[PATCH v5 5/9] KVM: MMU: introduce SPTE_MMU_WRITEABLE bit

[Xiao Guangrong]

This bit indicates whether the spte can be writable on MMU, that means
the corresponding gpte is writable and the corresponding gfn is not
protected by shadow page protection

Signed-off-by: Xiao Guangrong <xiaoguangrong@xxxxxxxxxxxxxxxxxx>
---
 arch/x86/kvm/mmu.c |   43 +++++++++++++++++++++++++++++--------------
 1 files changed, 29 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4810992..bd837f3 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -145,7 +145,8 @@ module_param(dbg, bool, 0644);
 #define CREATE_TRACE_POINTS
 #include "mmutrace.h"

-#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
+#define SPTE_HOST_WRITEABLE	(1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
+#define SPTE_MMU_WRITEABLE	(1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))

 #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)

@@ -1065,32 +1066,45 @@ static void drop_spte(struct kvm *kvm, u64 *sptep)
 		rmap_remove(kvm, sptep);
 }

+static bool spte_can_be_writable(u64 spte)
+{
+	u64 mask = SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE;
+
+	return (spte & mask) == mask;
+}
+
 /* Return true if the spte is dropped. */
-static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush)
+static bool
+spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
 {
 	u64 spte = *sptep;

-	if (!is_writable_pte(spte))
+	if (!is_writable_pte(spte) &&
+	      !(pt_protect && spte_can_be_writable(spte)))
 		return false;

 	rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep);

-	*flush |= true;
 	if (is_large_pte(spte)) {
 		WARN_ON(page_header(__pa(sptep))->role.level ==
 		       PT_PAGE_TABLE_LEVEL);
+
+		*flush |= true;
 		drop_spte(kvm, sptep);
 		--kvm->stat.lpages;
 		return true;
 	}

+	if (pt_protect)
+		spte &= ~SPTE_MMU_WRITEABLE;
 	spte = spte & ~PT_WRITABLE_MASK;
-	mmu_spte_update(sptep, spte);
+
+	*flush = mmu_spte_update(sptep, spte);
 	return false;
 }

-static bool
-__rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, int level)
+static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
+				 int level, bool pt_protect)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1098,7 +1112,7 @@ __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, int level)

 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
 		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-		if (spte_write_protect(kvm, sptep, &flush)) {
+		if (spte_write_protect(kvm, sptep, &flush, pt_protect)) {
 			sptep = rmap_get_first(*rmapp, &iter);
 			continue;
 		}
@@ -1127,7 +1141,7 @@ void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,

 	while (mask) {
 		rmapp = &slot->rmap[gfn_offset + __ffs(mask)];
-		__rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL);
+		__rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL, false);

 		/* clear the first set bit */
 		mask &= mask - 1;
@@ -1146,7 +1160,7 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
 	for (i = PT_PAGE_TABLE_LEVEL;
 	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
 		rmapp = __gfn_to_rmap(gfn, i, slot);
-		write_protected |= __rmap_write_protect(kvm, rmapp, i);
+		write_protected |= __rmap_write_protect(kvm, rmapp, i, true);
 	}

 	return write_protected;
@@ -2284,8 +2298,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		spte |= shadow_x_mask;
 	else
 		spte |= shadow_nx_mask;
+
 	if (pte_access & ACC_USER_MASK)
 		spte |= shadow_user_mask;
+
 	if (level > PT_PAGE_TABLE_LEVEL)
 		spte |= PT_PAGE_SIZE_MASK;
 	if (tdp_enabled)
@@ -2310,7 +2326,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			goto done;
 		}

-		spte |= PT_WRITABLE_MASK;
+		spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;

 		if (!vcpu->arch.mmu.direct_map
 		    && !(pte_access & ACC_WRITE_MASK)) {
@@ -2339,8 +2355,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 				 __func__, gfn);
 			ret = 1;
 			pte_access &= ~ACC_WRITE_MASK;
-			if (is_writable_pte(spte))
-				spte &= ~PT_WRITABLE_MASK;
+			spte &= ~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE);
 		}
 	}

@@ -3921,7 +3936,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
 			      !is_last_spte(pt[i], sp->role.level))
 				continue;

-			spte_write_protect(kvm, &pt[i], &flush);
+			spte_write_protect(kvm, &pt[i], &flush, false);
 		}
 	}
 	kvm_flush_remote_tlbs(kvm);
-- 
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/