[PATCH] KVM: MMU: If emulating an instruction fails, try unprotecting the page

A page table may have been recycled into a regular page, and so any
instruction can be executed on it.  Unprotect the page and let the cpu do its
thing.

Signed-off-by: Avi Kivity <avi@qumranet.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index b7068ecd7765ad5956efb6a8d779a40c4aa836d6..34c43bb4d3482242e7544a9fd4729f63dc2e267b 100644 (file)
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -450,6 +450,7 @@ unsigned long segment_base(u16 selector);
 
 void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
 void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
+int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 
 static inline struct page *_gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {

diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 047f6f6ed3f67580be892f0570977725c6e0f86a..79032438dd167a8ad37e52c273dfe56a5620a602 100644 (file)
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -1063,6 +1063,8 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
        }
 
        if (r) {
+               if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
+                       return EMULATE_DONE;
                if (!vcpu->mmio_needed) {
                        report_emulation_failure(&emulate_ctxt);
                        return EMULATE_FAIL;

diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c
index 6dbd83b866239be935a3ba984240c22c6931e86b..1484b721171718c645d3d5eee85f8585cd745969 100644 (file)
--- a/drivers/kvm/mmu.c
+++ b/drivers/kvm/mmu.c
@@ -478,11 +478,62 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
        return page;
 }
 
+static void kvm_mmu_page_unlink_children(struct kvm_vcpu *vcpu,
+                                        struct kvm_mmu_page *page)
+{
+       BUG();
+}
+
 static void kvm_mmu_put_page(struct kvm_vcpu *vcpu,
                             struct kvm_mmu_page *page,
                             u64 *parent_pte)
 {
        mmu_page_remove_parent_pte(page, parent_pte);
+       if (page->role.level > PT_PAGE_TABLE_LEVEL)
+               kvm_mmu_page_unlink_children(vcpu, page);
+       hlist_del(&page->hash_link);
+       list_del(&page->link);
+       list_add(&page->link, &vcpu->free_pages);
+}
+
+static void kvm_mmu_zap_page(struct kvm_vcpu *vcpu,
+                            struct kvm_mmu_page *page)
+{
+       u64 *parent_pte;
+
+       while (page->multimapped || page->parent_pte) {
+               if (!page->multimapped)
+                       parent_pte = page->parent_pte;
+               else {
+                       struct kvm_pte_chain *chain;
+
+                       chain = container_of(page->parent_ptes.first,
+                                            struct kvm_pte_chain, link);
+                       parent_pte = chain->parent_ptes[0];
+               }
+               kvm_mmu_put_page(vcpu, page, parent_pte);
+               *parent_pte = 0;
+       }
+}
+
+static int kvm_mmu_unprotect_page(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+       unsigned index;
+       struct hlist_head *bucket;
+       struct kvm_mmu_page *page;
+       struct hlist_node *node, *n;
+       int r;
+
+       pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
+       r = 0;
+       index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+       bucket = &vcpu->kvm->mmu_page_hash[index];
+       hlist_for_each_entry_safe(page, node, n, bucket, hash_link)
+               if (page->gfn == gfn && !page->role.metaphysical) {
+                       kvm_mmu_zap_page(vcpu, page);
+                       r = 1;
+               }
+       return r;
 }
 
 static void page_header_update_slot(struct kvm *kvm, void *pte, gpa_t gpa)
@@ -1001,6 +1052,13 @@ void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes)
 {
 }
 
+int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
+{
+       gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva);
+
+       return kvm_mmu_unprotect_page(vcpu, gpa >> PAGE_SHIFT);
+}
+
 static void free_mmu_pages(struct kvm_vcpu *vcpu)
 {
        while (!list_empty(&vcpu->free_pages)) {