Merge branch 'for-5.11/elecom' into for-linus

- support for EX-G M-XGL20DLBK device, from YOSHIOKA Takuma

1 files changed, 30 insertions, 20 deletions

diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 4dd6b1e5b8cf..50e268eb8e1a 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -550,7 +550,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	 * 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, pte_access, 0, PG_LEVEL_4K, gfn, pfn,
+	mmu_set_spte(vcpu, spte, pte_access, false, PG_LEVEL_4K, gfn, pfn,
 		     true, true);
 
 	kvm_release_pfn_clean(pfn);
@@ -625,15 +625,18 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  * emulate this operation, return 1 to indicate this case.
  */
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
-			 struct guest_walker *gw,
-			 int write_fault, int max_level,
-			 kvm_pfn_t pfn, bool map_writable, bool prefault,
-			 bool lpage_disallowed)
+			 struct guest_walker *gw, u32 error_code,
+			 int max_level, kvm_pfn_t pfn, bool map_writable,
+			 bool prefault)
 {
+	bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled();
+	bool write_fault = error_code & PFERR_WRITE_MASK;
+	bool exec = error_code & PFERR_FETCH_MASK;
+	bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled;
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
 	unsigned direct_access, access = gw->pt_access;
-	int top_level, hlevel, ret;
+	int top_level, level, req_level, ret;
 	gfn_t base_gfn = gw->gfn;
 
 	direct_access = gw->pte_access;
@@ -679,7 +682,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			link_shadow_page(vcpu, it.sptep, sp);
 	}
 
-	hlevel = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn);
+	level = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn,
+					huge_page_disallowed, &req_level);
 
 	trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
 
@@ -690,10 +694,12 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 		 * We cannot overwrite existing page tables with an NX
 		 * large page, as the leaf could be executable.
 		 */
-		disallowed_hugepage_adjust(it, gw->gfn, &pfn, &hlevel);
+		if (nx_huge_page_workaround_enabled)
+			disallowed_hugepage_adjust(*it.sptep, gw->gfn, it.level,
+						   &pfn, &level);
 
 		base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
-		if (it.level == hlevel)
+		if (it.level == level)
 			break;
 
 		validate_direct_spte(vcpu, it.sptep, direct_access);
@@ -704,13 +710,16 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
 					      it.level - 1, true, direct_access);
 			link_shadow_page(vcpu, it.sptep, sp);
-			if (lpage_disallowed)
+			if (huge_page_disallowed && req_level >= it.level)
 				account_huge_nx_page(vcpu->kvm, sp);
 		}
 	}
 
 	ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
 			   it.level, base_gfn, pfn, prefault, map_writable);
+	if (ret == RET_PF_SPURIOUS)
+		return ret;
+
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 	++vcpu->stat.pf_fixed;
 	return ret;
@@ -738,7 +747,7 @@ out_gpte_changed:
  */
 static bool
 FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
-			      struct guest_walker *walker, int user_fault,
+			      struct guest_walker *walker, bool user_fault,
 			      bool *write_fault_to_shadow_pgtable)
 {
 	int level;
@@ -776,15 +785,13 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
 static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 			     bool prefault)
 {
-	int write_fault = error_code & PFERR_WRITE_MASK;
-	int user_fault = error_code & PFERR_USER_MASK;
+	bool write_fault = error_code & PFERR_WRITE_MASK;
+	bool user_fault = error_code & PFERR_USER_MASK;
 	struct guest_walker walker;
 	int r;
 	kvm_pfn_t pfn;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
-	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
-				is_nx_huge_page_enabled();
 	int max_level;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
@@ -825,7 +832,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
 	      &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);
 
-	if (lpage_disallowed || is_self_change_mapping)
+	if (is_self_change_mapping)
 		max_level = PG_LEVEL_4K;
 	else
 		max_level = walker.level;
@@ -869,8 +876,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
-	r = FNAME(fetch)(vcpu, addr, &walker, write_fault, max_level, pfn,
-			 map_writable, prefault, lpage_disallowed);
+	r = FNAME(fetch)(vcpu, addr, &walker, error_code, max_level, pfn,
+			 map_writable, prefault);
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 
 out_unlock:
@@ -895,6 +902,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 {
 	struct kvm_shadow_walk_iterator iterator;
 	struct kvm_mmu_page *sp;
+	u64 old_spte;
 	int level;
 	u64 *sptep;
 
@@ -917,7 +925,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 		sptep = iterator.sptep;
 
 		sp = sptep_to_sp(sptep);
-		if (is_last_spte(*sptep, level)) {
+		old_spte = *sptep;
+		if (is_last_spte(old_spte, level)) {
 			pt_element_t gpte;
 			gpa_t pte_gpa;
 
@@ -927,7 +936,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 			pte_gpa = FNAME(get_level1_sp_gpa)(sp);
 			pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
 
-			if (mmu_page_zap_pte(vcpu->kvm, sp, sptep))
+			mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL);
+			if (is_shadow_present_pte(old_spte))
 				kvm_flush_remote_tlbs_with_address(vcpu->kvm,
 					sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level));