@@ -2458,17 +2458,33 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
kvm_mmu_mark_parents_unsync(sp);
}
-bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
- bool can_unsync)
+/*
+ * Attempt to unsync any shadow pages that can be reached by the specified gfn,
+ * KVM is creating a writable mapping for said gfn. Returns 0 if all pages
+ * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must
+ * be write-protected.
+ */
+int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync)
{
struct kvm_mmu_page *sp;
+ /*
+ * Force write-protection if the page is being tracked. Note, the page
+ * track machinery is used to write-protect upper-level shadow pages,
+ * i.e. this guards the role.level == 4K assertion below!
+ */
if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
- return true;
+ return -EPERM;
+ /*
+ * The page is not write-tracked, mark existing shadow pages unsync
+ * unless KVM is synchronizing an unsync SP (can_unsync = false). In
+ * that case, KVM must complete emulation of the guest TLB flush before
+ * allowing shadow pages to become unsync (writable by the guest).
+ */
for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (!can_unsync)
- return true;
+ return -EPERM;
if (sp->unsync)
continue;
@@ -2499,8 +2515,8 @@ bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
* 2.2 Guest issues TLB flush.
* That causes a VM Exit.
*
- * 2.3 kvm_mmu_sync_pages() reads sp->unsync.
- * Since it is false, so it just returns.
+ * 2.3 Walking of unsync pages sees sp->unsync is
+ * false and skips the page.
*
* 2.4 Guest accesses GVA X.
* Since the mapping in the SP was not updated,
@@ -2516,7 +2532,7 @@ bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
*/
smp_wmb();
- return false;
+ return 0;
}
static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
@@ -3461,8 +3477,8 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
* flush strictly after those changes are made. We only need to
* ensure that the other CPU sets these flags before any actual
* changes to the page tables are made. The comments in
- * mmu_need_write_protect() describe what could go wrong if this
- * requirement isn't satisfied.
+ * mmu_try_to_unsync_pages() describe what could go wrong if
+ * this requirement isn't satisfied.
*/
if (!smp_load_acquire(&sp->unsync) &&
!smp_load_acquire(&sp->unsync_children))
@@ -122,8 +122,7 @@ static inline bool is_nx_huge_page_enabled(void)
return READ_ONCE(nx_huge_pages);
}
-bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
- bool can_unsync);
+int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync);
void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
@@ -147,13 +147,19 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level,
/*
* Optimization: for pte sync, if spte was writable the hash
* lookup is unnecessary (and expensive). Write protection
- * is responsibility of mmu_get_page / kvm_sync_page.
+ * is responsibility of kvm_mmu_get_page / kvm_mmu_sync_roots.
* Same reasoning can be applied to dirty page accounting.
*/
if (!can_unsync && is_writable_pte(old_spte))
goto out;
- if (mmu_need_write_protect(vcpu, gfn, can_unsync)) {
+ /*
+ * Unsync shadow pages that are reachable by the new, writable
+ * SPTE. Write-protect the SPTE if the page can't be unsync'd,
+ * e.g. it's write-tracked (upper-level SPs) or has one or more
+ * shadow pages and unsync'ing pages is not allowed.
+ */
+ if (mmu_try_to_unsync_pages(vcpu, gfn, can_unsync)) {
pgprintk("%s: found shadow page for %llx, marking ro\n",
__func__, gfn);
ret |= SET_SPTE_WRITE_PROTECTED_PT;
Rename mmu_need_write_protect() to mmu_try_to_unsync_pages() and update a variety of related, stale comments. Add several new comments to call out subtle details, e.g. that upper-level shadow pages are write-tracked, and that can_unsync is false iff KVM is in the process of synchronizing pages. No functional change intended. Signed-off-by: Sean Christopherson <seanjc@google.com> --- arch/x86/kvm/mmu/mmu.c | 34 ++++++++++++++++++++++++--------- arch/x86/kvm/mmu/mmu_internal.h | 3 +-- arch/x86/kvm/mmu/spte.c | 10 ++++++++-- 3 files changed, 34 insertions(+), 13 deletions(-)