From 31639fd6cebd4fc3687cceda14814f140c9fd95b Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 29 Jan 2024 11:07:01 +0100 Subject: stackdepot: use variable size records for non-evictable entries With the introduction of stack depot evictions, each stack record is now fixed size, so that future reuse after an eviction can safely store differently sized stack traces. In all cases that do not make use of evictions, this wastes lots of space. Fix it by re-introducing variable size stack records (up to the max allowed size) for entries that will never be evicted. We know if an entry will never be evicted if the flag STACK_DEPOT_FLAG_GET is not provided, since a later stack_depot_put() attempt is undefined behavior. With my current kernel config that enables KASAN and also SLUB owner tracking, I observe (after a kernel boot) a whopping reduction of 296 stack depot pools, which translates into 4736 KiB saved. The savings here are from SLUB owner tracking only, because KASAN generic mode still uses refcounting. Before: pools: 893 allocations: 29841 frees: 6524 in_use: 23317 freelist_size: 3454 After: pools: 597 refcounted_allocations: 17547 refcounted_frees: 6477 refcounted_in_use: 11070 freelist_size: 3497 persistent_count: 12163 persistent_bytes: 1717008 [elver@google.com: fix -Wstringop-overflow warning] Link: https://lore.kernel.org/all/20240201135747.18eca98e@canb.auug.org.au/ Link: https://lkml.kernel.org/r/20240201090434.1762340-1-elver@google.com Link: https://lore.kernel.org/all/CABXGCsOzpRPZGg23QqJAzKnqkZPKzvieeg=W7sgjgi3q0pBo0g@mail.gmail.com/ Link: https://lkml.kernel.org/r/20240129100708.39460-1-elver@google.com Link: https://lore.kernel.org/all/CABXGCsOzpRPZGg23QqJAzKnqkZPKzvieeg=W7sgjgi3q0pBo0g@mail.gmail.com/ Fixes: 108be8def46e ("lib/stackdepot: allow users to evict stack traces") Signed-off-by: Marco Elver Reviewed-by: Andrey Konovalov Tested-by: Mikhail Gavrilov Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Vincenzo Frascino Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- lib/stackdepot.c | 250 ++++++++++++++++++++++++++++--------------------------- 1 file changed, 127 insertions(+), 123 deletions(-) (limited to 'lib/stackdepot.c') diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 5caa1f566553..4a7055a63d9f 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -43,17 +44,7 @@ #define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN) #define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \ STACK_DEPOT_EXTRA_BITS) -#if IS_ENABLED(CONFIG_KMSAN) && CONFIG_STACKDEPOT_MAX_FRAMES >= 32 -/* - * KMSAN is frequently used in fuzzing scenarios and thus saves a lot of stack - * traces. As KMSAN does not support evicting stack traces from the stack - * depot, the stack depot capacity might be reached quickly with large stack - * records. Adjust the maximum number of stack depot pools for this case. - */ -#define DEPOT_POOLS_CAP (8192 * (CONFIG_STACKDEPOT_MAX_FRAMES / 16)) -#else #define DEPOT_POOLS_CAP 8192 -#endif #define DEPOT_MAX_POOLS \ (((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \ (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP) @@ -93,9 +84,6 @@ struct stack_record { }; }; -#define DEPOT_STACK_RECORD_SIZE \ - ALIGN(sizeof(struct stack_record), 1 << DEPOT_STACK_ALIGN) - 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; @@ -121,32 +109,31 @@ static void *stack_pools[DEPOT_MAX_POOLS]; static void *new_pool; /* Number of pools in stack_pools. */ static int pools_num; +/* Offset to the unused space in the currently used pool. */ +static size_t pool_offset = DEPOT_POOL_SIZE; /* Freelist of stack records within stack_pools. */ static LIST_HEAD(free_stacks); -/* - * Stack depot tries to keep an extra pool allocated even before it runs out - * of space in the currently used pool. This flag marks whether this extra pool - * needs to be allocated. It has the value 0 when either an extra pool is not - * yet allocated or if the limit on the number of pools is reached. - */ -static bool new_pool_required = true; /* The lock must be held when performing pool or freelist modifications. */ static DEFINE_RAW_SPINLOCK(pool_lock); /* Statistics counters for debugfs. */ enum depot_counter_id { - DEPOT_COUNTER_ALLOCS, - DEPOT_COUNTER_FREES, - DEPOT_COUNTER_INUSE, + DEPOT_COUNTER_REFD_ALLOCS, + DEPOT_COUNTER_REFD_FREES, + DEPOT_COUNTER_REFD_INUSE, DEPOT_COUNTER_FREELIST_SIZE, + DEPOT_COUNTER_PERSIST_COUNT, + DEPOT_COUNTER_PERSIST_BYTES, DEPOT_COUNTER_COUNT, }; static long counters[DEPOT_COUNTER_COUNT]; static const char *const counter_names[] = { - [DEPOT_COUNTER_ALLOCS] = "allocations", - [DEPOT_COUNTER_FREES] = "frees", - [DEPOT_COUNTER_INUSE] = "in_use", + [DEPOT_COUNTER_REFD_ALLOCS] = "refcounted_allocations", + [DEPOT_COUNTER_REFD_FREES] = "refcounted_frees", + [DEPOT_COUNTER_REFD_INUSE] = "refcounted_in_use", [DEPOT_COUNTER_FREELIST_SIZE] = "freelist_size", + [DEPOT_COUNTER_PERSIST_COUNT] = "persistent_count", + [DEPOT_COUNTER_PERSIST_BYTES] = "persistent_bytes", }; static_assert(ARRAY_SIZE(counter_names) == DEPOT_COUNTER_COUNT); @@ -294,48 +281,52 @@ out_unlock: EXPORT_SYMBOL_GPL(stack_depot_init); /* - * Initializes new stack depot @pool, release all its entries to the freelist, - * and update the list of pools. + * Initializes new stack pool, and updates the list of pools. */ -static void depot_init_pool(void *pool) +static bool depot_init_pool(void **prealloc) { - int offset; - lockdep_assert_held(&pool_lock); - /* Initialize handles and link stack records into the freelist. */ - for (offset = 0; offset <= DEPOT_POOL_SIZE - DEPOT_STACK_RECORD_SIZE; - offset += DEPOT_STACK_RECORD_SIZE) { - struct stack_record *stack = pool + offset; - - stack->handle.pool_index = pools_num; - stack->handle.offset = offset >> DEPOT_STACK_ALIGN; - stack->handle.extra = 0; - - /* - * Stack traces of size 0 are never saved, and we can simply use - * the size field as an indicator if this is a new unused stack - * record in the freelist. - */ - stack->size = 0; + if (unlikely(pools_num >= DEPOT_MAX_POOLS)) { + /* Bail out if we reached the pool limit. */ + WARN_ON_ONCE(pools_num > DEPOT_MAX_POOLS); /* should never happen */ + WARN_ON_ONCE(!new_pool); /* to avoid unnecessary pre-allocation */ + WARN_ONCE(1, "Stack depot reached limit capacity"); + return false; + } - INIT_LIST_HEAD(&stack->hash_list); - /* - * Add to the freelist front to prioritize never-used entries: - * required in case there are entries in the freelist, but their - * RCU cookie still belongs to the current RCU grace period - * (there can still be concurrent readers). - */ - list_add(&stack->free_list, &free_stacks); - counters[DEPOT_COUNTER_FREELIST_SIZE]++; + if (!new_pool && *prealloc) { + /* We have preallocated memory, use it. */ + WRITE_ONCE(new_pool, *prealloc); + *prealloc = NULL; } + if (!new_pool) + return false; /* new_pool and *prealloc are NULL */ + /* Save reference to the pool to be used by depot_fetch_stack(). */ - stack_pools[pools_num] = pool; + stack_pools[pools_num] = new_pool; + + /* + * Stack depot tries to keep an extra pool allocated even before it runs + * out of space in the currently used pool. + * + * To indicate that a new preallocation is needed new_pool is reset to + * NULL; do not reset to NULL if we have reached the maximum number of + * pools. + */ + if (pools_num < DEPOT_MAX_POOLS) + WRITE_ONCE(new_pool, NULL); + else + WRITE_ONCE(new_pool, STACK_DEPOT_POISON); /* Pairs with concurrent READ_ONCE() in depot_fetch_stack(). */ WRITE_ONCE(pools_num, pools_num + 1); ASSERT_EXCLUSIVE_WRITER(pools_num); + + pool_offset = 0; + + return true; } /* Keeps the preallocated memory to be used for a new stack depot pool. */ @@ -347,63 +338,51 @@ static void depot_keep_new_pool(void **prealloc) * If a new pool is already saved or the maximum number of * pools is reached, do not use the preallocated memory. */ - if (!new_pool_required) + if (new_pool) return; - /* - * Use the preallocated memory for the new pool - * as long as we do not exceed the maximum number of pools. - */ - if (pools_num < DEPOT_MAX_POOLS) { - new_pool = *prealloc; - *prealloc = NULL; - } - - /* - * At this point, either a new pool is kept or the maximum - * number of pools is reached. In either case, take note that - * keeping another pool is not required. - */ - WRITE_ONCE(new_pool_required, false); + WRITE_ONCE(new_pool, *prealloc); + *prealloc = NULL; } /* - * Try to initialize a new stack depot pool from either a previous or the - * current pre-allocation, and release all its entries to the freelist. + * Try to initialize a new stack record from the current pool, a cached pool, or + * the current pre-allocation. */ -static bool depot_try_init_pool(void **prealloc) +static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size) { + struct stack_record *stack; + void *current_pool; + u32 pool_index; + lockdep_assert_held(&pool_lock); - /* Check if we have a new pool saved and use it. */ - if (new_pool) { - depot_init_pool(new_pool); - new_pool = NULL; + if (pool_offset + size > DEPOT_POOL_SIZE) { + if (!depot_init_pool(prealloc)) + return NULL; + } - /* Take note that we might need a new new_pool. */ - if (pools_num < DEPOT_MAX_POOLS) - WRITE_ONCE(new_pool_required, true); + if (WARN_ON_ONCE(pools_num < 1)) + return NULL; + pool_index = pools_num - 1; + current_pool = stack_pools[pool_index]; + if (WARN_ON_ONCE(!current_pool)) + return NULL; - return true; - } + stack = current_pool + pool_offset; - /* Bail out if we reached the pool limit. */ - if (unlikely(pools_num >= DEPOT_MAX_POOLS)) { - WARN_ONCE(1, "Stack depot reached limit capacity"); - return false; - } + /* Pre-initialize handle once. */ + stack->handle.pool_index = pool_index; + stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN; + stack->handle.extra = 0; + INIT_LIST_HEAD(&stack->hash_list); - /* Check if we have preallocated memory and use it. */ - if (*prealloc) { - depot_init_pool(*prealloc); - *prealloc = NULL; - return true; - } + pool_offset += size; - return false; + return stack; } -/* Try to find next free usable entry. */ +/* Try to find next free usable entry from the freelist. */ static struct stack_record *depot_pop_free(void) { struct stack_record *stack; @@ -420,7 +399,7 @@ static struct stack_record *depot_pop_free(void) * check the first entry. */ stack = list_first_entry(&free_stacks, struct stack_record, free_list); - if (stack->size && !poll_state_synchronize_rcu(stack->rcu_state)) + if (!poll_state_synchronize_rcu(stack->rcu_state)) return NULL; list_del(&stack->free_list); @@ -429,48 +408,73 @@ static struct stack_record *depot_pop_free(void) return stack; } +static inline size_t depot_stack_record_size(struct stack_record *s, unsigned int nr_entries) +{ + const size_t used = flex_array_size(s, entries, nr_entries); + const size_t unused = sizeof(s->entries) - used; + + WARN_ON_ONCE(sizeof(s->entries) < used); + + return ALIGN(sizeof(struct stack_record) - unused, 1 << DEPOT_STACK_ALIGN); +} + /* 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) +depot_alloc_stack(unsigned long *entries, unsigned int nr_entries, u32 hash, depot_flags_t flags, void **prealloc) { - struct stack_record *stack; + struct stack_record *stack = NULL; + size_t record_size; lockdep_assert_held(&pool_lock); /* This should already be checked by public API entry points. */ - if (WARN_ON_ONCE(!size)) + if (WARN_ON_ONCE(!nr_entries)) return NULL; - /* Check if we have a stack record to save the stack trace. */ - stack = depot_pop_free(); - if (!stack) { - /* No usable entries on the freelist - try to refill the freelist. */ - if (!depot_try_init_pool(prealloc)) - return NULL; + /* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */ + if (nr_entries > CONFIG_STACKDEPOT_MAX_FRAMES) + nr_entries = CONFIG_STACKDEPOT_MAX_FRAMES; + + if (flags & STACK_DEPOT_FLAG_GET) { + /* + * Evictable entries have to allocate the max. size so they may + * safely be re-used by differently sized allocations. + */ + record_size = depot_stack_record_size(stack, CONFIG_STACKDEPOT_MAX_FRAMES); stack = depot_pop_free(); - if (WARN_ON(!stack)) - return NULL; + } else { + record_size = depot_stack_record_size(stack, nr_entries); } - /* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */ - if (size > CONFIG_STACKDEPOT_MAX_FRAMES) - size = CONFIG_STACKDEPOT_MAX_FRAMES; + if (!stack) { + stack = depot_pop_free_pool(prealloc, record_size); + if (!stack) + return NULL; + } /* Save the stack trace. */ stack->hash = hash; - stack->size = size; - /* stack->handle is already filled in by depot_init_pool(). */ - refcount_set(&stack->count, 1); - memcpy(stack->entries, entries, flex_array_size(stack, entries, size)); + stack->size = nr_entries; + /* stack->handle is already filled in by depot_pop_free_pool(). */ + memcpy(stack->entries, entries, flex_array_size(stack, entries, nr_entries)); + + if (flags & STACK_DEPOT_FLAG_GET) { + refcount_set(&stack->count, 1); + counters[DEPOT_COUNTER_REFD_ALLOCS]++; + counters[DEPOT_COUNTER_REFD_INUSE]++; + } else { + /* Warn on attempts to switch to refcounting this entry. */ + refcount_set(&stack->count, REFCOUNT_SATURATED); + counters[DEPOT_COUNTER_PERSIST_COUNT]++; + counters[DEPOT_COUNTER_PERSIST_BYTES] += record_size; + } /* * Let KMSAN know the stored stack record is initialized. This shall * prevent false positive reports if instrumented code accesses it. */ - kmsan_unpoison_memory(stack, DEPOT_STACK_RECORD_SIZE); + kmsan_unpoison_memory(stack, record_size); - counters[DEPOT_COUNTER_ALLOCS]++; - counters[DEPOT_COUNTER_INUSE]++; return stack; } @@ -538,8 +542,8 @@ static void depot_free_stack(struct stack_record *stack) list_add_tail(&stack->free_list, &free_stacks); counters[DEPOT_COUNTER_FREELIST_SIZE]++; - counters[DEPOT_COUNTER_FREES]++; - counters[DEPOT_COUNTER_INUSE]--; + counters[DEPOT_COUNTER_REFD_FREES]++; + counters[DEPOT_COUNTER_REFD_INUSE]--; printk_deferred_exit(); raw_spin_unlock_irqrestore(&pool_lock, flags); @@ -660,7 +664,7 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, * Allocate memory for a new pool if required now: * we won't be able to do that under the lock. */ - if (unlikely(can_alloc && READ_ONCE(new_pool_required))) { + if (unlikely(can_alloc && !READ_ONCE(new_pool))) { /* * Zero out zone modifiers, as we don't have specific zone * requirements. Keep the flags related to allocation in atomic @@ -681,7 +685,7 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, found = find_stack(bucket, entries, nr_entries, hash, depot_flags); if (!found) { struct stack_record *new = - depot_alloc_stack(entries, nr_entries, hash, &prealloc); + depot_alloc_stack(entries, nr_entries, hash, depot_flags, &prealloc); if (new) { /* -- cgit v1.2.3 From 3ee34eabac2abb6b1b6fcdebffe18870719ad000 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 15 Feb 2024 22:59:01 +0100 Subject: lib/stackdepot: fix first entry having a 0-handle Patch series "page_owner: print stacks and their outstanding allocations", v10. page_owner is a great debug functionality tool that lets us know about all pages that have been allocated/freed and their specific stacktrace. This comes very handy when debugging memory leaks, since with some scripting we can see the outstanding allocations, which might point to a memory leak. In my experience, that is one of the most useful cases, but it can get really tedious to screen through all pages and try to reconstruct the stack <-> allocated/freed relationship, becoming most of the time a daunting and slow process when we have tons of allocation/free operations. This patchset aims to ease that by adding a new functionality into page_owner. This functionality creates a new directory called 'page_owner_stacks' under 'sys/kernel//debug' with a read-only file called 'show_stacks', which prints out all the stacks followed by their outstanding number of allocations (being that the times the stacktrace has allocated but not freed yet). This gives us a clear and a quick overview of stacks <-> allocated/free. We take advantage of the new refcount_f field that stack_record struct gained, and increment/decrement the stack refcount on every __set_page_owner() (alloc operation) and __reset_page_owner (free operation) call. Unfortunately, we cannot use the new stackdepot api STACK_DEPOT_FLAG_GET because it does not fulfill page_owner needs, meaning we would have to special case things, at which point makes more sense for page_owner to do its own {dec,inc}rementing of the stacks. E.g: Using STACK_DEPOT_FLAG_PUT, once the refcount reaches 0, such stack gets evicted, so page_owner would lose information. This patchset also creates a new file called 'set_threshold' within 'page_owner_stacks' directory, and by writing a value to it, the stacks which refcount is below such value will be filtered out. A PoC can be found below: # cat /sys/kernel/debug/page_owner_stacks/show_stacks > page_owner_full_stacks.txt # head -40 page_owner_full_stacks.txt prep_new_page+0xa9/0x120 get_page_from_freelist+0x801/0x2210 __alloc_pages+0x18b/0x350 alloc_pages_mpol+0x91/0x1f0 folio_alloc+0x14/0x50 filemap_alloc_folio+0xb2/0x100 page_cache_ra_unbounded+0x96/0x180 filemap_get_pages+0xfd/0x590 filemap_read+0xcc/0x330 blkdev_read_iter+0xb8/0x150 vfs_read+0x285/0x320 ksys_read+0xa5/0xe0 do_syscall_64+0x80/0x160 entry_SYSCALL_64_after_hwframe+0x6e/0x76 stack_count: 521 prep_new_page+0xa9/0x120 get_page_from_freelist+0x801/0x2210 __alloc_pages+0x18b/0x350 alloc_pages_mpol+0x91/0x1f0 folio_alloc+0x14/0x50 filemap_alloc_folio+0xb2/0x100 __filemap_get_folio+0x14a/0x490 ext4_write_begin+0xbd/0x4b0 [ext4] generic_perform_write+0xc1/0x1e0 ext4_buffered_write_iter+0x68/0xe0 [ext4] ext4_file_write_iter+0x70/0x740 [ext4] vfs_write+0x33d/0x420 ksys_write+0xa5/0xe0 do_syscall_64+0x80/0x160 entry_SYSCALL_64_after_hwframe+0x6e/0x76 stack_count: 4609 ... ... # echo 5000 > /sys/kernel/debug/page_owner_stacks/set_threshold # cat /sys/kernel/debug/page_owner_stacks/show_stacks > page_owner_full_stacks_5000.txt # head -40 page_owner_full_stacks_5000.txt prep_new_page+0xa9/0x120 get_page_from_freelist+0x801/0x2210 __alloc_pages+0x18b/0x350 alloc_pages_mpol+0x91/0x1f0 folio_alloc+0x14/0x50 filemap_alloc_folio+0xb2/0x100 __filemap_get_folio+0x14a/0x490 ext4_write_begin+0xbd/0x4b0 [ext4] generic_perform_write+0xc1/0x1e0 ext4_buffered_write_iter+0x68/0xe0 [ext4] ext4_file_write_iter+0x70/0x740 [ext4] vfs_write+0x33d/0x420 ksys_pwrite64+0x75/0x90 do_syscall_64+0x80/0x160 entry_SYSCALL_64_after_hwframe+0x6e/0x76 stack_count: 6781 prep_new_page+0xa9/0x120 get_page_from_freelist+0x801/0x2210 __alloc_pages+0x18b/0x350 pcpu_populate_chunk+0xec/0x350 pcpu_balance_workfn+0x2d1/0x4a0 process_scheduled_works+0x84/0x380 worker_thread+0x12a/0x2a0 kthread+0xe3/0x110 ret_from_fork+0x30/0x50 ret_from_fork_asm+0x1b/0x30 stack_count: 8641 This patch (of 7): The very first entry of stack_record gets a handle of 0, but this is wrong because stackdepot treats a 0-handle as a non-valid one. E.g: See the check in stack_depot_fetch() Fix this by adding and offset of 1. This bug has been lurking since the very beginning of stackdepot, but no one really cared as it seems. Because of that I am not adding a Fixes tag. Link: https://lkml.kernel.org/r/20240215215907.20121-1-osalvador@suse.de Link: https://lkml.kernel.org/r/20240215215907.20121-2-osalvador@suse.de Co-developed-by: Marco Elver Signed-off-by: Marco Elver Signed-off-by: Oscar Salvador Acked-by: Vlastimil Babka Acked-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Michal Hocko Signed-off-by: Andrew Morton --- lib/stackdepot.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'lib/stackdepot.c') diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 4a7055a63d9f..c043a4186bc5 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -45,15 +45,16 @@ #define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \ STACK_DEPOT_EXTRA_BITS) #define DEPOT_POOLS_CAP 8192 +/* The pool_index is offset by 1 so the first record does not have a 0 handle. */ #define DEPOT_MAX_POOLS \ - (((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \ - (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP) + (((1LL << (DEPOT_POOL_INDEX_BITS)) - 1 < DEPOT_POOLS_CAP) ? \ + (1LL << (DEPOT_POOL_INDEX_BITS)) - 1 : DEPOT_POOLS_CAP) /* Compact structure that stores a reference to a stack. */ union handle_parts { depot_stack_handle_t handle; struct { - u32 pool_index : DEPOT_POOL_INDEX_BITS; + u32 pool_index : DEPOT_POOL_INDEX_BITS; /* pool_index is offset by 1 */ u32 offset : DEPOT_OFFSET_BITS; u32 extra : STACK_DEPOT_EXTRA_BITS; }; @@ -372,7 +373,7 @@ static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size) stack = current_pool + pool_offset; /* Pre-initialize handle once. */ - stack->handle.pool_index = pool_index; + stack->handle.pool_index = pool_index + 1; stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN; stack->handle.extra = 0; INIT_LIST_HEAD(&stack->hash_list); @@ -483,18 +484,19 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle) const int pools_num_cached = READ_ONCE(pools_num); union handle_parts parts = { .handle = handle }; void *pool; + u32 pool_index = parts.pool_index - 1; size_t offset = parts.offset << DEPOT_STACK_ALIGN; struct stack_record *stack; lockdep_assert_not_held(&pool_lock); - if (parts.pool_index > pools_num_cached) { + if (pool_index > pools_num_cached) { WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n", - parts.pool_index, pools_num_cached, handle); + pool_index, pools_num_cached, handle); return NULL; } - pool = stack_pools[parts.pool_index]; + pool = stack_pools[pool_index]; if (WARN_ON(!pool)) return NULL; -- cgit v1.2.3 From 8151c7a35d8bd8a12e93538ef7963ea209b6ab41 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 15 Feb 2024 22:59:02 +0100 Subject: lib/stackdepot: move stack_record struct definition into the header In order to move the heavy lifting into page_owner code, this one needs to have access to the stack_record structure, which right now sits in lib/stackdepot.c. Move it to the stackdepot.h header so page_owner can access stack_record's struct fields. Link: https://lkml.kernel.org/r/20240215215907.20121-3-osalvador@suse.de Signed-off-by: Oscar Salvador Reviewed-by: Marco Elver Reviewed-by: Vlastimil Babka Acked-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 47 ++++++++++++++++++++++++++++++++++++++++++++++ lib/stackdepot.c | 43 ------------------------------------------ 2 files changed, 47 insertions(+), 43 deletions(-) (limited to 'lib/stackdepot.c') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index adcbb8f23600..c4b5ad57c066 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -30,6 +30,53 @@ typedef u32 depot_stack_handle_t; */ #define STACK_DEPOT_EXTRA_BITS 5 +#define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8) + +#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_OFFSET_BITS - \ + STACK_DEPOT_EXTRA_BITS) + +#ifdef CONFIG_STACKDEPOT +/* Compact structure that stores a reference to a stack. */ +union handle_parts { + depot_stack_handle_t handle; + struct { + /* pool_index is offset by 1 */ + u32 pool_index : DEPOT_POOL_INDEX_BITS; + u32 offset : DEPOT_OFFSET_BITS; + u32 extra : STACK_DEPOT_EXTRA_BITS; + }; +}; + +struct stack_record { + struct list_head hash_list; /* Links in the hash table */ + u32 hash; /* Hash in hash table */ + u32 size; /* Number of stored frames */ + union handle_parts handle; /* Constant after initialization */ + refcount_t count; + union { + unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES]; /* Frames */ + struct { + /* + * An important invariant of the implementation is to + * only place a stack record onto the freelist iff its + * refcount is zero. Because stack records with a zero + * refcount are never considered as valid, it is safe to + * union @entries and freelist management state below. + * Conversely, as soon as an entry is off the freelist + * and its refcount becomes non-zero, the below must not + * be accessed until being placed back on the freelist. + */ + struct list_head free_list; /* Links in the freelist */ + unsigned long rcu_state; /* RCU cookie */ + }; + }; +}; +#endif + typedef u32 depot_flags_t; /* diff --git a/lib/stackdepot.c b/lib/stackdepot.c index c043a4186bc5..514b8d40ff57 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -36,55 +36,12 @@ #include #include -#define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8) - -#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_OFFSET_BITS - \ - STACK_DEPOT_EXTRA_BITS) #define DEPOT_POOLS_CAP 8192 /* The pool_index is offset by 1 so the first record does not have a 0 handle. */ #define DEPOT_MAX_POOLS \ (((1LL << (DEPOT_POOL_INDEX_BITS)) - 1 < DEPOT_POOLS_CAP) ? \ (1LL << (DEPOT_POOL_INDEX_BITS)) - 1 : DEPOT_POOLS_CAP) -/* Compact structure that stores a reference to a stack. */ -union handle_parts { - depot_stack_handle_t handle; - struct { - u32 pool_index : DEPOT_POOL_INDEX_BITS; /* pool_index is offset by 1 */ - u32 offset : DEPOT_OFFSET_BITS; - u32 extra : STACK_DEPOT_EXTRA_BITS; - }; -}; - -struct stack_record { - struct list_head hash_list; /* Links in the hash table */ - u32 hash; /* Hash in hash table */ - u32 size; /* Number of stored frames */ - union handle_parts handle; /* Constant after initialization */ - refcount_t count; - union { - unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES]; /* Frames */ - struct { - /* - * An important invariant of the implementation is to - * only place a stack record onto the freelist iff its - * refcount is zero. Because stack records with a zero - * refcount are never considered as valid, it is safe to - * union @entries and freelist management state below. - * Conversely, as soon as an entry is off the freelist - * and its refcount becomes non-zero, the below must not - * be accessed until being placed back on the freelist. - */ - struct list_head free_list; /* Links in the freelist */ - unsigned long rcu_state; /* RCU cookie */ - }; - }; -}; - 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; -- cgit v1.2.3 From 4bedfb314bdd85c1662ecc46fa25b33b998f994d Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 15 Feb 2024 22:59:03 +0100 Subject: mm,page_owner: maintain own list of stack_records structs page_owner needs to increment a stack_record refcount when a new allocation occurs, and decrement it on a free operation. In order to do that, we need to have a way to get a stack_record from a handle. Implement __stack_depot_get_stack_record() which just does that, and make it public so page_owner can use it. Also, traversing all stackdepot buckets comes with its own complexity, plus we would have to implement a way to mark only those stack_records that were originated from page_owner, as those are the ones we are interested in. For that reason, page_owner maintains its own list of stack_records, because traversing that list is faster than traversing all buckets while keeping at the same time a low complexity. For now, add to stack_list only the stack_records of dummy_handle and failure_handle, and set their refcount of 1. Further patches will add code to increment or decrement stack_records count on allocation and free operation. Link: https://lkml.kernel.org/r/20240215215907.20121-4-osalvador@suse.de Signed-off-by: Oscar Salvador Reviewed-by: Vlastimil Babka Reviewed-by: Marco Elver Acked-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 11 +++++++++++ lib/stackdepot.c | 8 ++++++++ mm/page_owner.c | 15 +++++++++++++++ 3 files changed, 34 insertions(+) (limited to 'lib/stackdepot.c') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index c4b5ad57c066..3c6caa5abc7c 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -178,6 +178,17 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); +/** + * __stack_depot_get_stack_record - Get a pointer to a stack_record struct + * + * @handle: Stack depot handle + * + * This function is only for internal purposes. + * + * Return: Returns a pointer to a stack_record struct + */ +struct stack_record *__stack_depot_get_stack_record(depot_stack_handle_t handle); + /** * stack_depot_fetch - Fetch a stack trace from stack depot * diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 514b8d40ff57..8c795bb20afb 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -687,6 +687,14 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, } EXPORT_SYMBOL_GPL(stack_depot_save); +struct stack_record *__stack_depot_get_stack_record(depot_stack_handle_t handle) +{ + if (!handle) + return NULL; + + return depot_fetch_stack(handle); +} + unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries) { diff --git a/mm/page_owner.c b/mm/page_owner.c index 5634e5d890f8..33e342b15d9b 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -36,6 +36,14 @@ struct page_owner { pid_t free_tgid; }; +struct stack { + struct stack_record *stack_record; + struct stack *next; +}; +static struct stack dummy_stack; +static struct stack failure_stack; +static struct stack *stack_list; + static bool page_owner_enabled __initdata; DEFINE_STATIC_KEY_FALSE(page_owner_inited); @@ -95,6 +103,13 @@ static __init void init_page_owner(void) register_early_stack(); static_branch_enable(&page_owner_inited); init_early_allocated_pages(); + /* Initialize dummy and failure stacks and link them to stack_list */ + dummy_stack.stack_record = __stack_depot_get_stack_record(dummy_handle); + failure_stack.stack_record = __stack_depot_get_stack_record(failure_handle); + refcount_set(&dummy_stack.stack_record->count, 1); + refcount_set(&failure_stack.stack_record->count, 1); + dummy_stack.next = &failure_stack; + stack_list = &dummy_stack; } struct page_ext_operations page_owner_ops = { -- cgit v1.2.3 From dc24559472a682eb124e869cb110e7a2fd857322 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 23 Feb 2024 17:20:13 +0300 Subject: lib/stackdepot: off by one in depot_fetch_stack() The stack_pools[] array has DEPOT_MAX_POOLS. The "pools_num" tracks the number of pools which are initialized. See depot_init_pool() for more details. If pool_index == pools_num_cached, this will read one element beyond what we want. If not all the pools are initialized, then the pool will be NULL, triggering a WARN(), and if they are all initialized it will read one element beyond the end of the array. Link: https://lkml.kernel.org/r/361ac881-60b7-471f-91e5-5bf8fe8042b2@moroto.mountain Fixes: b29d31885814 ("lib/stackdepot: store free stack records in a freelist") Signed-off-by: Dan Carpenter Cc: Alexander Potapenko Cc: Andrey Konovalov Signed-off-by: Andrew Morton --- lib/stackdepot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib/stackdepot.c') diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 8c795bb20afb..af6cc19a2003 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -447,7 +447,7 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle) lockdep_assert_not_held(&pool_lock); - if (pool_index > pools_num_cached) { + if (pool_index >= pools_num_cached) { WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n", pool_index, pools_num_cached, handle); return NULL; -- cgit v1.2.3