[patch 70/88] KVM: MMU: handle large host sptes on invlpg/resync

[Greg KH]

2.6.28-stable review patch.  If anyone has any objections, please let us know.

------------------


(cherry picked from 87917239204d67a316cb89751750f86c9ed3640b)

The invlpg and sync walkers lack knowledge of large host sptes,
descending to non-existant pagetable level.

Stop at directory level in such case.

Fixes SMP Windows XP with hugepages.

Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
Signed-off-by: Avi Kivity <avi@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>
---
 arch/x86/kvm/mmu.c         |    2 +-
 arch/x86/kvm/paging_tmpl.h |    8 ++++++--
 2 files changed, 7 insertions(+), 3 deletions(-)

--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -981,7 +981,7 @@ static int mmu_unsync_walk(struct kvm_mm
 	for_each_unsync_children(sp->unsync_child_bitmap, i) {
 		u64 ent = sp->spt[i];
 
-		if (is_shadow_present_pte(ent)) {
+		if (is_shadow_present_pte(ent) && !is_large_pte(ent)) {
 			struct kvm_mmu_page *child;
 			child = page_header(ent & PT64_BASE_ADDR_MASK);
 
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -467,9 +467,13 @@ static int FNAME(shadow_invlpg_entry)(st
 				      u64 *sptep, int level)
 {
 
-	if (level == PT_PAGE_TABLE_LEVEL) {
-		if (is_shadow_present_pte(*sptep))
+	if (level == PT_PAGE_TABLE_LEVEL ||
+	    ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) {
+		if (is_shadow_present_pte(*sptep)) {
 			rmap_remove(vcpu->kvm, sptep);
+			if (is_large_pte(*sptep))
+				--vcpu->kvm->stat.lpages;
+		}
 		set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
 		return 1;
 	}


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/