1 files changed, 178 insertions, 133 deletions

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 7a7ddc4558a7..0121ef2c7c8d 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -55,12 +55,13 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
  */
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid, kvm);
+	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
 }
 
-static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+static void kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
+				   int level)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
+	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ipa, level);
 }
 
 /*
@@ -90,74 +91,80 @@ static bool kvm_is_device_pfn(unsigned long pfn)
 
 /**
  * stage2_dissolve_pmd() - clear and flush huge PMD entry
- * @kvm:	pointer to kvm structure.
+ * @mmu:	pointer to mmu structure to operate on
  * @addr:	IPA
  * @pmd:	pmd pointer for IPA
  *
  * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs.
  */
-static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
+static void stage2_dissolve_pmd(struct kvm_s2_mmu *mmu, phys_addr_t addr, pmd_t *pmd)
 {
 	if (!pmd_thp_or_huge(*pmd))
 		return;
 
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
 	put_page(virt_to_page(pmd));
 }
 
 /**
  * stage2_dissolve_pud() - clear and flush huge PUD entry
- * @kvm:	pointer to kvm structure.
+ * @mmu:	pointer to mmu structure to operate on
  * @addr:	IPA
  * @pud:	pud pointer for IPA
  *
  * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs.
  */
-static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp)
+static void stage2_dissolve_pud(struct kvm_s2_mmu *mmu, phys_addr_t addr, pud_t *pudp)
 {
+	struct kvm *kvm = mmu->kvm;
+
 	if (!stage2_pud_huge(kvm, *pudp))
 		return;
 
 	stage2_pud_clear(kvm, pudp);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
 	put_page(virt_to_page(pudp));
 }
 
-static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
+static void clear_stage2_pgd_entry(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d_table __maybe_unused = stage2_p4d_offset(kvm, pgd, 0UL);
 	stage2_pgd_clear(kvm, pgd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	stage2_p4d_free(kvm, p4d_table);
 	put_page(virt_to_page(pgd));
 }
 
-static void clear_stage2_p4d_entry(struct kvm *kvm, p4d_t *p4d, phys_addr_t addr)
+static void clear_stage2_p4d_entry(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud_table __maybe_unused = stage2_pud_offset(kvm, p4d, 0);
 	stage2_p4d_clear(kvm, p4d);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	stage2_pud_free(kvm, pud_table);
 	put_page(virt_to_page(p4d));
 }
 
-static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
+static void clear_stage2_pud_entry(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(kvm, pud, 0);
+
 	VM_BUG_ON(stage2_pud_huge(kvm, *pud));
 	stage2_pud_clear(kvm, pud);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	stage2_pmd_free(kvm, pmd_table);
 	put_page(virt_to_page(pud));
 }
 
-static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
+static void clear_stage2_pmd_entry(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr)
 {
 	pte_t *pte_table = pte_offset_kernel(pmd, 0);
 	VM_BUG_ON(pmd_thp_or_huge(*pmd));
 	pmd_clear(pmd);
-	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT);
 	free_page((unsigned long)pte_table);
 	put_page(virt_to_page(pmd));
 }
@@ -223,7 +230,7 @@ static inline void kvm_pgd_populate(pgd_t *pgdp, p4d_t *p4dp)
  * we then fully enforce cacheability of RAM, no matter what the guest
  * does.
  */
-static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
+static void unmap_stage2_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 		       phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t start_addr = addr;
@@ -235,7 +242,7 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
 			pte_t old_pte = *pte;
 
 			kvm_set_pte(pte, __pte(0));
-			kvm_tlb_flush_vmid_ipa(kvm, addr);
+			kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL);
 
 			/* No need to invalidate the cache for device mappings */
 			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
@@ -245,13 +252,14 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
-	if (stage2_pte_table_empty(kvm, start_pte))
-		clear_stage2_pmd_entry(kvm, pmd, start_addr);
+	if (stage2_pte_table_empty(mmu->kvm, start_pte))
+		clear_stage2_pmd_entry(mmu, pmd, start_addr);
 }
 
-static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
+static void unmap_stage2_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 		       phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	phys_addr_t next, start_addr = addr;
 	pmd_t *pmd, *start_pmd;
 
@@ -263,24 +271,25 @@ static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
 				pmd_t old_pmd = *pmd;
 
 				pmd_clear(pmd);
-				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
 
 				kvm_flush_dcache_pmd(old_pmd);
 
 				put_page(virt_to_page(pmd));
 			} else {
-				unmap_stage2_ptes(kvm, pmd, addr, next);
+				unmap_stage2_ptes(mmu, pmd, addr, next);
 			}
 		}
 	} while (pmd++, addr = next, addr != end);
 
 	if (stage2_pmd_table_empty(kvm, start_pmd))
-		clear_stage2_pud_entry(kvm, pud, start_addr);
+		clear_stage2_pud_entry(mmu, pud, start_addr);
 }
 
-static void unmap_stage2_puds(struct kvm *kvm, p4d_t *p4d,
+static void unmap_stage2_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 		       phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	phys_addr_t next, start_addr = addr;
 	pud_t *pud, *start_pud;
 
@@ -292,22 +301,23 @@ static void unmap_stage2_puds(struct kvm *kvm, p4d_t *p4d,
 				pud_t old_pud = *pud;
 
 				stage2_pud_clear(kvm, pud);
-				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
 				kvm_flush_dcache_pud(old_pud);
 				put_page(virt_to_page(pud));
 			} else {
-				unmap_stage2_pmds(kvm, pud, addr, next);
+				unmap_stage2_pmds(mmu, pud, addr, next);
 			}
 		}
 	} while (pud++, addr = next, addr != end);
 
 	if (stage2_pud_table_empty(kvm, start_pud))
-		clear_stage2_p4d_entry(kvm, p4d, start_addr);
+		clear_stage2_p4d_entry(mmu, p4d, start_addr);
 }
 
-static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 		       phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	phys_addr_t next, start_addr = addr;
 	p4d_t *p4d, *start_p4d;
 
@@ -315,11 +325,11 @@ static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_p4d_addr_end(kvm, addr, end);
 		if (!stage2_p4d_none(kvm, *p4d))
-			unmap_stage2_puds(kvm, p4d, addr, next);
+			unmap_stage2_puds(mmu, p4d, addr, next);
 	} while (p4d++, addr = next, addr != end);
 
 	if (stage2_p4d_table_empty(kvm, start_p4d))
-		clear_stage2_pgd_entry(kvm, pgd, start_addr);
+		clear_stage2_pgd_entry(mmu, pgd, start_addr);
 }
 
 /**
@@ -333,8 +343,9 @@ static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
  * destroying the VM), otherwise another faulting VCPU may come in and mess
  * with things behind our backs.
  */
-static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
 {
+	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
@@ -342,18 +353,18 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	assert_spin_locked(&kvm->mmu_lock);
 	WARN_ON(size & ~PAGE_MASK);
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	do {
 		/*
 		 * Make sure the page table is still active, as another thread
 		 * could have possibly freed the page table, while we released
 		 * the lock.
 		 */
-		if (!READ_ONCE(kvm->arch.pgd))
+		if (!READ_ONCE(mmu->pgd))
 			break;
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (!stage2_pgd_none(kvm, *pgd))
-			unmap_stage2_p4ds(kvm, pgd, addr, next);
+			unmap_stage2_p4ds(mmu, pgd, addr, next);
 		/*
 		 * If the range is too large, release the kvm->mmu_lock
 		 * to prevent starvation and lockup detector warnings.
@@ -363,7 +374,7 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	} while (pgd++, addr = next, addr != end);
 }
 
-static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd,
 			      phys_addr_t addr, phys_addr_t end)
 {
 	pte_t *pte;
@@ -375,9 +386,10 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+static void stage2_flush_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 			      phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pmd_t *pmd;
 	phys_addr_t next;
 
@@ -388,14 +400,15 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
 			if (pmd_thp_or_huge(*pmd))
 				kvm_flush_dcache_pmd(*pmd);
 			else
-				stage2_flush_ptes(kvm, pmd, addr, next);
+				stage2_flush_ptes(mmu, pmd, addr, next);
 		}
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void stage2_flush_puds(struct kvm *kvm, p4d_t *p4d,
+static void stage2_flush_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 			      phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	phys_addr_t next;
 
@@ -406,14 +419,15 @@ static void stage2_flush_puds(struct kvm *kvm, p4d_t *p4d,
 			if (stage2_pud_huge(kvm, *pud))
 				kvm_flush_dcache_pud(*pud);
 			else
-				stage2_flush_pmds(kvm, pud, addr, next);
+				stage2_flush_pmds(mmu, pud, addr, next);
 		}
 	} while (pud++, addr = next, addr != end);
 }
 
-static void stage2_flush_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void stage2_flush_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 			      phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d;
 	phys_addr_t next;
 
@@ -421,23 +435,24 @@ static void stage2_flush_p4ds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_p4d_addr_end(kvm, addr, end);
 		if (!stage2_p4d_none(kvm, *p4d))
-			stage2_flush_puds(kvm, p4d, addr, next);
+			stage2_flush_puds(mmu, p4d, addr, next);
 	} while (p4d++, addr = next, addr != end);
 }
 
 static void stage2_flush_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
+	struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
 	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
 	phys_addr_t next;
 	pgd_t *pgd;
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	do {
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (!stage2_pgd_none(kvm, *pgd))
-			stage2_flush_p4ds(kvm, pgd, addr, next);
+			stage2_flush_p4ds(mmu, pgd, addr, next);
 
 		if (next != end)
 			cond_resched_lock(&kvm->mmu_lock);
@@ -964,21 +979,23 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 }
 
 /**
- * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
- * @kvm:	The KVM struct pointer for the VM.
+ * kvm_init_stage2_mmu - Initialise a S2 MMU strucrure
+ * @kvm:	The pointer to the KVM structure
+ * @mmu:	The pointer to the s2 MMU structure
  *
  * Allocates only the stage-2 HW PGD level table(s) of size defined by
- * stage2_pgd_size(kvm).
+ * stage2_pgd_size(mmu->kvm).
  *
  * Note we don't need locking here as this is only called when the VM is
  * created, which can only be done once.
  */
-int kvm_alloc_stage2_pgd(struct kvm *kvm)
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 {
 	phys_addr_t pgd_phys;
 	pgd_t *pgd;
+	int cpu;
 
-	if (kvm->arch.pgd != NULL) {
+	if (mmu->pgd != NULL) {
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
@@ -992,8 +1009,20 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 	if (WARN_ON(pgd_phys & ~kvm_vttbr_baddr_mask(kvm)))
 		return -EINVAL;
 
-	kvm->arch.pgd = pgd;
-	kvm->arch.pgd_phys = pgd_phys;
+	mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
+	if (!mmu->last_vcpu_ran) {
+		free_pages_exact(pgd, stage2_pgd_size(kvm));
+		return -ENOMEM;
+	}
+
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;
+
+	mmu->kvm = kvm;
+	mmu->pgd = pgd;
+	mmu->pgd_phys = pgd_phys;
+	mmu->vmid.vmid_gen = 0;
+
 	return 0;
 }
 
@@ -1032,7 +1061,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
 
 		if (!(vma->vm_flags & VM_PFNMAP)) {
 			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
-			unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+			unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
@@ -1064,39 +1093,34 @@ void stage2_unmap_vm(struct kvm *kvm)
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
-/**
- * kvm_free_stage2_pgd - free all stage-2 tables
- * @kvm:	The KVM struct pointer for the VM.
- *
- * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
- * underlying level-2 and level-3 tables before freeing the actual level-1 table
- * and setting the struct pointer to NULL.
- */
-void kvm_free_stage2_pgd(struct kvm *kvm)
+void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 {
+	struct kvm *kvm = mmu->kvm;
 	void *pgd = NULL;
 
 	spin_lock(&kvm->mmu_lock);
-	if (kvm->arch.pgd) {
-		unmap_stage2_range(kvm, 0, kvm_phys_size(kvm));
-		pgd = READ_ONCE(kvm->arch.pgd);
-		kvm->arch.pgd = NULL;
-		kvm->arch.pgd_phys = 0;
+	if (mmu->pgd) {
+		unmap_stage2_range(mmu, 0, kvm_phys_size(kvm));
+		pgd = READ_ONCE(mmu->pgd);
+		mmu->pgd = NULL;
 	}
 	spin_unlock(&kvm->mmu_lock);
 
 	/* Free the HW pgd, one page at a time */
-	if (pgd)
+	if (pgd) {
 		free_pages_exact(pgd, stage2_pgd_size(kvm));
+		free_percpu(mmu->last_vcpu_ran);
+	}
 }
 
-static p4d_t *stage2_get_p4d(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static p4d_t *stage2_get_p4d(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
 	p4d_t *p4d;
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	if (stage2_pgd_none(kvm, *pgd)) {
 		if (!cache)
 			return NULL;
@@ -1108,13 +1132,14 @@ static p4d_t *stage2_get_p4d(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	return stage2_p4d_offset(kvm, pgd, addr);
 }
 
-static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pud_t *stage2_get_pud(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d;
 	pud_t *pud;
 
-	p4d = stage2_get_p4d(kvm, cache, addr);
+	p4d = stage2_get_p4d(mmu, cache, addr);
 	if (stage2_p4d_none(kvm, *p4d)) {
 		if (!cache)
 			return NULL;
@@ -1126,13 +1151,14 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	return stage2_pud_offset(kvm, p4d, addr);
 }
 
-static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pmd_t *stage2_get_pmd(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	pmd_t *pmd;
 
-	pud = stage2_get_pud(kvm, cache, addr);
+	pud = stage2_get_pud(mmu, cache, addr);
 	if (!pud || stage2_pud_huge(kvm, *pud))
 		return NULL;
 
@@ -1147,13 +1173,14 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	return stage2_pmd_offset(kvm, pud, addr);
 }
 
-static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
-			       *cache, phys_addr_t addr, const pmd_t *new_pmd)
+static int stage2_set_pmd_huge(struct kvm_s2_mmu *mmu,
+			       struct kvm_mmu_memory_cache *cache,
+			       phys_addr_t addr, const pmd_t *new_pmd)
 {
 	pmd_t *pmd, old_pmd;
 
 retry:
-	pmd = stage2_get_pmd(kvm, cache, addr);
+	pmd = stage2_get_pmd(mmu, cache, addr);
 	VM_BUG_ON(!pmd);
 
 	old_pmd = *pmd;
@@ -1186,7 +1213,7 @@ retry:
 		 * get handled accordingly.
 		 */
 		if (!pmd_thp_or_huge(old_pmd)) {
-			unmap_stage2_range(kvm, addr & S2_PMD_MASK, S2_PMD_SIZE);
+			unmap_stage2_range(mmu, addr & S2_PMD_MASK, S2_PMD_SIZE);
 			goto retry;
 		}
 		/*
@@ -1202,7 +1229,7 @@ retry:
 		 */
 		WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
 		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL);
 	} else {
 		get_page(virt_to_page(pmd));
 	}
@@ -1211,13 +1238,15 @@ retry:
 	return 0;
 }
 
-static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static int stage2_set_pud_huge(struct kvm_s2_mmu *mmu,
+			       struct kvm_mmu_memory_cache *cache,
 			       phys_addr_t addr, const pud_t *new_pudp)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pudp, old_pud;
 
 retry:
-	pudp = stage2_get_pud(kvm, cache, addr);
+	pudp = stage2_get_pud(mmu, cache, addr);
 	VM_BUG_ON(!pudp);
 
 	old_pud = *pudp;
@@ -1236,13 +1265,13 @@ retry:
 		 * the range for this block and retry.
 		 */
 		if (!stage2_pud_huge(kvm, old_pud)) {
-			unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE);
+			unmap_stage2_range(mmu, addr & S2_PUD_MASK, S2_PUD_SIZE);
 			goto retry;
 		}
 
 		WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp));
 		stage2_pud_clear(kvm, pudp);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL);
 	} else {
 		get_page(virt_to_page(pudp));
 	}
@@ -1257,9 +1286,10 @@ retry:
  * leaf-entry is returned in the appropriate level variable - pudpp,
  * pmdpp, ptepp.
  */
-static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
+static bool stage2_get_leaf_entry(struct kvm_s2_mmu *mmu, phys_addr_t addr,
 				  pud_t **pudpp, pmd_t **pmdpp, pte_t **ptepp)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
@@ -1268,7 +1298,7 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
 	*pmdpp = NULL;
 	*ptepp = NULL;
 
-	pudp = stage2_get_pud(kvm, NULL, addr);
+	pudp = stage2_get_pud(mmu, NULL, addr);
 	if (!pudp || stage2_pud_none(kvm, *pudp) || !stage2_pud_present(kvm, *pudp))
 		return false;
 
@@ -1294,14 +1324,14 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
 	return true;
 }
 
-static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz)
+static bool stage2_is_exec(struct kvm_s2_mmu *mmu, phys_addr_t addr, unsigned long sz)
 {
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 	bool found;
 
-	found = stage2_get_leaf_entry(kvm, addr, &pudp, &pmdp, &ptep);
+	found = stage2_get_leaf_entry(mmu, addr, &pudp, &pmdp, &ptep);
 	if (!found)
 		return false;
 
@@ -1313,10 +1343,12 @@ static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz)
 		return sz == PAGE_SIZE && kvm_s2pte_exec(ptep);
 }
 
-static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static int stage2_set_pte(struct kvm_s2_mmu *mmu,
+			  struct kvm_mmu_memory_cache *cache,
 			  phys_addr_t addr, const pte_t *new_pte,
 			  unsigned long flags)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte, old_pte;
@@ -1326,7 +1358,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	VM_BUG_ON(logging_active && !cache);
 
 	/* Create stage-2 page table mapping - Levels 0 and 1 */
-	pud = stage2_get_pud(kvm, cache, addr);
+	pud = stage2_get_pud(mmu, cache, addr);
 	if (!pud) {
 		/*
 		 * Ignore calls from kvm_set_spte_hva for unallocated
@@ -1340,7 +1372,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	 * on to allocate page.
 	 */
 	if (logging_active)
-		stage2_dissolve_pud(kvm, addr, pud);
+		stage2_dissolve_pud(mmu, addr, pud);
 
 	if (stage2_pud_none(kvm, *pud)) {
 		if (!cache)
@@ -1364,7 +1396,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	 * allocate page.
 	 */
 	if (logging_active)
-		stage2_dissolve_pmd(kvm, addr, pmd);
+		stage2_dissolve_pmd(mmu, addr, pmd);
 
 	/* Create stage-2 page mappings - Level 2 */
 	if (pmd_none(*pmd)) {
@@ -1388,7 +1420,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 			return 0;
 
 		kvm_set_pte(pte, __pte(0));
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
+		kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL);
 	} else {
 		get_page(virt_to_page(pte));
 	}
@@ -1453,8 +1485,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 		if (ret)
 			goto out;
 		spin_lock(&kvm->mmu_lock);
-		ret = stage2_set_pte(kvm, &cache, addr, &pte,
-						KVM_S2PTE_FLAG_IS_IOMAP);
+		ret = stage2_set_pte(&kvm->arch.mmu, &cache, addr, &pte,
+				     KVM_S2PTE_FLAG_IS_IOMAP);
 		spin_unlock(&kvm->mmu_lock);
 		if (ret)
 			goto out;
@@ -1493,9 +1525,10 @@ static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
  * @addr:	range start address
  * @end:	range end address
  */
-static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud,
+static void stage2_wp_pmds(struct kvm_s2_mmu *mmu, pud_t *pud,
 			   phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pmd_t *pmd;
 	phys_addr_t next;
 
@@ -1516,13 +1549,14 @@ static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud,
 
 /**
  * stage2_wp_puds - write protect P4D range
- * @pgd:	pointer to pgd entry
+ * @p4d:	pointer to p4d entry
  * @addr:	range start address
  * @end:	range end address
  */
-static void  stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
+static void  stage2_wp_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d,
 			    phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pud_t *pud;
 	phys_addr_t next;
 
@@ -1534,7 +1568,7 @@ static void  stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
 				if (!kvm_s2pud_readonly(pud))
 					kvm_set_s2pud_readonly(pud);
 			} else {
-				stage2_wp_pmds(kvm, pud, addr, next);
+				stage2_wp_pmds(mmu, pud, addr, next);
 			}
 		}
 	} while (pud++, addr = next, addr != end);
@@ -1546,9 +1580,10 @@ static void  stage2_wp_puds(struct kvm *kvm, p4d_t *p4d,
  * @addr:	range start address
  * @end:	range end address
  */
-static void  stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
+static void  stage2_wp_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 			    phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	p4d_t *p4d;
 	phys_addr_t next;
 
@@ -1556,7 +1591,7 @@ static void  stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
 	do {
 		next = stage2_p4d_addr_end(kvm, addr, end);
 		if (!stage2_p4d_none(kvm, *p4d))
-			stage2_wp_puds(kvm, p4d, addr, next);
+			stage2_wp_puds(mmu, p4d, addr, next);
 	} while (p4d++, addr = next, addr != end);
 }
 
@@ -1566,12 +1601,13 @@ static void  stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd,
  * @addr:	Start address of range
  * @end:	End address of range
  */
-static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
+	struct kvm *kvm = mmu->kvm;
 	pgd_t *pgd;
 	phys_addr_t next;
 
-	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
 	do {
 		/*
 		 * Release kvm_mmu_lock periodically if the memory region is
@@ -1583,11 +1619,11 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 		 * the lock.
 		 */
 		cond_resched_lock(&kvm->mmu_lock);
-		if (!READ_ONCE(kvm->arch.pgd))
+		if (!READ_ONCE(mmu->pgd))
 			break;
 		next = stage2_pgd_addr_end(kvm, addr, end);
 		if (stage2_pgd_present(kvm, *pgd))
-			stage2_wp_p4ds(kvm, pgd, addr, next);
+			stage2_wp_p4ds(mmu, pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -1617,7 +1653,7 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
 	spin_lock(&kvm->mmu_lock);
-	stage2_wp_range(kvm, start, end);
+	stage2_wp_range(&kvm->arch.mmu, start, end);
 	spin_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs(kvm);
 }
@@ -1641,7 +1677,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
 	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
 
-	stage2_wp_range(kvm, start, end);
+	stage2_wp_range(&kvm->arch.mmu, start, end);
 }
 
 /*
@@ -1804,6 +1840,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	pgprot_t mem_type = PAGE_S2;
 	bool logging_active = memslot_is_logging(memslot);
 	unsigned long vma_pagesize, flags = 0;
+	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
 
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
@@ -1925,7 +1962,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 */
 	needs_exec = exec_fault ||
 		(fault_status == FSC_PERM &&
-		 stage2_is_exec(kvm, fault_ipa, vma_pagesize));
+		 stage2_is_exec(mmu, fault_ipa, vma_pagesize));
 
 	if (vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
@@ -1937,7 +1974,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		if (needs_exec)
 			new_pud = kvm_s2pud_mkexec(new_pud);
 
-		ret = stage2_set_pud_huge(kvm, memcache, fault_ipa, &new_pud);
+		ret = stage2_set_pud_huge(mmu, memcache, fault_ipa, &new_pud);
 	} else if (vma_pagesize == PMD_SIZE) {
 		pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type);
 
@@ -1949,7 +1986,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		if (needs_exec)
 			new_pmd = kvm_s2pmd_mkexec(new_pmd);
 
-		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
+		ret = stage2_set_pmd_huge(mmu, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = kvm_pfn_pte(pfn, mem_type);
 
@@ -1961,7 +1998,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		if (needs_exec)
 			new_pte = kvm_s2pte_mkexec(new_pte);
 
-		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
+		ret = stage2_set_pte(mmu, memcache, fault_ipa, &new_pte, flags);
 	}
 
 out_unlock:
@@ -1990,7 +2027,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 
 	spin_lock(&vcpu->kvm->mmu_lock);
 
-	if (!stage2_get_leaf_entry(vcpu->kvm, fault_ipa, &pud, &pmd, &pte))
+	if (!stage2_get_leaf_entry(vcpu->arch.hw_mmu, fault_ipa, &pud, &pmd, &pte))
 		goto out;
 
 	if (pud) {		/* HugeTLB */
@@ -2040,21 +2077,18 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
 	/* Synchronous External Abort? */
-	if (kvm_vcpu_dabt_isextabt(vcpu)) {
+	if (kvm_vcpu_abt_issea(vcpu)) {
 		/*
 		 * For RAS the host kernel may handle this abort.
 		 * There is no need to pass the error into the guest.
 		 */
-		if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_hsr(vcpu)))
-			return 1;
-
-		if (unlikely(!is_iabt)) {
+		if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
 			kvm_inject_vabt(vcpu);
-			return 1;
-		}
+
+		return 1;
 	}
 
-	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu),
+	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
@@ -2063,7 +2097,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
-			(unsigned long)kvm_vcpu_get_hsr(vcpu));
+			(unsigned long)kvm_vcpu_get_esr(vcpu));
 		return -EFAULT;
 	}
 
@@ -2074,12 +2108,23 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
 	write_fault = kvm_is_write_fault(vcpu);
 	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
+		/*
+		 * The guest has put either its instructions or its page-tables
+		 * somewhere it shouldn't have. Userspace won't be able to do
+		 * anything about this (there's no syndrome for a start), so
+		 * re-inject the abort back into the guest.
+		 */
 		if (is_iabt) {
-			/* Prefetch Abort on I/O address */
 			ret = -ENOEXEC;
 			goto out;
 		}
 
+		if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+			ret = 1;
+			goto out_unlock;
+		}
+
 		/*
 		 * Check for a cache maintenance operation. Since we
 		 * ended-up here, we know it is outside of any memory
@@ -2090,7 +2135,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		 * So let's assume that the guest is just being
 		 * cautious, and skip the instruction.
 		 */
-		if (kvm_vcpu_dabt_is_cm(vcpu)) {
+		if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) {
 			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 			ret = 1;
 			goto out_unlock;
@@ -2163,14 +2208,14 @@ static int handle_hva_to_gpa(struct kvm *kvm,
 
 static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	unmap_stage2_range(kvm, gpa, size);
+	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
 	return 0;
 }
 
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end)
 {
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 
 	trace_kvm_unmap_hva_range(start, end);
@@ -2190,7 +2235,7 @@ static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data
 	 * therefore stage2_set_pte() never needs to clear out a huge PMD
 	 * through this calling path.
 	 */
-	stage2_set_pte(kvm, NULL, gpa, pte, 0);
+	stage2_set_pte(&kvm->arch.mmu, NULL, gpa, pte, 0);
 	return 0;
 }
 
@@ -2201,7 +2246,7 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	kvm_pfn_t pfn = pte_pfn(pte);
 	pte_t stage2_pte;
 
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 
 	trace_kvm_set_spte_hva(hva);
@@ -2224,7 +2269,7 @@ static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 	pte_t *pte;
 
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-	if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
+	if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
 		return 0;
 
 	if (pud)
@@ -2242,7 +2287,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 	pte_t *pte;
 
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-	if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
+	if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
 		return 0;
 
 	if (pud)
@@ -2255,7 +2300,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 	trace_kvm_age_hva(start, end);
 	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
@@ -2263,7 +2308,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	if (!kvm->arch.pgd)
+	if (!kvm->arch.mmu.pgd)
 		return 0;
 	trace_kvm_test_age_hva(hva);
 	return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE,
@@ -2476,7 +2521,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	if (ret)
-		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
+		unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size);
 	else
 		stage2_flush_memslot(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
@@ -2495,7 +2540,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
-	kvm_free_stage2_pgd(kvm);
+	kvm_free_stage2_pgd(&kvm->arch.mmu);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
@@ -2505,7 +2550,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	phys_addr_t size = slot->npages << PAGE_SHIFT;
 
 	spin_lock(&kvm->mmu_lock);
-	unmap_stage2_range(kvm, gpa, size);
+	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
 	spin_unlock(&kvm->mmu_lock);
 }