x86/vIRQ: IRR and TMR race condition bug fix

In vlapic_set_irq, we set the IRR register before the TMR. And the IRR
might be serviced before setting TMR, and even worse EOI might occur
before TMR setting, in which case the vioapic_update_EOI won't be
called, and further prevent all the subsequent interrupt injecting.
Reorder setting the TMR and IRR will solve the problem.

Besides, KVM has fixed a similar bug in:
http://markmail.org/search/?q=APIC_TMR#query:APIC_TMR+page:1+mid:rphs4f7lkxjlldne+state:results

Signed-off-by: Yongan Liu<Liuyongan@huawei.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Committed-by: Jan Beulich <jbeulich@suse.com>
xen-unstable changeset:   24453:02b92d035f64
xen-unstable date:        Thu Jan 05 09:29:59 2012 +0100

diff --git a/xen/arch/x86/hvm/vlapic.c b/xen/arch/x86/hvm/vlapic.c
index 8b05f1adc394a7bfe97d9abe847c64b3aa6fda52..b4142875ef480c6dd737e69dc3924fb159eb7ee1 100644 (file)
--- a/xen/arch/x86/hvm/vlapic.c
+++ b/xen/arch/x86/hvm/vlapic.c
@@ -142,14 +142,11 @@ static int vlapic_find_highest_irr(struct vlapic *vlapic)
 
 int vlapic_set_irq(struct vlapic *vlapic, uint8_t vec, uint8_t trig)
 {
-    int ret;
-
-    ret = !vlapic_test_and_set_irr(vec, vlapic);
     if ( trig )
         vlapic_set_vector(vec, &vlapic->regs->data[APIC_TMR]);
 
     /* We may need to wake up target vcpu, besides set pending bit here */
-    return ret;
+    return !vlapic_test_and_set_irr(vec, vlapic);
 }
 
 static int vlapic_find_highest_isr(struct vlapic *vlapic)