1 files changed, 324 insertions, 330 deletions

diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 79e894cf8406..036da8e295d1 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -1,24 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Generic stack depot for storing stack traces.
+ * Stack depot - a stack trace storage that avoids duplication.
  *
- * Some debugging tools need to save stack traces of certain events which can
- * be later presented to the user. For example, KASAN needs to safe alloc and
- * free stacks for each object, but storing two stack traces per object
- * requires too much memory (e.g. SLUB_DEBUG needs 256 bytes per object for
- * that).
- *
- * Instead, stack depot maintains a hashtable of unique stacktraces. Since alloc
- * and free stacks repeat a lot, we save about 100x space.
- * Stacks are never removed from depot, so we store them contiguously one after
- * another in a contiguous memory allocation.
+ * Internally, stack depot maintains a hash table of unique stacktraces. The
+ * stack traces themselves are stored contiguously one after another in a set
+ * of separate page allocations.
  *
  * Author: Alexander Potapenko <glider@google.com>
  * Copyright (C) 2016 Google, Inc.
  *
- * Based on code by Dmitry Chernenkov.
+ * Based on the code by Dmitry Chernenkov.
  */
 
+#define pr_fmt(fmt) "stackdepot: " fmt
+
 #include <linux/gfp.h>
 #include <linux/jhash.h>
 #include <linux/kernel.h>
@@ -34,243 +29,288 @@
 #include <linux/memblock.h>
 #include <linux/kasan-enabled.h>
 
-#define DEPOT_STACK_BITS (sizeof(depot_stack_handle_t) * 8)
-
-#define STACK_ALLOC_NULL_PROTECTION_BITS 1
-#define STACK_ALLOC_ORDER 2 /* 'Slab' size order for stack depot, 4 pages */
-#define STACK_ALLOC_SIZE (1LL << (PAGE_SHIFT + STACK_ALLOC_ORDER))
-#define STACK_ALLOC_ALIGN 4
-#define STACK_ALLOC_OFFSET_BITS (STACK_ALLOC_ORDER + PAGE_SHIFT - \
-					STACK_ALLOC_ALIGN)
-#define STACK_ALLOC_INDEX_BITS (DEPOT_STACK_BITS - \
-		STACK_ALLOC_NULL_PROTECTION_BITS - \
-		STACK_ALLOC_OFFSET_BITS - STACK_DEPOT_EXTRA_BITS)
-#define STACK_ALLOC_SLABS_CAP 8192
-#define STACK_ALLOC_MAX_SLABS \
-	(((1LL << (STACK_ALLOC_INDEX_BITS)) < STACK_ALLOC_SLABS_CAP) ? \
-	 (1LL << (STACK_ALLOC_INDEX_BITS)) : STACK_ALLOC_SLABS_CAP)
-
-/* The compact structure to store the reference to stacks. */
+#define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8)
+
+#define DEPOT_VALID_BITS 1
+#define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */
+#define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER))
+#define DEPOT_STACK_ALIGN 4
+#define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN)
+#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_VALID_BITS - \
+			       DEPOT_OFFSET_BITS - STACK_DEPOT_EXTRA_BITS)
+#define DEPOT_POOLS_CAP 8192
+#define DEPOT_MAX_POOLS \
+	(((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \
+	 (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP)
+
+/* Compact structure that stores a reference to a stack. */
 union handle_parts {
 	depot_stack_handle_t handle;
 	struct {
-		u32 slabindex : STACK_ALLOC_INDEX_BITS;
-		u32 offset : STACK_ALLOC_OFFSET_BITS;
-		u32 valid : STACK_ALLOC_NULL_PROTECTION_BITS;
-		u32 extra : STACK_DEPOT_EXTRA_BITS;
+		u32 pool_index	: DEPOT_POOL_INDEX_BITS;
+		u32 offset	: DEPOT_OFFSET_BITS;
+		u32 valid	: DEPOT_VALID_BITS;
+		u32 extra	: STACK_DEPOT_EXTRA_BITS;
 	};
 };
 
 struct stack_record {
-	struct stack_record *next;	/* Link in the hashtable */
-	u32 hash;			/* Hash in the hastable */
-	u32 size;			/* Number of frames in the stack */
+	struct stack_record *next;	/* Link in the hash table */
+	u32 hash;			/* Hash in the hash table */
+	u32 size;			/* Number of stored frames */
 	union handle_parts handle;
-	unsigned long entries[];	/* Variable-sized array of entries. */
+	unsigned long entries[];	/* Variable-sized array of frames */
 };
 
-static bool __stack_depot_want_early_init __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT);
+static bool stack_depot_disabled;
+static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT);
 static bool __stack_depot_early_init_passed __initdata;
 
-static void *stack_slabs[STACK_ALLOC_MAX_SLABS];
-
-static int depot_index;
-static int next_slab_inited;
-static size_t depot_offset;
-static DEFINE_RAW_SPINLOCK(depot_lock);
-
-unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle)
-{
-	union handle_parts parts = { .handle = handle };
-
-	return parts.extra;
-}
-EXPORT_SYMBOL(stack_depot_get_extra_bits);
-
-static bool init_stack_slab(void **prealloc)
-{
-	if (!*prealloc)
-		return false;
-	/*
-	 * This smp_load_acquire() pairs with smp_store_release() to
-	 * |next_slab_inited| below and in depot_alloc_stack().
-	 */
-	if (smp_load_acquire(&next_slab_inited))
-		return true;
-	if (stack_slabs[depot_index] == NULL) {
-		stack_slabs[depot_index] = *prealloc;
-		*prealloc = NULL;
-	} else {
-		/* If this is the last depot slab, do not touch the next one. */
-		if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) {
-			stack_slabs[depot_index + 1] = *prealloc;
-			*prealloc = NULL;
-		}
-		/*
-		 * This smp_store_release pairs with smp_load_acquire() from
-		 * |next_slab_inited| above and in stack_depot_save().
-		 */
-		smp_store_release(&next_slab_inited, 1);
-	}
-	return true;
-}
-
-/* Allocation of a new stack in raw storage */
-static struct stack_record *
-depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
-{
-	struct stack_record *stack;
-	size_t required_size = struct_size(stack, entries, size);
-
-	required_size = ALIGN(required_size, 1 << STACK_ALLOC_ALIGN);
-
-	if (unlikely(depot_offset + required_size > STACK_ALLOC_SIZE)) {
-		if (unlikely(depot_index + 1 >= STACK_ALLOC_MAX_SLABS)) {
-			WARN_ONCE(1, "Stack depot reached limit capacity");
-			return NULL;
-		}
-		depot_index++;
-		depot_offset = 0;
-		/*
-		 * smp_store_release() here pairs with smp_load_acquire() from
-		 * |next_slab_inited| in stack_depot_save() and
-		 * init_stack_slab().
-		 */
-		if (depot_index + 1 < STACK_ALLOC_MAX_SLABS)
-			smp_store_release(&next_slab_inited, 0);
-	}
-	init_stack_slab(prealloc);
-	if (stack_slabs[depot_index] == NULL)
-		return NULL;
-
-	stack = stack_slabs[depot_index] + depot_offset;
-
-	stack->hash = hash;
-	stack->size = size;
-	stack->handle.slabindex = depot_index;
-	stack->handle.offset = depot_offset >> STACK_ALLOC_ALIGN;
-	stack->handle.valid = 1;
-	stack->handle.extra = 0;
-	memcpy(stack->entries, entries, flex_array_size(stack, entries, size));
-	depot_offset += required_size;
-
-	return stack;
-}
-
-/* one hash table bucket entry per 16kB of memory */
-#define STACK_HASH_SCALE	14
-/* limited between 4k and 1M buckets */
-#define STACK_HASH_ORDER_MIN	12
-#define STACK_HASH_ORDER_MAX	20
+/* Use one hash table bucket per 16 KB of memory. */
+#define STACK_HASH_TABLE_SCALE 14
+/* Limit the number of buckets between 4K and 1M. */
+#define STACK_BUCKET_NUMBER_ORDER_MIN 12
+#define STACK_BUCKET_NUMBER_ORDER_MAX 20
+/* Initial seed for jhash2. */
 #define STACK_HASH_SEED 0x9747b28c
 
-static unsigned int stack_hash_order;
+/* Hash table of pointers to stored stack traces. */
+static struct stack_record **stack_table;
+/* Fixed order of the number of table buckets. Used when KASAN is enabled. */
+static unsigned int stack_bucket_number_order;
+/* Hash mask for indexing the table. */
 static unsigned int stack_hash_mask;
 
-static bool stack_depot_disable;
-static struct stack_record **stack_table;
+/* Array of memory regions that store stack traces. */
+static void *stack_pools[DEPOT_MAX_POOLS];
+/* Currently used pool in stack_pools. */
+static int pool_index;
+/* Offset to the unused space in the currently used pool. */
+static size_t pool_offset;
+/* Lock that protects the variables above. */
+static DEFINE_RAW_SPINLOCK(pool_lock);
+/*
+ * Stack depot tries to keep an extra pool allocated even before it runs out
+ * of space in the currently used pool.
+ * This flag marks that this next extra pool needs to be allocated and
+ * initialized. It has the value 0 when either the next pool is not yet
+ * initialized or the limit on the number of pools is reached.
+ */
+static int next_pool_required = 1;
 
-static int __init is_stack_depot_disabled(char *str)
+static int __init disable_stack_depot(char *str)
 {
 	int ret;
 
-	ret = kstrtobool(str, &stack_depot_disable);
-	if (!ret && stack_depot_disable) {
-		pr_info("Stack Depot is disabled\n");
+	ret = kstrtobool(str, &stack_depot_disabled);
+	if (!ret && stack_depot_disabled) {
+		pr_info("disabled\n");
 		stack_table = NULL;
 	}
 	return 0;
 }
-early_param("stack_depot_disable", is_stack_depot_disabled);
+early_param("stack_depot_disable", disable_stack_depot);
 
-void __init stack_depot_want_early_init(void)
+void __init stack_depot_request_early_init(void)
 {
-	/* Too late to request early init now */
+	/* Too late to request early init now. */
 	WARN_ON(__stack_depot_early_init_passed);
 
-	__stack_depot_want_early_init = true;
+	__stack_depot_early_init_requested = true;
 }
 
+/* Allocates a hash table via memblock. Can only be used during early boot. */
 int __init stack_depot_early_init(void)
 {
 	unsigned long entries = 0;
 
-	/* This is supposed to be called only once, from mm_init() */
+	/* This function must be called only once, from mm_init(). */
 	if (WARN_ON(__stack_depot_early_init_passed))
 		return 0;
-
 	__stack_depot_early_init_passed = true;
 
-	if (kasan_enabled() && !stack_hash_order)
-		stack_hash_order = STACK_HASH_ORDER_MAX;
+	/*
+	 * If KASAN is enabled, use the maximum order: KASAN is frequently used
+	 * in fuzzing scenarios, which leads to a large number of different
+	 * stack traces being stored in stack depot.
+	 */
+	if (kasan_enabled() && !stack_bucket_number_order)
+		stack_bucket_number_order = STACK_BUCKET_NUMBER_ORDER_MAX;
 
-	if (!__stack_depot_want_early_init || stack_depot_disable)
+	if (!__stack_depot_early_init_requested || stack_depot_disabled)
 		return 0;
 
-	if (stack_hash_order)
-		entries = 1UL <<  stack_hash_order;
+	/*
+	 * If stack_bucket_number_order is not set, leave entries as 0 to rely
+	 * on the automatic calculations performed by alloc_large_system_hash.
+	 */
+	if (stack_bucket_number_order)
+		entries = 1UL << stack_bucket_number_order;
+	pr_info("allocating hash table via alloc_large_system_hash\n");
 	stack_table = alloc_large_system_hash("stackdepot",
 						sizeof(struct stack_record *),
 						entries,
-						STACK_HASH_SCALE,
+						STACK_HASH_TABLE_SCALE,
 						HASH_EARLY | HASH_ZERO,
 						NULL,
 						&stack_hash_mask,
-						1UL << STACK_HASH_ORDER_MIN,
-						1UL << STACK_HASH_ORDER_MAX);
-
+						1UL << STACK_BUCKET_NUMBER_ORDER_MIN,
+						1UL << STACK_BUCKET_NUMBER_ORDER_MAX);
 	if (!stack_table) {
-		pr_err("Stack Depot hash table allocation failed, disabling\n");
-		stack_depot_disable = true;
+		pr_err("hash table allocation failed, disabling\n");
+		stack_depot_disabled = true;
 		return -ENOMEM;
 	}
 
 	return 0;
 }
 
+/* Allocates a hash table via kvcalloc. Can be used after boot. */
 int stack_depot_init(void)
 {
 	static DEFINE_MUTEX(stack_depot_init_mutex);
+	unsigned long entries;
 	int ret = 0;
 
 	mutex_lock(&stack_depot_init_mutex);
-	if (!stack_depot_disable && !stack_table) {
-		unsigned long entries;
-		int scale = STACK_HASH_SCALE;
-
-		if (stack_hash_order) {
-			entries = 1UL << stack_hash_order;
-		} else {
-			entries = nr_free_buffer_pages();
-			entries = roundup_pow_of_two(entries);
-
-			if (scale > PAGE_SHIFT)
-				entries >>= (scale - PAGE_SHIFT);
-			else
-				entries <<= (PAGE_SHIFT - scale);
-		}
 
-		if (entries < 1UL << STACK_HASH_ORDER_MIN)
-			entries = 1UL << STACK_HASH_ORDER_MIN;
-		if (entries > 1UL << STACK_HASH_ORDER_MAX)
-			entries = 1UL << STACK_HASH_ORDER_MAX;
-
-		pr_info("Stack Depot allocating hash table of %lu entries with kvcalloc\n",
-				entries);
-		stack_table = kvcalloc(entries, sizeof(struct stack_record *), GFP_KERNEL);
-		if (!stack_table) {
-			pr_err("Stack Depot hash table allocation failed, disabling\n");
-			stack_depot_disable = true;
-			ret = -ENOMEM;
-		}
-		stack_hash_mask = entries - 1;
+	if (stack_depot_disabled || stack_table)
+		goto out_unlock;
+
+	/*
+	 * Similarly to stack_depot_early_init, use stack_bucket_number_order
+	 * if assigned, and rely on automatic scaling otherwise.
+	 */
+	if (stack_bucket_number_order) {
+		entries = 1UL << stack_bucket_number_order;
+	} else {
+		int scale = STACK_HASH_TABLE_SCALE;
+
+		entries = nr_free_buffer_pages();
+		entries = roundup_pow_of_two(entries);
+
+		if (scale > PAGE_SHIFT)
+			entries >>= (scale - PAGE_SHIFT);
+		else
+			entries <<= (PAGE_SHIFT - scale);
+	}
+
+	if (entries < 1UL << STACK_BUCKET_NUMBER_ORDER_MIN)
+		entries = 1UL << STACK_BUCKET_NUMBER_ORDER_MIN;
+	if (entries > 1UL << STACK_BUCKET_NUMBER_ORDER_MAX)
+		entries = 1UL << STACK_BUCKET_NUMBER_ORDER_MAX;
+
+	pr_info("allocating hash table of %lu entries via kvcalloc\n", entries);
+	stack_table = kvcalloc(entries, sizeof(struct stack_record *), GFP_KERNEL);
+	if (!stack_table) {
+		pr_err("hash table allocation failed, disabling\n");
+		stack_depot_disabled = true;
+		ret = -ENOMEM;
+		goto out_unlock;
 	}
+	stack_hash_mask = entries - 1;
+
+out_unlock:
 	mutex_unlock(&stack_depot_init_mutex);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(stack_depot_init);
 
-/* Calculate hash for a stack */
+/* Uses preallocated memory to initialize a new stack depot pool. */
+static void depot_init_pool(void **prealloc)
+{
+	/*
+	 * If the next pool is already initialized or the maximum number of
+	 * pools is reached, do not use the preallocated memory.
+	 * smp_load_acquire() here pairs with smp_store_release() below and
+	 * in depot_alloc_stack().
+	 */
+	if (!smp_load_acquire(&next_pool_required))
+		return;
+
+	/* Check if the current pool is not yet allocated. */
+	if (stack_pools[pool_index] == NULL) {
+		/* Use the preallocated memory for the current pool. */
+		stack_pools[pool_index] = *prealloc;
+		*prealloc = NULL;
+	} else {
+		/*
+		 * Otherwise, use the preallocated memory for the next pool
+		 * as long as we do not exceed the maximum number of pools.
+		 */
+		if (pool_index + 1 < DEPOT_MAX_POOLS) {
+			stack_pools[pool_index + 1] = *prealloc;
+			*prealloc = NULL;
+		}
+		/*
+		 * At this point, either the next pool is initialized or the
+		 * maximum number of pools is reached. In either case, take
+		 * note that initializing another pool is not required.
+		 * This smp_store_release pairs with smp_load_acquire() above
+		 * and in stack_depot_save().
+		 */
+		smp_store_release(&next_pool_required, 0);
+	}
+}
+
+/* Allocates a new stack in a stack depot pool. */
+static struct stack_record *
+depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
+{
+	struct stack_record *stack;
+	size_t required_size = struct_size(stack, entries, size);
+
+	required_size = ALIGN(required_size, 1 << DEPOT_STACK_ALIGN);
+
+	/* Check if there is not enough space in the current pool. */
+	if (unlikely(pool_offset + required_size > DEPOT_POOL_SIZE)) {
+		/* Bail out if we reached the pool limit. */
+		if (unlikely(pool_index + 1 >= DEPOT_MAX_POOLS)) {
+			WARN_ONCE(1, "Stack depot reached limit capacity");
+			return NULL;
+		}
+
+		/*
+		 * Move on to the next pool.
+		 * WRITE_ONCE pairs with potential concurrent read in
+		 * stack_depot_fetch().
+		 */
+		WRITE_ONCE(pool_index, pool_index + 1);
+		pool_offset = 0;
+		/*
+		 * If the maximum number of pools is not reached, take note
+		 * that the next pool needs to initialized.
+		 * smp_store_release() here pairs with smp_load_acquire() in
+		 * stack_depot_save() and depot_init_pool().
+		 */
+		if (pool_index + 1 < DEPOT_MAX_POOLS)
+			smp_store_release(&next_pool_required, 1);
+	}
+
+	/* Assign the preallocated memory to a pool if required. */
+	if (*prealloc)
+		depot_init_pool(prealloc);
+
+	/* Check if we have a pool to save the stack trace. */
+	if (stack_pools[pool_index] == NULL)
+		return NULL;
+
+	/* Save the stack trace. */
+	stack = stack_pools[pool_index] + pool_offset;
+	stack->hash = hash;
+	stack->size = size;
+	stack->handle.pool_index = pool_index;
+	stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN;
+	stack->handle.valid = 1;
+	stack->handle.extra = 0;
+	memcpy(stack->entries, entries, flex_array_size(stack, entries, size));
+	pool_offset += required_size;
+
+	return stack;
+}
+
+/* Calculates the hash for a stack. */
 static inline u32 hash_stack(unsigned long *entries, unsigned int size)
 {
 	return jhash2((u32 *)entries,
@@ -278,9 +318,9 @@ static inline u32 hash_stack(unsigned long *entries, unsigned int size)
 		      STACK_HASH_SEED);
 }
 
-/* Use our own, non-instrumented version of memcmp().
- *
- * We actually don't care about the order, just the equality.
+/*
+ * Non-instrumented version of memcmp().
+ * Does not check the lexicographical order, only the equality.
  */
 static inline
 int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2,
@@ -293,7 +333,7 @@ int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2,
 	return 0;
 }
 
-/* Find a stack that is equal to the one stored in entries in the hash */
+/* Finds a stack in a bucket of the hash table. */
 static inline struct stack_record *find_stack(struct stack_record *bucket,
 					     unsigned long *entries, int size,
 					     u32 hash)
@@ -309,116 +349,8 @@ static inline struct stack_record *find_stack(struct stack_record *bucket,
 	return NULL;
 }
 
-/**
- * stack_depot_snprint - print stack entries from a depot into a buffer
- *
- * @handle:	Stack depot handle which was returned from
- *		stack_depot_save().
- * @buf:	Pointer to the print buffer
- *
- * @size:	Size of the print buffer
- *
- * @spaces:	Number of leading spaces to print
- *
- * Return:	Number of bytes printed.
- */
-int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size,
-		       int spaces)
-{
-	unsigned long *entries;
-	unsigned int nr_entries;
-
-	nr_entries = stack_depot_fetch(handle, &entries);
-	return nr_entries ? stack_trace_snprint(buf, size, entries, nr_entries,
-						spaces) : 0;
-}
-EXPORT_SYMBOL_GPL(stack_depot_snprint);
-
-/**
- * stack_depot_print - print stack entries from a depot
- *
- * @stack:		Stack depot handle which was returned from
- *			stack_depot_save().
- *
- */
-void stack_depot_print(depot_stack_handle_t stack)
-{
-	unsigned long *entries;
-	unsigned int nr_entries;
-
-	nr_entries = stack_depot_fetch(stack, &entries);
-	if (nr_entries > 0)
-		stack_trace_print(entries, nr_entries, 0);
-}
-EXPORT_SYMBOL_GPL(stack_depot_print);
-
-/**
- * stack_depot_fetch - Fetch stack entries from a depot
- *
- * @handle:		Stack depot handle which was returned from
- *			stack_depot_save().
- * @entries:		Pointer to store the entries address
- *
- * Return: The number of trace entries for this depot.
- */
-unsigned int stack_depot_fetch(depot_stack_handle_t handle,
-			       unsigned long **entries)
-{
-	union handle_parts parts = { .handle = handle };
-	void *slab;
-	size_t offset = parts.offset << STACK_ALLOC_ALIGN;
-	struct stack_record *stack;
-
-	*entries = NULL;
-	if (!handle)
-		return 0;
-
-	if (parts.slabindex > depot_index) {
-		WARN(1, "slab index %d out of bounds (%d) for stack id %08x\n",
-			parts.slabindex, depot_index, handle);
-		return 0;
-	}
-	slab = stack_slabs[parts.slabindex];
-	if (!slab)
-		return 0;
-	stack = slab + offset;
-
-	*entries = stack->entries;
-	return stack->size;
-}
-EXPORT_SYMBOL_GPL(stack_depot_fetch);
-
-/**
- * __stack_depot_save - Save a stack trace from an array
- *
- * @entries:		Pointer to storage array
- * @nr_entries:		Size of the storage array
- * @extra_bits:		Flags to store in unused bits of depot_stack_handle_t
- * @alloc_flags:	Allocation gfp flags
- * @can_alloc:		Allocate stack slabs (increased chance of failure if false)
- *
- * Saves a stack trace from @entries array of size @nr_entries. If @can_alloc is
- * %true, is allowed to replenish the stack slab pool in case no space is left
- * (allocates using GFP flags of @alloc_flags). If @can_alloc is %false, avoids
- * any allocations and will fail if no space is left to store the stack trace.
- *
- * If the stack trace in @entries is from an interrupt, only the portion up to
- * interrupt entry is saved.
- *
- * Additional opaque flags can be passed in @extra_bits, stored in the unused
- * bits of the stack handle, and retrieved using stack_depot_get_extra_bits()
- * without calling stack_depot_fetch().
- *
- * Context: Any context, but setting @can_alloc to %false is required if
- *          alloc_pages() cannot be used from the current context. Currently
- *          this is the case from contexts where neither %GFP_ATOMIC nor
- *          %GFP_NOWAIT can be used (NMI, raw_spin_lock).
- *
- * Return: The handle of the stack struct stored in depot, 0 on failure.
- */
 depot_stack_handle_t __stack_depot_save(unsigned long *entries,
 					unsigned int nr_entries,
-					unsigned int extra_bits,
 					gfp_t alloc_flags, bool can_alloc)
 {
 	struct stack_record *found = NULL, **bucket;
@@ -430,15 +362,15 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
 
 	/*
 	 * If this stack trace is from an interrupt, including anything before
-	 * interrupt entry usually leads to unbounded stackdepot growth.
+	 * interrupt entry usually leads to unbounded stack depot growth.
 	 *
-	 * Because use of filter_irq_stacks() is a requirement to ensure
-	 * stackdepot can efficiently deduplicate interrupt stacks, always
-	 * filter_irq_stacks() to simplify all callers' use of stackdepot.
+	 * Since use of filter_irq_stacks() is a requirement to ensure stack
+	 * depot can efficiently deduplicate interrupt stacks, always
+	 * filter_irq_stacks() to simplify all callers' use of stack depot.
 	 */
 	nr_entries = filter_irq_stacks(entries, nr_entries);
 
-	if (unlikely(nr_entries == 0) || stack_depot_disable)
+	if (unlikely(nr_entries == 0) || stack_depot_disabled)
 		goto fast_exit;
 
 	hash = hash_stack(entries, nr_entries);
@@ -449,20 +381,18 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
 	 * The smp_load_acquire() here pairs with smp_store_release() to
 	 * |bucket| below.
 	 */
-	found = find_stack(smp_load_acquire(bucket), entries,
-			   nr_entries, hash);
+	found = find_stack(smp_load_acquire(bucket), entries, nr_entries, hash);
 	if (found)
 		goto exit;
 
 	/*
-	 * Check if the current or the next stack slab need to be initialized.
-	 * If so, allocate the memory - we won't be able to do that under the
-	 * lock.
+	 * Check if another stack pool needs to be initialized. If so, allocate
+	 * the memory now - we won't be able to do that under the lock.
 	 *
 	 * The smp_load_acquire() here pairs with smp_store_release() to
-	 * |next_slab_inited| in depot_alloc_stack() and init_stack_slab().
+	 * |next_pool_inited| in depot_alloc_stack() and depot_init_pool().
 	 */
-	if (unlikely(can_alloc && !smp_load_acquire(&next_slab_inited))) {
+	if (unlikely(can_alloc && smp_load_acquire(&next_pool_required))) {
 		/*
 		 * Zero out zone modifiers, as we don't have specific zone
 		 * requirements. Keep the flags related to allocation in atomic
@@ -471,16 +401,17 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
 		alloc_flags &= ~GFP_ZONEMASK;
 		alloc_flags &= (GFP_ATOMIC | GFP_KERNEL);
 		alloc_flags |= __GFP_NOWARN;
-		page = alloc_pages(alloc_flags, STACK_ALLOC_ORDER);
+		page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER);
 		if (page)
 			prealloc = page_address(page);
 	}
 
-	raw_spin_lock_irqsave(&depot_lock, flags);
+	raw_spin_lock_irqsave(&pool_lock, flags);
 
 	found = find_stack(*bucket, entries, nr_entries, hash);
 	if (!found) {
-		struct stack_record *new = depot_alloc_stack(entries, nr_entries, hash, &prealloc);
+		struct stack_record *new =
+			depot_alloc_stack(entries, nr_entries, hash, &prealloc);
 
 		if (new) {
 			new->next = *bucket;
@@ -493,43 +424,106 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
 		}
 	} else if (prealloc) {
 		/*
-		 * We didn't need to store this stack trace, but let's keep
-		 * the preallocated memory for the future.
+		 * Stack depot already contains this stack trace, but let's
+		 * keep the preallocated memory for the future.
 		 */
-		WARN_ON(!init_stack_slab(&prealloc));
+		depot_init_pool(&prealloc);
 	}
 
-	raw_spin_unlock_irqrestore(&depot_lock, flags);
+	raw_spin_unlock_irqrestore(&pool_lock, flags);
 exit:
 	if (prealloc) {
-		/* Nobody used this memory, ok to free it. */
-		free_pages((unsigned long)prealloc, STACK_ALLOC_ORDER);
+		/* Stack depot didn't use this memory, free it. */
+		free_pages((unsigned long)prealloc, DEPOT_POOL_ORDER);
 	}
 	if (found)
 		retval.handle = found->handle.handle;
 fast_exit:
-	retval.extra = extra_bits;
-
 	return retval.handle;
 }
 EXPORT_SYMBOL_GPL(__stack_depot_save);
 
-/**
- * stack_depot_save - Save a stack trace from an array
- *
- * @entries:		Pointer to storage array
- * @nr_entries:		Size of the storage array
- * @alloc_flags:	Allocation gfp flags
- *
- * Context: Contexts where allocations via alloc_pages() are allowed.
- *          See __stack_depot_save() for more details.
- *
- * Return: The handle of the stack struct stored in depot, 0 on failure.
- */
 depot_stack_handle_t stack_depot_save(unsigned long *entries,
 				      unsigned int nr_entries,
 				      gfp_t alloc_flags)
 {
-	return __stack_depot_save(entries, nr_entries, 0, alloc_flags, true);
+	return __stack_depot_save(entries, nr_entries, alloc_flags, true);
 }
 EXPORT_SYMBOL_GPL(stack_depot_save);
+
+unsigned int stack_depot_fetch(depot_stack_handle_t handle,
+			       unsigned long **entries)
+{
+	union handle_parts parts = { .handle = handle };
+	/*
+	 * READ_ONCE pairs with potential concurrent write in
+	 * depot_alloc_stack.
+	 */
+	int pool_index_cached = READ_ONCE(pool_index);
+	void *pool;
+	size_t offset = parts.offset << DEPOT_STACK_ALIGN;
+	struct stack_record *stack;
+
+	*entries = NULL;
+	if (!handle)
+		return 0;
+
+	if (parts.pool_index > pool_index_cached) {
+		WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
+			parts.pool_index, pool_index_cached, handle);
+		return 0;
+	}
+	pool = stack_pools[parts.pool_index];
+	if (!pool)
+		return 0;
+	stack = pool + offset;
+
+	*entries = stack->entries;
+	return stack->size;
+}
+EXPORT_SYMBOL_GPL(stack_depot_fetch);
+
+void stack_depot_print(depot_stack_handle_t stack)
+{
+	unsigned long *entries;
+	unsigned int nr_entries;
+
+	nr_entries = stack_depot_fetch(stack, &entries);
+	if (nr_entries > 0)
+		stack_trace_print(entries, nr_entries, 0);
+}
+EXPORT_SYMBOL_GPL(stack_depot_print);
+
+int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size,
+		       int spaces)
+{
+	unsigned long *entries;
+	unsigned int nr_entries;
+
+	nr_entries = stack_depot_fetch(handle, &entries);
+	return nr_entries ? stack_trace_snprint(buf, size, entries, nr_entries,
+						spaces) : 0;
+}
+EXPORT_SYMBOL_GPL(stack_depot_snprint);
+
+depot_stack_handle_t __must_check stack_depot_set_extra_bits(
+			depot_stack_handle_t handle, unsigned int extra_bits)
+{
+	union handle_parts parts = { .handle = handle };
+
+	/* Don't set extra bits on empty handles. */
+	if (!handle)
+		return 0;
+
+	parts.extra = extra_bits;
+	return parts.handle;
+}
+EXPORT_SYMBOL(stack_depot_set_extra_bits);
+
+unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle)
+{
+	union handle_parts parts = { .handle = handle };
+
+	return parts.extra;
+}
+EXPORT_SYMBOL(stack_depot_get_extra_bits);