diff options
| author | Zhang Haoyu <zhanghy@sangfor.com> | 2014-09-11 08:47:04 (GMT) |
|---|---|---|
| committer | Paolo Bonzini <pbonzini@redhat.com> | 2014-09-16 12:44:48 (GMT) |
| commit | 184564efae4d775225c8fe3b762a56956fb1f827 (patch) | |
| tree | ce6630689fb883ec69b5c18e299b638c4b1b9454 /include/trace/events | |
| parent | 105b21bbf67bb50000a0dc4b547a2f99b6376136 (diff) | |
| download | linux-184564efae4d775225c8fe3b762a56956fb1f827.tar.xz | |
kvm: ioapic: conditionally delay irq delivery duringeoi broadcast
Currently, we call ioapic_service() immediately when we find the irq is still
active during eoi broadcast. But for real hardware, there's some delay between
the EOI writing and irq delivery. If we do not emulate this behavior, and
re-inject the interrupt immediately after the guest sends an EOI and re-enables
interrupts, a guest might spend all its time in the ISR if it has a broken
handler for a level-triggered interrupt.
Such livelock actually happens with Windows guests when resuming from
hibernation.
As there's no way to recognize the broken handle from new raised ones, this patch
delays an interrupt if 10.000 consecutive EOIs found that the interrupt was
still high. The guest can then make a little forward progress, until a proper
IRQ handler is set or until some detection routine in the guest (such as
Linux's note_interrupt()) recognizes the situation.
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Zhang Haoyu <zhanghy@sangfor.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'include/trace/events')
| -rw-r--r-- | include/trace/events/kvm.h | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 908925a..ab679c3 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -95,6 +95,26 @@ TRACE_EVENT(kvm_ioapic_set_irq, __entry->coalesced ? " (coalesced)" : "") ); +TRACE_EVENT(kvm_ioapic_delayed_eoi_inj, + TP_PROTO(__u64 e), + TP_ARGS(e), + + TP_STRUCT__entry( + __field( __u64, e ) + ), + + TP_fast_assign( + __entry->e = e; + ), + + TP_printk("dst %x vec=%u (%s|%s|%s%s)", + (u8)(__entry->e >> 56), (u8)__entry->e, + __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode), + (__entry->e & (1<<11)) ? "logical" : "physical", + (__entry->e & (1<<15)) ? "level" : "edge", + (__entry->e & (1<<16)) ? "|masked" : "") +); + TRACE_EVENT(kvm_msi_set_irq, TP_PROTO(__u64 address, __u64 data), TP_ARGS(address, data), |