KVM: MMU: cleanup mapping-level

In order to detecting spte remapping, we can simply check whether the spte has already been pointing to the pfn even if the spte is not the last spte for middle spte is pointing to the kernel pfn which can not be mapped to userspace

Also, update slot and stat.lpages iff the spte is not remapped

Signed-off-by Xiao Guangrong <[email protected]>

---
 arch/x86/kvm/mmu.c |   40 +++++++++++++---------------------------
 1 files changed, 13 insertions(+), 27 deletions(-)

arch/x86/kvm/mmu.c +1 -6

index 692ebb1..4ea731e 100644
@@ -2420,8 +2420,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			 pfn_t pfn, bool speculative,
 			 bool host_writable)
 {
-	int was_rmapped = 0;
-	int rmap_count;
+	bool was_rmapped = false;
 
 	pgprintk("%s: spte %llx access %x write_fault %d"
 		 " user_fault %d gfn %llx\n",

@@ -2429,25 +2428,13 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		 write_fault, user_fault, gfn);
 
 	if (is_rmap_spte(*sptep)) {
-		/*
-		 * If we overwrite a PTE page pointer with a 2MB PMD, unlink
-		 * the parent of the now unreachable PTE.
-		 */

Quoted 41 lines · Xiao Guangrong

In order to detecting spte remapping, we can simply check whether the spte has already been pointing to the pfn even if the spte is not the last spte for middle spte is pointing to the kernel pfn which can not be mapped to userspace

Also, update slot and stat.lpages iff the spte is not remapped

Signed-off-by Xiao Guangrong <[email protected]>

---
 arch/x86/kvm/mmu.c |   40 +++++++++++++---------------------------
 1 files changed, 13 insertions(+), 27 deletions(-)

arch/x86/kvm/mmu.c +3 -10

index 692ebb1..4ea731e 100644
@@ -2420,8 +2420,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			 pfn_t pfn, bool speculative,
 			 bool host_writable)
 {
-	int was_rmapped = 0;
-	int rmap_count;
+	bool was_rmapped = false;
 
 	pgprintk("%s: spte %llx access %x write_fault %d"
 		 " user_fault %d gfn %llx\n",

@@ -2429,25 +2428,13 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		 write_fault, user_fault, gfn);
 
 	if (is_rmap_spte(*sptep)) {
-		/*
-		 * If we overwrite a PTE page pointer with a 2MB PMD, unlink
-		 * the parent of the now unreachable PTE.
-		 */
-		if (level > PT_PAGE_TABLE_LEVEL &&
-		    !is_large_pte(*sptep)) {
-			struct kvm_mmu_page *child;
-			u64 pte = *sptep;
+		if (pfn != spte_to_pfn(*sptep)) {
+			struct kvm_mmu_page *sp = page_header(__pa(sptep));
 

arch/x86/kvm/mmu.c static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, · line 2443

Quoted 3 lines

arch/x86/kvm/mmu.c +0 -3

-			child = page_header(pte & PT64_BASE_ADDR_MASK);
-			drop_parent_pte(child, sptep);
-			kvm_flush_remote_tlbs(vcpu->kvm);

How come its safe to drop this case?

Quoted 42 lines · Marcelo Tosatti

Quoted 41 lines · Xiao Guangrong

In order to detecting spte remapping, we can simply check whether the spte has already been pointing to the pfn even if the spte is not the last spte for middle spte is pointing to the kernel pfn which can not be mapped to userspace

Also, update slot and stat.lpages iff the spte is not remapped

Signed-off-by Xiao Guangrong <[email protected]>

---
 arch/x86/kvm/mmu.c |   40 +++++++++++++---------------------------
 1 files changed, 13 insertions(+), 27 deletions(-)

arch/x86/kvm/mmu.c +3 -10

index 692ebb1..4ea731e 100644
@@ -2420,8 +2420,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			 pfn_t pfn, bool speculative,
 			 bool host_writable)
 {
-	int was_rmapped = 0;
-	int rmap_count;
+	bool was_rmapped = false;
 
 	pgprintk("%s: spte %llx access %x write_fault %d"
 		 " user_fault %d gfn %llx\n",

@@ -2429,25 +2428,13 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		 write_fault, user_fault, gfn);
 
 	if (is_rmap_spte(*sptep)) {
-		/*
-		 * If we overwrite a PTE page pointer with a 2MB PMD, unlink
-		 * the parent of the now unreachable PTE.
-		 */
-		if (level > PT_PAGE_TABLE_LEVEL &&
-		    !is_large_pte(*sptep)) {
-			struct kvm_mmu_page *child;
-			u64 pte = *sptep;
+		if (pfn != spte_to_pfn(*sptep)) {
+			struct kvm_mmu_page *sp = page_header(__pa(sptep));
 

Quoted 5 lines

arch/x86/kvm/mmu.c static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, · line 2443

Quoted 3 lines

arch/x86/kvm/mmu.c +0 -3

-			child = page_header(pte & PT64_BASE_ADDR_MASK);
-			drop_parent_pte(child, sptep);
-			kvm_flush_remote_tlbs(vcpu->kvm);

How come its safe to drop this case?

We use "if (pfn != spte_to_pfn(*sptep))" to simplify the thing. There are two cases:
1) the sptep is not the last mapping.
under this case, sptep must point to a shadow page table, that means spte_to_pfn(*sptep)) is used by KVM module, and 'pfn' is used by userspace. so, 'if' condition must be satisfied, the sptep will be dropped.

Actually, This is the origin case:
| if (level > PT_PAGE_TABLE_LEVEL &&
| !is_large_pte(*sptep))"

2) the sptep is the last mapping.
under this case, the level of spte (sp.level) must equal the 'level' which we pass to mmu_set_spte. If they point to the same pfn, it is 'remap', otherwise we drop it.

I think this is safe. :)

Quoted 17 lines

Quoted 5 lines

arch/x86/kvm/mmu.c static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, · line 2443

Quoted 3 lines

arch/x86/kvm/mmu.c +0 -3

-			child = page_header(pte & PT64_BASE_ADDR_MASK);
-			drop_parent_pte(child, sptep);
-			kvm_flush_remote_tlbs(vcpu->kvm);

How come its safe to drop this case?

We use "if (pfn != spte_to_pfn(*sptep))" to simplify the thing. There are two cases:
1) the sptep is not the last mapping.
under this case, sptep must point to a shadow page table, that means spte_to_pfn(*sptep)) is used by KVM module, and 'pfn' is used by userspace. so, 'if' condition must be satisfied, the sptep will be dropped.

Actually, This is the origin case:
| if (level > PT_PAGE_TABLE_LEVEL &&
| !is_large_pte(*sptep))"

Quoted 6 lines

2) the sptep is the last mapping.
under this case, the level of spte (sp.level) must equal the 'level' which we pass to mmu_set_spte. If they point to the same pfn, it is 'remap', otherwise we drop it.

I think this is safe. :)

mmu_page_zap_pte takes care of it, OK.

What if was_rmapped=true but gfn is different? Say if the spte comes from an unsync shadow page, the guest modifies that shadow page (but does not invalidate it with invlpg), then faults. gfn can still point to the same gfn (but in that case, with your patch, page_header_update_slot is not called.

Quoted 24 lines · Marcelo Tosatti

Quoted 17 lines

Quoted 5 lines

arch/x86/kvm/mmu.c static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, · line 2443

Quoted 3 lines

arch/x86/kvm/mmu.c +0 -3

-			child = page_header(pte & PT64_BASE_ADDR_MASK);
-			drop_parent_pte(child, sptep);
-			kvm_flush_remote_tlbs(vcpu->kvm);

How come its safe to drop this case?

We use "if (pfn != spte_to_pfn(*sptep))" to simplify the thing. There are two cases:
1) the sptep is not the last mapping.
under this case, sptep must point to a shadow page table, that means spte_to_pfn(*sptep)) is used by KVM module, and 'pfn' is used by userspace. so, 'if' condition must be satisfied, the sptep will be dropped.

Actually, This is the origin case:
| if (level > PT_PAGE_TABLE_LEVEL &&
| !is_large_pte(*sptep))"

Quoted 6 lines

2) the sptep is the last mapping.
under this case, the level of spte (sp.level) must equal the 'level' which we pass to mmu_set_spte. If they point to the same pfn, it is 'remap', otherwise we drop it.

I think this is safe. :)

Quoted 7 lines

mmu_page_zap_pte takes care of it, OK.

What if was_rmapped=true but gfn is different? Say if the spte comes from an unsync shadow page, the guest modifies that shadow page (but does not invalidate it with invlpg), then faults. gfn can still point to the same gfn (but in that case, with your patch, page_header_update_slot is not called.

Marcelo,

Page fault path and other sync/prefetch paths will reread guest page table, then it get a different target pfn.

The scenario is like this:

gfn1 = pfn1, gfn2 = pfn2
gpte = pfn1, spte is shadowed by gpte and it is a unsync spte

Guest Host

                                     spte = (gfn1, pfn1)

modify gpte to let it point to gfn2

                                    spte = (gfn1, pfn1)

page-fault on gpte
intercept the page-fault, then want to update spte to (gfn2, pfn2)

in mmu_set_spte, we can detect pfn2 != pfn1, then drop it.

Hmm, the interesting thing is what if different gfns map to the same pfn. For example, spte1 is shadowed by gfn1 and spte2 is shadowed by pfn2, both gfn1 and gfn2 map to pfn, the code (including the current code) will set spte1 to the gfn2's rmap and spte2 to the gfn1's rmap. But i think it is ok.

Quoted 53 lines · Xiao Guangrong

Quoted 24 lines · Marcelo Tosatti

Quoted 17 lines

Quoted 5 lines

arch/x86/kvm/mmu.c static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, · line 2443

Quoted 3 lines

arch/x86/kvm/mmu.c +0 -3

-			child = page_header(pte & PT64_BASE_ADDR_MASK);
-			drop_parent_pte(child, sptep);
-			kvm_flush_remote_tlbs(vcpu->kvm);

How come its safe to drop this case?

We use "if (pfn != spte_to_pfn(*sptep))" to simplify the thing. There are two cases:
1) the sptep is not the last mapping.
under this case, sptep must point to a shadow page table, that means spte_to_pfn(*sptep)) is used by KVM module, and 'pfn' is used by userspace. so, 'if' condition must be satisfied, the sptep will be dropped.

Actually, This is the origin case:
| if (level > PT_PAGE_TABLE_LEVEL &&
| !is_large_pte(*sptep))"

Quoted 6 lines

2) the sptep is the last mapping.
under this case, the level of spte (sp.level) must equal the 'level' which we pass to mmu_set_spte. If they point to the same pfn, it is 'remap', otherwise we drop it.

I think this is safe. :)

Quoted 7 lines

mmu_page_zap_pte takes care of it, OK.

What if was_rmapped=true but gfn is different? Say if the spte comes from an unsync shadow page, the guest modifies that shadow page (but does not invalidate it with invlpg), then faults. gfn can still point to the same gfn (but in that case, with your patch, page_header_update_slot is not called.

Marcelo,

Page fault path and other sync/prefetch paths will reread guest page table, then it get a different target pfn.

The scenario is like this:

gfn1 = pfn1, gfn2 = pfn2
gpte = pfn1, spte is shadowed by gpte and it is a unsync spte

Guest Host

                                     spte = (gfn1, pfn1)

modify gpte to let it point to gfn2

                                    spte = (gfn1, pfn1)

page-fault on gpte
intercept the page-fault, then want to update spte to (gfn2, pfn2)

Quoted 7 lines

in mmu_set_spte, we can detect pfn2 != pfn1, then drop it.

Hmm, the interesting thing is what if different gfns map to the same pfn. For example, spte1 is shadowed by gfn1 and spte2 is shadowed by pfn2, both gfn1 and gfn2 map to pfn, the code (including the current code) will set spte1 to the gfn2's rmap and spte2 to the gfn1's rmap. But i think it is ok.

Current code updates gfn properly in set_spte by
page_header_update_slot.

Better keep state properly.

It is more cleaner if we can update pte_access fist then set spte according to pte_access, also introduce gfn_need_write_protect to check whether the gfn need to be write-protected

Signed-off-by Xiao Guangrong <[email protected]>

 arch/x86/kvm/mmu.c |  109 ++++++++++++++++++++++++++++++++--------------------
 1 files changed, 67 insertions(+), 42 deletions(-)

arch/x86/kvm/mmu.c +67 -42

index 4ea731e..49957df 100644
@@ -2329,6 +2329,63 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return 0;
 }
 
+static bool gfn_need_write_protect(struct kvm_vcpu *vcpu, u64 *sptep,
+				   int level,  gfn_t gfn, bool can_unsync)
+{
+	/*
+	 * 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.
+	 * Same reasoning can be applied to dirty page accounting.
+	 */
+	if (!can_unsync && is_writable_pte(*sptep))
+		return false;
+
+	if ((level > PT_PAGE_TABLE_LEVEL &&
+	   has_wrprotected_page(vcpu->kvm, gfn, level)) ||
+	      mmu_need_write_protect(vcpu, gfn, can_unsync))
+		return true;
+
+	return false;
+}
+
+/* The return value indicates whether the @gfn need to be write protected. */
+static bool vcpu_adjust_access(struct kvm_vcpu *vcpu, u64 *sptep,
+			       unsigned *pte_access, int user_fault,
+			       int write_fault, int level, gfn_t gfn,
+			       bool can_unsync, bool host_writable)
+{
+	bool ret = false;
+	unsigned access = *pte_access;
+
+	if (!host_writable)
+		access &= ~ACC_WRITE_MASK;
+
+	if (!(access & ACC_WRITE_MASK) && (!vcpu->arch.mmu.direct_map &&
+	      write_fault && !is_write_protection(vcpu) && !user_fault)) {
+		access |= ACC_WRITE_MASK;
+		access &= ~ACC_USER_MASK;
+
+		/*
+		 * If we converted a user page to a kernel page,
+		 * so that the kernel can write to it when cr0.wp=0,
+		 * then we should prevent the kernel from executing it
+		 * if SMEP is enabled.
+		 */
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
+			access &= ~ACC_EXEC_MASK;
+	}
+
+	if ((access & ACC_WRITE_MASK) &&
+		  gfn_need_write_protect(vcpu, sptep, level, gfn, can_unsync)) {
+		access &= ~ACC_WRITE_MASK;
+		ret = true;
+	}
+
+	*pte_access = access;
+	return ret;
+}
+
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    unsigned pte_access, int user_fault,
 		    int write_fault, int level,

@@ -2341,6 +2398,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (set_mmio_spte(sptep, gfn, pfn, pte_access))
 		return 0;
 
+	ret = vcpu_adjust_access(vcpu, sptep, &pte_access, user_fault,
+		      write_fault, level, gfn, can_unsync, host_writable);
+
 	spte = PT_PRESENT_MASK;
 	if (!speculative)
 		spte |= shadow_accessed_mask;

@@ -2353,61 +2413,26 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (pte_access & ACC_USER_MASK)
 		spte |= shadow_user_mask;
 
+	if (pte_access & ACC_WRITE_MASK) {
+		spte |= PT_WRITABLE_MASK;
+		spte |= SPTE_MMU_WRITEABLE;
+	}
+
 	if (level > PT_PAGE_TABLE_LEVEL)
 		spte |= PT_PAGE_SIZE_MASK;
+
 	if (tdp_enabled)
 		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
 			kvm_is_mmio_pfn(pfn));
 
 	if (host_writable)
 		spte |= SPTE_HOST_WRITEABLE;
-	else
-		pte_access &= ~ACC_WRITE_MASK;
 
 	spte |= (u64)pfn << PAGE_SHIFT;
 
-	if ((pte_access & ACC_WRITE_MASK)
-	    || (!vcpu->arch.mmu.direct_map && write_fault
-		&& !is_write_protection(vcpu) && !user_fault)) {
-		spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
-
-		if (!vcpu->arch.mmu.direct_map
-		    && !(pte_access & ACC_WRITE_MASK)) {
-			spte &= ~PT_USER_MASK;
-			/*
-			 * If we converted a user page to a kernel page,
-			 * so that the kernel can write to it when cr0.wp=0,
-			 * then we should prevent the kernel from executing it
-			 * if SMEP is enabled.
-			 */
-			if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
-				spte |= PT64_NX_MASK;
-		}
-
-		/*
-		 * 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.
-		 * Same reasoning can be applied to dirty page accounting.
-		 */
-		if (!can_unsync && is_writable_pte(*sptep))
-			goto set_pte;
-
-		if ((level > PT_PAGE_TABLE_LEVEL &&
-		   has_wrprotected_page(vcpu->kvm, gfn, level)) ||
-		      mmu_need_write_protect(vcpu, gfn, can_unsync)) {
-			pgprintk("%s: found shadow page for %llx, marking ro\n",
-				 __func__, gfn);
-			ret = 1;
-			pte_access &= ~ACC_WRITE_MASK;
-			spte &= ~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE);
-		}
-	}
-
-	if (pte_access & ACC_WRITE_MASK)
+	if (is_writable_pte(spte))
 		mark_page_dirty(vcpu->kvm, gfn);
 
-set_pte:
 	if (mmu_spte_update(sptep, spte))
 		kvm_flush_remote_tlbs(vcpu->kvm);
 	return ret;

Signature · 6 lines

1.7.7.6

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

Quoted 5 lines · Xiao Guangrong

It is more cleaner if we can update pte_access fist then set spte according to pte_access, also introduce gfn_need_write_protect to check whether the gfn need to be write-protected

Signed-off-by Xiao Guangrong <[email protected]>

Please separate patch in:
- code movement with no logical modification.
- logical modification (such as condition for mark_page_dirty).
- move code to helper functions.

Then, no mmu specified code exists in the common function and drop two parameters in set_spte

Signed-off-by Xiao Guangrong <[email protected]>

 arch/x86/kvm/mmu.c         |   42 +++++++++++-------------------------------
 arch/x86/kvm/paging_tmpl.h |   25 ++++++++++++++++++++-----
 2 files changed, 31 insertions(+), 36 deletions(-)

arch/x86/kvm/mmu.c +11 -31

index 49957df..4229e78 100644
@@ -2351,8 +2351,7 @@ static bool gfn_need_write_protect(struct kvm_vcpu *vcpu, u64 *sptep,
 
 /* The return value indicates whether the @gfn need to be write protected. */
 static bool vcpu_adjust_access(struct kvm_vcpu *vcpu, u64 *sptep,
-			       unsigned *pte_access, int user_fault,
-			       int write_fault, int level, gfn_t gfn,
+			       unsigned *pte_access, int level, gfn_t gfn,
 			       bool can_unsync, bool host_writable)
 {
 	bool ret = false;

@@ -2361,21 +2360,6 @@ static bool vcpu_adjust_access(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (!host_writable)
 		access &= ~ACC_WRITE_MASK;
 
-	if (!(access & ACC_WRITE_MASK) && (!vcpu->arch.mmu.direct_map &&
-	      write_fault && !is_write_protection(vcpu) && !user_fault)) {
-		access |= ACC_WRITE_MASK;
-		access &= ~ACC_USER_MASK;
-
-		/*
-		 * If we converted a user page to a kernel page,
-		 * so that the kernel can write to it when cr0.wp=0,
-		 * then we should prevent the kernel from executing it
-		 * if SMEP is enabled.
-		 */
-		if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
-			access &= ~ACC_EXEC_MASK;
-	}
-
 	if ((access & ACC_WRITE_MASK) &&
 		  gfn_need_write_protect(vcpu, sptep, level, gfn, can_unsync)) {
 		access &= ~ACC_WRITE_MASK;

@@ -2387,8 +2371,7 @@ static bool vcpu_adjust_access(struct kvm_vcpu *vcpu, u64 *sptep,
 }
 
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
-		    unsigned pte_access, int user_fault,
-		    int write_fault, int level,
+		    unsigned pte_access, int level,
 		    gfn_t gfn, pfn_t pfn, bool speculative,
 		    bool can_unsync, bool host_writable)
 {

@@ -2398,8 +2381,8 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (set_mmio_spte(sptep, gfn, pfn, pte_access))
 		return 0;
 
-	ret = vcpu_adjust_access(vcpu, sptep, &pte_access, user_fault,
-		      write_fault, level, gfn, can_unsync, host_writable);
+	ret = vcpu_adjust_access(vcpu, sptep, &pte_access, level, gfn,
+				 can_unsync, host_writable);
 
 	spte = PT_PRESENT_MASK;
 	if (!speculative)

@@ -2440,17 +2423,14 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			 unsigned pt_access, unsigned pte_access,
-			 int user_fault, int write_fault,
-			 int *emulate, int level, gfn_t gfn,
-			 pfn_t pfn, bool speculative,
+			 int write_fault, int *emulate, int level,
+			 gfn_t gfn, pfn_t pfn, bool speculative,
 			 bool host_writable)
 {
 	bool was_rmapped = false;
 
-	pgprintk("%s: spte %llx access %x write_fault %d"
-		 " user_fault %d gfn %llx\n",
-		 __func__, *sptep, pt_access,
-		 write_fault, user_fault, gfn);
+	pgprintk("%s: spte %llx access %x write_fault %d gfn %llx\n",
+		 __func__, *sptep, pt_access, write_fault, gfn);
 
 	if (is_rmap_spte(*sptep)) {
 		if (pfn != spte_to_pfn(*sptep)) {

@@ -2462,7 +2442,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			was_rmapped = true;
 	}
 
-	if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
+	if (set_spte(vcpu, sptep, pte_access,
 		      level, gfn, pfn, speculative, true,
 		      host_writable)) {
 		if (write_fault)

@@ -2556,7 +2536,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 
 	for (i = 0; i < ret; i++, gfn++, start++)
 		mmu_set_spte(vcpu, start, ACC_ALL,
-			     access, 0, 0, NULL,
+			     access, 0, NULL,
 			     sp->role.level, gfn,
 			     page_to_pfn(pages[i]), true, true);
 

@@ -2620,7 +2600,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 			unsigned pte_access = ACC_ALL;
 
 			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, pte_access,
-				     0, write, &emulate,
+				     write, &emulate,
 				     level, gfn, pfn, prefault, map_writable);
 			direct_pte_prefetch(vcpu, iterator.sptep);
 			++vcpu->stat.pf_fixed;

arch/x86/kvm/paging_tmpl.h +8 -3

index 891eb6d..b1bcd68 100644
@@ -330,7 +330,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	 * we call mmu_set_spte() with host_writable = true because
 	 * pte_prefetch_gfn_to_pfn always gets a writable pfn.
 	 */
-	mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
+	mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0,
 		     NULL, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true);
 
 	return true;

@@ -405,7 +405,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  */
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
-			 int user_fault, int write_fault, int hlevel,
+			 int write_fault, int hlevel,
 			 pfn_t pfn, bool map_writable, bool prefault)
 {
 	struct kvm_mmu_page *sp = NULL;

@@ -478,7 +478,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 
 	clear_sp_write_flooding_count(it.sptep);
 	mmu_set_spte(vcpu, it.sptep, access, gw->pte_access,
-		     user_fault, write_fault, &emulate, it.level,
+		     write_fault, &emulate, it.level,
 		     gw->gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 

@@ -544,6 +544,21 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 		return 0;
 	}
 
+	if (write_fault && !(walker.pte_access & ACC_WRITE_MASK) &&
+	      !is_write_protection(vcpu) && !user_fault) {
+		walker.pte_access |= ACC_WRITE_MASK;
+		walker.pte_access &= ~ACC_USER_MASK;
+

arch/x86/kvm/paging_tmpl.h +2 -2

 	if (walker.level >= PT_DIRECTORY_LEVEL)
 		force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn);
 	else

@@ -572,7 +587,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	kvm_mmu_free_some_pages(vcpu);
 	if (!force_pt_level)
 		transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level);
-	r = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
+	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
 			 level, pfn, map_writable, prefault);
 	++vcpu->stat.pf_fixed;
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);

@@ -747,7 +762,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE;
 
-		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
+		set_spte(vcpu, &sp->spt[i], pte_access,
 			 PT_PAGE_TABLE_LEVEL, gfn,
 			 spte_to_pfn(sp->spt[i]), true, false,
 			 host_writable);

Signature · 6 lines

1.7.7.6

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

Quoted 13 lines

arch/x86/kvm/paging_tmpl.h +9 -0

@@ -544,6 +544,21 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 		return 0;
 	}
 
+	if (write_fault && !(walker.pte_access & ACC_WRITE_MASK) &&
+	      !is_write_protection(vcpu) && !user_fault) {
+		walker.pte_access |= ACC_WRITE_MASK;
+		walker.pte_access &= ~ACC_USER_MASK;
+
+		/*
+		 * If we converted a user page to a kernel page,
+		 * so that the kernel can write to it when cr0.wp=0,
+		 * then we should prevent the kernel from executing it

arch/x86/kvm/paging_tmpl.h static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, · line 561

Quoted 6 lines

arch/x86/kvm/paging_tmpl.h +6 -0

+		 * if SMEP is enabled.
+		 */
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
+			walker.pte_access &= ~ACC_EXEC_MASK;
+	}
+

What about sync_page path?