Merge commit 'v3.7-rc1' into stable/for-linus-3.7

* commit 'v3.7-rc1': (10892 commits)
  Linux 3.7-rc1
  x86, boot: Explicitly include autoconf.h for hostprogs
  perf: Fix UAPI fallout
  ARM: config: make sure that platforms are ordered by option string
  ARM: config: sort select statements alphanumerically
  UAPI: (Scripted) Disintegrate include/linux/byteorder
  UAPI: (Scripted) Disintegrate include/linux
  UAPI: Unexport linux/blk_types.h
  UAPI: Unexport part of linux/ppp-comp.h
  perf: Handle new rbtree implementation
  procfs: don't need a PATH_MAX allocation to hold a string representation of an int
  vfs: embed struct filename inside of names_cache allocation if possible
  audit: make audit_inode take struct filename
  vfs: make path_openat take a struct filename pointer
  vfs: turn do_path_lookup into wrapper around struct filename variant
  audit: allow audit code to satisfy getname requests from its names_list
  vfs: define struct filename and have getname() return it
  btrfs: Fix compilation with user namespace support enabled
  userns: Fix posix_acl_file_xattr_userns gid conversion
  userns: Properly print bluetooth socket uids
  ...

1 files changed, 83 insertions, 116 deletions

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index bb7cf01cae76..714e2c01a6fe 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -63,10 +63,12 @@
  */
 struct guest_walker {
 	int level;
+	unsigned max_level;
 	gfn_t table_gfn[PT_MAX_FULL_LEVELS];
 	pt_element_t ptes[PT_MAX_FULL_LEVELS];
 	pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
 	gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
+	pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
 	unsigned pt_access;
 	unsigned pte_access;
 	gfn_t gfn;
@@ -101,38 +103,41 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	return (ret != orig_pte);
 }
 
-static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte,
-				   bool last)
+static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
+					     struct kvm_mmu *mmu,
+					     struct guest_walker *walker,
+					     int write_fault)
 {
-	unsigned access;
-
-	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
-	if (last && !is_dirty_gpte(gpte))
-		access &= ~ACC_WRITE_MASK;
-
-#if PTTYPE == 64
-	if (vcpu->arch.mmu.nx)
-		access &= ~(gpte >> PT64_NX_SHIFT);
-#endif
-	return access;
-}
-
-static bool FNAME(is_last_gpte)(struct guest_walker *walker,
-				struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-				pt_element_t gpte)
-{
-	if (walker->level == PT_PAGE_TABLE_LEVEL)
-		return true;
-
-	if ((walker->level == PT_DIRECTORY_LEVEL) && is_large_pte(gpte) &&
-	    (PTTYPE == 64 || is_pse(vcpu)))
-		return true;
+	unsigned level, index;
+	pt_element_t pte, orig_pte;
+	pt_element_t __user *ptep_user;
+	gfn_t table_gfn;
+	int ret;
+
+	for (level = walker->max_level; level >= walker->level; --level) {
+		pte = orig_pte = walker->ptes[level - 1];
+		table_gfn = walker->table_gfn[level - 1];
+		ptep_user = walker->ptep_user[level - 1];
+		index = offset_in_page(ptep_user) / sizeof(pt_element_t);
+		if (!(pte & PT_ACCESSED_MASK)) {
+			trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte));
+			pte |= PT_ACCESSED_MASK;
+		}
+		if (level == walker->level && write_fault && !is_dirty_gpte(pte)) {
+			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
+			pte |= PT_DIRTY_MASK;
+		}
+		if (pte == orig_pte)
+			continue;
 
-	if ((walker->level == PT_PDPE_LEVEL) && is_large_pte(gpte) &&
-	    (mmu->root_level == PT64_ROOT_LEVEL))
-		return true;
+		ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
+		if (ret)
+			return ret;
 
-	return false;
+		mark_page_dirty(vcpu->kvm, table_gfn);
+		walker->ptes[level] = pte;
+	}
+	return 0;
 }
 
 /*
@@ -142,21 +147,22 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 				    gva_t addr, u32 access)
 {
+	int ret;
 	pt_element_t pte;
 	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
-	unsigned index, pt_access, uninitialized_var(pte_access);
+	unsigned index, pt_access, pte_access, accessed_dirty, shift;
 	gpa_t pte_gpa;
-	bool eperm, last_gpte;
 	int offset;
 	const int write_fault = access & PFERR_WRITE_MASK;
 	const int user_fault  = access & PFERR_USER_MASK;
 	const int fetch_fault = access & PFERR_FETCH_MASK;
 	u16 errcode = 0;
+	gpa_t real_gpa;
+	gfn_t gfn;
 
 	trace_kvm_mmu_pagetable_walk(addr, access);
 retry_walk:
-	eperm = false;
 	walker->level = mmu->root_level;
 	pte           = mmu->get_cr3(vcpu);
 
@@ -169,15 +175,21 @@ retry_walk:
 		--walker->level;
 	}
 #endif
+	walker->max_level = walker->level;
 	ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
 	       (mmu->get_cr3(vcpu) & CR3_NONPAE_RESERVED_BITS) == 0);
 
-	pt_access = ACC_ALL;
+	accessed_dirty = PT_ACCESSED_MASK;
+	pt_access = pte_access = ACC_ALL;
+	++walker->level;
 
-	for (;;) {
+	do {
 		gfn_t real_gfn;
 		unsigned long host_addr;
 
+		pt_access &= pte_access;
+		--walker->level;
+
 		index = PT_INDEX(addr, walker->level);
 
 		table_gfn = gpte_to_gfn(pte);
@@ -199,6 +211,7 @@ retry_walk:
 		ptep_user = (pt_element_t __user *)((void *)host_addr + offset);
 		if (unlikely(__copy_from_user(&pte, ptep_user, sizeof(pte))))
 			goto error;
+		walker->ptep_user[walker->level - 1] = ptep_user;
 
 		trace_kvm_mmu_paging_element(pte, walker->level);
 
@@ -211,92 +224,48 @@ retry_walk:
 			goto error;
 		}
 
-		if (!check_write_user_access(vcpu, write_fault, user_fault,
-					  pte))
-			eperm = true;
-
-#if PTTYPE == 64
-		if (unlikely(fetch_fault && (pte & PT64_NX_MASK)))
-			eperm = true;
-#endif
-
-		last_gpte = FNAME(is_last_gpte)(walker, vcpu, mmu, pte);
-		if (last_gpte) {
-			pte_access = pt_access &
-				     FNAME(gpte_access)(vcpu, pte, true);
-			/* check if the kernel is fetching from user page */
-			if (unlikely(pte_access & PT_USER_MASK) &&
-			    kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
-				if (fetch_fault && !user_fault)
-					eperm = true;
-		}
-
-		if (!eperm && unlikely(!(pte & PT_ACCESSED_MASK))) {
-			int ret;
-			trace_kvm_mmu_set_accessed_bit(table_gfn, index,
-						       sizeof(pte));
-			ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index,
-						  pte, pte|PT_ACCESSED_MASK);
-			if (unlikely(ret < 0))
-				goto error;
-			else if (ret)
-				goto retry_walk;
-
-			mark_page_dirty(vcpu->kvm, table_gfn);
-			pte |= PT_ACCESSED_MASK;
-		}
+		accessed_dirty &= pte;
+		pte_access = pt_access & gpte_access(vcpu, pte);
 
 		walker->ptes[walker->level - 1] = pte;
+	} while (!is_last_gpte(mmu, walker->level, pte));
 
-		if (last_gpte) {
-			int lvl = walker->level;
-			gpa_t real_gpa;
-			gfn_t gfn;
-			u32 ac;
-
-			gfn = gpte_to_gfn_lvl(pte, lvl);
-			gfn += (addr & PT_LVL_OFFSET_MASK(lvl)) >> PAGE_SHIFT;
-
-			if (PTTYPE == 32 &&
-			    walker->level == PT_DIRECTORY_LEVEL &&
-			    is_cpuid_PSE36())
-				gfn += pse36_gfn_delta(pte);
-
-			ac = write_fault | fetch_fault | user_fault;
+	if (unlikely(permission_fault(mmu, pte_access, access))) {
+		errcode |= PFERR_PRESENT_MASK;
+		goto error;
+	}
 
-			real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn),
-						      ac);
-			if (real_gpa == UNMAPPED_GVA)
-				return 0;
+	gfn = gpte_to_gfn_lvl(pte, walker->level);
+	gfn += (addr & PT_LVL_OFFSET_MASK(walker->level)) >> PAGE_SHIFT;
 
-			walker->gfn = real_gpa >> PAGE_SHIFT;
+	if (PTTYPE == 32 && walker->level == PT_DIRECTORY_LEVEL && is_cpuid_PSE36())
+		gfn += pse36_gfn_delta(pte);
 
-			break;
-		}
+	real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access);
+	if (real_gpa == UNMAPPED_GVA)
+		return 0;
 
-		pt_access &= FNAME(gpte_access)(vcpu, pte, false);
-		--walker->level;
-	}
+	walker->gfn = real_gpa >> PAGE_SHIFT;
 
-	if (unlikely(eperm)) {
-		errcode |= PFERR_PRESENT_MASK;
-		goto error;
-	}
+	if (!write_fault)
+		protect_clean_gpte(&pte_access, pte);
 
-	if (write_fault && unlikely(!is_dirty_gpte(pte))) {
-		int ret;
+	/*
+	 * On a write fault, fold the dirty bit into accessed_dirty by shifting it one
+	 * place right.
+	 *
+	 * On a read fault, do nothing.
+	 */
+	shift = write_fault >> ilog2(PFERR_WRITE_MASK);
+	shift *= PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT;
+	accessed_dirty &= pte >> shift;
 
-		trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
-		ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index,
-					  pte, pte|PT_DIRTY_MASK);
+	if (unlikely(!accessed_dirty)) {
+		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
 		if (unlikely(ret < 0))
 			goto error;
 		else if (ret)
 			goto retry_walk;
-
-		mark_page_dirty(vcpu->kvm, table_gfn);
-		pte |= PT_DIRTY_MASK;
-		walker->ptes[walker->level - 1] = pte;
 	}
 
 	walker->pt_access = pt_access;
@@ -368,12 +337,11 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		return;
 
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
-	pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte, true);
+	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)) {
-		kvm_release_pfn_clean(pfn);
+	if (mmu_invalid_pfn(pfn))
 		return;
-	}
 
 	/*
 	 * we call mmu_set_spte() with host_writable = true because that
@@ -443,15 +411,13 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 			continue;
 
-		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte,
-								  true);
+		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 (mmu_invalid_pfn(pfn)) {
-			kvm_release_pfn_clean(pfn);
+		if (mmu_invalid_pfn(pfn))
 			break;
-		}
 
 		mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
 			     NULL, PT_PAGE_TABLE_LEVEL, gfn,
@@ -798,7 +764,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		gfn = gpte_to_gfn(gpte);
 		pte_access = sp->role.access;
-		pte_access &= FNAME(gpte_access)(vcpu, gpte, true);
+		pte_access &= gpte_access(vcpu, gpte);
+		protect_clean_gpte(&pte_access, gpte);
 
 		if (sync_mmio_spte(&sp->spt[i], gfn, pte_access, &nr_present))
 			continue;