diff options
113 files changed, 5632 insertions, 1520 deletions
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9977e845633f..dd3fe231e435 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5034,6 +5034,54 @@ see KVM_XEN_VCPU_SET_ATTR above. The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used with the KVM_XEN_VCPU_GET_ATTR ioctl. + +4.131 KVM_GET_SREGS2 +------------------ + +:Capability: KVM_CAP_SREGS2 +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_sregs2 (out) +:Returns: 0 on success, -1 on error + +Reads special registers from the vcpu. +This ioctl (when supported) replaces the KVM_GET_SREGS. + +:: + +struct kvm_sregs2 { + /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */ + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 flags; + __u64 pdptrs[4]; +}; + +flags values for ``kvm_sregs2``: + +``KVM_SREGS2_FLAGS_PDPTRS_VALID`` + + Indicates thats the struct contain valid PDPTR values. + + +4.132 KVM_SET_SREGS2 +------------------ + +:Capability: KVM_CAP_SREGS2 +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_sregs2 (in) +:Returns: 0 on success, -1 on error + +Writes special registers into the vcpu. +See KVM_GET_SREGS2 for the data structures. +This ioctl (when supported) replaces the KVM_SET_SREGS. + + 5. The kvm_run structure ======================== @@ -6909,3 +6957,33 @@ This capability is always enabled. This capability indicates that the KVM virtual PTP service is supported in the host. A VMM can check whether the service is available to the guest on migration. + +8.33 KVM_CAP_HYPERV_ENFORCE_CPUID +----------------------------- + +Architectures: x86 + +When enabled, KVM will disable emulated Hyper-V features provided to the +guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all +currently implmented Hyper-V features are provided unconditionally when +Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001) +leaf. + +8.34 KVM_CAP_EXIT_HYPERCALL +--------------------------- + +:Capability: KVM_CAP_EXIT_HYPERCALL +:Architectures: x86 +:Type: vm + +This capability, if enabled, will cause KVM to exit to userspace +with KVM_EXIT_HYPERCALL exit reason to process some hypercalls. + +Calling KVM_CHECK_EXTENSION for this capability will return a bitmask +of hypercalls that can be configured to exit to userspace. +Right now, the only such hypercall is KVM_HC_MAP_GPA_RANGE. + +The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset +of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace +the hypercalls whose corresponding bit is in the argument, and return +ENOSYS for the others. diff --git a/Documentation/virt/kvm/cpuid.rst b/Documentation/virt/kvm/cpuid.rst index cf62162d4be2..bda3e3e737d7 100644 --- a/Documentation/virt/kvm/cpuid.rst +++ b/Documentation/virt/kvm/cpuid.rst @@ -96,6 +96,13 @@ KVM_FEATURE_MSI_EXT_DEST_ID 15 guest checks this feature bit before using extended destination ID bits in MSI address bits 11-5. +KVM_FEATURE_HC_MAP_GPA_RANGE 16 guest checks this feature bit before + using the map gpa range hypercall + to notify the page state change + +KVM_FEATURE_MIGRATION_CONTROL 17 guest checks this feature bit before + using MSR_KVM_MIGRATION_CONTROL + KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 24 host will warn if no guest-side per-cpu warps are expected in kvmclock diff --git a/Documentation/virt/kvm/hypercalls.rst b/Documentation/virt/kvm/hypercalls.rst index ed4fddd364ea..e56fa8b9cfca 100644 --- a/Documentation/virt/kvm/hypercalls.rst +++ b/Documentation/virt/kvm/hypercalls.rst @@ -169,3 +169,24 @@ a0: destination APIC ID :Usage example: When sending a call-function IPI-many to vCPUs, yield if any of the IPI target vCPUs was preempted. + +8. KVM_HC_MAP_GPA_RANGE +------------------------- +:Architecture: x86 +:Status: active +:Purpose: Request KVM to map a GPA range with the specified attributes. + +a0: the guest physical address of the start page +a1: the number of (4kb) pages (must be contiguous in GPA space) +a2: attributes + + Where 'attributes' : + * bits 3:0 - preferred page size encoding 0 = 4kb, 1 = 2mb, 2 = 1gb, etc... + * bit 4 - plaintext = 0, encrypted = 1 + * bits 63:5 - reserved (must be zero) + +**Implementation note**: this hypercall is implemented in userspace via +the KVM_CAP_EXIT_HYPERCALL capability. Userspace must enable that capability +before advertising KVM_FEATURE_HC_MAP_GPA_RANGE in the guest CPUID. In +addition, if the guest supports KVM_FEATURE_MIGRATION_CONTROL, userspace +must also set up an MSR filter to process writes to MSR_KVM_MIGRATION_CONTROL. diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 1fc860c007a3..35eca377543d 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -16,6 +16,11 @@ The acquisition orders for mutexes are as follows: - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring them together is quite rare. +- Unlike kvm->slots_lock, kvm->slots_arch_lock is released before + synchronize_srcu(&kvm->srcu). Therefore kvm->slots_arch_lock + can be taken inside a kvm->srcu read-side critical section, + while kvm->slots_lock cannot. + On x86: - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/mmu.rst index 5bfe28b0728e..20d85daed395 100644 --- a/Documentation/virt/kvm/mmu.rst +++ b/Documentation/virt/kvm/mmu.rst @@ -171,8 +171,8 @@ Shadow pages contain the following information: shadow pages) so role.quadrant takes values in the range 0..3. Each quadrant maps 1GB virtual address space. role.access: - Inherited guest access permissions in the form uwx. Note execute - permission is positive, not negative. + Inherited guest access permissions from the parent ptes in the form uwx. + Note execute permission is positive, not negative. role.invalid: The page is invalid and should not be used. It is a root page that is currently pinned (by a cpu hardware register pointing to it); once it is diff --git a/Documentation/virt/kvm/msr.rst b/Documentation/virt/kvm/msr.rst index e37a14c323d2..9315fc385fb0 100644 --- a/Documentation/virt/kvm/msr.rst +++ b/Documentation/virt/kvm/msr.rst @@ -376,3 +376,16 @@ data: write '1' to bit 0 of the MSR, this causes the host to re-scan its queue and check if there are more notifications pending. The MSR is available if KVM_FEATURE_ASYNC_PF_INT is present in CPUID. + +MSR_KVM_MIGRATION_CONTROL: + 0x4b564d08 + +data: + This MSR is available if KVM_FEATURE_MIGRATION_CONTROL is present in + CPUID. Bit 0 represents whether live migration of the guest is allowed. + + When a guest is started, bit 0 will be 0 if the guest has encrypted + memory and 1 if the guest does not have encrypted memory. If the + guest is communicating page encryption status to the host using the + ``KVM_HC_MAP_GPA_RANGE`` hypercall, it can set bit 0 in this MSR to + allow live migration of the guest. diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index 5feb3706a7ae..af1b37441e0a 100644 --- a/Documentation/virt/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst @@ -118,10 +118,12 @@ KVM_REQ_MMU_RELOAD necessary to inform each VCPU to completely refresh the tables. This request is used for that. -KVM_REQ_PENDING_TIMER +KVM_REQ_UNBLOCK - This request may be made from a timer handler run on the host on behalf - of a VCPU. It informs the VCPU thread to inject a timer interrupt. + This request informs the vCPU to exit kvm_vcpu_block. It is used for + example from timer handlers that run on the host on behalf of a vCPU, + or in order to update the interrupt routing and ensure that assigned + devices will wake up the vCPU. KVM_REQ_UNHALT diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index cf8df032b9c3..5e9b33cbac51 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -63,6 +63,7 @@ #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19 #define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20 +#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 21 #ifndef __ASSEMBLY__ @@ -201,6 +202,8 @@ extern void __kvm_timer_set_cntvoff(u64 cntvoff); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); +extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu); + extern u64 __vgic_v3_get_gic_config(void); extern u64 __vgic_v3_read_vmcr(void); extern void __vgic_v3_write_vmcr(u32 vmcr); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f612c090f2e4..01b9857757f2 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -463,4 +463,9 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC; } +static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature) +{ + return test_bit(feature, vcpu->arch.features); +} + #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7cd7d5c8c4bc..d56f365b38a8 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -556,7 +556,7 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) } struct kvm_vm_stat { - ulong remote_tlb_flush; + u64 remote_tlb_flush; }; struct kvm_vcpu_stat { diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1cb39c0803a4..e720148232a0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -720,11 +720,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) return ret; } - if (run->immediate_exit) - return -EINTR; - vcpu_load(vcpu); + if (run->immediate_exit) { + ret = -EINTR; + goto out; + } + kvm_sigset_activate(vcpu); ret = 1; @@ -897,6 +899,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_sigset_deactivate(vcpu); +out: + /* + * In the unlikely event that we are returning to userspace + * with pending exceptions or PC adjustment, commit these + * adjustments in order to give userspace a consistent view of + * the vcpu state. Note that this relies on __kvm_adjust_pc() + * being preempt-safe on VHE. + */ + if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_INCREMENT_PC))) + kvm_call_hyp(__kvm_adjust_pc, vcpu); + vcpu_put(vcpu); return ret; } diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 73629094f903..11541b94b328 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -296,7 +296,7 @@ static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) *vcpu_pc(vcpu) = vect_offset; } -void kvm_inject_exception(struct kvm_vcpu *vcpu) +static void kvm_inject_exception(struct kvm_vcpu *vcpu) { if (vcpu_el1_is_32bit(vcpu)) { switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) { @@ -329,3 +329,19 @@ void kvm_inject_exception(struct kvm_vcpu *vcpu) } } } + +/* + * Adjust the guest PC (and potentially exception state) depending on + * flags provided by the emulation code. + */ +void __kvm_adjust_pc(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { + kvm_inject_exception(vcpu); + vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_EXCEPT_MASK); + } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { + kvm_skip_instr(vcpu); + vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; + } +} diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h index 61716359035d..4fdfeabefeb4 100644 --- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h @@ -13,8 +13,6 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> -void kvm_inject_exception(struct kvm_vcpu *vcpu); - static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { @@ -44,22 +42,6 @@ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) } /* - * Adjust the guest PC on entry, depending on flags provided by EL1 - * for the purpose of emulation (MMIO, sysreg) or exception injection. - */ -static inline void __adjust_pc(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { - kvm_inject_exception(vcpu); - vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | - KVM_ARM64_EXCEPT_MASK); - } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { - kvm_skip_instr(vcpu); - vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; - } -} - -/* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index f36420a80474..1632f001f4ed 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -28,6 +28,13 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu)); } +static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); + + __kvm_adjust_pc(kern_hyp_va(vcpu)); +} + static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt) { __kvm_flush_vm_context(); @@ -170,6 +177,7 @@ typedef void (*hcall_t)(struct kvm_cpu_context *); static const hcall_t host_hcall[] = { HANDLE_FUNC(__kvm_vcpu_run), + HANDLE_FUNC(__kvm_adjust_pc), HANDLE_FUNC(__kvm_flush_vm_context), HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), HANDLE_FUNC(__kvm_tlb_flush_vmid), diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index e342f7f4f4fb..4b60c0056c04 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -23,8 +23,8 @@ extern unsigned long hyp_nr_cpus; struct host_kvm host_kvm; -struct hyp_pool host_s2_mem; -struct hyp_pool host_s2_dev; +static struct hyp_pool host_s2_mem; +static struct hyp_pool host_s2_dev; /* * Copies of the host's CPU features registers holding sanitized values. diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 7488f53b0aa2..a3d3a275344e 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -17,7 +17,6 @@ #include <nvhe/trap_handler.h> struct hyp_pool hpool; -struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; unsigned long hyp_nr_cpus; #define hyp_percpu_size ((unsigned long)__per_cpu_end - \ @@ -27,6 +26,7 @@ static void *vmemmap_base; static void *hyp_pgt_base; static void *host_s2_mem_pgt_base; static void *host_s2_dev_pgt_base; +static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; static int divide_memory_pool(void *virt, unsigned long size) { diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index e9f6ea704d07..f7af9688c1f7 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <hyp/sysreg-sr.h> @@ -201,7 +200,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) */ __debug_save_host_buffers_nvhe(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); /* * We must restore the 32-bit state before the sysregs, thanks diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 7b8f7db5c1ed..b3229924d243 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <linux/arm-smccc.h> @@ -132,7 +131,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __load_guest_stage2(vcpu->arch.hw_mmu); __activate_traps(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c5d1f3c87dbd..c10207fed2f3 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1156,13 +1156,13 @@ out_unlock: bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; __unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); - return 0; + return false; } bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1170,7 +1170,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) kvm_pfn_t pfn = pte_pfn(range->pte); if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(range->end - range->start != 1); @@ -1190,7 +1190,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) PAGE_SIZE, __pfn_to_phys(pfn), KVM_PGTABLE_PROT_R, NULL); - return 0; + return false; } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1200,7 +1200,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) pte_t pte; if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); @@ -1213,7 +1213,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 956cdc240148..d37ebee085cf 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -166,6 +166,25 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) return 0; } +static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu *tmp; + bool is32bit; + int i; + + is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) + return false; + + /* Check that the vcpus are either all 32bit or all 64bit */ + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit) + return false; + } + + return true; +} + /** * kvm_reset_vcpu - sets core registers and sys_regs to reset value * @vcpu: The VCPU pointer @@ -217,13 +236,14 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } } + if (!vcpu_allowed_register_width(vcpu)) { + ret = -EINVAL; + goto out; + } + switch (vcpu->arch.target) { default: if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { - if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) { - ret = -EINVAL; - goto out; - } pstate = VCPU_RESET_PSTATE_SVC; } else { pstate = VCPU_RESET_PSTATE_EL1; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 76ea2800c33e..1a7968ad078c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -399,14 +399,14 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -414,7 +414,7 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -424,7 +424,7 @@ static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -434,21 +434,21 @@ static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = rd->val; } static bool trap_bcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -456,7 +456,7 @@ static bool trap_bcr(struct kvm_vcpu *vcpu, static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -467,7 +467,7 @@ static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -477,22 +477,22 @@ static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = rd->val; } static bool trap_wvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]); + trace_trap_reg(__func__, rd->CRm, p->is_write, + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]); return true; } @@ -500,7 +500,7 @@ static bool trap_wvr(struct kvm_vcpu *vcpu, static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -510,7 +510,7 @@ static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -520,21 +520,21 @@ static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = rd->val; } static bool trap_wcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -542,7 +542,7 @@ static bool trap_wcr(struct kvm_vcpu *vcpu, static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -552,7 +552,7 @@ static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -562,7 +562,7 @@ static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = rd->val; } static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index fca4547d580f..4245c082095f 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -109,7 +109,7 @@ static inline bool kvm_is_error_hva(unsigned long addr) } struct kvm_vm_stat { - ulong remote_tlb_flush; + u64 remote_tlb_flush; }; struct kvm_vcpu_stat { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 6904ce9e8190..dd8bd4706259 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -51,6 +51,7 @@ /* PPC-specific vcpu->requests bit members */ #define KVM_REQ_WATCHDOG KVM_ARCH_REQ(0) #define KVM_REQ_EPR_EXIT KVM_ARCH_REQ(1) +#define KVM_REQ_PENDING_TIMER KVM_ARCH_REQ(2) #include <linux/mmu_notifier.h> @@ -80,9 +81,9 @@ struct kvmppc_book3s_shadow_vcpu; struct kvm_nested_guest; struct kvm_vm_stat { - ulong remote_tlb_flush; - ulong num_2M_pages; - ulong num_1G_pages; + u64 remote_tlb_flush; + u64 num_2M_pages; + u64 num_1G_pages; }; struct kvm_vcpu_stat { diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 279eae8f9dbc..7e73e5bfe4ba 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4103,7 +4103,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) break; } cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 606f5cc579b2..f1366ce609e3 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -52,7 +52,7 @@ * Support for passing hypercall input parameter block via XMM * registers is available */ -#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4) +#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) /* Support for a virtual guest idle state is available */ #define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) /* Frequency MSRs available */ @@ -61,6 +61,11 @@ #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) /* Support for debug MSRs available */ #define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) +/* + * Support for returning hypercall output block via XMM + * registers is available + */ +#define HV_X64_HYPERCALL_XMM_OUTPUT_AVAILABLE BIT(15) /* stimer Direct Mode is available */ #define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) @@ -133,6 +138,15 @@ #define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) #define HV_X64_NESTED_MSR_BITMAP BIT(19) +/* + * This is specific to AMD and specifies that enlightened TLB flush is + * supported. If guest opts in to this feature, ASID invalidations only + * flushes gva -> hpa mapping entries. To flush the TLB entries derived + * from NPT, hypercalls should be used (HvFlushGuestPhysicalAddressSpace + * or HvFlushGuestPhysicalAddressList). + */ +#define HV_X64_NESTED_ENLIGHTENED_TLB BIT(22) + /* HYPERV_CPUID_ISOLATION_CONFIG.EAX bits. */ #define HV_PARAVISOR_PRESENT BIT(0) @@ -314,6 +328,9 @@ struct hv_tsc_emulation_status { #define HV_X64_MSR_TSC_REFERENCE_ENABLE 0x00000001 #define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT 12 +/* Number of XMM registers used in hypercall input/output */ +#define HV_HYPERCALL_MAX_XMM_REGISTERS 6 + struct hv_nested_enlightenments_control { struct { __u32 directhypercall:1; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 323641097f63..a12a4987154e 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -87,7 +87,10 @@ KVM_X86_OP(set_identity_map_addr) KVM_X86_OP(get_mt_mask) KVM_X86_OP(load_mmu_pgd) KVM_X86_OP_NULL(has_wbinvd_exit) -KVM_X86_OP(write_l1_tsc_offset) +KVM_X86_OP(get_l2_tsc_offset) +KVM_X86_OP(get_l2_tsc_multiplier) +KVM_X86_OP(write_tsc_offset) +KVM_X86_OP(write_tsc_multiplier) KVM_X86_OP(get_exit_info) KVM_X86_OP(check_intercept) KVM_X86_OP(handle_exit_irqoff) @@ -99,14 +102,15 @@ KVM_X86_OP_NULL(post_block) KVM_X86_OP_NULL(vcpu_blocking) KVM_X86_OP_NULL(vcpu_unblocking) KVM_X86_OP_NULL(update_pi_irte) +KVM_X86_OP_NULL(start_assignment) KVM_X86_OP_NULL(apicv_post_state_restore) KVM_X86_OP_NULL(dy_apicv_has_pending_interrupt) KVM_X86_OP_NULL(set_hv_timer) KVM_X86_OP_NULL(cancel_hv_timer) KVM_X86_OP(setup_mce) KVM_X86_OP(smi_allowed) -KVM_X86_OP(pre_enter_smm) -KVM_X86_OP(pre_leave_smm) +KVM_X86_OP(enter_smm) +KVM_X86_OP(leave_smm) KVM_X86_OP(enable_smi_window) KVM_X86_OP_NULL(mem_enc_op) KVM_X86_OP_NULL(mem_enc_reg_region) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 55efbacfc244..e11d64aa0bcd 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -85,7 +85,7 @@ #define KVM_REQ_APICV_UPDATE \ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) -#define KVM_REQ_HV_TLB_FLUSH \ +#define KVM_REQ_TLB_FLUSH_GUEST \ KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29) @@ -543,6 +543,15 @@ struct kvm_vcpu_hv { struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); cpumask_t tlb_flush; + bool enforce_cpuid; + struct { + u32 features_eax; /* HYPERV_CPUID_FEATURES.EAX */ + u32 features_ebx; /* HYPERV_CPUID_FEATURES.EBX */ + u32 features_edx; /* HYPERV_CPUID_FEATURES.EDX */ + u32 enlightenments_eax; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ + u32 enlightenments_ebx; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EBX */ + u32 syndbg_cap_eax; /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ + } cpuid_cache; }; /* Xen HVM per vcpu emulation context */ @@ -707,7 +716,7 @@ struct kvm_vcpu_arch { } st; u64 l1_tsc_offset; - u64 tsc_offset; + u64 tsc_offset; /* current tsc offset */ u64 last_guest_tsc; u64 last_host_tsc; u64 tsc_offset_adjustment; @@ -721,7 +730,8 @@ struct kvm_vcpu_arch { u32 virtual_tsc_khz; s64 ia32_tsc_adjust_msr; u64 msr_ia32_power_ctl; - u64 tsc_scaling_ratio; + u64 l1_tsc_scaling_ratio; + u64 tsc_scaling_ratio; /* current scaling ratio */ atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ @@ -851,6 +861,16 @@ struct kvm_vcpu_arch { /* Protected Guests */ bool guest_state_protected; + + /* + * Set when PDPTS were loaded directly by the userspace without + * reading the guest memory + */ + bool pdptrs_from_userspace; + +#if IS_ENABLED(CONFIG_HYPERV) + hpa_t hv_root_tdp; +#endif }; struct kvm_lpage_info { @@ -1067,6 +1087,8 @@ struct kvm_arch { u32 user_space_msr_mask; struct kvm_x86_msr_filter __rcu *msr_filter; + u32 hypercall_exit_enabled; + /* Guest can access the SGX PROVISIONKEY. */ bool sgx_provisioning_allowed; @@ -1124,20 +1146,31 @@ struct kvm_arch { */ spinlock_t tdp_mmu_pages_lock; #endif /* CONFIG_X86_64 */ + + /* + * If set, rmaps have been allocated for all memslots and should be + * allocated for any newly created or modified memslots. + */ + bool memslots_have_rmaps; + +#if IS_ENABLED(CONFIG_HYPERV) + hpa_t hv_root_tdp; + spinlock_t hv_root_tdp_lock; +#endif }; struct kvm_vm_stat { - ulong mmu_shadow_zapped; - ulong mmu_pte_write; - ulong mmu_pde_zapped; - ulong mmu_flooded; - ulong mmu_recycled; - ulong mmu_cache_miss; - ulong mmu_unsync; - ulong remote_tlb_flush; - ulong lpages; - ulong nx_lpage_splits; - ulong max_mmu_page_hash_collisions; + u64 mmu_shadow_zapped; + u64 mmu_pte_write; + u64 mmu_pde_zapped; + u64 mmu_flooded; + u64 mmu_recycled; + u64 mmu_cache_miss; + u64 mmu_unsync; + u64 remote_tlb_flush; + u64 lpages; + u64 nx_lpage_splits; + u64 max_mmu_page_hash_collisions; }; struct kvm_vcpu_stat { @@ -1173,6 +1206,7 @@ struct kvm_vcpu_stat { u64 nested_run; u64 directed_yield_attempted; u64 directed_yield_successful; + u64 guest_mode; }; struct x86_instruction_info; @@ -1304,8 +1338,10 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - /* Returns actual tsc_offset set in active VMCS */ - u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); + u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); + u64 (*get_l2_tsc_multiplier)(struct kvm_vcpu *vcpu); + void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); + void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu, u64 multiplier); /* * Retrieve somewhat arbitrary exit information. Intended to be used @@ -1352,6 +1388,7 @@ struct kvm_x86_ops { int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); + void (*start_assignment)(struct kvm *kvm); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); @@ -1362,8 +1399,8 @@ struct kvm_x86_ops { void (*setup_mce)(struct kvm_vcpu *vcpu); int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); - int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); - int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); + int (*enter_smm)(struct kvm_vcpu *vcpu, char *smstate); + int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); void (*enable_smi_window)(struct kvm_vcpu *vcpu); int (*mem_enc_op)(struct kvm *kvm, void __user *argp); @@ -1422,6 +1459,7 @@ struct kvm_arch_async_pf { extern u32 __read_mostly kvm_nr_uret_msrs; extern u64 __read_mostly host_efer; extern bool __read_mostly allow_smaller_maxphyaddr; +extern bool __read_mostly enable_apicv; extern struct kvm_x86_ops kvm_x86_ops; #define KVM_X86_OP(func) \ @@ -1476,7 +1514,6 @@ unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); -bool pdptrs_changed(struct kvm_vcpu *vcpu); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); @@ -1649,6 +1686,7 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, ulong roots_to_free); +void kvm_mmu_free_guest_mode_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu); gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, @@ -1661,7 +1699,6 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); bool kvm_apicv_activated(struct kvm *kvm); -void kvm_apicv_init(struct kvm *kvm, bool enable); void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); void kvm_request_apicv_update(struct kvm *kvm, bool activate, unsigned long bit); @@ -1674,8 +1711,7 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gva_t gva, hpa_t root_hpa); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); -void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush, - bool skip_mmu_sync); +void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level, int tdp_huge_page_level); @@ -1787,8 +1823,10 @@ static inline bool kvm_is_supported_user_return_msr(u32 msr) return kvm_find_user_return_msr(msr) >= 0; } -u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc, u64 ratio); u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); +u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier); +u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier); unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); @@ -1862,4 +1900,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) int kvm_cpu_dirty_log_size(void); +int alloc_all_memslots_rmaps(struct kvm *kvm); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 772e60efe243..e322676039f4 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -156,6 +156,12 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u64 avic_physical_id; /* Offset 0xf8 */ u8 reserved_7[8]; u64 vmsa_pa; /* Used for an SEV-ES guest */ + u8 reserved_8[720]; + /* + * Offset 0x3e0, 32 bytes reserved + * for use by hypervisor/software. + */ + u8 reserved_sw[32]; }; @@ -314,7 +320,7 @@ struct ghcb { #define EXPECTED_VMCB_SAVE_AREA_SIZE 1032 -#define EXPECTED_VMCB_CONTROL_AREA_SIZE 272 +#define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024 #define EXPECTED_GHCB_SIZE PAGE_SIZE static inline void __unused_size_checks(void) @@ -326,7 +332,6 @@ static inline void __unused_size_checks(void) struct vmcb { struct vmcb_control_area control; - u8 reserved_control[1024 - sizeof(struct vmcb_control_area)]; struct vmcb_save_area save; } __packed; diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 0662f644aad9..a6c327f8ad9e 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -159,6 +159,19 @@ struct kvm_sregs { __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; }; +struct kvm_sregs2 { + /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */ + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 flags; + __u64 pdptrs[4]; +}; +#define KVM_SREGS2_FLAGS_PDPTRS_VALID 1 + /* for KVM_GET_FPU and KVM_SET_FPU */ struct kvm_fpu { __u8 fpr[8][16]; diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 950afebfba88..5146bbab84d4 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -33,6 +33,8 @@ #define KVM_FEATURE_PV_SCHED_YIELD 13 #define KVM_FEATURE_ASYNC_PF_INT 14 #define KVM_FEATURE_MSI_EXT_DEST_ID 15 +#define KVM_FEATURE_HC_MAP_GPA_RANGE 16 +#define KVM_FEATURE_MIGRATION_CONTROL 17 #define KVM_HINTS_REALTIME 0 @@ -54,6 +56,7 @@ #define MSR_KVM_POLL_CONTROL 0x4b564d05 #define MSR_KVM_ASYNC_PF_INT 0x4b564d06 #define MSR_KVM_ASYNC_PF_ACK 0x4b564d07 +#define MSR_KVM_MIGRATION_CONTROL 0x4b564d08 struct kvm_steal_time { __u64 steal; @@ -90,6 +93,16 @@ struct kvm_clock_pairing { /* MSR_KVM_ASYNC_PF_INT */ #define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0) +/* MSR_KVM_MIGRATION_CONTROL */ +#define KVM_MIGRATION_READY (1 << 0) + +/* KVM_HC_MAP_GPA_RANGE */ +#define KVM_MAP_GPA_RANGE_PAGE_SZ_4K 0 +#define KVM_MAP_GPA_RANGE_PAGE_SZ_2M (1 << 0) +#define KVM_MAP_GPA_RANGE_PAGE_SZ_1G (1 << 1) +#define KVM_MAP_GPA_RANGE_ENC_STAT(n) (n << 4) +#define KVM_MAP_GPA_RANGE_ENCRYPTED KVM_MAP_GPA_RANGE_ENC_STAT(1) +#define KVM_MAP_GPA_RANGE_DECRYPTED KVM_MAP_GPA_RANGE_ENC_STAT(0) /* Operations for KVM_HC_MMU_OP */ #define KVM_MMU_OP_WRITE_PTE 1 diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 554f75fe013c..efa969325ede 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -110,6 +110,9 @@ #define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff +/* Exit code reserved for hypervisor/software use */ +#define SVM_EXIT_SW 0xf0000000 + #define SVM_EXIT_ERR -1 #define SVM_EXIT_REASONS \ diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 22f13343b5da..c268c2730048 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -252,6 +252,7 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus) static void __init ms_hyperv_init_platform(void) { + int hv_max_functions_eax; int hv_host_info_eax; int hv_host_info_ebx; int hv_host_info_ecx; @@ -269,6 +270,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); + hv_max_functions_eax = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS); + pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n", ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints, ms_hyperv.misc_features); @@ -298,8 +301,7 @@ static void __init ms_hyperv_init_platform(void) /* * Extract host information. */ - if (cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS) >= - HYPERV_CPUID_VERSION) { + if (hv_max_functions_eax >= HYPERV_CPUID_VERSION) { hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION); hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION); hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION); @@ -325,9 +327,11 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); } - if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) { + if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) { ms_hyperv.nested_features = cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); + pr_info("Hyper-V: Nested features: 0x%x\n", + ms_hyperv.nested_features); } /* diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index f6b93a35ce14..7a78b88c0f1a 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -46,6 +46,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO select SRCU + select HAVE_KVM_PM_NOTIFIER if PM help Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index c589db5d91b3..83331376b779 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -18,6 +18,11 @@ kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \ mmu/spte.o + +ifdef CONFIG_HYPERV +kvm-y += kvm_onhyperv.o +endif + kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o kvm-$(CONFIG_KVM_XEN) += xen.o @@ -27,6 +32,10 @@ kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o svm/sev.o +ifdef CONFIG_HYPERV +kvm-amd-y += svm/svm_onhyperv.o +endif + obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o obj-$(CONFIG_KVM_AMD) += kvm-amd.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9a48f138832d..b4da665bb892 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -655,6 +655,7 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) entry->ecx = F(RDPID); ++array->nent; + break; default: break; } diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 7e818d64bb4d..95a98413dc32 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -17,6 +17,15 @@ static int vcpu_get_timer_advance_ns(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(vcpu_timer_advance_ns_fops, vcpu_get_timer_advance_ns, NULL, "%llu\n"); +static int vcpu_get_guest_mode(void *data, u64 *val) +{ + struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data; + *val = vcpu->stat.guest_mode; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(vcpu_guest_mode_fops, vcpu_get_guest_mode, NULL, "%lld\n"); + static int vcpu_get_tsc_offset(void *data, u64 *val) { struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data; @@ -45,6 +54,8 @@ DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_frac_fops, vcpu_get_tsc_scaling_frac_bi void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) { + debugfs_create_file("guest_mode", 0444, debugfs_dentry, vcpu, + &vcpu_guest_mode_fops); debugfs_create_file("tsc-offset", 0444, debugfs_dentry, vcpu, &vcpu_tsc_offset_fops); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8a0ccdb56076..2837110e66ed 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -22,7 +22,6 @@ #include "kvm_cache_regs.h" #include "kvm_emulate.h" #include <linux/stringify.h> -#include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/nospec-branch.h> @@ -1081,116 +1080,14 @@ static void fetch_register_operand(struct operand *op) } } -static void emulator_get_fpu(void) -{ - fpregs_lock(); - - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); -} - -static void emulator_put_fpu(void) -{ - fpregs_unlock(); -} - -static void read_sse_reg(sse128_t *data, int reg) -{ - emulator_get_fpu(); - switch (reg) { - case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; - case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; - case 2: asm("movdqa %%xmm2, %0" : "=m"(*data)); break; - case 3: asm("movdqa %%xmm3, %0" : "=m"(*data)); break; - case 4: asm("movdqa %%xmm4, %0" : "=m"(*data)); break; - case 5: asm("movdqa %%xmm5, %0" : "=m"(*data)); break; - case 6: asm("movdqa %%xmm6, %0" : "=m"(*data)); break; - case 7: asm("movdqa %%xmm7, %0" : "=m"(*data)); break; -#ifdef CONFIG_X86_64 - case 8: asm("movdqa %%xmm8, %0" : "=m"(*data)); break; - case 9: asm("movdqa %%xmm9, %0" : "=m"(*data)); break; - case 10: asm("movdqa %%xmm10, %0" : "=m"(*data)); break; - case 11: asm("movdqa %%xmm11, %0" : "=m"(*data)); break; - case 12: asm("movdqa %%xmm12, %0" : "=m"(*data)); break; - case 13: asm("movdqa %%xmm13, %0" : "=m"(*data)); break; - case 14: asm("movdqa %%xmm14, %0" : "=m"(*data)); break; - case 15: asm("movdqa %%xmm15, %0" : "=m"(*data)); break; -#endif - default: BUG(); - } - emulator_put_fpu(); -} - -static void write_sse_reg(sse128_t *data, int reg) -{ - emulator_get_fpu(); - switch (reg) { - case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; - case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; - case 2: asm("movdqa %0, %%xmm2" : : "m"(*data)); break; - case 3: asm("movdqa %0, %%xmm3" : : "m"(*data)); break; - case 4: asm("movdqa %0, %%xmm4" : : "m"(*data)); break; - case 5: asm("movdqa %0, %%xmm5" : : "m"(*data)); break; - case 6: asm("movdqa %0, %%xmm6" : : "m"(*data)); break; - case 7: asm("movdqa %0, %%xmm7" : : "m"(*data)); break; -#ifdef CONFIG_X86_64 - case 8: asm("movdqa %0, %%xmm8" : : "m"(*data)); break; - case 9: asm("movdqa %0, %%xmm9" : : "m"(*data)); break; - case 10: asm("movdqa %0, %%xmm10" : : "m"(*data)); break; - case 11: asm("movdqa %0, %%xmm11" : : "m"(*data)); break; - case 12: asm("movdqa %0, %%xmm12" : : "m"(*data)); break; - case 13: asm("movdqa %0, %%xmm13" : : "m"(*data)); break; - case 14: asm("movdqa %0, %%xmm14" : : "m"(*data)); break; - case 15: asm("movdqa %0, %%xmm15" : : "m"(*data)); break; -#endif - default: BUG(); - } - emulator_put_fpu(); -} - -static void read_mmx_reg(u64 *data, int reg) -{ - emulator_get_fpu(); - switch (reg) { - case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; - case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; - case 2: asm("movq %%mm2, %0" : "=m"(*data)); break; - case 3: asm("movq %%mm3, %0" : "=m"(*data)); break; - case 4: asm("movq %%mm4, %0" : "=m"(*data)); break; - case 5: asm("movq %%mm5, %0" : "=m"(*data)); break; - case 6: asm("movq %%mm6, %0" : "=m"(*data)); break; - case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; - default: BUG(); - } - emulator_put_fpu(); -} - -static void write_mmx_reg(u64 *data, int reg) -{ - emulator_get_fpu(); - switch (reg) { - case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; - case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; - case 2: asm("movq %0, %%mm2" : : "m"(*data)); break; - case 3: asm("movq %0, %%mm3" : : "m"(*data)); break; - case 4: asm("movq %0, %%mm4" : : "m"(*data)); break; - case 5: asm("movq %0, %%mm5" : : "m"(*data)); break; - case 6: asm("movq %0, %%mm6" : : "m"(*data)); break; - case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; - default: BUG(); - } - emulator_put_fpu(); -} - static int em_fninit(struct x86_emulate_ctxt *ctxt) { if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); - emulator_get_fpu(); + kvm_fpu_get(); asm volatile("fninit"); - emulator_put_fpu(); + kvm_fpu_put(); return X86EMUL_CONTINUE; } @@ -1201,9 +1098,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); - emulator_get_fpu(); + kvm_fpu_get(); asm volatile("fnstcw %0": "+m"(fcw)); - emulator_put_fpu(); + kvm_fpu_put(); ctxt->dst.val = fcw; @@ -1217,9 +1114,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); - emulator_get_fpu(); + kvm_fpu_get(); asm volatile("fnstsw %0": "+m"(fsw)); - emulator_put_fpu(); + kvm_fpu_put(); ctxt->dst.val = fsw; @@ -1238,7 +1135,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = reg; - read_sse_reg(&op->vec_val, reg); + kvm_read_sse_reg(reg, &op->vec_val); return; } if (ctxt->d & Mmx) { @@ -1289,7 +1186,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = ctxt->modrm_rm; - read_sse_reg(&op->vec_val, ctxt->modrm_rm); + kvm_read_sse_reg(ctxt->modrm_rm, &op->vec_val); return rc; } if (ctxt->d & Mmx) { @@ -1866,10 +1763,10 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) op->bytes * op->count); break; case OP_XMM: - write_sse_reg(&op->vec_val, op->addr.xmm); + kvm_write_sse_reg(op->addr.xmm, &op->vec_val); break; case OP_MM: - write_mmx_reg(&op->mm_val, op->addr.mm); + kvm_write_mmx_reg(op->addr.mm, &op->mm_val); break; case OP_NONE: /* no writeback */ @@ -2638,8 +2535,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) ctxt->ops->set_nmi_mask(ctxt, false); - ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) & - ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK)); + ctxt->ops->exiting_smm(ctxt); /* * Get back to real mode, to prepare a safe state in which to load @@ -2678,12 +2574,12 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) } /* - * Give pre_leave_smm() a chance to make ISA-specific changes to the - * vCPU state (e.g. enter guest mode) before loading state from the SMM + * Give leave_smm() a chance to make ISA-specific changes to the vCPU + * state (e.g. enter guest mode) before loading state from the SMM * state-save area. */ - if (ctxt->ops->pre_leave_smm(ctxt, buf)) - return X86EMUL_UNHANDLEABLE; + if (ctxt->ops->leave_smm(ctxt, buf)) + goto emulate_shutdown; #ifdef CONFIG_X86_64 if (emulator_has_longmode(ctxt)) @@ -2692,13 +2588,21 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) #endif ret = rsm_load_state_32(ctxt, buf); - if (ret != X86EMUL_CONTINUE) { - /* FIXME: should triple fault */ - return X86EMUL_UNHANDLEABLE; - } + if (ret != X86EMUL_CONTINUE) + goto emulate_shutdown; - ctxt->ops->post_leave_smm(ctxt); + /* + * Note, the ctxt->ops callbacks are responsible for handling side + * effects when writing MSRs and CRs, e.g. MMU context resets, CPUID + * runtime updates, etc... If that changes, e.g. this flow is moved + * out of the emulator to make it look more like enter_smm(), then + * those side effects need to be explicitly handled for both success + * and shutdown. + */ + return X86EMUL_CONTINUE; +emulate_shutdown: + ctxt->ops->triple_fault(ctxt); return X86EMUL_CONTINUE; } @@ -4124,11 +4028,11 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - emulator_get_fpu(); + kvm_fpu_get(); rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); - emulator_put_fpu(); + kvm_fpu_put(); if (rc != X86EMUL_CONTINUE) return rc; @@ -4172,7 +4076,7 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - emulator_get_fpu(); + kvm_fpu_get(); if (size < __fxstate_size(16)) { rc = fxregs_fixup(&fx_state, size); @@ -4189,7 +4093,7 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); out: - emulator_put_fpu(); + kvm_fpu_put(); return rc; } @@ -5111,7 +5015,7 @@ done: return rc; } -int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) +int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type) { int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; @@ -5322,7 +5226,8 @@ done_prefixes: ctxt->execute = opcode.u.execute; - if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD))) + if (unlikely(emulation_type & EMULTYPE_TRAP_UD) && + likely(!(ctxt->d & EmulateOnUD))) return EMULATION_FAILED; if (unlikely(ctxt->d & @@ -5436,9 +5341,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { int rc; - emulator_get_fpu(); + kvm_fpu_get(); rc = asm_safe("fwait"); - emulator_put_fpu(); + kvm_fpu_put(); if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); @@ -5449,7 +5354,7 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) static void fetch_possible_mmx_operand(struct operand *op) { if (op->type == OP_MM) - read_mmx_reg(&op->mm_val, op->addr.mm); + kvm_read_mmx_reg(op->addr.mm, &op->mm_val); } static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop) diff --git a/arch/x86/kvm/fpu.h b/arch/x86/kvm/fpu.h new file mode 100644 index 000000000000..3ba12888bf66 --- /dev/null +++ b/arch/x86/kvm/fpu.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __KVM_FPU_H_ +#define __KVM_FPU_H_ + +#include <asm/fpu/api.h> + +typedef u32 __attribute__((vector_size(16))) sse128_t; +#define __sse128_u union { sse128_t vec; u64 as_u64[2]; u32 as_u32[4]; } +#define sse128_lo(x) ({ __sse128_u t; t.vec = x; t.as_u64[0]; }) +#define sse128_hi(x) ({ __sse128_u t; t.vec = x; t.as_u64[1]; }) +#define sse128_l0(x) ({ __sse128_u t; t.vec = x; t.as_u32[0]; }) +#define sse128_l1(x) ({ __sse128_u t; t.vec = x; t.as_u32[1]; }) +#define sse128_l2(x) ({ __sse128_u t; t.vec = x; t.as_u32[2]; }) +#define sse128_l3(x) ({ __sse128_u t; t.vec = x; t.as_u32[3]; }) +#define sse128(lo, hi) ({ __sse128_u t; t.as_u64[0] = lo; t.as_u64[1] = hi; t.vec; }) + +static inline void _kvm_read_sse_reg(int reg, sse128_t *data) +{ + switch (reg) { + case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; + case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; + case 2: asm("movdqa %%xmm2, %0" : "=m"(*data)); break; + case 3: asm("movdqa %%xmm3, %0" : "=m"(*data)); break; + case 4: asm("movdqa %%xmm4, %0" : "=m"(*data)); break; + case 5: asm("movdqa %%xmm5, %0" : "=m"(*data)); break; + case 6: asm("movdqa %%xmm6, %0" : "=m"(*data)); break; + case 7: asm("movdqa %%xmm7, %0" : "=m"(*data)); break; +#ifdef CONFIG_X86_64 + case 8: asm("movdqa %%xmm8, %0" : "=m"(*data)); break; + case 9: asm("movdqa %%xmm9, %0" : "=m"(*data)); break; + case 10: asm("movdqa %%xmm10, %0" : "=m"(*data)); break; + case 11: asm("movdqa %%xmm11, %0" : "=m"(*data)); break; + case 12: asm("movdqa %%xmm12, %0" : "=m"(*data)); break; + case 13: asm("movdqa %%xmm13, %0" : "=m"(*data)); break; + case 14: asm("movdqa %%xmm14, %0" : "=m"(*data)); break; + case 15: asm("movdqa %%xmm15, %0" : "=m"(*data)); break; +#endif + default: BUG(); + } +} + +static inline void _kvm_write_sse_reg(int reg, const sse128_t *data) +{ + switch (reg) { + case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; + case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; + case 2: asm("movdqa %0, %%xmm2" : : "m"(*data)); break; + case 3: asm("movdqa %0, %%xmm3" : : "m"(*data)); break; + case 4: asm("movdqa %0, %%xmm4" : : "m"(*data)); break; + case 5: asm("movdqa %0, %%xmm5" : : "m"(*data)); break; + case 6: asm("movdqa %0, %%xmm6" : : "m"(*data)); break; + case 7: asm("movdqa %0, %%xmm7" : : "m"(*data)); break; +#ifdef CONFIG_X86_64 + case 8: asm("movdqa %0, %%xmm8" : : "m"(*data)); break; + case 9: asm("movdqa %0, %%xmm9" : : "m"(*data)); break; + case 10: asm("movdqa %0, %%xmm10" : : "m"(*data)); break; + case 11: asm("movdqa %0, %%xmm11" : : "m"(*data)); break; + case 12: asm("movdqa %0, %%xmm12" : : "m"(*data)); break; + case 13: asm("movdqa %0, %%xmm13" : : "m"(*data)); break; + case 14: asm("movdqa %0, %%xmm14" : : "m"(*data)); break; + case 15: asm("movdqa %0, %%xmm15" : : "m"(*data)); break; +#endif + default: BUG(); + } +} + +static inline void _kvm_read_mmx_reg(int reg, u64 *data) +{ + switch (reg) { + case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; + case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; + case 2: asm("movq %%mm2, %0" : "=m"(*data)); break; + case 3: asm("movq %%mm3, %0" : "=m"(*data)); break; + case 4: asm("movq %%mm4, %0" : "=m"(*data)); break; + case 5: asm("movq %%mm5, %0" : "=m"(*data)); break; + case 6: asm("movq %%mm6, %0" : "=m"(*data)); break; + case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; + default: BUG(); + } +} + +static inline void _kvm_write_mmx_reg(int reg, const u64 *data) +{ + switch (reg) { + case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; + case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; + case 2: asm("movq %0, %%mm2" : : "m"(*data)); break; + case 3: asm("movq %0, %%mm3" : : "m"(*data)); break; + case 4: asm("movq %0, %%mm4" : : "m"(*data)); break; + case 5: asm("movq %0, %%mm5" : : "m"(*data)); break; + case 6: asm("movq %0, %%mm6" : : "m"(*data)); break; + case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; + default: BUG(); + } +} + +static inline void kvm_fpu_get(void) +{ + fpregs_lock(); + + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); +} + +static inline void kvm_fpu_put(void) +{ + fpregs_unlock(); +} + +static inline void kvm_read_sse_reg(int reg, sse128_t *data) +{ + kvm_fpu_get(); + _kvm_read_sse_reg(reg, data); + kvm_fpu_put(); +} + +static inline void kvm_write_sse_reg(int reg, const sse128_t *data) +{ + kvm_fpu_get(); + _kvm_write_sse_reg(reg, data); + kvm_fpu_put(); +} + +static inline void kvm_read_mmx_reg(int reg, u64 *data) +{ + kvm_fpu_get(); + _kvm_read_mmx_reg(reg, data); + kvm_fpu_put(); +} + +static inline void kvm_write_mmx_reg(int reg, const u64 *data) +{ + kvm_fpu_get(); + _kvm_write_mmx_reg(reg, data); + kvm_fpu_put(); +} + +#endif diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index f98370a39936..b07592ca92f0 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -36,6 +36,7 @@ #include "trace.h" #include "irq.h" +#include "fpu.h" /* "Hv#1" signature */ #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 @@ -273,15 +274,10 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, static bool kvm_hv_is_syndbg_enabled(struct kvm_vcpu *vcpu) { - struct kvm_cpuid_entry2 *entry; - - entry = kvm_find_cpuid_entry(vcpu, - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, - 0); - if (!entry) - return false; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); - return entry->eax & HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + return hv_vcpu->cpuid_cache.syndbg_cap_eax & + HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; } static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu) @@ -635,11 +631,17 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, union hv_stimer_config new_config = {.as_uint64 = config}, old_config = {.as_uint64 = stimer->config.as_uint64}; struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); if (!synic->active && !host) return 1; + if (unlikely(!host && hv_vcpu->enforce_cpuid && new_config.direct_mode && + !(hv_vcpu->cpuid_cache.features_edx & + HV_STIMER_DIRECT_MODE_AVAILABLE))) + return 1; + trace_kvm_hv_stimer_set_config(hv_stimer_to_vcpu(stimer)->vcpu_id, stimer->index, config, host); @@ -1172,6 +1174,7 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); u64 gfn; + int idx; if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET || @@ -1190,20 +1193,105 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm) gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; hv->tsc_ref.tsc_sequence = 0; + + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&kvm->srcu); if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; + srcu_read_unlock(&kvm->srcu, idx); out_unlock: mutex_unlock(&hv->hv_lock); } + +static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) +{ + if (!hv_vcpu->enforce_cpuid) + return true; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + case HV_X64_MSR_HYPERCALL: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_HYPERCALL_AVAILABLE; + case HV_X64_MSR_VP_RUNTIME: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_VP_RUNTIME_AVAILABLE; + case HV_X64_MSR_TIME_REF_COUNT: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_TIME_REF_COUNT_AVAILABLE; + case HV_X64_MSR_VP_INDEX: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_VP_INDEX_AVAILABLE; + case HV_X64_MSR_RESET: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_RESET_AVAILABLE; + case HV_X64_MSR_REFERENCE_TSC: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_REFERENCE_TSC_AVAILABLE; + case HV_X64_MSR_SCONTROL: + case HV_X64_MSR_SVERSION: + case HV_X64_MSR_SIEFP: + case HV_X64_MSR_SIMP: + case HV_X64_MSR_EOM: + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_SYNIC_AVAILABLE; + case HV_X64_MSR_STIMER0_CONFIG: + case HV_X64_MSR_STIMER1_CONFIG: + case HV_X64_MSR_STIMER2_CONFIG: + case HV_X64_MSR_STIMER3_CONFIG: + case HV_X64_MSR_STIMER0_COUNT: + case HV_X64_MSR_STIMER1_COUNT: + case HV_X64_MSR_STIMER2_COUNT: + case HV_X64_MSR_STIMER3_COUNT: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_SYNTIMER_AVAILABLE; + case HV_X64_MSR_EOI: + case HV_X64_MSR_ICR: + case HV_X64_MSR_TPR: + case HV_X64_MSR_VP_ASSIST_PAGE: + return hv_vcpu->cpuid_cache.features_eax & + HV_MSR_APIC_ACCESS_AVAILABLE; + break; + case HV_X64_MSR_TSC_FREQUENCY: + case HV_X64_MSR_APIC_FREQUENCY: + return hv_vcpu->cpuid_cache.features_eax & + HV_ACCESS_FREQUENCY_MSRS; + case HV_X64_MSR_REENLIGHTENMENT_CONTROL: + case HV_X64_MSR_TSC_EMULATION_CONTROL: + case HV_X64_MSR_TSC_EMULATION_STATUS: + return hv_vcpu->cpuid_cache.features_eax & + HV_ACCESS_REENLIGHTENMENT; + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_CRASH_CTL: + return hv_vcpu->cpuid_cache.features_edx & + HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + case HV_X64_MSR_SYNDBG_OPTIONS: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + return hv_vcpu->cpuid_cache.features_edx & + HV_FEATURE_DEBUG_MSRS_AVAILABLE; + default: + break; + } + + return false; +} + static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { struct kvm *kvm = vcpu->kvm; struct kvm_hv *hv = to_kvm_hv(kvm); + if (unlikely(!host && !hv_check_msr_access(to_hv_vcpu(vcpu), msr))) + return 1; + switch (msr) { case HV_X64_MSR_GUEST_OS_ID: hv->hv_guest_os_id = data; @@ -1332,6 +1420,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + if (unlikely(!host && !hv_check_msr_access(hv_vcpu, msr))) + return 1; + switch (msr) { case HV_X64_MSR_VP_INDEX: { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); @@ -1446,6 +1537,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, struct kvm *kvm = vcpu->kvm; struct kvm_hv *hv = to_kvm_hv(kvm); + if (unlikely(!host && !hv_check_msr_access(to_hv_vcpu(vcpu), msr))) + return 1; + switch (msr) { case HV_X64_MSR_GUEST_OS_ID: data = hv->hv_guest_os_id; @@ -1495,6 +1589,9 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, u64 data = 0; struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + if (unlikely(!host && !hv_check_msr_access(hv_vcpu, msr))) + return 1; + switch (msr) { case HV_X64_MSR_VP_INDEX: data = hv_vcpu->vp_index; @@ -1623,8 +1720,22 @@ static __always_inline unsigned long *sparse_set_to_vcpu_mask( return vcpu_bitmap; } -static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool ex) +struct kvm_hv_hcall { + u64 param; + u64 ingpa; + u64 outgpa; + u16 code; + u16 rep_cnt; + u16 rep_idx; + bool fast; + bool rep; + sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; +}; + +static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex) { + int i; + gpa_t gpa; struct kvm *kvm = vcpu->kvm; struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct hv_tlb_flush_ex flush_ex; @@ -1638,8 +1749,15 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool bool all_cpus; if (!ex) { - if (unlikely(kvm_read_guest(kvm, ingpa, &flush, sizeof(flush)))) - return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (hc->fast) { + flush.address_space = hc->ingpa; + flush.flags = hc->outgpa; + flush.processor_mask = sse128_lo(hc->xmm[0]); + } else { + if (unlikely(kvm_read_guest(kvm, hc->ingpa, + &flush, sizeof(flush)))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } trace_kvm_hv_flush_tlb(flush.processor_mask, flush.address_space, flush.flags); @@ -1657,9 +1775,16 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) || flush.processor_mask == 0; } else { - if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex, - sizeof(flush_ex)))) - return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (hc->fast) { + flush_ex.address_space = hc->ingpa; + flush_ex.flags = hc->outgpa; + memcpy(&flush_ex.hv_vp_set, + &hc->xmm[0], sizeof(hc->xmm[0])); + } else { + if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex, + sizeof(flush_ex)))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, flush_ex.hv_vp_set.format, @@ -1670,20 +1795,28 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool all_cpus = flush_ex.hv_vp_set.format != HV_GENERIC_SET_SPARSE_4K; - sparse_banks_len = - bitmap_weight((unsigned long *)&valid_bank_mask, 64) * - sizeof(sparse_banks[0]); + sparse_banks_len = bitmap_weight((unsigned long *)&valid_bank_mask, 64); if (!sparse_banks_len && !all_cpus) goto ret_success; - if (!all_cpus && - kvm_read_guest(kvm, - ingpa + offsetof(struct hv_tlb_flush_ex, - hv_vp_set.bank_contents), - sparse_banks, - sparse_banks_len)) - return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (!all_cpus) { + if (hc->fast) { + if (sparse_banks_len > HV_HYPERCALL_MAX_XMM_REGISTERS - 1) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + for (i = 0; i < sparse_banks_len; i += 2) { + sparse_banks[i] = sse128_lo(hc->xmm[i / 2 + 1]); + sparse_banks[i + 1] = sse128_hi(hc->xmm[i / 2 + 1]); + } + } else { + gpa = hc->ingpa + offsetof(struct hv_tlb_flush_ex, + hv_vp_set.bank_contents); + if (unlikely(kvm_read_guest(kvm, gpa, sparse_banks, + sparse_banks_len * + sizeof(sparse_banks[0])))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } + } } cpumask_clear(&hv_vcpu->tlb_flush); @@ -1696,13 +1829,13 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, u64 ingpa, u16 rep_cnt, bool * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't * analyze it here, flush TLB regardless of the specified address space. */ - kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, + kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, NULL, vcpu_mask, &hv_vcpu->tlb_flush); ret_success: - /* We always do full TLB flush, set rep_done = rep_cnt. */ + /* We always do full TLB flush, set 'Reps completed' = 'Rep Count' */ return (u64)HV_STATUS_SUCCESS | - ((u64)rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET); + ((u64)hc->rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET); } static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, @@ -1724,8 +1857,7 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, } } -static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, u64 ingpa, u64 outgpa, - bool ex, bool fast) +static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex) { struct kvm *kvm = vcpu->kvm; struct hv_send_ipi_ex send_ipi_ex; @@ -1740,25 +1872,25 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, u64 ingpa, u64 outgpa, bool all_cpus; if (!ex) { - if (!fast) { - if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi, + if (!hc->fast) { + if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi, sizeof(send_ipi)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; sparse_banks[0] = send_ipi.cpu_mask; vector = send_ipi.vector; } else { /* 'reserved' part of hv_send_ipi should be 0 */ - if (unlikely(ingpa >> 32 != 0)) + if (unlikely(hc->ingpa >> 32 != 0)) return HV_STATUS_INVALID_HYPERCALL_INPUT; - sparse_banks[0] = outgpa; - vector = (u32)ingpa; + sparse_banks[0] = hc->outgpa; + vector = (u32)hc->ingpa; } all_cpus = false; valid_bank_mask = BIT_ULL(0); trace_kvm_hv_send_ipi(vector, sparse_banks[0]); } else { - if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi_ex, + if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex, sizeof(send_ipi_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -1778,8 +1910,8 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, u64 ingpa, u64 outgpa, if (!all_cpus && kvm_read_guest(kvm, - ingpa + offsetof(struct hv_send_ipi_ex, - vp_set.bank_contents), + hc->ingpa + offsetof(struct hv_send_ipi_ex, + vp_set.bank_contents), sparse_banks, sparse_banks_len)) return HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -1801,12 +1933,67 @@ ret_success: void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *entry; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0); - if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) + if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) { vcpu->arch.hyperv_enabled = true; - else + } else { vcpu->arch.hyperv_enabled = false; + return; + } + + if (!to_hv_vcpu(vcpu) && kvm_hv_vcpu_init(vcpu)) + return; + + hv_vcpu = to_hv_vcpu(vcpu); + + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES, 0); + if (entry) { + hv_vcpu->cpuid_cache.features_eax = entry->eax; + hv_vcpu->cpuid_cache.features_ebx = entry->ebx; + hv_vcpu->cpuid_cache.features_edx = entry->edx; + } else { + hv_vcpu->cpuid_cache.features_eax = 0; + hv_vcpu->cpuid_cache.features_ebx = 0; + hv_vcpu->cpuid_cache.features_edx = 0; + } + + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO, 0); + if (entry) { + hv_vcpu->cpuid_cache.enlightenments_eax = entry->eax; + hv_vcpu->cpuid_cache.enlightenments_ebx = entry->ebx; + } else { + hv_vcpu->cpuid_cache.enlightenments_eax = 0; + hv_vcpu->cpuid_cache.enlightenments_ebx = 0; + } + + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0); + if (entry) + hv_vcpu->cpuid_cache.syndbg_cap_eax = entry->eax; + else + hv_vcpu->cpuid_cache.syndbg_cap_eax = 0; +} + +int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce) +{ + struct kvm_vcpu_hv *hv_vcpu; + int ret = 0; + + if (!to_hv_vcpu(vcpu)) { + if (enforce) { + ret = kvm_hv_vcpu_init(vcpu); + if (ret) + return ret; + } else { + return 0; + } + } + + hv_vcpu = to_hv_vcpu(vcpu); + hv_vcpu->enforce_cpuid = enforce; + + return ret; } bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu) @@ -1839,20 +2026,21 @@ static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result); } -static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) +static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); struct eventfd_ctx *eventfd; - if (unlikely(!fast)) { + if (unlikely(!hc->fast)) { int ret; - gpa_t gpa = param; + gpa_t gpa = hc->ingpa; - if ((gpa & (__alignof__(param) - 1)) || - offset_in_page(gpa) + sizeof(param) > PAGE_SIZE) + if ((gpa & (__alignof__(hc->ingpa) - 1)) || + offset_in_page(gpa) + sizeof(hc->ingpa) > PAGE_SIZE) return HV_STATUS_INVALID_ALIGNMENT; - ret = kvm_vcpu_read_guest(vcpu, gpa, ¶m, sizeof(param)); + ret = kvm_vcpu_read_guest(vcpu, gpa, + &hc->ingpa, sizeof(hc->ingpa)); if (ret < 0) return HV_STATUS_INVALID_ALIGNMENT; } @@ -1862,15 +2050,15 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) * have no use for it, and in all known usecases it is zero, so just * report lookup failure if it isn't. */ - if (param & 0xffff00000000ULL) + if (hc->ingpa & 0xffff00000000ULL) return HV_STATUS_INVALID_PORT_ID; /* remaining bits are reserved-zero */ - if (param & ~KVM_HYPERV_CONN_ID_MASK) + if (hc->ingpa & ~KVM_HYPERV_CONN_ID_MASK) return HV_STATUS_INVALID_HYPERCALL_INPUT; /* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */ rcu_read_lock(); - eventfd = idr_find(&hv->conn_to_evt, param); + eventfd = idr_find(&hv->conn_to_evt, hc->ingpa); rcu_read_unlock(); if (!eventfd) return HV_STATUS_INVALID_PORT_ID; @@ -1879,11 +2067,80 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) return HV_STATUS_SUCCESS; } +static bool is_xmm_fast_hypercall(struct kvm_hv_hcall *hc) +{ + switch (hc->code) { + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: + return true; + } + + return false; +} + +static void kvm_hv_hypercall_read_xmm(struct kvm_hv_hcall *hc) +{ + int reg; + + kvm_fpu_get(); + for (reg = 0; reg < HV_HYPERCALL_MAX_XMM_REGISTERS; reg++) + _kvm_read_sse_reg(reg, &hc->xmm[reg]); + kvm_fpu_put(); +} + +static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code) +{ + if (!hv_vcpu->enforce_cpuid) + return true; + + switch (code) { + case HVCALL_NOTIFY_LONG_SPIN_WAIT: + return hv_vcpu->cpuid_cache.enlightenments_ebx && + hv_vcpu->cpuid_cache.enlightenments_ebx != U32_MAX; + case HVCALL_POST_MESSAGE: + return hv_vcpu->cpuid_cache.features_ebx & HV_POST_MESSAGES; + case HVCALL_SIGNAL_EVENT: + return hv_vcpu->cpuid_cache.features_ebx & HV_SIGNAL_EVENTS; + case HVCALL_POST_DEBUG_DATA: + case HVCALL_RETRIEVE_DEBUG_DATA: + case HVCALL_RESET_DEBUG_SESSION: + /* + * Return 'true' when SynDBG is disabled so the resulting code + * will be HV_STATUS_INVALID_HYPERCALL_CODE. + */ + return !kvm_hv_is_syndbg_enabled(hv_vcpu->vcpu) || + hv_vcpu->cpuid_cache.features_ebx & HV_DEBUGGING; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: + if (!(hv_vcpu->cpuid_cache.enlightenments_eax & + HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return false; + fallthrough; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: + return hv_vcpu->cpuid_cache.enlightenments_eax & + HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + case HVCALL_SEND_IPI_EX: + if (!(hv_vcpu->cpuid_cache.enlightenments_eax & + HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return false; + fallthrough; + case HVCALL_SEND_IPI: + return hv_vcpu->cpuid_cache.enlightenments_eax & + HV_X64_CLUSTER_IPI_RECOMMENDED; + default: + break; + } + + return true; +} + int kvm_hv_hypercall(struct kvm_vcpu *vcpu) { - u64 param, ingpa, outgpa, ret = HV_STATUS_SUCCESS; - uint16_t code, rep_idx, rep_cnt; - bool fast, rep; + struct kvm_hv_hcall hc; + u64 ret = HV_STATUS_SUCCESS; /* * hypercall generates UD from non zero cpl and real mode @@ -1896,104 +2153,113 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 if (is_64_bit_mode(vcpu)) { - param = kvm_rcx_read(vcpu); - ingpa = kvm_rdx_read(vcpu); - outgpa = kvm_r8_read(vcpu); + hc.param = kvm_rcx_read(vcpu); + hc.ingpa = kvm_rdx_read(vcpu); + hc.outgpa = kvm_r8_read(vcpu); } else #endif { - param = ((u64)kvm_rdx_read(vcpu) << 32) | - (kvm_rax_read(vcpu) & 0xffffffff); - ingpa = ((u64)kvm_rbx_read(vcpu) << 32) | - (kvm_rcx_read(vcpu) & 0xffffffff); - outgpa = ((u64)kvm_rdi_read(vcpu) << 32) | - (kvm_rsi_read(vcpu) & 0xffffffff); + hc.param = ((u64)kvm_rdx_read(vcpu) << 32) | + (kvm_rax_read(vcpu) & 0xffffffff); + hc.ingpa = ((u64)kvm_rbx_read(vcpu) << 32) | + (kvm_rcx_read(vcpu) & 0xffffffff); + hc.outgpa = ((u64)kvm_rdi_read(vcpu) << 32) | + (kvm_rsi_read(vcpu) & 0xffffffff); } - code = param & 0xffff; - fast = !!(param & HV_HYPERCALL_FAST_BIT); - rep_cnt = (param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff; - rep_idx = (param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff; - rep = !!(rep_cnt || rep_idx); + hc.code = hc.param & 0xffff; + hc.fast = !!(hc.param & HV_HYPERCALL_FAST_BIT); + hc.rep_cnt = (hc.param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff; + hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff; + hc.rep = !!(hc.rep_cnt || hc.rep_idx); - trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + if (hc.fast && is_xmm_fast_hypercall(&hc)) + kvm_hv_hypercall_read_xmm(&hc); - switch (code) { + trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx, + hc.ingpa, hc.outgpa); + + if (unlikely(!hv_check_hypercall_access(to_hv_vcpu(vcpu), hc.code))) { + ret = HV_STATUS_ACCESS_DENIED; + goto hypercall_complete; + } + + switch (hc.code) { case HVCALL_NOTIFY_LONG_SPIN_WAIT: - if (unlikely(rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } kvm_vcpu_on_spin(vcpu, true); break; case HVCALL_SIGNAL_EVENT: - if (unlikely(rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hvcall_signal_event(vcpu, fast, ingpa); + ret = kvm_hvcall_signal_event(vcpu, &hc); if (ret != HV_STATUS_INVALID_PORT_ID) break; fallthrough; /* maybe userspace knows this conn_id */ case HVCALL_POST_MESSAGE: /* don't bother userspace if it has no way to handle it */ - if (unlikely(rep || !to_hv_synic(vcpu)->active)) { + if (unlikely(hc.rep || !to_hv_synic(vcpu)->active)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } vcpu->run->exit_reason = KVM_EXIT_HYPERV; vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = param; - vcpu->run->hyperv.u.hcall.params[0] = ingpa; - vcpu->run->hyperv.u.hcall.params[1] = outgpa; + vcpu->run->hyperv.u.hcall.input = hc.param; + vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; + vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; return 0; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: - if (unlikely(fast || !rep_cnt || rep_idx)) { + if (unlikely(!hc.rep_cnt || hc.rep_idx)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false); + ret = kvm_hv_flush_tlb(vcpu, &hc, false); break; case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: - if (unlikely(fast || rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false); + ret = kvm_hv_flush_tlb(vcpu, &hc, false); break; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: - if (unlikely(fast || !rep_cnt || rep_idx)) { + if (unlikely(!hc.rep_cnt || hc.rep_idx)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true); + ret = kvm_hv_flush_tlb(vcpu, &hc, true); break; case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: - if (unlikely(fast || rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true); + ret = kvm_hv_flush_tlb(vcpu, &hc, true); break; case HVCALL_SEND_IPI: - if (unlikely(rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, false, fast); + ret = kvm_hv_send_ipi(vcpu, &hc, false); break; case HVCALL_SEND_IPI_EX: - if (unlikely(fast || rep)) { + if (unlikely(hc.fast || hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, true, false); + ret = kvm_hv_send_ipi(vcpu, &hc, true); break; case HVCALL_POST_DEBUG_DATA: case HVCALL_RETRIEVE_DEBUG_DATA: - if (unlikely(fast)) { + if (unlikely(hc.fast)) { ret = HV_STATUS_INVALID_PARAMETER; break; } @@ -2012,9 +2278,9 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) } vcpu->run->exit_reason = KVM_EXIT_HYPERV; vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = param; - vcpu->run->hyperv.u.hcall.params[0] = ingpa; - vcpu->run->hyperv.u.hcall.params[1] = outgpa; + vcpu->run->hyperv.u.hcall.input = hc.param; + vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; + vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; return 0; @@ -2024,6 +2290,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) break; } +hypercall_complete: return kvm_hv_hypercall_complete(vcpu, ret); } @@ -2172,6 +2439,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->ebx |= HV_POST_MESSAGES; ent->ebx |= HV_SIGNAL_EVENTS; + ent->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 60547d5cb6d7..730da8537d05 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -138,6 +138,7 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu); +int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce); int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 3db5c42c9ecd..90e1ffdc05b7 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -55,6 +55,13 @@ static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); } +static inline void kvm_register_clear_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + __clear_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, enum kvm_reg reg) { @@ -118,6 +125,11 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) return vcpu->arch.walk_mmu->pdptrs[index]; } +static inline void kvm_pdptr_write(struct kvm_vcpu *vcpu, int index, u64 value) +{ + vcpu->arch.walk_mmu->pdptrs[index] = value; +} + static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; @@ -162,6 +174,7 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu) static inline void enter_guest_mode(struct kvm_vcpu *vcpu) { vcpu->arch.hflags |= HF_GUEST_MASK; + vcpu->stat.guest_mode = 1; } static inline void leave_guest_mode(struct kvm_vcpu *vcpu) @@ -172,6 +185,8 @@ static inline void leave_guest_mode(struct kvm_vcpu *vcpu) vcpu->arch.load_eoi_exitmap_pending = false; kvm_make_request(KVM_REQ_LOAD_EOI_EXITMAP, vcpu); } + + vcpu->stat.guest_mode = 0; } static inline bool is_guest_mode(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index f016838faedd..68b420289d7e 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -13,6 +13,7 @@ #define _ASM_X86_KVM_X86_EMULATE_H #include <asm/desc_defs.h> +#include "fpu.h" struct x86_emulate_ctxt; enum x86_intercept; @@ -229,15 +230,12 @@ struct x86_emulate_ops { void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); - void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags); - int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, - const char *smstate); - void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt); + void (*exiting_smm)(struct x86_emulate_ctxt *ctxt); + int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate); + void (*triple_fault)(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; - /* Type, address-of, and value of an instruction's operand. */ struct operand { enum { OP_REG, OP_MEM, OP_MEM_STR, OP_IMM, OP_XMM, OP_MM, OP_NONE } type; @@ -314,7 +312,6 @@ struct x86_emulate_ctxt { int interruptibility; bool perm_ok; /* do not check permissions if true */ - bool ud; /* inject an #UD if host doesn't support insn */ bool tf; /* TF value before instruction (after for syscall/sysret) */ bool have_exception; @@ -491,7 +488,7 @@ enum x86_intercept { #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64 #endif -int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len); +int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type); bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt); #define EMULATION_FAILED -1 #define EMULATION_OK 0 diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c new file mode 100644 index 000000000000..c7db2df50a7a --- /dev/null +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM L1 hypervisor optimizations on Hyper-V. + */ + +#include <linux/kvm_host.h> +#include <asm/mshyperv.h> + +#include "hyperv.h" +#include "kvm_onhyperv.h" + +static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush, + void *data) +{ + struct kvm_tlb_range *range = data; + + return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn, + range->pages); +} + +static inline int hv_remote_flush_root_tdp(hpa_t root_tdp, + struct kvm_tlb_range *range) +{ + if (range) + return hyperv_flush_guest_mapping_range(root_tdp, + kvm_fill_hv_flush_list_func, (void *)range); + else + return hyperv_flush_guest_mapping(root_tdp); +} + +int hv_remote_flush_tlb_with_range(struct kvm *kvm, + struct kvm_tlb_range *range) +{ + struct kvm_arch *kvm_arch = &kvm->arch; + struct kvm_vcpu *vcpu; + int ret = 0, i, nr_unique_valid_roots; + hpa_t root; + + spin_lock(&kvm_arch->hv_root_tdp_lock); + + if (!VALID_PAGE(kvm_arch->hv_root_tdp)) { + nr_unique_valid_roots = 0; + + /* + * Flush all valid roots, and see if all vCPUs have converged + * on a common root, in which case future flushes can skip the + * loop and flush the common root. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + root = vcpu->arch.hv_root_tdp; + if (!VALID_PAGE(root) || root == kvm_arch->hv_root_tdp) + continue; + + /* + * Set the tracked root to the first valid root. Keep + * this root for the entirety of the loop even if more + * roots are encountered as a low effort optimization + * to avoid flushing the same (first) root again. + */ + if (++nr_unique_valid_roots == 1) + kvm_arch->hv_root_tdp = root; + + if (!ret) + ret = hv_remote_flush_root_tdp(root, range); + + /* + * Stop processing roots if a failure occurred and + * multiple valid roots have already been detected. + */ + if (ret && nr_unique_valid_roots > 1) + break; + } + + /* + * The optimized flush of a single root can't be used if there + * are multiple valid roots (obviously). + */ + if (nr_unique_valid_roots > 1) + kvm_arch->hv_root_tdp = INVALID_PAGE; + } else { + ret = hv_remote_flush_root_tdp(kvm_arch->hv_root_tdp, range); + } + + spin_unlock(&kvm_arch->hv_root_tdp_lock); + return ret; +} +EXPORT_SYMBOL_GPL(hv_remote_flush_tlb_with_range); + +int hv_remote_flush_tlb(struct kvm *kvm) +{ + return hv_remote_flush_tlb_with_range(kvm, NULL); +} +EXPORT_SYMBOL_GPL(hv_remote_flush_tlb); diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h new file mode 100644 index 000000000000..1c67abf2eba9 --- /dev/null +++ b/arch/x86/kvm/kvm_onhyperv.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * KVM L1 hypervisor optimizations on Hyper-V. + */ + +#ifndef __ARCH_X86_KVM_KVM_ONHYPERV_H__ +#define __ARCH_X86_KVM_KVM_ONHYPERV_H__ + +#if IS_ENABLED(CONFIG_HYPERV) +int hv_remote_flush_tlb_with_range(struct kvm *kvm, + struct kvm_tlb_range *range); +int hv_remote_flush_tlb(struct kvm *kvm); + +static inline void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp) +{ + struct kvm_arch *kvm_arch = &vcpu->kvm->arch; + + if (kvm_x86_ops.tlb_remote_flush == hv_remote_flush_tlb) { + spin_lock(&kvm_arch->hv_root_tdp_lock); + vcpu->arch.hv_root_tdp = root_tdp; + if (root_tdp != kvm_arch->hv_root_tdp) + kvm_arch->hv_root_tdp = INVALID_PAGE; + spin_unlock(&kvm_arch->hv_root_tdp_lock); + } +} +#else /* !CONFIG_HYPERV */ +static inline void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp) +{ +} +#endif /* !CONFIG_HYPERV */ + +#endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c0ebef560bd1..ba5a27879f1d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1410,6 +1410,9 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, if (!apic_x2apic_mode(apic)) valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI); + if (alignment + len > 4) + return 1; + if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset))) return 1; @@ -1494,6 +1497,15 @@ static void limit_periodic_timer_frequency(struct kvm_lapic *apic) static void cancel_hv_timer(struct kvm_lapic *apic); +static void cancel_apic_timer(struct kvm_lapic *apic) +{ + hrtimer_cancel(&apic->lapic_timer.timer); + preempt_disable(); + if (apic->lapic_timer.hv_timer_in_use) + cancel_hv_timer(apic); + preempt_enable(); +} + static void apic_update_lvtt(struct kvm_lapic *apic) { u32 timer_mode = kvm_lapic_get_reg(apic, APIC_LVTT) & @@ -1502,11 +1514,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic) if (apic->lapic_timer.timer_mode != timer_mode) { if (apic_lvtt_tscdeadline(apic) != (timer_mode == APIC_LVT_TIMER_TSCDEADLINE)) { - hrtimer_cancel(&apic->lapic_timer.timer); - preempt_disable(); - if (apic->lapic_timer.hv_timer_in_use) - cancel_hv_timer(apic); - preempt_enable(); + cancel_apic_timer(apic); kvm_lapic_set_reg(apic, APIC_TMICT, 0); apic->lapic_timer.period = 0; apic->lapic_timer.tscdeadline = 0; @@ -1598,11 +1606,19 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline; + if (lapic_timer_advance_dynamic) { + adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); + /* + * If the timer fired early, reread the TSC to account for the + * overhead of the above adjustment to avoid waiting longer + * than is necessary. + */ + if (guest_tsc < tsc_deadline) + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + } + if (guest_tsc < tsc_deadline) __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - - if (lapic_timer_advance_dynamic) - adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); } void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) @@ -1661,7 +1677,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) } atomic_inc(&apic->lapic_timer.pending); - kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_make_request(KVM_REQ_UNBLOCK, vcpu); if (from_timer_fn) kvm_vcpu_kick(vcpu); } @@ -2084,7 +2100,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) if (apic_lvtt_tscdeadline(apic)) break; - hrtimer_cancel(&apic->lapic_timer.timer); + cancel_apic_timer(apic); kvm_lapic_set_reg(apic, APIC_TMICT, val); start_apic_timer(apic); break; @@ -2615,6 +2631,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); __start_apic_timer(apic, APIC_TMCCT); + kvm_lapic_set_reg(apic, APIC_TMCCT, 0); kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { @@ -2856,7 +2873,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len) return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len); } -void kvm_apic_accept_events(struct kvm_vcpu *vcpu) +int kvm_apic_accept_events(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; u8 sipi_vector; @@ -2864,7 +2881,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) unsigned long pe; if (!lapic_in_kernel(vcpu)) - return; + return 0; /* * Read pending events before calling the check_events @@ -2872,12 +2889,12 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) */ pe = smp_load_acquire(&apic->pending_events); if (!pe) - return; + return 0; if (is_guest_mode(vcpu)) { r = kvm_check_nested_events(vcpu); if (r < 0) - return; + return r == -EBUSY ? 0 : r; /* * If an event has happened and caused a vmexit, * we know INITs are latched and therefore @@ -2898,7 +2915,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); if (test_bit(KVM_APIC_SIPI, &pe)) clear_bit(KVM_APIC_SIPI, &apic->pending_events); - return; + return 0; } if (test_bit(KVM_APIC_INIT, &pe)) { @@ -2919,6 +2936,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } } + return 0; } void kvm_lapic_exit(void) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 997c45a5963a..d7c25d0c1354 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -76,7 +76,7 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); -void kvm_apic_accept_events(struct kvm_vcpu *vcpu); +int kvm_apic_accept_events(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 88d0ed5225a4..bc11402df83b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -65,7 +65,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); -void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots); +void kvm_init_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer, gpa_t nested_cr3); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, @@ -232,4 +232,14 @@ int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); +static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) +{ + /* + * Read memslot_have_rmaps before rmap pointers. Hence, threads reading + * memslots_have_rmaps in any lock context are guaranteed to see the + * pointers. Pairs with smp_store_release in alloc_all_memslots_rmaps. + */ + return smp_load_acquire(&kvm->arch.memslots_have_rmaps); +} + #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 0144c40d09c7..84d48a33e38b 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -55,7 +55,7 @@ extern bool itlb_multihit_kvm_mitigation; -static int __read_mostly nx_huge_pages = -1; +int __read_mostly nx_huge_pages = -1; #ifdef CONFIG_PREEMPT_RT /* Recovery can cause latency spikes, disable it for PREEMPT_RT. */ static uint __read_mostly nx_huge_pages_recovery_ratio = 0; @@ -208,11 +208,6 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } -bool is_nx_huge_page_enabled(void) -{ - return READ_ONCE(nx_huge_pages); -} - static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned int access) { @@ -1177,8 +1172,7 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, * @gfn_offset: start of the BITS_PER_LONG pages we care about * @mask: indicates which pages we should protect * - * Used when we do not need to care about huge page mappings: e.g. during dirty - * logging we do not have any such mappings. + * Used when we do not need to care about huge page mappings. */ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -1189,6 +1183,10 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, true); + + if (!kvm_memslots_have_rmaps(kvm)) + return; + while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); @@ -1218,6 +1216,10 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, false); + + if (!kvm_memslots_have_rmaps(kvm)) + return; + while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); @@ -1235,13 +1237,36 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to * enable dirty logging for them. * - * Used when we do not need to care about huge page mappings: e.g. during dirty - * logging we do not have any such mappings. + * We need to care about huge page mappings: e.g. during dirty logging we may + * have such mappings. */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { + /* + * Huge pages are NOT write protected when we start dirty logging in + * initially-all-set mode; must write protect them here so that they + * are split to 4K on the first write. + * + * The gfn_offset is guaranteed to be aligned to 64, but the base_gfn + * of memslot has no such restriction, so the range can cross two large + * pages. + */ + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) { + gfn_t start = slot->base_gfn + gfn_offset + __ffs(mask); + gfn_t end = slot->base_gfn + gfn_offset + __fls(mask); + + kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M); + + /* Cross two large pages? */ + if (ALIGN(start << PAGE_SHIFT, PMD_SIZE) != + ALIGN(end << PAGE_SHIFT, PMD_SIZE)) + kvm_mmu_slot_gfn_write_protect(kvm, slot, end, + PG_LEVEL_2M); + } + + /* Now handle 4K PTEs. */ if (kvm_x86_ops.cpu_dirty_log_size) kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else @@ -1254,20 +1279,23 @@ int kvm_cpu_dirty_log_size(void) } bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, - struct kvm_memory_slot *slot, u64 gfn) + struct kvm_memory_slot *slot, u64 gfn, + int min_level) { struct kvm_rmap_head *rmap_head; int i; bool write_protected = false; - for (i = PG_LEVEL_4K; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { - rmap_head = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(kvm, rmap_head, true); + if (kvm_memslots_have_rmaps(kvm)) { + for (i = min_level; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { + rmap_head = __gfn_to_rmap(gfn, i, slot); + write_protected |= __rmap_write_protect(kvm, rmap_head, true); + } } if (is_tdp_mmu_enabled(kvm)) write_protected |= - kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn); + kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn, min_level); return write_protected; } @@ -1277,7 +1305,7 @@ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) struct kvm_memory_slot *slot; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn); + return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn, PG_LEVEL_4K); } static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, @@ -1433,9 +1461,10 @@ static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { - bool flush; + bool flush = false; - flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp); + if (kvm_memslots_have_rmaps(kvm)) + flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp); if (is_tdp_mmu_enabled(kvm)) flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); @@ -1445,9 +1474,10 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - bool flush; + bool flush = false; - flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmapp); + if (kvm_memslots_have_rmaps(kvm)) + flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmapp); if (is_tdp_mmu_enabled(kvm)) flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range); @@ -1500,9 +1530,10 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - bool young; + bool young = false; - young = kvm_handle_gfn_range(kvm, range, kvm_age_rmapp); + if (kvm_memslots_have_rmaps(kvm)) + young = kvm_handle_gfn_range(kvm, range, kvm_age_rmapp); if (is_tdp_mmu_enabled(kvm)) young |= kvm_tdp_mmu_age_gfn_range(kvm, range); @@ -1512,9 +1543,10 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - bool young; + bool young = false; - young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmapp); + if (kvm_memslots_have_rmaps(kvm)) + young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmapp); if (is_tdp_mmu_enabled(kvm)) young |= kvm_tdp_mmu_test_age_gfn(kvm, range); @@ -2827,9 +2859,6 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, gfn_t gfn = gpa >> PAGE_SHIFT; gfn_t base_gfn = gfn; - if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) - return RET_PF_RETRY; - level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn, huge_page_disallowed, &req_level); @@ -3180,6 +3209,33 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); +void kvm_mmu_free_guest_mode_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) +{ + unsigned long roots_to_free = 0; + hpa_t root_hpa; + int i; + + /* + * This should not be called while L2 is active, L2 can't invalidate + * _only_ its own roots, e.g. INVVPID unconditionally exits. + */ + WARN_ON_ONCE(mmu->mmu_role.base.guest_mode); + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + root_hpa = mmu->prev_roots[i].hpa; + if (!VALID_PAGE(root_hpa)) + continue; + + if (!to_shadow_page(root_hpa) || + to_shadow_page(root_hpa)->role.guest_mode) + roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); + } + + kvm_mmu_free_roots(vcpu, mmu, roots_to_free); +} +EXPORT_SYMBOL_GPL(kvm_mmu_free_guest_mode_roots); + + static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn) { int ret = 0; @@ -3280,6 +3336,10 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) } } + r = alloc_all_memslots_rmaps(vcpu->kvm); + if (r) + return r; + write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); if (r < 0) @@ -3540,12 +3600,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) int root, leaf, level; bool reserved = false; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) { - *sptep = 0ull; - return reserved; - } - - if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + if (is_tdp_mmu(vcpu->arch.mmu)) leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else leaf = get_walk(vcpu, addr, sptes, &root); @@ -3717,6 +3772,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault, int max_level, bool is_tdp) { + bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); bool write = error_code & PFERR_WRITE_MASK; bool map_writable; @@ -3729,7 +3785,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, if (page_fault_handle_page_track(vcpu, error_code, gfn)) return RET_PF_EMULATE; - if (!is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) { + if (!is_tdp_mmu_fault) { r = fast_page_fault(vcpu, gpa, error_code); if (r != RET_PF_INVALID) return r; @@ -3751,7 +3807,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, r = RET_PF_RETRY; - if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + if (is_tdp_mmu_fault) read_lock(&vcpu->kvm->mmu_lock); else write_lock(&vcpu->kvm->mmu_lock); @@ -3762,7 +3818,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, if (r) goto out_unlock; - if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + if (is_tdp_mmu_fault) r = kvm_tdp_mmu_map(vcpu, gpa, error_code, map_writable, max_level, pfn, prefault); else @@ -3770,7 +3826,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, prefault, is_tdp); out_unlock: - if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + if (is_tdp_mmu_fault) read_unlock(&vcpu->kvm->mmu_lock); else write_unlock(&vcpu->kvm->mmu_lock); @@ -3913,8 +3969,7 @@ static bool fast_pgd_switch(struct kvm_vcpu *vcpu, gpa_t new_pgd, } static void __kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, - union kvm_mmu_page_role new_role, - bool skip_tlb_flush, bool skip_mmu_sync) + union kvm_mmu_page_role new_role) { if (!fast_pgd_switch(vcpu, new_pgd, new_role)) { kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, KVM_MMU_ROOT_CURRENT); @@ -3929,10 +3984,10 @@ static void __kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, */ kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); - if (!skip_mmu_sync || force_flush_and_sync_on_reuse) + if (force_flush_and_sync_on_reuse) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - if (!skip_tlb_flush || force_flush_and_sync_on_reuse) kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + } /* * The last MMIO access's GVA and GPA are cached in the VCPU. When @@ -3951,11 +4006,9 @@ static void __kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, to_shadow_page(vcpu->arch.mmu->root_hpa)); } -void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush, - bool skip_mmu_sync) +void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) { - __kvm_mmu_new_pgd(vcpu, new_pgd, kvm_mmu_calc_root_page_role(vcpu), - skip_tlb_flush, skip_mmu_sync); + __kvm_mmu_new_pgd(vcpu, new_pgd, kvm_mmu_calc_root_page_role(vcpu)); } EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); @@ -4648,7 +4701,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer, struct kvm_mmu *context = &vcpu->arch.guest_mmu; union kvm_mmu_role new_role = kvm_calc_shadow_npt_root_page_role(vcpu); - __kvm_mmu_new_pgd(vcpu, nested_cr3, new_role.base, false, false); + __kvm_mmu_new_pgd(vcpu, nested_cr3, new_role.base); if (new_role.as_u64 != context->mmu_role.as_u64) { shadow_mmu_init_context(vcpu, context, cr0, cr4, efer, new_role); @@ -4700,7 +4753,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty, execonly, level); - __kvm_mmu_new_pgd(vcpu, new_eptp, new_role.base, true, true); + __kvm_mmu_new_pgd(vcpu, new_eptp, new_role.base); if (new_role.as_u64 == context->mmu_role.as_u64) return; @@ -4739,9 +4792,33 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu) context->inject_page_fault = kvm_inject_page_fault; } +static union kvm_mmu_role kvm_calc_nested_mmu_role(struct kvm_vcpu *vcpu) +{ + union kvm_mmu_role role = kvm_calc_shadow_root_page_role_common(vcpu, false); + + /* + * Nested MMUs are used only for walking L2's gva->gpa, they never have + * shadow pages of their own and so "direct" has no meaning. Set it + * to "true" to try to detect bogus usage of the nested MMU. + */ + role.base.direct = true; + + if (!is_paging(vcpu)) + role.base.level = 0; + else if (is_long_mode(vcpu)) + role.base.level = is_la57_mode(vcpu) ? PT64_ROOT_5LEVEL : + PT64_ROOT_4LEVEL; + else if (is_pae(vcpu)) + role.base.level = PT32E_ROOT_LEVEL; + else + role.base.level = PT32_ROOT_LEVEL; + + return role; +} + static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) { - union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false); + union kvm_mmu_role new_role = kvm_calc_nested_mmu_role(vcpu); struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; if (new_role.as_u64 == g_context->mmu_role.as_u64) @@ -4793,17 +4870,8 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) update_last_nonleaf_level(vcpu, g_context); } -void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots) +void kvm_init_mmu(struct kvm_vcpu *vcpu) { - if (reset_roots) { - uint i; - - vcpu->arch.mmu->root_hpa = INVALID_PAGE; - - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - vcpu->arch.mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; - } - if (mmu_is_nested(vcpu)) init_kvm_nested_mmu(vcpu); else if (tdp_enabled) @@ -4829,7 +4897,7 @@ kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu) void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); - kvm_init_mmu(vcpu, true); + kvm_init_mmu(vcpu); } EXPORT_SYMBOL_GPL(kvm_mmu_reset_context); @@ -5467,7 +5535,13 @@ void kvm_mmu_init_vm(struct kvm *kvm) { struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; - kvm_mmu_init_tdp_mmu(kvm); + if (!kvm_mmu_init_tdp_mmu(kvm)) + /* + * No smp_load/store wrappers needed here as we are in + * VM init and there cannot be any memslots / other threads + * accessing this struct kvm yet. + */ + kvm->arch.memslots_have_rmaps = true; node->track_write = kvm_mmu_pte_write; node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; @@ -5490,29 +5564,29 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) int i; bool flush = false; - write_lock(&kvm->mmu_lock); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) { - gfn_t start, end; - - start = max(gfn_start, memslot->base_gfn); - end = min(gfn_end, memslot->base_gfn + memslot->npages); - if (start >= end) - continue; + if (kvm_memslots_have_rmaps(kvm)) { + write_lock(&kvm->mmu_lock); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(memslot, slots) { + gfn_t start, end; + + start = max(gfn_start, memslot->base_gfn); + end = min(gfn_end, memslot->base_gfn + memslot->npages); + if (start >= end) + continue; - flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, - PG_LEVEL_4K, - KVM_MAX_HUGEPAGE_LEVEL, - start, end - 1, true, flush); + flush = slot_handle_level_range(kvm, memslot, + kvm_zap_rmapp, PG_LEVEL_4K, + KVM_MAX_HUGEPAGE_LEVEL, start, + end - 1, true, flush); + } } + if (flush) + kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end); + write_unlock(&kvm->mmu_lock); } - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end); - - write_unlock(&kvm->mmu_lock); - if (is_tdp_mmu_enabled(kvm)) { flush = false; @@ -5539,12 +5613,15 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot, int start_level) { - bool flush; + bool flush = false; - write_lock(&kvm->mmu_lock); - flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, - start_level, KVM_MAX_HUGEPAGE_LEVEL, false); - write_unlock(&kvm->mmu_lock); + if (kvm_memslots_have_rmaps(kvm)) { + write_lock(&kvm->mmu_lock); + flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, + start_level, KVM_MAX_HUGEPAGE_LEVEL, + false); + write_unlock(&kvm->mmu_lock); + } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); @@ -5614,16 +5691,15 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_memory_slot *slot = (struct kvm_memory_slot *)memslot; bool flush; - write_lock(&kvm->mmu_lock); - flush = slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true); - - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, slot); - write_unlock(&kvm->mmu_lock); + if (kvm_memslots_have_rmaps(kvm)) { + write_lock(&kvm->mmu_lock); + flush = slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true); + if (flush) + kvm_arch_flush_remote_tlbs_memslot(kvm, slot); + write_unlock(&kvm->mmu_lock); + } if (is_tdp_mmu_enabled(kvm)) { - flush = false; - read_lock(&kvm->mmu_lock); flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush); if (flush) @@ -5650,11 +5726,14 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { - bool flush; + bool flush = false; - write_lock(&kvm->mmu_lock); - flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); - write_unlock(&kvm->mmu_lock); + if (kvm_memslots_have_rmaps(kvm)) { + write_lock(&kvm->mmu_lock); + flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, + false); + write_unlock(&kvm->mmu_lock); + } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); @@ -5957,6 +6036,7 @@ static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel static void kvm_recover_nx_lpages(struct kvm *kvm) { + unsigned long nx_lpage_splits = kvm->stat.nx_lpage_splits; int rcu_idx; struct kvm_mmu_page *sp; unsigned int ratio; @@ -5968,7 +6048,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) write_lock(&kvm->mmu_lock); ratio = READ_ONCE(nx_huge_pages_recovery_ratio); - to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0; for ( ; to_zap; --to_zap) { if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) break; diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index d64ccb417c60..18be103df9d5 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -116,14 +116,20 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) kvm_x86_ops.cpu_dirty_log_size; } -bool is_nx_huge_page_enabled(void); +extern int nx_huge_pages; +static inline bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); +} + bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync); void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, - struct kvm_memory_slot *slot, u64 gfn); + struct kvm_memory_slot *slot, u64 gfn, + int min_level); void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, u64 start_gfn, u64 pages); @@ -158,8 +164,6 @@ int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, void disallowed_hugepage_adjust(u64 spte, gfn_t gfn, int cur_level, kvm_pfn_t *pfnp, int *goal_levelp); -bool is_nx_huge_page_enabled(void); - void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 34bb0ec69bd8..91a9f7e0fd91 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -100,7 +100,7 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, kvm_mmu_gfn_disallow_lpage(slot, gfn); if (mode == KVM_PAGE_TRACK_WRITE) - if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn)) + if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) kvm_flush_remote_tlbs(kvm); } EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 70b7e44e3035..823a5919f9fa 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -90,8 +90,8 @@ struct guest_walker { gpa_t pte_gpa[PT_MAX_FULL_LEVELS]; pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS]; bool pte_writable[PT_MAX_FULL_LEVELS]; - unsigned pt_access; - unsigned pte_access; + unsigned int pt_access[PT_MAX_FULL_LEVELS]; + unsigned int pte_access; gfn_t gfn; struct x86_exception fault; }; @@ -418,13 +418,15 @@ retry_walk: } walker->ptes[walker->level - 1] = pte; + + /* Convert to ACC_*_MASK flags for struct guest_walker. */ + walker->pt_access[walker->level - 1] = FNAME(gpte_access)(pt_access ^ walk_nx_mask); } while (!is_last_gpte(mmu, walker->level, pte)); pte_pkey = FNAME(gpte_pkeys)(vcpu, pte); accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0; /* Convert to ACC_*_MASK flags for struct guest_walker. */ - walker->pt_access = FNAME(gpte_access)(pt_access ^ walk_nx_mask); walker->pte_access = FNAME(gpte_access)(pte_access ^ walk_nx_mask); errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access); if (unlikely(errcode)) @@ -463,7 +465,8 @@ retry_walk: } pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, walker->pte_access, walker->pt_access); + __func__, (u64)pte, walker->pte_access, + walker->pt_access[walker->level - 1]); return 1; error: @@ -643,7 +646,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled; struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; - unsigned direct_access, access = gw->pt_access; + unsigned int direct_access, access; int top_level, level, req_level, ret; gfn_t base_gfn = gw->gfn; @@ -675,6 +678,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, sp = NULL; if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; + access = gw->pt_access[it.level - 2]; sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, false, access); } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 95eeb5ac6a8a..caac4ddb46df 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -14,10 +14,10 @@ static bool __read_mostly tdp_mmu_enabled = false; module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); /* Initializes the TDP MMU for the VM, if enabled. */ -void kvm_mmu_init_tdp_mmu(struct kvm *kvm) +bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) { if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled)) - return; + return false; /* This should not be changed for the lifetime of the VM. */ kvm->arch.tdp_mmu_enabled = true; @@ -25,6 +25,8 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm) INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages); + + return true; } static __always_inline void kvm_lockdep_assert_mmu_lock_held(struct kvm *kvm, @@ -335,7 +337,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, for (i = 0; i < PT64_ENT_PER_PAGE; i++) { sptep = rcu_dereference(pt) + i; - gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)); + gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); if (shared) { /* @@ -377,12 +379,12 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, WRITE_ONCE(*sptep, REMOVED_SPTE); } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, - old_child_spte, REMOVED_SPTE, level - 1, + old_child_spte, REMOVED_SPTE, level, shared); } kvm_flush_remote_tlbs_with_address(kvm, gfn, - KVM_PAGES_PER_HPAGE(level)); + KVM_PAGES_PER_HPAGE(level + 1)); call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); } @@ -912,7 +914,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, kvm_pfn_t pfn, bool prefault) { u64 new_spte; - int ret = 0; + int ret = RET_PF_FIXED; int make_spte_ret = 0; if (unlikely(is_noslot_pfn(pfn))) @@ -949,7 +951,11 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, rcu_dereference(iter->sptep)); } - if (!prefault) + /* + * Increase pf_fixed in both RET_PF_EMULATE and RET_PF_FIXED to be + * consistent with legacy MMU behavior. + */ + if (ret != RET_PF_SPURIOUS) vcpu->stat.pf_fixed++; return ret; @@ -977,11 +983,6 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, int level; int req_level; - if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) - return RET_PF_RETRY; - if (WARN_ON(!is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa))) - return RET_PF_RETRY; - level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn, huge_page_disallowed, &req_level); @@ -1024,7 +1025,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, if (is_removed_spte(iter.old_spte)) break; - sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level); + sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level - 1); child_pt = sp->spt; new_spte = make_nonleaf_spte(child_pt, @@ -1192,9 +1193,9 @@ bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) } /* - * Remove write access from all the SPTEs mapping GFNs [start, end). If - * skip_4k is set, SPTEs that map 4k pages, will not be write-protected. - * Returns true if an SPTE has been changed and the TLBs need to be flushed. + * Remove write access from all SPTEs at or above min_level that map GFNs + * [start, end). Returns true if an SPTE has been changed and the TLBs need to + * be flushed. */ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, int min_level) @@ -1462,15 +1463,22 @@ bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, * Returns true if an SPTE was set and a TLB flush is needed. */ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t gfn) + gfn_t gfn, int min_level) { struct tdp_iter iter; u64 new_spte; bool spte_set = false; + BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL); + rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, gfn, gfn + 1) { + for_each_tdp_pte_min_level(iter, root->spt, root->role.level, + min_level, gfn, gfn + 1) { + if (!is_shadow_present_pte(iter.old_spte) || + !is_last_spte(iter.old_spte, iter.level)) + continue; + if (!is_writable_pte(iter.old_spte)) break; @@ -1492,14 +1500,15 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, * Returns true if an SPTE was set and a TLB flush is needed. */ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn) + struct kvm_memory_slot *slot, gfn_t gfn, + int min_level) { struct kvm_mmu_page *root; bool spte_set = false; lockdep_assert_held_write(&kvm->mmu_lock); for_each_tdp_mmu_root(kvm, root, slot->as_id) - spte_set |= write_protect_gfn(kvm, root, gfn); + 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 5fdf63090451..b981a044ab55 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -31,7 +31,7 @@ static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, } static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { - gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level); + gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level + 1); /* * Don't allow yielding, as the caller may have a flush pending. Note, @@ -74,29 +74,23 @@ bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, bool flush); bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn); + struct kvm_memory_slot *slot, gfn_t gfn, + int min_level); int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level); #ifdef CONFIG_X86_64 -void kvm_mmu_init_tdp_mmu(struct kvm *kvm); +bool kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return kvm->arch.tdp_mmu_enabled; } static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; } -#else -static inline void kvm_mmu_init_tdp_mmu(struct kvm *kvm) {} -static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } -static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } -#endif -static inline bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) +static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { struct kvm_mmu_page *sp; + hpa_t hpa = mmu->root_hpa; - if (!is_tdp_mmu_enabled(kvm)) - return false; if (WARN_ON(!VALID_PAGE(hpa))) return false; @@ -106,5 +100,12 @@ static inline bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) return is_tdp_mmu_page(sp) && sp->root_count; } +#else +static inline bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return false; } +static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} +static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } +static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } +static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; } +#endif #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 712b4e0de481..a9abed054cd5 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -27,12 +27,6 @@ #include "irq.h" #include "svm.h" -/* enable / disable AVIC */ -int avic; -#ifdef CONFIG_X86_LOCAL_APIC -module_param(avic, int, S_IRUGO); -#endif - #define SVM_AVIC_DOORBELL 0xc001011b #define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) @@ -126,7 +120,7 @@ void avic_vm_destroy(struct kvm *kvm) unsigned long flags; struct kvm_svm *kvm_svm = to_kvm_svm(kvm); - if (!avic) + if (!enable_apicv) return; if (kvm_svm->avic_logical_id_table_page) @@ -149,7 +143,7 @@ int avic_vm_init(struct kvm *kvm) struct page *l_page; u32 vm_id; - if (!avic) + if (!enable_apicv) return 0; /* Allocating physical APIC ID table (4KB) */ @@ -223,7 +217,7 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, return &avic_physical_id_table[index]; } -/** +/* * Note: * AVIC hardware walks the nested page table to check permissions, * but does not use the SPA address specified in the leaf page @@ -571,7 +565,7 @@ int avic_init_vcpu(struct vcpu_svm *svm) int ret; struct kvm_vcpu *vcpu = &svm->vcpu; - if (!avic || !irqchip_in_kernel(vcpu->kvm)) + if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm)) return 0; ret = avic_init_backing_page(vcpu); @@ -595,7 +589,7 @@ void avic_post_state_restore(struct kvm_vcpu *vcpu) void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate) { - if (!avic || !lapic_in_kernel(vcpu)) + if (!enable_apicv || !lapic_in_kernel(vcpu)) return; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -655,7 +649,7 @@ void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) struct vmcb *vmcb = svm->vmcb; bool activated = kvm_vcpu_apicv_active(vcpu); - if (!avic) + if (!enable_apicv) return; if (activated) { @@ -766,7 +760,7 @@ out: return ret; } -/** +/* * Note: * The HW cannot support posting multicast/broadcast * interrupts to a vCPU. So, we still use legacy interrupt @@ -1007,7 +1001,7 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } -/** +/* * This function is called during VCPU halt/unhalt. */ static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 5e8d8443154e..dca20f949b63 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -380,33 +380,46 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm) return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE; } +static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) +{ + /* + * TODO: optimize unconditional TLB flush/MMU sync. A partial list of + * things to fix before this can be conditional: + * + * - Flush TLBs for both L1 and L2 remote TLB flush + * - Honor L1's request to flush an ASID on nested VMRUN + * - Sync nested NPT MMU on VMRUN that flushes L2's ASID[*] + * - Don't crush a pending TLB flush in vmcb02 on nested VMRUN + * - Flush L1's ASID on KVM_REQ_TLB_FLUSH_GUEST + * + * [*] Unlike nested EPT, SVM's ASID management can invalidate nested + * NPT guest-physical mappings on VMRUN. + */ + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); +} + /* * Load guest's/host's cr3 on nested vmentry or vmexit. @nested_npt is true * if we are emulating VM-Entry into a guest with NPT enabled. */ static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, - bool nested_npt) + bool nested_npt, bool reload_pdptrs) { if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) return -EINVAL; - if (!nested_npt && is_pae_paging(vcpu) && - (cr3 != kvm_read_cr3(vcpu) || pdptrs_changed(vcpu))) { - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) - return -EINVAL; - } + if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && + CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) + return -EINVAL; - /* - * TODO: optimize unconditional TLB flush/MMU sync here and in - * kvm_init_shadow_npt_mmu(). - */ if (!nested_npt) - kvm_mmu_new_pgd(vcpu, cr3, false, false); + kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); - kvm_init_mmu(vcpu, false); + kvm_init_mmu(vcpu); return 0; } @@ -481,6 +494,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) { const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK; + struct kvm_vcpu *vcpu = &svm->vcpu; /* * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2, @@ -505,10 +519,10 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) /* nested_cr3. */ if (nested_npt_enabled(svm)) - nested_svm_init_mmu_context(&svm->vcpu); + nested_svm_init_mmu_context(vcpu); - svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset = - svm->vcpu.arch.l1_tsc_offset + svm->nested.ctl.tsc_offset; + svm->vmcb->control.tsc_offset = vcpu->arch.tsc_offset = + vcpu->arch.l1_tsc_offset + svm->nested.ctl.tsc_offset; svm->vmcb->control.int_ctl = (svm->nested.ctl.int_ctl & ~mask) | @@ -523,8 +537,10 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) svm->vmcb->control.pause_filter_count = svm->nested.ctl.pause_filter_count; svm->vmcb->control.pause_filter_thresh = svm->nested.ctl.pause_filter_thresh; + nested_svm_transition_tlb_flush(vcpu); + /* Enter Guest-Mode */ - enter_guest_mode(&svm->vcpu); + enter_guest_mode(vcpu); /* * Merge guest and host intercepts - must be called with vcpu in @@ -576,7 +592,7 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_save(svm, vmcb12); ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, - nested_npt_enabled(svm)); + nested_npt_enabled(svm), true); if (ret) return ret; @@ -596,8 +612,6 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) struct kvm_host_map map; u64 vmcb12_gpa; - ++vcpu->stat.nested_run; - if (is_smm(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; @@ -803,9 +817,11 @@ int nested_svm_vmexit(struct vcpu_svm *svm) kvm_vcpu_unmap(vcpu, &map, true); + nested_svm_transition_tlb_flush(vcpu); + nested_svm_uninit_mmu_context(vcpu); - rc = nested_svm_load_cr3(vcpu, svm->vmcb->save.cr3, false); + rc = nested_svm_load_cr3(vcpu, svm->vmcb->save.cr3, false, true); if (rc) return 1; @@ -1302,6 +1318,19 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, goto out_free; /* + * While the nested guest CR3 is already checked and set by + * KVM_SET_SREGS, it was set when nested state was yet loaded, + * thus MMU might not be initialized correctly. + * Set it again to fix this. + */ + + ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, + nested_npt_enabled(svm), false); + if (WARN_ON_ONCE(ret)) + goto out_free; + + + /* * All checks done, we can enter guest mode. Userspace provides * vmcb12.control, which will be combined with L1 and stored into * vmcb02, and the L1 save state which we store in vmcb01. @@ -1358,9 +1387,15 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) if (WARN_ON(!is_guest_mode(vcpu))) return true; - if (nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, - nested_npt_enabled(svm))) - return false; + if (!vcpu->arch.pdptrs_from_userspace && + !nested_npt_enabled(svm) && is_pae_paging(vcpu)) + /* + * Reload the guest's PDPTRs since after a migration + * the guest CR3 might be restored prior to setting the nested + * state which can lead to a load of wrong PDPTRs. + */ + if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + return false; if (!nested_svm_vmrun_msrpm(svm)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 5bc887e9a986..8d36f0c73071 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -199,9 +199,19 @@ static void sev_asid_free(struct kvm_sev_info *sev) sev->misc_cg = NULL; } -static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +static void sev_decommission(unsigned int handle) { struct sev_data_decommission decommission; + + if (!handle) + return; + + decommission.handle = handle; + sev_guest_decommission(&decommission, NULL); +} + +static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +{ struct sev_data_deactivate deactivate; if (!handle) @@ -214,9 +224,7 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) sev_guest_deactivate(&deactivate, NULL); up_read(&sev_deactivate_lock); - /* decommission handle */ - decommission.handle = handle; - sev_guest_decommission(&decommission, NULL); + sev_decommission(handle); } static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) @@ -341,8 +349,10 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Bind ASID to this guest */ ret = sev_bind_asid(kvm, start.handle, error); - if (ret) + if (ret) { + sev_decommission(start.handle); goto e_free_session; + } /* return handle to userspace */ params.handle = start.handle; @@ -1103,10 +1113,9 @@ __sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp, struct sev_data_send_start data; int ret; + memset(&data, 0, sizeof(data)); data.handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error); - if (ret < 0) - return ret; params->session_len = data.session_len; if (copy_to_user((void __user *)(uintptr_t)argp->data, params, @@ -1215,10 +1224,9 @@ __sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp, struct sev_data_send_update_data data; int ret; + memset(&data, 0, sizeof(data)); data.handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error); - if (ret < 0) - return ret; params->hdr_len = data.hdr_len; params->trans_len = data.trans_len; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 05eca131eaf2..4cee285b0185 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -43,6 +43,9 @@ #include "svm.h" #include "svm_ops.h" +#include "kvm_onhyperv.h" +#include "svm_onhyperv.h" + #define __ex(x) __kvm_handle_fault_on_reboot(x) MODULE_AUTHOR("Qumranet"); @@ -185,6 +188,13 @@ module_param(vls, int, 0444); static int vgif = true; module_param(vgif, int, 0444); +/* + * enable / disable AVIC. Because the defaults differ for APICv + * support between VMX and SVM we cannot use module_param_named. + */ +static bool avic; +module_param(avic, bool, 0444); + bool __read_mostly dump_invalid_vmcb; module_param(dump_invalid_vmcb, bool, 0644); @@ -673,6 +683,9 @@ static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm, write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp); msrpm[offset] = tmp; + + svm_hv_vmcb_dirty_nested_enlightenments(vcpu); + } void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, @@ -939,6 +952,16 @@ static __init int svm_hardware_setup(void) int r; unsigned int order = get_order(IOPM_SIZE); + /* + * NX is required for shadow paging and for NPT if the NX huge pages + * mitigation is enabled. + */ + if (!boot_cpu_has(X86_FEATURE_NX)) { + pr_err_ratelimited("NX (Execute Disable) not supported\n"); + return -EOPNOTSUPP; + } + kvm_enable_efer_bits(EFER_NX); + iopm_pages = alloc_pages(GFP_KERNEL, order); if (!iopm_pages) @@ -952,9 +975,6 @@ static __init int svm_hardware_setup(void) supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); - if (boot_cpu_has(X86_FEATURE_NX)) - kvm_enable_efer_bits(EFER_NX); - if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) kvm_enable_efer_bits(EFER_FFXSR); @@ -996,6 +1016,8 @@ static __init int svm_hardware_setup(void) /* Note, SEV setup consumes npt_enabled. */ sev_hardware_setup(); + svm_hv_hardware_setup(); + svm_adjust_mmio_mask(); for_each_possible_cpu(cpu) { @@ -1009,16 +1031,12 @@ static __init int svm_hardware_setup(void) nrips = false; } - if (avic) { - if (!npt_enabled || - !boot_cpu_has(X86_FEATURE_AVIC) || - !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) { - avic = false; - } else { - pr_info("AVIC enabled\n"); + enable_apicv = avic = avic && npt_enabled && boot_cpu_has(X86_FEATURE_AVIC); - amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); - } + if (enable_apicv) { + pr_info("AVIC enabled\n"); + + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); } if (vls) { @@ -1082,26 +1100,30 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static u64 svm_get_l2_tsc_offset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - u64 g_tsc_offset = 0; - if (is_guest_mode(vcpu)) { - /* Write L1's TSC offset. */ - g_tsc_offset = svm->vmcb->control.tsc_offset - - svm->vmcb01.ptr->control.tsc_offset; - svm->vmcb01.ptr->control.tsc_offset = offset; - } + return svm->nested.ctl.tsc_offset; +} - trace_kvm_write_tsc_offset(vcpu->vcpu_id, - svm->vmcb->control.tsc_offset - g_tsc_offset, - offset); +static u64 svm_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) +{ + return kvm_default_tsc_scaling_ratio; +} - svm->vmcb->control.tsc_offset = offset + g_tsc_offset; +static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +{ + struct vcpu_svm *svm = to_svm(vcpu); + svm->vmcb01.ptr->control.tsc_offset = vcpu->arch.l1_tsc_offset; + svm->vmcb->control.tsc_offset = offset; vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); - return svm->vmcb->control.tsc_offset; +} + +static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +{ + wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); } /* Evaluate instruction intercepts that depend on guest CPUID features. */ @@ -1289,6 +1311,8 @@ static void init_vmcb(struct kvm_vcpu *vcpu) } } + svm_hv_init_vmcb(svm->vmcb); + vmcb_mark_all_dirty(svm->vmcb); enable_gif(svm); @@ -3764,6 +3788,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) } svm->vmcb->save.cr2 = vcpu->arch.cr2; + svm_hv_update_vp_id(svm->vmcb, vcpu); + /* * Run with all-zero DR6 unless needed, so that we can get the exact cause * of a #DB. @@ -3837,6 +3863,12 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) svm->next_rip = 0; if (is_guest_mode(vcpu)) { nested_sync_control_from_vmcb02(svm); + + /* Track VMRUNs that have made past consistency checking */ + if (svm->nested.nested_run_pending && + svm->vmcb->control.exit_code != SVM_EXIT_ERR) + ++vcpu->stat.nested_run; + svm->nested.nested_run_pending = 0; } @@ -3848,10 +3880,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); - if (npt_enabled) { - vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); - vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR); - } + if (npt_enabled) + kvm_register_clear_available(vcpu, VCPU_EXREG_PDPTR); /* * We need to handle MC intercepts here before the vcpu has a chance to @@ -3879,6 +3909,8 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, svm->vmcb->control.nested_cr3 = __sme_set(root_hpa); vmcb_mark_dirty(svm->vmcb, VMCB_NPT); + hv_track_root_tdp(vcpu, root_hpa); + /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) return; @@ -4251,7 +4283,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !svm_smi_blocked(vcpu); } -static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); int ret; @@ -4273,7 +4305,7 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map; @@ -4429,13 +4461,12 @@ static int svm_vm_init(struct kvm *kvm) if (!pause_filter_count || !pause_filter_thresh) kvm->arch.pause_in_guest = true; - if (avic) { + if (enable_apicv) { int ret = avic_vm_init(kvm); if (ret) return ret; } - kvm_apicv_init(kvm, avic); return 0; } @@ -4526,7 +4557,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .has_wbinvd_exit = svm_has_wbinvd_exit, - .write_l1_tsc_offset = svm_write_l1_tsc_offset, + .get_l2_tsc_offset = svm_get_l2_tsc_offset, + .get_l2_tsc_multiplier = svm_get_l2_tsc_multiplier, + .write_tsc_offset = svm_write_tsc_offset, + .write_tsc_multiplier = svm_write_tsc_multiplier, .load_mmu_pgd = svm_load_mmu_pgd, @@ -4546,8 +4580,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .setup_mce = svm_setup_mce, .smi_allowed = svm_smi_allowed, - .pre_enter_smm = svm_pre_enter_smm, - .pre_leave_smm = svm_pre_leave_smm, + .enter_smm = svm_enter_smm, + .leave_smm = svm_leave_smm, .enable_smi_window = svm_enable_smi_window, .mem_enc_op = svm_mem_enc_op, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 2c9ece618b29..f89b623bb591 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -32,6 +32,11 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; +/* + * Clean bits in VMCB. + * VMCB_ALL_CLEAN_MASK might also need to + * be updated if this enum is modified. + */ enum { VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, pause filter count */ @@ -49,9 +54,17 @@ enum { * AVIC PHYSICAL_TABLE pointer, * AVIC LOGICAL_TABLE pointer */ - VMCB_DIRTY_MAX, + VMCB_SW = 31, /* Reserved for hypervisor/software use */ }; +#define VMCB_ALL_CLEAN_MASK ( \ + (1U << VMCB_INTERCEPTS) | (1U << VMCB_PERM_MAP) | \ + (1U << VMCB_ASID) | (1U << VMCB_INTR) | \ + (1U << VMCB_NPT) | (1U << VMCB_CR) | (1U << VMCB_DR) | \ + (1U << VMCB_DT) | (1U << VMCB_SEG) | (1U << VMCB_CR2) | \ + (1U << VMCB_LBR) | (1U << VMCB_AVIC) | \ + (1U << VMCB_SW)) + /* TPR and CR2 are always written before VMRUN */ #define VMCB_ALWAYS_DIRTY_MASK ((1U << VMCB_INTR) | (1U << VMCB_CR2)) @@ -238,10 +251,15 @@ static inline void vmcb_mark_all_dirty(struct vmcb *vmcb) static inline void vmcb_mark_all_clean(struct vmcb *vmcb) { - vmcb->control.clean = ((1 << VMCB_DIRTY_MAX) - 1) + vmcb->control.clean = VMCB_ALL_CLEAN_MASK & ~VMCB_ALWAYS_DIRTY_MASK; } +static inline bool vmcb_is_clean(struct vmcb *vmcb, int bit) +{ + return (vmcb->control.clean & (1 << bit)); +} + static inline void vmcb_mark_dirty(struct vmcb *vmcb, int bit) { vmcb->control.clean &= ~(1 << bit); @@ -480,8 +498,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops; #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL -extern int avic; - static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) { svm->vmcb->control.avic_vapic_bar = data & VMCB_AVIC_APIC_BAR_MASK; diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c new file mode 100644 index 000000000000..98aa981c04ec --- /dev/null +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM L1 hypervisor optimizations on Hyper-V for SVM. + */ + +#include <linux/kvm_host.h> +#include "kvm_cache_regs.h" + +#include <asm/mshyperv.h> + +#include "svm.h" +#include "svm_ops.h" + +#include "hyperv.h" +#include "kvm_onhyperv.h" +#include "svm_onhyperv.h" + +int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +{ + struct hv_enlightenments *hve; + struct hv_partition_assist_pg **p_hv_pa_pg = + &to_kvm_hv(vcpu->kvm)->hv_pa_pg; + + if (!*p_hv_pa_pg) + *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); + + if (!*p_hv_pa_pg) + return -ENOMEM; + + hve = (struct hv_enlightenments *)to_svm(vcpu)->vmcb->control.reserved_sw; + + hve->partition_assist_page = __pa(*p_hv_pa_pg); + hve->hv_vm_id = (unsigned long)vcpu->kvm; + if (!hve->hv_enlightenments_control.nested_flush_hypercall) { + hve->hv_enlightenments_control.nested_flush_hypercall = 1; + vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + } + + return 0; +} + diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h new file mode 100644 index 000000000000..9b9a55abc29f --- /dev/null +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * KVM L1 hypervisor optimizations on Hyper-V for SVM. + */ + +#ifndef __ARCH_X86_KVM_SVM_ONHYPERV_H__ +#define __ARCH_X86_KVM_SVM_ONHYPERV_H__ + +#if IS_ENABLED(CONFIG_HYPERV) +#include <asm/mshyperv.h> + +#include "hyperv.h" +#include "kvm_onhyperv.h" + +static struct kvm_x86_ops svm_x86_ops; + +/* + * Hyper-V uses the software reserved 32 bytes in VMCB + * control area to expose SVM enlightenments to guests. + */ +struct hv_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 enlightened_npt_tlb: 1; + u32 reserved:29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB + */ +#define VMCB_HV_NESTED_ENLIGHTENMENTS VMCB_SW + +int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu); + +static inline void svm_hv_init_vmcb(struct vmcb *vmcb) +{ + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + + if (npt_enabled && + ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) + hve->hv_enlightenments_control.enlightened_npt_tlb = 1; +} + +static inline void svm_hv_hardware_setup(void) +{ + if (npt_enabled && + ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) { + pr_info("kvm: Hyper-V enlightened NPT TLB flush enabled\n"); + svm_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; + svm_x86_ops.tlb_remote_flush_with_range = + hv_remote_flush_tlb_with_range; + } + + if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) { + int cpu; + + pr_info("kvm: Hyper-V Direct TLB Flush enabled\n"); + for_each_online_cpu(cpu) { + struct hv_vp_assist_page *vp_ap = + hv_get_vp_assist_page(cpu); + + if (!vp_ap) + continue; + + vp_ap->nested_control.features.directhypercall = 1; + } + svm_x86_ops.enable_direct_tlbflush = + svm_hv_enable_direct_tlbflush; + } +} + +static inline void svm_hv_vmcb_dirty_nested_enlightenments( + struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = to_svm(vcpu)->vmcb; + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + + /* + * vmcb can be NULL if called during early vcpu init. + * And its okay not to mark vmcb dirty during vcpu init + * as we mark it dirty unconditionally towards end of vcpu + * init phase. + */ + if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && + hve->hv_enlightenments_control.msr_bitmap) + vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); +} + +static inline void svm_hv_update_vp_id(struct vmcb *vmcb, + struct kvm_vcpu *vcpu) +{ + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + u32 vp_index = kvm_hv_get_vpindex(vcpu); + + if (hve->hv_vp_id != vp_index) { + hve->hv_vp_id = vp_index; + vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + } +} +#else + +static inline void svm_hv_init_vmcb(struct vmcb *vmcb) +{ +} + +static inline void svm_hv_hardware_setup(void) +{ +} + +static inline void svm_hv_vmcb_dirty_nested_enlightenments( + struct kvm_vcpu *vcpu) +{ +} + +static inline void svm_hv_update_vp_id(struct vmcb *vmcb, + struct kvm_vcpu *vcpu) +{ +} +#endif /* CONFIG_HYPERV */ + +#endif /* __ARCH_X86_KVM_SVM_ONHYPERV_H__ */ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a61c015870e3..b484141ea15b 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -997,7 +997,7 @@ TRACE_EVENT(kvm_wait_lapic_expire, __entry->delta < 0 ? "early" : "late") ); -TRACE_EVENT(kvm_enter_smm, +TRACE_EVENT(kvm_smm_transition, TP_PROTO(unsigned int vcpu_id, u64 smbase, bool entering), TP_ARGS(vcpu_id, smbase, entering), @@ -1550,16 +1550,16 @@ TRACE_EVENT(kvm_nested_vmenter_failed, TP_ARGS(msg, err), TP_STRUCT__entry( - __field(const char *, msg) + __string(msg, msg) __field(u32, err) ), TP_fast_assign( - __entry->msg = msg; + __assign_str(msg, msg); __entry->err = err; ), - TP_printk("%s%s", __entry->msg, !__entry->err ? "" : + TP_printk("%s%s", __get_str(msg), !__entry->err ? "" : __print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS)) ); diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 8dee8a5fbc17..4705ad55abb5 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -12,7 +12,6 @@ extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; extern bool __read_mostly enable_pml; -extern bool __read_mostly enable_apicv; extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 @@ -90,8 +89,7 @@ static inline bool cpu_has_vmx_preemption_timer(void) static inline bool cpu_has_vmx_posted_intr(void) { - return IS_ENABLED(CONFIG_X86_LOCAL_APIC) && - vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; + return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; } static inline bool cpu_has_load_ia32_efer(void) diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 41f24661af04..896b2a50b4aa 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -319,6 +319,9 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) if (unlikely(!assist_page.enlighten_vmentry)) return false; + if (unlikely(!evmptr_is_valid(assist_page.current_nested_vmcs))) + return false; + *evmcs_gpa = assist_page.current_nested_vmcs; return true; diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index bd41d9462355..2ec9b46f0d0c 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -197,6 +197,14 @@ static inline void evmcs_load(u64 phys_addr) {} static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ +#define EVMPTR_INVALID (-1ULL) +#define EVMPTR_MAP_PENDING (-2ULL) + +static inline bool evmptr_is_valid(u64 evmptr) +{ + return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; +} + enum nested_evmptrld_status { EVMPTRLD_DISABLED, EVMPTRLD_SUCCEEDED, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 6058a65a6ede..183fd9d62fc5 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -173,9 +173,13 @@ static int nested_vmx_failValid(struct kvm_vcpu *vcpu, | X86_EFLAGS_ZF); get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error; /* - * We don't need to force a shadow sync because - * VM_INSTRUCTION_ERROR is not shadowed + * We don't need to force sync to shadow VMCS because + * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all + * fields and thus must be synced. */ + if (to_vmx(vcpu)->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true; + return kvm_skip_emulated_instruction(vcpu); } @@ -187,7 +191,8 @@ static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error) * failValid writes the error number to the current VMCS, which * can't be done if there isn't a current VMCS. */ - if (vmx->nested.current_vmptr == -1ull && !vmx->nested.hv_evmcs) + if (vmx->nested.current_vmptr == -1ull && + !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) return nested_vmx_failInvalid(vcpu); return nested_vmx_failValid(vcpu, vm_instruction_error); @@ -221,12 +226,12 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx->nested.hv_evmcs) - return; + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); + vmx->nested.hv_evmcs = NULL; + } - kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); - vmx->nested.hv_evmcs_vmptr = 0; - vmx->nested.hv_evmcs = NULL; + vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, @@ -346,16 +351,21 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, vmcs12->guest_physical_address = fault->address; } +static void nested_ept_new_eptp(struct kvm_vcpu *vcpu) +{ + kvm_init_shadow_ept_mmu(vcpu, + to_vmx(vcpu)->nested.msrs.ept_caps & + VMX_EPT_EXECUTE_ONLY_BIT, + nested_ept_ad_enabled(vcpu), + nested_ept_get_eptp(vcpu)); +} + static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) { WARN_ON(mmu_is_nested(vcpu)); vcpu->arch.mmu = &vcpu->arch.guest_mmu; - kvm_init_shadow_ept_mmu(vcpu, - to_vmx(vcpu)->nested.msrs.ept_caps & - VMX_EPT_EXECUTE_ONLY_BIT, - nested_ept_ad_enabled(vcpu), - nested_ept_get_eptp(vcpu)); + nested_ept_new_eptp(vcpu); vcpu->arch.mmu->get_guest_pgd = nested_ept_get_eptp; vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault; vcpu->arch.mmu->get_pdptr = kvm_pdptr_read; @@ -1058,54 +1068,13 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, } /* - * Returns true if the MMU needs to be sync'd on nested VM-Enter/VM-Exit. - * tl;dr: the MMU needs a sync if L0 is using shadow paging and L1 didn't - * enable VPID for L2 (implying it expects a TLB flush on VMX transitions). - * Here's why. - * - * If EPT is enabled by L0 a sync is never needed: - * - if it is disabled by L1, then L0 is not shadowing L1 or L2 PTEs, there - * cannot be unsync'd SPTEs for either L1 or L2. - * - * - if it is also enabled by L1, then L0 doesn't need to sync on VM-Enter - * VM-Enter as VM-Enter isn't required to invalidate guest-physical mappings - * (irrespective of VPID), i.e. L1 can't rely on the (virtual) CPU to flush - * stale guest-physical mappings for L2 from the TLB. And as above, L0 isn't - * shadowing L1 PTEs so there are no unsync'd SPTEs to sync on VM-Exit. - * - * If EPT is disabled by L0: - * - if VPID is enabled by L1 (for L2), the situation is similar to when L1 - * enables EPT: L0 doesn't need to sync as VM-Enter and VM-Exit aren't - * required to invalidate linear mappings (EPT is disabled so there are - * no combined or guest-physical mappings), i.e. L1 can't rely on the - * (virtual) CPU to flush stale linear mappings for either L2 or itself (L1). - * - * - however if VPID is disabled by L1, then a sync is needed as L1 expects all - * linear mappings (EPT is disabled so there are no combined or guest-physical - * mappings) to be invalidated on both VM-Enter and VM-Exit. - * - * Note, this logic is subtly different than nested_has_guest_tlb_tag(), which - * additionally checks that L2 has been assigned a VPID (when EPT is disabled). - * Whether or not L2 has been assigned a VPID by L0 is irrelevant with respect - * to L1's expectations, e.g. L0 needs to invalidate hardware TLB entries if L2 - * doesn't have a unique VPID to prevent reusing L1's entries (assuming L1 has - * been assigned a VPID), but L0 doesn't need to do a MMU sync because L1 - * doesn't expect stale (virtual) TLB entries to be flushed, i.e. L1 doesn't - * know that L0 will flush the TLB and so L1 will do INVVPID as needed to flush - * stale TLB entries, at which point L0 will sync L2's MMU. - */ -static bool nested_vmx_transition_mmu_sync(struct kvm_vcpu *vcpu) -{ - return !enable_ept && !nested_cpu_has_vpid(get_vmcs12(vcpu)); -} - -/* * Load guest's/host's cr3 at nested entry/exit. @nested_ept is true if we are * emulating VM-Entry into a guest with EPT enabled. On failure, the expected * Exit Qualification (for a VM-Entry consistency check VM-Exit) is assigned to * @entry_failure_code. */ -static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, +static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, + bool nested_ept, bool reload_pdptrs, enum vm_entry_failure_code *entry_failure_code) { if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) { @@ -1117,27 +1086,19 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * If PAE paging and EPT are both on, CR3 is not used by the CPU and * must not be dereferenced. */ - if (!nested_ept && is_pae_paging(vcpu) && - (cr3 != kvm_read_cr3(vcpu) || pdptrs_changed(vcpu))) { - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { - *entry_failure_code = ENTRY_FAIL_PDPTE; - return -EINVAL; - } + if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) && + CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { + *entry_failure_code = ENTRY_FAIL_PDPTE; + return -EINVAL; } - /* - * Unconditionally skip the TLB flush on fast CR3 switch, all TLB - * flushes are handled by nested_vmx_transition_tlb_flush(). See - * nested_vmx_transition_mmu_sync for details on skipping the MMU sync. - */ if (!nested_ept) - kvm_mmu_new_pgd(vcpu, cr3, true, - !nested_vmx_transition_mmu_sync(vcpu)); + kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); - kvm_init_mmu(vcpu, false); + kvm_init_mmu(vcpu); return 0; } @@ -1170,17 +1131,28 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); /* - * If VPID is disabled, linear and combined mappings are flushed on - * VM-Enter/VM-Exit, and guest-physical mappings are valid only for - * their associated EPTP. + * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings + * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a + * full TLB flush from the guest's perspective. This is required even + * if VPID is disabled in the host as KVM may need to synchronize the + * MMU in response to the guest TLB flush. + * + * Note, using TLB_FLUSH_GUEST is correct even if nested EPT is in use. + * EPT is a special snowflake, as guest-physical mappings aren't + * flushed on VPID invalidations, including VM-Enter or VM-Exit with + * VPID disabled. As a result, KVM _never_ needs to sync nEPT + * entries on VM-Enter because L1 can't rely on VM-Enter to flush + * those mappings. */ - if (!enable_vpid) + if (!nested_cpu_has_vpid(vmcs12)) { + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return; + } + + /* L2 should never have a VPID if VPID is disabled. */ + WARN_ON(!enable_vpid); /* - * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings - * for *all* contexts to be flushed on VM-Enter/VM-Exit. - * * If VPID is enabled and used by vmc12, but L2 does not have a unique * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate * a VPID for L2, flush the current context as the effective ASID is @@ -1192,13 +1164,12 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, * * If a TLB flush isn't required due to any of the above, and vpid12 is * changing then the new "virtual" VPID (vpid12) will reuse the same - * "real" VPID (vpid02), and so needs to be sync'd. There is no direct + * "real" VPID (vpid02), and so needs to be flushed. There's no direct * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for - * all nested vCPUs. + * all nested vCPUs. Remember, a flush on VM-Enter does not invalidate + * guest-physical mappings, so there is no need to sync the nEPT MMU. */ - if (!nested_cpu_has_vpid(vmcs12)) { - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } else if (!nested_has_guest_tlb_tag(vcpu)) { + if (!nested_has_guest_tlb_tag(vcpu)) { kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } else if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) { @@ -1586,7 +1557,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) vmcs_load(vmx->loaded_vmcs->vmcs); } -static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) +static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields) { struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; @@ -1595,7 +1566,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->tpr_threshold = evmcs->tpr_threshold; vmcs12->guest_rip = evmcs->guest_rip; - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) { vmcs12->guest_rsp = evmcs->guest_rsp; vmcs12->guest_rflags = evmcs->guest_rflags; @@ -1603,23 +1574,23 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) evmcs->guest_interruptibility_info; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) { vmcs12->cpu_based_vm_exec_control = evmcs->cpu_based_vm_exec_control; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN))) { vmcs12->exception_bitmap = evmcs->exception_bitmap; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY))) { vmcs12->vm_entry_controls = evmcs->vm_entry_controls; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT))) { vmcs12->vm_entry_intr_info_field = evmcs->vm_entry_intr_info_field; @@ -1629,7 +1600,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) evmcs->vm_entry_instruction_len; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) { vmcs12->host_ia32_pat = evmcs->host_ia32_pat; vmcs12->host_ia32_efer = evmcs->host_ia32_efer; @@ -1649,7 +1620,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->host_tr_selector = evmcs->host_tr_selector; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1))) { vmcs12->pin_based_vm_exec_control = evmcs->pin_based_vm_exec_control; @@ -1658,18 +1629,18 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) evmcs->secondary_vm_exec_control; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP))) { vmcs12->io_bitmap_a = evmcs->io_bitmap_a; vmcs12->io_bitmap_b = evmcs->io_bitmap_b; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP))) { vmcs12->msr_bitmap = evmcs->msr_bitmap; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2))) { vmcs12->guest_es_base = evmcs->guest_es_base; vmcs12->guest_cs_base = evmcs->guest_cs_base; @@ -1709,14 +1680,14 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->guest_tr_selector = evmcs->guest_tr_selector; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2))) { vmcs12->tsc_offset = evmcs->tsc_offset; vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr; vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR))) { vmcs12->cr0_guest_host_mask = evmcs->cr0_guest_host_mask; vmcs12->cr4_guest_host_mask = evmcs->cr4_guest_host_mask; @@ -1728,7 +1699,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->guest_dr7 = evmcs->guest_dr7; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER))) { vmcs12->host_fs_base = evmcs->host_fs_base; vmcs12->host_gs_base = evmcs->host_gs_base; @@ -1738,13 +1709,13 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) vmcs12->host_rsp = evmcs->host_rsp; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT))) { vmcs12->ept_pointer = evmcs->ept_pointer; vmcs12->virtual_processor_id = evmcs->virtual_processor_id; } - if (unlikely(!(evmcs->hv_clean_fields & + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1))) { vmcs12->vmcs_link_pointer = evmcs->vmcs_link_pointer; vmcs12->guest_ia32_debugctl = evmcs->guest_ia32_debugctl; @@ -1799,10 +1770,10 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) * vmcs12->exit_io_instruction_eip = evmcs->exit_io_instruction_eip; */ - return 0; + return; } -static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) +static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) { struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; @@ -1962,7 +1933,7 @@ static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs; - return 0; + return; } /* @@ -1979,13 +1950,13 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( if (likely(!vmx->nested.enlightened_vmcs_enabled)) return EVMPTRLD_DISABLED; - if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) + if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) { + nested_release_evmcs(vcpu); return EVMPTRLD_DISABLED; + } - if (unlikely(!vmx->nested.hv_evmcs || - evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { - if (!vmx->nested.hv_evmcs) - vmx->nested.current_vmptr = -1ull; + if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { + vmx->nested.current_vmptr = -1ull; nested_release_evmcs(vcpu); @@ -2023,7 +1994,6 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( return EVMPTRLD_VMFAIL; } - vmx->nested.dirty_vmcs12 = true; vmx->nested.hv_evmcs_vmptr = evmcs_gpa; evmcs_gpa_changed = true; @@ -2056,14 +2026,10 @@ void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vmx->nested.hv_evmcs) { + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) copy_vmcs12_to_enlightened(vmx); - /* All fields are clean */ - vmx->nested.hv_evmcs->hv_clean_fields |= - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; - } else { + else copy_vmcs12_to_shadow(vmx); - } vmx->nested.need_vmcs12_to_shadow_sync = false; } @@ -2208,7 +2174,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); - if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) + if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) prepare_vmcs02_early_rare(vmx, vmcs12); /* @@ -2277,7 +2243,8 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_ENABLE_VMFUNC); + SECONDARY_EXEC_ENABLE_VMFUNC | + SECONDARY_EXEC_TSC_SCALING); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -2488,18 +2455,18 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * is assigned to entry_failure_code on failure. */ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + bool from_vmentry, enum vm_entry_failure_code *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; bool load_guest_pdptrs_vmcs12 = false; - if (vmx->nested.dirty_vmcs12 || hv_evmcs) { + if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { prepare_vmcs02_rare(vmx, vmcs12); vmx->nested.dirty_vmcs12 = false; - load_guest_pdptrs_vmcs12 = !hv_evmcs || - !(hv_evmcs->hv_clean_fields & + load_guest_pdptrs_vmcs12 = !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) || + !(vmx->nested.hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); } @@ -2532,10 +2499,18 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); } - vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( + vcpu->arch.l1_tsc_offset, + vmx_get_l2_tsc_offset(vcpu), + vmx_get_l2_tsc_multiplier(vcpu)); + + vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( + vcpu->arch.l1_tsc_scaling_ratio, + vmx_get_l2_tsc_multiplier(vcpu)); + vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); if (kvm_has_tsc_control) - decache_tsc_multiplier(vmx); + vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); nested_vmx_transition_tlb_flush(vcpu, vmcs12, true); @@ -2572,7 +2547,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* Shadow page tables on either EPT or shadow page tables. */ if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12), - entry_failure_code)) + from_vmentry, entry_failure_code)) return -EINVAL; /* @@ -2604,6 +2579,17 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); + + /* + * It was observed that genuine Hyper-V running in L1 doesn't reset + * 'hv_clean_fields' by itself, it only sets the corresponding dirty + * bits when it changes a field in eVMCS. Mark all fields as clean + * here. + */ + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + vmx->nested.hv_evmcs->hv_clean_fields |= + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + return 0; } @@ -3093,13 +3079,20 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) * L2 was running), map it here to make sure vmcs12 changes are * properly reflected. */ - if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs) { + if (vmx->nested.enlightened_vmcs_enabled && + vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) { enum nested_evmptrld_status evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, false); if (evmptrld_status == EVMPTRLD_VMFAIL || evmptrld_status == EVMPTRLD_ERROR) return false; + + /* + * Post migration VMCS12 always provides the most actual + * information, copy it to eVMCS upon entry. + */ + vmx->nested.need_vmcs12_to_shadow_sync = true; } return true; @@ -3113,6 +3106,18 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) struct page *page; u64 hpa; + if (!vcpu->arch.pdptrs_from_userspace && + !nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { + /* + * Reload the guest's PDPTRs since after a migration + * the guest CR3 might be restored prior to setting the nested + * state which can lead to a load of wrong PDPTRs. + */ + if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))) + return false; + } + + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { /* * Translate L1 physical address to host physical @@ -3175,6 +3180,15 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) offset_in_page(vmcs12->posted_intr_desc_addr)); vmcs_write64(POSTED_INTR_DESC_ADDR, pfn_to_hpa(map->pfn) + offset_in_page(vmcs12->posted_intr_desc_addr)); + } else { + /* + * Defer the KVM_INTERNAL_EXIT until KVM tries to + * access the contents of the VMCS12 posted interrupt + * descriptor. (Note that KVM may do this when it + * should not, per the architectural specification.) + */ + vmx->nested.pi_desc = NULL; + pin_controls_clearbit(vmx, PIN_BASED_POSTED_INTR); } } if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) @@ -3354,10 +3368,8 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, } enter_guest_mode(vcpu); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) - vcpu->arch.tsc_offset += vmcs12->tsc_offset; - if (prepare_vmcs02(vcpu, vmcs12, &entry_failure_code)) { + if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &entry_failure_code)) { exit_reason.basic = EXIT_REASON_INVALID_STATE; vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit_guest_mode; @@ -3437,7 +3449,7 @@ vmentry_fail_vmexit: load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason.full; - if (enable_shadow_vmcs || vmx->nested.hv_evmcs) + if (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; } @@ -3454,8 +3466,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); enum nested_evmptrld_status evmptrld_status; - ++vcpu->stat.nested_run; - if (!nested_vmx_check_permission(vcpu)) return 1; @@ -3467,7 +3477,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return nested_vmx_failInvalid(vcpu); } - if (CC(!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull)) + if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) && + vmx->nested.current_vmptr == -1ull)) return nested_vmx_failInvalid(vcpu); vmcs12 = get_vmcs12(vcpu); @@ -3481,8 +3492,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (CC(vmcs12->hdr.shadow_vmcs)) return nested_vmx_failInvalid(vcpu); - if (vmx->nested.hv_evmcs) { - copy_enlightened_to_vmcs12(vmx); + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields); /* Enlightened VMCS doesn't have launch state */ vmcs12->launch_state = !launch; } else if (enable_shadow_vmcs) { @@ -3682,25 +3693,29 @@ void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) } } -static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) +static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; void *vapic_page; u16 status; - if (!vmx->nested.pi_desc || !vmx->nested.pi_pending) - return; + if (!vmx->nested.pi_pending) + return 0; + + if (!vmx->nested.pi_desc) + goto mmio_needed; vmx->nested.pi_pending = false; + if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return; + return 0; max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); if (max_irr != 256) { vapic_page = vmx->nested.virtual_apic_map.hva; if (!vapic_page) - return; + goto mmio_needed; __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page, &max_irr); @@ -3713,6 +3728,11 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) } nested_mark_vmcs12_pages_dirty(vcpu); + return 0; + +mmio_needed: + kvm_handle_memory_failure(vcpu, X86EMUL_IO_NEEDED, NULL); + return -ENXIO; } static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, @@ -3887,8 +3907,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) } no_vmexit: - vmx_complete_nested_posted_interrupt(vcpu); - return 0; + return vmx_complete_nested_posted_interrupt(vcpu); } static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) @@ -4032,10 +4051,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vmx->nested.hv_evmcs) + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - vmx->nested.need_sync_vmcs02_to_vmcs12_rare = !vmx->nested.hv_evmcs; + vmx->nested.need_sync_vmcs02_to_vmcs12_rare = + !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); @@ -4206,7 +4226,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * Only PDPTE load can fail as the value of cr3 was checked on entry and * couldn't have changed. */ - if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored)) + if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, true, &ignored)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); nested_vmx_transition_tlb_flush(vcpu, vmcs12, false); @@ -4463,8 +4483,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, if (nested_cpu_has_preemption_timer(vmcs12)) hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) - vcpu->arch.tsc_offset -= vmcs12->tsc_offset; + if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING)) { + vcpu->arch.tsc_offset = vcpu->arch.l1_tsc_offset; + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING)) + vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; + } if (likely(!vmx->fail)) { sync_vmcs02_to_vmcs12(vcpu, vmcs12); @@ -4501,12 +4524,12 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); + if (kvm_has_tsc_control) + vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); + if (vmx->nested.l1_tpr_threshold != -1) vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold); - if (kvm_has_tsc_control) - decache_tsc_multiplier(vmx); - if (vmx->nested.change_vmcs01_virtual_apic_mode) { vmx->nested.change_vmcs01_virtual_apic_mode = false; vmx_set_virtual_apic_mode(vcpu); @@ -4532,7 +4555,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, } if ((vm_exit_reason != -1) && - (enable_shadow_vmcs || vmx->nested.hv_evmcs)) + (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ @@ -4987,6 +5010,8 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); + } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { + nested_release_evmcs(vcpu); } return nested_vmx_succeed(vcpu); @@ -5228,7 +5253,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); /* Forbid normal VMPTRLD if Enlightened version was used */ - if (vmx->nested.hv_evmcs) + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) return 1; if (vmx->nested.current_vmptr != vmptr) { @@ -5284,7 +5309,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (unlikely(to_vmx(vcpu)->nested.hv_evmcs)) + if (unlikely(evmptr_is_valid(to_vmx(vcpu)->nested.hv_evmcs_vmptr))) return 1; if (get_vmx_mem_address(vcpu, exit_qual, instr_info, @@ -5461,8 +5486,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) /* * Sync the shadow page tables if EPT is disabled, L1 is invalidating - * linear mappings for L2 (tagged with L2's VPID). Free all roots as - * VPIDs are not tracked in the MMU role. + * linear mappings for L2 (tagged with L2's VPID). Free all guest + * roots as VPIDs are not tracked in the MMU role. * * Note, this operates on root_mmu, not guest_mmu, as L1 and L2 share * an MMU when EPT is disabled. @@ -5470,8 +5495,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) * TODO: sync only the affected SPTEs for INVDIVIDUAL_ADDR. */ if (!enable_ept) - kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, - KVM_MMU_ROOTS_ALL); + kvm_mmu_free_guest_mode_roots(vcpu, &vcpu->arch.root_mmu); return nested_vmx_succeed(vcpu); } @@ -5481,23 +5505,16 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu, { u32 index = kvm_rcx_read(vcpu); u64 new_eptp; - bool accessed_dirty; - struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - if (!nested_cpu_has_eptp_switching(vmcs12) || - !nested_cpu_has_ept(vmcs12)) + if (WARN_ON_ONCE(!nested_cpu_has_ept(vmcs12))) return 1; - if (index >= VMFUNC_EPTP_ENTRIES) return 1; - if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT, &new_eptp, index * 8, 8)) return 1; - accessed_dirty = !!(new_eptp & VMX_EPTP_AD_ENABLE_BIT); - /* * If the (L2) guest does a vmfunc to the currently * active ept pointer, we don't have to do anything else @@ -5506,11 +5523,11 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu, if (!nested_vmx_check_eptp(vcpu, new_eptp)) return 1; - mmu->ept_ad = accessed_dirty; - mmu->mmu_role.base.ad_disabled = !accessed_dirty; vmcs12->ept_pointer = new_eptp; + nested_ept_new_eptp(vcpu); - kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + if (!nested_cpu_has_vpid(vmcs12)) + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } return 0; @@ -5533,7 +5550,17 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) } vmcs12 = get_vmcs12(vcpu); - if ((vmcs12->vm_function_control & (1 << function)) == 0) + + /* + * #UD on out-of-bounds function has priority over VM-Exit, and VMFUNC + * is enabled in vmcs02 if and only if it's enabled in vmcs12. + */ + if (WARN_ON_ONCE((function > 63) || !nested_cpu_has_vmfunc(vmcs12))) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + if (!(vmcs12->vm_function_control & BIT_ULL(function))) goto fail; switch (function) { @@ -6056,7 +6083,8 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (vmx_has_valid_vmcs12(vcpu)) { kvm_state.size += sizeof(user_vmx_nested_state->vmcs12); - if (vmx->nested.hv_evmcs) + /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ + if (vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID) kvm_state.flags |= KVM_STATE_NESTED_EVMCS; if (is_guest_mode(vcpu) && @@ -6112,8 +6140,15 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, } else { copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); if (!vmx->nested.need_vmcs12_to_shadow_sync) { - if (vmx->nested.hv_evmcs) - copy_enlightened_to_vmcs12(vmx); + if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + /* + * L1 hypervisor is not obliged to keep eVMCS + * clean fields data always up-to-date while + * not in guest mode, 'hv_clean_fields' is only + * supposed to be actual upon vmentry so we need + * to ignore it here and do full copy. + */ + copy_enlightened_to_vmcs12(vmx, 0); else if (enable_shadow_vmcs) copy_shadow_to_vmcs12(vmx); } @@ -6255,6 +6290,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, * restored yet. EVMCS will be mapped from * nested_get_vmcs12_pages(). */ + vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING; kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); } else { return -EINVAL; @@ -6339,6 +6375,40 @@ void nested_vmx_set_vmcs_shadowing_bitmap(void) } /* + * Indexing into the vmcs12 uses the VMCS encoding rotated left by 6. Undo + * that madness to get the encoding for comparison. + */ +#define VMCS12_IDX_TO_ENC(idx) ((u16)(((u16)(idx) >> 6) | ((u16)(idx) << 10))) + +static u64 nested_vmx_calc_vmcs_enum_msr(void) +{ + /* + * Note these are the so called "index" of the VMCS field encoding, not + * the index into vmcs12. + */ + unsigned int max_idx, idx; + int i; + + /* + * For better or worse, KVM allows VMREAD/VMWRITE to all fields in + * vmcs12, regardless of whether or not the associated feature is + * exposed to L1. Simply find the field with the highest index. + */ + max_idx = 0; + for (i = 0; i < nr_vmcs12_fields; i++) { + /* The vmcs12 table is very, very sparsely populated. */ + if (!vmcs_field_to_offset_table[i]) + continue; + + idx = vmcs_field_index(VMCS12_IDX_TO_ENC(i)); + if (idx > max_idx) + max_idx = idx; + } + + return (u64)max_idx << VMCS_FIELD_INDEX_SHIFT; +} + +/* * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be * returned for the various VMX controls MSRs when nested VMX is enabled. * The same values should also be used to verify that vmcs12 control fields are @@ -6474,7 +6544,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_XSAVES; + SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_TSC_SCALING; /* * We can emulate "VMCS shadowing," even if the hardware @@ -6582,8 +6653,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1); rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1); - /* highest index: VMX_PREEMPTION_TIMER_VALUE */ - msrs->vmcs_enum = VMCS12_MAX_FIELD_INDEX << 1; + msrs->vmcs_enum = nested_vmx_calc_vmcs_enum_msr(); } void nested_vmx_hardware_unsetup(void) diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 184418baeb3c..b69a80f43b37 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -56,14 +56,9 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * In case we do two consecutive get/set_nested_state()s while L2 was - * running hv_evmcs may end up not being mapped (we map it from - * nested_vmx_run()/vmx_vcpu_run()). Check is_guest_mode() as we always - * have vmcs12 if it is true. - */ - return is_guest_mode(vcpu) || vmx->nested.current_vmptr != -1ull || - vmx->nested.hv_evmcs; + /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ + return vmx->nested.current_vmptr != -1ull || + vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID; } static inline u16 nested_get_vpid02(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 459748680daf..5f81ef092bd4 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -238,6 +238,20 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) /* + * Bail out of the block loop if the VM has an assigned + * device, but the blocking vCPU didn't reconfigure the + * PI.NV to the wakeup vector, i.e. the assigned device + * came along after the initial check in pi_pre_block(). + */ +void vmx_pi_start_assignment(struct kvm *kvm) +{ + if (!irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK); +} + +/* * pi_update_irte - set IRTE for Posted-Interrupts * * @kvm: kvm diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 0bdc41391c5b..7f7b2326caf5 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -95,5 +95,6 @@ void __init pi_init_cpu(int cpu); bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu); int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); +void vmx_pi_start_assignment(struct kvm *kvm); #endif /* __KVM_X86_VMX_POSTED_INTR_H */ diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 1472c6c376f7..de3b04d4b587 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -164,4 +164,12 @@ static inline int vmcs_field_readonly(unsigned long field) return (((field >> 10) & 0x3) == 1); } +#define VMCS_FIELD_INDEX_SHIFT (1) +#define VMCS_FIELD_INDEX_MASK GENMASK(9, 1) + +static inline unsigned int vmcs_field_index(unsigned long field) +{ + return (field & VMCS_FIELD_INDEX_MASK) >> VMCS_FIELD_INDEX_SHIFT; +} + #endif /* __KVM_X86_VMX_VMCS_H */ diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index 034adb6404dc..d9f5d7c56ae3 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -37,6 +37,7 @@ const unsigned short vmcs_field_to_offset_table[] = { FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr), FIELD64(PML_ADDRESS, pml_address), FIELD64(TSC_OFFSET, tsc_offset), + FIELD64(TSC_MULTIPLIER, tsc_multiplier), FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr), FIELD64(APIC_ACCESS_ADDR, apic_access_addr), FIELD64(POSTED_INTR_DESC_ADDR, posted_intr_desc_addr), diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 13494956d0e9..5e0e1b39f495 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -70,7 +70,8 @@ struct __packed vmcs12 { u64 eptp_list_address; u64 pml_address; u64 encls_exiting_bitmap; - u64 padding64[2]; /* room for future expansion */ + u64 tsc_multiplier; + u64 padding64[1]; /* room for future expansion */ /* * To allow migration of L1 (complete with its L2 guests) between * machines of different natural widths (32 or 64 bit), we cannot have @@ -205,12 +206,6 @@ struct __packed vmcs12 { #define VMCS12_SIZE KVM_STATE_NESTED_VMX_VMCS_SIZE /* - * VMCS12_MAX_FIELD_INDEX is the highest index value used in any - * supported VMCS12 field encoding. - */ -#define VMCS12_MAX_FIELD_INDEX 0x17 - -/* * For save/restore compatibility, the vmcs12 field offsets must not change. */ #define CHECK_OFFSET(field, loc) \ @@ -258,6 +253,7 @@ static inline void vmx_check_vmcs12_offsets(void) CHECK_OFFSET(eptp_list_address, 304); CHECK_OFFSET(pml_address, 312); CHECK_OFFSET(encls_exiting_bitmap, 320); + CHECK_OFFSET(tsc_multiplier, 328); CHECK_OFFSET(cr0_guest_host_mask, 344); CHECK_OFFSET(cr4_guest_host_mask, 352); CHECK_OFFSET(cr0_read_shadow, 360); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4bceb5ca3a89..ab6f682645d7 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -52,6 +52,7 @@ #include "cpuid.h" #include "evmcs.h" #include "hyperv.h" +#include "kvm_onhyperv.h" #include "irq.h" #include "kvm_cache_regs.h" #include "lapic.h" @@ -101,7 +102,6 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -bool __read_mostly enable_apicv = 1; module_param(enable_apicv, bool, S_IRUGO); /* @@ -459,86 +459,6 @@ static unsigned long host_idt_base; static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); -static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush, - void *data) -{ - struct kvm_tlb_range *range = data; - - return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn, - range->pages); -} - -static inline int hv_remote_flush_root_ept(hpa_t root_ept, - struct kvm_tlb_range *range) -{ - if (range) - return hyperv_flush_guest_mapping_range(root_ept, - kvm_fill_hv_flush_list_func, (void *)range); - else - return hyperv_flush_guest_mapping(root_ept); -} - -static int hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_tlb_range *range) -{ - struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); - struct kvm_vcpu *vcpu; - int ret = 0, i, nr_unique_valid_roots; - hpa_t root; - - spin_lock(&kvm_vmx->hv_root_ept_lock); - - if (!VALID_PAGE(kvm_vmx->hv_root_ept)) { - nr_unique_valid_roots = 0; - - /* - * Flush all valid roots, and see if all vCPUs have converged - * on a common root, in which case future flushes can skip the - * loop and flush the common root. - */ - kvm_for_each_vcpu(i, vcpu, kvm) { - root = to_vmx(vcpu)->hv_root_ept; - if (!VALID_PAGE(root) || root == kvm_vmx->hv_root_ept) - continue; - - /* - * Set the tracked root to the first valid root. Keep - * this root for the entirety of the loop even if more - * roots are encountered as a low effort optimization - * to avoid flushing the same (first) root again. - */ - if (++nr_unique_valid_roots == 1) - kvm_vmx->hv_root_ept = root; - - if (!ret) - ret = hv_remote_flush_root_ept(root, range); - - /* - * Stop processing roots if a failure occurred and - * multiple valid roots have already been detected. - */ - if (ret && nr_unique_valid_roots > 1) - break; - } - - /* - * The optimized flush of a single root can't be used if there - * are multiple valid roots (obviously). - */ - if (nr_unique_valid_roots > 1) - kvm_vmx->hv_root_ept = INVALID_PAGE; - } else { - ret = hv_remote_flush_root_ept(kvm_vmx->hv_root_ept, range); - } - - spin_unlock(&kvm_vmx->hv_root_ept_lock); - return ret; -} -static int hv_remote_flush_tlb(struct kvm *kvm) -{ - return hv_remote_flush_tlb_with_range(kvm, NULL); -} - static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; @@ -566,21 +486,6 @@ static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) #endif /* IS_ENABLED(CONFIG_HYPERV) */ -static void hv_track_root_ept(struct kvm_vcpu *vcpu, hpa_t root_ept) -{ -#if IS_ENABLED(CONFIG_HYPERV) - struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm); - - if (kvm_x86_ops.tlb_remote_flush == hv_remote_flush_tlb) { - spin_lock(&kvm_vmx->hv_root_ept_lock); - to_vmx(vcpu)->hv_root_ept = root_ept; - if (root_ept != kvm_vmx->hv_root_ept) - kvm_vmx->hv_root_ept = INVALID_PAGE; - spin_unlock(&kvm_vmx->hv_root_ept_lock); - } -#endif -} - /* * Comment's format: document - errata name - stepping - processor name. * Refer from @@ -842,16 +747,21 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; else { - /* - * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched - * between guest and host. In that case we only care about present - * faults. For vmcs02, however, PFEC_MASK and PFEC_MATCH are set in - * prepare_vmcs02_rare. - */ - bool selective_pf_trap = enable_ept && (eb & (1u << PF_VECTOR)); - int mask = selective_pf_trap ? PFERR_PRESENT_MASK : 0; + int mask = 0, match = 0; + + if (enable_ept && (eb & (1u << PF_VECTOR))) { + /* + * If EPT is enabled, #PF is currently only intercepted + * if MAXPHYADDR is smaller on the guest than on the + * host. In that case we only care about present, + * non-reserved faults. For vmcs02, however, PFEC_MASK + * and PFEC_MATCH are set in prepare_vmcs02_rare. + */ + mask = PFERR_PRESENT_MASK | PFERR_RSVD_MASK; + match = PFERR_PRESENT_MASK; + } vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, mask); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, match); } vmcs_write32(EXCEPTION_BITMAP, eb); @@ -1390,11 +1300,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, vmx->loaded_vmcs->cpu = cpu; } - - /* Setup TSC multiplier */ - if (kvm_has_tsc_control && - vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) - decache_tsc_multiplier(vmx); } /* @@ -1787,26 +1692,35 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx->guest_uret_msrs_loaded = false; } -static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u64 g_tsc_offset = 0; - /* - * We're here if L1 chose not to trap WRMSR to TSC. According - * to the spec, this should set L1's TSC; The offset that L1 - * set for L2 remains unchanged, and still needs to be added - * to the newly set TSC to get L2's TSC. - */ - if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) - g_tsc_offset = vmcs12->tsc_offset; + if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING)) + return vmcs12->tsc_offset; + + return 0; +} + +u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING) && + nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING)) + return vmcs12->tsc_multiplier; - trace_kvm_write_tsc_offset(vcpu->vcpu_id, - vcpu->arch.tsc_offset - g_tsc_offset, - offset); - vmcs_write64(TSC_OFFSET, offset + g_tsc_offset); - return offset + g_tsc_offset; + return kvm_default_tsc_scaling_ratio; +} + +static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +{ + vmcs_write64(TSC_OFFSET, offset); +} + +static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +{ + vmcs_write64(TSC_MULTIPLIER, multiplier); } /* @@ -3181,7 +3095,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, eptp = construct_eptp(vcpu, root_hpa, root_level); vmcs_write64(EPT_POINTER, eptp); - hv_track_root_ept(vcpu, root_hpa); + hv_track_root_tdp(vcpu, root_hpa); if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; @@ -4843,7 +4757,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_run *kvm_run = vcpu->run; u32 intr_info, ex_no, error_code; - unsigned long cr2, rip, dr6; + unsigned long cr2, dr6; u32 vect_info; vect_info = vmx->idt_vectoring_info; @@ -4933,8 +4847,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vmx->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); kvm_run->exit_reason = KVM_EXIT_DEBUG; - rip = kvm_rip_read(vcpu); - kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; + kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = ex_no; break; case AC_VECTOR: @@ -6248,6 +6161,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) switch (kvm_get_apic_mode(vcpu)) { case LAPIC_MODE_INVALID: WARN_ONCE(true, "Invalid local APIC state"); + break; case LAPIC_MODE_DISABLED: break; case LAPIC_MODE_XAPIC: @@ -6806,7 +6720,18 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_load_host_xsave_state(vcpu); - vmx->nested.nested_run_pending = 0; + if (is_guest_mode(vcpu)) { + /* + * Track VMLAUNCH/VMRESUME that have made past guest state + * checking. + */ + if (vmx->nested.nested_run_pending && + !vmx->exit_reason.failed_vmentry) + ++vcpu->stat.nested_run; + + vmx->nested.nested_run_pending = 0; + } + vmx->idt_vectoring_info = 0; if (unlikely(vmx->fail)) { @@ -6941,6 +6866,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; + vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; @@ -6952,9 +6878,6 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) vmx->pi_desc.nv = POSTED_INTR_VECTOR; vmx->pi_desc.sn = 1; -#if IS_ENABLED(CONFIG_HYPERV) - vmx->hv_root_ept = INVALID_PAGE; -#endif return 0; free_vmcs: @@ -6971,10 +6894,6 @@ free_vpid: static int vmx_vm_init(struct kvm *kvm) { -#if IS_ENABLED(CONFIG_HYPERV) - spin_lock_init(&to_kvm_vmx(kvm)->hv_root_ept_lock); -#endif - if (!ple_gap) kvm->arch.pause_in_guest = true; @@ -7001,7 +6920,6 @@ static int vmx_vm_init(struct kvm *kvm) break; } } - kvm_apicv_init(kvm, enable_apicv); return 0; } @@ -7453,10 +7371,10 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, delta_tsc = 0; /* Convert to host delta tsc if tsc scaling is enabled */ - if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && + if (vcpu->arch.l1_tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && delta_tsc && u64_shl_div_u64(delta_tsc, kvm_tsc_scaling_ratio_frac_bits, - vcpu->arch.tsc_scaling_ratio, &delta_tsc)) + vcpu->arch.l1_tsc_scaling_ratio, &delta_tsc)) return -ERANGE; /* @@ -7542,7 +7460,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !is_smm(vcpu); } -static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7556,7 +7474,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -7700,7 +7618,10 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .write_l1_tsc_offset = vmx_write_l1_tsc_offset, + .get_l2_tsc_offset = vmx_get_l2_tsc_offset, + .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier, + .write_tsc_offset = vmx_write_tsc_offset, + .write_tsc_multiplier = vmx_write_tsc_multiplier, .load_mmu_pgd = vmx_load_mmu_pgd, @@ -7721,6 +7642,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .nested_ops = &vmx_nested_ops, .update_pi_irte = pi_update_irte, + .start_assignment = vmx_pi_start_assignment, #ifdef CONFIG_X86_64 .set_hv_timer = vmx_set_hv_timer, @@ -7730,8 +7652,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .setup_mce = vmx_setup_mce, .smi_allowed = vmx_smi_allowed, - .pre_enter_smm = vmx_pre_enter_smm, - .pre_leave_smm = vmx_pre_leave_smm, + .enter_smm = vmx_enter_smm, + .leave_smm = vmx_leave_smm, .enable_smi_window = vmx_enable_smi_window, .can_emulate_instruction = vmx_can_emulate_instruction, @@ -7806,6 +7728,12 @@ static __init int hardware_setup(void) !cpu_has_vmx_invept_global()) enable_ept = 0; + /* NX support is required for shadow paging. */ + if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { + pr_err_ratelimited("kvm: NX (Execute Disable) not supported\n"); + return -EOPNOTSUPP; + } + if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 16e4e457ba23..5740f8e2aa23 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -322,8 +322,6 @@ struct vcpu_vmx { /* apic deadline value in host tsc */ u64 hv_deadline_tsc; - u64 current_tsc_ratio; - unsigned long host_debugctlmsr; /* @@ -336,10 +334,6 @@ struct vcpu_vmx { /* SGX Launch Control public key hash */ u64 msr_ia32_sgxlepubkeyhash[4]; -#if IS_ENABLED(CONFIG_HYPERV) - u64 hv_root_ept; -#endif - struct pt_desc pt_desc; struct lbr_desc lbr_desc; @@ -357,11 +351,6 @@ struct kvm_vmx { unsigned int tss_addr; bool ept_identity_pagetable_done; gpa_t ept_identity_map_addr; - -#if IS_ENABLED(CONFIG_HYPERV) - hpa_t hv_root_ept; - spinlock_t hv_root_ept_lock; -#endif }; bool nested_vmx_allowed(struct kvm_vcpu *vcpu); @@ -404,6 +393,9 @@ void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type); void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type); +u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); +u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); + static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool value) { @@ -529,12 +521,6 @@ static inline struct vmcs *alloc_vmcs(bool shadow) GFP_KERNEL_ACCOUNT); } -static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx) -{ - vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio; - vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); -} - static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) { return vmx->secondary_exec_control & diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bbc4e04e67ad..38c003b60339 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -58,6 +58,7 @@ #include <linux/sched/isolation.h> #include <linux/mem_encrypt.h> #include <linux/entry-kvm.h> +#include <linux/suspend.h> #include <trace/events/kvm.h> @@ -102,6 +103,8 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; +#define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) + #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -113,6 +116,9 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); + struct kvm_x86_ops kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -209,6 +215,9 @@ EXPORT_SYMBOL_GPL(host_efer); bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); +bool __read_mostly enable_apicv = true; +EXPORT_SYMBOL_GPL(enable_apicv); + u64 __read_mostly host_xss; EXPORT_SYMBOL_GPL(host_xss); u64 __read_mostly supported_xss; @@ -246,6 +255,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("nested_run", nested_run), VCPU_STAT("directed_yield_attempted", directed_yield_attempted), VCPU_STAT("directed_yield_successful", directed_yield_successful), + VCPU_STAT("guest_mode", guest_mode), VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), VM_STAT("mmu_pte_write", mmu_pte_write), VM_STAT("mmu_pde_zapped", mmu_pde_zapped), @@ -778,13 +788,6 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); -static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, - void *data, int offset, int len, u32 access) -{ - return kvm_read_guest_page_mmu(vcpu, vcpu->arch.walk_mmu, gfn, - data, offset, len, access); -} - static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); @@ -819,6 +822,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + vcpu->arch.pdptrs_from_userspace = false; out: @@ -826,30 +830,6 @@ out: } EXPORT_SYMBOL_GPL(load_pdptrs); -bool pdptrs_changed(struct kvm_vcpu *vcpu) -{ - u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; - int offset; - gfn_t gfn; - int r; - - if (!is_pae_paging(vcpu)) - return false; - - if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR)) - return true; - - gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT; - offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1); - r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), - PFERR_USER_MASK | PFERR_WRITE_MASK); - if (r < 0) - return true; - - return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; -} -EXPORT_SYMBOL_GPL(pdptrs_changed); - void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) { unsigned long update_bits = X86_CR0_PG | X86_CR0_WP; @@ -1084,25 +1064,46 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) } EXPORT_SYMBOL_GPL(kvm_set_cr4); +static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) +{ + struct kvm_mmu *mmu = vcpu->arch.mmu; + unsigned long roots_to_free = 0; + int i; + + /* + * If neither the current CR3 nor any of the prev_roots use the given + * PCID, then nothing needs to be done here because a resync will + * happen anyway before switching to any other CR3. + */ + if (kvm_get_active_pcid(vcpu) == pcid) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + } + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if (kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd) == pcid) + roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); + + kvm_mmu_free_roots(vcpu, mmu, roots_to_free); +} + int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { bool skip_tlb_flush = false; + unsigned long pcid = 0; #ifdef CONFIG_X86_64 bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); if (pcid_enabled) { skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH; cr3 &= ~X86_CR3_PCID_NOFLUSH; + pcid = cr3 & X86_CR3_PCID_MASK; } #endif - if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { - if (!skip_tlb_flush) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } - return 0; - } + /* PDPTRs are always reloaded for PAE paging. */ + if (cr3 == kvm_read_cr3(vcpu) && !is_pae_paging(vcpu)) + goto handle_tlb_flush; /* * Do not condition the GPA check on long mode, this helper is used to @@ -1115,10 +1116,23 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) return 1; - kvm_mmu_new_pgd(vcpu, cr3, skip_tlb_flush, skip_tlb_flush); + if (cr3 != kvm_read_cr3(vcpu)) + kvm_mmu_new_pgd(vcpu, cr3); + vcpu->arch.cr3 = cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); +handle_tlb_flush: + /* + * A load of CR3 that flushes the TLB flushes only the current PCID, + * even if PCID is disabled, in which case PCID=0 is flushed. It's a + * moot point in the end because _disabling_ PCID will flush all PCIDs, + * and it's impossible to use a non-zero PCID when PCID is disabled, + * i.e. only PCID=0 can be relevant. + */ + if (!skip_tlb_flush) + kvm_invalidate_pcid(vcpu, pcid); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr3); @@ -2179,13 +2193,15 @@ static u32 adjust_tsc_khz(u32 khz, s32 ppm) return v; } +static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier); + static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) { u64 ratio; /* Guest TSC same frequency as host TSC? */ if (!scale) { - vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio); return 0; } @@ -2211,7 +2227,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) return -1; } - vcpu->arch.tsc_scaling_ratio = ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, ratio); return 0; } @@ -2223,7 +2239,7 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) /* tsc_khz can be zero if TSC calibration fails */ if (user_tsc_khz == 0) { /* set tsc_scaling_ratio to a safe value */ - vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio); return -1; } @@ -2305,10 +2321,9 @@ static inline u64 __scale_tsc(u64 ratio, u64 tsc) return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits); } -u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc, u64 ratio) { u64 _tsc = tsc; - u64 ratio = vcpu->arch.tsc_scaling_ratio; if (ratio != kvm_default_tsc_scaling_ratio) _tsc = __scale_tsc(ratio, tsc); @@ -2317,25 +2332,86 @@ u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) } EXPORT_SYMBOL_GPL(kvm_scale_tsc); -static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { u64 tsc; - tsc = kvm_scale_tsc(vcpu, rdtsc()); + tsc = kvm_scale_tsc(vcpu, rdtsc(), vcpu->arch.l1_tsc_scaling_ratio); return target_tsc - tsc; } u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - return vcpu->arch.l1_tsc_offset + kvm_scale_tsc(vcpu, host_tsc); + return vcpu->arch.l1_tsc_offset + + kvm_scale_tsc(vcpu, host_tsc, vcpu->arch.l1_tsc_scaling_ratio); } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); -static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) { - vcpu->arch.l1_tsc_offset = offset; - vcpu->arch.tsc_offset = static_call(kvm_x86_write_l1_tsc_offset)(vcpu, offset); + u64 nested_offset; + + if (l2_multiplier == kvm_default_tsc_scaling_ratio) + nested_offset = l1_offset; + else + nested_offset = mul_s64_u64_shr((s64) l1_offset, l2_multiplier, + kvm_tsc_scaling_ratio_frac_bits); + + nested_offset += l2_offset; + return nested_offset; +} +EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_offset); + +u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) +{ + if (l2_multiplier != kvm_default_tsc_scaling_ratio) + return mul_u64_u64_shr(l1_multiplier, l2_multiplier, + kvm_tsc_scaling_ratio_frac_bits); + + return l1_multiplier; +} +EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_multiplier); + +static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset) +{ + trace_kvm_write_tsc_offset(vcpu->vcpu_id, + vcpu->arch.l1_tsc_offset, + l1_offset); + + vcpu->arch.l1_tsc_offset = l1_offset; + + /* + * If we are here because L1 chose not to trap WRMSR to TSC then + * according to the spec this should set L1's TSC (as opposed to + * setting L1's offset for L2). + */ + if (is_guest_mode(vcpu)) + vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( + l1_offset, + static_call(kvm_x86_get_l2_tsc_offset)(vcpu), + static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); + else + vcpu->arch.tsc_offset = l1_offset; + + static_call(kvm_x86_write_tsc_offset)(vcpu, vcpu->arch.tsc_offset); +} + +static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier) +{ + vcpu->arch.l1_tsc_scaling_ratio = l1_multiplier; + + /* Userspace is changing the multiplier while L2 is active */ + if (is_guest_mode(vcpu)) + vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( + l1_multiplier, + static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); + else + vcpu->arch.tsc_scaling_ratio = l1_multiplier; + + if (kvm_has_tsc_control) + static_call(kvm_x86_write_tsc_multiplier)( + vcpu, vcpu->arch.tsc_scaling_ratio); } static inline bool kvm_check_tsc_unstable(void) @@ -2361,7 +2437,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) bool synchronizing = false; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); - offset = kvm_compute_tsc_offset(vcpu, data); + offset = kvm_compute_l1_tsc_offset(vcpu, data); ns = get_kvmclock_base_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; @@ -2400,7 +2476,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) } else { u64 delta = nsec_to_cycles(vcpu, elapsed); data += delta; - offset = kvm_compute_tsc_offset(vcpu, data); + offset = kvm_compute_l1_tsc_offset(vcpu, data); } matched = true; already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation); @@ -2459,9 +2535,10 @@ static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { - if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) + if (vcpu->arch.l1_tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) WARN_ON(adjustment < 0); - adjustment = kvm_scale_tsc(vcpu, (u64) adjustment); + adjustment = kvm_scale_tsc(vcpu, (u64) adjustment, + vcpu->arch.l1_tsc_scaling_ratio); adjust_tsc_offset_guest(vcpu, adjustment); } @@ -2844,7 +2921,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ if (kvm_has_tsc_control) - tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz); + tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz, + v->arch.l1_tsc_scaling_ratio); if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL, @@ -3072,6 +3150,19 @@ static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; + + if (!tdp_enabled) { + /* + * A TLB flush on behalf of the guest is equivalent to + * INVPCID(all), toggling CR4.PGE, etc., which requires + * a forced sync of the shadow page tables. Unload the + * entire MMU here and the subsequent load will sync the + * shadow page tables, and also flush the TLB. + */ + kvm_mmu_unload(vcpu); + return; + } + static_call(kvm_x86_tlb_flush_guest)(vcpu); } @@ -3101,10 +3192,14 @@ static void record_steal_time(struct kvm_vcpu *vcpu) * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { + u8 st_preempted = xchg(&st->preempted, 0); + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, - st->preempted & KVM_VCPU_FLUSH_TLB); - if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) + st_preempted & KVM_VCPU_FLUSH_TLB); + if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + } else { + st->preempted = 0; } vcpu->arch.st.preempted = 0; @@ -3233,7 +3328,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (msr_info->host_initiated) { kvm_synchronize_tsc(vcpu, data); } else { - u64 adj = kvm_compute_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; + u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); vcpu->arch.ia32_tsc_adjust_msr += adj; } @@ -3535,10 +3630,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * return L1's TSC value to ensure backwards-compatible * behavior for migration. */ - u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset : - vcpu->arch.tsc_offset; + u64 offset, ratio; - msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset; + if (msr_info->host_initiated) { + offset = vcpu->arch.l1_tsc_offset; + ratio = vcpu->arch.l1_tsc_scaling_ratio; + } else { + offset = vcpu->arch.tsc_offset; + ratio = vcpu->arch.tsc_scaling_ratio; + } + + msr_info->data = kvm_scale_tsc(vcpu, rdtsc(), ratio) + offset; break; } case MSR_MTRRcap: @@ -3862,6 +3964,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: case KVM_CAP_HYPERV_CPUID: + case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: @@ -3892,8 +3995,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SGX_ATTRIBUTE: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + case KVM_CAP_SREGS2: r = 1; break; + case KVM_CAP_EXIT_HYPERCALL: + r = KVM_EXIT_HYPERCALL_VALID_MASK; + break; case KVM_CAP_SET_GUEST_DEBUG2: return KVM_GUESTDBG_VALID_MASK; #ifdef CONFIG_KVM_XEN @@ -4121,7 +4228,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mark_tsc_unstable("KVM discovered backwards TSC"); if (kvm_check_tsc_unstable()) { - u64 offset = kvm_compute_tsc_offset(vcpu, + u64 offset = kvm_compute_l1_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_vcpu_write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; @@ -4440,7 +4547,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, memset(&events->reserved, 0, sizeof(events->reserved)); } -static void kvm_smm_changed(struct kvm_vcpu *vcpu); +static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm); static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) @@ -4500,13 +4607,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { - if (events->smi.smm) - vcpu->arch.hflags |= HF_SMM_MASK; - else - vcpu->arch.hflags &= ~HF_SMM_MASK; - kvm_smm_changed(vcpu); - } + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) + kvm_smm_changed(vcpu, events->smi.smm); vcpu->arch.smi_pending = events->smi.pending; @@ -4790,6 +4892,9 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return static_call(kvm_x86_enable_direct_tlbflush)(vcpu); + case KVM_CAP_HYPERV_ENFORCE_CPUID: + return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); + case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; if (vcpu->arch.pv_cpuid.enforce) @@ -4808,6 +4913,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; union { + struct kvm_sregs2 *sregs2; struct kvm_lapic_state *lapic; struct kvm_xsave *xsave; struct kvm_xcrs *xcrs; @@ -5180,6 +5286,28 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } #endif + case KVM_GET_SREGS2: { + u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL); + r = -ENOMEM; + if (!u.sregs2) + goto out; + __get_sregs2(vcpu, u.sregs2); + r = -EFAULT; + if (copy_to_user(argp, u.sregs2, sizeof(struct kvm_sregs2))) + goto out; + r = 0; + break; + } + case KVM_SET_SREGS2: { + u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2)); + if (IS_ERR(u.sregs2)) { + r = PTR_ERR(u.sregs2); + u.sregs2 = NULL; + goto out; + } + r = __set_sregs2(vcpu, u.sregs2); + break; + } default: r = -EINVAL; } @@ -5499,6 +5627,14 @@ split_irqchip_unlock: if (kvm_x86_ops.vm_copy_enc_context_from) r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); return r; + case KVM_CAP_EXIT_HYPERCALL: + if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { + r = -EINVAL; + break; + } + kvm->arch.hypercall_exit_enabled = cap->args[0]; + r = 0; + break; default: r = -EINVAL; break; @@ -5613,6 +5749,41 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) return 0; } +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +static int kvm_arch_suspend_notifier(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i, ret = 0; + + mutex_lock(&kvm->lock); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!vcpu->arch.pv_time_enabled) + continue; + + ret = kvm_set_guest_paused(vcpu); + if (ret) { + kvm_err("Failed to pause guest VCPU%d: %d\n", + vcpu->vcpu_id, ret); + break; + } + } + mutex_unlock(&kvm->lock); + + return ret ? NOTIFY_BAD : NOTIFY_DONE; +} + +int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state) +{ + switch (state) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: + return kvm_arch_suspend_notifier(kvm); + } + + return NOTIFY_DONE; +} +#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -7087,20 +7258,22 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) return emul_to_vcpu(ctxt)->arch.hflags; } -static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) +static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt) { - emul_to_vcpu(ctxt)->arch.hflags = emul_flags; + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + kvm_smm_changed(vcpu, false); } -static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, +static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt, const char *smstate) { - return static_call(kvm_x86_pre_leave_smm)(emul_to_vcpu(ctxt), smstate); + return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate); } -static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) +static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) { - kvm_smm_changed(emul_to_vcpu(ctxt)); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, emul_to_vcpu(ctxt)); } static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) @@ -7149,9 +7322,9 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_fxsr = emulator_guest_has_fxsr, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, - .set_hflags = emulator_set_hflags, - .pre_leave_smm = emulator_pre_leave_smm, - .post_leave_smm = emulator_post_leave_smm, + .exiting_smm = emulator_exiting_smm, + .leave_smm = emulator_leave_smm, + .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, }; @@ -7226,6 +7399,11 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->exception.vector = -1; + ctxt->perm_ok = false; + init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } @@ -7407,11 +7585,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); -static void kvm_smm_changed(struct kvm_vcpu *vcpu) +static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) { - if (!(vcpu->arch.hflags & HF_SMM_MASK)) { - /* This is a good place to trace that we are exiting SMM. */ - trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false); + trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); + + if (entering_smm) { + vcpu->arch.hflags |= HF_SMM_MASK; + } else { + vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK); /* Process a latched INIT or SMI, if any. */ kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -7561,14 +7742,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, kvm_vcpu_check_breakpoint(vcpu, &r)) return r; - ctxt->interruptibility = 0; - ctxt->have_exception = false; - ctxt->exception.vector = -1; - ctxt->perm_ok = false; - - ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; - - r = x86_decode_insn(ctxt, insn, insn_len); + r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; @@ -8243,6 +8417,7 @@ void kvm_arch_exit(void) kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); free_percpu(user_return_msrs); + kmem_cache_destroy(x86_emulator_cache); kmem_cache_destroy(x86_fpu_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); @@ -8342,16 +8517,15 @@ bool kvm_apicv_activated(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_apicv_activated); -void kvm_apicv_init(struct kvm *kvm, bool enable) +static void kvm_apicv_init(struct kvm *kvm) { - if (enable) + if (enable_apicv) clear_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); else set_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); } -EXPORT_SYMBOL_GPL(kvm_apicv_init); static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) { @@ -8360,6 +8534,9 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) vcpu->stat.directed_yield_attempted++; + if (single_task_running()) + goto no_yield; + rcu_read_lock(); map = rcu_dereference(vcpu->kvm->arch.apic_map); @@ -8384,6 +8561,17 @@ no_yield: return; } +static int complete_hypercall_exit(struct kvm_vcpu *vcpu) +{ + u64 ret = vcpu->run->hypercall.ret; + + if (!is_64_bit_mode(vcpu)) + ret = (u32)ret; + kvm_rax_write(vcpu, ret); + ++vcpu->stat.hypercalls; + return kvm_skip_emulated_instruction(vcpu); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; @@ -8449,6 +8637,28 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) kvm_sched_yield(vcpu, a0); ret = 0; break; + case KVM_HC_MAP_GPA_RANGE: { + u64 gpa = a0, npages = a1, attrs = a2; + + ret = -KVM_ENOSYS; + if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) + break; + + if (!PAGE_ALIGNED(gpa) || !npages || + gpa_to_gfn(gpa) + npages <= gpa_to_gfn(gpa)) { + ret = -KVM_EINVAL; + break; + } + + vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; + vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + vcpu->run->hypercall.args[0] = gpa; + vcpu->run->hypercall.args[1] = npages; + vcpu->run->hypercall.args[2] = attrs; + vcpu->run->hypercall.longmode = op_64_bit; + vcpu->arch.complete_userspace_io = complete_hypercall_exit; + return 0; + } default: ret = -KVM_ENOSYS; break; @@ -8532,9 +8742,6 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) int kvm_check_nested_events(struct kvm_vcpu *vcpu) { - if (WARN_ON_ONCE(!is_guest_mode(vcpu))) - return -EIO; - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; @@ -8550,7 +8757,7 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu) static_call(kvm_x86_queue_exception)(vcpu); } -static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) +static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) { int r; bool can_inject = true; @@ -8597,7 +8804,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (is_guest_mode(vcpu)) { r = kvm_check_nested_events(vcpu); if (r < 0) - goto busy; + goto out; } /* try to inject new event if pending */ @@ -8639,7 +8846,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (vcpu->arch.smi_pending) { r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY; if (r < 0) - goto busy; + goto out; if (r) { vcpu->arch.smi_pending = false; ++vcpu->arch.smi_count; @@ -8652,7 +8859,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (vcpu->arch.nmi_pending) { r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY; if (r < 0) - goto busy; + goto out; if (r) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; @@ -8667,7 +8874,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit if (kvm_cpu_has_injectable_intr(vcpu)) { r = can_inject ? static_call(kvm_x86_interrupt_allowed)(vcpu, true) : -EBUSY; if (r < 0) - goto busy; + goto out; if (r) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); static_call(kvm_x86_set_irq)(vcpu); @@ -8683,11 +8890,14 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit *req_immediate_exit = true; WARN_ON(vcpu->arch.exception.pending); - return; + return 0; -busy: - *req_immediate_exit = true; - return; +out: + if (r == -EBUSY) { + *req_immediate_exit = true; + r = 0; + } + return r; } static void process_nmi(struct kvm_vcpu *vcpu) @@ -8869,7 +9079,6 @@ static void enter_smm(struct kvm_vcpu *vcpu) char buf[512]; u32 cr0; - trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); memset(buf, 0, 512); #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) @@ -8879,13 +9088,13 @@ static void enter_smm(struct kvm_vcpu *vcpu) enter_smm_save_state_32(vcpu, buf); /* - * Give pre_enter_smm() a chance to make ISA-specific changes to the - * vCPU state (e.g. leave guest mode) after we've saved the state into - * the SMM state-save area. + * Give enter_smm() a chance to make ISA-specific changes to the vCPU + * state (e.g. leave guest mode) after we've saved the state into the + * SMM state-save area. */ - static_call(kvm_x86_pre_enter_smm)(vcpu, buf); + static_call(kvm_x86_enter_smm)(vcpu, buf); - vcpu->arch.hflags |= HF_SMM_MASK; + kvm_smm_changed(vcpu, true); kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); if (static_call(kvm_x86_get_nmi_mask)(vcpu)) @@ -8974,6 +9183,15 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); kvm_apic_update_apicv(vcpu); static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); + + /* + * When APICv gets disabled, we may still have injected interrupts + * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was + * still active when the interrupt got accepted. Make sure + * inject_pending_event() is called to check for that. + */ + if (!vcpu->arch.apicv_active) + kvm_make_request(KVM_REQ_EVENT, vcpu); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -9149,7 +9367,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); - if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu)) + if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { @@ -9242,13 +9460,21 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || kvm_xen_has_interrupt(vcpu)) { ++vcpu->stat.req_event; - kvm_apic_accept_events(vcpu); + r = kvm_apic_accept_events(vcpu); + if (r < 0) { + r = 0; + goto out; + } if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { r = 1; goto out; } - inject_pending_event(vcpu, &req_immediate_exit); + r = inject_pending_event(vcpu, &req_immediate_exit); + if (r < 0) { + r = 0; + goto out; + } if (req_int_win) static_call(kvm_x86_enable_irq_window)(vcpu); @@ -9450,7 +9676,8 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) return 1; } - kvm_apic_accept_events(vcpu); + if (kvm_apic_accept_events(vcpu) < 0) + return 0; switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: case KVM_MP_STATE_AP_RESET_HOLD: @@ -9496,7 +9723,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (r <= 0) break; - kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_clear_request(KVM_REQ_UNBLOCK, vcpu); if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); @@ -9674,7 +9901,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) goto out; } kvm_vcpu_block(vcpu); - kvm_apic_accept_events(vcpu); + if (kvm_apic_accept_events(vcpu) < 0) { + r = 0; + goto out; + } kvm_clear_request(KVM_REQ_UNHALT, vcpu); r = -EAGAIN; if (signal_pending(current)) { @@ -9823,7 +10053,7 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) } EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); -static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct desc_ptr dt; @@ -9856,14 +10086,36 @@ skip_protected_regs: sregs->cr8 = kvm_get_cr8(vcpu); sregs->efer = vcpu->arch.efer; sregs->apic_base = kvm_get_apic_base(vcpu); +} - memset(sregs->interrupt_bitmap, 0, sizeof(sregs->interrupt_bitmap)); +static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + __get_sregs_common(vcpu, sregs); + + if (vcpu->arch.guest_state_protected) + return; if (vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft) set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); } +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int i; + + __get_sregs_common(vcpu, (struct kvm_sregs *)sregs2); + + if (vcpu->arch.guest_state_protected) + return; + + if (is_pae_paging(vcpu)) { + for (i = 0 ; i < 4 ; i++) + sregs2->pdptrs[i] = kvm_pdptr_read(vcpu, i); + sregs2->flags |= KVM_SREGS2_FLAGS_PDPTRS_VALID; + } +} + int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { @@ -9876,11 +10128,17 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + int r; + vcpu_load(vcpu); if (kvm_mpx_supported()) kvm_load_guest_fpu(vcpu); - kvm_apic_accept_events(vcpu); + r = kvm_apic_accept_events(vcpu); + if (r < 0) + goto out; + r = 0; + if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && vcpu->arch.pv.pv_unhalted) @@ -9888,10 +10146,11 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; +out: if (kvm_mpx_supported()) kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); - return 0; + return r; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, @@ -9975,24 +10234,23 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return kvm_is_valid_cr4(vcpu, sregs->cr4); } -static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, + int *mmu_reset_needed, bool update_pdptrs) { struct msr_data apic_base_msr; - int mmu_reset_needed = 0; - int pending_vec, max_bits, idx; + int idx; struct desc_ptr dt; - int ret = -EINVAL; if (!kvm_is_valid_sregs(vcpu, sregs)) - goto out; + return -EINVAL; apic_base_msr.data = sregs->apic_base; apic_base_msr.host_initiated = true; if (kvm_set_apic_base(vcpu, &apic_base_msr)) - goto out; + return -EINVAL; if (vcpu->arch.guest_state_protected) - goto skip_protected_regs; + return 0; dt.size = sregs->idt.limit; dt.address = sregs->idt.base; @@ -10002,31 +10260,30 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) static_call(kvm_x86_set_gdt)(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; - mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; + *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); - mmu_reset_needed |= vcpu->arch.efer != sregs->efer; + *mmu_reset_needed |= vcpu->arch.efer != sregs->efer; static_call(kvm_x86_set_efer)(vcpu, sregs->efer); - mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; + *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; - mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; + *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (is_pae_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); - mmu_reset_needed = 1; + if (update_pdptrs) { + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (is_pae_paging(vcpu)) { + load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + *mmu_reset_needed = 1; + } + srcu_read_unlock(&vcpu->kvm->srcu, idx); } - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (mmu_reset_needed) - kvm_mmu_reset_context(vcpu); kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); @@ -10046,20 +10303,63 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) !is_protmode(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; -skip_protected_regs: + return 0; +} + +static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + int pending_vec, max_bits; + int mmu_reset_needed = 0; + int ret = __set_sregs_common(vcpu, sregs, &mmu_reset_needed, true); + + if (ret) + return ret; + + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( (const unsigned long *)sregs->interrupt_bitmap, max_bits); + if (pending_vec < max_bits) { kvm_queue_interrupt(vcpu, pending_vec, false); pr_debug("Set back pending irq %d\n", pending_vec); + kvm_make_request(KVM_REQ_EVENT, vcpu); } + return 0; +} - kvm_make_request(KVM_REQ_EVENT, vcpu); +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int mmu_reset_needed = 0; + bool valid_pdptrs = sregs2->flags & KVM_SREGS2_FLAGS_PDPTRS_VALID; + bool pae = (sregs2->cr0 & X86_CR0_PG) && (sregs2->cr4 & X86_CR4_PAE) && + !(sregs2->efer & EFER_LMA); + int i, ret; - ret = 0; -out: - return ret; + if (sregs2->flags & ~KVM_SREGS2_FLAGS_PDPTRS_VALID) + return -EINVAL; + + if (valid_pdptrs && (!pae || vcpu->arch.guest_state_protected)) + return -EINVAL; + + ret = __set_sregs_common(vcpu, (struct kvm_sregs *)sregs2, + &mmu_reset_needed, !valid_pdptrs); + if (ret) + return ret; + + if (valid_pdptrs) { + for (i = 0; i < 4 ; i++) + kvm_pdptr_write(vcpu, i, sregs2->pdptrs[i]); + + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + mmu_reset_needed = 1; + vcpu->arch.pdptrs_from_userspace = true; + } + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, @@ -10115,8 +10415,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, kvm_update_dr7(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + - get_segment_base(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu); /* * Trigger an rflags update that will inject or remove the trace @@ -10289,8 +10588,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) else vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - kvm_set_tsc_khz(vcpu, max_tsc_khz); - r = kvm_mmu_create(vcpu); if (r < 0) return r; @@ -10350,6 +10647,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.pending_external_vector = -1; vcpu->arch.preempted_in_kernel = false; +#if IS_ENABLED(CONFIG_HYPERV) + vcpu->arch.hv_root_tdp = INVALID_PAGE; +#endif + r = static_call(kvm_x86_vcpu_create)(vcpu); if (r) goto free_guest_fpu; @@ -10358,8 +10659,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); + kvm_set_tsc_khz(vcpu, max_tsc_khz); kvm_vcpu_reset(vcpu, false); - kvm_init_mmu(vcpu, false); + kvm_init_mmu(vcpu); vcpu_put(vcpu); return 0; @@ -10618,6 +10920,9 @@ int kvm_arch_hardware_setup(void *opaque) int r; rdmsrl_safe(MSR_EFER, &host_efer); + if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) && + !(host_efer & EFER_NX))) + return -EIO; if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); @@ -10733,9 +11038,15 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.guest_can_read_msr_platform_info = true; +#if IS_ENABLED(CONFIG_HYPERV) + spin_lock_init(&kvm->arch.hv_root_tdp_lock); + kvm->arch.hv_root_tdp = INVALID_PAGE; +#endif + INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); + kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); @@ -10896,17 +11207,23 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_hv_destroy_vm(kvm); } -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) +static void memslot_rmap_free(struct kvm_memory_slot *slot) { int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { kvfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; + } +} - if (i == 0) - continue; +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + int i; + + memslot_rmap_free(slot); + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } @@ -10914,11 +11231,79 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) kvm_page_track_free_memslot(slot); } -static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, - unsigned long npages) +static int memslot_rmap_alloc(struct kvm_memory_slot *slot, + unsigned long npages) { + const int sz = sizeof(*slot->arch.rmap[0]); int i; + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + int level = i + 1; + int lpages = gfn_to_index(slot->base_gfn + npages - 1, + slot->base_gfn, level) + 1; + + WARN_ON(slot->arch.rmap[i]); + + slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); + if (!slot->arch.rmap[i]) { + memslot_rmap_free(slot); + return -ENOMEM; + } + } + + return 0; +} + +int alloc_all_memslots_rmaps(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; + int r, i; + + /* + * Check if memslots alreday have rmaps early before acquiring + * the slots_arch_lock below. + */ + if (kvm_memslots_have_rmaps(kvm)) + return 0; + + mutex_lock(&kvm->slots_arch_lock); + + /* + * Read memslots_have_rmaps again, under the slots arch lock, + * before allocating the rmaps + */ + if (kvm_memslots_have_rmaps(kvm)) { + mutex_unlock(&kvm->slots_arch_lock); + return 0; + } + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(slot, slots) { + r = memslot_rmap_alloc(slot, slot->npages); + if (r) { + mutex_unlock(&kvm->slots_arch_lock); + return r; + } + } + } + + /* + * Ensure that memslots_have_rmaps becomes true strictly after + * all the rmap pointers are set. + */ + smp_store_release(&kvm->arch.memslots_have_rmaps, true); + mutex_unlock(&kvm->slots_arch_lock); + return 0; +} + +static int kvm_alloc_memslot_metadata(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned long npages) +{ + int i, r; + /* * Clear out the previous array pointers for the KVM_MR_MOVE case. The * old arrays will be freed by __kvm_set_memory_region() if installing @@ -10926,7 +11311,13 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, */ memset(&slot->arch, 0, sizeof(slot->arch)); - for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + if (kvm_memslots_have_rmaps(kvm)) { + r = memslot_rmap_alloc(slot, npages); + if (r) + return r; + } + + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; int lpages; @@ -10935,14 +11326,6 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, lpages = gfn_to_index(slot->base_gfn + npages - 1, slot->base_gfn, level) + 1; - slot->arch.rmap[i] = - kvcalloc(lpages, sizeof(*slot->arch.rmap[i]), - GFP_KERNEL_ACCOUNT); - if (!slot->arch.rmap[i]) - goto out_free; - if (i == 0) - continue; - linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; @@ -10972,12 +11355,9 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, return 0; out_free: - for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.rmap[i]); - slot->arch.rmap[i] = NULL; - if (i == 0) - continue; + memslot_rmap_free(slot); + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } @@ -11006,7 +11386,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, enum kvm_mr_change change) { if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) - return kvm_alloc_memslot_metadata(memslot, + return kvm_alloc_memslot_metadata(kvm, memslot, mem->memory_size >> PAGE_SHIFT); return 0; } @@ -11082,36 +11462,19 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, */ kvm_mmu_zap_collapsible_sptes(kvm, new); } else { - /* By default, write-protect everything to log writes. */ - int level = PG_LEVEL_4K; + /* + * Initially-all-set does not require write protecting any page, + * because they're all assumed to be dirty. + */ + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + return; if (kvm_x86_ops.cpu_dirty_log_size) { - /* - * Clear all dirty bits, unless pages are treated as - * dirty from the get-go. - */ - if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) - kvm_mmu_slot_leaf_clear_dirty(kvm, new); - - /* - * Write-protect large pages on write so that dirty - * logging happens at 4k granularity. No need to - * write-protect small SPTEs since write accesses are - * logged by the CPU via dirty bits. - */ - level = PG_LEVEL_2M; - } else if (kvm_dirty_log_manual_protect_and_init_set(kvm)) { - /* - * If we're with initial-all-set, we don't need - * to write protect any small page because - * they're reported as dirty already. However - * we still need to write-protect huge pages - * so that the page split can happen lazily on - * the first write to the huge page. - */ - level = PG_LEVEL_2M; + kvm_mmu_slot_leaf_clear_dirty(kvm, new); + kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M); + } else { + kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K); } - kvm_mmu_slot_remove_write_access(kvm, new, level); } } @@ -11499,7 +11862,8 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) void kvm_arch_start_assignment(struct kvm *kvm) { - atomic_inc(&kvm->arch.assigned_device_count); + if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) + static_call_cond(kvm_x86_start_assignment)(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); @@ -11679,8 +12043,6 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) { bool pcid_enabled; struct x86_exception e; - unsigned i; - unsigned long roots_to_free = 0; struct { u64 pcid; u64 gla; @@ -11714,23 +12076,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) return 1; } - if (kvm_get_active_pcid(vcpu) == operand.pcid) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } - - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].pgd) - == operand.pcid) - roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); - - kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); - /* - * If neither the current cr3 nor any of the prev_roots use the - * given PCID, then nothing needs to be done here because a - * resync will happen anyway before switching to any other CR3. - */ - + kvm_invalidate_pcid(vcpu, operand.pcid); return kvm_skip_emulated_instruction(vcpu); case INVPCID_TYPE_ALL_NON_GLOBAL: @@ -11743,7 +12089,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: - kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return kvm_skip_emulated_instruction(vcpu); default: diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index 515c3fb06ab3..56348a541c50 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -194,6 +194,7 @@ enum HV_GENERIC_SET_FORMAT { #define HV_STATUS_INVALID_HYPERCALL_INPUT 3 #define HV_STATUS_INVALID_ALIGNMENT 4 #define HV_STATUS_INVALID_PARAMETER 5 +#define HV_STATUS_ACCESS_DENIED 6 #define HV_STATUS_OPERATION_DENIED 8 #define HV_STATUS_INSUFFICIENT_MEMORY 11 #define HV_STATUS_INVALID_PORT_ID 17 diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2f34487e21f2..37cbb56ccd09 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -10,6 +10,7 @@ #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> +#include <linux/sched/stat.h> #include <linux/bug.h> #include <linux/minmax.h> #include <linux/mm.h> @@ -27,6 +28,7 @@ #include <linux/rcuwait.h> #include <linux/refcount.h> #include <linux/nospec.h> +#include <linux/notifier.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -146,7 +148,7 @@ static inline bool is_error_page(struct page *page) */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_PENDING_TIMER 2 +#define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 #define KVM_REQUEST_ARCH_BASE 8 @@ -265,6 +267,11 @@ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) return !!map->hva; } +static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) +{ + return single_task_running() && !need_resched() && ktime_before(cur, stop); +} + /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. @@ -517,6 +524,15 @@ struct kvm { #endif /* KVM_HAVE_MMU_RWLOCK */ struct mutex slots_lock; + + /* + * Protects the arch-specific fields of struct kvm_memory_slots in + * use by the VM. To be used under the slots_lock (above) or in a + * kvm->srcu critical section where acquiring the slots_lock would + * lead to deadlock with the synchronize_srcu in + * install_new_memslots. + */ + struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; @@ -579,6 +595,10 @@ struct kvm { pid_t userspace_pid; unsigned int max_halt_poll_ns; u32 dirty_ring_size; + +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER + struct notifier_block pm_notifier; +#endif }; #define kvm_err(fmt, ...) \ @@ -992,6 +1012,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); +#endif + #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); #endif @@ -1179,7 +1203,15 @@ __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { - return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE; + /* + * The index was checked originally in search_memslots. To avoid + * that a malicious guest builds a Spectre gadget out of e.g. page + * table walks, do not let the processor speculate loads outside + * the guest's registered memslots. + */ + unsigned long offset = gfn - slot->base_gfn; + offset = array_index_nospec(offset, slot->npages); + return slot->userspace_addr + offset * PAGE_SIZE; } static inline int memslot_id(struct kvm *kvm, gfn_t gfn) diff --git a/include/linux/math64.h b/include/linux/math64.h index 66deb1fdc2ef..2928f03d6d46 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -3,6 +3,7 @@ #define _LINUX_MATH64_H #include <linux/types.h> +#include <linux/math.h> #include <vdso/math64.h> #include <asm/div64.h> @@ -234,6 +235,24 @@ static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift) #endif +#ifndef mul_s64_u64_shr +static inline u64 mul_s64_u64_shr(s64 a, u64 b, unsigned int shift) +{ + u64 ret; + + /* + * Extract the sign before the multiplication and put it back + * afterwards if needed. + */ + ret = mul_u64_u64_shr(abs(a), b, shift); + + if (a < 0) + ret = -((s64) ret); + + return ret; +} +#endif /* mul_s64_u64_shr */ + #ifndef mul_u64_u32_div static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) { diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 613198a94c43..330835f1005b 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/ioctl.h> @@ -1082,7 +1083,10 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SGX_ATTRIBUTE 196 #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 #define KVM_CAP_PTP_KVM 198 -#define KVM_CAP_PPC_RPT_INVALIDATE 199 +#define KVM_CAP_HYPERV_ENFORCE_CPUID 199 +#define KVM_CAP_SREGS2 200 +#define KVM_CAP_EXIT_HYPERCALL 201 +#define KVM_CAP_PPC_RPT_INVALIDATE 202 #ifdef KVM_CAP_IRQ_ROUTING @@ -1621,6 +1625,9 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) +#define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) +#define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) + struct kvm_xen_vcpu_attr { __u16 type; __u16 pad[3]; @@ -1880,8 +1887,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h index 8b86609849b9..960c7e93d1a9 100644 --- a/include/uapi/linux/kvm_para.h +++ b/include/uapi/linux/kvm_para.h @@ -29,6 +29,7 @@ #define KVM_HC_CLOCK_PAIRING 9 #define KVM_HC_SEND_IPI 10 #define KVM_HC_SCHED_YIELD 11 +#define KVM_HC_MAP_GPA_RANGE 12 /* * hypercalls use architecture specific diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 3fd9a7e9d90c..79d9c44d1ad7 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include <linux/const.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/ioctl.h> @@ -1879,8 +1880,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index bd83158e0e0b..e0e14150744e 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -13,6 +13,7 @@ /x86_64/kvm_pv_test /x86_64/hyperv_clock /x86_64/hyperv_cpuid +/x86_64/hyperv_features /x86_64/mmio_warning_test /x86_64/platform_info_test /x86_64/set_boot_cpu_id @@ -29,6 +30,7 @@ /x86_64/vmx_preemption_timer_test /x86_64/vmx_set_nested_state_test /x86_64/vmx_tsc_adjust_test +/x86_64/vmx_nested_tsc_scaling_test /x86_64/xapic_ipi_test /x86_64/xen_shinfo_test /x86_64/xen_vmcall_test @@ -41,5 +43,6 @@ /kvm_create_max_vcpus /kvm_page_table_test /memslot_modification_stress_test +/memslot_perf_test /set_memory_region_test /steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index e439d027939d..61e2accd080d 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -33,8 +33,8 @@ ifeq ($(ARCH),s390) UNAME_M := s390x endif -LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S +LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c +LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c @@ -44,6 +44,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test @@ -60,6 +61,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test +TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs @@ -74,6 +76,7 @@ TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test +TEST_GEN_PROGS_x86_64 += memslot_perf_test TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 5f7a229c3af1..b74704305835 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -9,6 +9,7 @@ #define _GNU_SOURCE /* for pipe2 */ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <time.h> @@ -38,6 +39,7 @@ static int nr_vcpus = 1; static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; +static size_t demand_paging_size; static char *guest_data_prototype; static void *vcpu_worker(void *data) @@ -71,36 +73,51 @@ static void *vcpu_worker(void *data) return NULL; } -static int handle_uffd_page_request(int uffd, uint64_t addr) +static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr) { - pid_t tid; + pid_t tid = syscall(__NR_gettid); struct timespec start; struct timespec ts_diff; - struct uffdio_copy copy; int r; - tid = syscall(__NR_gettid); + clock_gettime(CLOCK_MONOTONIC, &start); - copy.src = (uint64_t)guest_data_prototype; - copy.dst = addr; - copy.len = perf_test_args.host_page_size; - copy.mode = 0; + if (uffd_mode == UFFDIO_REGISTER_MODE_MISSING) { + struct uffdio_copy copy; - clock_gettime(CLOCK_MONOTONIC, &start); + copy.src = (uint64_t)guest_data_prototype; + copy.dst = addr; + copy.len = demand_paging_size; + copy.mode = 0; - r = ioctl(uffd, UFFDIO_COPY, ©); - if (r == -1) { - pr_info("Failed Paged in 0x%lx from thread %d with errno: %d\n", - addr, tid, errno); - return r; + r = ioctl(uffd, UFFDIO_COPY, ©); + if (r == -1) { + pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else if (uffd_mode == UFFDIO_REGISTER_MODE_MINOR) { + struct uffdio_continue cont = {0}; + + cont.range.start = addr; + cont.range.len = demand_paging_size; + + r = ioctl(uffd, UFFDIO_CONTINUE, &cont); + if (r == -1) { + pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n", + addr, tid, errno); + return r; + } + } else { + TEST_FAIL("Invalid uffd mode %d", uffd_mode); } ts_diff = timespec_elapsed(start); - PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, + PER_PAGE_DEBUG("UFFD page-in %d \t%ld ns\n", tid, timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - perf_test_args.host_page_size, addr, tid); + demand_paging_size, addr, tid); return 0; } @@ -108,6 +125,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) bool quit_uffd_thread; struct uffd_handler_args { + int uffd_mode; int uffd; int pipefd; useconds_t delay; @@ -169,7 +187,7 @@ static void *uffd_handler_thread_fn(void *arg) if (r == -1) { if (errno == EAGAIN) continue; - pr_info("Read of uffd gor errno %d", errno); + pr_info("Read of uffd got errno %d\n", errno); return NULL; } @@ -184,7 +202,7 @@ static void *uffd_handler_thread_fn(void *arg) if (delay) usleep(delay); addr = msg.arg.pagefault.address; - r = handle_uffd_page_request(uffd, addr); + r = handle_uffd_page_request(uffd_args->uffd_mode, uffd, addr); if (r < 0) return NULL; pages++; @@ -198,43 +216,53 @@ static void *uffd_handler_thread_fn(void *arg) return NULL; } -static int setup_demand_paging(struct kvm_vm *vm, - pthread_t *uffd_handler_thread, int pipefd, - useconds_t uffd_delay, - struct uffd_handler_args *uffd_args, - void *hva, uint64_t len) +static void setup_demand_paging(struct kvm_vm *vm, + pthread_t *uffd_handler_thread, int pipefd, + int uffd_mode, useconds_t uffd_delay, + struct uffd_handler_args *uffd_args, + void *hva, void *alias, uint64_t len) { + bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR); int uffd; struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; + uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY; - uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); - if (uffd == -1) { - pr_info("uffd creation failed\n"); - return -1; + PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", + is_minor ? "MINOR" : "MISSING", + is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY"); + + /* In order to get minor faults, prefault via the alias. */ + if (is_minor) { + size_t p; + + expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE; + + TEST_ASSERT(alias != NULL, "Alias required for minor faults"); + for (p = 0; p < (len / demand_paging_size); ++p) { + memcpy(alias + (p * demand_paging_size), + guest_data_prototype, demand_paging_size); + } } + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno); + uffdio_api.api = UFFD_API; uffdio_api.features = 0; - if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) { - pr_info("ioctl uffdio_api failed\n"); - return -1; - } + TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1, + "ioctl UFFDIO_API failed: %" PRIu64, + (uint64_t)uffdio_api.api); uffdio_register.range.start = (uint64_t)hva; uffdio_register.range.len = len; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { - pr_info("ioctl uffdio_register failed\n"); - return -1; - } - - if ((uffdio_register.ioctls & UFFD_API_RANGE_IOCTLS) != - UFFD_API_RANGE_IOCTLS) { - pr_info("unexpected userfaultfd ioctl set\n"); - return -1; - } + uffdio_register.mode = uffd_mode; + TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1, + "ioctl UFFDIO_REGISTER failed"); + TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) == + expected_ioctls, "missing userfaultfd ioctls"); + uffd_args->uffd_mode = uffd_mode; uffd_args->uffd = uffd; uffd_args->pipefd = pipefd; uffd_args->delay = uffd_delay; @@ -243,13 +271,12 @@ static int setup_demand_paging(struct kvm_vm *vm, PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n", hva, hva + len); - - return 0; } struct test_params { - bool use_uffd; + int uffd_mode; useconds_t uffd_delay; + enum vm_mem_backing_src_type src_type; bool partition_vcpu_memory_access; }; @@ -267,14 +294,16 @@ static void run_test(enum vm_guest_mode mode, void *arg) int r; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, - VM_MEM_SRC_ANONYMOUS); + p->src_type); perf_test_args.wr_fract = 1; - guest_data_prototype = malloc(perf_test_args.host_page_size); + demand_paging_size = get_backing_src_pagesz(p->src_type); + + guest_data_prototype = malloc(demand_paging_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); + memset(guest_data_prototype, 0xAB, demand_paging_size); vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); @@ -282,7 +311,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, p->partition_vcpu_memory_access); - if (p->use_uffd) { + if (p->uffd_mode) { uffd_handler_threads = malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); @@ -296,6 +325,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { vm_paddr_t vcpu_gpa; void *vcpu_hva; + void *vcpu_alias; uint64_t vcpu_mem_size; @@ -310,8 +340,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size); - /* Cache the HVA pointer of the region */ + /* Cache the host addresses of the region */ vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + vcpu_alias = addr_gpa2alias(vm, vcpu_gpa); /* * Set up user fault fd to handle demand paging @@ -321,13 +352,11 @@ static void run_test(enum vm_guest_mode mode, void *arg) O_CLOEXEC | O_NONBLOCK); TEST_ASSERT(!r, "Failed to set up pipefd"); - r = setup_demand_paging(vm, - &uffd_handler_threads[vcpu_id], - pipefds[vcpu_id * 2], - p->uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_mem_size); - if (r < 0) - exit(-r); + setup_demand_paging(vm, &uffd_handler_threads[vcpu_id], + pipefds[vcpu_id * 2], p->uffd_mode, + p->uffd_delay, &uffd_args[vcpu_id], + vcpu_hva, vcpu_alias, + vcpu_mem_size); } } @@ -355,7 +384,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("All vCPU threads joined\n"); - if (p->use_uffd) { + if (p->uffd_mode) { char c; /* Tell the user fault fd handler threads to quit */ @@ -377,7 +406,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) free(guest_data_prototype); free(vcpu_threads); - if (p->use_uffd) { + if (p->uffd_mode) { free(uffd_handler_threads); free(uffd_args); free(pipefds); @@ -387,17 +416,19 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n" - " [-b memory] [-v vcpus] [-o]\n", name); + printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" + " [-b memory] [-t type] [-v vcpus] [-o]\n", name); guest_modes_help(); - printf(" -u: use User Fault FD to handle vCPU page\n" - " faults.\n"); + printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" + " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); printf(" -d: add a delay in usec to the User Fault\n" " FD handler to simulate demand paging\n" " overheads. Ignored without -u.\n"); printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); + printf(" -t: The type of backing memory to use. Default: anonymous\n"); + backing_src_help(); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); @@ -409,19 +440,24 @@ int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { + .src_type = VM_MEM_SRC_ANONYMOUS, .partition_vcpu_memory_access = true, }; int opt; guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:ud:b:v:o")) != -1) { + while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); break; case 'u': - p.use_uffd = true; + if (!strcmp("MISSING", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MISSING; + else if (!strcmp("MINOR", optarg)) + p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR; + TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'."); break; case 'd': p.uffd_delay = strtoul(optarg, NULL, 0); @@ -430,6 +466,9 @@ int main(int argc, char *argv[]) case 'b': guest_percpu_mem_size = parse_size(optarg); break; + case 't': + p.src_type = parse_backing_src_type(optarg); + break; case 'v': nr_vcpus = atoi(optarg); TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, @@ -445,6 +484,11 @@ int main(int argc, char *argv[]) } } + if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR && + !backing_src_is_shared(p.src_type)) { + TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t"); + } + for_each_guest_mode(run_test, &p); return 0; diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index 5aadf84c91c0..4b8db3bce610 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -132,6 +132,36 @@ static void run_test(uint32_t run) TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run); } +void wait_for_child_setup(pid_t pid) +{ + /* + * Wait for the child to post to the semaphore, but wake up periodically + * to check if the child exited prematurely. + */ + for (;;) { + const struct timespec wait_period = { .tv_sec = 1 }; + int status; + + if (!sem_timedwait(sem, &wait_period)) + return; + + /* Child is still running, keep waiting. */ + if (pid != waitpid(pid, &status, WNOHANG)) + continue; + + /* + * Child is no longer running, which is not expected. + * + * If it exited with a non-zero status, we explicitly forward + * the child's status in case it exited with KSFT_SKIP. + */ + if (WIFEXITED(status)) + exit(WEXITSTATUS(status)); + else + TEST_ASSERT(false, "Child exited unexpectedly"); + } +} + int main(int argc, char **argv) { uint32_t i; @@ -148,7 +178,7 @@ int main(int argc, char **argv) run_test(i); /* This function always exits */ pr_debug("%s: [%d] waiting semaphore\n", __func__, i); - sem_wait(sem); + wait_for_child_setup(pid); r = (rand() % DELAY_US_MAX) + 1; pr_debug("%s: [%d] waiting %dus\n", __func__, i, r); usleep(r); diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a8f022794ce3..35739567189e 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -43,6 +43,7 @@ enum vm_guest_mode { VM_MODE_P40V48_4K, VM_MODE_P40V48_64K, VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ + VM_MODE_P47V64_4K, NUM_VM_MODES, }; @@ -60,7 +61,7 @@ enum vm_guest_mode { #elif defined(__s390x__) -#define VM_MODE_DEFAULT VM_MODE_P52V48_4K +#define VM_MODE_DEFAULT VM_MODE_P47V64_4K #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 16) @@ -77,6 +78,7 @@ struct vm_guest_mode_params { }; extern const struct vm_guest_mode_params vm_guest_mode_params[]; +int open_kvm_dev_path_or_exit(void); int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, @@ -146,6 +148,7 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); /* * Address Guest Virtual to Guest Physical @@ -283,10 +286,11 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me uint32_t num_percpu_pages, void *guest_code, uint32_t vcpuids[]); -/* Like vm_create_default_with_vcpus, but accepts mode as a parameter */ +/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t extra_mem_pages, uint32_t num_percpu_pages, - void *guest_code, uint32_t vcpuids[]); + uint64_t slot0_mem_pages, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]); /* * Adds a vCPU with reasonable defaults (e.g. a stack) @@ -302,7 +306,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm); unsigned int vm_get_page_size(struct kvm_vm *vm); unsigned int vm_get_page_shift(struct kvm_vm *vm); -unsigned int vm_get_max_gfn(struct kvm_vm *vm); +uint64_t vm_get_max_gfn(struct kvm_vm *vm); int vm_get_fd(struct kvm_vm *vm); unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index fade3130eb01..d79be15dd3d2 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -17,6 +17,7 @@ #include <errno.h> #include <unistd.h> #include <fcntl.h> +#include <sys/mman.h> #include "kselftest.h" static inline int _no_printf(const char *format, ...) { return 0; } @@ -84,6 +85,8 @@ enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB, + VM_MEM_SRC_SHMEM, + VM_MEM_SRC_SHARED_HUGETLB, NUM_SRC_TYPES, }; @@ -100,4 +103,13 @@ size_t get_backing_src_pagesz(uint32_t i); void backing_src_help(void); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); +/* + * Whether or not the given source type is shared memory (as opposed to + * anonymous). + */ +static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) +{ + return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; +} + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h new file mode 100644 index 000000000000..0be4757f1f20 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/apic.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/x86_64/apic.h + * + * Copyright (C) 2021, Google LLC. + */ + +#ifndef SELFTEST_KVM_APIC_H +#define SELFTEST_KVM_APIC_H + +#include <stdint.h> + +#include "processor.h" + +#define APIC_DEFAULT_GPA 0xfee00000ULL + +/* APIC base address MSR and fields */ +#define MSR_IA32_APICBASE 0x0000001b +#define MSR_IA32_APICBASE_BSP (1<<8) +#define MSR_IA32_APICBASE_EXTD (1<<10) +#define MSR_IA32_APICBASE_ENABLE (1<<11) +#define MSR_IA32_APICBASE_BASE (0xfffff<<12) +#define GET_APIC_BASE(x) (((x) >> 12) << 12) + +#define APIC_BASE_MSR 0x800 +#define X2APIC_ENABLE (1UL << 10) +#define APIC_ID 0x20 +#define APIC_LVR 0x30 +#define GET_APIC_ID_FIELD(x) (((x) >> 24) & 0xFF) +#define APIC_TASKPRI 0x80 +#define APIC_PROCPRI 0xA0 +#define APIC_EOI 0xB0 +#define APIC_SPIV 0xF0 +#define APIC_SPIV_FOCUS_DISABLED (1 << 9) +#define APIC_SPIV_APIC_ENABLED (1 << 8) +#define APIC_ICR 0x300 +#define APIC_DEST_SELF 0x40000 +#define APIC_DEST_ALLINC 0x80000 +#define APIC_DEST_ALLBUT 0xC0000 +#define APIC_ICR_RR_MASK 0x30000 +#define APIC_ICR_RR_INVALID 0x00000 +#define APIC_ICR_RR_INPROG 0x10000 +#define APIC_ICR_RR_VALID 0x20000 +#define APIC_INT_LEVELTRIG 0x08000 +#define APIC_INT_ASSERT 0x04000 +#define APIC_ICR_BUSY 0x01000 +#define APIC_DEST_LOGICAL 0x00800 +#define APIC_DEST_PHYSICAL 0x00000 +#define APIC_DM_FIXED 0x00000 +#define APIC_DM_FIXED_MASK 0x00700 +#define APIC_DM_LOWEST 0x00100 +#define APIC_DM_SMI 0x00200 +#define APIC_DM_REMRD 0x00300 +#define APIC_DM_NMI 0x00400 +#define APIC_DM_INIT 0x00500 +#define APIC_DM_STARTUP 0x00600 +#define APIC_DM_EXTINT 0x00700 +#define APIC_VECTOR_MASK 0x000FF +#define APIC_ICR2 0x310 +#define SET_APIC_DEST_FIELD(x) ((x) << 24) + +void apic_disable(void); +void xapic_enable(void); +void x2apic_enable(void); + +static inline uint32_t get_bsp_flag(void) +{ + return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP; +} + +static inline uint32_t xapic_read_reg(unsigned int reg) +{ + return ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2]; +} + +static inline void xapic_write_reg(unsigned int reg, uint32_t val) +{ + ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2] = val; +} + +static inline uint64_t x2apic_read_reg(unsigned int reg) +{ + return rdmsr(APIC_BASE_MSR + (reg >> 4)); +} + +static inline void x2apic_write_reg(unsigned int reg, uint64_t value) +{ + wrmsr(APIC_BASE_MSR + (reg >> 4), value); +} + +#endif /* SELFTEST_KVM_APIC_H */ diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h index a034438b6266..c9af97abd622 100644 --- a/tools/testing/selftests/kvm/include/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * tools/testing/selftests/kvm/include/vmx.h + * tools/testing/selftests/kvm/include/x86_64/evmcs.h * * Copyright (C) 2018, Red Hat, Inc. * diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h new file mode 100644 index 000000000000..412eaee7884a --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -0,0 +1,185 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * tools/testing/selftests/kvm/include/x86_64/hyperv.h + * + * Copyright (C) 2021, Red Hat, Inc. + * + */ + +#ifndef SELFTEST_KVM_HYPERV_H +#define SELFTEST_KVM_HYPERV_H + +#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 0x40000000 +#define HYPERV_CPUID_INTERFACE 0x40000001 +#define HYPERV_CPUID_VERSION 0x40000002 +#define HYPERV_CPUID_FEATURES 0x40000003 +#define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004 +#define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005 +#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES 0x40000007 +#define HYPERV_CPUID_NESTED_FEATURES 0x4000000A +#define HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS 0x40000080 +#define HYPERV_CPUID_SYNDBG_INTERFACE 0x40000081 +#define HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES 0x40000082 + +#define HV_X64_MSR_GUEST_OS_ID 0x40000000 +#define HV_X64_MSR_HYPERCALL 0x40000001 +#define HV_X64_MSR_VP_INDEX 0x40000002 +#define HV_X64_MSR_RESET 0x40000003 +#define HV_X64_MSR_VP_RUNTIME 0x40000010 +#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 +#define HV_X64_MSR_REFERENCE_TSC 0x40000021 +#define HV_X64_MSR_TSC_FREQUENCY 0x40000022 +#define HV_X64_MSR_APIC_FREQUENCY 0x40000023 +#define HV_X64_MSR_EOI 0x40000070 +#define HV_X64_MSR_ICR 0x40000071 +#define HV_X64_MSR_TPR 0x40000072 +#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 +#define HV_X64_MSR_SCONTROL 0x40000080 +#define HV_X64_MSR_SVERSION 0x40000081 +#define HV_X64_MSR_SIEFP 0x40000082 +#define HV_X64_MSR_SIMP 0x40000083 +#define HV_X64_MSR_EOM 0x40000084 +#define HV_X64_MSR_SINT0 0x40000090 +#define HV_X64_MSR_SINT1 0x40000091 +#define HV_X64_MSR_SINT2 0x40000092 +#define HV_X64_MSR_SINT3 0x40000093 +#define HV_X64_MSR_SINT4 0x40000094 +#define HV_X64_MSR_SINT5 0x40000095 +#define HV_X64_MSR_SINT6 0x40000096 +#define HV_X64_MSR_SINT7 0x40000097 +#define HV_X64_MSR_SINT8 0x40000098 +#define HV_X64_MSR_SINT9 0x40000099 +#define HV_X64_MSR_SINT10 0x4000009A +#define HV_X64_MSR_SINT11 0x4000009B +#define HV_X64_MSR_SINT12 0x4000009C +#define HV_X64_MSR_SINT13 0x4000009D +#define HV_X64_MSR_SINT14 0x4000009E +#define HV_X64_MSR_SINT15 0x4000009F +#define HV_X64_MSR_STIMER0_CONFIG 0x400000B0 +#define HV_X64_MSR_STIMER0_COUNT 0x400000B1 +#define HV_X64_MSR_STIMER1_CONFIG 0x400000B2 +#define HV_X64_MSR_STIMER1_COUNT 0x400000B3 +#define HV_X64_MSR_STIMER2_CONFIG 0x400000B4 +#define HV_X64_MSR_STIMER2_COUNT 0x400000B5 +#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 +#define HV_X64_MSR_STIMER3_COUNT 0x400000B7 +#define HV_X64_MSR_GUEST_IDLE 0x400000F0 +#define HV_X64_MSR_CRASH_P0 0x40000100 +#define HV_X64_MSR_CRASH_P1 0x40000101 +#define HV_X64_MSR_CRASH_P2 0x40000102 +#define HV_X64_MSR_CRASH_P3 0x40000103 +#define HV_X64_MSR_CRASH_P4 0x40000104 +#define HV_X64_MSR_CRASH_CTL 0x40000105 +#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 +#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 +#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 +#define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118 + +#define HV_X64_MSR_SYNDBG_CONTROL 0x400000F1 +#define HV_X64_MSR_SYNDBG_STATUS 0x400000F2 +#define HV_X64_MSR_SYNDBG_SEND_BUFFER 0x400000F3 +#define HV_X64_MSR_SYNDBG_RECV_BUFFER 0x400000F4 +#define HV_X64_MSR_SYNDBG_PENDING_BUFFER 0x400000F5 +#define HV_X64_MSR_SYNDBG_OPTIONS 0x400000FF + +/* HYPERV_CPUID_FEATURES.EAX */ +#define HV_MSR_VP_RUNTIME_AVAILABLE BIT(0) +#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1) +#define HV_MSR_SYNIC_AVAILABLE BIT(2) +#define HV_MSR_SYNTIMER_AVAILABLE BIT(3) +#define HV_MSR_APIC_ACCESS_AVAILABLE BIT(4) +#define HV_MSR_HYPERCALL_AVAILABLE BIT(5) +#define HV_MSR_VP_INDEX_AVAILABLE BIT(6) +#define HV_MSR_RESET_AVAILABLE BIT(7) +#define HV_MSR_STAT_PAGES_AVAILABLE BIT(8) +#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9) +#define HV_MSR_GUEST_IDLE_AVAILABLE BIT(10) +#define HV_ACCESS_FREQUENCY_MSRS BIT(11) +#define HV_ACCESS_REENLIGHTENMENT BIT(13) +#define HV_ACCESS_TSC_INVARIANT BIT(15) + +/* HYPERV_CPUID_FEATURES.EBX */ +#define HV_CREATE_PARTITIONS BIT(0) +#define HV_ACCESS_PARTITION_ID BIT(1) +#define HV_ACCESS_MEMORY_POOL BIT(2) +#define HV_ADJUST_MESSAGE_BUFFERS BIT(3) +#define HV_POST_MESSAGES BIT(4) +#define HV_SIGNAL_EVENTS BIT(5) +#define HV_CREATE_PORT BIT(6) +#define HV_CONNECT_PORT BIT(7) +#define HV_ACCESS_STATS BIT(8) +#define HV_DEBUGGING BIT(11) +#define HV_CPU_MANAGEMENT BIT(12) +#define HV_ISOLATION BIT(22) + +/* HYPERV_CPUID_FEATURES.EDX */ +#define HV_X64_MWAIT_AVAILABLE BIT(0) +#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) +#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) +#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) +#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4) +#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) +#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) +#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) + +/* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ +#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) +#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) +#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) +#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) +#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) +#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) +#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) +#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) +#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) + +/* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ +#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING BIT(1) + +/* Hypercalls */ +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003 +#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008 +#define HVCALL_SEND_IPI 0x000b +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013 +#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014 +#define HVCALL_SEND_IPI_EX 0x0015 +#define HVCALL_GET_PARTITION_ID 0x0046 +#define HVCALL_DEPOSIT_MEMORY 0x0048 +#define HVCALL_CREATE_VP 0x004e +#define HVCALL_GET_VP_REGISTERS 0x0050 +#define HVCALL_SET_VP_REGISTERS 0x0051 +#define HVCALL_POST_MESSAGE 0x005c +#define HVCALL_SIGNAL_EVENT 0x005d +#define HVCALL_POST_DEBUG_DATA 0x0069 +#define HVCALL_RETRIEVE_DEBUG_DATA 0x006a +#define HVCALL_RESET_DEBUG_SESSION 0x006b +#define HVCALL_ADD_LOGICAL_PROCESSOR 0x0076 +#define HVCALL_MAP_DEVICE_INTERRUPT 0x007c +#define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d +#define HVCALL_RETARGET_INTERRUPT 0x007e +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 + +#define HV_FLUSH_ALL_PROCESSORS BIT(0) +#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1) +#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2) +#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3) + +/* hypercall status code */ +#define HV_STATUS_SUCCESS 0 +#define HV_STATUS_INVALID_HYPERCALL_CODE 2 +#define HV_STATUS_INVALID_HYPERCALL_INPUT 3 +#define HV_STATUS_INVALID_ALIGNMENT 4 +#define HV_STATUS_INVALID_PARAMETER 5 +#define HV_STATUS_ACCESS_DENIED 6 +#define HV_STATUS_OPERATION_DENIED 8 +#define HV_STATUS_INSUFFICIENT_MEMORY 11 +#define HV_STATUS_INVALID_PORT_ID 17 +#define HV_STATUS_INVALID_CONNECTION_ID 18 +#define HV_STATUS_INSUFFICIENT_BUFFERS 19 + +#endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 0b30b4e15c38..9a5b47d2d5d6 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -13,6 +13,8 @@ #include <asm/msr-index.h> +#include "../kvm_util.h" + #define X86_EFLAGS_FIXED (1u << 1) #define X86_CR4_VME (1ul << 0) @@ -425,53 +427,6 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui #define X86_CR0_CD (1UL<<30) /* Cache Disable */ #define X86_CR0_PG (1UL<<31) /* Paging */ -#define APIC_DEFAULT_GPA 0xfee00000ULL - -/* APIC base address MSR and fields */ -#define MSR_IA32_APICBASE 0x0000001b -#define MSR_IA32_APICBASE_BSP (1<<8) -#define MSR_IA32_APICBASE_EXTD (1<<10) -#define MSR_IA32_APICBASE_ENABLE (1<<11) -#define MSR_IA32_APICBASE_BASE (0xfffff<<12) -#define GET_APIC_BASE(x) (((x) >> 12) << 12) - -#define APIC_BASE_MSR 0x800 -#define X2APIC_ENABLE (1UL << 10) -#define APIC_ID 0x20 -#define APIC_LVR 0x30 -#define GET_APIC_ID_FIELD(x) (((x) >> 24) & 0xFF) -#define APIC_TASKPRI 0x80 -#define APIC_PROCPRI 0xA0 -#define APIC_EOI 0xB0 -#define APIC_SPIV 0xF0 -#define APIC_SPIV_FOCUS_DISABLED (1 << 9) -#define APIC_SPIV_APIC_ENABLED (1 << 8) -#define APIC_ICR 0x300 -#define APIC_DEST_SELF 0x40000 -#define APIC_DEST_ALLINC 0x80000 -#define APIC_DEST_ALLBUT 0xC0000 -#define APIC_ICR_RR_MASK 0x30000 -#define APIC_ICR_RR_INVALID 0x00000 -#define APIC_ICR_RR_INPROG 0x10000 -#define APIC_ICR_RR_VALID 0x20000 -#define APIC_INT_LEVELTRIG 0x08000 -#define APIC_INT_ASSERT 0x04000 -#define APIC_ICR_BUSY 0x01000 -#define APIC_DEST_LOGICAL 0x00800 -#define APIC_DEST_PHYSICAL 0x00000 -#define APIC_DM_FIXED 0x00000 -#define APIC_DM_FIXED_MASK 0x00700 -#define APIC_DM_LOWEST 0x00100 -#define APIC_DM_SMI 0x00200 -#define APIC_DM_REMRD 0x00300 -#define APIC_DM_NMI 0x00400 -#define APIC_DM_INIT 0x00500 -#define APIC_DM_STARTUP 0x00600 -#define APIC_DM_EXTINT 0x00700 -#define APIC_VECTOR_MASK 0x000FF -#define APIC_ICR2 0x310 -#define SET_APIC_DEST_FIELD(x) ((x) << 24) - /* VMX_EPT_VPID_CAP bits */ #define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21) diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 65eb1079a161..516c81d86353 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -10,6 +10,7 @@ #include <stdint.h> #include "processor.h" +#include "apic.h" /* * Definitions of Primary Processor-Based VM-Execution Controls. diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 1c4753fff19e..82171f17c1d7 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -268,7 +268,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) /* Create a VM with enough guest pages */ guest_num_pages = test_mem_size / guest_page_size; - vm = vm_create_with_vcpus(mode, nr_vcpus, + vm = vm_create_with_vcpus(mode, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, guest_num_pages, 0, guest_code, NULL); /* Align down GPA of the testing memslot */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index fc83f6c5902d..a2b732cf96ea 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -32,6 +32,34 @@ static void *align(void *x, size_t size) } /* + * Open KVM_DEV_PATH if available, otherwise exit the entire program. + * + * Input Args: + * flags - The flags to pass when opening KVM_DEV_PATH. + * + * Return: + * The opened file descriptor of /dev/kvm. + */ +static int _open_kvm_dev_path_or_exit(int flags) +{ + int fd; + + fd = open(KVM_DEV_PATH, flags); + if (fd < 0) { + print_skip("%s not available, is KVM loaded? (errno: %d)", + KVM_DEV_PATH, errno); + exit(KSFT_SKIP); + } + + return fd; +} + +int open_kvm_dev_path_or_exit(void) +{ + return _open_kvm_dev_path_or_exit(O_RDONLY); +} + +/* * Capability * * Input Args: @@ -52,12 +80,9 @@ int kvm_check_cap(long cap) int ret; int kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); - + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" + TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n" " rc: %i errno: %i", ret, errno); close(kvm_fd); @@ -128,9 +153,7 @@ void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) static void vm_open(struct kvm_vm *vm, int perm) { - vm->kvm_fd = open(KVM_DEV_PATH, perm); - if (vm->kvm_fd < 0) - exit(KSFT_SKIP); + vm->kvm_fd = _open_kvm_dev_path_or_exit(perm); if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { print_skip("immediate_exit not available"); @@ -152,6 +175,7 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages", [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", + [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, "Missing new mode strings?"); @@ -169,6 +193,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { { 40, 48, 0x1000, 12 }, { 40, 48, 0x10000, 16 }, { 0, 0, 0x1000, 12 }, + { 47, 64, 0x1000, 12 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -203,7 +228,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_ASSERT(vm != NULL, "Insufficient Memory"); INIT_LIST_HEAD(&vm->vcpus); - INIT_LIST_HEAD(&vm->userspace_mem_regions); + vm->regions.gpa_tree = RB_ROOT; + vm->regions.hva_tree = RB_ROOT; + hash_init(vm->regions.slot_hash); vm->mode = mode; vm->type = 0; @@ -252,6 +279,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms"); #endif break; + case VM_MODE_P47V64_4K: + vm->pgtable_levels = 5; + break; default: TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); } @@ -283,21 +313,50 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } +/* + * VM Create with customized parameters + * + * Input Args: + * mode - VM Mode (e.g. VM_MODE_P52V48_4K) + * nr_vcpus - VCPU count + * slot0_mem_pages - Slot0 physical memory size + * extra_mem_pages - Non-slot0 physical memory total size + * num_percpu_pages - Per-cpu physical memory pages + * guest_code - Guest entry point + * vcpuids - VCPU IDs + * + * Output Args: None + * + * Return: + * Pointer to opaque structure that describes the created VM. + * + * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K), + * with customized slot0 memory size, at least 512 pages currently. + * extra_mem_pages is only used to calculate the maximum page table size, + * no real memory allocation for non-slot0 memory in this function. + */ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t extra_mem_pages, uint32_t num_percpu_pages, - void *guest_code, uint32_t vcpuids[]) + uint64_t slot0_mem_pages, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]) { + uint64_t vcpu_pages, extra_pg_pages, pages; + struct kvm_vm *vm; + int i; + + /* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */ + if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES) + slot0_mem_pages = DEFAULT_GUEST_PHY_PAGES; + /* The maximum page table size for a memory region will be when the * smallest pages are used. Considering each page contains x page * table descriptors, the total extra size for page tables (for extra * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller * than N/x*2. */ - uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; - uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; - struct kvm_vm *vm; - int i; + vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; + extra_pg_pages = (slot0_mem_pages + extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; + pages = slot0_mem_pages + vcpu_pages + extra_pg_pages; TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), "nr_vcpus = %d too large for host, max-vcpus = %d", @@ -329,8 +388,8 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me uint32_t num_percpu_pages, void *guest_code, uint32_t vcpuids[]) { - return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages, - num_percpu_pages, guest_code, vcpuids); + return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, + extra_mem_pages, num_percpu_pages, guest_code, vcpuids); } struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, @@ -355,13 +414,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, */ void kvm_vm_restart(struct kvm_vm *vmp, int perm) { + int ctr; struct userspace_mem_region *region; vm_open(vmp, perm); if (vmp->has_irqchip) vm_create_irqchip(vmp); - list_for_each_entry(region, &vmp->userspace_mem_regions, list) { + hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" @@ -424,14 +484,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) static struct userspace_mem_region * userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + for (node = vm->regions.gpa_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, gpa_node); uint64_t existing_start = region->region.guest_phys_addr; uint64_t existing_end = region->region.guest_phys_addr + region->region.memory_size - 1; if (start <= existing_end && end >= existing_start) return region; + + if (start < existing_start) + node = node->rb_left; + else + node = node->rb_right; } return NULL; @@ -546,11 +613,16 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region) + struct userspace_mem_region *region, + bool unlink) { int ret; - list_del(®ion->list); + if (unlink) { + rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); + rb_erase(®ion->hva_node, &vm->regions.hva_tree); + hash_del(®ion->slot_node); + } region->region.memory_size = 0; ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); @@ -569,14 +641,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, */ void kvm_vm_free(struct kvm_vm *vmp) { - struct userspace_mem_region *region, *tmp; + int ctr; + struct hlist_node *node; + struct userspace_mem_region *region; if (vmp == NULL) return; /* Free userspace_mem_regions. */ - list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list) - __vm_mem_region_delete(vmp, region); + hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) + __vm_mem_region_delete(vmp, region, false); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -658,13 +732,64 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) return 0; } +static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), gpa_node); + parent = *cur; + if (region->region.guest_phys_addr < + cregion->region.guest_phys_addr) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->region.guest_phys_addr != + cregion->region.guest_phys_addr, + "Duplicate GPA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->gpa_node, parent, cur); + rb_insert_color(®ion->gpa_node, gpa_tree); +} + +static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, + struct userspace_mem_region *region) +{ + struct rb_node **cur, *parent; + + for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) { + struct userspace_mem_region *cregion; + + cregion = container_of(*cur, typeof(*cregion), hva_node); + parent = *cur; + if (region->host_mem < cregion->host_mem) + cur = &(*cur)->rb_left; + else { + TEST_ASSERT(region->host_mem != + cregion->host_mem, + "Duplicate HVA in region tree"); + + cur = &(*cur)->rb_right; + } + } + + rb_link_node(®ion->hva_node, parent, cur); + rb_insert_color(®ion->hva_node, hva_tree); +} + /* * VM Userspace Memory Region Add * * Input Args: * vm - Virtual Machine - * backing_src - Storage source for this region. - * NULL to use anonymous memory. + * src_type - Storage source for this region. + * NULL to use anonymous memory. * guest_paddr - Starting guest physical address * slot - KVM region slot * npages - Number of physical pages @@ -722,7 +847,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, (uint64_t) region->region.memory_size); /* Confirm no region with the requested slot already exists. */ - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + slot) { if (region->region.slot != slot) continue; @@ -755,11 +881,30 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, if (alignment > 1) region->mmap_size += alignment; + region->fd = -1; + if (backing_src_is_shared(src_type)) { + int memfd_flags = MFD_CLOEXEC; + + if (src_type == VM_MEM_SRC_SHARED_HUGETLB) + memfd_flags |= MFD_HUGETLB; + + region->fd = memfd_create("kvm_selftest", memfd_flags); + TEST_ASSERT(region->fd != -1, + "memfd_create failed, errno: %i", errno); + + ret = ftruncate(region->fd, region->mmap_size); + TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno); + + ret = fallocate(region->fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, + region->mmap_size); + TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno); + } + region->mmap_start = mmap(NULL, region->mmap_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS - | vm_mem_backing_src_alias(src_type)->flag, - -1, 0); + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); TEST_ASSERT(region->mmap_start != MAP_FAILED, "test_malloc failed, mmap_start: %p errno: %i", region->mmap_start, errno); @@ -793,8 +938,23 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, ret, errno, slot, flags, guest_paddr, (uint64_t) region->region.memory_size); - /* Add to linked-list of memory regions. */ - list_add(®ion->list, &vm->userspace_mem_regions); + /* Add to quick lookup data structures */ + vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); + vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region); + hash_add(vm->regions.slot_hash, ®ion->slot_node, slot); + + /* If shared memory, create an alias. */ + if (region->fd >= 0) { + region->mmap_alias = mmap(NULL, region->mmap_size, + PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd, 0); + TEST_ASSERT(region->mmap_alias != MAP_FAILED, + "mmap of alias failed, errno: %i", errno); + + /* Align host alias address */ + region->host_alias = align(region->mmap_alias, alignment); + } } /* @@ -817,10 +977,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each_possible(vm->regions.slot_hash, region, slot_node, + memslot) if (region->region.slot == memslot) return region; - } fprintf(stderr, "No mem region with the requested slot found,\n" " requested slot: %u\n", memslot); @@ -905,7 +1065,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot)); + __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } /* @@ -925,9 +1085,7 @@ static int vcpu_mmap_sz(void) { int dev_fd, ret; - dev_fd = open(KVM_DEV_PATH, O_RDONLY); - if (dev_fd < 0) - exit(KSFT_SKIP); + dev_fd = open_kvm_dev_path_or_exit(); ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); TEST_ASSERT(ret >= sizeof(struct kvm_run), @@ -1099,6 +1257,9 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); virt_pgd_alloc(vm, pgd_memslot); + vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages, + KVM_UTIL_MIN_PFN * vm->page_size, + data_memslot); /* * Find an unused range of virtual page addresses of at least @@ -1108,11 +1269,7 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, /* Map the virtual pages. */ for (vm_vaddr_t vaddr = vaddr_start; pages > 0; - pages--, vaddr += vm->page_size) { - vm_paddr_t paddr; - - paddr = vm_phy_page_alloc(vm, - KVM_UTIL_MIN_PFN * vm->page_size, data_memslot); + pages--, vaddr += vm->page_size, paddr += vm->page_size) { virt_pg_map(vm, vaddr, paddr, pgd_memslot); @@ -1177,16 +1334,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((gpa >= region->region.guest_phys_addr) - && (gpa <= (region->region.guest_phys_addr - + region->region.memory_size - 1))) - return (void *) ((uintptr_t) region->host_mem - + (gpa - region->region.guest_phys_addr)); + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) { + TEST_FAIL("No vm physical memory at 0x%lx", gpa); + return NULL; } - TEST_FAIL("No vm physical memory at 0x%lx", gpa); - return NULL; + return (void *)((uintptr_t)region->host_mem + + (gpa - region->region.guest_phys_addr)); } /* @@ -1208,15 +1363,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) */ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) { - struct userspace_mem_region *region; + struct rb_node *node; - list_for_each_entry(region, &vm->userspace_mem_regions, list) { - if ((hva >= region->host_mem) - && (hva <= (region->host_mem - + region->region.memory_size - 1))) - return (vm_paddr_t) ((uintptr_t) - region->region.guest_phys_addr - + (hva - (uintptr_t) region->host_mem)); + for (node = vm->regions.hva_tree.rb_node; node; ) { + struct userspace_mem_region *region = + container_of(node, struct userspace_mem_region, hva_node); + + if (hva >= region->host_mem) { + if (hva <= (region->host_mem + + region->region.memory_size - 1)) + return (vm_paddr_t)((uintptr_t) + region->region.guest_phys_addr + + (hva - (uintptr_t)region->host_mem)); + + node = node->rb_right; + } else + node = node->rb_left; } TEST_FAIL("No mapping to a guest physical address, hva: %p", hva); @@ -1224,6 +1386,42 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) } /* + * Address VM physical to Host Virtual *alias*. + * + * Input Args: + * vm - Virtual Machine + * gpa - VM physical address + * + * Output Args: None + * + * Return: + * Equivalent address within the host virtual *alias* area, or NULL + * (without failing the test) if the guest memory is not shared (so + * no alias exists). + * + * When vm_create() and related functions are called with a shared memory + * src_type, we also create a writable, shared alias mapping of the + * underlying guest memory. This allows the host to manipulate guest memory + * without mapping that memory in the guest's address space. And, for + * userfaultfd-based demand paging, we can do so without triggering userfaults. + */ +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) +{ + struct userspace_mem_region *region; + uintptr_t offset; + + region = userspace_mem_region_find(vm, gpa, gpa); + if (!region) + return NULL; + + if (!region->host_alias) + return NULL; + + offset = gpa - region->region.guest_phys_addr; + return (void *) ((uintptr_t) region->host_alias + offset); +} + +/* * VM Create IRQ Chip * * Input Args: @@ -1822,6 +2020,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, */ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { + int ctr; struct userspace_mem_region *region; struct vcpu *vcpu; @@ -1829,7 +2028,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size); fprintf(stream, "%*sMem Regions:\n", indent, ""); - list_for_each_entry(region, &vm->userspace_mem_regions, list) { + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx " "host_virt: %p\n", indent + 2, "", (uint64_t) region->region.guest_phys_addr, @@ -2015,10 +2214,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm) if (vm == NULL) { /* Ensure that the KVM vendor-specific module is loaded. */ - f = fopen(KVM_DEV_PATH, "r"); - TEST_ASSERT(f != NULL, "Error in opening KVM dev file: %d", - errno); - fclose(f); + close(open_kvm_dev_path_or_exit()); } f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r"); @@ -2041,7 +2237,7 @@ unsigned int vm_get_page_shift(struct kvm_vm *vm) return vm->page_shift; } -unsigned int vm_get_max_gfn(struct kvm_vm *vm) +uint64_t vm_get_max_gfn(struct kvm_vm *vm) { return vm->max_gfn; } diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 91ce1b5d480b..a03febc24ba6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -8,6 +8,9 @@ #ifndef SELFTEST_KVM_UTIL_INTERNAL_H #define SELFTEST_KVM_UTIL_INTERNAL_H +#include "linux/hashtable.h" +#include "linux/rbtree.h" + #include "sparsebit.h" struct userspace_mem_region { @@ -16,9 +19,13 @@ struct userspace_mem_region { int fd; off_t offset; void *host_mem; + void *host_alias; void *mmap_start; + void *mmap_alias; size_t mmap_size; - struct list_head list; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; }; struct vcpu { @@ -31,6 +38,12 @@ struct vcpu { uint32_t dirty_gfns_count; }; +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + struct kvm_vm { int mode; unsigned long type; @@ -43,7 +56,7 @@ struct kvm_vm { unsigned int va_bits; uint64_t max_gfn; struct list_head vcpus; - struct list_head userspace_mem_regions; + struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c index 81490b9b4e32..7397ca299835 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/perf_test_util.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2020, Google LLC. */ +#include <inttypes.h> #include "kvm_util.h" #include "perf_test_util.h" @@ -68,7 +69,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, "Guest memory size is not guest page size aligned."); - vm = vm_create_with_vcpus(mode, vcpus, + vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES, (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size, 0, guest_code, NULL); @@ -80,7 +81,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, */ TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + " guest pages: %" PRIx64 " max gfn: %" PRIx64 + " vcpus: %d wss: %" PRIx64 "]\n", guest_num_pages, vm_get_max_gfn(vm), vcpus, vcpu_memory_bytes); diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c new file mode 100644 index 000000000000..a703f0194ea3 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/rbtree.c @@ -0,0 +1 @@ +#include "../../../../lib/rbtree.c" diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 63d2bc7d757b..af1031fed97f 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -166,72 +166,89 @@ size_t get_def_hugetlb_pagesz(void) return 0; } +#define ANON_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS) +#define ANON_HUGE_FLAGS (ANON_FLAGS | MAP_HUGETLB) + const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i) { static const struct vm_mem_backing_src_alias aliases[] = { [VM_MEM_SRC_ANONYMOUS] = { .name = "anonymous", - .flag = 0, + .flag = ANON_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_THP] = { .name = "anonymous_thp", - .flag = 0, + .flag = ANON_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB] = { .name = "anonymous_hugetlb", - .flag = MAP_HUGETLB, + .flag = ANON_HUGE_FLAGS, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = { .name = "anonymous_hugetlb_16kb", - .flag = MAP_HUGETLB | MAP_HUGE_16KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = { .name = "anonymous_hugetlb_64kb", - .flag = MAP_HUGETLB | MAP_HUGE_64KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_64KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = { .name = "anonymous_hugetlb_512kb", - .flag = MAP_HUGETLB | MAP_HUGE_512KB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_512KB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = { .name = "anonymous_hugetlb_1mb", - .flag = MAP_HUGETLB | MAP_HUGE_1MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_1MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = { .name = "anonymous_hugetlb_2mb", - .flag = MAP_HUGETLB | MAP_HUGE_2MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_2MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = { .name = "anonymous_hugetlb_8mb", - .flag = MAP_HUGETLB | MAP_HUGE_8MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_8MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = { .name = "anonymous_hugetlb_16mb", - .flag = MAP_HUGETLB | MAP_HUGE_16MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = { .name = "anonymous_hugetlb_32mb", - .flag = MAP_HUGETLB | MAP_HUGE_32MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_32MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = { .name = "anonymous_hugetlb_256mb", - .flag = MAP_HUGETLB | MAP_HUGE_256MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_256MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = { .name = "anonymous_hugetlb_512mb", - .flag = MAP_HUGETLB | MAP_HUGE_512MB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_512MB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = { .name = "anonymous_hugetlb_1gb", - .flag = MAP_HUGETLB | MAP_HUGE_1GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_1GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = { .name = "anonymous_hugetlb_2gb", - .flag = MAP_HUGETLB | MAP_HUGE_2GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_2GB, }, [VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = { .name = "anonymous_hugetlb_16gb", - .flag = MAP_HUGETLB | MAP_HUGE_16GB, + .flag = ANON_HUGE_FLAGS | MAP_HUGE_16GB, + }, + [VM_MEM_SRC_SHMEM] = { + .name = "shmem", + .flag = MAP_SHARED, + }, + [VM_MEM_SRC_SHARED_HUGETLB] = { + .name = "shared_hugetlb", + /* + * No MAP_HUGETLB, we use MFD_HUGETLB instead. Since + * we're using "file backed" memory, we need to specify + * this when the FD is created, not when the area is + * mapped. + */ + .flag = MAP_SHARED, }, }; _Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES, @@ -250,10 +267,12 @@ size_t get_backing_src_pagesz(uint32_t i) switch (i) { case VM_MEM_SRC_ANONYMOUS: + case VM_MEM_SRC_SHMEM: return getpagesize(); case VM_MEM_SRC_ANONYMOUS_THP: return get_trans_hugepagesz(); case VM_MEM_SRC_ANONYMOUS_HUGETLB: + case VM_MEM_SRC_SHARED_HUGETLB: return get_def_hugetlb_pagesz(); default: return MAP_HUGE_PAGE_SIZE(flag); diff --git a/tools/testing/selftests/kvm/lib/x86_64/apic.c b/tools/testing/selftests/kvm/lib/x86_64/apic.c new file mode 100644 index 000000000000..7168e25c194e --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/apic.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * tools/testing/selftests/kvm/lib/x86_64/processor.c + * + * Copyright (C) 2021, Google LLC. + */ + +#include "apic.h" + +void apic_disable(void) +{ + wrmsr(MSR_IA32_APICBASE, + rdmsr(MSR_IA32_APICBASE) & + ~(MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD)); +} + +void xapic_enable(void) +{ + uint64_t val = rdmsr(MSR_IA32_APICBASE); + + /* Per SDM: to enable xAPIC when in x2APIC must first disable APIC */ + if (val & MSR_IA32_APICBASE_EXTD) { + apic_disable(); + wrmsr(MSR_IA32_APICBASE, + rdmsr(MSR_IA32_APICBASE) | MSR_IA32_APICBASE_ENABLE); + } else if (!(val & MSR_IA32_APICBASE_ENABLE)) { + wrmsr(MSR_IA32_APICBASE, val | MSR_IA32_APICBASE_ENABLE); + } + + /* + * Per SDM: reset value of spurious interrupt vector register has the + * APIC software enabled bit=0. It must be enabled in addition to the + * enable bit in the MSR. + */ + val = xapic_read_reg(APIC_SPIV) | APIC_SPIV_APIC_ENABLED; + xapic_write_reg(APIC_SPIV, val); +} + +void x2apic_enable(void) +{ + wrmsr(MSR_IA32_APICBASE, rdmsr(MSR_IA32_APICBASE) | + MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD); + x2apic_write_reg(APIC_SPIV, + x2apic_read_reg(APIC_SPIV) | APIC_SPIV_APIC_ENABLED); +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index a8906e60a108..efe235044421 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -657,9 +657,7 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", @@ -691,9 +689,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) buffer.header.nmsrs = 1; buffer.entry.index = msr_index; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); r = ioctl(kvm_fd, KVM_GET_MSRS, &buffer.header); TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" @@ -986,9 +982,7 @@ struct kvm_msr_list *kvm_get_msr_index_list(void) struct kvm_msr_list *list; int nmsrs, r, kvm_fd; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); nmsrs = kvm_get_num_msrs_fd(kvm_fd); list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); @@ -1312,9 +1306,7 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) return cpuid; cpuid = allocate_kvm_cpuid2(); - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_HV_CPUID failed %d %d\n", diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 6096bf0a5b34..98351ba0933c 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -71,14 +71,22 @@ struct memslot_antagonist_args { }; static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, - uint64_t nr_modifications, uint64_t gpa) + uint64_t nr_modifications) { + const uint64_t pages = 1; + uint64_t gpa; int i; + /* + * Add the dummy memslot just below the perf_test_util memslot, which is + * at the top of the guest physical address space. + */ + gpa = guest_test_phys_mem - pages * vm_get_page_size(vm); + for (i = 0; i < nr_modifications; i++) { usleep(delay); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa, - DUMMY_MEMSLOT_INDEX, 1, 0); + DUMMY_MEMSLOT_INDEX, pages, 0); vm_mem_region_delete(vm, DUMMY_MEMSLOT_INDEX); } @@ -120,11 +128,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("Started all vCPUs\n"); add_remove_memslot(vm, p->memslot_modification_delay, - p->nr_memslot_modifications, - guest_test_phys_mem + - (guest_percpu_mem_size * nr_vcpus) + - perf_test_args.host_page_size + - perf_test_args.guest_page_size); + p->nr_memslot_modifications); run_vcpus = false; diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c new file mode 100644 index 000000000000..11239652d805 --- /dev/null +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -0,0 +1,1037 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A memslot-related performance benchmark. + * + * Copyright (C) 2021 Oracle and/or its affiliates. + * + * Basic guest setup / host vCPU thread code lifted from set_memory_region_test. + */ +#include <pthread.h> +#include <sched.h> +#include <semaphore.h> +#include <stdatomic.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <time.h> +#include <unistd.h> + +#include <linux/compiler.h> + +#include <test_util.h> +#include <kvm_util.h> +#include <processor.h> + +#define VCPU_ID 0 + +#define MEM_SIZE ((512U << 20) + 4096) +#define MEM_SIZE_PAGES (MEM_SIZE / 4096) +#define MEM_GPA 0x10000000UL +#define MEM_AUX_GPA MEM_GPA +#define MEM_SYNC_GPA MEM_AUX_GPA +#define MEM_TEST_GPA (MEM_AUX_GPA + 4096) +#define MEM_TEST_SIZE (MEM_SIZE - 4096) +static_assert(MEM_SIZE % 4096 == 0, "invalid mem size"); +static_assert(MEM_TEST_SIZE % 4096 == 0, "invalid mem test size"); + +/* + * 32 MiB is max size that gets well over 100 iterations on 509 slots. + * Considering that each slot needs to have at least one page up to + * 8194 slots in use can then be tested (although with slightly + * limited resolution). + */ +#define MEM_SIZE_MAP ((32U << 20) + 4096) +#define MEM_SIZE_MAP_PAGES (MEM_SIZE_MAP / 4096) +#define MEM_TEST_MAP_SIZE (MEM_SIZE_MAP - 4096) +#define MEM_TEST_MAP_SIZE_PAGES (MEM_TEST_MAP_SIZE / 4096) +static_assert(MEM_SIZE_MAP % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE % 4096 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES % 2 == 0, "invalid map test region size"); +static_assert(MEM_TEST_MAP_SIZE_PAGES > 2, "invalid map test region size"); + +/* + * 128 MiB is min size that fills 32k slots with at least one page in each + * while at the same time gets 100+ iterations in such test + */ +#define MEM_TEST_UNMAP_SIZE (128U << 20) +#define MEM_TEST_UNMAP_SIZE_PAGES (MEM_TEST_UNMAP_SIZE / 4096) +/* 2 MiB chunk size like a typical huge page */ +#define MEM_TEST_UNMAP_CHUNK_PAGES (2U << (20 - 12)) +static_assert(MEM_TEST_UNMAP_SIZE <= MEM_TEST_SIZE, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE % 4096 == 0, + "invalid unmap test region size"); +static_assert(MEM_TEST_UNMAP_SIZE_PAGES % + (2 * MEM_TEST_UNMAP_CHUNK_PAGES) == 0, + "invalid unmap test region size"); + +/* + * For the move active test the middle of the test area is placed on + * a memslot boundary: half lies in the memslot being moved, half in + * other memslot(s). + * + * When running this test with 32k memslots (32764, really) each memslot + * contains 4 pages. + * The last one additionally contains the remaining 21 pages of memory, + * for the total size of 25 pages. + * Hence, the maximum size here is 50 pages. + */ +#define MEM_TEST_MOVE_SIZE_PAGES (50) +#define MEM_TEST_MOVE_SIZE (MEM_TEST_MOVE_SIZE_PAGES * 4096) +#define MEM_TEST_MOVE_GPA_DEST (MEM_GPA + MEM_SIZE) +static_assert(MEM_TEST_MOVE_SIZE <= MEM_TEST_SIZE, + "invalid move test region size"); + +#define MEM_TEST_VAL_1 0x1122334455667788 +#define MEM_TEST_VAL_2 0x99AABBCCDDEEFF00 + +struct vm_data { + struct kvm_vm *vm; + pthread_t vcpu_thread; + uint32_t nslots; + uint64_t npages; + uint64_t pages_per_slot; + void **hva_slots; + bool mmio_ok; + uint64_t mmio_gpa_min; + uint64_t mmio_gpa_max; +}; + +struct sync_area { + atomic_bool start_flag; + atomic_bool exit_flag; + atomic_bool sync_flag; + void *move_area_ptr; +}; + +/* + * Technically, we need also for the atomic bool to be address-free, which + * is recommended, but not strictly required, by C11 for lockless + * implementations. + * However, in practice both GCC and Clang fulfill this requirement on + * all KVM-supported platforms. + */ +static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless"); + +static sem_t vcpu_ready; + +static bool map_unmap_verify; + +static bool verbose; +#define pr_info_v(...) \ + do { \ + if (verbose) \ + pr_info(__VA_ARGS__); \ + } while (0) + +static void *vcpu_worker(void *data) +{ + struct vm_data *vm = data; + struct kvm_run *run; + struct ucall uc; + uint64_t cmd; + + run = vcpu_state(vm->vm, VCPU_ID); + while (1) { + vcpu_run(vm->vm, VCPU_ID); + + if (run->exit_reason == KVM_EXIT_IO) { + cmd = get_ucall(vm->vm, VCPU_ID, &uc); + if (cmd != UCALL_SYNC) + break; + + sem_post(&vcpu_ready); + continue; + } + + if (run->exit_reason != KVM_EXIT_MMIO) + break; + + TEST_ASSERT(vm->mmio_ok, "Unexpected mmio exit"); + TEST_ASSERT(run->mmio.is_write, "Unexpected mmio read"); + TEST_ASSERT(run->mmio.len == 8, + "Unexpected exit mmio size = %u", run->mmio.len); + TEST_ASSERT(run->mmio.phys_addr >= vm->mmio_gpa_min && + run->mmio.phys_addr <= vm->mmio_gpa_max, + "Unexpected exit mmio address = 0x%llx", + run->mmio.phys_addr); + } + + if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT) + TEST_FAIL("%s at %s:%ld, val = %lu", (const char *)uc.args[0], + __FILE__, uc.args[1], uc.args[2]); + + return NULL; +} + +static void wait_for_vcpu(void) +{ + struct timespec ts; + + TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts), + "clock_gettime() failed: %d\n", errno); + + ts.tv_sec += 2; + TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts), + "sem_timedwait() failed: %d\n", errno); +} + +static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages) +{ + uint64_t gpage, pgoffs; + uint32_t slot, slotoffs; + void *base; + + TEST_ASSERT(gpa >= MEM_GPA, "Too low gpa to translate"); + TEST_ASSERT(gpa < MEM_GPA + data->npages * 4096, + "Too high gpa to translate"); + gpa -= MEM_GPA; + + gpage = gpa / 4096; + pgoffs = gpa % 4096; + slot = min(gpage / data->pages_per_slot, (uint64_t)data->nslots - 1); + slotoffs = gpage - (slot * data->pages_per_slot); + + if (rempages) { + uint64_t slotpages; + + if (slot == data->nslots - 1) + slotpages = data->npages - slot * data->pages_per_slot; + else + slotpages = data->pages_per_slot; + + TEST_ASSERT(!pgoffs, + "Asking for remaining pages in slot but gpa not page aligned"); + *rempages = slotpages - slotoffs; + } + + base = data->hva_slots[slot]; + return (uint8_t *)base + slotoffs * 4096 + pgoffs; +} + +static uint64_t vm_slot2gpa(struct vm_data *data, uint32_t slot) +{ + TEST_ASSERT(slot < data->nslots, "Too high slot number"); + + return MEM_GPA + slot * data->pages_per_slot * 4096; +} + +static struct vm_data *alloc_vm(void) +{ + struct vm_data *data; + + data = malloc(sizeof(*data)); + TEST_ASSERT(data, "malloc(vmdata) failed"); + + data->vm = NULL; + data->hva_slots = NULL; + + return data; +} + +static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, + void *guest_code, uint64_t mempages, + struct timespec *slot_runtime) +{ + uint32_t max_mem_slots; + uint64_t rempages; + uint64_t guest_addr; + uint32_t slot; + struct timespec tstart; + struct sync_area *sync; + + max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS); + TEST_ASSERT(max_mem_slots > 1, + "KVM_CAP_NR_MEMSLOTS should be greater than 1"); + TEST_ASSERT(nslots > 1 || nslots == -1, + "Slot count cap should be greater than 1"); + if (nslots != -1) + max_mem_slots = min(max_mem_slots, (uint32_t)nslots); + pr_info_v("Allowed number of memory slots: %"PRIu32"\n", max_mem_slots); + + TEST_ASSERT(mempages > 1, + "Can't test without any memory"); + + data->npages = mempages; + data->nslots = max_mem_slots - 1; + data->pages_per_slot = mempages / data->nslots; + if (!data->pages_per_slot) { + *maxslots = mempages + 1; + return false; + } + + rempages = mempages % data->nslots; + data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots); + TEST_ASSERT(data->hva_slots, "malloc() fail"); + + data->vm = vm_create_default(VCPU_ID, mempages, guest_code); + + pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", + max_mem_slots - 1, data->pages_per_slot, rempages); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + for (slot = 1, guest_addr = MEM_GPA; slot < max_mem_slots; slot++) { + uint64_t npages; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 1) + npages += rempages; + + vm_userspace_mem_region_add(data->vm, VM_MEM_SRC_ANONYMOUS, + guest_addr, slot, npages, + 0); + guest_addr += npages * 4096; + } + *slot_runtime = timespec_elapsed(tstart); + + for (slot = 0, guest_addr = MEM_GPA; slot < max_mem_slots - 1; slot++) { + uint64_t npages; + uint64_t gpa; + + npages = data->pages_per_slot; + if (slot == max_mem_slots - 2) + npages += rempages; + + gpa = vm_phy_pages_alloc(data->vm, npages, guest_addr, + slot + 1); + TEST_ASSERT(gpa == guest_addr, + "vm_phy_pages_alloc() failed\n"); + + data->hva_slots[slot] = addr_gpa2hva(data->vm, guest_addr); + memset(data->hva_slots[slot], 0, npages * 4096); + + guest_addr += npages * 4096; + } + + virt_map(data->vm, MEM_GPA, MEM_GPA, mempages, 0); + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + atomic_init(&sync->start_flag, false); + atomic_init(&sync->exit_flag, false); + atomic_init(&sync->sync_flag, false); + + data->mmio_ok = false; + + return true; +} + +static void launch_vm(struct vm_data *data) +{ + pr_info_v("Launching the test VM\n"); + + pthread_create(&data->vcpu_thread, NULL, vcpu_worker, data); + + /* Ensure the guest thread is spun up. */ + wait_for_vcpu(); +} + +static void free_vm(struct vm_data *data) +{ + kvm_vm_free(data->vm); + free(data->hva_slots); + free(data); +} + +static void wait_guest_exit(struct vm_data *data) +{ + pthread_join(data->vcpu_thread, NULL); +} + +static void let_guest_run(struct sync_area *sync) +{ + atomic_store_explicit(&sync->start_flag, true, memory_order_release); +} + +static void guest_spin_until_start(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + while (!atomic_load_explicit(&sync->start_flag, memory_order_acquire)) + ; +} + +static void make_guest_exit(struct sync_area *sync) +{ + atomic_store_explicit(&sync->exit_flag, true, memory_order_release); +} + +static bool _guest_should_exit(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + return atomic_load_explicit(&sync->exit_flag, memory_order_acquire); +} + +#define guest_should_exit() unlikely(_guest_should_exit()) + +/* + * noinline so we can easily see how much time the host spends waiting + * for the guest. + * For the same reason use alarm() instead of polling clock_gettime() + * to implement a wait timeout. + */ +static noinline void host_perform_sync(struct sync_area *sync) +{ + alarm(2); + + atomic_store_explicit(&sync->sync_flag, true, memory_order_release); + while (atomic_load_explicit(&sync->sync_flag, memory_order_acquire)) + ; + + alarm(0); +} + +static bool guest_perform_sync(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + bool expected; + + do { + if (guest_should_exit()) + return false; + + expected = true; + } while (!atomic_compare_exchange_weak_explicit(&sync->sync_flag, + &expected, false, + memory_order_acq_rel, + memory_order_relaxed)); + + return true; +} + +static void guest_code_test_memslot_move(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + uintptr_t base = (typeof(base))READ_ONCE(sync->move_area_ptr); + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (!guest_should_exit()) { + uintptr_t ptr; + + for (ptr = base; ptr < base + MEM_TEST_MOVE_SIZE; + ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + /* + * No host sync here since the MMIO exits are so expensive + * that the host would spend most of its time waiting for + * the guest and so instead of measuring memslot move + * performance we would measure the performance and + * likelihood of MMIO exits + */ + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_map(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + MEM_TEST_MAP_SIZE / 2; + ptr < MEM_TEST_GPA + MEM_TEST_MAP_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_unmap(void) +{ + struct sync_area *sync = (typeof(sync))MEM_SYNC_GPA; + + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr = MEM_TEST_GPA; + + /* + * We can afford to access (map) just a small number of pages + * per host sync as otherwise the host will spend + * a significant amount of its time waiting for the guest + * (instead of doing unmap operations), so this will + * effectively turn this test into a map performance test. + * + * Just access a single page to be on the safe side. + */ + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + ptr += MEM_TEST_UNMAP_SIZE / 2; + *(uint64_t *)ptr = MEM_TEST_VAL_2; + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static void guest_code_test_memslot_rw(void) +{ + GUEST_SYNC(0); + + guest_spin_until_start(); + + while (1) { + uintptr_t ptr; + + for (ptr = MEM_TEST_GPA; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) + *(uint64_t *)ptr = MEM_TEST_VAL_1; + + if (!guest_perform_sync()) + break; + + for (ptr = MEM_TEST_GPA + 4096 / 2; + ptr < MEM_TEST_GPA + MEM_TEST_SIZE; ptr += 4096) { + uint64_t val = *(uint64_t *)ptr; + + GUEST_ASSERT_1(val == MEM_TEST_VAL_2, val); + *(uint64_t *)ptr = 0; + } + + if (!guest_perform_sync()) + break; + } + + GUEST_DONE(); +} + +static bool test_memslot_move_prepare(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots, bool isactive) +{ + uint64_t movesrcgpa, movetestgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + + if (isactive) { + uint64_t lastpages; + + vm_gpa2hva(data, movesrcgpa, &lastpages); + if (lastpages < MEM_TEST_MOVE_SIZE_PAGES / 2) { + *maxslots = 0; + return false; + } + } + + movetestgpa = movesrcgpa - (MEM_TEST_MOVE_SIZE / (isactive ? 2 : 1)); + sync->move_area_ptr = (void *)movetestgpa; + + if (isactive) { + data->mmio_ok = true; + data->mmio_gpa_min = movesrcgpa; + data->mmio_gpa_max = movesrcgpa + MEM_TEST_MOVE_SIZE / 2 - 1; + } + + return true; +} + +static bool test_memslot_move_prepare_active(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, true); +} + +static bool test_memslot_move_prepare_inactive(struct vm_data *data, + struct sync_area *sync, + uint64_t *maxslots) +{ + return test_memslot_move_prepare(data, sync, maxslots, false); +} + +static void test_memslot_move_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t movesrcgpa; + + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, + MEM_TEST_MOVE_GPA_DEST); + vm_mem_region_move(data->vm, data->nslots - 1 + 1, movesrcgpa); +} + +static void test_memslot_do_unmap(struct vm_data *data, + uint64_t offsp, uint64_t count) +{ + uint64_t gpa, ctr; + + for (gpa = MEM_TEST_GPA + offsp * 4096, ctr = 0; ctr < count; ) { + uint64_t npages; + void *hva; + int ret; + + hva = vm_gpa2hva(data, gpa, &npages); + TEST_ASSERT(npages, "Empty memory slot at gptr 0x%"PRIx64, gpa); + npages = min(npages, count - ctr); + ret = madvise(hva, npages * 4096, MADV_DONTNEED); + TEST_ASSERT(!ret, + "madvise(%p, MADV_DONTNEED) on VM memory should not fail for gptr 0x%"PRIx64, + hva, gpa); + ctr += npages; + gpa += npages * 4096; + } + TEST_ASSERT(ctr == count, + "madvise(MADV_DONTNEED) should exactly cover all of the requested area"); +} + +static void test_memslot_map_unmap_check(struct vm_data *data, + uint64_t offsp, uint64_t valexp) +{ + uint64_t gpa; + uint64_t *val; + + if (!map_unmap_verify) + return; + + gpa = MEM_TEST_GPA + offsp * 4096; + val = (typeof(val))vm_gpa2hva(data, gpa, NULL); + TEST_ASSERT(*val == valexp, + "Guest written values should read back correctly before unmap (%"PRIu64" vs %"PRIu64" @ %"PRIx64")", + *val, valexp, gpa); + *val = 0; +} + +static void test_memslot_map_loop(struct vm_data *data, struct sync_area *sync) +{ + /* + * Unmap the second half of the test area while guest writes to (maps) + * the first half. + */ + test_memslot_do_unmap(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_MAP_SIZE_PAGES / 2); + + /* + * Wait for the guest to finish writing the first half of the test + * area, verify the written value on the first and the last page of + * this area and then unmap it. + * Meanwhile, the guest is writing to (mapping) the second half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + test_memslot_map_unmap_check(data, + MEM_TEST_MAP_SIZE_PAGES / 2 - 1, + MEM_TEST_VAL_1); + test_memslot_do_unmap(data, 0, MEM_TEST_MAP_SIZE_PAGES / 2); + + + /* + * Wait for the guest to finish writing the second half of the test + * area and verify the written value on the first and the last page + * of this area. + * The area will be unmapped at the beginning of the next loop + * iteration. + * Meanwhile, the guest is writing to (mapping) the first half of + * the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + test_memslot_map_unmap_check(data, MEM_TEST_MAP_SIZE_PAGES - 1, + MEM_TEST_VAL_2); +} + +static void test_memslot_unmap_loop_common(struct vm_data *data, + struct sync_area *sync, + uint64_t chunk) +{ + uint64_t ctr; + + /* + * Wait for the guest to finish mapping page(s) in the first half + * of the test area, verify the written value and then perform unmap + * of this area. + * Meanwhile, the guest is writing to (mapping) page(s) in the second + * half of the test area. + */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, 0, MEM_TEST_VAL_1); + for (ctr = 0; ctr < MEM_TEST_UNMAP_SIZE_PAGES / 2; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); + + /* Likewise, but for the opposite host / guest areas */ + host_perform_sync(sync); + test_memslot_map_unmap_check(data, MEM_TEST_UNMAP_SIZE_PAGES / 2, + MEM_TEST_VAL_2); + for (ctr = MEM_TEST_UNMAP_SIZE_PAGES / 2; + ctr < MEM_TEST_UNMAP_SIZE_PAGES; ctr += chunk) + test_memslot_do_unmap(data, ctr, chunk); +} + +static void test_memslot_unmap_loop(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, 1); +} + +static void test_memslot_unmap_loop_chunked(struct vm_data *data, + struct sync_area *sync) +{ + test_memslot_unmap_loop_common(data, sync, MEM_TEST_UNMAP_CHUNK_PAGES); +} + +static void test_memslot_rw_loop(struct vm_data *data, struct sync_area *sync) +{ + uint64_t gptr; + + for (gptr = MEM_TEST_GPA + 4096 / 2; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) + *(uint64_t *)vm_gpa2hva(data, gptr, NULL) = MEM_TEST_VAL_2; + + host_perform_sync(sync); + + for (gptr = MEM_TEST_GPA; + gptr < MEM_TEST_GPA + MEM_TEST_SIZE; gptr += 4096) { + uint64_t *vptr = (typeof(vptr))vm_gpa2hva(data, gptr, NULL); + uint64_t val = *vptr; + + TEST_ASSERT(val == MEM_TEST_VAL_1, + "Guest written values should read back correctly (is %"PRIu64" @ %"PRIx64")", + val, gptr); + *vptr = 0; + } + + host_perform_sync(sync); +} + +struct test_data { + const char *name; + uint64_t mem_size; + void (*guest_code)(void); + bool (*prepare)(struct vm_data *data, struct sync_area *sync, + uint64_t *maxslots); + void (*loop)(struct vm_data *data, struct sync_area *sync); +}; + +static bool test_execute(int nslots, uint64_t *maxslots, + unsigned int maxtime, + const struct test_data *tdata, + uint64_t *nloops, + struct timespec *slot_runtime, + struct timespec *guest_runtime) +{ + uint64_t mem_size = tdata->mem_size ? : MEM_SIZE_PAGES; + struct vm_data *data; + struct sync_area *sync; + struct timespec tstart; + bool ret = true; + + data = alloc_vm(); + if (!prepare_vm(data, nslots, maxslots, tdata->guest_code, + mem_size, slot_runtime)) { + ret = false; + goto exit_free; + } + + sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + + if (tdata->prepare && + !tdata->prepare(data, sync, maxslots)) { + ret = false; + goto exit_free; + } + + launch_vm(data); + + clock_gettime(CLOCK_MONOTONIC, &tstart); + let_guest_run(sync); + + while (1) { + *guest_runtime = timespec_elapsed(tstart); + if (guest_runtime->tv_sec >= maxtime) + break; + + tdata->loop(data, sync); + + (*nloops)++; + } + + make_guest_exit(sync); + wait_guest_exit(data); + +exit_free: + free_vm(data); + + return ret; +} + +static const struct test_data tests[] = { + { + .name = "map", + .mem_size = MEM_SIZE_MAP_PAGES, + .guest_code = guest_code_test_memslot_map, + .loop = test_memslot_map_loop, + }, + { + .name = "unmap", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop, + }, + { + .name = "unmap chunked", + .mem_size = MEM_TEST_UNMAP_SIZE_PAGES + 1, + .guest_code = guest_code_test_memslot_unmap, + .loop = test_memslot_unmap_loop_chunked, + }, + { + .name = "move active area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_active, + .loop = test_memslot_move_loop, + }, + { + .name = "move inactive area", + .guest_code = guest_code_test_memslot_move, + .prepare = test_memslot_move_prepare_inactive, + .loop = test_memslot_move_loop, + }, + { + .name = "RW", + .guest_code = guest_code_test_memslot_rw, + .loop = test_memslot_rw_loop + }, +}; + +#define NTESTS ARRAY_SIZE(tests) + +struct test_args { + int tfirst; + int tlast; + int nslots; + int seconds; + int runs; +}; + +static void help(char *name, struct test_args *targs) +{ + int ctr; + + pr_info("usage: %s [-h] [-v] [-d] [-s slots] [-f first_test] [-e last_test] [-l test_length] [-r run_count]\n", + name); + pr_info(" -h: print this help screen.\n"); + pr_info(" -v: enable verbose mode (not for benchmarking).\n"); + pr_info(" -d: enable extra debug checks.\n"); + pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n", + targs->nslots); + pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n", + targs->tfirst, NTESTS - 1); + pr_info(" -e: specify the last test to run (currently: %i; max %zu)\n", + targs->tlast, NTESTS - 1); + pr_info(" -l: specify the test length in seconds (currently: %i)\n", + targs->seconds); + pr_info(" -r: specify the number of runs per test (currently: %i)\n", + targs->runs); + + pr_info("\nAvailable tests:\n"); + for (ctr = 0; ctr < NTESTS; ctr++) + pr_info("%d: %s\n", ctr, tests[ctr].name); +} + +static bool parse_args(int argc, char *argv[], + struct test_args *targs) +{ + int opt; + + while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) { + switch (opt) { + case 'h': + default: + help(argv[0], targs); + return false; + case 'v': + verbose = true; + break; + case 'd': + map_unmap_verify = true; + break; + case 's': + targs->nslots = atoi(optarg); + if (targs->nslots <= 0 && targs->nslots != -1) { + pr_info("Slot count cap has to be positive or -1 for no cap\n"); + return false; + } + break; + case 'f': + targs->tfirst = atoi(optarg); + if (targs->tfirst < 0) { + pr_info("First test to run has to be non-negative\n"); + return false; + } + break; + case 'e': + targs->tlast = atoi(optarg); + if (targs->tlast < 0 || targs->tlast >= NTESTS) { + pr_info("Last test to run has to be non-negative and less than %zu\n", + NTESTS); + return false; + } + break; + case 'l': + targs->seconds = atoi(optarg); + if (targs->seconds < 0) { + pr_info("Test length in seconds has to be non-negative\n"); + return false; + } + break; + case 'r': + targs->runs = atoi(optarg); + if (targs->runs <= 0) { + pr_info("Runs per test has to be positive\n"); + return false; + } + break; + } + } + + if (optind < argc) { + help(argv[0], targs); + return false; + } + + if (targs->tfirst > targs->tlast) { + pr_info("First test to run cannot be greater than the last test to run\n"); + return false; + } + + return true; +} + +struct test_result { + struct timespec slot_runtime, guest_runtime, iter_runtime; + int64_t slottimens, runtimens; + uint64_t nloops; +}; + +static bool test_loop(const struct test_data *data, + const struct test_args *targs, + struct test_result *rbestslottime, + struct test_result *rbestruntime) +{ + uint64_t maxslots; + struct test_result result; + + result.nloops = 0; + if (!test_execute(targs->nslots, &maxslots, targs->seconds, data, + &result.nloops, + &result.slot_runtime, &result.guest_runtime)) { + if (maxslots) + pr_info("Memslot count too high for this test, decrease the cap (max is %"PRIu64")\n", + maxslots); + else + pr_info("Memslot count may be too high for this test, try adjusting the cap\n"); + + return false; + } + + pr_info("Test took %ld.%.9lds for slot setup + %ld.%.9lds all iterations\n", + result.slot_runtime.tv_sec, result.slot_runtime.tv_nsec, + result.guest_runtime.tv_sec, result.guest_runtime.tv_nsec); + if (!result.nloops) { + pr_info("No full loops done - too short test time or system too loaded?\n"); + return true; + } + + result.iter_runtime = timespec_div(result.guest_runtime, + result.nloops); + pr_info("Done %"PRIu64" iterations, avg %ld.%.9lds each\n", + result.nloops, + result.iter_runtime.tv_sec, + result.iter_runtime.tv_nsec); + result.slottimens = timespec_to_ns(result.slot_runtime); + result.runtimens = timespec_to_ns(result.iter_runtime); + + /* + * Only rank the slot setup time for tests using the whole test memory + * area so they are comparable + */ + if (!data->mem_size && + (!rbestslottime->slottimens || + result.slottimens < rbestslottime->slottimens)) + *rbestslottime = result; + if (!rbestruntime->runtimens || + result.runtimens < rbestruntime->runtimens) + *rbestruntime = result; + + return true; +} + +int main(int argc, char *argv[]) +{ + struct test_args targs = { + .tfirst = 0, + .tlast = NTESTS - 1, + .nslots = -1, + .seconds = 5, + .runs = 1, + }; + struct test_result rbestslottime; + int tctr; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + if (!parse_args(argc, argv, &targs)) + return -1; + + rbestslottime.slottimens = 0; + for (tctr = targs.tfirst; tctr <= targs.tlast; tctr++) { + const struct test_data *data = &tests[tctr]; + unsigned int runctr; + struct test_result rbestruntime; + + if (tctr > targs.tfirst) + pr_info("\n"); + + pr_info("Testing %s performance with %i runs, %d seconds each\n", + data->name, targs.runs, targs.seconds); + + rbestruntime.runtimens = 0; + for (runctr = 0; runctr < targs.runs; runctr++) + if (!test_loop(data, &targs, + &rbestslottime, &rbestruntime)) + break; + + if (rbestruntime.runtimens) + pr_info("Best runtime result was %ld.%.9lds per iteration (with %"PRIu64" iterations)\n", + rbestruntime.iter_runtime.tv_sec, + rbestruntime.iter_runtime.tv_nsec, + rbestruntime.nloops); + } + + if (rbestslottime.slottimens) + pr_info("Best slot setup time for the whole test area was %ld.%.9lds\n", + rbestslottime.slot_runtime.tv_sec, + rbestslottime.slot_runtime.tv_nsec); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 63096cea26c6..d0a7a998e840 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -22,15 +22,6 @@ static int ud_count; -void enable_x2apic(void) -{ - uint32_t spiv_reg = APIC_BASE_MSR + (APIC_SPIV >> 4); - - wrmsr(MSR_IA32_APICBASE, rdmsr(MSR_IA32_APICBASE) | - MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD); - wrmsr(spiv_reg, rdmsr(spiv_reg) | APIC_SPIV_APIC_ENABLED); -} - static void guest_ud_handler(struct ex_regs *regs) { ud_count++; @@ -59,7 +50,7 @@ void guest_code(struct vmx_pages *vmx_pages) #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; - enable_x2apic(); + x2apic_enable(); GUEST_SYNC(1); GUEST_SYNC(2); @@ -121,14 +112,38 @@ void inject_nmi(struct kvm_vm *vm) vcpu_events_set(vm, VCPU_ID, &events); } +static void save_restore_vm(struct kvm_vm *vm) +{ + struct kvm_regs regs1, regs2; + struct kvm_x86_state *state; + + state = vcpu_save_state(vm, VCPU_ID); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + kvm_vm_restart(vm, O_RDWR); + vm_vcpu_add(vm, VCPU_ID); + vcpu_set_hv_cpuid(vm, VCPU_ID); + vcpu_enable_evmcs(vm, VCPU_ID); + vcpu_load_state(vm, VCPU_ID, state); + free(state); + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vm, VCPU_ID, ®s2); + TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), + "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", + (ulong) regs2.rdi, (ulong) regs2.rsi); +} + int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva = 0; - struct kvm_regs regs1, regs2; struct kvm_vm *vm; struct kvm_run *run; - struct kvm_x86_state *state; struct ucall uc; int stage; @@ -145,10 +160,6 @@ int main(int argc, char *argv[]) vcpu_set_hv_cpuid(vm, VCPU_ID); vcpu_enable_evmcs(vm, VCPU_ID); - run = vcpu_state(vm, VCPU_ID); - - vcpu_regs_get(vm, VCPU_ID, ®s1); - vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); @@ -160,6 +171,7 @@ int main(int argc, char *argv[]) pr_info("Running L1 which uses EVMCS to run L2\n"); for (stage = 1;; stage++) { + run = vcpu_state(vm, VCPU_ID); _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Stage %d: unexpected exit reason: %u (%s),\n", @@ -184,32 +196,23 @@ int main(int argc, char *argv[]) uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx", stage, (ulong)uc.args[1]); - state = vcpu_save_state(vm, VCPU_ID); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); - - kvm_vm_release(vm); - - /* Restore state in a new VM. */ - kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID); - vcpu_set_hv_cpuid(vm, VCPU_ID); - vcpu_enable_evmcs(vm, VCPU_ID); - vcpu_load_state(vm, VCPU_ID, state); - run = vcpu_state(vm, VCPU_ID); - free(state); - - memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vm, VCPU_ID, ®s2); - TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), - "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", - (ulong) regs2.rdi, (ulong) regs2.rsi); + save_restore_vm(vm); /* Force immediate L2->L1 exit before resuming */ if (stage == 8) { pr_info("Injecting NMI into L1 before L2 had a chance to run after restore\n"); inject_nmi(vm); } + + /* + * Do KVM_GET_NESTED_STATE/KVM_SET_NESTED_STATE for a freshly + * restored VM (before the first KVM_RUN) to check that + * KVM_STATE_NESTED_EVMCS is not lost. + */ + if (stage == 9) { + pr_info("Trying extra KVM_GET_NESTED_STATE/KVM_SET_NESTED_STATE cycle\n"); + save_restore_vm(vm); + } } done: diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c index 9b78e8889638..8c77537af5a1 100644 --- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c @@ -19,7 +19,12 @@ struct { u32 function; u32 index; } mangled_cpuids[] = { + /* + * These entries depend on the vCPU's XCR0 register and IA32_XSS MSR, + * which are not controlled for by this test. + */ {.function = 0xd, .index = 0}, + {.function = 0xd, .index = 1}, }; static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c index cb953df4d7d0..8aed0db1331d 100644 --- a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c +++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c @@ -37,9 +37,7 @@ static void test_get_msr_index(void) int old_res, res, kvm_fd, r; struct kvm_msr_list *list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_index_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); @@ -101,9 +99,7 @@ static void test_get_msr_feature(void) int res, old_res, i, kvm_fd; struct kvm_msr_list *feature_list; - kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - if (kvm_fd < 0) - exit(KSFT_SKIP); + kvm_fd = open_kvm_dev_path_or_exit(); old_res = kvm_num_feature_msrs(kvm_fd, 0); TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0"); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index 7f1d2765572c..489625acc9cf 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -7,6 +7,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "hyperv.h" struct ms_hyperv_tsc_page { volatile u32 tsc_sequence; @@ -15,13 +16,6 @@ struct ms_hyperv_tsc_page { volatile s64 tsc_offset; } __packed; -#define HV_X64_MSR_GUEST_OS_ID 0x40000000 -#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 -#define HV_X64_MSR_REFERENCE_TSC 0x40000021 -#define HV_X64_MSR_TSC_FREQUENCY 0x40000022 -#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 -#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 - /* Simplified mul_u64_u64_shr() */ static inline u64 mul_u64_u64_shr64(u64 a, u64 b) { diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c new file mode 100644 index 000000000000..9947ef63dfa1 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -0,0 +1,649 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021, Red Hat, Inc. + * + * Tests for Hyper-V features enablement + */ +#include <asm/kvm_para.h> +#include <linux/kvm_para.h> +#include <stdint.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "hyperv.h" + +#define VCPU_ID 0 +#define LINUX_OS_ID ((u64)0x8100 << 48) + +extern unsigned char rdmsr_start; +extern unsigned char rdmsr_end; + +static u64 do_rdmsr(u32 idx) +{ + u32 lo, hi; + + asm volatile("rdmsr_start: rdmsr;" + "rdmsr_end:" + : "=a"(lo), "=c"(hi) + : "c"(idx)); + + return (((u64) hi) << 32) | lo; +} + +extern unsigned char wrmsr_start; +extern unsigned char wrmsr_end; + +static void do_wrmsr(u32 idx, u64 val) +{ + u32 lo, hi; + + lo = val; + hi = val >> 32; + + asm volatile("wrmsr_start: wrmsr;" + "wrmsr_end:" + : : "a"(lo), "c"(idx), "d"(hi)); +} + +static int nr_gp; + +static inline u64 hypercall(u64 control, vm_vaddr_t input_address, + vm_vaddr_t output_address) +{ + u64 hv_status; + + asm volatile("mov %3, %%r8\n" + "vmcall" + : "=a" (hv_status), + "+c" (control), "+d" (input_address) + : "r" (output_address) + : "cc", "memory", "r8", "r9", "r10", "r11"); + + return hv_status; +} + +static void guest_gp_handler(struct ex_regs *regs) +{ + unsigned char *rip = (unsigned char *)regs->rip; + bool r, w; + + r = rip == &rdmsr_start; + w = rip == &wrmsr_start; + GUEST_ASSERT(r || w); + + nr_gp++; + + if (r) + regs->rip = (uint64_t)&rdmsr_end; + else + regs->rip = (uint64_t)&wrmsr_end; +} + +struct msr_data { + uint32_t idx; + bool available; + bool write; + u64 write_val; +}; + +struct hcall_data { + uint64_t control; + uint64_t expect; +}; + +static void guest_msr(struct msr_data *msr) +{ + int i = 0; + + while (msr->idx) { + WRITE_ONCE(nr_gp, 0); + if (!msr->write) + do_rdmsr(msr->idx); + else + do_wrmsr(msr->idx, msr->write_val); + + if (msr->available) + GUEST_ASSERT(READ_ONCE(nr_gp) == 0); + else + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + + GUEST_SYNC(i++); + } + + GUEST_DONE(); +} + +static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) +{ + int i = 0; + + wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID); + wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); + + while (hcall->control) { + GUEST_ASSERT(hypercall(hcall->control, pgs_gpa, + pgs_gpa + 4096) == hcall->expect); + GUEST_SYNC(i++); + } + + GUEST_DONE(); +} + +static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 *feat, + struct kvm_cpuid_entry2 *recomm, + struct kvm_cpuid_entry2 *dbg) +{ + TEST_ASSERT(set_cpuid(cpuid, feat), + "failed to set KVM_CPUID_FEATURES leaf"); + TEST_ASSERT(set_cpuid(cpuid, recomm), + "failed to set HYPERV_CPUID_ENLIGHTMENT_INFO leaf"); + TEST_ASSERT(set_cpuid(cpuid, dbg), + "failed to set HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES leaf"); + vcpu_set_cpuid(vm, VCPU_ID, cpuid); +} + +static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, + struct kvm_cpuid2 *best) +{ + struct kvm_run *run; + struct ucall uc; + int stage = 0, r; + struct kvm_cpuid_entry2 feat = { + .function = HYPERV_CPUID_FEATURES + }; + struct kvm_cpuid_entry2 recomm = { + .function = HYPERV_CPUID_ENLIGHTMENT_INFO + }; + struct kvm_cpuid_entry2 dbg = { + .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES + }; + struct kvm_enable_cap cap = {0}; + + run = vcpu_state(vm, VCPU_ID); + + while (true) { + switch (stage) { + case 0: + /* + * Only available when Hyper-V identification is set + */ + msr->idx = HV_X64_MSR_GUEST_OS_ID; + msr->write = 0; + msr->available = 0; + break; + case 1: + msr->idx = HV_X64_MSR_HYPERCALL; + msr->write = 0; + msr->available = 0; + break; + case 2: + feat.eax |= HV_MSR_HYPERCALL_AVAILABLE; + /* + * HV_X64_MSR_GUEST_OS_ID has to be written first to make + * HV_X64_MSR_HYPERCALL available. + */ + msr->idx = HV_X64_MSR_GUEST_OS_ID; + msr->write = 1; + msr->write_val = LINUX_OS_ID; + msr->available = 1; + break; + case 3: + msr->idx = HV_X64_MSR_GUEST_OS_ID; + msr->write = 0; + msr->available = 1; + break; + case 4: + msr->idx = HV_X64_MSR_HYPERCALL; + msr->write = 0; + msr->available = 1; + break; + + case 5: + msr->idx = HV_X64_MSR_VP_RUNTIME; + msr->write = 0; + msr->available = 0; + break; + case 6: + feat.eax |= HV_MSR_VP_RUNTIME_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 7: + /* Read only */ + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 8: + msr->idx = HV_X64_MSR_TIME_REF_COUNT; + msr->write = 0; + msr->available = 0; + break; + case 9: + feat.eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 10: + /* Read only */ + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 11: + msr->idx = HV_X64_MSR_VP_INDEX; + msr->write = 0; + msr->available = 0; + break; + case 12: + feat.eax |= HV_MSR_VP_INDEX_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 13: + /* Read only */ + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 14: + msr->idx = HV_X64_MSR_RESET; + msr->write = 0; + msr->available = 0; + break; + case 15: + feat.eax |= HV_MSR_RESET_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 16: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + + case 17: + msr->idx = HV_X64_MSR_REFERENCE_TSC; + msr->write = 0; + msr->available = 0; + break; + case 18: + feat.eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 19: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + + case 20: + msr->idx = HV_X64_MSR_EOM; + msr->write = 0; + msr->available = 0; + break; + case 21: + /* + * Remains unavailable even with KVM_CAP_HYPERV_SYNIC2 + * capability enabled and guest visible CPUID bit unset. + */ + cap.cap = KVM_CAP_HYPERV_SYNIC2; + vcpu_enable_cap(vm, VCPU_ID, &cap); + break; + case 22: + feat.eax |= HV_MSR_SYNIC_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 23: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + + case 24: + msr->idx = HV_X64_MSR_STIMER0_CONFIG; + msr->write = 0; + msr->available = 0; + break; + case 25: + feat.eax |= HV_MSR_SYNTIMER_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 26: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + case 27: + /* Direct mode test */ + msr->write = 1; + msr->write_val = 1 << 12; + msr->available = 0; + break; + case 28: + feat.edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + msr->available = 1; + break; + + case 29: + msr->idx = HV_X64_MSR_EOI; + msr->write = 0; + msr->available = 0; + break; + case 30: + feat.eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + msr->write = 1; + msr->write_val = 1; + msr->available = 1; + break; + + case 31: + msr->idx = HV_X64_MSR_TSC_FREQUENCY; + msr->write = 0; + msr->available = 0; + break; + case 32: + feat.eax |= HV_ACCESS_FREQUENCY_MSRS; + msr->write = 0; + msr->available = 1; + break; + case 33: + /* Read only */ + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 34: + msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; + msr->write = 0; + msr->available = 0; + break; + case 35: + feat.eax |= HV_ACCESS_REENLIGHTENMENT; + msr->write = 0; + msr->available = 1; + break; + case 36: + msr->write = 1; + msr->write_val = 1; + msr->available = 1; + break; + case 37: + /* Can only write '0' */ + msr->idx = HV_X64_MSR_TSC_EMULATION_STATUS; + msr->write = 1; + msr->write_val = 1; + msr->available = 0; + break; + + case 38: + msr->idx = HV_X64_MSR_CRASH_P0; + msr->write = 0; + msr->available = 0; + break; + case 39: + feat.edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + msr->write = 0; + msr->available = 1; + break; + case 40: + msr->write = 1; + msr->write_val = 1; + msr->available = 1; + break; + + case 41: + msr->idx = HV_X64_MSR_SYNDBG_STATUS; + msr->write = 0; + msr->available = 0; + break; + case 42: + feat.edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; + dbg.eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + msr->write = 0; + msr->available = 1; + break; + case 43: + msr->write = 1; + msr->write_val = 0; + msr->available = 1; + break; + + case 44: + /* END */ + msr->idx = 0; + break; + } + + hv_set_cpuid(vm, best, &feat, &recomm, &dbg); + + if (msr->idx) + pr_debug("Stage %d: testing msr: 0x%x for %s\n", stage, + msr->idx, msr->write ? "write" : "read"); + else + pr_debug("Stage %d: finish\n", stage); + + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + TEST_ASSERT(uc.args[1] == stage, + "Unexpected stage: %ld (%d expected)\n", + uc.args[1], stage); + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + return; + case UCALL_DONE: + return; + } + + stage++; + } +} + +static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall, + void *input, void *output, struct kvm_cpuid2 *best) +{ + struct kvm_run *run; + struct ucall uc; + int stage = 0, r; + struct kvm_cpuid_entry2 feat = { + .function = HYPERV_CPUID_FEATURES, + .eax = HV_MSR_HYPERCALL_AVAILABLE + }; + struct kvm_cpuid_entry2 recomm = { + .function = HYPERV_CPUID_ENLIGHTMENT_INFO + }; + struct kvm_cpuid_entry2 dbg = { + .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES + }; + + run = vcpu_state(vm, VCPU_ID); + + while (true) { + switch (stage) { + case 0: + hcall->control = 0xdeadbeef; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + + case 1: + hcall->control = HVCALL_POST_MESSAGE; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 2: + feat.ebx |= HV_POST_MESSAGES; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + + case 3: + hcall->control = HVCALL_SIGNAL_EVENT; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 4: + feat.ebx |= HV_SIGNAL_EVENTS; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + + case 5: + hcall->control = HVCALL_RESET_DEBUG_SESSION; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + case 6: + dbg.eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 7: + feat.ebx |= HV_DEBUGGING; + hcall->expect = HV_STATUS_OPERATION_DENIED; + break; + + case 8: + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 9: + recomm.eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + hcall->expect = HV_STATUS_SUCCESS; + break; + case 10: + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 11: + recomm.eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + hcall->expect = HV_STATUS_SUCCESS; + break; + + case 12: + hcall->control = HVCALL_SEND_IPI; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 13: + recomm.eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + case 14: + /* Nothing in 'sparse banks' -> success */ + hcall->control = HVCALL_SEND_IPI_EX; + hcall->expect = HV_STATUS_SUCCESS; + break; + + case 15: + hcall->control = HVCALL_NOTIFY_LONG_SPIN_WAIT; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 16: + recomm.ebx = 0xfff; + hcall->expect = HV_STATUS_SUCCESS; + break; + + case 17: + /* END */ + hcall->control = 0; + break; + } + + hv_set_cpuid(vm, best, &feat, &recomm, &dbg); + + if (hcall->control) + pr_debug("Stage %d: testing hcall: 0x%lx\n", stage, + hcall->control); + else + pr_debug("Stage %d: finish\n", stage); + + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + TEST_ASSERT(uc.args[1] == stage, + "Unexpected stage: %ld (%d expected)\n", + uc.args[1], stage); + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + return; + case UCALL_DONE: + return; + } + + stage++; + } +} + +int main(void) +{ + struct kvm_cpuid2 *best; + struct kvm_vm *vm; + vm_vaddr_t msr_gva, hcall_page, hcall_params; + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + + /* Test MSRs */ + vm = vm_create_default(VCPU_ID, 0, guest_msr); + + msr_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); + vcpu_args_set(vm, VCPU_ID, 1, msr_gva); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + + pr_info("Testing access to Hyper-V specific MSRs\n"); + guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva), + best); + kvm_vm_free(vm); + + /* Test hypercalls */ + vm = vm_create_default(VCPU_ID, 0, guest_hcall); + + /* Hypercall input/output */ + hcall_page = vm_vaddr_alloc(vm, 2 * getpagesize(), 0x10000, 0, 0); + memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); + + hcall_params = vm_vaddr_alloc(vm, getpagesize(), 0x20000, 0, 0); + memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize()); + + vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + pr_info("Testing access to Hyper-V hypercalls\n"); + guest_test_hcalls_access(vm, addr_gva2hva(vm, hcall_params), + addr_gva2hva(vm, hcall_page), + addr_gva2hva(vm, hcall_page) + getpagesize(), + best); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c index 12c558fc8074..5f8dd74d415f 100644 --- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c +++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c @@ -14,16 +14,12 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "apic.h" #define N_VCPU 2 #define VCPU_ID0 0 #define VCPU_ID1 1 -static uint32_t get_bsp_flag(void) -{ - return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP; -} - static void guest_bsp_vcpu(void *arg) { GUEST_SYNC(1); diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index 613c42c5a9b8..c1f831803ad2 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -55,8 +55,8 @@ static inline void sync_with_host(uint64_t phase) void self_smi(void) { - wrmsr(APIC_BASE_MSR + (APIC_ICR >> 4), - APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI); + x2apic_write_reg(APIC_ICR, + APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI); } void guest_code(void *arg) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c new file mode 100644 index 000000000000..280c01fd2412 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vmx_nested_tsc_scaling_test + * + * Copyright 2021 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * This test case verifies that nested TSC scaling behaves as expected when + * both L1 and L2 are scaled using different ratios. For this test we scale + * L1 down and scale L2 up. + */ + +#include <time.h> + +#include "kvm_util.h" +#include "vmx.h" +#include "kselftest.h" + + +#define VCPU_ID 0 + +/* L2 is scaled up (from L1's perspective) by this factor */ +#define L2_SCALE_FACTOR 4ULL + +#define TSC_OFFSET_L2 ((uint64_t) -33125236320908) +#define TSC_MULTIPLIER_L2 (L2_SCALE_FACTOR << 48) + +#define L2_GUEST_STACK_SIZE 64 + +enum { USLEEP, UCHECK_L1, UCHECK_L2 }; +#define GUEST_SLEEP(sec) ucall(UCALL_SYNC, 2, USLEEP, sec) +#define GUEST_CHECK(level, freq) ucall(UCALL_SYNC, 2, level, freq) + + +/* + * This function checks whether the "actual" TSC frequency of a guest matches + * its expected frequency. In order to account for delays in taking the TSC + * measurements, a difference of 1% between the actual and the expected value + * is tolerated. + */ +static void compare_tsc_freq(uint64_t actual, uint64_t expected) +{ + uint64_t tolerance, thresh_low, thresh_high; + + tolerance = expected / 100; + thresh_low = expected - tolerance; + thresh_high = expected + tolerance; + + TEST_ASSERT(thresh_low < actual, + "TSC freq is expected to be between %"PRIu64" and %"PRIu64 + " but it actually is %"PRIu64, + thresh_low, thresh_high, actual); + TEST_ASSERT(thresh_high > actual, + "TSC freq is expected to be between %"PRIu64" and %"PRIu64 + " but it actually is %"PRIu64, + thresh_low, thresh_high, actual); +} + +static void check_tsc_freq(int level) +{ + uint64_t tsc_start, tsc_end, tsc_freq; + + /* + * Reading the TSC twice with about a second's difference should give + * us an approximation of the TSC frequency from the guest's + * perspective. Now, this won't be completely accurate, but it should + * be good enough for the purposes of this test. + */ + tsc_start = rdmsr(MSR_IA32_TSC); + GUEST_SLEEP(1); + tsc_end = rdmsr(MSR_IA32_TSC); + + tsc_freq = tsc_end - tsc_start; + + GUEST_CHECK(level, tsc_freq); +} + +static void l2_guest_code(void) +{ + check_tsc_freq(UCHECK_L2); + + /* exit to L1 */ + __asm__ __volatile__("vmcall"); +} + +static void l1_guest_code(struct vmx_pages *vmx_pages) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + uint32_t control; + + /* check that L1's frequency looks alright before launching L2 */ + check_tsc_freq(UCHECK_L1); + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + + /* prepare the VMCS for L2 execution */ + prepare_vmcs(vmx_pages, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* enable TSC offsetting and TSC scaling for L2 */ + control = vmreadz(CPU_BASED_VM_EXEC_CONTROL); + control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING; + vmwrite(CPU_BASED_VM_EXEC_CONTROL, control); + + control = vmreadz(SECONDARY_VM_EXEC_CONTROL); + control |= SECONDARY_EXEC_TSC_SCALING; + vmwrite(SECONDARY_VM_EXEC_CONTROL, control); + + vmwrite(TSC_OFFSET, TSC_OFFSET_L2); + vmwrite(TSC_MULTIPLIER, TSC_MULTIPLIER_L2); + vmwrite(TSC_MULTIPLIER_HIGH, TSC_MULTIPLIER_L2 >> 32); + + /* launch L2 */ + GUEST_ASSERT(!vmlaunch()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + + /* check that L1's frequency still looks good */ + check_tsc_freq(UCHECK_L1); + + GUEST_DONE(); +} + +static void tsc_scaling_check_supported(void) +{ + if (!kvm_check_cap(KVM_CAP_TSC_CONTROL)) { + print_skip("TSC scaling not supported by the HW"); + exit(KSFT_SKIP); + } +} + +static void stable_tsc_check_supported(void) +{ + FILE *fp; + char buf[4]; + + fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r"); + if (fp == NULL) + goto skip_test; + + if (fgets(buf, sizeof(buf), fp) == NULL) + goto skip_test; + + if (strncmp(buf, "tsc", sizeof(buf))) + goto skip_test; + + return; +skip_test: + print_skip("Kernel does not use TSC clocksource - assuming that host TSC is not stable"); + exit(KSFT_SKIP); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + vm_vaddr_t vmx_pages_gva; + + uint64_t tsc_start, tsc_end; + uint64_t tsc_khz; + uint64_t l1_scale_factor; + uint64_t l0_tsc_freq = 0; + uint64_t l1_tsc_freq = 0; + uint64_t l2_tsc_freq = 0; + + nested_vmx_check_supported(); + tsc_scaling_check_supported(); + stable_tsc_check_supported(); + + /* + * We set L1's scale factor to be a random number from 2 to 10. + * Ideally we would do the same for L2's factor but that one is + * referenced by both main() and l1_guest_code() and using a global + * variable does not work. + */ + srand(time(NULL)); + l1_scale_factor = (rand() % 9) + 2; + printf("L1's scale down factor is: %"PRIu64"\n", l1_scale_factor); + printf("L2's scale up factor is: %llu\n", L2_SCALE_FACTOR); + + tsc_start = rdtsc(); + sleep(1); + tsc_end = rdtsc(); + + l0_tsc_freq = tsc_end - tsc_start; + printf("real TSC frequency is around: %"PRIu64"\n", l0_tsc_freq); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + + tsc_khz = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_TSC_KHZ, NULL); + TEST_ASSERT(tsc_khz != -1, "vcpu ioctl KVM_GET_TSC_KHZ failed"); + + /* scale down L1's TSC frequency */ + vcpu_ioctl(vm, VCPU_ID, KVM_SET_TSC_KHZ, + (void *) (tsc_khz / l1_scale_factor)); + + for (;;) { + volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s", (const char *) uc.args[0]); + case UCALL_SYNC: + switch (uc.args[0]) { + case USLEEP: + sleep(uc.args[1]); + break; + case UCHECK_L1: + l1_tsc_freq = uc.args[1]; + printf("L1's TSC frequency is around: %"PRIu64 + "\n", l1_tsc_freq); + + compare_tsc_freq(l1_tsc_freq, + l0_tsc_freq / l1_scale_factor); + break; + case UCHECK_L2: + l2_tsc_freq = uc.args[1]; + printf("L2's TSC frequency is around: %"PRIu64 + "\n", l2_tsc_freq); + + compare_tsc_freq(l2_tsc_freq, + l1_tsc_freq * L2_SCALE_FACTOR); + break; + } + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c index 2f964cdc273c..21b22718a9db 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c @@ -42,8 +42,6 @@ #define HALTER_VCPU_ID 0 #define SENDER_VCPU_ID 1 -volatile uint32_t *apic_base = (volatile uint32_t *)APIC_DEFAULT_GPA; - /* * Vector for IPI from sender vCPU to halting vCPU. * Value is arbitrary and was chosen for the alternating bit pattern. Any @@ -86,45 +84,6 @@ struct thread_params { uint64_t *pipis_rcvd; /* host address of ipis_rcvd global */ }; -uint32_t read_apic_reg(uint reg) -{ - return apic_base[reg >> 2]; -} - -void write_apic_reg(uint reg, uint32_t val) -{ - apic_base[reg >> 2] = val; -} - -void disable_apic(void) -{ - wrmsr(MSR_IA32_APICBASE, - rdmsr(MSR_IA32_APICBASE) & - ~(MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD)); -} - -void enable_xapic(void) -{ - uint64_t val = rdmsr(MSR_IA32_APICBASE); - - /* Per SDM: to enable xAPIC when in x2APIC must first disable APIC */ - if (val & MSR_IA32_APICBASE_EXTD) { - disable_apic(); - wrmsr(MSR_IA32_APICBASE, - rdmsr(MSR_IA32_APICBASE) | MSR_IA32_APICBASE_ENABLE); - } else if (!(val & MSR_IA32_APICBASE_ENABLE)) { - wrmsr(MSR_IA32_APICBASE, val | MSR_IA32_APICBASE_ENABLE); - } - - /* - * Per SDM: reset value of spurious interrupt vector register has the - * APIC software enabled bit=0. It must be enabled in addition to the - * enable bit in the MSR. - */ - val = read_apic_reg(APIC_SPIV) | APIC_SPIV_APIC_ENABLED; - write_apic_reg(APIC_SPIV, val); -} - void verify_apic_base_addr(void) { uint64_t msr = rdmsr(MSR_IA32_APICBASE); @@ -136,10 +95,10 @@ void verify_apic_base_addr(void) static void halter_guest_code(struct test_data_page *data) { verify_apic_base_addr(); - enable_xapic(); + xapic_enable(); - data->halter_apic_id = GET_APIC_ID_FIELD(read_apic_reg(APIC_ID)); - data->halter_lvr = read_apic_reg(APIC_LVR); + data->halter_apic_id = GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID)); + data->halter_lvr = xapic_read_reg(APIC_LVR); /* * Loop forever HLTing and recording halts & wakes. Disable interrupts @@ -150,8 +109,8 @@ static void halter_guest_code(struct test_data_page *data) * TPR and PPR for diagnostic purposes in case the test fails. */ for (;;) { - data->halter_tpr = read_apic_reg(APIC_TASKPRI); - data->halter_ppr = read_apic_reg(APIC_PROCPRI); + data->halter_tpr = xapic_read_reg(APIC_TASKPRI); + data->halter_ppr = xapic_read_reg(APIC_PROCPRI); data->hlt_count++; asm volatile("sti; hlt; cli"); data->wake_count++; @@ -166,7 +125,7 @@ static void halter_guest_code(struct test_data_page *data) static void guest_ipi_handler(struct ex_regs *regs) { ipis_rcvd++; - write_apic_reg(APIC_EOI, 77); + xapic_write_reg(APIC_EOI, 77); } static void sender_guest_code(struct test_data_page *data) @@ -179,7 +138,7 @@ static void sender_guest_code(struct test_data_page *data) uint64_t tsc_start; verify_apic_base_addr(); - enable_xapic(); + xapic_enable(); /* * Init interrupt command register for sending IPIs @@ -206,8 +165,8 @@ static void sender_guest_code(struct test_data_page *data) * First IPI can be sent unconditionally because halter vCPU * starts earlier. */ - write_apic_reg(APIC_ICR2, icr2_val); - write_apic_reg(APIC_ICR, icr_val); + xapic_write_reg(APIC_ICR2, icr2_val); + xapic_write_reg(APIC_ICR, icr_val); data->ipis_sent++; /* diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 1c37ccd5d402..62b39149b8c8 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -63,3 +63,6 @@ config HAVE_KVM_NO_POLL config KVM_XFER_TO_GUEST_WORK bool + +config HAVE_KVM_PM_NOTIFIER + bool diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6b4feb92dc79..ed4d1581d502 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -51,6 +51,7 @@ #include <linux/io.h> #include <linux/lockdep.h> #include <linux/kthread.h> +#include <linux/suspend.h> #include <asm/processor.h> #include <asm/ioctl.h> @@ -307,6 +308,7 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { return kvm_make_all_cpus_request_except(kvm, req, NULL); } +EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) @@ -779,6 +781,38 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +static int kvm_pm_notifier_call(struct notifier_block *bl, + unsigned long state, + void *unused) +{ + struct kvm *kvm = container_of(bl, struct kvm, pm_notifier); + + return kvm_arch_pm_notifier(kvm, state); +} + +static void kvm_init_pm_notifier(struct kvm *kvm) +{ + kvm->pm_notifier.notifier_call = kvm_pm_notifier_call; + /* Suspend KVM before we suspend ftrace, RCU, etc. */ + kvm->pm_notifier.priority = INT_MAX; + register_pm_notifier(&kvm->pm_notifier); +} + +static void kvm_destroy_pm_notifier(struct kvm *kvm) +{ + unregister_pm_notifier(&kvm->pm_notifier); +} +#else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */ +static void kvm_init_pm_notifier(struct kvm *kvm) +{ +} + +static void kvm_destroy_pm_notifier(struct kvm *kvm) +{ +} +#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ + static struct kvm_memslots *kvm_alloc_memslots(void) { int i; @@ -908,6 +942,7 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); + mutex_init(&kvm->slots_arch_lock); INIT_LIST_HEAD(&kvm->devices); BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); @@ -962,6 +997,7 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_unlock(&kvm_lock); preempt_notifier_inc(); + kvm_init_pm_notifier(kvm); return kvm; @@ -1009,6 +1045,7 @@ static void kvm_destroy_vm(struct kvm *kvm) int i; struct mm_struct *mm = kvm->mm; + kvm_destroy_pm_notifier(kvm); kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm); kvm_destroy_vm_debugfs(kvm); kvm_arch_sync_events(kvm); @@ -1280,6 +1317,14 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; rcu_assign_pointer(kvm->memslots[as_id], slots); + + /* + * Acquired in kvm_set_memslot. Must be released before synchronize + * SRCU below in order to avoid deadlock with another thread + * acquiring the slots_arch_lock in an srcu critical section. + */ + mutex_unlock(&kvm->slots_arch_lock); + synchronize_srcu_expedited(&kvm->srcu); /* @@ -1306,6 +1351,18 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, return old_memslots; } +static size_t kvm_memslots_size(int slots) +{ + return sizeof(struct kvm_memslots) + + (sizeof(struct kvm_memory_slot) * slots); +} + +static void kvm_copy_memslots(struct kvm_memslots *to, + struct kvm_memslots *from) +{ + memcpy(to, from, kvm_memslots_size(from->used_slots)); +} + /* * Note, at a minimum, the current number of used slots must be allocated, even * when deleting a memslot, as we need a complete duplicate of the memslots for @@ -1315,19 +1372,16 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, enum kvm_mr_change change) { struct kvm_memslots *slots; - size_t old_size, new_size; - - old_size = sizeof(struct kvm_memslots) + - (sizeof(struct kvm_memory_slot) * old->used_slots); + size_t new_size; if (change == KVM_MR_CREATE) - new_size = old_size + sizeof(struct kvm_memory_slot); + new_size = kvm_memslots_size(old->used_slots + 1); else - new_size = old_size; + new_size = kvm_memslots_size(old->used_slots); slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT); if (likely(slots)) - memcpy(slots, old, old_size); + kvm_copy_memslots(slots, old); return slots; } @@ -1342,9 +1396,27 @@ static int kvm_set_memslot(struct kvm *kvm, struct kvm_memslots *slots; int r; + /* + * Released in install_new_memslots. + * + * Must be held from before the current memslots are copied until + * after the new memslots are installed with rcu_assign_pointer, + * then released before the synchronize srcu in install_new_memslots. + * + * When modifying memslots outside of the slots_lock, must be held + * before reading the pointer to the current memslots until after all + * changes to those memslots are complete. + * + * These rules ensure that installing new memslots does not lose + * changes made to the previous memslots. + */ + mutex_lock(&kvm->slots_arch_lock); + slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change); - if (!slots) + if (!slots) { + mutex_unlock(&kvm->slots_arch_lock); return -ENOMEM; + } if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { /* @@ -1355,10 +1427,9 @@ static int kvm_set_memslot(struct kvm *kvm, slot->flags |= KVM_MEMSLOT_INVALID; /* - * We can re-use the old memslots, the only difference from the - * newly installed memslots is the invalid flag, which will get - * dropped by update_memslots anyway. We'll also revert to the - * old memslots if preparing the new memory region fails. + * We can re-use the memory from the old memslots. + * It will be overwritten with a copy of the new memslots + * after reacquiring the slots_arch_lock below. */ slots = install_new_memslots(kvm, as_id, slots); @@ -1370,6 +1441,17 @@ static int kvm_set_memslot(struct kvm *kvm, * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, slot); + + /* Released in install_new_memslots. */ + mutex_lock(&kvm->slots_arch_lock); + + /* + * The arch-specific fields of the memslots could have changed + * between releasing the slots_arch_lock in + * install_new_memslots and here, so get a fresh copy of the + * slots. + */ + kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id)); } r = kvm_arch_prepare_memory_region(kvm, new, mem, change); @@ -1385,8 +1467,13 @@ static int kvm_set_memslot(struct kvm *kvm, return 0; out_slots: - if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { + slot = id_to_memslot(slots, old->id); + slot->flags &= ~KVM_MEMSLOT_INVALID; slots = install_new_memslots(kvm, as_id, slots); + } else { + mutex_unlock(&kvm->slots_arch_lock); + } kvfree(slots); return r; } @@ -2929,6 +3016,8 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) goto out; if (signal_pending(current)) goto out; + if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) + goto out; ret = 0; out: @@ -2973,8 +3062,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) goto out; } poll_end = cur = ktime_get(); - } while (single_task_running() && !need_resched() && - ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); } prepare_to_rcuwait(&vcpu->wait); @@ -4745,14 +4833,14 @@ static int kvm_debugfs_release(struct inode *inode, struct file *file) static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val) { - *val = *(ulong *)((void *)kvm + offset); + *val = *(u64 *)((void *)kvm + offset); return 0; } static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) { - *(ulong *)((void *)kvm + offset) = 0; + *(u64 *)((void *)kvm + offset) = 0; return 0; } diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c index c9bb3957f58a..28fda42e471b 100644 --- a/virt/lib/irqbypass.c +++ b/virt/lib/irqbypass.c @@ -40,21 +40,17 @@ static int __connect(struct irq_bypass_producer *prod, if (prod->add_consumer) ret = prod->add_consumer(prod, cons); - if (ret) - goto err_add_consumer; - - ret = cons->add_producer(cons, prod); - if (ret) - goto err_add_producer; + if (!ret) { + ret = cons->add_producer(cons, prod); + if (ret && prod->del_consumer) + prod->del_consumer(prod, cons); + } if (cons->start) cons->start(cons); if (prod->start) prod->start(prod); -err_add_producer: - if (prod->del_consumer) - prod->del_consumer(prod, cons); -err_add_consumer: + return ret; } |