summaryrefslogtreecommitdiffstats
path: root/virt
diff options
context:
space:
mode:
authorDmytro Maluka <dmy@semihalf.com>2023-03-22 21:43:44 +0100
committerPaolo Bonzini <pbonzini@redhat.com>2023-03-27 10:13:28 -0400
commitfef8f2b90edbd7089a4278021314f11f056b0cbb (patch)
treeb6ebf0f5916614be101792dce9e0ea845fa2da8a /virt
parentd583fbd7066a2dea43050521a95d9770f7d7593e (diff)
downloadlinux-stable-fef8f2b90edbd7089a4278021314f11f056b0cbb.tar.gz
linux-stable-fef8f2b90edbd7089a4278021314f11f056b0cbb.tar.bz2
linux-stable-fef8f2b90edbd7089a4278021314f11f056b0cbb.zip
KVM: x86/ioapic: Resample the pending state of an IRQ when unmasking
KVM irqfd based emulation of level-triggered interrupts doesn't work quite correctly in some cases, particularly in the case of interrupts that are handled in a Linux guest as oneshot interrupts (IRQF_ONESHOT). Such an interrupt is acked to the device in its threaded irq handler, i.e. later than it is acked to the interrupt controller (EOI at the end of hardirq), not earlier. Linux keeps such interrupt masked until its threaded handler finishes, to prevent the EOI from re-asserting an unacknowledged interrupt. However, with KVM + vfio (or whatever is listening on the resamplefd) we always notify resamplefd at the EOI, so vfio prematurely unmasks the host physical IRQ, thus a new physical interrupt is fired in the host. This extra interrupt in the host is not a problem per se. The problem is that it is unconditionally queued for injection into the guest, so the guest sees an extra bogus interrupt. [*] There are observed at least 2 user-visible issues caused by those extra erroneous interrupts for a oneshot irq in the guest: 1. System suspend aborted due to a pending wakeup interrupt from ChromeOS EC (drivers/platform/chrome/cros_ec.c). 2. Annoying "invalid report id data" errors from ELAN0000 touchpad (drivers/input/mouse/elan_i2c_core.c), flooding the guest dmesg every time the touchpad is touched. The core issue here is that by the time when the guest unmasks the IRQ, the physical IRQ line is no longer asserted (since the guest has acked the interrupt to the device in the meantime), yet we unconditionally inject the interrupt queued into the guest by the previous resampling. So to fix the issue, we need a way to detect that the IRQ is no longer pending, and cancel the queued interrupt in this case. With IOAPIC we are not able to probe the physical IRQ line state directly (at least not if the underlying physical interrupt controller is an IOAPIC too), so in this patch we use irqfd resampler for that. Namely, instead of injecting the queued interrupt, we just notify the resampler that this interrupt is done. If the IRQ line is actually already deasserted, we are done. If it is still asserted, a new interrupt will be shortly triggered through irqfd and injected into the guest. In the case if there is no irqfd resampler registered for this IRQ, we cannot fix the issue, so we keep the existing behavior: immediately unconditionally inject the queued interrupt. This patch fixes the issue for x86 IOAPIC only. In the long run, we can fix it for other irqchips and other architectures too, possibly taking advantage of reading the physical state of the IRQ line, which is possible with some other irqchips (e.g. with arm64 GIC, maybe even with the legacy x86 PIC). [*] In this description we assume that the interrupt is a physical host interrupt forwarded to the guest e.g. by vfio. Potentially the same issue may occur also with a purely virtual interrupt from an emulated device, e.g. if the guest handles this interrupt, again, as a oneshot interrupt. Signed-off-by: Dmytro Maluka <dmy@semihalf.com> Link: https://lore.kernel.org/kvm/31420943-8c5f-125c-a5ee-d2fde2700083@semihalf.com/ Link: https://lore.kernel.org/lkml/87o7wrug0w.wl-maz@kernel.org/ Message-Id: <20230322204344.50138-3-dmy@semihalf.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'virt')
-rw-r--r--virt/kvm/eventfd.c41
1 files changed, 35 insertions, 6 deletions
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 61aea70dd888..b0af834ffa95 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -55,6 +55,15 @@ irqfd_inject(struct work_struct *work)
irqfd->gsi, 1, false);
}
+static void irqfd_resampler_notify(struct kvm_kernel_irqfd_resampler *resampler)
+{
+ struct kvm_kernel_irqfd *irqfd;
+
+ list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link,
+ srcu_read_lock_held(&resampler->kvm->irq_srcu))
+ eventfd_signal(irqfd->resamplefd, 1);
+}
+
/*
* Since resampler irqfds share an IRQ source ID, we de-assert once
* then notify all of the resampler irqfds using this GSI. We can't
@@ -65,7 +74,6 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
{
struct kvm_kernel_irqfd_resampler *resampler;
struct kvm *kvm;
- struct kvm_kernel_irqfd *irqfd;
int idx;
resampler = container_of(kian,
@@ -76,11 +84,7 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
resampler->notifier.gsi, 0, false);
idx = srcu_read_lock(&kvm->irq_srcu);
-
- list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link,
- srcu_read_lock_held(&kvm->irq_srcu))
- eventfd_signal(irqfd->resamplefd, 1);
-
+ irqfd_resampler_notify(resampler);
srcu_read_unlock(&kvm->irq_srcu, idx);
}
@@ -648,6 +652,31 @@ void kvm_irq_routing_update(struct kvm *kvm)
spin_unlock_irq(&kvm->irqfds.lock);
}
+bool kvm_notify_irqfd_resampler(struct kvm *kvm,
+ unsigned int irqchip,
+ unsigned int pin)
+{
+ struct kvm_kernel_irqfd_resampler *resampler;
+ int gsi, idx;
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1) {
+ list_for_each_entry_srcu(resampler,
+ &kvm->irqfds.resampler_list, link,
+ srcu_read_lock_held(&kvm->irq_srcu)) {
+ if (resampler->notifier.gsi == gsi) {
+ irqfd_resampler_notify(resampler);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+ return true;
+ }
+ }
+ }
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+
+ return false;
+}
+
/*
* create a host-wide workqueue for issuing deferred shutdown requests
* aggregated from all vm* instances. We need our own isolated