }; #undef PRE_EX @@ -7314,6 +7314,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .pmu_ops = &amd_pmu_ops, .deliver_posted_interrupt = svm_deliver_avic_intr, + .dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt, .update_pi_irte = svm_update_pi_irte, .setup_mce = svm_setup_mce, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index b5c831e79094..6ce853a2e867 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1462,6 +1462,25 @@ TRACE_EVENT(kvm_hv_send_ipi_ex, __entry->vector, __entry->format, __entry->valid_bank_mask) ); + +TRACE_EVENT(kvm_pv_tlb_flush, + TP_PROTO(unsigned int vcpu_id, bool need_flush_tlb), + TP_ARGS(vcpu_id, need_flush_tlb), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( bool, need_flush_tlb ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->need_flush_tlb = need_flush_tlb; + ), + + TP_printk("vcpu %u need_flush_tlb %s", __entry->vcpu_id, + __entry->need_flush_tlb ? "true" : "false") +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 4010d519eb8c..751a384c2eb0 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -94,7 +94,7 @@ ENDPROC(vmx_vmexit) /** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode - * @vmx: struct vcpu_vmx * + * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) * @regs: unsigned long * (to guest registers) * @launched: %true if the VMCS has been launched * @@ -151,7 +151,7 @@ ENTRY(__vmx_vcpu_run) mov VCPU_R14(%_ASM_AX), %r14 mov VCPU_R15(%_ASM_AX), %r15 #endif - /* Load guest RAX. This kills the vmx_vcpu pointer! */ + /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX /* Enter guest mode */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 074385c86c09..63f3d88b36cc 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1472,8 +1472,11 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } - -static void skip_emulated_instruction(struct kvm_vcpu *vcpu) +/* + * Returns an int to be compatible with SVM implementation (which can fail). + * Do not use directly, use skip_emulated_instruction() instead. + */ +static int __skip_emulated_instruction(struct kvm_vcpu *vcpu) { unsigned long rip; @@ -1483,6 +1486,13 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) /* skipping an emulated instruction also counts */ vmx_set_interrupt_shadow(vcpu, 0); + + return EMULATE_DONE; +} + +static inline void skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + (void)__skip_emulated_instruction(vcpu); } static void vmx_clear_hlt(struct kvm_vcpu *vcpu) @@ -4026,7 +4036,7 @@ static void ept_set_mmio_spte_mask(void) * of an EPT paging-structure entry is 110b (write/execute). */ kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, - VMX_EPT_MISCONFIG_WX_VALUE); + VMX_EPT_MISCONFIG_WX_VALUE, 0); } #define VMX_XSS_EXIT_BITMAP 0 @@ -6117,6 +6127,11 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) return max_irr; } +static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return pi_test_on(vcpu_to_pi_desc(vcpu)); +} + static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) @@ -6610,6 +6625,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) unsigned long *msr_bitmap; int cpu; + BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0, + "struct kvm_vcpu must be at offset 0 for arch usercopy region"); + vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!vmx) return ERR_PTR(-ENOMEM); @@ -7364,10 +7382,14 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * irqbalance to make the interrupts single-CPU. * * We will support full lowest-priority interrupt later. + * + * In addition, we can only inject generic interrupts using + * the PI mechanism, refuse to route others through it. */ kvm_set_msi_irq(kvm, e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || + !kvm_irq_is_postable(&irq)) { /* * Make sure the IRTE is in remapped mode if * we don't handle it in posted mode. @@ -7700,7 +7722,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .run = vmx_vcpu_run, .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, + .skip_emulated_instruction = __skip_emulated_instruction, .set_interrupt_shadow = vmx_set_interrupt_shadow, .get_interrupt_shadow = vmx_get_interrupt_shadow, .patch_hypercall = vmx_patch_hypercall, @@ -7726,6 +7748,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, .sync_pir_to_irr = vmx_sync_pir_to_irr, .deliver_posted_interrupt = vmx_deliver_posted_interrupt, + .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt, .set_tss_addr = vmx_set_tss_addr, .set_identity_map_addr = vmx_set_identity_map_addr, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c6d951cbd76c..605f9902f164 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -674,8 +674,14 @@ static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, data, offset, len, access); } +static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) +{ + return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) | + rsvd_bits(1, 2); +} + /* - * Load the pae pdptrs. Return true is they are all valid. + * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) { @@ -694,8 +700,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if ((pdpte[i] & PT_PRESENT_MASK) && - (pdpte[i] & - vcpu->arch.mmu->guest_rsvd_check.rsvd_bits_mask[0][2])) { + (pdpte[i] & pdptr_rsvd_bits(vcpu))) { ret = 0; goto out; } @@ -1254,6 +1259,13 @@ static u64 kvm_get_arch_capabilities(void) if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + data |= ARCH_CAP_RDCL_NO; + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + data |= ARCH_CAP_SSB_NO; + if (!boot_cpu_has_bug(X86_BUG_MDS)) + data |= ARCH_CAP_MDS_NO; + return data; } @@ -2452,6 +2464,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu) * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, + vcpu->arch.st.steal.preempted & KVM_VCPU_FLUSH_TLB); if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb(vcpu, false); @@ -3506,8 +3520,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; - if (kvm_x86_ops->setup_mce) - kvm_x86_ops->setup_mce(vcpu); + kvm_x86_ops->setup_mce(vcpu); out: return r; } @@ -5370,7 +5383,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, */ if (vcpu_match_mmio_gva(vcpu, gva) && !permission_fault(vcpu, vcpu->arch.walk_mmu, - vcpu->arch.access, 0, access)) { + vcpu->arch.mmio_access, 0, access)) { *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | (gva & (PAGE_SIZE - 1)); trace_vcpu_match_mmio(gva, *gpa, write, false); @@ -6068,6 +6081,11 @@ static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) kvm_smm_changed(emul_to_vcpu(ctxt)); } +static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) +{ + return __kvm_set_xcr(emul_to_vcpu(ctxt), index, xcr); +} + static const struct x86_emulate_ops emulate_ops = { .read_gpr = emulator_read_gpr, .write_gpr = emulator_write_gpr, @@ -6109,6 +6127,7 @@ static const struct x86_emulate_ops emulate_ops = { .set_hflags = emulator_set_hflags, .pre_leave_smm = emulator_pre_leave_smm, .post_leave_smm = emulator_post_leave_smm, + .set_xcr = emulator_set_xcr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -6383,9 +6402,11 @@ static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); - int r = EMULATE_DONE; + int r; - kvm_x86_ops->skip_emulated_instruction(vcpu); + r = kvm_x86_ops->skip_emulated_instruction(vcpu); + if (unlikely(r != EMULATE_DONE)) + return 0; /* * rflags is the old, "raw" value of the flags. The new value has @@ -6537,6 +6558,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, kvm_rip_write(vcpu, ctxt->_eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); + kvm_x86_ops->set_interrupt_shadow(vcpu, 0); return EMULATE_DONE; } @@ -9314,10 +9336,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); - if (kvm_x86_ops->vm_init) - return kvm_x86_ops->vm_init(kvm); - - return 0; + return kvm_x86_ops->vm_init(kvm); } static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) @@ -9698,6 +9717,22 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || + kvm_test_request(KVM_REQ_SMI, vcpu) || + kvm_test_request(KVM_REQ_EVENT, vcpu)) + return true; + + if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu)) + return true; + + return false; +} + bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { return vcpu->arch.preempted_in_kernel; @@ -9993,7 +10028,7 @@ EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); bool kvm_arch_has_irq_bypass(void) { - return kvm_x86_ops->update_pi_irte != NULL; + return true; } int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, @@ -10033,9 +10068,6 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set) { - if (!kvm_x86_ops->update_pi_irte) - return -EINVAL; - return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 6594020c0691..b5274e2a53cf 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -196,7 +196,7 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, * actually a nGPA. */ vcpu->arch.mmio_gva = mmu_is_nested(vcpu) ? 0 : gva & PAGE_MASK; - vcpu->arch.access = access; + vcpu->arch.mmio_access = access; vcpu->arch.mmio_gfn = gfn; vcpu->arch.mmio_gen = gen; } diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 16c769a7f979..6db030439e29 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -34,6 +34,7 @@ struct kvm_pmu { u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx); void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val); u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu); +void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu); void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val); @@ -71,6 +72,7 @@ static inline u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu) { return 0; } +static inline void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 46bbc949c20a..7a30524a80ee 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -350,6 +350,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); void kvm_vgic_load(struct kvm_vcpu *vcpu); void kvm_vgic_put(struct kvm_vcpu *vcpu); +void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu); #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) #define vgic_initialized(k) ((k)->arch.vgic.initialized) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5c5b5867024c..fcb46b3374c6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -861,8 +861,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); -bool kvm_arch_has_vcpu_debugfs(void); -int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu); +#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS +void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu); +#endif int kvm_arch_hardware_enable(void); void kvm_arch_hardware_disable(void); @@ -872,6 +873,7 @@ int kvm_arch_check_processor_compat(void); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 41266af0d3dc..b35da375530a 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,7 +1,7 @@ +/s390x/sync_regs_test /x86_64/cr4_cpuid_sync_test /x86_64/evmcs_test /x86_64/hyperv_cpuid -/x86_64/kvm_create_max_vcpus /x86_64/mmio_warning_test /x86_64/platform_info_test /x86_64/set_sregs_test @@ -13,3 +13,4 @@ /x86_64/vmx_tsc_adjust_test /clear_dirty_log_test /dirty_log_test +/kvm_create_max_vcpus diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config new file mode 100644 index 000000000000..63ed533f73d6 --- /dev/null +++ b/tools/testing/selftests/kvm/config @@ -0,0 +1,3 @@ +CONFIG_KVM=y +CONFIG_KVM_INTEL=y +CONFIG_KVM_AMD=y diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h index 4059014d93ea..4912d23844bc 100644 --- a/tools/testing/selftests/kvm/include/evmcs.h +++ b/tools/testing/selftests/kvm/include/evmcs.h @@ -220,6 +220,8 @@ struct hv_enlightened_vmcs { struct hv_enlightened_vmcs *current_evmcs; struct hv_vp_assist_page *current_vp_assist; +int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id); + static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist) { u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) | diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 6cb34a0fa200..0a5e487dbc50 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1060,9 +1060,11 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i", r); - r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i", - r); + if (kvm_check_cap(KVM_CAP_XCRS)) { + r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i", + r); + } r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i", @@ -1103,9 +1105,11 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", r); - r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i", - r); + if (kvm_check_cap(KVM_CAP_XCRS)) { + r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i", + r); + } r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i", diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 204f847bd065..9cef0455b819 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -12,6 +12,26 @@ bool enable_evmcs; +int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id) +{ + uint16_t evmcs_ver; + + struct kvm_enable_cap enable_evmcs_cap = { + .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS, + .args[0] = (unsigned long)&evmcs_ver + }; + + vcpu_ioctl(vm, vcpu_id, KVM_ENABLE_CAP, &enable_evmcs_cap); + + /* KVM should return supported EVMCS version range */ + TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) && + (evmcs_ver & 0xff) > 0, + "Incorrect EVMCS version range: %x:%x\n", + evmcs_ver & 0xff, evmcs_ver >> 8); + + return evmcs_ver; +} + /* Allocate memory regions for nested VMX tests. * * Input Args: diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index f95c08343b48..92915e6408e7 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -79,11 +79,6 @@ int main(int argc, char *argv[]) struct kvm_x86_state *state; struct ucall uc; int stage; - uint16_t evmcs_ver; - struct kvm_enable_cap enable_evmcs_cap = { - .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS, - .args[0] = (unsigned long)&evmcs_ver - }; /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); @@ -96,13 +91,7 @@ int main(int argc, char *argv[]) exit(KSFT_SKIP); } - vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); - - /* KVM should return supported EVMCS version range */ - TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) && - (evmcs_ver & 0xff) > 0, - "Incorrect EVMCS version range: %x:%x\n", - evmcs_ver & 0xff, evmcs_ver >> 8); + vcpu_enable_evmcs(vm, VCPU_ID); run = vcpu_state(vm, VCPU_ID); @@ -146,7 +135,7 @@ int main(int argc, char *argv[]) kvm_vm_restart(vm, O_RDWR); vm_vcpu_add(vm, VCPU_ID); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); + vcpu_enable_evmcs(vm, VCPU_ID); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); free(state); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index f72b3043db0e..ee59831fbc98 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -18,6 +18,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "vmx.h" #define VCPU_ID 0 @@ -106,12 +107,7 @@ int main(int argc, char *argv[]) { struct kvm_vm *vm; int rv; - uint16_t evmcs_ver; struct kvm_cpuid2 *hv_cpuid_entries; - struct kvm_enable_cap enable_evmcs_cap = { - .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS, - .args[0] = (unsigned long)&evmcs_ver - }; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); @@ -136,14 +132,14 @@ int main(int argc, char *argv[]) free(hv_cpuid_entries); - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); - - if (rv) { + if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { fprintf(stderr, "Enlightened VMCS is unsupported, skip related test\n"); goto vm_free; } + vcpu_enable_evmcs(vm, VCPU_ID); + hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm); if (!hv_cpuid_entries) return 1; diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index 40050e44ec0a..f9334bd3cce9 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -99,8 +99,8 @@ int main(int argc, char *argv[]) msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO); vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); - test_msr_platform_info_disabled(vm); test_msr_platform_info_enabled(vm); + test_msr_platform_info_disabled(vm); vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index ed7218d166da..853e370e8a39 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -25,24 +25,17 @@ #define VMCS12_REVISION 0x11e57ed0 #define VCPU_ID 5 +bool have_evmcs; + void test_nested_state(struct kvm_vm *vm, struct kvm_nested_state *state) { - volatile struct kvm_run *run; - vcpu_nested_state_set(vm, VCPU_ID, state, false); - run = vcpu_state(vm, VCPU_ID); - vcpu_run(vm, VCPU_ID); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); } void test_nested_state_expect_errno(struct kvm_vm *vm, struct kvm_nested_state *state, int expected_errno) { - volatile struct kvm_run *run; int rv; rv = vcpu_nested_state_set(vm, VCPU_ID, state, true); @@ -50,12 +43,6 @@ void test_nested_state_expect_errno(struct kvm_vm *vm, "Expected %s (%d) from vcpu_nested_state_set but got rv: %i errno: %s (%d)", strerror(expected_errno), expected_errno, rv, strerror(errno), errno); - run = vcpu_state(vm, VCPU_ID); - vcpu_run(vm, VCPU_ID); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); } void test_nested_state_expect_einval(struct kvm_vm *vm, @@ -90,8 +77,9 @@ void set_default_vmx_state(struct kvm_nested_state *state, int size) { memset(state, 0, size); state->flags = KVM_STATE_NESTED_GUEST_MODE | - KVM_STATE_NESTED_RUN_PENDING | - KVM_STATE_NESTED_EVMCS; + KVM_STATE_NESTED_RUN_PENDING; + if (have_evmcs) + state->flags |= KVM_STATE_NESTED_EVMCS; state->format = 0; state->size = size; state->hdr.vmx.vmxon_pa = 0x1000; @@ -141,13 +129,19 @@ void test_vmx_nested_state(struct kvm_vm *vm) /* * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without * setting the nested state but flags other than eVMCS must be clear. + * The eVMCS flag can be set if the enlightened VMCS capability has + * been enabled. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; state->hdr.vmx.vmcs12_pa = -1ull; test_nested_state_expect_einval(vm, state); - state->flags = KVM_STATE_NESTED_EVMCS; + state->flags &= KVM_STATE_NESTED_EVMCS; + if (have_evmcs) { + test_nested_state_expect_einval(vm, state); + vcpu_enable_evmcs(vm, VCPU_ID); + } test_nested_state(vm, state); /* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */ @@ -232,6 +226,8 @@ int main(int argc, char *argv[]) struct kvm_nested_state state; struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); + have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS); + if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) { printf("KVM_CAP_NESTED_STATE not available, skipping test\n"); exit(KSFT_SKIP); diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index acc43242a310..35a069815baf 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -144,11 +144,6 @@ out_fail_alloc: return ret; } -bool kvm_arch_has_vcpu_debugfs(void) -{ - return false; -} - int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) { return 0; @@ -323,6 +318,17 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { + /* + * If we're about to block (most likely because we've just hit a + * WFI), we need to sync back the state of the GIC CPU interface + * so that we have the lastest PMR and group enables. This ensures + * that kvm_arch_vcpu_runnable has up-to-date data to decide + * whether we have pending interrupts. + */ + preempt_disable(); + kvm_vgic_vmcr_sync(vcpu); + preempt_enable(); + kvm_vgic_v4_enable_doorbell(vcpu); } @@ -340,6 +346,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) /* Set up the timer */ kvm_timer_vcpu_init(vcpu); + kvm_pmu_vcpu_init(vcpu); + kvm_arm_reset_debug_ptr(vcpu); return kvm_vgic_vcpu_init(vcpu); diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c index 254c5f190a3d..ccf1fde9836c 100644 --- a/virt/kvm/arm/hyp/vgic-v3-sr.c +++ b/virt/kvm/arm/hyp/vgic-v3-sr.c @@ -349,8 +349,10 @@ void __hyp_text __vgic_v3_save_aprs(struct kvm_vcpu *vcpu) case 7: cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3); cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2); + /* Fall through */ case 6: cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1); + /* Fall through */ default: cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0); } @@ -359,8 +361,10 @@ void __hyp_text __vgic_v3_save_aprs(struct kvm_vcpu *vcpu) case 7: cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3); cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2); + /* Fall through */ case 6: cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1); + /* Fall through */ default: cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0); } @@ -382,8 +386,10 @@ void __hyp_text __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu) case 7: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3); __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2); + /* Fall through */ case 6: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1); + /* Fall through */ default: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0); } @@ -392,8 +398,10 @@ void __hyp_text __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu) case 7: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3); __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2); + /* Fall through */ case 6: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1); + /* Fall through */ default: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0); } diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c index 3dd8238ed246..362a01886bab 100644 --- a/virt/kvm/arm/pmu.c +++ b/virt/kvm/arm/pmu.c @@ -215,6 +215,20 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc) } /** + * kvm_pmu_vcpu_init - assign pmu counter idx for cpu + * @vcpu: The vcpu pointer + * + */ +void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_pmu *pmu = &vcpu->arch.pmu; + + for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) + pmu->pmc[i].idx = i; +} + +/** * kvm_pmu_vcpu_reset - reset pmu state for cpu * @vcpu: The vcpu pointer * @@ -224,10 +238,8 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) int i; struct kvm_pmu *pmu = &vcpu->arch.pmu; - for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { + for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]); - pmu->pmc[i].idx = i; - } bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS); } diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 3ba7278fb533..44efc2ff863f 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -113,6 +113,22 @@ void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (vgic_irq_is_mapped_level(irq)) { + bool was_high = irq->line_level; + + /* + * We need to update the state of the interrupt because + * the guest might have changed the state of the device + * while the interrupt was disabled at the VGIC level. + */ + irq->line_level = vgic_get_phys_line_level(irq); + /* + * Deactivate the physical interrupt so the GIC will let + * us know when it is asserted again. + */ + if (!irq->active && was_high && !irq->line_level) + vgic_irq_set_phys_active(irq, false); + } irq->enabled = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index 6dd5ad706c92..96aab77d0471 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -484,10 +484,17 @@ void vgic_v2_load(struct kvm_vcpu *vcpu) kvm_vgic_global_state.vctrl_base + GICH_APR); } -void vgic_v2_put(struct kvm_vcpu *vcpu) +void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu) { struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; cpu_if->vgic_vmcr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_VMCR); +} + +void vgic_v2_put(struct kvm_vcpu *vcpu) +{ + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + + vgic_v2_vmcr_sync(vcpu); cpu_if->vgic_apr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_APR); } diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index c2c9ce009f63..0c653a1e5215 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -662,12 +662,17 @@ void vgic_v3_load(struct kvm_vcpu *vcpu) __vgic_v3_activate_traps(vcpu); } -void vgic_v3_put(struct kvm_vcpu *vcpu) +void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; if (likely(cpu_if->vgic_sre)) cpu_if->vgic_vmcr = kvm_call_hyp_ret(__vgic_v3_read_vmcr); +} + +void vgic_v3_put(struct kvm_vcpu *vcpu) +{ + vgic_v3_vmcr_sync(vcpu); kvm_call_hyp(__vgic_v3_save_aprs, vcpu); diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 04786c8ec77e..13d4b38a94ec 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -919,6 +919,17 @@ void kvm_vgic_put(struct kvm_vcpu *vcpu) vgic_v3_put(vcpu); } +void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu) +{ + if (unlikely(!irqchip_in_kernel(vcpu->kvm))) + return; + + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_vmcr_sync(vcpu); + else + vgic_v3_vmcr_sync(vcpu); +} + int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 3b7525deec80..797e05004d80 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -193,6 +193,7 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, void vgic_v2_init_lrs(void); void vgic_v2_load(struct kvm_vcpu *vcpu); void vgic_v2_put(struct kvm_vcpu *vcpu); +void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu); void vgic_v2_save_state(struct kvm_vcpu *vcpu); void vgic_v2_restore_state(struct kvm_vcpu *vcpu); @@ -223,6 +224,7 @@ bool vgic_v3_check_base(struct kvm *kvm); void vgic_v3_load(struct kvm_vcpu *vcpu); void vgic_v3_put(struct kvm_vcpu *vcpu); +void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu); bool vgic_has_its(struct kvm *kvm); int kvm_vgic_register_its_device(void); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 887f3b0c2b60..c6a91b044d8d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1855,8 +1855,7 @@ void kvm_set_pfn_dirty(kvm_pfn_t pfn) if (!kvm_is_reserved_pfn(pfn)) { struct page *page = pfn_to_page(pfn); - if (!PageReserved(page)) - SetPageDirty(page); + SetPageDirty(page); } } EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); @@ -2477,6 +2476,29 @@ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) #endif } +/* + * Unlike kvm_arch_vcpu_runnable, this function is called outside + * a vcpu_load/vcpu_put pair. However, for most architectures + * kvm_arch_vcpu_runnable does not require vcpu_load. + */ +bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_arch_vcpu_runnable(vcpu); +} + +static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) +{ + if (kvm_arch_dy_runnable(vcpu)) + return true; + +#ifdef CONFIG_KVM_ASYNC_PF + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; +#endif + + return false; +} + void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; @@ -2506,9 +2528,10 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; if (vcpu == me) continue; - if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) + if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu)) continue; - if (yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(vcpu)) + if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && + !kvm_arch_vcpu_in_kernel(vcpu)) continue; if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) continue; @@ -2591,30 +2614,20 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu) return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } -static int kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) { +#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS char dir_name[ITOA_MAX_LEN * 2]; - int ret; - - if (!kvm_arch_has_vcpu_debugfs()) - return 0; if (!debugfs_initialized()) - return 0; + return; snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id); vcpu->debugfs_dentry = debugfs_create_dir(dir_name, - vcpu->kvm->debugfs_dentry); - if (!vcpu->debugfs_dentry) - return -ENOMEM; - - ret = kvm_arch_create_vcpu_debugfs(vcpu); - if (ret < 0) { - debugfs_remove_recursive(vcpu->debugfs_dentry); - return ret; - } + vcpu->kvm->debugfs_dentry); - return 0; + kvm_arch_create_vcpu_debugfs(vcpu); +#endif } /* @@ -2649,9 +2662,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) if (r) goto vcpu_destroy; - r = kvm_create_vcpu_debugfs(vcpu); - if (r) - goto vcpu_destroy; + kvm_create_vcpu_debugfs(vcpu); mutex_lock(&kvm->lock); if (kvm_get_vcpu_by_id(kvm, id)) { @@ -4205,7 +4216,7 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); - vcpu->preempted = false; + WRITE_ONCE(vcpu->preempted, false); WRITE_ONCE(vcpu->ready, false); kvm_arch_sched_in(vcpu, cpu); @@ -4219,7 +4230,7 @@ static void kvm_sched_out(struct preempt_notifier *pn, struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); if (current->state == TASK_RUNNING) { - vcpu->preempted = true; + WRITE_ONCE(vcpu->preempted, true); WRITE_ONCE(vcpu->ready, true); } kvm_arch_vcpu_put(vcpu); |