[PATCH v2 12/12] KVM: MMU: improve write flooding detected

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Detecting write-flooding does not work well, when we handle page written, if
the last speculative spte is not accessed, we treat the page is
write-flooding, however, we can speculative spte on many path, such as pte
prefetch, page synced, that means the last speculative spte may be not point
to the written page and the written page can be accessed via other sptes, so
depends on the Accessed bit of the last speculative spte is not enough

Instead of detected page accessed, we can detect whether the spte is accessed
or not, if the spte is not accessed but it is written frequently, we treat is
not a page table or it not used for a long time

Signed-off-by: Xiao Guangrong <xiaoguangrong@xxxxxxxxxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |    6 +---
 arch/x86/kvm/mmu.c              |   51 ++++++++++-----------------------------
 arch/x86/kvm/paging_tmpl.h      |    9 +-----
 3 files changed, 17 insertions(+), 49 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2c08458..50fe100 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -239,6 +239,8 @@ struct kvm_mmu_page {
 	int clear_spte_count;
 #endif
 
+	int write_flooding_count;
+
 	struct rcu_head rcu;
 };
 
@@ -352,10 +354,6 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
-	gfn_t last_pt_write_gfn;
-	int   last_pt_write_count;
-	u64  *last_pte_updated;
-
 	struct fpu guest_fpu;
 	u64 xcr0;
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 67eead6..7ee4ef4 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1696,6 +1696,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		} else if (sp->unsync)
 			kvm_mmu_mark_parents_unsync(sp);
 
+		sp->write_flooding_count = 0;
 		trace_kvm_mmu_get_page(sp, false);
 		return sp;
 	}
@@ -1848,15 +1849,6 @@ static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
 	mmu_page_remove_parent_pte(sp, parent_pte);
 }
 
-static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm)
-{
-	int i;
-	struct kvm_vcpu *vcpu;
-
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		vcpu->arch.last_pte_updated = NULL;
-}
-
 static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	u64 *parent_pte;
@@ -1916,7 +1908,6 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 	}
 
 	sp->role.invalid = 1;
-	kvm_mmu_reset_last_pte_updated(kvm);
 	return ret;
 }
 
@@ -2358,8 +2349,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		}
 	}
 	kvm_release_pfn_clean(pfn);
-	if (speculative)
-		vcpu->arch.last_pte_updated = sptep;
 }
 
 static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
@@ -3517,13 +3506,6 @@ static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page,
 		kvm_mmu_flush_tlb(vcpu);
 }
 
-static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu)
-{
-	u64 *spte = vcpu->arch.last_pte_updated;
-
-	return !!(spte && (*spte & shadow_accessed_mask));
-}
-
 static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
 				    const u8 *new, int *bytes)
 {
@@ -3565,22 +3547,14 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
  * If we're seeing too many writes to a page, it may no longer be a page table,
  * or we may be forking, in which case it is better to unmap the page.
  */
-static bool detect_write_flooding(struct kvm_vcpu *vcpu, gfn_t gfn)
+static bool detect_write_flooding(struct kvm_mmu_page *sp, u64 *spte)
 {
-	bool flooded = false;
-
-	if (gfn == vcpu->arch.last_pt_write_gfn
-	    && !last_updated_pte_accessed(vcpu)) {
-		++vcpu->arch.last_pt_write_count;
-		if (vcpu->arch.last_pt_write_count >= 3)
-			flooded = true;
-	} else {
-		vcpu->arch.last_pt_write_gfn = gfn;
-		vcpu->arch.last_pt_write_count = 1;
-		vcpu->arch.last_pte_updated = NULL;
-	}
+	if (spte && !(*spte & shadow_accessed_mask))
+		sp->write_flooding_count++;
+	else
+		sp->write_flooding_count = 0;
 
-	return flooded;
+	return sp->write_flooding_count >= 3;
 }
 
 
@@ -3654,7 +3628,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	LIST_HEAD(invalid_list);
 	u64 entry, gentry, *spte;
 	int npte;
-	bool remote_flush, local_flush, zap_page, flooded, misaligned;
+	bool remote_flush, local_flush, zap_page;
 
 	/*
 	 * If we don't have indirect shadow pages, it means no page is
@@ -3673,18 +3647,19 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	++vcpu->kvm->stat.mmu_pte_write;
 	trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 
-	flooded = detect_write_flooding(vcpu, gfn);
 	mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
 	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) {
-		misaligned = detect_write_misaligned(sp, gpa, bytes);
-		if (misaligned || flooded || !page_table_written) {
+		spte = get_written_sptes(sp, gpa, &npte);
+
+		if (!page_table_written ||
+		      detect_write_misaligned(sp, gpa, bytes) ||
+		      detect_write_flooding(sp, spte)) {
 			zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
 						     &invalid_list);
 			++vcpu->kvm->stat.mmu_flooded;
 			continue;
 		}
 
-		spte = get_written_sptes(sp, gpa, &npte);
 		if (!spte)
 			continue;
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 3466229..82063b2 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -595,11 +595,9 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	 */
 	if (!r) {
 		pgprintk("%s: guest page fault\n", __func__);
-		if (!prefault) {
+		if (!prefault)
 			inject_page_fault(vcpu, &walker.fault);
-			/* reset fork detector */
-			vcpu->arch.last_pt_write_count = 0;
-		}
+
 		return 0;
 	}
 
@@ -637,9 +635,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	pgprintk("%s: shadow pte %p %llx emulate %d\n", __func__,
 		 sptep, *sptep, emulate);
 
-	if (!emulate)
-		vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
-
 	++vcpu->stat.pf_fixed;
 	trace_kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 	spin_unlock(&vcpu->kvm->mmu_lock);
-- 
1.7.5.4

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]
  Powered by Linux