Skip to contentSkip to conversation

KVM: MMU: fix release noslot pfn

PATCH Applied Xiao Guangrong 3 participants 9 messages Oct 16, 2012 – Oct 29, 2012

Subsystems (5)
x86 KVM PowerPC KVM x86 +1 more subsystems
lore
Share & tools
lore

Xiao Guangrong

author
#0 lore raw

PATCH v5 1/6 KVM: MMU: fix release noslot pfn

We can not directly call kvm_release_pfn_clean to release the pfn since we can meet noslot pfn which is used to cache mmio info into spte

Signed-off-by Xiao Guangrong <[email protected]>
---
 arch/x86/kvm/mmu.c  |    3 +--
 virt/kvm/kvm_main.c |    4 +---
 2 files changed, 2 insertions(+), 5 deletions(-)
arch/x86/kvm/mmu.c +1 -2
index d289fee..6f85fe0 100644
@@ -2497,8 +2497,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		}
 	}
 
-	if (!is_error_pfn(pfn))
-		kvm_release_pfn_clean(pfn);
+	kvm_release_pfn_clean(pfn);
 }
 
 static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
virt/kvm/kvm_main.c +1 -3
index c353b45..a65bc02 100644
@@ -1322,9 +1322,7 @@ EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(pfn_t pfn)
 {
-	WARN_ON(is_error_pfn(pfn));
-
-	if (!kvm_is_mmio_pfn(pfn))
+	if (!is_error_pfn(pfn) && !kvm_is_mmio_pfn(pfn))
 		put_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
Signature · 1 line
1.7.7.6
author
#1 lore raw

PATCH v5 2/6 KVM: MMU: remove mmu_is_invalid

Remove mmu_is_invalid and use is_invalid_pfn instead

Signed-off-by Xiao Guangrong <[email protected]>
---
 arch/x86/kvm/mmu.c         |    5 -----
 arch/x86/kvm/paging_tmpl.h |    4 ++--
 2 files changed, 2 insertions(+), 7 deletions(-)
arch/x86/kvm/mmu.c +0 -5
index 6f85fe0..b8d13d7 100644
@@ -2699,11 +2699,6 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	}
 }
 
-static bool mmu_invalid_pfn(pfn_t pfn)
-{
-	return unlikely(is_invalid_pfn(pfn));
-}
-
 static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 				pfn_t pfn, unsigned access, int *ret_val)
 {
arch/x86/kvm/paging_tmpl.h +2 -2
index 714e2c0..045d31a 100644
@@ -340,7 +340,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	pte_access = sp->role.access & gpte_access(vcpu, gpte);
 	protect_clean_gpte(&pte_access, gpte);
 	pfn = gfn_to_pfn_atomic(vcpu->kvm, gpte_to_gfn(gpte));
-	if (mmu_invalid_pfn(pfn))
+	if (is_invalid_pfn(pfn))
 		return;
 
 	/*

@@ -416,7 +416,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 		gfn = gpte_to_gfn(gpte);
 		pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
 				      pte_access & ACC_WRITE_MASK);
-		if (mmu_invalid_pfn(pfn))
+		if (is_invalid_pfn(pfn))
 			break;
 
 		mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
Signature · 1 line
1.7.7.6
#2 lore raw

Re: [PATCH v5 2/6] KVM: MMU: remove mmu_is_invalid

Quoted 1 line · Xiao Guangrong

Remove mmu_is_invalid and use is_invalid_pfn instead

Applied 2-5 to next; 6 depends on 1, so will wait until it is merged upstream.

Signature · 1 line
error compiling committee.c: too many arguments to function
#3 lore raw

Re: [PATCH v5 2/6] KVM: MMU: remove mmu_is_invalid

Quoted 6 lines · Avi Kivity
Quoted 1 line · Xiao Guangrong

Remove mmu_is_invalid and use is_invalid_pfn instead

Applied 2-5 to next; 6 depends on 1, so will wait until it is merged upstream.

Applied 6.

author
#4 lore raw

PATCH v5 3/6 KVM: MMU: cleanup FNAME(page_fault)

In reply to Xiao Guangrong

Let it return emulate state instead of spte like __direct_map

Signed-off-by Xiao Guangrong <[email protected]>
---
 arch/x86/kvm/paging_tmpl.h |   32 +++++++++++++-------------------
 1 files changed, 13 insertions(+), 19 deletions(-)
arch/x86/kvm/paging_tmpl.h +13 -19
index 045d31a..c555532 100644
@@ -427,21 +427,21 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 
 /*
  * Fetch a shadow pte for a specific level in the paging hierarchy.
+ * If the guest tries to write a write-protected page, we need to
+ * emulate this operation, return 1 to indicate this case.
  */
-static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
+static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
 			 int user_fault, int write_fault, int hlevel,
-			 int *emulate, pfn_t pfn, bool map_writable,
-			 bool prefault)
+			 pfn_t pfn, bool map_writable, bool prefault)
 {
-	unsigned access = gw->pt_access;
 	struct kvm_mmu_page *sp = NULL;
-	int top_level;
-	unsigned direct_access;
 	struct kvm_shadow_walk_iterator it;
+	unsigned direct_access, access = gw->pt_access;
+	int top_level, emulate = 0;
 
 	if (!is_present_gpte(gw->ptes[gw->level - 1]))
-		return NULL;
+		return 0;
 
 	direct_access = gw->pte_access;
 

@@ -505,17 +505,17 @@ static u64 *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,
+		     user_fault, write_fault, &emulate, it.level,
 		     gw->gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 
-	return it.sptep;
+	return emulate;
 
 out_gpte_changed:
 	if (sp)
 		kvm_mmu_put_page(sp, it.sptep);
 	kvm_release_pfn_clean(pfn);
-	return NULL;
+	return 0;
 }
 
 /*

@@ -538,8 +538,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	int write_fault = error_code & PFERR_WRITE_MASK;
 	int user_fault = error_code & PFERR_USER_MASK;
 	struct guest_walker walker;
-	u64 *sptep;
-	int emulate = 0;
 	int r;
 	pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;

@@ -601,17 +599,13 @@ 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);
-	sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
-			     level, &emulate, pfn, map_writable, prefault);
-	(void)sptep;
-	pgprintk("%s: shadow pte %p %llx emulate %d\n", __func__,
-		 sptep, *sptep, emulate);
-
+	r = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
+			 level, pfn, map_writable, prefault);
 	++vcpu->stat.pf_fixed;
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
-	return emulate;
+	return r;
 
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
Signature · 1 line
1.7.7.6
author
#5 lore raw

PATCH v5 4/6 KVM: MMU: move prefetch_invalid_gpte out of pagaing_tmp.h

In reply to Xiao Guangrong

The function does not depend on guest mmu mode, move it out from paging_tmpl.h

Signed-off-by Xiao Guangrong <[email protected]>
---
 arch/x86/kvm/mmu.c         |   36 ++++++++++++++++++++++++++++--------
 arch/x86/kvm/paging_tmpl.h |   26 +++-----------------------
 2 files changed, 31 insertions(+), 31 deletions(-)
arch/x86/kvm/mmu.c +28 -8
index b8d13d7..56c0e39 100644
@@ -2505,6 +2505,14 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
 	mmu_free_roots(vcpu);
 }
 
+static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+	int bit7;
+
+	bit7 = (gpte >> 7) & 1;
+	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
+}
+
 static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 				     bool no_dirty_log)
 {

@@ -2517,6 +2525,26 @@ static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return gfn_to_pfn_memslot_atomic(slot, gfn);
 }
 
+static bool prefetch_invalid_gpte(struct kvm_vcpu *vcpu,
+				  struct kvm_mmu_page *sp, u64 *spte,
+				  u64 gpte)
+{
+	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+		goto no_present;
+
+	if (!is_present_gpte(gpte))
+		goto no_present;
+
+	if (!(gpte & PT_ACCESSED_MASK))
+		goto no_present;
+
+	return false;
+
+no_present:
+	drop_spte(vcpu->kvm, spte);
+	return true;
+}
+
 static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 				    struct kvm_mmu_page *sp,
 				    u64 *start, u64 *end)

@@ -3394,14 +3422,6 @@ static void paging_free(struct kvm_vcpu *vcpu)
 	nonpaging_free(vcpu);
 }
 
-static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
-{
-	int bit7;
-
-	bit7 = (gpte >> 7) & 1;
-	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
-}
-
 static inline void protect_clean_gpte(unsigned *access, unsigned gpte)
 {
 	unsigned mask;
arch/x86/kvm/paging_tmpl.h +3 -23
index c555532..36a80ed 100644
@@ -305,26 +305,6 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker,
 					addr, access);
 }
 
-static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
-				    struct kvm_mmu_page *sp, u64 *spte,
-				    pt_element_t gpte)
-{
-	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
-		goto no_present;
-
-	if (!is_present_gpte(gpte))
-		goto no_present;
-
-	if (!(gpte & PT_ACCESSED_MASK))
-		goto no_present;
-
-	return false;
-
-no_present:
-	drop_spte(vcpu->kvm, spte);
-	return true;
-}
-
 static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			      u64 *spte, const void *pte)
 {

@@ -333,7 +313,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	pfn_t pfn;
 
 	gpte = *(const pt_element_t *)pte;
-	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
+	if (prefetch_invalid_gpte(vcpu, sp, spte, gpte))
 		return;
 
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);

@@ -408,7 +388,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 
 		gpte = gptep[i];
 
-		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
+		if (prefetch_invalid_gpte(vcpu, sp, spte, gpte))
 			continue;
 
 		pte_access = sp->role.access & gpte_access(vcpu, gpte);

@@ -751,7 +731,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 					  sizeof(pt_element_t)))
 			return -EINVAL;
 
-		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
+		if (prefetch_invalid_gpte(vcpu, sp, &sp->spt[i], gpte)) {
 			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
Signature · 1 line
1.7.7.6
author
#6 lore raw

PATCH v5 5/6 KVM: MMU: introduce FNAME(prefetch_gpte)

In reply to Xiao Guangrong

The only difference between FNAME(update_pte) and FNAME(pte_prefetch) is that the former is allowed to prefetch gfn from dirty logged slot, so introduce a common function to prefetch spte

Signed-off-by Xiao Guangrong <[email protected]>
---
 arch/x86/kvm/paging_tmpl.h |   55 +++++++++++++++++++------------------------
 1 files changed, 24 insertions(+), 31 deletions(-)
arch/x86/kvm/paging_tmpl.h +24 -31
index 36a80ed..f887e4c 100644
@@ -305,31 +305,43 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker,
 					addr, access);
 }
 
-static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-			      u64 *spte, const void *pte)
+static bool
+FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+		     u64 *spte, pt_element_t gpte, bool no_dirty_log)
 {
-	pt_element_t gpte;
 	unsigned pte_access;
+	gfn_t gfn;
 	pfn_t pfn;
 
-	gpte = *(const pt_element_t *)pte;
 	if (prefetch_invalid_gpte(vcpu, sp, spte, gpte))
-		return;
+		return false;
 
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
+
+	gfn = gpte_to_gfn(gpte);
 	pte_access = sp->role.access & gpte_access(vcpu, gpte);
 	protect_clean_gpte(&pte_access, gpte);
-	pfn = gfn_to_pfn_atomic(vcpu->kvm, gpte_to_gfn(gpte));
+	pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
+			no_dirty_log && (pte_access & ACC_WRITE_MASK));
 	if (is_invalid_pfn(pfn))
-		return;
+		return false;
 
 	/*
-	 * we call mmu_set_spte() with host_writable = true because that
-	 * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1).
+	 * 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,
-		     NULL, PT_PAGE_TABLE_LEVEL,
-		     gpte_to_gfn(gpte), pfn, true, true);
+		     NULL, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true);
+
+	return true;
+}
+
+static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+			      u64 *spte, const void *pte)
+{
+	pt_element_t gpte = *(const pt_element_t *)pte;
+
+	FNAME(prefetch_gpte)(vcpu, sp, spte, gpte, false);
 }
 
 static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu,

@@ -375,33 +387,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 	spte = sp->spt + i;
 
 	for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) {
-		pt_element_t gpte;
-		unsigned pte_access;
-		gfn_t gfn;
-		pfn_t pfn;
-
 		if (spte == sptep)
 			continue;
 
 		if (is_shadow_present_pte(*spte))
 			continue;
 
-		gpte = gptep[i];
-
-		if (prefetch_invalid_gpte(vcpu, sp, spte, gpte))
-			continue;
-
-		pte_access = sp->role.access & gpte_access(vcpu, gpte);
-		protect_clean_gpte(&pte_access, gpte);
-		gfn = gpte_to_gfn(gpte);
-		pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
-				      pte_access & ACC_WRITE_MASK);
-		if (is_invalid_pfn(pfn))
+		if (!FNAME(prefetch_gpte)(vcpu, sp, spte, gptep[i], true))
 			break;
-
-		mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
-			     NULL, PT_PAGE_TABLE_LEVEL, gfn,
-			     pfn, true, true);
 	}
 }
Signature · 1 line
1.7.7.6
author
#7 lore raw

PATCH v5 6/6 KVM: do not treat noslot pfn as a error pfn

In reply to Xiao Guangrong

This patch filters noslot pfn out from error pfns based on Marcelo comment:
noslot pfn is not a error pfn

After this patch,
- is_noslot_pfn indicates that the gfn is not in slot
- is_error_pfn indicates that the gfn is in slot but the error is occurred when translate the gfn to pfn
- is_error_noslot_pfn indicates that the pfn either it is error pfns or it is noslot pfn
And is_invalid_pfn can be removed, it makes the code more clean

[ The patch has been compiling tested for powerpc ]

Signed-off-by Xiao Guangrong <[email protected]>
---
 arch/powerpc/kvm/book3s_32_mmu_host.c |    2 +-
 arch/powerpc/kvm/book3s_64_mmu_host.c |    2 +-
 arch/powerpc/kvm/e500_tlb.c           |    2 +-
 arch/x86/kvm/mmu.c                    |    4 ++--
 arch/x86/kvm/paging_tmpl.h            |    2 +-
 arch/x86/kvm/x86.c                    |    2 +-
 include/linux/kvm_host.h              |   28 ++++++++++++++++++++--------
 virt/kvm/iommu.c                      |    4 ++--
 virt/kvm/kvm_main.c                   |    6 +++---
 9 files changed, 32 insertions(+), 20 deletions(-)
arch/powerpc/kvm/book3s_32_mmu_host.c +1 -1
index 9fac010..844d591 100644
@@ -155,7 +155,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
-	if (is_error_pfn(hpaddr)) {
+	if (is_error_noslot_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
 				 orig_pte->eaddr);
 		r = -EINVAL;
arch/powerpc/kvm/book3s_64_mmu_host.c +1 -1
index 6b2c80e..53f390f 100644
@@ -92,7 +92,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
-	if (is_error_pfn(hpaddr)) {
+	if (is_error_noslot_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
 		r = -EINVAL;
 		goto out;
arch/powerpc/kvm/e500_tlb.c +1 -1
index c733894..6305ee6 100644
@@ -524,7 +524,7 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	if (likely(!pfnmap)) {
 		unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
 		pfn = gfn_to_pfn_memslot(slot, gfn);
-		if (is_error_pfn(pfn)) {
+		if (is_error_noslot_pfn(pfn)) {
 			printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
 					(long)gfn);
 			return;
arch/x86/kvm/mmu.c +2 -2
index 56c0e39..54c3557 100644
@@ -2699,7 +2699,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	 * PT_PAGE_TABLE_LEVEL and there would be no adjustment done
 	 * here.
 	 */
-	if (!is_error_pfn(pfn) && !kvm_is_mmio_pfn(pfn) &&
+	if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn) &&
 	    level == PT_PAGE_TABLE_LEVEL &&
 	    PageTransCompound(pfn_to_page(pfn)) &&
 	    !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) {

@@ -2733,7 +2733,7 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 	bool ret = true;
 
 	/* The pfn is invalid, report the error! */
-	if (unlikely(is_invalid_pfn(pfn))) {
+	if (unlikely(is_error_pfn(pfn))) {
 		*ret_val = kvm_handle_bad_page(vcpu, gfn, pfn);
 		goto exit;
 	}
arch/x86/kvm/paging_tmpl.h +1 -1
index f887e4c..89f3241 100644
@@ -323,7 +323,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	protect_clean_gpte(&pte_access, gpte);
 	pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
 			no_dirty_log && (pte_access & ACC_WRITE_MASK));
-	if (is_invalid_pfn(pfn))
+	if (is_error_pfn(pfn))
 		return false;
 
 	/*
arch/x86/kvm/x86.c +1 -1
index 841d09b..8b90dd5 100644
@@ -4504,7 +4504,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 	 * instruction -> ...
 	 */
 	pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa));
-	if (!is_error_pfn(pfn)) {
+	if (!is_error_noslot_pfn(pfn)) {
 		kvm_release_pfn_clean(pfn);
 		return true;
 	}
include/linux/kvm_host.h +20 -8
index 6afc5be..e235068 100644
@@ -58,28 +58,40 @@
 
 /*
  * For the normal pfn, the highest 12 bits should be zero,
- * so we can mask these bits to indicate the error.
+ * so we can mask bit 62 ~ bit 52  to indicate the error pfn,
+ * mask bit 63 to indicate the noslot pfn.
  */
-#define KVM_PFN_ERR_MASK	(0xfffULL << 52)
+#define KVM_PFN_ERR_MASK	(0x7ffULL << 52)
+#define KVM_PFN_ERR_NOSLOT_MASK	(0xfffULL << 52)
+#define KVM_PFN_NOSLOT		(0x1ULL << 63)
 
 #define KVM_PFN_ERR_FAULT	(KVM_PFN_ERR_MASK)
 #define KVM_PFN_ERR_HWPOISON	(KVM_PFN_ERR_MASK + 1)
-#define KVM_PFN_ERR_BAD		(KVM_PFN_ERR_MASK + 2)
-#define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 3)
+#define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 2)
 
+/*
+ * error pfns indicate that the gfn is in slot but faild to
+ * translate it to pfn on host.
+ */
 static inline bool is_error_pfn(pfn_t pfn)
 {
 	return !!(pfn & KVM_PFN_ERR_MASK);
 }
 
-static inline bool is_noslot_pfn(pfn_t pfn)
+/*
+ * error_noslot pfns indicate that the gfn can not be
+ * translated to pfn - it is not in slot or failed to
+ * translate it to pfn.
+ */
+static inline bool is_error_noslot_pfn(pfn_t pfn)
 {
-	return pfn == KVM_PFN_ERR_BAD;
+	return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK);
 }
 
-static inline bool is_invalid_pfn(pfn_t pfn)
+/* noslot pfn indicates that the gfn is not in slot. */
+static inline bool is_noslot_pfn(pfn_t pfn)
 {
-	return !is_noslot_pfn(pfn) && is_error_pfn(pfn);
+	return pfn == KVM_PFN_NOSLOT;
 }
 
 #define KVM_HVA_ERR_BAD		(PAGE_OFFSET)
virt/kvm/iommu.c +2 -2
index 18e1e30..4a340cb 100644
@@ -52,7 +52,7 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
 	end_gfn = gfn + (size >> PAGE_SHIFT);
 	gfn    += 1;
 
-	if (is_error_pfn(pfn))
+	if (is_error_noslot_pfn(pfn))
 		return pfn;
 
 	while (gfn < end_gfn)

@@ -106,7 +106,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 		 * important because we unmap and unpin in 4kb steps later.
 		 */
 		pfn = kvm_pin_pages(slot, gfn, page_size);
-		if (is_error_pfn(pfn)) {
+		if (is_error_noslot_pfn(pfn)) {
 			gfn += 1;
 			continue;
 		}
virt/kvm/kvm_main.c +3 -3
index a65bc02..e26a55f 100644
@@ -1208,7 +1208,7 @@ __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic,
 		return KVM_PFN_ERR_RO_FAULT;
 
 	if (kvm_is_error_hva(addr))
-		return KVM_PFN_ERR_BAD;
+		return KVM_PFN_NOSLOT;
 
 	/* Do not map writable pfn in the readonly memslot. */
 	if (writable && memslot_is_readonly(slot)) {

@@ -1290,7 +1290,7 @@ EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
 
 static struct page *kvm_pfn_to_page(pfn_t pfn)
 {
-	if (is_error_pfn(pfn))
+	if (is_error_noslot_pfn(pfn))
 		return KVM_ERR_PTR_BAD_PAGE;
 
 	if (kvm_is_mmio_pfn(pfn)) {

@@ -1322,7 +1322,7 @@ EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(pfn_t pfn)
 {
-	if (!is_error_pfn(pfn) && !kvm_is_mmio_pfn(pfn))
+	if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn))
 		put_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
Signature · 1 line
1.7.7.6
Applied
#8 lore raw
In reply to Xiao Guangrong
Quoted 3 lines · Xiao Guangrong

We can not directly call kvm_release_pfn_clean to release the pfn since we can meet noslot pfn which is used to cache mmio info into spte

Applied to master for 3.7, 3.6, thanks.

Signature · 1 line
error compiling committee.c: too many arguments to function