From 127770ac0d043435375ab86434f31a93efa88215 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Mon, 14 Feb 2022 21:29:51 +0000 Subject: KVM: x86: Add KVM_CAP_ENABLE_CAP to x86 Follow the precedent set by other architectures that support the VCPU ioctl, KVM_ENABLE_CAP, and advertise the VM extension, KVM_CAP_ENABLE_CAP. This way, userspace can ensure that KVM_ENABLE_CAP is available on a vcpu before using it. Fixes: 5c919412fe61 ("kvm/x86: Hyper-V synthetic interrupt controller") Signed-off-by: Aaron Lewis Message-Id: <20220214212950.1776943-1-aaronlewis@google.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kvm/x86.c') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 641044db415d..b8bd8da32045 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4233,6 +4233,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_SYS_ATTRIBUTES: + case KVM_CAP_ENABLE_CAP: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: -- cgit v1.2.3 From 3a55f729240a686aa8af00af436306c0cd532522 Mon Sep 17 00:00:00 2001 From: Anton Romanov Date: Wed, 16 Feb 2022 18:26:54 +0000 Subject: kvm: x86: Disable KVM_HC_CLOCK_PAIRING if tsc is in always catchup mode If vcpu has tsc_always_catchup set each request updates pvclock data. KVM_HC_CLOCK_PAIRING consumers such as ptp_kvm_x86 rely on tsc read on host's side and do hypercall inside pvclock_read_retry loop leading to infinite loop in such situation. v3: Removed warn Changed return code to KVM_EFAULT v2: Added warn Signed-off-by: Anton Romanov Message-Id: <20220216182653.506850-1-romanton@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/x86/kvm/x86.c') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b8bd8da32045..3471efe47e5f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8943,6 +8943,13 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; + /* + * When tsc is in permanent catchup mode guests won't be able to use + * pvclock_read_retry loop to get consistent view of pvclock + */ + if (vcpu->arch.tsc_always_catchup) + return -KVM_EOPNOTSUPP; + if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; -- cgit v1.2.3 From 988896bb61827345c6d074dd5f2af1b7b008193f Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Thu, 17 Feb 2022 02:30:30 -0300 Subject: x86/kvm/fpu: Remove kvm_vcpu_arch.guest_supported_xcr0 kvm_vcpu_arch currently contains the guest supported features in both guest_supported_xcr0 and guest_fpu.fpstate->user_xfeatures field. Currently both fields are set to the same value in kvm_vcpu_after_set_cpuid() and are not changed anywhere else after that. Since it's not good to keep duplicated data, remove guest_supported_xcr0. To keep the code more readable, introduce kvm_guest_supported_xcr() and kvm_guest_supported_xfd() to replace the previous usages of guest_supported_xcr0. Signed-off-by: Leonardo Bras Message-Id: <20220217053028.96432-3-leobras@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/cpuid.c | 5 +++-- arch/x86/kvm/x86.c | 18 +++++++++++++----- 3 files changed, 16 insertions(+), 8 deletions(-) (limited to 'arch/x86/kvm/x86.c') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6dcccb304775..ec9830d2aabf 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -703,7 +703,6 @@ struct kvm_vcpu_arch { struct fpu_guest guest_fpu; u64 xcr0; - u64 guest_supported_xcr0; struct kvm_pio_request pio; void *pio_data; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 71125291c578..b8f8d268d058 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -282,6 +282,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; + u64 guest_supported_xcr0; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (best && apic) { @@ -293,10 +294,10 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - vcpu->arch.guest_supported_xcr0 = + guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0; + vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0; kvm_update_pv_runtime(vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3471efe47e5f..20ad6fe391bf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -984,6 +984,16 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); +static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_fpu.fpstate->user_xfeatures; +} + +static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) +{ + return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC; +} + static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; @@ -1003,7 +1013,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ - valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; + valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; @@ -3706,8 +3716,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data); @@ -3717,8 +3726,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; vcpu->arch.guest_fpu.xfd_err = data; -- cgit v1.2.3 From ba1f77c546966c12d86220d078e5838dcaeab348 Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Fri, 18 Feb 2022 00:41:00 -0300 Subject: x86/kvm: Fix compilation warning in non-x86_64 builds On non-x86_64 builds, helpers gtod_is_based_on_tsc() and kvm_guest_supported_xfd() are defined but never used. Because these are static inline but are in a .c file, some compilers do warn for them with -Wunused-function, which becomes an error if -Werror is present. Add #ifdef so they are only defined in x86_64 builds. Reported-by: kernel test robot Signed-off-by: Leonardo Bras Message-Id: <20220218034100.115702-1-leobras@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/x86/kvm/x86.c') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 20ad6fe391bf..82a9dcd8c67f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -989,10 +989,12 @@ static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu) return vcpu->arch.guest_fpu.fpstate->user_xfeatures; } +#ifdef CONFIG_X86_64 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) { return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC; } +#endif static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -2361,10 +2363,12 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } +#ifdef CONFIG_X86_64 static inline int gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } +#endif static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { -- cgit v1.2.3 From 8d25b7beca7ed6ca34f53f0f8abd009e2be15d94 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Sat, 19 Feb 2022 04:28:20 -0500 Subject: KVM: x86: pull kvm->srcu read-side to kvm_arch_vcpu_ioctl_run kvm_arch_vcpu_ioctl_run is already doing srcu_read_lock/unlock in two places, namely vcpu_run and post_kvm_run_save, and a third is actually needed around the call to vcpu->arch.complete_userspace_io to avoid the following splat: WARNING: suspicious RCU usage arch/x86/kvm/pmu.c:190 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by CPU 28/KVM/370841: #0: ff11004089f280b8 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x87/0x730 [kvm] Call Trace: dump_stack_lvl+0x59/0x73 reprogram_fixed_counter+0x15d/0x1a0 [kvm] kvm_pmu_trigger_event+0x1a3/0x260 [kvm] ? free_moved_vector+0x1b4/0x1e0 complete_fast_pio_in+0x8a/0xd0 [kvm] This splat is not at all unexpected, since complete_userspace_io callbacks can execute similar code to vmexits. For example, SVM with nrips=false will call into the emulator from svm_skip_emulated_instruction(). While it's tempting to never acquire kvm->srcu for an uninitialized vCPU, practically speaking there's no penalty to acquiring kvm->srcu "early" as the KVM_MP_STATE_UNINITIALIZED path is a one-time thing per vCPU. On the other hand, seemingly innocuous helpers like kvm_apic_accept_events() and sync_regs() can theoretically reach code that might access SRCU-protected data structures, e.g. sync_regs() can trigger forced existing of nested mode via kvm_vcpu_ioctl_x86_set_vcpu_events(). Reported-by: Like Xu Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'arch/x86/kvm/x86.c') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 82a9dcd8c67f..eb4029660bd9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9180,6 +9180,7 @@ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) likely(!pic_in_kernel(vcpu->kvm)); } +/* Called within kvm->srcu read side. */ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; @@ -9188,16 +9189,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - /* - * The call to kvm_ready_for_interrupt_injection() may end up in - * kvm_xen_has_interrupt() which may require the srcu lock to be - * held, to protect against changes in the vcpu_info address. - */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; @@ -9815,6 +9809,7 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); /* + * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. @@ -10193,6 +10188,7 @@ out: return r; } +/* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { bool hv_timer; @@ -10252,12 +10248,12 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted); } +/* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; struct kvm *kvm = vcpu->kvm; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); vcpu->arch.l1tf_flush_l1d = true; for (;;) { @@ -10285,14 +10281,12 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (__xfer_to_guest_mode_work_pending()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); r = xfer_to_guest_mode_handle_work(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (r) return r; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - return r; } @@ -10398,6 +10392,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; + struct kvm *kvm = vcpu->kvm; int r; vcpu_load(vcpu); @@ -10405,6 +10400,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -10415,7 +10411,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * use before KVM has ever run the vCPU. */ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); + + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (kvm_apic_accept_events(vcpu) < 0) { r = 0; goto out; @@ -10475,8 +10475,9 @@ out: if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); - kvm_sigset_deactivate(vcpu); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); return r; } -- cgit v1.2.3