Merge branch 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (202 commits)
  MAINTAINERS: update KVM entry
  KVM: correct error-handling code
  KVM: fix compile warnings on s390
  KVM: VMX: Check cpl before emulating debug register access
  KVM: fix misreporting of coalesced interrupts by kvm tracer
  KVM: x86: drop duplicate kvm_flush_remote_tlb calls
  KVM: VMX: call vmx_load_host_state() only if msr is cached
  KVM: VMX: Conditionally reload debug register 6
  KVM: Use thread debug register storage instead of kvm specific data
  KVM guest: do not batch pte updates from interrupt context
  KVM: Fix coalesced interrupt reporting in IOAPIC
  KVM guest: fix bogus wallclock physical address calculation
  KVM: VMX: Fix cr8 exiting control clobbering by EPT
  KVM: Optimize kvm_mmu_unprotect_page_virt() for tdp
  KVM: Document KVM_CAP_IRQCHIP
  KVM: Protect update_cr8_intercept() when running without an apic
  KVM: VMX: Fix EPT with WP bit change during paging
  KVM: Use kvm_{read,write}_guest_virt() to read and write segment descriptors
  KVM: x86 emulator: Add adc and sbb missing decoder flags
  KVM: Add missing #include
  ...

1 files changed, 74 insertions, 67 deletions

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 67785f635399..d2fec9c12d22 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -27,7 +27,8 @@
 	#define guest_walker guest_walker64
 	#define FNAME(name) paging##64_##name
 	#define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
-	#define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK
+	#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
+	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
 	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
 	#define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level)
 	#define PT_LEVEL_BITS PT64_LEVEL_BITS
@@ -43,7 +44,8 @@
 	#define guest_walker guest_walker32
 	#define FNAME(name) paging##32_##name
 	#define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK
-	#define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK
+	#define PT_LVL_ADDR_MASK(lvl) PT32_LVL_ADDR_MASK(lvl)
+	#define PT_LVL_OFFSET_MASK(lvl) PT32_LVL_OFFSET_MASK(lvl)
 	#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
 	#define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level)
 	#define PT_LEVEL_BITS PT32_LEVEL_BITS
@@ -53,8 +55,8 @@
 	#error Invalid PTTYPE value
 #endif
 
-#define gpte_to_gfn FNAME(gpte_to_gfn)
-#define gpte_to_gfn_pde FNAME(gpte_to_gfn_pde)
+#define gpte_to_gfn_lvl FNAME(gpte_to_gfn_lvl)
+#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PT_PAGE_TABLE_LEVEL)
 
 /*
  * The guest_walker structure emulates the behavior of the hardware page
@@ -71,14 +73,9 @@ struct guest_walker {
 	u32 error_code;
 };
 
-static gfn_t gpte_to_gfn(pt_element_t gpte)
+static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
 {
-	return (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
-}
-
-static gfn_t gpte_to_gfn_pde(pt_element_t gpte)
-{
-	return (gpte & PT_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
+	return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
 }
 
 static bool FNAME(cmpxchg_gpte)(struct kvm *kvm,
@@ -125,14 +122,16 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 	gpa_t pte_gpa;
 	int rsvd_fault = 0;
 
-	pgprintk("%s: addr %lx\n", __func__, addr);
+	trace_kvm_mmu_pagetable_walk(addr, write_fault, user_fault,
+				     fetch_fault);
 walk:
 	walker->level = vcpu->arch.mmu.root_level;
 	pte = vcpu->arch.cr3;
 #if PTTYPE == 64
 	if (!is_long_mode(vcpu)) {
-		pte = vcpu->arch.pdptrs[(addr >> 30) & 3];
-		if (!is_present_pte(pte))
+		pte = kvm_pdptr_read(vcpu, (addr >> 30) & 3);
+		trace_kvm_mmu_paging_element(pte, walker->level);
+		if (!is_present_gpte(pte))
 			goto not_present;
 		--walker->level;
 	}
@@ -150,12 +149,11 @@ walk:
 		pte_gpa += index * sizeof(pt_element_t);
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
-		pgprintk("%s: table_gfn[%d] %lx\n", __func__,
-			 walker->level - 1, table_gfn);
 
 		kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte));
+		trace_kvm_mmu_paging_element(pte, walker->level);
 
-		if (!is_present_pte(pte))
+		if (!is_present_gpte(pte))
 			goto not_present;
 
 		rsvd_fault = is_rsvd_bits_set(vcpu, pte, walker->level);
@@ -175,6 +173,8 @@ walk:
 #endif
 
 		if (!(pte & PT_ACCESSED_MASK)) {
+			trace_kvm_mmu_set_accessed_bit(table_gfn, index,
+						       sizeof(pte));
 			mark_page_dirty(vcpu->kvm, table_gfn);
 			if (FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn,
 			    index, pte, pte|PT_ACCESSED_MASK))
@@ -186,18 +186,24 @@ walk:
 
 		walker->ptes[walker->level - 1] = pte;
 
-		if (walker->level == PT_PAGE_TABLE_LEVEL) {
-			walker->gfn = gpte_to_gfn(pte);
-			break;
-		}
-
-		if (walker->level == PT_DIRECTORY_LEVEL
-		    && (pte & PT_PAGE_SIZE_MASK)
-		    && (PTTYPE == 64 || is_pse(vcpu))) {
-			walker->gfn = gpte_to_gfn_pde(pte);
-			walker->gfn += PT_INDEX(addr, PT_PAGE_TABLE_LEVEL);
-			if (PTTYPE == 32 && is_cpuid_PSE36())
+		if ((walker->level == PT_PAGE_TABLE_LEVEL) ||
+		    ((walker->level == PT_DIRECTORY_LEVEL) &&
+				(pte & PT_PAGE_SIZE_MASK)  &&
+				(PTTYPE == 64 || is_pse(vcpu))) ||
+		    ((walker->level == PT_PDPE_LEVEL) &&
+				(pte & PT_PAGE_SIZE_MASK)  &&
+				is_long_mode(vcpu))) {
+			int lvl = walker->level;
+
+			walker->gfn = gpte_to_gfn_lvl(pte, lvl);
+			walker->gfn += (addr & PT_LVL_OFFSET_MASK(lvl))
+					>> PAGE_SHIFT;
+
+			if (PTTYPE == 32 &&
+			    walker->level == PT_DIRECTORY_LEVEL &&
+			    is_cpuid_PSE36())
 				walker->gfn += pse36_gfn_delta(pte);
+
 			break;
 		}
 
@@ -205,9 +211,10 @@ walk:
 		--walker->level;
 	}
 
-	if (write_fault && !is_dirty_pte(pte)) {
+	if (write_fault && !is_dirty_gpte(pte)) {
 		bool ret;
 
+		trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
 		mark_page_dirty(vcpu->kvm, table_gfn);
 		ret = FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte,
 			    pte|PT_DIRTY_MASK);
@@ -239,6 +246,7 @@ err:
 		walker->error_code |= PFERR_FETCH_MASK;
 	if (rsvd_fault)
 		walker->error_code |= PFERR_RSVD_MASK;
+	trace_kvm_mmu_walker_error(walker->error_code);
 	return 0;
 }
 
@@ -248,12 +256,11 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
 	pt_element_t gpte;
 	unsigned pte_access;
 	pfn_t pfn;
-	int largepage = vcpu->arch.update_pte.largepage;
 
 	gpte = *(const pt_element_t *)pte;
 	if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
-		if (!is_present_pte(gpte))
-			set_shadow_pte(spte, shadow_notrap_nonpresent_pte);
+		if (!is_present_gpte(gpte))
+			__set_spte(spte, shadow_notrap_nonpresent_pte);
 		return;
 	}
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
@@ -267,7 +274,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
 		return;
 	kvm_get_pfn(pfn);
 	mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
-		     gpte & PT_DIRTY_MASK, NULL, largepage,
+		     gpte & PT_DIRTY_MASK, NULL, PT_PAGE_TABLE_LEVEL,
 		     gpte_to_gfn(gpte), pfn, true);
 }
 
@@ -276,7 +283,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
  */
 static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
-			 int user_fault, int write_fault, int largepage,
+			 int user_fault, int write_fault, int hlevel,
 			 int *ptwrite, pfn_t pfn)
 {
 	unsigned access = gw->pt_access;
@@ -289,19 +296,18 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	pt_element_t curr_pte;
 	struct kvm_shadow_walk_iterator iterator;
 
-	if (!is_present_pte(gw->ptes[gw->level - 1]))
+	if (!is_present_gpte(gw->ptes[gw->level - 1]))
 		return NULL;
 
 	for_each_shadow_entry(vcpu, addr, iterator) {
 		level = iterator.level;
 		sptep = iterator.sptep;
-		if (level == PT_PAGE_TABLE_LEVEL
-		    || (largepage && level == PT_DIRECTORY_LEVEL)) {
+		if (iterator.level == hlevel) {
 			mmu_set_spte(vcpu, sptep, access,
 				     gw->pte_access & access,
 				     user_fault, write_fault,
 				     gw->ptes[gw->level-1] & PT_DIRTY_MASK,
-				     ptwrite, largepage,
+				     ptwrite, level,
 				     gw->gfn, pfn, false);
 			break;
 		}
@@ -311,16 +317,19 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 
 		if (is_large_pte(*sptep)) {
 			rmap_remove(vcpu->kvm, sptep);
-			set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
+			__set_spte(sptep, shadow_trap_nonpresent_pte);
 			kvm_flush_remote_tlbs(vcpu->kvm);
 		}
 
-		if (level == PT_DIRECTORY_LEVEL
-		    && gw->level == PT_DIRECTORY_LEVEL) {
+		if (level <= gw->level) {
+			int delta = level - gw->level + 1;
 			direct = 1;
-			if (!is_dirty_pte(gw->ptes[level - 1]))
+			if (!is_dirty_gpte(gw->ptes[level - delta]))
 				access &= ~ACC_WRITE_MASK;
-			table_gfn = gpte_to_gfn(gw->ptes[level - 1]);
+			table_gfn = gpte_to_gfn(gw->ptes[level - delta]);
+			/* advance table_gfn when emulating 1gb pages with 4k */
+			if (delta == 0)
+				table_gfn += PT_INDEX(addr, level);
 		} else {
 			direct = 0;
 			table_gfn = gw->table_gfn[level - 2];
@@ -369,11 +378,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	int user_fault = error_code & PFERR_USER_MASK;
 	int fetch_fault = error_code & PFERR_FETCH_MASK;
 	struct guest_walker walker;
-	u64 *shadow_pte;
+	u64 *sptep;
 	int write_pt = 0;
 	int r;
 	pfn_t pfn;
-	int largepage = 0;
+	int level = PT_PAGE_TABLE_LEVEL;
 	unsigned long mmu_seq;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
@@ -399,14 +408,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 		return 0;
 	}
 
-	if (walker.level == PT_DIRECTORY_LEVEL) {
-		gfn_t large_gfn;
-		large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1);
-		if (is_largepage_backed(vcpu, large_gfn)) {
-			walker.gfn = large_gfn;
-			largepage = 1;
-		}
+	if (walker.level >= PT_DIRECTORY_LEVEL) {
+		level = min(walker.level, mapping_level(vcpu, walker.gfn));
+		walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
 	}
+
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 	pfn = gfn_to_pfn(vcpu->kvm, walker.gfn);
@@ -422,11 +428,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	if (mmu_notifier_retry(vcpu, mmu_seq))
 		goto out_unlock;
 	kvm_mmu_free_some_pages(vcpu);
-	shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
-				  largepage, &write_pt, pfn);
-
+	sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
+			     level, &write_pt, pfn);
 	pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__,
-		 shadow_pte, *shadow_pte, write_pt);
+		 sptep, *sptep, write_pt);
 
 	if (!write_pt)
 		vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
@@ -459,8 +464,9 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 		sptep = iterator.sptep;
 
 		/* FIXME: properly handle invlpg on large guest pages */
-		if (level == PT_PAGE_TABLE_LEVEL ||
-		    ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) {
+		if (level == PT_PAGE_TABLE_LEVEL  ||
+		    ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) ||
+		    ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) {
 			struct kvm_mmu_page *sp = page_header(__pa(sptep));
 
 			pte_gpa = (sp->gfn << PAGE_SHIFT);
@@ -472,7 +478,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 					--vcpu->kvm->stat.lpages;
 				need_flush = 1;
 			}
-			set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
+			__set_spte(sptep, shadow_trap_nonpresent_pte);
 			break;
 		}
 
@@ -489,7 +495,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 	if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
 				  sizeof(pt_element_t)))
 		return;
-	if (is_present_pte(gpte) && (gpte & PT_ACCESSED_MASK)) {
+	if (is_present_gpte(gpte) && (gpte & PT_ACCESSED_MASK)) {
 		if (mmu_topup_memory_caches(vcpu))
 			return;
 		kvm_mmu_pte_write(vcpu, pte_gpa, (const u8 *)&gpte,
@@ -536,7 +542,7 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
 		r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa, pt, sizeof pt);
 		pte_gpa += ARRAY_SIZE(pt) * sizeof(pt_element_t);
 		for (j = 0; j < ARRAY_SIZE(pt); ++j)
-			if (r || is_present_pte(pt[j]))
+			if (r || is_present_gpte(pt[j]))
 				sp->spt[i+j] = shadow_trap_nonpresent_pte;
 			else
 				sp->spt[i+j] = shadow_notrap_nonpresent_pte;
@@ -574,23 +580,23 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 					  sizeof(pt_element_t)))
 			return -EINVAL;
 
-		if (gpte_to_gfn(gpte) != gfn || !is_present_pte(gpte) ||
+		if (gpte_to_gfn(gpte) != gfn || !is_present_gpte(gpte) ||
 		    !(gpte & PT_ACCESSED_MASK)) {
 			u64 nonpresent;
 
 			rmap_remove(vcpu->kvm, &sp->spt[i]);
-			if (is_present_pte(gpte))
+			if (is_present_gpte(gpte))
 				nonpresent = shadow_trap_nonpresent_pte;
 			else
 				nonpresent = shadow_notrap_nonpresent_pte;
-			set_shadow_pte(&sp->spt[i], nonpresent);
+			__set_spte(&sp->spt[i], nonpresent);
 			continue;
 		}
 
 		nr_present++;
 		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
 		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
-			 is_dirty_pte(gpte), 0, gfn,
+			 is_dirty_gpte(gpte), PT_PAGE_TABLE_LEVEL, gfn,
 			 spte_to_pfn(sp->spt[i]), true, false);
 	}
 
@@ -603,9 +609,10 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 #undef PT_BASE_ADDR_MASK
 #undef PT_INDEX
 #undef PT_LEVEL_MASK
-#undef PT_DIR_BASE_ADDR_MASK
+#undef PT_LVL_ADDR_MASK
+#undef PT_LVL_OFFSET_MASK
 #undef PT_LEVEL_BITS
 #undef PT_MAX_FULL_LEVELS
 #undef gpte_to_gfn
-#undef gpte_to_gfn_pde
+#undef gpte_to_gfn_lvl
 #undef CMPXCHG