1 files changed, 293 insertions, 40 deletions

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 3d61bd3e591d..f7a93ef29250 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -21,8 +21,10 @@
 
 #define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX	GENMASK(4, 2)
 #define KVM_PTE_LEAF_ATTR_LO_S1_AP	GENMASK(7, 6)
-#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO	3
-#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW	1
+#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO		\
+	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 2 : 3; })
+#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW		\
+	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 0 : 1; })
 #define KVM_PTE_LEAF_ATTR_LO_S1_SH	GENMASK(9, 8)
 #define KVM_PTE_LEAF_ATTR_LO_S1_SH_IS	3
 #define KVM_PTE_LEAF_ATTR_LO_S1_AF	BIT(10)
@@ -34,7 +36,7 @@
 #define KVM_PTE_LEAF_ATTR_LO_S2_SH_IS	3
 #define KVM_PTE_LEAF_ATTR_LO_S2_AF	BIT(10)
 
-#define KVM_PTE_LEAF_ATTR_HI		GENMASK(63, 51)
+#define KVM_PTE_LEAF_ATTR_HI		GENMASK(63, 50)
 
 #define KVM_PTE_LEAF_ATTR_HI_SW		GENMASK(58, 55)
 
@@ -42,6 +44,8 @@
 
 #define KVM_PTE_LEAF_ATTR_HI_S2_XN	BIT(54)
 
+#define KVM_PTE_LEAF_ATTR_HI_S1_GP	BIT(50)
+
 #define KVM_PTE_LEAF_ATTR_S2_PERMS	(KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | \
 					 KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \
 					 KVM_PTE_LEAF_ATTR_HI_S2_XN)
@@ -58,10 +62,21 @@
 struct kvm_pgtable_walk_data {
 	struct kvm_pgtable_walker	*walker;
 
+	const u64			start;
 	u64				addr;
-	u64				end;
+	const u64			end;
 };
 
+static bool kvm_pgtable_walk_skip_bbm_tlbi(const struct kvm_pgtable_visit_ctx *ctx)
+{
+	return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_BBM_TLBI);
+}
+
+static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx)
+{
+	return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO);
+}
+
 static bool kvm_phys_is_valid(u64 phys)
 {
 	return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_EL1_PARANGE_MAX));
@@ -201,20 +216,33 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 		.old	= READ_ONCE(*ptep),
 		.arg	= data->walker->arg,
 		.mm_ops	= mm_ops,
+		.start	= data->start,
 		.addr	= data->addr,
 		.end	= data->end,
 		.level	= level,
 		.flags	= flags,
 	};
 	int ret = 0;
+	bool reload = false;
 	kvm_pteref_t childp;
 	bool table = kvm_pte_table(ctx.old, level);
 
-	if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE))
+	if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) {
 		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE);
+		reload = true;
+	}
 
 	if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) {
 		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF);
+		reload = true;
+	}
+
+	/*
+	 * Reload the page table after invoking the walker callback for leaf
+	 * entries or after pre-order traversal, to allow the walker to descend
+	 * into a newly installed or replaced table.
+	 */
+	if (reload) {
 		ctx.old = READ_ONCE(*ptep);
 		table = kvm_pte_table(ctx.old, level);
 	}
@@ -293,6 +321,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
 		     struct kvm_pgtable_walker *walker)
 {
 	struct kvm_pgtable_walk_data walk_data = {
+		.start	= ALIGN_DOWN(addr, PAGE_SIZE),
 		.addr	= ALIGN_DOWN(addr, PAGE_SIZE),
 		.end	= PAGE_ALIGN(walk_data.addr + size),
 		.walker	= walker,
@@ -349,7 +378,7 @@ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
 }
 
 struct hyp_map_data {
-	u64				phys;
+	const u64			phys;
 	kvm_pte_t			attr;
 };
 
@@ -371,6 +400,9 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
 
 		if (device)
 			return -EINVAL;
+
+		if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
+			attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP;
 	} else {
 		attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN;
 	}
@@ -407,13 +439,12 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte)
 static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 				    struct hyp_map_data *data)
 {
+	u64 phys = data->phys + (ctx->addr - ctx->start);
 	kvm_pte_t new;
-	u64 granule = kvm_granule_size(ctx->level), phys = data->phys;
 
 	if (!kvm_block_mapping_supported(ctx, phys))
 		return false;
 
-	data->phys += granule;
 	new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level);
 	if (ctx->old == new)
 		return true;
@@ -576,7 +607,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt)
 }
 
 struct stage2_map_data {
-	u64				phys;
+	const u64			phys;
 	kvm_pte_t			attr;
 	u8				owner_id;
 
@@ -609,10 +640,18 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 #ifdef CONFIG_ARM64_HW_AFDBM
 	/*
 	 * Enable the Hardware Access Flag management, unconditionally
-	 * on all CPUs. The features is RES0 on CPUs without the support
-	 * and must be ignored by the CPUs.
+	 * on all CPUs. In systems that have asymmetric support for the feature
+	 * this allows KVM to leverage hardware support on the subset of cores
+	 * that implement the feature.
+	 *
+	 * The architecture requires VTCR_EL2.HA to be RES0 (thus ignored by
+	 * hardware) on implementations that do not advertise support for the
+	 * feature. As such, setting HA unconditionally is safe, unless you
+	 * happen to be running on a design that has unadvertised support for
+	 * HAFDBS. Here be dragons.
 	 */
-	vtcr |= VTCR_EL2_HA;
+	if (!cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
+		vtcr |= VTCR_EL2_HA;
 #endif /* CONFIG_ARM64_HW_AFDBM */
 
 	/* Set the vmid bits */
@@ -741,14 +780,17 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
 	if (!stage2_try_set_pte(ctx, KVM_INVALID_PTE_LOCKED))
 		return false;
 
-	/*
-	 * Perform the appropriate TLB invalidation based on the evicted pte
-	 * value (if any).
-	 */
-	if (kvm_pte_table(ctx->old, ctx->level))
-		kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
-	else if (kvm_pte_valid(ctx->old))
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level);
+	if (!kvm_pgtable_walk_skip_bbm_tlbi(ctx)) {
+		/*
+		 * Perform the appropriate TLB invalidation based on the
+		 * evicted pte value (if any).
+		 */
+		if (kvm_pte_table(ctx->old, ctx->level))
+			kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
+		else if (kvm_pte_valid(ctx->old))
+			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
+				     ctx->addr, ctx->level);
+	}
 
 	if (stage2_pte_is_counted(ctx->old))
 		mm_ops->put_page(ctx->ptep);
@@ -794,20 +836,43 @@ static bool stage2_pte_executable(kvm_pte_t pte)
 	return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN);
 }
 
+static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx,
+				       const struct stage2_map_data *data)
+{
+	u64 phys = data->phys;
+
+	/*
+	 * Stage-2 walks to update ownership data are communicated to the map
+	 * walker using an invalid PA. Avoid offsetting an already invalid PA,
+	 * which could overflow and make the address valid again.
+	 */
+	if (!kvm_phys_is_valid(phys))
+		return phys;
+
+	/*
+	 * Otherwise, work out the correct PA based on how far the walk has
+	 * gotten.
+	 */
+	return phys + (ctx->addr - ctx->start);
+}
+
 static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx,
 					struct stage2_map_data *data)
 {
+	u64 phys = stage2_map_walker_phys_addr(ctx, data);
+
 	if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1)))
 		return false;
 
-	return kvm_block_mapping_supported(ctx, data->phys);
+	return kvm_block_mapping_supported(ctx, phys);
 }
 
 static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 				      struct stage2_map_data *data)
 {
 	kvm_pte_t new;
-	u64 granule = kvm_granule_size(ctx->level), phys = data->phys;
+	u64 phys = stage2_map_walker_phys_addr(ctx, data);
+	u64 granule = kvm_granule_size(ctx->level);
 	struct kvm_pgtable *pgt = data->mmu->pgt;
 	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
 
@@ -832,17 +897,17 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 		return -EAGAIN;
 
 	/* Perform CMOs before installation of the guest stage-2 PTE */
-	if (mm_ops->dcache_clean_inval_poc && stage2_pte_cacheable(pgt, new))
+	if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->dcache_clean_inval_poc &&
+	    stage2_pte_cacheable(pgt, new))
 		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(new, mm_ops),
-						granule);
+					       granule);
 
-	if (mm_ops->icache_inval_pou && stage2_pte_executable(new))
+	if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->icache_inval_pou &&
+	    stage2_pte_executable(new))
 		mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule);
 
 	stage2_make_pte(ctx, new);
 
-	if (kvm_phys_is_valid(phys))
-		data->phys += granule;
 	return 0;
 }
 
@@ -860,7 +925,7 @@ static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx,
 	if (ret)
 		return ret;
 
-	mm_ops->free_removed_table(childp, ctx->level);
+	mm_ops->free_unlinked_table(childp, ctx->level);
 	return 0;
 }
 
@@ -905,7 +970,7 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx,
  * The TABLE_PRE callback runs for table entries on the way down, looking
  * for table entries which we could conceivably replace with a block entry
  * for this mapping. If it finds one it replaces the entry and calls
- * kvm_pgtable_mm_ops::free_removed_table() to tear down the detached table.
+ * kvm_pgtable_mm_ops::free_unlinked_table() to tear down the detached table.
  *
  * Otherwise, the LEAF callback performs the mapping at the existing leaves
  * instead.
@@ -1130,25 +1195,54 @@ kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
 	return pte;
 }
 
-kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
+struct stage2_age_data {
+	bool	mkold;
+	bool	young;
+};
+
+static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			     enum kvm_pgtable_walk_flags visit)
 {
-	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, KVM_PTE_LEAF_ATTR_LO_S2_AF,
-				 &pte, NULL, 0);
+	kvm_pte_t new = ctx->old & ~KVM_PTE_LEAF_ATTR_LO_S2_AF;
+	struct stage2_age_data *data = ctx->arg;
+
+	if (!kvm_pte_valid(ctx->old) || new == ctx->old)
+		return 0;
+
+	data->young = true;
+
+	/*
+	 * stage2_age_walker() is always called while holding the MMU lock for
+	 * write, so this will always succeed. Nonetheless, this deliberately
+	 * follows the race detection pattern of the other stage-2 walkers in
+	 * case the locking mechanics of the MMU notifiers is ever changed.
+	 */
+	if (data->mkold && !stage2_try_set_pte(ctx, new))
+		return -EAGAIN;
+
 	/*
 	 * "But where's the TLBI?!", you scream.
 	 * "Over in the core code", I sigh.
 	 *
 	 * See the '->clear_flush_young()' callback on the KVM mmu notifier.
 	 */
-	return pte;
+	return 0;
 }
 
-bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr)
+bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
+					 u64 size, bool mkold)
 {
-	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL, 0);
-	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
+	struct stage2_age_data data = {
+		.mkold		= mkold,
+	};
+	struct kvm_pgtable_walker walker = {
+		.cb		= stage2_age_walker,
+		.arg		= &data,
+		.flags		= KVM_PGTABLE_WALK_LEAF,
+	};
+
+	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
+	return data.young;
 }
 
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
@@ -1174,7 +1268,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 				       KVM_PGTABLE_WALK_HANDLE_FAULT |
 				       KVM_PGTABLE_WALK_SHARED);
 	if (!ret)
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level);
+		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level);
 	return ret;
 }
 
@@ -1207,6 +1301,162 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 	return kvm_pgtable_walk(pgt, addr, size, &walker);
 }
 
+kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
+					      u64 phys, u32 level,
+					      enum kvm_pgtable_prot prot,
+					      void *mc, bool force_pte)
+{
+	struct stage2_map_data map_data = {
+		.phys		= phys,
+		.mmu		= pgt->mmu,
+		.memcache	= mc,
+		.force_pte	= force_pte,
+	};
+	struct kvm_pgtable_walker walker = {
+		.cb		= stage2_map_walker,
+		.flags		= KVM_PGTABLE_WALK_LEAF |
+				  KVM_PGTABLE_WALK_SKIP_BBM_TLBI |
+				  KVM_PGTABLE_WALK_SKIP_CMO,
+		.arg		= &map_data,
+	};
+	/*
+	 * The input address (.addr) is irrelevant for walking an
+	 * unlinked table. Construct an ambiguous IA range to map
+	 * kvm_granule_size(level) worth of memory.
+	 */
+	struct kvm_pgtable_walk_data data = {
+		.walker	= &walker,
+		.addr	= 0,
+		.end	= kvm_granule_size(level),
+	};
+	struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops;
+	kvm_pte_t *pgtable;
+	int ret;
+
+	if (!IS_ALIGNED(phys, kvm_granule_size(level)))
+		return ERR_PTR(-EINVAL);
+
+	ret = stage2_set_prot_attr(pgt, prot, &map_data.attr);
+	if (ret)
+		return ERR_PTR(ret);
+
+	pgtable = mm_ops->zalloc_page(mc);
+	if (!pgtable)
+		return ERR_PTR(-ENOMEM);
+
+	ret = __kvm_pgtable_walk(&data, mm_ops, (kvm_pteref_t)pgtable,
+				 level + 1);
+	if (ret) {
+		kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level);
+		mm_ops->put_page(pgtable);
+		return ERR_PTR(ret);
+	}
+
+	return pgtable;
+}
+
+/*
+ * Get the number of page-tables needed to replace a block with a
+ * fully populated tree up to the PTE entries. Note that @level is
+ * interpreted as in "level @level entry".
+ */
+static int stage2_block_get_nr_page_tables(u32 level)
+{
+	switch (level) {
+	case 1:
+		return PTRS_PER_PTE + 1;
+	case 2:
+		return 1;
+	case 3:
+		return 0;
+	default:
+		WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL ||
+			     level >= KVM_PGTABLE_MAX_LEVELS);
+		return -EINVAL;
+	};
+}
+
+static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			       enum kvm_pgtable_walk_flags visit)
+{
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
+	struct kvm_mmu_memory_cache *mc = ctx->arg;
+	struct kvm_s2_mmu *mmu;
+	kvm_pte_t pte = ctx->old, new, *childp;
+	enum kvm_pgtable_prot prot;
+	u32 level = ctx->level;
+	bool force_pte;
+	int nr_pages;
+	u64 phys;
+
+	/* No huge-pages exist at the last level */
+	if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+		return 0;
+
+	/* We only split valid block mappings */
+	if (!kvm_pte_valid(pte))
+		return 0;
+
+	nr_pages = stage2_block_get_nr_page_tables(level);
+	if (nr_pages < 0)
+		return nr_pages;
+
+	if (mc->nobjs >= nr_pages) {
+		/* Build a tree mapped down to the PTE granularity. */
+		force_pte = true;
+	} else {
+		/*
+		 * Don't force PTEs, so create_unlinked() below does
+		 * not populate the tree up to the PTE level. The
+		 * consequence is that the call will require a single
+		 * page of level 2 entries at level 1, or a single
+		 * page of PTEs at level 2. If we are at level 1, the
+		 * PTEs will be created recursively.
+		 */
+		force_pte = false;
+		nr_pages = 1;
+	}
+
+	if (mc->nobjs < nr_pages)
+		return -ENOMEM;
+
+	mmu = container_of(mc, struct kvm_s2_mmu, split_page_cache);
+	phys = kvm_pte_to_phys(pte);
+	prot = kvm_pgtable_stage2_pte_prot(pte);
+
+	childp = kvm_pgtable_stage2_create_unlinked(mmu->pgt, phys,
+						    level, prot, mc, force_pte);
+	if (IS_ERR(childp))
+		return PTR_ERR(childp);
+
+	if (!stage2_try_break_pte(ctx, mmu)) {
+		kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level);
+		mm_ops->put_page(childp);
+		return -EAGAIN;
+	}
+
+	/*
+	 * Note, the contents of the page table are guaranteed to be made
+	 * visible before the new PTE is assigned because stage2_make_pte()
+	 * writes the PTE using smp_store_release().
+	 */
+	new = kvm_init_table_pte(childp, mm_ops);
+	stage2_make_pte(ctx, new);
+	dsb(ishst);
+	return 0;
+}
+
+int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			     struct kvm_mmu_memory_cache *mc)
+{
+	struct kvm_pgtable_walker walker = {
+		.cb	= stage2_split_walker,
+		.flags	= KVM_PGTABLE_WALK_LEAF,
+		.arg	= mc,
+	};
+
+	return kvm_pgtable_walk(pgt, addr, size, &walker);
+}
 
 int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			      struct kvm_pgtable_mm_ops *mm_ops,
@@ -1276,7 +1526,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
 	pgt->pgd = NULL;
 }
 
-void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level)
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
 	struct kvm_pgtable_walker walker = {
@@ -1297,4 +1547,7 @@ void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pg
 	};
 
 	WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1));
+
+	WARN_ON(mm_ops->page_count(pgtable) != 1);
+	mm_ops->put_page(pgtable);
 }