From 9b57e9d5010bbed7c0d9d445085840f7025e6f9a Mon Sep 17 00:00:00 2001 From: Halil Pasic Date: Tue, 19 Oct 2021 19:53:59 +0200 Subject: [PATCH 1/6] KVM: s390: clear kicked_mask before sleeping again The idea behind kicked mask is that we should not re-kick a vcpu that is already in the "kick" process, i.e. that was kicked and is is about to be dispatched if certain conditions are met. The problem with the current implementation is, that it assumes the kicked vcpu is going to enter SIE shortly. But under certain circumstances, the vcpu we just kicked will be deemed non-runnable and will remain in wait state. This can happen, if the interrupt(s) this vcpu got kicked to deal with got already cleared (because the interrupts got delivered to another vcpu). In this case kvm_arch_vcpu_runnable() would return false, and the vcpu would remain in kvm_vcpu_block(), but this time with its kicked_mask bit set. So next time around we wouldn't kick the vcpu form __airqs_kick_single_vcpu(), but would assume that we just kicked it. Let us make sure the kicked_mask is cleared before we give up on re-dispatching the vcpu. Fixes: 9f30f6216378 ("KVM: s390: add gib_alert_irq_handler()") Reported-by: Matthew Rosato Signed-off-by: Halil Pasic Reviewed-by: Christian Borntraeger Reviewed-by: Michael Mueller Reviewed-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20211019175401.3757927-2-pasic@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 6a6dd5e1daf6..1c97493d21e1 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3363,6 +3363,7 @@ out_free_sie_block: int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); return kvm_s390_vcpu_has_irq(vcpu, 0); } From 0e9ff65f455dfd0a8aea5e7843678ab6fe097e21 Mon Sep 17 00:00:00 2001 From: Halil Pasic Date: Tue, 19 Oct 2021 19:54:00 +0200 Subject: [PATCH 2/6] KVM: s390: preserve deliverable_mask in __airqs_kick_single_vcpu Changing the deliverable mask in __airqs_kick_single_vcpu() is a bug. If one idle vcpu can't take the interrupts we want to deliver, we should look for another vcpu that can, instead of saying that we don't want to deliver these interrupts by clearing the bits from the deliverable_mask. Fixes: 9f30f6216378 ("KVM: s390: add gib_alert_irq_handler()") Signed-off-by: Halil Pasic Reviewed-by: Christian Borntraeger Reviewed-by: Michael Mueller Reviewed-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20211019175401.3757927-3-pasic@linux.ibm.com Signed-off-by: Christian Borntraeger --- arch/s390/kvm/interrupt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 10722455fd02..2245f4b8d362 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3053,13 +3053,14 @@ static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask) int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus); struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; struct kvm_vcpu *vcpu; + u8 vcpu_isc_mask; for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) { vcpu = kvm_get_vcpu(kvm, vcpu_idx); if (psw_ioint_disabled(vcpu)) continue; - deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24); - if (deliverable_mask) { + vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24); + if (deliverable_mask & vcpu_isc_mask) { /* lately kicked but not yet running */ if (test_and_set_bit(vcpu_idx, gi->kicked_mask)) return; From 8228c77d8b56e3f735baf71fefb1b548c23691a7 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 23 Oct 2021 21:29:22 +0100 Subject: [PATCH 3/6] KVM: x86: switch pvclock_gtod_sync_lock to a raw spinlock On the preemption path when updating a Xen guest's runstate times, this lock is taken inside the scheduler rq->lock, which is a raw spinlock. This was shown in a lockdep warning: [ 89.138354] ============================= [ 89.138356] [ BUG: Invalid wait context ] [ 89.138358] 5.15.0-rc5+ #834 Tainted: G S I E [ 89.138360] ----------------------------- [ 89.138361] xen_shinfo_test/2575 is trying to lock: [ 89.138363] ffffa34a0364efd8 (&kvm->arch.pvclock_gtod_sync_lock){....}-{3:3}, at: get_kvmclock_ns+0x1f/0x130 [kvm] [ 89.138442] other info that might help us debug this: [ 89.138444] context-{5:5} [ 89.138445] 4 locks held by xen_shinfo_test/2575: [ 89.138447] #0: ffff972bdc3b8108 (&vcpu->mutex){+.+.}-{4:4}, at: kvm_vcpu_ioctl+0x77/0x6f0 [kvm] [ 89.138483] #1: ffffa34a03662e90 (&kvm->srcu){....}-{0:0}, at: kvm_arch_vcpu_ioctl_run+0xdc/0x8b0 [kvm] [ 89.138526] #2: ffff97331fdbac98 (&rq->__lock){-.-.}-{2:2}, at: __schedule+0xff/0xbd0 [ 89.138534] #3: ffffa34a03662e90 (&kvm->srcu){....}-{0:0}, at: kvm_arch_vcpu_put+0x26/0x170 [kvm] ... [ 89.138695] get_kvmclock_ns+0x1f/0x130 [kvm] [ 89.138734] kvm_xen_update_runstate+0x14/0x90 [kvm] [ 89.138783] kvm_xen_update_runstate_guest+0x15/0xd0 [kvm] [ 89.138830] kvm_arch_vcpu_put+0xe6/0x170 [kvm] [ 89.138870] kvm_sched_out+0x2f/0x40 [kvm] [ 89.138900] __schedule+0x5de/0xbd0 Cc: stable@vger.kernel.org Reported-by: syzbot+b282b65c2c68492df769@syzkaller.appspotmail.com Fixes: 30b5c851af79 ("KVM: x86/xen: Add support for vCPU runstate information") Signed-off-by: David Woodhouse Message-Id: <1b02a06421c17993df337493a68ba923f3bd5c0f.camel@infradead.org> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/x86.c | 28 ++++++++++++++-------------- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8f48a7ec577..70771376e246 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1097,7 +1097,7 @@ struct kvm_arch { u64 cur_tsc_generation; int nr_vcpus_matched_tsc; - spinlock_t pvclock_gtod_sync_lock; + raw_spinlock_t pvclock_gtod_sync_lock; bool use_master_clock; u64 master_kernel_ns; u64 master_cycle_now; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0c8b5129effd..5c82eff19e4a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2542,7 +2542,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) kvm_vcpu_write_tsc_offset(vcpu, offset); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); - spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags); if (!matched) { kvm->arch.nr_vcpus_matched_tsc = 0; } else if (!already_matched) { @@ -2550,7 +2550,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) } kvm_track_tsc_matching(vcpu); - spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags); } static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, @@ -2780,9 +2780,9 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) kvm_make_mclock_inprogress_request(kvm); /* no guest entries from this point */ - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -2800,15 +2800,15 @@ u64 get_kvmclock_ns(struct kvm *kvm) unsigned long flags; u64 ret; - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); if (!ka->use_master_clock) { - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); return get_kvmclock_base_ns() + ka->kvmclock_offset; } hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); @@ -2902,13 +2902,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); use_master_clock = ka->use_master_clock; if (use_master_clock) { host_tsc = ka->master_cycle_now; kernel_ns = ka->master_kernel_ns; } - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); @@ -6100,13 +6100,13 @@ set_pit2_out: * is slightly ahead) here we risk going negative on unsigned * 'system_time' when 'user_ns.clock' is very small. */ - spin_lock_irq(&ka->pvclock_gtod_sync_lock); + raw_spin_lock_irq(&ka->pvclock_gtod_sync_lock); if (kvm->arch.use_master_clock) now_ns = ka->master_kernel_ns; else now_ns = get_kvmclock_base_ns(); ka->kvmclock_offset = user_ns.clock - now_ns; - spin_unlock_irq(&ka->pvclock_gtod_sync_lock); + raw_spin_unlock_irq(&ka->pvclock_gtod_sync_lock); kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); break; @@ -8139,9 +8139,9 @@ static void kvm_hyperv_tsc_notifier(void) list_for_each_entry(kvm, &vm_list, vm_list) { struct kvm_arch *ka = &kvm->arch; - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -11182,7 +11182,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) raw_spin_lock_init(&kvm->arch.tsc_write_lock); mutex_init(&kvm->arch.apic_map_lock); - spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); + raw_spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); kvm->arch.kvmclock_offset = -get_kvmclock_base_ns(); pvclock_update_vm_gtod_copy(kvm); From 0985dba842eaa391858972cfe2724c3c174a2827 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 23 Oct 2021 20:47:19 +0100 Subject: [PATCH 4/6] KVM: x86/xen: Fix kvm_xen_has_interrupt() sleeping in kvm_vcpu_block() In kvm_vcpu_block, the current task is set to TASK_INTERRUPTIBLE before making a final check whether the vCPU should be woken from HLT by any incoming interrupt. This is a problem for the get_user() in __kvm_xen_has_interrupt(), which really shouldn't be sleeping when the task state has already been set. I think it's actually harmless as it would just manifest itself as a spurious wakeup, but it's causing a debug warning: [ 230.963649] do not call blocking ops when !TASK_RUNNING; state=1 set at [<00000000b6bcdbc9>] prepare_to_swait_exclusive+0x30/0x80 Fix the warning by turning it into an *explicit* spurious wakeup. When invoked with !task_is_running(current) (and we might as well add in_atomic() there while we're at it), just return 1 to indicate that an IRQ is pending, which will cause a wakeup and then something will call it again in a context that *can* sleep so it can fault the page back in. Cc: stable@vger.kernel.org Fixes: 40da8ccd724f ("KVM: x86/xen: Add event channel interrupt vector upcall") Signed-off-by: David Woodhouse Message-Id: <168bf8c689561da904e48e2ff5ae4713eaef9e2d.camel@infradead.org> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/xen.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 9ea9c3dabe37..8f62baebd028 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -190,6 +190,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) int __kvm_xen_has_interrupt(struct kvm_vcpu *v) { + int err; u8 rc = 0; /* @@ -216,13 +217,29 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) if (likely(slots->generation == ghc->generation && !kvm_is_error_hva(ghc->hva) && ghc->memslot)) { /* Fast path */ - __get_user(rc, (u8 __user *)ghc->hva + offset); - } else { - /* Slow path */ - kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, - sizeof(rc)); + pagefault_disable(); + err = __get_user(rc, (u8 __user *)ghc->hva + offset); + pagefault_enable(); + if (!err) + return rc; } + /* Slow path */ + + /* + * This function gets called from kvm_vcpu_block() after setting the + * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately + * from a HLT. So we really mustn't sleep. If the page ended up absent + * at that point, just return 1 in order to trigger an immediate wake, + * and we'll end up getting called again from a context where we *can* + * fault in the page and wait for it. + */ + if (in_atomic() || !task_is_running(current)) + return 1; + + kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, + sizeof(rc)); + return rc; } From 9b0971ca7fc75daca80c0bb6c02e96059daea90a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 25 Oct 2021 12:14:31 -0400 Subject: [PATCH 5/6] KVM: SEV-ES: fix another issue with string I/O VMGEXITs If the guest requests string I/O from the hypervisor via VMGEXIT, SW_EXITINFO2 will contain the REP count. However, sev_es_string_io was incorrectly treating it as the size of the GHCB buffer in bytes. This fixes the "outsw" test in the experimental SEV tests of kvm-unit-tests. Cc: stable@vger.kernel.org Fixes: 7ed9abfe8e9f ("KVM: SVM: Support string IO operations for an SEV-ES guest") Reported-by: Marc Orr Tested-by: Marc Orr Reviewed-by: Marc Orr Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index e672493b5d8d..efd207fd335e 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2579,11 +2579,20 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) { - if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2)) + int count; + int bytes; + + if (svm->vmcb->control.exit_info_2 > INT_MAX) return -EINVAL; - return kvm_sev_es_string_io(&svm->vcpu, size, port, - svm->ghcb_sa, svm->ghcb_sa_len / size, in); + count = svm->vmcb->control.exit_info_2; + if (unlikely(check_mul_overflow(count, size, &bytes))) + return -EINVAL; + + if (!setup_vmgexit_scratch(svm, in, bytes)) + return -EINVAL; + + return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in); } void sev_es_init_vmcb(struct vcpu_svm *svm) From f3d1436d4bf8ced1c9a62a045d193a65567e1fcc Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Tue, 26 Oct 2021 04:12:38 +0100 Subject: [PATCH 6/6] KVM: x86: Take srcu lock in post_kvm_run_save() The Xen interrupt injection for event channels relies on accessing the guest's vcpu_info structure in __kvm_xen_has_interrupt(), through a gfn_to_hva_cache. This requires the srcu lock to be held, which is mostly the case except for this code path: [ 11.822877] WARNING: suspicious RCU usage [ 11.822965] ----------------------------- [ 11.823013] include/linux/kvm_host.h:664 suspicious rcu_dereference_check() usage! [ 11.823131] [ 11.823131] other info that might help us debug this: [ 11.823131] [ 11.823196] [ 11.823196] rcu_scheduler_active = 2, debug_locks = 1 [ 11.823253] 1 lock held by dom:0/90: [ 11.823292] #0: ffff998956ec8118 (&vcpu->mutex){+.+.}, at: kvm_vcpu_ioctl+0x85/0x680 [ 11.823379] [ 11.823379] stack backtrace: [ 11.823428] CPU: 2 PID: 90 Comm: dom:0 Kdump: loaded Not tainted 5.4.34+ #5 [ 11.823496] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 [ 11.823612] Call Trace: [ 11.823645] dump_stack+0x7a/0xa5 [ 11.823681] lockdep_rcu_suspicious+0xc5/0x100 [ 11.823726] __kvm_xen_has_interrupt+0x179/0x190 [ 11.823773] kvm_cpu_has_extint+0x6d/0x90 [ 11.823813] kvm_cpu_accept_dm_intr+0xd/0x40 [ 11.823853] kvm_vcpu_ready_for_interrupt_injection+0x20/0x30 < post_kvm_run_save() inlined here > [ 11.823906] kvm_arch_vcpu_ioctl_run+0x135/0x6a0 [ 11.823947] kvm_vcpu_ioctl+0x263/0x680 Fixes: 40da8ccd724f ("KVM: x86/xen: Add event channel interrupt vector upcall") Signed-off-by: David Woodhouse Cc: stable@vger.kernel.org Message-Id: <606aaaf29fca3850a63aa4499826104e77a72346.camel@infradead.org> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5c82eff19e4a..ffd9dd7d5d14 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8783,9 +8783,17 @@ 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;