--- zzzz-none-000/linux-3.10.107/arch/x86/kvm/paging_tmpl.h	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/arch/x86/kvm/paging_tmpl.h	2021-02-04 17:41:59.000000000 +0000
@@ -23,6 +23,13 @@
  * so the code in this file is compiled twice, once per pte size.
  */
 
+/*
+ * This is used to catch non optimized PT_GUEST_(DIRTY|ACCESS)_SHIFT macro
+ * uses for EPT without A/D paging type.
+ */
+extern u64 __pure __using_nonexistent_pte_bit(void)
+	       __compiletime_error("wrong use of PT_GUEST_(DIRTY|ACCESS)_SHIFT");
+
 #if PTTYPE == 64
 	#define pt_element_t u64
 	#define guest_walker guest_walker64
@@ -32,6 +39,10 @@
 	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
 	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
 	#define PT_LEVEL_BITS PT64_LEVEL_BITS
+	#define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK
+	#define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
+	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#ifdef CONFIG_X86_64
 	#define PT_MAX_FULL_LEVELS 4
 	#define CMPXCHG cmpxchg
@@ -49,7 +60,26 @@
 	#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
 	#define PT_LEVEL_BITS PT32_LEVEL_BITS
 	#define PT_MAX_FULL_LEVELS 2
+	#define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK
+	#define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
+	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#define CMPXCHG cmpxchg
+#elif PTTYPE == PTTYPE_EPT
+	#define pt_element_t u64
+	#define guest_walker guest_walkerEPT
+	#define FNAME(name) ept_##name
+	#define PT_BASE_ADDR_MASK PT64_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_BITS PT64_LEVEL_BITS
+	#define PT_GUEST_ACCESSED_MASK 0
+	#define PT_GUEST_DIRTY_MASK 0
+	#define PT_GUEST_DIRTY_SHIFT __using_nonexistent_pte_bit()
+	#define PT_GUEST_ACCESSED_SHIFT __using_nonexistent_pte_bit()
+	#define CMPXCHG cmpxchg64
+	#define PT_MAX_FULL_LEVELS 4
 #else
 	#error Invalid PTTYPE value
 #endif
@@ -69,6 +99,7 @@
 	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];
+	bool pte_writable[PT_MAX_FULL_LEVELS];
 	unsigned pt_access;
 	unsigned pte_access;
 	gfn_t gfn;
@@ -80,6 +111,32 @@
 	return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
 }
 
+static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte)
+{
+	unsigned mask;
+
+	/* dirty bit is not supported, so no need to track it */
+	if (!PT_GUEST_DIRTY_MASK)
+		return;
+
+	BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
+
+	mask = (unsigned)~ACC_WRITE_MASK;
+	/* Allow write access to dirty gptes */
+	mask |= (gpte >> (PT_GUEST_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) &
+		PT_WRITABLE_MASK;
+	*access &= mask;
+}
+
+static inline int FNAME(is_present_gpte)(unsigned long pte)
+{
+#if PTTYPE != PTTYPE_EPT
+	return is_present_gpte(pte);
+#else
+	return pte & 7;
+#endif
+}
+
 static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			       pt_element_t __user *ptep_user, unsigned index,
 			       pt_element_t orig_pte, pt_element_t new_pte)
@@ -103,6 +160,42 @@
 	return (ret != orig_pte);
 }
 
+static bool FNAME(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 (!FNAME(is_present_gpte)(gpte))
+		goto no_present;
+
+	/* if accessed bit is not supported prefetch non accessed gpte */
+	if (PT_GUEST_ACCESSED_MASK && !(gpte & PT_GUEST_ACCESSED_MASK))
+		goto no_present;
+
+	return false;
+
+no_present:
+	drop_spte(vcpu->kvm, spte);
+	return true;
+}
+
+static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte)
+{
+	unsigned access;
+#if PTTYPE == PTTYPE_EPT
+	access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) |
+		((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) |
+		ACC_USER_MASK;
+#else
+	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
+	access &= ~(gpte >> PT64_NX_SHIFT);
+#endif
+
+	return access;
+}
+
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
@@ -114,28 +207,49 @@
 	gfn_t table_gfn;
 	int ret;
 
+	/* dirty/accessed bits are not supported, so no need to update them */
+	if (!PT_GUEST_DIRTY_MASK)
+		return 0;
+
 	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)) {
+		if (!(pte & PT_GUEST_ACCESSED_MASK)) {
 			trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte));
-			pte |= PT_ACCESSED_MASK;
+			pte |= PT_GUEST_ACCESSED_MASK;
 		}
-		if (level == walker->level && write_fault && !is_dirty_gpte(pte)) {
+		if (level == walker->level && write_fault &&
+				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
-			pte |= PT_DIRTY_MASK;
+			pte |= PT_GUEST_DIRTY_MASK;
 		}
 		if (pte == orig_pte)
 			continue;
 
+		/*
+		 * If the slot is read-only, simply do not process the accessed
+		 * and dirty bits.  This is the correct thing to do if the slot
+		 * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
+		 * are only supported if the accessed and dirty bits are already
+		 * set in the ROM (so that MMIO writes are never needed).
+		 *
+		 * Note that NPT does not allow this at all and faults, since
+		 * it always wants nested page table entries for the guest
+		 * page tables to be writable.  And EPT works but will simply
+		 * overwrite the read-only memory to set the accessed and dirty
+		 * bits.
+		 */
+		if (unlikely(!walker->pte_writable[level - 1]))
+			continue;
+
 		ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
 		if (ret)
 			return ret;
 
-		mark_page_dirty(vcpu->kvm, table_gfn);
-		walker->ptes[level] = pte;
+		kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
+		walker->ptes[level - 1] = pte;
 	}
 	return 0;
 }
@@ -170,16 +284,15 @@
 	if (walker->level == PT32E_ROOT_LEVEL) {
 		pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
 		trace_kvm_mmu_paging_element(pte, walker->level);
-		if (!is_present_gpte(pte))
+		if (!FNAME(is_present_gpte)(pte))
 			goto error;
 		--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);
+	ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
 
-	accessed_dirty = PT_ACCESSED_MASK;
+	accessed_dirty = PT_GUEST_ACCESSED_MASK;
 	pt_access = pte_access = ACC_ALL;
 	++walker->level;
 
@@ -199,12 +312,26 @@
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
 		real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
-					      PFERR_USER_MASK|PFERR_WRITE_MASK);
+					      PFERR_USER_MASK|PFERR_WRITE_MASK,
+					      &walker->fault);
+
+		/*
+		 * FIXME: This can happen if emulation (for of an INS/OUTS
+		 * instruction) triggers a nested page fault.  The exit
+		 * qualification / exit info field will incorrectly have
+		 * "guest page access" as the nested page fault's cause,
+		 * instead of "guest page structure access".  To fix this,
+		 * the x86_exception struct should be augmented with enough
+		 * information to fix the exit_qualification or exit_info_1
+		 * fields.
+		 */
 		if (unlikely(real_gfn == UNMAPPED_GVA))
-			goto error;
+			return 0;
+
 		real_gfn = gpa_to_gfn(real_gfn);
 
-		host_addr = gfn_to_hva(vcpu->kvm, real_gfn);
+		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn,
+					    &walker->pte_writable[walker->level - 1]);
 		if (unlikely(kvm_is_error_hva(host_addr)))
 			goto error;
 
@@ -215,22 +342,21 @@
 
 		trace_kvm_mmu_paging_element(pte, walker->level);
 
-		if (unlikely(!is_present_gpte(pte)))
+		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
-		if (unlikely(is_rsvd_bits_set(&vcpu->arch.mmu, pte,
-					      walker->level))) {
+		if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) {
 			errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}
 
 		accessed_dirty &= pte;
-		pte_access = pt_access & gpte_access(vcpu, pte);
+		pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
 
 		walker->ptes[walker->level - 1] = pte;
 	} while (!is_last_gpte(mmu, walker->level, pte));
 
-	if (unlikely(permission_fault(mmu, pte_access, access))) {
+	if (unlikely(permission_fault(vcpu, mmu, pte_access, access))) {
 		errcode |= PFERR_PRESENT_MASK;
 		goto error;
 	}
@@ -241,20 +367,22 @@
 	if (PTTYPE == 32 && walker->level == PT_DIRECTORY_LEVEL && is_cpuid_PSE36())
 		gfn += pse36_gfn_delta(pte);
 
-	real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access);
+	real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault);
 	if (real_gpa == UNMAPPED_GVA)
 		return 0;
 
 	walker->gfn = real_gpa >> PAGE_SHIFT;
 
 	if (!write_fault)
-		protect_clean_gpte(&pte_access, pte);
+		FNAME(protect_clean_gpte)(&pte_access, pte);
 	else
 		/*
-		 * On a write fault, fold the dirty bit into accessed_dirty by
-		 * shifting it one place right.
+		 * On a write fault, fold the dirty bit into accessed_dirty.
+		 * For modes without A/D bits support accessed_dirty will be
+		 * always clear.
 		 */
-		accessed_dirty &= pte >> (PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT);
+		accessed_dirty &= pte >>
+			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
 		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
@@ -279,6 +407,25 @@
 	walker->fault.vector = PF_VECTOR;
 	walker->fault.error_code_valid = true;
 	walker->fault.error_code = errcode;
+
+#if PTTYPE == PTTYPE_EPT
+	/*
+	 * Use PFERR_RSVD_MASK in error_code to to tell if EPT
+	 * misconfiguration requires to be injected. The detection is
+	 * done by is_rsvd_bits_set() above.
+	 *
+	 * We set up the value of exit_qualification to inject:
+	 * [2:0] - Derive from [2:0] of real exit_qualification at EPT violation
+	 * [5:3] - Calculated by the page walk of the guest EPT page tables
+	 * [7:8] - Derived from [7:8] of real exit_qualification
+	 *
+	 * The other bits are set to 0.
+	 */
+	if (!(errcode & PFERR_RSVD_MASK)) {
+		vcpu->arch.exit_qualification &= 0x187;
+		vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+	}
+#endif
 	walker->fault.address = addr;
 	walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu;
 
@@ -293,6 +440,7 @@
 					access);
 }
 
+#if PTTYPE != PTTYPE_EPT
 static int FNAME(walk_addr_nested)(struct guest_walker *walker,
 				   struct kvm_vcpu *vcpu, gva_t addr,
 				   u32 access)
@@ -300,6 +448,7 @@
 	return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu,
 					addr, access);
 }
+#endif
 
 static bool
 FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
@@ -309,14 +458,14 @@
 	gfn_t gfn;
 	pfn_t pfn;
 
-	if (prefetch_invalid_gpte(vcpu, sp, spte, gpte))
+	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 		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);
+	pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+	FNAME(protect_clean_gpte)(&pte_access, gpte);
 	pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
 			no_dirty_log && (pte_access & ACC_WRITE_MASK));
 	if (is_error_pfn(pfn))
@@ -353,11 +502,11 @@
 		base_gpa = pte_gpa & ~mask;
 		index = (pte_gpa - base_gpa) / sizeof(pt_element_t);
 
-		r = kvm_read_guest_atomic(vcpu->kvm, base_gpa,
+		r = kvm_vcpu_read_guest_atomic(vcpu, base_gpa,
 				gw->prefetch_ptes, sizeof(gw->prefetch_ptes));
 		curr_pte = gw->prefetch_ptes[index];
 	} else
-		r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa,
+		r = kvm_vcpu_read_guest_atomic(vcpu, pte_gpa,
 				  &curr_pte, sizeof(curr_pte));
 
 	return r || curr_pte != gw->ptes[level - 1];
@@ -449,7 +598,7 @@
 			goto out_gpte_changed;
 
 		if (sp)
-			link_shadow_page(it.sptep, sp);
+			link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
 	}
 
 	for (;
@@ -469,7 +618,7 @@
 
 		sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1,
 				      true, direct_access, it.sptep);
-		link_shadow_page(it.sptep, sp);
+		link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
 	}
 
 	clear_sp_write_flooding_count(it.sptep);
@@ -549,15 +698,24 @@
 	int r;
 	pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;
-	int force_pt_level;
+	bool force_pt_level = false;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
-	if (unlikely(error_code & PFERR_RSVD_MASK))
-		return handle_mmio_page_fault(vcpu, addr, error_code,
-					      mmu_is_nested(vcpu));
+	if (unlikely(error_code & PFERR_RSVD_MASK)) {
+		r = handle_mmio_page_fault(vcpu, addr, mmu_is_nested(vcpu));
+		if (likely(r != RET_MMIO_PF_INVALID))
+			return r;
+
+		/*
+		 * page fault with PFEC.RSVD  = 1 is caused by shadow
+		 * page fault, should not be used to walk guest page
+		 * table.
+		 */
+		error_code &= ~PFERR_RSVD_MASK;
+	};
 
 	r = mmu_topup_memory_caches(vcpu);
 	if (r)
@@ -584,15 +742,14 @@
 	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
 	      &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);
 
-	if (walker.level >= PT_DIRECTORY_LEVEL)
-		force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn)
-		   || is_self_change_mapping;
-	else
-		force_pt_level = 1;
-	if (!force_pt_level) {
-		level = min(walker.level, mapping_level(vcpu, walker.gfn));
-		walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
-	}
+	if (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) {
+		level = mapping_level(vcpu, walker.gfn, &force_pt_level);
+		if (likely(!force_pt_level)) {
+			level = min(walker.level, level);
+			walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
+		}
+	} else
+		force_pt_level = true;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
@@ -701,8 +858,8 @@
 			if (!rmap_can_add(vcpu))
 				break;
 
-			if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
-						  sizeof(pt_element_t)))
+			if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
+						       sizeof(pt_element_t)))
 				break;
 
 			FNAME(update_pte)(vcpu, sp, sptep, &gpte);
@@ -732,6 +889,7 @@
 	return gpa;
 }
 
+#if PTTYPE != PTTYPE_EPT
 static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 				      u32 access,
 				      struct x86_exception *exception)
@@ -750,6 +908,7 @@
 
 	return gpa;
 }
+#endif
 
 /*
  * Using the cached information from sp->gfns is safe because:
@@ -786,21 +945,22 @@
 
 		pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
 
-		if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
-					  sizeof(pt_element_t)))
+		if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
+					       sizeof(pt_element_t)))
 			return -EINVAL;
 
-		if (prefetch_invalid_gpte(vcpu, sp, &sp->spt[i], gpte)) {
+		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
 			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 
 		gfn = gpte_to_gfn(gpte);
 		pte_access = sp->role.access;
-		pte_access &= gpte_access(vcpu, gpte);
-		protect_clean_gpte(&pte_access, gpte);
+		pte_access &= FNAME(gpte_access)(vcpu, gpte);
+		FNAME(protect_clean_gpte)(&pte_access, gpte);
 
-		if (sync_mmio_spte(&sp->spt[i], gfn, pte_access, &nr_present))
+		if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access,
+		      &nr_present))
 			continue;
 
 		if (gfn != sp->gfns[i]) {
@@ -834,3 +994,7 @@
 #undef gpte_to_gfn
 #undef gpte_to_gfn_lvl
 #undef CMPXCHG
+#undef PT_GUEST_ACCESSED_MASK
+#undef PT_GUEST_DIRTY_MASK
+#undef PT_GUEST_DIRTY_SHIFT
+#undef PT_GUEST_ACCESSED_SHIFT