This is a note to let you know that I've just added the patch titled KVM: x86: Take srcu lock in post_kvm_run_save() to the 5.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: kvm-x86-take-srcu-lock-in-post_kvm_run_save.patch and it can be found in the queue-5.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From f3d1436d4bf8ced1c9a62a045d193a65567e1fcc Mon Sep 17 00:00:00 2001 From: David Woodhouse <dwmw@xxxxxxxxxxxx> Date: Tue, 26 Oct 2021 04:12:38 +0100 Subject: KVM: x86: Take srcu lock in post_kvm_run_save() From: David Woodhouse <dwmw@xxxxxxxxxxxx> commit f3d1436d4bf8ced1c9a62a045d193a65567e1fcc upstream. 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 <dwmw@xxxxxxxxxxxx> Cc: stable@xxxxxxxxxxxxxxx Message-Id: <606aaaf29fca3850a63aa4499826104e77a72346.camel@xxxxxxxxxxxxx> Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- arch/x86/kvm/x86.c | 8 ++++++++ 1 file changed, 8 insertions(+) --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8799,9 +8799,17 @@ static void post_kvm_run_save(struct kvm 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; Patches currently in stable-queue which might be from dwmw@xxxxxxxxxxxx are queue-5.14/kvm-x86-take-srcu-lock-in-post_kvm_run_save.patch queue-5.14/kvm-x86-switch-pvclock_gtod_sync_lock-to-a-raw-spinlock.patch queue-5.14/kvm-x86-xen-fix-kvm_xen_has_interrupt-sleeping-in-kvm_vcpu_block.patch