KVM: Reduce misfirings of the fork detector
The kvm mmu tries to detects forks by looking for repeated writes to a
page table. If it sees a fork, it unshadows the page table so the page
table copying can proceed at native speed instead of being emulated.
However, the detector also triggered on simple demand paging access patterns:
a linear walk of memory would of course cause repeated writes to the same
pagetable page, causing it to unshadow prematurely.
Fix by resetting the fork detector if we detect a demand fault.
Signed-off-by: Avi Kivity <avi@qumranet.com>
diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h
index 73ffbff..bc64cce 100644
--- a/drivers/kvm/paging_tmpl.h
+++ b/drivers/kvm/paging_tmpl.h
@@ -421,6 +421,7 @@
pgprintk("%s: guest page fault\n", __FUNCTION__);
inject_page_fault(vcpu, addr, walker.error_code);
FNAME(release_walker)(&walker);
+ vcpu->last_pt_write_count = 0; /* reset fork detector */
return 0;
}
@@ -442,6 +443,9 @@
FNAME(release_walker)(&walker);
+ if (!write_pt)
+ vcpu->last_pt_write_count = 0; /* reset fork detector */
+
/*
* mmio: emulate if accessible, otherwise its a guest fault.
*/