KVM: x86: optimize for writing guest page

index 5d7fbf0..b01afee 100644
@@ -592,6 +592,11 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
 	return 0;
 }
 
+static int mmu_memory_cache_free_objects(struct kvm_mmu_memory_cache *cache)
+{
+	return cache->nobjs;
+}
+
 static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc,
 				  struct kmem_cache *cache)
 {

@@ -969,6 +974,14 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
 	return &linfo->rmap_pde;
 }
 
+static bool rmap_can_add(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmu_memory_cache *cache;
+
+	cache = &vcpu->arch.mmu_pte_list_desc_cache;
+	return mmu_memory_cache_free_objects(cache);
+}
+
 static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 {
 	struct kvm_mmu_page *sp;

@@ -3585,6 +3598,12 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		break;
 	}
 
+	/*
+	 * No need to care whether allocation memory is successful
+	 * or not since pte prefetch is skiped if it does not have
+	 * enough objects in the cache.
+	 */
+	mmu_topup_memory_caches(vcpu);
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter)
 		gentry = 0;

@@ -3655,7 +3674,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 			mmu_page_zap_pte(vcpu->kvm, sp, spte);
 			if (gentry &&
 			      !((sp->role.word ^ vcpu->arch.mmu.base_role.word)
-			      & mask.word))
+			      & mask.word) && rmap_can_add(vcpu))
 				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
 			if (!remote_flush && need_remote_flush(entry, *spte))
 				remote_flush = true;

@@ -3716,10 +3735,6 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 		goto out;
 	}
 
-	r = mmu_topup_memory_caches(vcpu);
-	if (r)
-		goto out;
-
 	er = x86_emulate_instruction(vcpu, cr2, 0, insn, insn_len);
 
 	switch (er) {

index f1e3be1..a10950a 100644
@@ -125,8 +125,9 @@
 #define Lock        (1<<26) /* lock prefix is allowed for the instruction */
 #define Priv        (1<<27) /* instruction generates #GP if current CPL != 0 */
 #define No64	    (1<<28)
+#define PageTable   (1 << 29)   /* instruction used to write page table */
 /* Source 2 operand type */
-#define Src2Shift   (29)
+#define Src2Shift   (30)
 #define Src2None    (OpNone << Src2Shift)
 #define Src2CL      (OpCL << Src2Shift)
 #define Src2ImmByte (OpImmByte << Src2Shift)

@@ -3033,10 +3034,10 @@ static struct opcode group7_rm7[] = {
 
 static struct opcode group1[] = {
 	I(Lock, em_add),
-	I(Lock, em_or),
+	I(Lock | PageTable, em_or),
 	I(Lock, em_adc),
 	I(Lock, em_sbb),
-	I(Lock, em_and),
+	I(Lock | PageTable, em_and),
 	I(Lock, em_sub),
 	I(Lock, em_xor),
 	I(0, em_cmp),

@@ -3096,18 +3097,21 @@ static struct group_dual group7 = { {
 
 static struct opcode group8[] = {
 	N, N, N, N,
-	D(DstMem | SrcImmByte | ModRM), D(DstMem | SrcImmByte | ModRM | Lock),
-	D(DstMem | SrcImmByte | ModRM | Lock), D(DstMem | SrcImmByte | ModRM | Lock),
+	D(DstMem | SrcImmByte | ModRM),
+	D(DstMem | SrcImmByte | ModRM | Lock | PageTable),
+	D(DstMem | SrcImmByte | ModRM | Lock),
+	D(DstMem | SrcImmByte | ModRM | Lock | PageTable),
 };
 
 static struct group_dual group9 = { {
-	N, D(DstMem64 | ModRM | Lock), N, N, N, N, N, N,
+	N, D(DstMem64 | ModRM | Lock | PageTable), N, N, N, N, N, N,
 }, {
 	N, N, N, N, N, N, N, N,
 } };
 
 static struct opcode group11[] = {
-	I(DstMem | SrcImm | ModRM | Mov, em_mov), X7(D(Undefined)),
+	I(DstMem | SrcImm | ModRM | Mov | PageTable, em_mov),
+	X7(D(Undefined)),
 };
 
 static struct gprefix pfx_0f_6f_0f_7f = {

@@ -3120,7 +3124,7 @@ static struct opcode opcode_table[256] = {
 	I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg),
 	/* 0x08 - 0x0F */
-	I6ALU(Lock, em_or),
+	I6ALU(Lock | PageTable, em_or),
 	I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg),
 	N,
 	/* 0x10 - 0x17 */

@@ -3132,7 +3136,7 @@ static struct opcode opcode_table[256] = {
 	I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg),
 	/* 0x20 - 0x27 */
-	I6ALU(Lock, em_and), N, N,
+	I6ALU(Lock | PageTable, em_and), N, N,
 	/* 0x28 - 0x2F */
 	I6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das),
 	/* 0x30 - 0x37 */

@@ -3165,11 +3169,11 @@ static struct opcode opcode_table[256] = {
 	G(ByteOp | DstMem | SrcImm | ModRM | No64 | Group, group1),
 	G(DstMem | SrcImmByte | ModRM | Group, group1),
 	I2bv(DstMem | SrcReg | ModRM, em_test),
-	I2bv(DstMem | SrcReg | ModRM | Lock, em_xchg),
+	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg),
 	/* 0x88 - 0x8F */
-	I2bv(DstMem | SrcReg | ModRM | Mov, em_mov),
+	I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov),
 	I2bv(DstReg | SrcMem | ModRM | Mov, em_mov),
-	I(DstMem | SrcNone | ModRM | Mov, em_mov_rm_sreg),
+	I(DstMem | SrcNone | ModRM | Mov | PageTable, em_mov_rm_sreg),
 	D(ModRM | SrcMem | NoAccess | DstReg),
 	I(ImplicitOps | SrcMem16 | ModRM, em_mov_sreg_rm),
 	G(0, group1A),

@@ -3182,7 +3186,7 @@ static struct opcode opcode_table[256] = {
 	II(ImplicitOps | Stack, em_popf, popf), N, N,
 	/* 0xA0 - 0xA7 */
 	I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
-	I2bv(DstMem | SrcAcc | Mov | MemAbs, em_mov),
+	I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
 	I2bv(SrcSI | DstDI | Mov | String, em_mov),
 	I2bv(SrcSI | DstDI | String, em_cmp),
 	/* 0xA8 - 0xAF */

@@ -3280,12 +3284,13 @@ static struct opcode twobyte_table[256] = {
 	D(DstMem | SrcReg | Src2CL | ModRM), N, N,
 	/* 0xA8 - 0xAF */
 	I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg),
-	DI(ImplicitOps, rsm), D(DstMem | SrcReg | ModRM | BitOp | Lock),
+	DI(ImplicitOps, rsm),
+	D(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable),
 	D(DstMem | SrcReg | Src2ImmByte | ModRM),
 	D(DstMem | SrcReg | Src2CL | ModRM),
 	D(ModRM), I(DstReg | SrcMem | ModRM, em_imul),
 	/* 0xB0 - 0xB7 */
-	D2bv(DstMem | SrcReg | ModRM | Lock),
+	D2bv(DstMem | SrcReg | ModRM | Lock | PageTable),
 	I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg),
 	D(DstMem | SrcReg | ModRM | BitOp | Lock),
 	I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg),

@@ -3293,7 +3298,7 @@ static struct opcode twobyte_table[256] = {
 	D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xB8 - 0xBF */
 	N, N,
-	G(BitOp, group8), D(DstMem | SrcReg | ModRM | BitOp | Lock),
+	G(BitOp, group8), D(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable),
 	D(DstReg | SrcMem | ModRM), D(DstReg | SrcMem | ModRM),
 	D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xC0 - 0xCF */

index a026507..9a4acf4 100644
@@ -364,6 +364,7 @@ enum x86_intercept {
 #endif
 
 int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
+bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
 #define EMULATION_FAILED -1
 #define EMULATION_OK 0
 #define EMULATION_RESTART 1

index 6ab4241..27a25df 100644
@@ -443,6 +443,9 @@ struct kvm_vcpu_arch {
 
 	cpumask_var_t wbinvd_dirty_mask;
 
+	unsigned long last_retry_eip;
+	unsigned long last_retry_addr;
+
 	struct {
 		bool halted;
 		gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];

@@ -689,6 +692,7 @@ enum emulation_result {
 #define EMULTYPE_NO_DECODE	    (1 << 0)
 #define EMULTYPE_TRAP_UD	    (1 << 1)
 #define EMULTYPE_SKIP		    (1 << 2)
+#define EMULTYPE_RETRY		    (1 << 3)
 int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
 			    int emulation_type, void *insn, int insn_len);
 

@@ -753,6 +757,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes,
 		       bool guest_initiated);
+int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
 int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);

index a10950a..8547958 100644
@@ -3702,6 +3702,11 @@ done:
 	return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK;
 }
 
+bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt)
+{
+	return ctxt->d & PageTable;
+}
+
 static bool string_insn_completed(struct x86_emulate_ctxt *ctxt)
 {
 	/* The second termination condition only applies for REPE

index b01afee..4e53d6b 100644
@@ -1997,7 +1997,7 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
 	kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;
 }
 
-static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
+int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_mmu_page *sp;
 	struct hlist_node *node;

@@ -2006,7 +2006,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 
 	pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
 	r = 0;
-
+	spin_lock(&kvm->mmu_lock);
 	for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) {
 		pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
 			 sp->role.word);

@@ -2014,8 +2014,11 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 	}
 	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+	spin_unlock(&kvm->mmu_lock);
+
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
 
 static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 {

@@ -3697,9 +3700,8 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
 
 	gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
 
-	spin_lock(&vcpu->kvm->mmu_lock);
 	r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
-	spin_unlock(&vcpu->kvm->mmu_lock);
+
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);

@@ -3720,10 +3722,18 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
 }
 
+static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr)
+{
+	if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu))
+		return vcpu_match_mmio_gpa(vcpu, addr);
+
+	return vcpu_match_mmio_gva(vcpu, addr);
+}
+
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 		       void *insn, int insn_len)
 {
-	int r;
+	int r, emulation_type = EMULTYPE_RETRY;
 	enum emulation_result er;
 
 	r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);

@@ -3735,7 +3745,10 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 		goto out;
 	}
 
-	er = x86_emulate_instruction(vcpu, cr2, 0, insn, insn_len);
+	if (is_mmio_page_fault(vcpu, cr2))
+		emulation_type = 0;
+
+	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
 
 	switch (er) {
 	case EMULATE_DONE:

59 lines not on this page · raw message

index 727a6af..a69a3e5 100644
@@ -4327,32 +4327,24 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 	return r;
 }
 
-
-static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
-				    int size, unsigned short port, void *val,
-				    unsigned int count)
+static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
+			       unsigned short port, void *val,
+			       unsigned int count, bool in)
 {
-	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
-	if (vcpu->arch.pio.count)
-		goto data_avail;
-
-	trace_kvm_pio(0, port, size, count);
+	trace_kvm_pio(!in, port, size, count);
 
 	vcpu->arch.pio.port = port;
-	vcpu->arch.pio.in = 1;
+	vcpu->arch.pio.in = in;
 	vcpu->arch.pio.count  = count;
 	vcpu->arch.pio.size = size;
 
 	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
-	data_avail:
-		memcpy(val, vcpu->arch.pio_data, size * count);
 		vcpu->arch.pio.count = 0;
 		return 1;
 	}
 
 	vcpu->run->exit_reason = KVM_EXIT_IO;
-	vcpu->run->io.direction = KVM_EXIT_IO_IN;
+	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
 	vcpu->run->io.size = size;
 	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
 	vcpu->run->io.count = count;

@@ -4361,36 +4353,37 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 	return 0;
 }
 
-static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
-				     int size, unsigned short port,
-				     const void *val, unsigned int count)
+static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
+				    int size, unsigned short port, void *val,
+				    unsigned int count)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int ret;
 
-	trace_kvm_pio(1, port, size, count);
-
-	vcpu->arch.pio.port = port;
-	vcpu->arch.pio.in = 0;
-	vcpu->arch.pio.count = count;
-	vcpu->arch.pio.size = size;
-
-	memcpy(vcpu->arch.pio_data, val, size * count);
+	if (vcpu->arch.pio.count)
+		goto data_avail;
 
-	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
+	ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
+	if (ret) {
+data_avail:
+		memcpy(val, vcpu->arch.pio_data, size * count);
 		vcpu->arch.pio.count = 0;
 		return 1;
 	}
 
-	vcpu->run->exit_reason = KVM_EXIT_IO;
-	vcpu->run->io.direction = KVM_EXIT_IO_OUT;
-	vcpu->run->io.size = size;
-	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
-	vcpu->run->io.count = count;
-	vcpu->run->io.port = port;
-
 	return 0;
 }
 
+static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
+				     int size, unsigned short port,
+				     const void *val, unsigned int count)
+{
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+	memcpy(vcpu->arch.pio_data, val, size * count);
+	return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
+}
+
 static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
 {
 	return kvm_x86_ops->get_segment_base(vcpu, seg);

index 27a25df..58ea3a7 100644
@@ -356,7 +356,6 @@ struct kvm_vcpu_arch {
 	gfn_t last_pt_write_gfn;
 	int   last_pt_write_count;
 	u64  *last_pte_updated;
-	gfn_t last_pte_gfn;
 
 	struct fpu guest_fpu;
 	u64 xcr0;

index 4e53d6b..6a35024 100644
@@ -2206,11 +2206,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (set_mmio_spte(sptep, gfn, pfn, pte_access))
 		return 0;
 
-	/*
-	 * We don't set the accessed bit, since we sometimes want to see
-	 * whether the guest actually used the pte (in order to detect
-	 * demand paging).
-	 */
 	spte = PT_PRESENT_MASK;
 	if (!speculative)
 		spte |= shadow_accessed_mask;

@@ -2361,10 +2356,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		}
 	}
 	kvm_release_pfn_clean(pfn);
-	if (speculative) {
+	if (speculative)
 		vcpu->arch.last_pte_updated = sptep;
-		vcpu->arch.last_pte_gfn = gfn;
-	}
 }
 
 static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)

@@ -3532,18 +3525,6 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu)
 	return !!(spte && (*spte & shadow_accessed_mask));
 }
 
-static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
-	u64 *spte = vcpu->arch.last_pte_updated;
-
-	if (spte
-	    && vcpu->arch.last_pte_gfn == gfn
-	    && shadow_accessed_mask
-	    && !(*spte & shadow_accessed_mask)
-	    && is_shadow_present_pte(*spte))
-		set_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
-}
-
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes,
 		       bool guest_initiated)

@@ -3614,7 +3595,6 @@ 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);
 	if (guest_initiated) {
-		kvm_mmu_access_page(vcpu, gfn);
 		if (gfn == vcpu->arch.last_pt_write_gfn
 		    && !last_updated_pte_accessed(vcpu)) {
 			++vcpu->arch.last_pt_write_count;

index 6a35024..805a9d5 100644
@@ -1808,7 +1808,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	}
 }
 
-static void mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
+static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 			     u64 *spte)
 {
 	u64 pte;

@@ -1816,17 +1816,21 @@ static void mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 
 	pte = *spte;
 	if (is_shadow_present_pte(pte)) {
-		if (is_last_spte(pte, sp->role.level))
+		if (is_last_spte(pte, sp->role.level)) {
 			drop_spte(kvm, spte);
-		else {
+			if (is_large_pte(pte))
+				--kvm->stat.lpages;
+		} else {
 			child = page_header(pte & PT64_BASE_ADDR_MASK);
 			drop_parent_pte(child, spte);
 		}
-	} else if (is_mmio_spte(pte))
+		return true;
+	}
+
+	if (is_mmio_spte(pte))
 		mmu_spte_clear_no_track(spte);
 
-	if (is_large_pte(pte))
-		--kvm->stat.lpages;
+	return false;
 }
 
 static void kvm_mmu_page_unlink_children(struct kvm *kvm,

85 lines not on this page · raw message

index 58ea3a7..927ba73 100644
@@ -460,7 +460,6 @@ struct kvm_arch {
 	unsigned int n_requested_mmu_pages;
 	unsigned int n_max_mmu_pages;
 	unsigned int indirect_shadow_pages;
-	atomic_t invlpg_counter;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	/*
 	 * Hash table of struct kvm_mmu_page.

@@ -754,8 +753,7 @@ int fx_init(struct kvm_vcpu *vcpu);
 
 void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		       const u8 *new, int bytes,
-		       bool guest_initiated);
+		       const u8 *new, int bytes);
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
 int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);

index 805a9d5..4128aba 100644
@@ -3530,8 +3530,7 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu)
 }
 
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		       const u8 *new, int bytes,
-		       bool guest_initiated)
+		       const u8 *new, int bytes)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	union kvm_mmu_page_role mask = { .word = 0 };

@@ -3540,7 +3539,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	LIST_HEAD(invalid_list);
 	u64 entry, gentry, *spte;
 	unsigned pte_size, page_offset, misaligned, quadrant, offset;
-	int level, npte, invlpg_counter, r, flooded = 0;
+	int level, npte, r, flooded = 0;
 	bool remote_flush, local_flush, zap_page;
 
 	/*

@@ -3555,19 +3554,16 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 
 	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
 
-	invlpg_counter = atomic_read(&vcpu->kvm->arch.invlpg_counter);
-
 	/*
 	 * Assume that the pte write on a page table of the same type
 	 * as the current vcpu paging mode since we update the sptes only
 	 * when they have the same mode.
 	 */
-	if ((is_pae(vcpu) && bytes == 4) || !new) {
+	if (is_pae(vcpu) && bytes == 4) {
 		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
-		if (is_pae(vcpu)) {
-			gpa &= ~(gpa_t)7;
-			bytes = 8;
-		}
+		gpa &= ~(gpa_t)7;
+		bytes = 8;
+
 		r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8));
 		if (r)
 			gentry = 0;

@@ -3593,22 +3589,18 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	 */
 	mmu_topup_memory_caches(vcpu);
 	spin_lock(&vcpu->kvm->mmu_lock);
-	if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter)
-		gentry = 0;
 	kvm_mmu_free_some_pages(vcpu);
 	++vcpu->kvm->stat.mmu_pte_write;
 	trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
-	if (guest_initiated) {
-		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 = 1;
-		} else {
-			vcpu->arch.last_pt_write_gfn = gfn;
-			vcpu->arch.last_pt_write_count = 1;
-			vcpu->arch.last_pte_updated = NULL;
-		}
+	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 = 1;
+	} else {
+		vcpu->arch.last_pt_write_gfn = gfn;
+		vcpu->arch.last_pt_write_count = 1;
+		vcpu->arch.last_pte_updated = NULL;
 	}
 
 	mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;

index d8d3906..9efb860 100644
@@ -672,20 +672,27 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 {
 	struct kvm_shadow_walk_iterator iterator;
 	struct kvm_mmu_page *sp;
-	gpa_t pte_gpa = -1;
 	int level;
 	u64 *sptep;
 
 	vcpu_clear_mmio_info(vcpu, gva);
 
-	spin_lock(&vcpu->kvm->mmu_lock);
+	/*
+	 * No need to check return value here, rmap_can_add() can
+	 * help us to skip pte prefetch later.
+	 */
+	mmu_topup_memory_caches(vcpu);
 
+	spin_lock(&vcpu->kvm->mmu_lock);
 	for_each_shadow_entry(vcpu, gva, iterator) {
 		level = iterator.level;
 		sptep = iterator.sptep;
 
 		sp = page_header(__pa(sptep));
 		if (is_last_spte(*sptep, level)) {
+			pt_element_t gpte;
+			gpa_t pte_gpa;
+
 			if (!sp->unsync)
 				break;
 

@@ -694,22 +701,21 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 
 			if (mmu_page_zap_pte(vcpu->kvm, sp, sptep))
 				kvm_flush_remote_tlbs(vcpu->kvm);
+
+			if (!rmap_can_add(vcpu))
+				break;
+
+			if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
+						  sizeof(pt_element_t)))
+				break;
+
+			FNAME(update_pte)(vcpu, sp, sptep, &gpte);
 		}
 
 		if (!is_shadow_present_pte(*sptep) || !sp->unsync_children)
 			break;
 	}
-
-	atomic_inc(&vcpu->kvm->arch.invlpg_counter);
-
 	spin_unlock(&vcpu->kvm->mmu_lock);
-
-	if (pte_gpa == -1)
-		return;
-
-	if (mmu_topup_memory_caches(vcpu))
-		return;
-	kvm_mmu_pte_write(vcpu, pte_gpa, NULL, sizeof(pt_element_t), 0);
 }
 
 static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,

index a69a3e5..9206e39 100644
@@ -4065,7 +4065,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 	ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
 	if (ret < 0)
 		return 0;
-	kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1);
+	kvm_mmu_pte_write(vcpu, gpa, val, bytes);
 	return 1;
 }
 

@@ -4302,7 +4302,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 	if (!exchanged)
 		return X86EMUL_CMPXCHG_FAILED;
 
-	kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1);
+	kvm_mmu_pte_write(vcpu, gpa, new, bytes);
 
 	return X86EMUL_CONTINUE;
 

index 4128aba..7b22f3a 100644
@@ -3589,7 +3589,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	 */
 	mmu_topup_memory_caches(vcpu);
 	spin_lock(&vcpu->kvm->mmu_lock);
-	kvm_mmu_free_some_pages(vcpu);
 	++vcpu->kvm->stat.mmu_pte_write;
 	trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 	if (gfn == vcpu->arch.last_pt_write_gfn

index 7b22f3a..6e39ec5 100644
@@ -3529,48 +3529,28 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu)
 	return !!(spte && (*spte & shadow_accessed_mask));
 }
 
-void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		       const u8 *new, int bytes)
+static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
+				    const u8 *new, int *bytes)
 {
-	gfn_t gfn = gpa >> PAGE_SHIFT;
-	union kvm_mmu_page_role mask = { .word = 0 };
-	struct kvm_mmu_page *sp;
-	struct hlist_node *node;
-	LIST_HEAD(invalid_list);
-	u64 entry, gentry, *spte;
-	unsigned pte_size, page_offset, misaligned, quadrant, offset;
-	int level, npte, r, flooded = 0;
-	bool remote_flush, local_flush, zap_page;
-
-	/*
-	 * If we don't have indirect shadow pages, it means no page is
-	 * write-protected, so we can exit simply.
-	 */
-	if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
-		return;
-
-	zap_page = remote_flush = local_flush = false;
-	offset = offset_in_page(gpa);
-
-	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
+	u64 gentry;
+	int r;
 
 	/*
 	 * Assume that the pte write on a page table of the same type
 	 * as the current vcpu paging mode since we update the sptes only
 	 * when they have the same mode.
 	 */
-	if (is_pae(vcpu) && bytes == 4) {
+	if (is_pae(vcpu) && *bytes == 4) {
 		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
-		gpa &= ~(gpa_t)7;
-		bytes = 8;
-
-		r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8));
+		*gpa &= ~(gpa_t)7;
+		*bytes = 8;
+		r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, min(*bytes, 8));
 		if (r)
 			gentry = 0;
 		new = (const u8 *)&gentry;
 	}
 
-	switch (bytes) {
+	switch (*bytes) {
 	case 4:
 		gentry = *(const u32 *)new;
 		break;

@@ -3582,71 +3562,135 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		break;
 	}
 
-	/*
-	 * No need to care whether allocation memory is successful
-	 * or not since pte prefetch is skiped if it does not have
-	 * enough objects in the cache.
-	 */
-	mmu_topup_memory_caches(vcpu);
-	spin_lock(&vcpu->kvm->mmu_lock);
-	++vcpu->kvm->stat.mmu_pte_write;
-	trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
+	return gentry;
+}
+
+/*
+ * 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)
+{
+	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 = 1;
+			flooded = true;
 	} else {
 		vcpu->arch.last_pt_write_gfn = gfn;
 		vcpu->arch.last_pt_write_count = 1;
 		vcpu->arch.last_pte_updated = NULL;
 	}
 
+	return flooded;
+}
+
+/*
+ * Misaligned accesses are too much trouble to fix up; also, they usually
+ * indicate a page is not used as a page table.
+ */
+static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
+				    int bytes)
+{
+	unsigned offset, pte_size, misaligned;
+
+	pgprintk("misaligned: gpa %llx bytes %d role %x\n",
+		 gpa, bytes, sp->role.word);
+
+	offset = offset_in_page(gpa);
+	pte_size = sp->role.cr4_pae ? 8 : 4;
+	misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
+	misaligned |= bytes < 4;
+
+	return misaligned;
+}
+
+static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
+{
+	unsigned page_offset, quadrant;
+	u64 *spte;
+	int level;
+
+	page_offset = offset_in_page(gpa);
+	level = sp->role.level;
+	*nspte = 1;
+	if (!sp->role.cr4_pae) {
+		page_offset <<= 1;	/* 32->64 */
+		/*
+		 * A 32-bit pde maps 4MB while the shadow pdes map
+		 * only 2MB.  So we need to double the offset again
+		 * and zap two pdes instead of one.
+		 */
+		if (level == PT32_ROOT_LEVEL) {
+			page_offset &= ~7; /* kill rounding error */
+			page_offset <<= 1;
+			*nspte = 2;
+		}
+		quadrant = page_offset >> PAGE_SHIFT;
+		page_offset &= ~PAGE_MASK;
+		if (quadrant != sp->role.quadrant)
+			return NULL;
+	}
+
+	spte = &sp->spt[page_offset / sizeof(*spte)];
+	return spte;
+}
+
+void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+		       const u8 *new, int bytes)
+{
+	gfn_t gfn = gpa >> PAGE_SHIFT;
+	union kvm_mmu_page_role mask = { .word = 0 };
+	struct kvm_mmu_page *sp;
+	struct hlist_node *node;
+	LIST_HEAD(invalid_list);
+	u64 entry, gentry, *spte;
+	int npte;
+	bool remote_flush, local_flush, zap_page, flooded, misaligned;
+
+	/*
+	 * If we don't have indirect shadow pages, it means no page is
+	 * write-protected, so we can exit simply.
+	 */
+	if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
+		return;
+
+	zap_page = remote_flush = local_flush = false;
+
+	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
+
+	gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, new, &bytes);
+
+	/*
+	 * No need to care whether allocation memory is successful
+	 * or not since pte prefetch is skiped if it does not have
+	 * enough objects in the cache.
+	 */
+	mmu_topup_memory_caches(vcpu);
+
+	spin_lock(&vcpu->kvm->mmu_lock);
+	++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) {
-		pte_size = sp->role.cr4_pae ? 8 : 4;
-		misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
-		misaligned |= bytes < 4;
+		misaligned = detect_write_misaligned(sp, gpa, bytes);
+
 		if (misaligned || flooded) {
-			/*
-			 * Misaligned accesses are too much trouble to fix
-			 * up; also, they usually indicate a page is not used
-			 * as a page table.
-			 *
-			 * 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.
-			 */
-			pgprintk("misaligned: gpa %llx bytes %d role %x\n",
-				 gpa, bytes, sp->role.word);
 			zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
 						     &invalid_list);
 			++vcpu->kvm->stat.mmu_flooded;
 			continue;
 		}
-		page_offset = offset;
-		level = sp->role.level;
-		npte = 1;
-		if (!sp->role.cr4_pae) {
-			page_offset <<= 1;	/* 32->64 */
-			/*
-			 * A 32-bit pde maps 4MB while the shadow pdes map
-			 * only 2MB.  So we need to double the offset again
-			 * and zap two pdes instead of one.
-			 */
-			if (level == PT32_ROOT_LEVEL) {
-				page_offset &= ~7; /* kill rounding error */
-				page_offset <<= 1;
-				npte = 2;
-			}
-			quadrant = page_offset >> PAGE_SHIFT;
-			page_offset &= ~PAGE_MASK;
-			if (quadrant != sp->role.quadrant)
-				continue;
-		}
+
+		spte = get_written_sptes(sp, gpa, &npte);
+		if (!spte)
+			continue;
+
 		local_flush = true;
-		spte = &sp->spt[page_offset / sizeof(*spte)];
 		while (npte--) {
 			entry = *spte;
 			mmu_page_zap_pte(vcpu->kvm, sp, spte);

index 6e39ec5..13f4d2a 100644
@@ -3601,6 +3601,14 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
 
 	offset = offset_in_page(gpa);
 	pte_size = sp->role.cr4_pae ? 8 : 4;
+
+	/*
+	 * Sometimes, the OS only writes the last one bytes to update status
+	 * bits, for example, in linux, andb instruction is used in clear_bit().
+	 */
+	if (!(offset & (pte_size - 1)) && bytes == 1)
+		return false;
+
 	misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
 	misaligned |= bytes < 4;
 

index 927ba73..9d17238 100644
@@ -239,6 +239,8 @@ struct kvm_mmu_page {
 	int clear_spte_count;
 #endif
 
+	int write_flooding_count;
+
 	struct rcu_head rcu;
 };
 

@@ -353,10 +355,6 @@ 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;
 

121 lines not on this page · raw message

index 9efb860..52e9d58 100644
@@ -497,6 +497,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	     shadow_walk_next(&it)) {
 		gfn_t table_gfn;
 
+		clear_sp_write_flooding_count(it.sptep);
 		drop_large_spte(vcpu, it.sptep);
 
 		sp = NULL;

@@ -522,6 +523,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	     shadow_walk_next(&it)) {
 		gfn_t direct_gfn;
 
+		clear_sp_write_flooding_count(it.sptep);
 		validate_direct_spte(vcpu, it.sptep, direct_access);
 
 		drop_large_spte(vcpu, it.sptep);

@@ -536,6 +538,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 		link_shadow_page(it.sptep, sp);
 	}
 
+	clear_sp_write_flooding_count(it.sptep);
 	mmu_set_spte(vcpu, it.sptep, access, gw->pte_access,
 		     user_fault, write_fault, emulate, it.level,
 		     gw->gfn, pfn, prefault, map_writable);

@@ -599,11 +602,9 @@ 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;
 	}
 

@@ -641,9 +642,6 @@ 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);