Merge branch 'main' into zstd-linus

1 files changed, 108 insertions, 27 deletions

diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index bf5ba9af0500..79e894cf8406 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -32,6 +32,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/memblock.h>
+#include <linux/kasan-enabled.h>
 
 #define DEPOT_STACK_BITS (sizeof(depot_stack_handle_t) * 8)
 
@@ -42,7 +43,8 @@
 #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_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) ? \
@@ -55,6 +57,7 @@ union handle_parts {
 		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;
 	};
 };
 
@@ -66,6 +69,9 @@ struct stack_record {
 	unsigned long entries[];	/* Variable-sized array of entries. */
 };
 
+static bool __stack_depot_want_early_init __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;
@@ -73,6 +79,14 @@ 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)
@@ -136,16 +150,23 @@ depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
 	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;
 }
 
-#define STACK_HASH_SIZE (1L << CONFIG_STACK_HASH_ORDER)
-#define STACK_HASH_MASK (STACK_HASH_SIZE - 1)
+/* 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
 #define STACK_HASH_SEED 0x9747b28c
 
+static unsigned int stack_hash_order;
+static unsigned int stack_hash_mask;
+
 static bool stack_depot_disable;
 static struct stack_record **stack_table;
 
@@ -162,38 +183,90 @@ static int __init is_stack_depot_disabled(char *str)
 }
 early_param("stack_depot_disable", is_stack_depot_disabled);
 
-/*
- * __ref because of memblock_alloc(), which will not be actually called after
- * the __init code is gone, because at that point slab_is_available() is true
- */
-__ref int stack_depot_init(void)
+void __init stack_depot_want_early_init(void)
+{
+	/* Too late to request early init now */
+	WARN_ON(__stack_depot_early_init_passed);
+
+	__stack_depot_want_early_init = true;
+}
+
+int __init stack_depot_early_init(void)
+{
+	unsigned long entries = 0;
+
+	/* This is supposed to 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 (!__stack_depot_want_early_init || stack_depot_disable)
+		return 0;
+
+	if (stack_hash_order)
+		entries = 1UL <<  stack_hash_order;
+	stack_table = alloc_large_system_hash("stackdepot",
+						sizeof(struct stack_record *),
+						entries,
+						STACK_HASH_SCALE,
+						HASH_EARLY | HASH_ZERO,
+						NULL,
+						&stack_hash_mask,
+						1UL << STACK_HASH_ORDER_MIN,
+						1UL << STACK_HASH_ORDER_MAX);
+
+	if (!stack_table) {
+		pr_err("Stack Depot hash table allocation failed, disabling\n");
+		stack_depot_disable = true;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int stack_depot_init(void)
 {
 	static DEFINE_MUTEX(stack_depot_init_mutex);
+	int ret = 0;
 
 	mutex_lock(&stack_depot_init_mutex);
 	if (!stack_depot_disable && !stack_table) {
-		size_t size = (STACK_HASH_SIZE * sizeof(struct stack_record *));
-		int i;
+		unsigned long entries;
+		int scale = STACK_HASH_SCALE;
 
-		if (slab_is_available()) {
-			pr_info("Stack Depot allocating hash table with kvmalloc\n");
-			stack_table = kvmalloc(size, GFP_KERNEL);
+		if (stack_hash_order) {
+			entries = 1UL << stack_hash_order;
 		} else {
-			pr_info("Stack Depot allocating hash table with memblock_alloc\n");
-			stack_table = memblock_alloc(size, SMP_CACHE_BYTES);
+			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 (stack_table) {
-			for (i = 0; i < STACK_HASH_SIZE;  i++)
-				stack_table[i] = NULL;
-		} else {
+
+		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;
-			mutex_unlock(&stack_depot_init_mutex);
-			return -ENOMEM;
+			ret = -ENOMEM;
 		}
+		stack_hash_mask = entries - 1;
 	}
 	mutex_unlock(&stack_depot_init_mutex);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(stack_depot_init);
 
@@ -320,6 +393,7 @@ EXPORT_SYMBOL_GPL(stack_depot_fetch);
  *
  * @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)
  *
@@ -331,6 +405,10 @@ EXPORT_SYMBOL_GPL(stack_depot_fetch);
  * 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
@@ -340,10 +418,11 @@ EXPORT_SYMBOL_GPL(stack_depot_fetch);
  */
 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;
-	depot_stack_handle_t retval = 0;
+	union handle_parts retval = { .handle = 0 };
 	struct page *page = NULL;
 	void *prealloc = NULL;
 	unsigned long flags;
@@ -363,7 +442,7 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
 		goto fast_exit;
 
 	hash = hash_stack(entries, nr_entries);
-	bucket = &stack_table[hash & STACK_HASH_MASK];
+	bucket = &stack_table[hash & stack_hash_mask];
 
 	/*
 	 * Fast path: look the stack trace up without locking.
@@ -427,9 +506,11 @@ exit:
 		free_pages((unsigned long)prealloc, STACK_ALLOC_ORDER);
 	}
 	if (found)
-		retval = found->handle.handle;
+		retval.handle = found->handle.handle;
 fast_exit:
-	return retval;
+	retval.extra = extra_bits;
+
+	return retval.handle;
 }
 EXPORT_SYMBOL_GPL(__stack_depot_save);
 
@@ -449,6 +530,6 @@ 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, alloc_flags, true);
+	return __stack_depot_save(entries, nr_entries, 0, alloc_flags, true);
 }
 EXPORT_SYMBOL_GPL(stack_depot_save);