Merge branch kvm-arm64/parallel-faults into kvmarm-master/next

* kvm-arm64/parallel-faults:
  : .
  : Parallel stage-2 fault handling, courtesy of Oliver Upton.
  : From the cover letter:
  :
  : "Presently KVM only takes a read lock for stage 2 faults if it believes
  : the fault can be fixed by relaxing permissions on a PTE (write unprotect
  : for dirty logging). Otherwise, stage 2 faults grab the write lock, which
  : predictably can pile up all the vCPUs in a sufficiently large VM.
  :
  : Like the TDP MMU for x86, this series loosens the locking around
  : manipulations of the stage 2 page tables to allow parallel faults. RCU
  : and atomics are exploited to safely build/destroy the stage 2 page
  : tables in light of multiple software observers."
  : .
  KVM: arm64: Reject shared table walks in the hyp code
  KVM: arm64: Don't acquire RCU read lock for exclusive table walks
  KVM: arm64: Take a pointer to walker data in kvm_dereference_pteref()
  KVM: arm64: Handle stage-2 faults in parallel
  KVM: arm64: Make table->block changes parallel-aware
  KVM: arm64: Make leaf->leaf PTE changes parallel-aware
  KVM: arm64: Make block->table PTE changes parallel-aware
  KVM: arm64: Split init and set for table PTE
  KVM: arm64: Atomically update stage 2 leaf attributes in parallel walks
  KVM: arm64: Protect stage-2 traversal with RCU
  KVM: arm64: Tear down unlinked stage-2 subtree after break-before-make
  KVM: arm64: Use an opaque type for pteps
  KVM: arm64: Add a helper to tear down unlinked stage-2 subtrees
  KVM: arm64: Don't pass kvm_pgtable through kvm_pgtable_walk_data
  KVM: arm64: Pass mm_ops through the visitor context
  KVM: arm64: Stash observed pte value in visitor context
  KVM: arm64: Combine visitor arguments into a context structure

Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/kvm_pgtable.h

@@ -85,6 +85,8 @@ static inline bool kvm_level_supports_block_mapping(u32 level)
  *				allocation is physically contiguous.
  * @free_pages_exact:		Free an exact number of memory pages previously
  *				allocated by zalloc_pages_exact.
+ * @free_removed_table:		Free a removed paging structure by unlinking and
+ *				dropping references.
  * @get_page:			Increment the refcount on a page.
  * @put_page:			Decrement the refcount on a page. When the
  *				refcount reaches 0 the page is automatically
@@ -103,6 +105,7 @@ struct kvm_pgtable_mm_ops {
 	void*		(*zalloc_page)(void *arg);
 	void*		(*zalloc_pages_exact)(size_t size);
 	void		(*free_pages_exact)(void *addr, size_t size);
+	void		(*free_removed_table)(void *addr, u32 level);
 	void		(*get_page)(void *addr);
 	void		(*put_page)(void *addr);
 	int		(*page_count)(void *addr);
@@ -161,6 +164,121 @@ enum kvm_pgtable_prot {
 typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
 					   enum kvm_pgtable_prot prot);
 
+/**
+ * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk.
+ * @KVM_PGTABLE_WALK_LEAF:		Visit leaf entries, including invalid
+ *					entries.
+ * @KVM_PGTABLE_WALK_TABLE_PRE:		Visit table entries before their
+ *					children.
+ * @KVM_PGTABLE_WALK_TABLE_POST:	Visit table entries after their
+ *					children.
+ * @KVM_PGTABLE_WALK_SHARED:		Indicates the page-tables may be shared
+ *					with other software walkers.
+ */
+enum kvm_pgtable_walk_flags {
+	KVM_PGTABLE_WALK_LEAF			= BIT(0),
+	KVM_PGTABLE_WALK_TABLE_PRE		= BIT(1),
+	KVM_PGTABLE_WALK_TABLE_POST		= BIT(2),
+	KVM_PGTABLE_WALK_SHARED			= BIT(3),
+};
+
+struct kvm_pgtable_visit_ctx {
+	kvm_pte_t				*ptep;
+	kvm_pte_t				old;
+	void					*arg;
+	struct kvm_pgtable_mm_ops		*mm_ops;
+	u64					addr;
+	u64					end;
+	u32					level;
+	enum kvm_pgtable_walk_flags		flags;
+};
+
+typedef int (*kvm_pgtable_visitor_fn_t)(const struct kvm_pgtable_visit_ctx *ctx,
+					enum kvm_pgtable_walk_flags visit);
+
+static inline bool kvm_pgtable_walk_shared(const struct kvm_pgtable_visit_ctx *ctx)
+{
+	return ctx->flags & KVM_PGTABLE_WALK_SHARED;
+}
+
+/**
+ * struct kvm_pgtable_walker - Hook into a page-table walk.
+ * @cb:		Callback function to invoke during the walk.
+ * @arg:	Argument passed to the callback function.
+ * @flags:	Bitwise-OR of flags to identify the entry types on which to
+ *		invoke the callback function.
+ */
+struct kvm_pgtable_walker {
+	const kvm_pgtable_visitor_fn_t		cb;
+	void * const				arg;
+	const enum kvm_pgtable_walk_flags	flags;
+};
+
+/*
+ * RCU cannot be used in a non-kernel context such as the hyp. As such, page
+ * table walkers used in hyp do not call into RCU and instead use other
+ * synchronization mechanisms (such as a spinlock).
+ */
+#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__)
+
+typedef kvm_pte_t *kvm_pteref_t;
+
+static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker,
+						kvm_pteref_t pteref)
+{
+	return pteref;
+}
+
+static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
+{
+	/*
+	 * Due to the lack of RCU (or a similar protection scheme), only
+	 * non-shared table walkers are allowed in the hypervisor.
+	 */
+	if (walker->flags & KVM_PGTABLE_WALK_SHARED)
+		return -EPERM;
+
+	return 0;
+}
+
+static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) {}
+
+static inline bool kvm_pgtable_walk_lock_held(void)
+{
+	return true;
+}
+
+#else
+
+typedef kvm_pte_t __rcu *kvm_pteref_t;
+
+static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker,
+						kvm_pteref_t pteref)
+{
+	return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED));
+}
+
+static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
+{
+	if (walker->flags & KVM_PGTABLE_WALK_SHARED)
+		rcu_read_lock();
+
+	return 0;
+}
+
+static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker)
+{
+	if (walker->flags & KVM_PGTABLE_WALK_SHARED)
+		rcu_read_unlock();
+}
+
+static inline bool kvm_pgtable_walk_lock_held(void)
+{
+	return rcu_read_lock_held();
+}
+
+#endif
+
 /**
  * struct kvm_pgtable - KVM page-table.
  * @ia_bits:		Maximum input address size, in bits.
@@ -175,7 +293,7 @@ typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
 struct kvm_pgtable {
 	u32					ia_bits;
 	u32					start_level;
-	kvm_pte_t				*pgd;
+	kvm_pteref_t				pgd;
 	struct kvm_pgtable_mm_ops		*mm_ops;
 
 	/* Stage-2 only */
@@ -184,39 +302,6 @@ struct kvm_pgtable {
 	kvm_pgtable_force_pte_cb_t		force_pte_cb;
 };
 
-/**
- * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk.
- * @KVM_PGTABLE_WALK_LEAF:		Visit leaf entries, including invalid
- *					entries.
- * @KVM_PGTABLE_WALK_TABLE_PRE:		Visit table entries before their
- *					children.
- * @KVM_PGTABLE_WALK_TABLE_POST:	Visit table entries after their
- *					children.
- */
-enum kvm_pgtable_walk_flags {
-	KVM_PGTABLE_WALK_LEAF			= BIT(0),
-	KVM_PGTABLE_WALK_TABLE_PRE		= BIT(1),
-	KVM_PGTABLE_WALK_TABLE_POST		= BIT(2),
-};
-
-typedef int (*kvm_pgtable_visitor_fn_t)(u64 addr, u64 end, u32 level,
-					kvm_pte_t *ptep,
-					enum kvm_pgtable_walk_flags flag,
-					void * const arg);
-
-/**
- * struct kvm_pgtable_walker - Hook into a page-table walk.
- * @cb:		Callback function to invoke during the walk.
- * @arg:	Argument passed to the callback function.
- * @flags:	Bitwise-OR of flags to identify the entry types on which to
- *		invoke the callback function.
- */
-struct kvm_pgtable_walker {
-	const kvm_pgtable_visitor_fn_t		cb;
-	void * const				arg;
-	const enum kvm_pgtable_walk_flags	flags;
-};
-
 /**
  * kvm_pgtable_hyp_init() - Initialise a hypervisor stage-1 page-table.
  * @pgt:	Uninitialised page-table structure to initialise.
@@ -324,6 +409,17 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
  */
 void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
 
+/**
+ * kvm_pgtable_stage2_free_removed() - Free a removed stage-2 paging structure.
+ * @mm_ops:	Memory management callbacks.
+ * @pgtable:	Unlinked stage-2 paging structure to be freed.
+ * @level:	Level of the stage-2 paging structure to be freed.
+ *
+ * The page-table is assumed to be unreachable by any hardware walkers prior to
+ * freeing and therefore no TLB invalidation is performed.
+ */
+void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
+
 /**
  * kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
@@ -333,6 +429,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
  * @prot:	Permissions and attributes for the mapping.
  * @mc:		Cache of pre-allocated and zeroed memory from which to allocate
  *		page-table pages.
+ * @flags:	Flags to control the page-table walk (ex. a shared walk)
  *
  * The offset of @addr within a page is ignored, @size is rounded-up to
  * the next page boundary and @phys is rounded-down to the previous page
@@ -354,7 +451,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
  */
 int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 			   u64 phys, enum kvm_pgtable_prot prot,
-			   void *mc);
+			   void *mc, enum kvm_pgtable_walk_flags flags);
 
 /**
  * kvm_pgtable_stage2_set_owner() - Unmap and annotate pages in the IPA space to

arch/arm64/kvm/hyp/nvhe/mem_protect.c

@@ -79,6 +79,11 @@ static void host_s2_put_page(void *addr)
 	hyp_put_page(&host_s2_pool, addr);
 }
 
+static void host_s2_free_removed_table(void *addr, u32 level)
+{
+	kvm_pgtable_stage2_free_removed(&host_kvm.mm_ops, addr, level);
+}
+
 static int prepare_s2_pool(void *pgt_pool_base)
 {
 	unsigned long nr_pages, pfn;
@@ -93,6 +98,7 @@ static int prepare_s2_pool(void *pgt_pool_base)
 	host_kvm.mm_ops = (struct kvm_pgtable_mm_ops) {
 		.zalloc_pages_exact = host_s2_zalloc_pages_exact,
 		.zalloc_page = host_s2_zalloc_page,
+		.free_removed_table = host_s2_free_removed_table,
 		.phys_to_virt = hyp_phys_to_virt,
 		.virt_to_phys = hyp_virt_to_phys,
 		.page_count = hyp_page_count,
@@ -251,7 +257,7 @@ static inline int __host_stage2_idmap(u64 start, u64 end,
 				      enum kvm_pgtable_prot prot)
 {
 	return kvm_pgtable_stage2_map(&host_kvm.pgt, start, end - start, start,
-				      prot, &host_s2_pool);
+				      prot, &host_s2_pool, 0);
 }
 
 /*
@@ -417,18 +423,15 @@ struct check_walk_data {
 	enum pkvm_page_state	(*get_page_state)(kvm_pte_t pte);
 };
 
-static int __check_page_state_visitor(u64 addr, u64 end, u32 level,
+static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx,
-				      kvm_pte_t *ptep,
+				      enum kvm_pgtable_walk_flags visit)
-				      enum kvm_pgtable_walk_flags flag,
-				      void * const arg)
 {
-	struct check_walk_data *d = arg;
+	struct check_walk_data *d = ctx->arg;
-	kvm_pte_t pte = *ptep;
 
-	if (kvm_pte_valid(pte) && !addr_is_memory(kvm_pte_to_phys(pte)))
+	if (kvm_pte_valid(ctx->old) && !addr_is_memory(kvm_pte_to_phys(ctx->old)))
 		return -EINVAL;
 
-	return d->get_page_state(pte) == d->desired ? 0 : -EPERM;
+	return d->get_page_state(ctx->old) == d->desired ? 0 : -EPERM;
 }
 
 static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size,

arch/arm64/kvm/hyp/nvhe/setup.c

@@ -186,18 +186,15 @@ static void hpool_put_page(void *addr)
 	hyp_put_page(&hpool, addr);
 }
 
-static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level,
+static int finalize_host_mappings_walker(const struct kvm_pgtable_visit_ctx *ctx,
-					 kvm_pte_t *ptep,
+					 enum kvm_pgtable_walk_flags visit)
-					 enum kvm_pgtable_walk_flags flag,
-					 void * const arg)
 {
-	struct kvm_pgtable_mm_ops *mm_ops = arg;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
 	enum kvm_pgtable_prot prot;
 	enum pkvm_page_state state;
-	kvm_pte_t pte = *ptep;
 	phys_addr_t phys;
 
-	if (!kvm_pte_valid(pte))
+	if (!kvm_pte_valid(ctx->old))
 		return 0;
 
 	/*
@@ -205,14 +202,14 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level,
 	 * was unable to access the hyp_vmemmap and so the buddy allocator has
 	 * initialised the refcount to '1'.
 	 */
-	mm_ops->get_page(ptep);
+	mm_ops->get_page(ctx->ptep);
-	if (flag != KVM_PGTABLE_WALK_LEAF)
+	if (visit != KVM_PGTABLE_WALK_LEAF)
 		return 0;
 
-	if (level != (KVM_PGTABLE_MAX_LEVELS - 1))
+	if (ctx->level != (KVM_PGTABLE_MAX_LEVELS - 1))
 		return -EINVAL;
 
-	phys = kvm_pte_to_phys(pte);
+	phys = kvm_pte_to_phys(ctx->old);
 	if (!addr_is_memory(phys))
 		return -EINVAL;
 
@@ -220,7 +217,7 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level,
 	 * Adjust the host stage-2 mappings to match the ownership attributes
 	 * configured in the hypervisor stage-1.
 	 */
-	state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte));
+	state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(ctx->old));
 	switch (state) {
 	case PKVM_PAGE_OWNED:
 		return host_stage2_set_owner_locked(phys, PAGE_SIZE, pkvm_hyp_id);
@@ -242,7 +239,6 @@ static int finalize_host_mappings(void)
 	struct kvm_pgtable_walker walker = {
 		.cb	= finalize_host_mappings_walker,
 		.flags	= KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
-		.arg	= pkvm_pgtable.mm_ops,
 	};
 	int i, ret;
 

arch/arm64/kvm/mmu.c

@@ -128,6 +128,25 @@ static void kvm_s2_free_pages_exact(void *virt, size_t size)
 	free_pages_exact(virt, size);
 }
 
+static struct kvm_pgtable_mm_ops kvm_s2_mm_ops;
+
+static void stage2_free_removed_table_rcu_cb(struct rcu_head *head)
+{
+	struct page *page = container_of(head, struct page, rcu_head);
+	void *pgtable = page_to_virt(page);
+	u32 level = page_private(page);
+
+	kvm_pgtable_stage2_free_removed(&kvm_s2_mm_ops, pgtable, level);
+}
+
+static void stage2_free_removed_table(void *addr, u32 level)
+{
+	struct page *page = virt_to_page(addr);
+
+	set_page_private(page, (unsigned long)level);
+	call_rcu(&page->rcu_head, stage2_free_removed_table_rcu_cb);
+}
+
 static void kvm_host_get_page(void *addr)
 {
 	get_page(virt_to_page(addr));
@@ -640,7 +659,7 @@ static struct kvm_pgtable_mm_ops kvm_user_mm_ops = {
 static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 {
 	struct kvm_pgtable pgt = {
-		.pgd		= (kvm_pte_t *)kvm->mm->pgd,
+		.pgd		= (kvm_pteref_t)kvm->mm->pgd,
 		.ia_bits	= vabits_actual,
 		.start_level	= (KVM_PGTABLE_MAX_LEVELS -
 				   CONFIG_PGTABLE_LEVELS),
@@ -662,6 +681,7 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
 	.zalloc_page		= stage2_memcache_zalloc_page,
 	.zalloc_pages_exact	= kvm_s2_zalloc_pages_exact,
 	.free_pages_exact	= kvm_s2_free_pages_exact,
+	.free_removed_table	= stage2_free_removed_table,
 	.get_page		= kvm_host_get_page,
 	.put_page		= kvm_s2_put_page,
 	.page_count		= kvm_host_page_count,
@@ -841,7 +861,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 
 		write_lock(&kvm->mmu_lock);
 		ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot,
-					     &cache);
+					     &cache, 0);
 		write_unlock(&kvm->mmu_lock);
 		if (ret)
 			break;
@@ -1136,7 +1156,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
-	bool use_read_lock = false;
 	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	unsigned long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
@@ -1171,8 +1190,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (logging_active) {
 		force_pte = true;
 		vma_shift = PAGE_SHIFT;
-		use_read_lock = (fault_status == FSC_PERM && write_fault &&
-				 fault_granule == PAGE_SIZE);
 	} else {
 		vma_shift = get_vma_page_shift(vma, hva);
 	}
@@ -1271,15 +1288,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && device)
 		return -ENOEXEC;
 
-	/*
+	read_lock(&kvm->mmu_lock);
-	 * To reduce MMU contentions and enhance concurrency during dirty
-	 * logging dirty logging, only acquire read lock for permission
-	 * relaxation.
-	 */
-	if (use_read_lock)
-		read_lock(&kvm->mmu_lock);
-	else
-		write_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
@@ -1323,15 +1332,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_status == FSC_PERM && vma_pagesize == fault_granule) {
+	if (fault_status == FSC_PERM && vma_pagesize == fault_granule)
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
-	} else {
+	else
-		WARN_ONCE(use_read_lock, "Attempted stage-2 map outside of write lock\n");
-
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
-					     memcache);
+					     memcache, KVM_PGTABLE_WALK_SHARED);
-	}
 
 	/* Mark the page dirty only if the fault is handled successfully */
 	if (writable && !ret) {
@@ -1340,10 +1346,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 out_unlock:
-	if (use_read_lock)
+	read_unlock(&kvm->mmu_lock);
-		read_unlock(&kvm->mmu_lock);
-	else
-		write_unlock(&kvm->mmu_lock);
 	kvm_set_pfn_accessed(pfn);
 	kvm_release_pfn_clean(pfn);
 	return ret != -EAGAIN ? ret : 0;
@@ -1549,7 +1552,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	 */
 	kvm_pgtable_stage2_map(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT,
 			       PAGE_SIZE, __pfn_to_phys(pfn),
-			       KVM_PGTABLE_PROT_R, NULL);
+			       KVM_PGTABLE_PROT_R, NULL, 0);
 
 	return false;
 }