KVM: MMU: clear write-flooding on the fast path of tracked page

If the page fault is caused by write access on write tracked page, the
real shadow page walking is skipped, we lost the chance to clear write
flooding for the page structure current vcpu is using

Fix it by locklessly waking shadow page table to clear write flooding
on the shadow page structure out of mmu-lock. So that we change the
count to atomic_t

Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 24 insertions, 4 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 71e43fe04bbc..e2fc5c0ec86a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -285,7 +285,7 @@ struct kvm_mmu_page {
 #endif
 
         /* Number of writes since the last time traversal visited this page.  */
-        int write_flooding_count;
+        atomic_t write_flooding_count;
 };
 
 struct kvm_pio_request {
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index dd8e3ca2d79b..58c067da6efc 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2063,7 +2063,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu,
 
 static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
 {
-        sp->write_flooding_count = 0;
+        atomic_set(&sp->write_flooding_count,  0);
 }
 
 static void clear_sp_write_flooding_count(u64 *spte)
@@ -3406,6 +3406,23 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
         return false;
 }
 
+static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
+{
+        struct kvm_shadow_walk_iterator iterator;
+        u64 spte;
+
+        if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+                return;
+
+        walk_shadow_page_lockless_begin(vcpu);
+        for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
+                clear_sp_write_flooding_count(iterator.sptep);
+                if (!is_shadow_present_pte(spte))
+                        break;
+        }
+        walk_shadow_page_lockless_end(vcpu);
+}
+
 static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
                                 u32 error_code, bool prefault)
 {
@@ -4221,7 +4238,8 @@ static bool detect_write_flooding(struct kvm_mmu_page *sp)
         if (sp->role.level == PT_PAGE_TABLE_LEVEL)
                 return false;
 
-        return ++sp->write_flooding_count >= 3;
+        atomic_inc(&sp->write_flooding_count);
+        return atomic_read(&sp->write_flooding_count) >= 3;
 }
 
 /*
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 52ae2d94cc9e..4174cf290fa3 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -728,8 +728,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
                 return 0;
         }
 
-        if (page_fault_handle_page_track(vcpu, error_code, walker.gfn))
+        if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) {
+                shadow_page_table_clear_flood(vcpu, addr);
                 return 1;
+        }
 
         vcpu->arch.write_fault_to_shadow_pgtable = false;