Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Paolo Bonzini:
 "A collection of x86 and ARM bugfixes, and some improvements to
  documentation.

  On top of this, a cleanup of kvm_para.h headers, which were exported
  by some architectures even though they not support KVM at all. This is
  responsible for all the Kbuild changes in the diffstat"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
  Documentation: kvm: clarify KVM_SET_USER_MEMORY_REGION
  KVM: doc: Document the life cycle of a VM and its resources
  KVM: selftests: complete IO before migrating guest state
  KVM: selftests: disable stack protector for all KVM tests
  KVM: selftests: explicitly disable PIE for tests
  KVM: selftests: assert on exit reason in CR4/cpuid sync test
  KVM: x86: update %rip after emulating IO
  x86/kvm/hyper-v: avoid spurious pending stimer on vCPU init
  kvm/x86: Move MSR_IA32_ARCH_CAPABILITIES to array emulated_msrs
  KVM: x86: Emulate MSR_IA32_ARCH_CAPABILITIES on AMD hosts
  kvm: don't redefine flags as something else
  kvm: mmu: Used range based flushing in slot_handle_level_range
  KVM: export <linux/kvm_para.h> and <asm/kvm_para.h> iif KVM is supported
  KVM: x86: remove check on nr_mmu_pages in kvm_arch_commit_memory_region()
  kvm: nVMX: Add a vmentry check for HOST_SYSENTER_ESP and HOST_SYSENTER_EIP fields
  KVM: SVM: Workaround errata#1096 (insn_len maybe zero on SMAP violation)
  KVM: Reject device ioctls from processes other than the VM's creator
  KVM: doc: Fix incorrect word ordering regarding supported use of APIs
  KVM: x86: fix handling of role.cr4_pae and rename it to 'gpte_size'
  KVM: nVMX: Do not inherit quadrant and invalid for the root shadow EPT
  ...

1 files changed, 37 insertions, 17 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 7837ab001d80..eee455a8a612 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -182,7 +182,7 @@ struct kvm_shadow_walk_iterator {
 
 static const union kvm_mmu_page_role mmu_base_role_mask = {
 	.cr0_wp = 1,
-	.cr4_pae = 1,
+	.gpte_is_8_bytes = 1,
 	.nxe = 1,
 	.smep_andnot_wp = 1,
 	.smap_andnot_wp = 1,
@@ -2205,6 +2205,7 @@ static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 				    struct list_head *invalid_list);
 
+
 #define for_each_valid_sp(_kvm, _sp, _gfn)				\
 	hlist_for_each_entry(_sp,					\
 	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
@@ -2215,12 +2216,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	for_each_valid_sp(_kvm, _sp, _gfn)				\
 		if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else
 
+static inline bool is_ept_sp(struct kvm_mmu_page *sp)
+{
+	return sp->role.cr0_wp && sp->role.smap_andnot_wp;
+}
+
 /* @sp->gfn should be write-protected at the call site */
 static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			    struct list_head *invalid_list)
 {
-	if (sp->role.cr4_pae != !!is_pae(vcpu)
-	    || vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
+	if ((!is_ept_sp(sp) && sp->role.gpte_is_8_bytes != !!is_pae(vcpu)) ||
+	    vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
 		kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
 		return false;
 	}
@@ -2423,7 +2429,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	role.level = level;
 	role.direct = direct;
 	if (role.direct)
-		role.cr4_pae = 0;
+		role.gpte_is_8_bytes = true;
 	role.access = access;
 	if (!vcpu->arch.mmu->direct_map
 	    && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
@@ -4794,7 +4800,6 @@ static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu,
 
 	role.base.access = ACC_ALL;
 	role.base.nxe = !!is_nx(vcpu);
-	role.base.cr4_pae = !!is_pae(vcpu);
 	role.base.cr0_wp = is_write_protection(vcpu);
 	role.base.smm = is_smm(vcpu);
 	role.base.guest_mode = is_guest_mode(vcpu);
@@ -4815,6 +4820,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
 	role.base.ad_disabled = (shadow_accessed_mask == 0);
 	role.base.level = kvm_x86_ops->get_tdp_level(vcpu);
 	role.base.direct = true;
+	role.base.gpte_is_8_bytes = true;
 
 	return role;
 }
@@ -4879,6 +4885,7 @@ kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
 	role.base.smap_andnot_wp = role.ext.cr4_smap &&
 		!is_write_protection(vcpu);
 	role.base.direct = !is_paging(vcpu);
+	role.base.gpte_is_8_bytes = !!is_pae(vcpu);
 
 	if (!is_long_mode(vcpu))
 		role.base.level = PT32E_ROOT_LEVEL;
@@ -4918,18 +4925,26 @@ static union kvm_mmu_role
 kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
 				   bool execonly)
 {
-	union kvm_mmu_role role;
+	union kvm_mmu_role role = {0};
 
-	/* Base role is inherited from root_mmu */
-	role.base.word = vcpu->arch.root_mmu.mmu_role.base.word;
-	role.ext = kvm_calc_mmu_role_ext(vcpu);
+	/* SMM flag is inherited from root_mmu */
+	role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm;
 
 	role.base.level = PT64_ROOT_4LEVEL;
+	role.base.gpte_is_8_bytes = true;
 	role.base.direct = false;
 	role.base.ad_disabled = !accessed_dirty;
 	role.base.guest_mode = true;
 	role.base.access = ACC_ALL;
 
+	/*
+	 * WP=1 and NOT_WP=1 is an impossible combination, use WP and the
+	 * SMAP variation to denote shadow EPT entries.
+	 */
+	role.base.cr0_wp = true;
+	role.base.smap_andnot_wp = true;
+
+	role.ext = kvm_calc_mmu_role_ext(vcpu);
 	role.ext.execonly = execonly;
 
 	return role;
@@ -5179,7 +5194,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
 		 gpa, bytes, sp->role.word);
 
 	offset = offset_in_page(gpa);
-	pte_size = sp->role.cr4_pae ? 8 : 4;
+	pte_size = sp->role.gpte_is_8_bytes ? 8 : 4;
 
 	/*
 	 * Sometimes, the OS only writes the last one bytes to update status
@@ -5203,7 +5218,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
 	page_offset = offset_in_page(gpa);
 	level = sp->role.level;
 	*nspte = 1;
-	if (!sp->role.cr4_pae) {
+	if (!sp->role.gpte_is_8_bytes) {
 		page_offset <<= 1;	/* 32->64 */
 		/*
 		 * A 32-bit pde maps 4MB while the shadow pdes map
@@ -5393,10 +5408,12 @@ emulate:
 	 * This can happen if a guest gets a page-fault on data access but the HW
 	 * table walker is not able to read the instruction page (e.g instruction
 	 * page is not present in memory). In those cases we simply restart the
-	 * guest.
+	 * guest, with the exception of AMD Erratum 1096 which is unrecoverable.
 	 */
-	if (unlikely(insn && !insn_len))
-		return 1;
+	if (unlikely(insn && !insn_len)) {
+		if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu))
+			return 1;
+	}
 
 	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
 
@@ -5509,7 +5526,9 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
 
 		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
 			if (flush && lock_flush_tlb) {
-				kvm_flush_remote_tlbs(kvm);
+				kvm_flush_remote_tlbs_with_address(kvm,
+						start_gfn,
+						iterator.gfn - start_gfn + 1);
 				flush = false;
 			}
 			cond_resched_lock(&kvm->mmu_lock);
@@ -5517,7 +5536,8 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	}
 
 	if (flush && lock_flush_tlb) {
-		kvm_flush_remote_tlbs(kvm);
+		kvm_flush_remote_tlbs_with_address(kvm, start_gfn,
+						   end_gfn - start_gfn + 1);
 		flush = false;
 	}
 
@@ -6011,7 +6031,7 @@ out:
 /*
  * Calculate mmu pages needed for kvm.
  */
-unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
+unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
 {
 	unsigned int nr_mmu_pages;
 	unsigned int  nr_pages = 0;