From af9ea231c0b4530edc389a3126a69e0699b7699d Mon Sep 17 00:00:00 2001 From: Shengming Hu Date: Mon, 6 Jul 2026 21:39:09 +0800 Subject: mm/slub: fix lost local objects when bulk remote free batch fills In free_to_pcs_bulk(), when remote_objects[] fills to PCS_BATCH_MAX, the code jumps to flush_remote to free the batch. If all remote entries have already been compacted out of p[] via tail swaps while local objects remain, the flush_remote path returns early since `i < size` no longer holds. The leftover local objects are then neither cached in the sheaf nor returned to the slab freelist, causing a memory leak. For illustration: size = 64, local objects at p[0..31], remote objects at p[32..63] After scanning all remotes: i = 32, size = 32 p[0..31] local objects are dropped. Harry pointed out that, although the logic contains a real leak, it does not appear to be triggerable with the current in-tree users. To hit this path, at least PCS_BATCH_MAX objects, currently hardcoded to 32, need to be collected in remote_objects[]. Looking at current kmem_cache_free_bulk() users: * maple_node has sheaf_capacity = 32 * skbuff_head_cache has sheaf_capacity = 28 * panthor and msm drivers have sheaf_capacity = 4 The sheaf capacity is, at least for now, derived purely from the object size, with the user-requested capacity used as a minimum. Therefore, among the current users, only maple_node has a sheaf_capacity large enough to reach PCS_BATCH_MAX. However, for the bug to trigger in maple_node, all objects in the sheaf would have to be from remote nodes. In that case, there would be no local objects left to leak. So this issue was found by code review rather than from a runtime report, and it does not seem to be triggerable by current users. Still, the bug could become reachable with future users, a different sheaf capacity, or a change to PCS_BATCH_MAX. Fix the logic by freeing a full remote batch in place during the scan and then continuing to process the compacted array. This keeps all local objects on the normal fast path, while the tail path only handles any leftover partial remote batch. The redundant next_remote_batch jump label is removed as well. Fixes: 989b09b73978 ("slab: skip percpu sheaves for remote object freeing") Signed-off-by: Shengming Hu Link: https://patch.msgid.link/202607062139095043SOsLi6TIf403tcjPf8fm@zte.com.cn Cc: stable@vger.kernel.org Reviewed-by: Harry Yoo (Oracle) Signed-off-by: Vlastimil Babka (SUSE) --- mm/slub.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 9ec774dc7009..65febe957886 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -6217,7 +6217,6 @@ static void free_to_pcs_bulk(struct kmem_cache *s, size_t size, void **p) void *remote_objects[PCS_BATCH_MAX]; unsigned int remote_nr = 0; -next_remote_batch: while (i < size) { struct slab *slab = virt_to_slab(p[i]); @@ -6232,8 +6231,11 @@ next_remote_batch: if (unlikely(!can_free_to_pcs(slab))) { remote_objects[remote_nr] = p[i]; p[i] = p[--size]; - if (++remote_nr >= PCS_BATCH_MAX) - goto flush_remote; + if (++remote_nr >= PCS_BATCH_MAX) { + __kmem_cache_free_bulk(s, remote_nr, &remote_objects[0]); + stat_add(s, FREE_SLOWPATH, remote_nr); + remote_nr = 0; + } continue; } @@ -6317,10 +6319,6 @@ flush_remote: if (remote_nr) { __kmem_cache_free_bulk(s, remote_nr, &remote_objects[0]); stat_add(s, FREE_SLOWPATH, remote_nr); - if (i < size) { - remote_nr = 0; - goto next_remote_batch; - } } } -- cgit v1.3.1 From 1dba91a0493b7ffe9cbbcf7a8df1b361ddcac515 Mon Sep 17 00:00:00 2001 From: "Harry Yoo (Oracle)" Date: Mon, 13 Jul 2026 23:28:49 +0900 Subject: mm/slab: fix a memory leak due to bootstrapping sheaves twice When kmalloc caches are aliased, multiple cache pointers reference the same kmem_cache. As a result, iterating over kmalloc indices and bootstrapping sheaves can bootstrap the same cache more than once and leak memory. Currently, this could happen when the architecture specifies minimum alignment for slab caches that is larger than ARCH_KMALLOC_MINALIGN. Bootstrap sheaves only when the cache does not have them already. Add a warning when bootstrap_cache_sheaves() is called for a cache that already has sheaves enabled. Fixes: 913ffd3a1bf5 ("slab: handle kmalloc sheaves bootstrap") Cc: stable@vger.kernel.org Signed-off-by: Harry Yoo (Oracle) Reviewed-by: Suren Baghdasaryan Link: https://patch.msgid.link/20260713-kmalloc-no-objext-v3-1-47c7bd138de7@kernel.org Signed-off-by: Vlastimil Babka (SUSE) --- mm/slub.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 65febe957886..f9461a0c47d3 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -8497,6 +8497,8 @@ static void __init bootstrap_cache_sheaves(struct kmem_cache *s) bool failed = false; int node, cpu; + VM_WARN_ON_ONCE(cache_has_sheaves(s)); + capacity = calculate_sheaf_capacity(s, &empty_args); /* capacity can be 0 due to debugging or SLUB_TINY */ @@ -8548,8 +8550,11 @@ static void __init bootstrap_kmalloc_sheaves(void) for (type = KMALLOC_NORMAL; type <= KMALLOC_PARTITION_END; type++) { for (int idx = 0; idx < KMALLOC_SHIFT_HIGH + 1; idx++) { - if (kmalloc_caches[type][idx]) - bootstrap_cache_sheaves(kmalloc_caches[type][idx]); + struct kmem_cache *s = kmalloc_caches[type][idx]; + + /* Do not bootstrap twice when caches are aliased */ + if (s && !cache_has_sheaves(s)) + bootstrap_cache_sheaves(s); } } } -- cgit v1.3.1 From 982e31382d9a1a3c8c4e6a13702a53711f4efe9f Mon Sep 17 00:00:00 2001 From: "Harry Yoo (Oracle)" Date: Mon, 13 Jul 2026 23:28:50 +0900 Subject: mm/slab: decouple SLAB_NO_SHEAVES from SLAB_NO_OBJ_EXT Bootstrap caches are created with SLAB_NO_OBJ_EXT to disallow sheaves and obj_exts. To allow disabling obj_exts while allowing sheaves, decouple SLAB_NO_SHEAVES from SLAB_NO_OBJ_EXT. Bootstrap caches now have both SLAB_NO_SHEAVES and SLAB_NO_OBJ_EXT. No functional change intended. Reviewed-by: Vlastimil Babka (SUSE) Signed-off-by: Harry Yoo (Oracle) Reviewed-by: Suren Baghdasaryan Link: https://patch.msgid.link/20260713-kmalloc-no-objext-v3-2-47c7bd138de7@kernel.org Signed-off-by: Vlastimil Babka (SUSE) --- include/linux/slab.h | 13 +++++++++++-- mm/slub.c | 10 ++++++---- 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/include/linux/slab.h b/include/linux/slab.h index 51f03f18c9a7..08d7b6c9c4d6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -58,10 +58,13 @@ enum _slab_flag_bits { #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, +#ifdef CONFIG_SLAB_OBJ_EXT _SLAB_NO_OBJ_EXT, -#if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) +#ifdef CONFIG_64BIT _SLAB_OBJ_EXT_IN_OBJ, #endif +#endif + _SLAB_NO_SHEAVES, _SLAB_FLAGS_LAST_BIT }; @@ -239,8 +242,14 @@ enum _slab_flag_bits { #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ -/* Slab created using create_boot_cache */ +/* Slab caches without obj_exts array */ +#ifdef CONFIG_SLAB_OBJ_EXT #define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) +#else +#define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED +#endif + +#define SLAB_NO_SHEAVES __SLAB_FLAG_BIT(_SLAB_NO_SHEAVES) #if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) #define SLAB_OBJ_EXT_IN_OBJ __SLAB_FLAG_BIT(_SLAB_OBJ_EXT_IN_OBJ) diff --git a/mm/slub.c b/mm/slub.c index f9461a0c47d3..abe748b7dddb 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -7799,12 +7799,12 @@ static unsigned int calculate_sheaf_capacity(struct kmem_cache *s, return 0; /* - * Bootstrap caches can't have sheaves for now (SLAB_NO_OBJ_EXT). + * Bootstrap caches can't have sheaves for now (SLAB_NO_SHEAVES). * SLAB_NOLEAKTRACE caches (e.g., kmemleak's object_cache) must not * have sheaves to avoid recursion when sheaf allocation triggers * kmemleak tracking. */ - if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE)) + if (s->flags & (SLAB_NO_SHEAVES | SLAB_NOLEAKTRACE)) return 0; /* @@ -8586,7 +8586,8 @@ void __init kmem_cache_init(void) create_boot_cache(kmem_cache_node, "kmem_cache_node", sizeof(struct kmem_cache_node), - SLAB_HWCACHE_ALIGN | SLAB_NO_OBJ_EXT, 0, 0); + SLAB_HWCACHE_ALIGN | SLAB_NO_SHEAVES | SLAB_NO_OBJ_EXT, + 0, 0); hotplug_node_notifier(slab_memory_callback, SLAB_CALLBACK_PRI); @@ -8596,7 +8597,8 @@ void __init kmem_cache_init(void) create_boot_cache(kmem_cache, "kmem_cache", offsetof(struct kmem_cache, per_node) + nr_node_ids * sizeof(struct kmem_cache_per_node_ptrs), - SLAB_HWCACHE_ALIGN | SLAB_NO_OBJ_EXT, 0, 0); + SLAB_HWCACHE_ALIGN | SLAB_NO_SHEAVES | SLAB_NO_OBJ_EXT, + 0, 0); kmem_cache = bootstrap(&boot_kmem_cache); kmem_cache_node = bootstrap(&boot_kmem_cache_node); -- cgit v1.3.1 From a37b0066a10aabf3c968b4566706fb866eaf9a85 Mon Sep 17 00:00:00 2001 From: "Harry Yoo (Oracle)" Date: Mon, 13 Jul 2026 23:28:51 +0900 Subject: lib/alloc_tag: introduce mem_alloc_profiling_permanently_disabled() mem_alloc_profiling_enabled() tells whether memalloc profiling is currently enabled. However, even when this function returns false, it can be enabled later. However, this is not enough. Some optimizations can be applied only when memalloc profiling is permanently disabled. For example, to skip the creation of KMALLOC_NO_OBJ_EXT caches at boot time, mem_profiling must be set to "never", "0" w/ debugging on, or have been shutdown so that it can no longer be enabled. Introduce mem_alloc_profiling_permanently_disabled() for this purpose. Signed-off-by: Harry Yoo (Oracle) Acked-by: Suren Baghdasaryan Link: https://patch.msgid.link/20260713-kmalloc-no-objext-v3-3-47c7bd138de7@kernel.org Signed-off-by: Vlastimil Babka (SUSE) --- include/linux/alloc_tag.h | 3 +++ lib/alloc_tag.c | 9 +++++++++ 2 files changed, 12 insertions(+) diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 068ba2e77c5d..6ed9f82e639f 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -134,6 +134,8 @@ static inline bool mem_alloc_profiling_enabled(void) &mem_alloc_profiling_key); } +bool mem_alloc_profiling_permanently_disabled(void); + static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) { struct alloc_tag_counters v = { 0, 0 }; @@ -239,6 +241,7 @@ static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag) #define DEFINE_ALLOC_TAG(_alloc_tag) static inline bool mem_alloc_profiling_enabled(void) { return false; } +static inline bool mem_alloc_profiling_permanently_disabled(void) { return true; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) {} static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index d9be1cf5187d..e5b218176c5a 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -26,6 +26,15 @@ static bool mem_profiling_support = true; static bool mem_profiling_support; #endif +/* + * Memory allocation profiling is permanently disabled and cannot be enabled. + * Must be called after setup_early_mem_profiling(). + */ +bool mem_alloc_profiling_permanently_disabled(void) +{ + return !mem_profiling_support; +} + static struct codetag_type *alloc_tag_cttype; #ifdef CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU -- cgit v1.3.1 From d9e6a7623938968e3752b67e37eaff097e559a54 Mon Sep 17 00:00:00 2001 From: "Harry Yoo (Oracle)" Date: Mon, 13 Jul 2026 23:28:52 +0900 Subject: mm/slab: prevent unbounded recursion in free path with new kmalloc type Commit 280ea9c3154b ("mm/slab: avoid allocating slabobj_ext array from its own slab") avoided recursive allocation of obj_exts from kmalloc caches of the same size, by bumping the obj_exts array's allocation size whenever the array size equals the size of the object being allocated. However, as reported by Danielle Costantino and Shakeel Butt, even slabs from kmalloc caches of different sizes can form a cycle by allocating obj_exts arrays from each other [1]: What happened: a KMALLOC_NORMAL slab's obj_exts array (used by allocation profiling / memcg accounting) is itself kmalloc()'d from a KMALLOC_NORMAL cache, so the "slab holds another slab's obj_exts array" relation can form cycles. With sizeof(struct slabobj_ext) == 16 and the host's geometry: - kmalloc-512 has 64 objects/slab -> array is 64*16 == 1024 bytes, served from kmalloc-1k; - kmalloc-1k has 32 objects/slab -> array is 32*16 == 512 bytes, served from kmalloc-512. A kmalloc-512 slab and a kmalloc-1k slab therefore hold each other's obj_exts array. Discarding one frees the other's array, which empties and discards that slab, which frees the first's array, and so on: __free_slab() -> free_slab_obj_exts() -> kfree() -> discard_slab() -> __free_slab() recurses along the cycle until the stack is exhausted. With memory allocation profiling, this allows unbounded recursion in the free path and led to a stack overflow on a production host in the Meta fleet [1]: BUG: TASK stack guard page was hit Oops: stack guard page RIP: 0010:kfree+0x8/0x5d0 Call Trace: __free_slab+0x66/0xc0 kfree+0x3f0/0x5d0 ... ( ~125x __free_slab <-> kfree ) ... do_syscall_64 It is proposed [1] to resolve this issue by always serving the obj_exts array allocation from kmalloc caches (or large kmalloc) of sizes larger than the object size. However, as pointed out by Vlastimil Babka [2], this can waste an excessive amount of memory as slabs from large kmalloc sizes (e.g. kmalloc-8k) generally need obj_exts arrays much smaller than the object size. Therefore, rather than bumping the size, let us take a different approach; disallow formation of cycles between kmalloc types when allocating obj_exts arrays. Currently, all obj_exts arrays are served from normal kmalloc caches. Cycles cannot be created if obj_exts arrays of normal kmalloc caches are served from a special kmalloc type that can never have obj_exts arrays. To achieve this, create a new kmalloc type called KMALLOC_NO_OBJ_EXT. KMALLOC_NO_OBJ_EXT caches are created with SLAB_NO_OBJ_EXT flag when either 1) memory allocation profiling is not permanently disabled, or 2) kmalloc types with a priority higher than KMALLOC_CGROUP are aliased with KMALLOC_NORMAL. Sheaf bootstrapping for KMALLOC_NO_OBJ_EXT caches now must be deferred because allocation of a barn can trigger obj_exts array allocation of normal kmalloc caches when the KMALLOC_NO_OBJ_EXT cache for that size is not ready yet. For simplicity, perform bootstrapping of sheaves for all kmalloc caches later. Introduce a new slab alloc flag, SLAB_ALLOC_NO_OBJ_EXT, to prevent allocation of obj_exts arrays, and let kmalloc_slab() override the type to KMALLOC_NO_OBJ_EXT when specified. Note that kmalloc_type() remains unchanged because kmalloc_flags() bypasses the kmalloc fastpath. Do not pass SLAB_ALLOC_NO_RECURSE to kmalloc_flags() in alloc_slab_obj_exts() and instead use SLAB_ALLOC_NO_OBJ_EXT only when the objects are allocated from normal kmalloc caches. While this prevents unbounded recursive allocation of obj_exts, it allows KMALLOC_NO_OBJ_EXT caches to have sheaves. Since sheaf allocations specify SLAB_ALLOC_NO_RECURSE that prevents allocation of both sheaves and obj_exts arrays, the recursion depth is bounded. obj_exts arrays for non-kmalloc-normal caches can now have a valid tag. Do not call mark_obj_codetag_empty() when freeing an obj_exts array to avoid false warnings. KMALLOC_NO_OBJ_EXT don't need this as they never allocate those arrays. Reported-by: Danielle Costantino Reported-by: Shakeel Butt Closes: https://lore.kernel.org/linux-mm/20260625230029.703750-1-shakeel.butt@linux.dev [1] Fixes: 4b8736964640 ("mm/slab: add allocation accounting into slab allocation and free paths") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mm/c5c4208d-a6f0-413e-bad9-49be12f12d55@kernel.org [2] Signed-off-by: Harry Yoo (Oracle) Reviewed-by: Suren Baghdasaryan Link: https://patch.msgid.link/20260713-kmalloc-no-objext-v3-4-47c7bd138de7@kernel.org Signed-off-by: Vlastimil Babka (SUSE) --- include/linux/slab.h | 6 ++++ mm/slab.h | 32 +++++++++++++++++-- mm/slab_common.c | 19 ++++++++++- mm/slub.c | 90 +++++++++++++++++++--------------------------------- 4 files changed, 85 insertions(+), 62 deletions(-) diff --git a/include/linux/slab.h b/include/linux/slab.h index 08d7b6c9c4d6..3a14df50766a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -708,6 +708,9 @@ enum kmalloc_cache_type { #endif #ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, +#endif +#ifndef CONFIG_SLAB_OBJ_EXT + KMALLOC_NO_OBJ_EXT = KMALLOC_NORMAL, #endif KMALLOC_PARTITION_START = KMALLOC_NORMAL, KMALLOC_PARTITION_END = KMALLOC_PARTITION_START + KMALLOC_PARTITION_CACHES_NR, @@ -721,6 +724,9 @@ enum kmalloc_cache_type { #endif #ifdef CONFIG_MEMCG KMALLOC_CGROUP, +#endif +#ifdef CONFIG_SLAB_OBJ_EXT + KMALLOC_NO_OBJ_EXT, #endif NR_KMALLOC_TYPES }; diff --git a/mm/slab.h b/mm/slab.h index 281a65233795..f5e336b6b6b0 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -22,6 +22,7 @@ #define SLAB_ALLOC_NOLOCK 0x01 /* a kmalloc_nolock() allocation */ #define SLAB_ALLOC_NEW_SLAB 0x02 /* a flag for alloc_slab_obj_exts() */ #define SLAB_ALLOC_NO_RECURSE 0x04 /* prevent kmalloc() recursion */ +#define SLAB_ALLOC_NO_OBJ_EXT 0x08 /* prevent obj_exts array allocation */ static inline bool alloc_flags_allow_spinning(const unsigned int alloc_flags) { @@ -386,12 +387,17 @@ static inline unsigned int size_index_elem(unsigned int bytes) * KMALLOC_MAX_CACHE_SIZE and the caller must check that. */ static inline struct kmem_cache * -kmalloc_slab(size_t size, kmem_buckets *b, gfp_t flags, kmalloc_token_t token) +kmalloc_slab(size_t size, kmem_buckets *b, gfp_t flags, kmalloc_token_t token, + unsigned int alloc_flags) { unsigned int index; + enum kmalloc_cache_type type = kmalloc_type(flags, token); + + if (alloc_flags & SLAB_ALLOC_NO_OBJ_EXT) + type = KMALLOC_NO_OBJ_EXT; if (!b) - b = &kmalloc_caches[kmalloc_type(flags, token)]; + b = &kmalloc_caches[type]; if (size <= 192) index = kmalloc_size_index[size_index_elem(size)]; else @@ -426,7 +432,8 @@ static inline bool is_kmalloc_normal(struct kmem_cache *s) { if (!is_kmalloc_cache(s)) return false; - return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT)); + + return !(s->flags & (SLAB_CACHE_DMA|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT|SLAB_NO_OBJ_EXT)); } bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj); @@ -529,6 +536,25 @@ static inline void metadata_access_disable(void) kasan_enable_current(); } +/* + * Return true if KMALLOC_NORMAL caches may need obj_exts arrays. + * + * Memory allocation profiling requires obj_exts for all caches. + * Memcg usually doesn't need them for normal kmalloc caches, but kmalloc types + * with a priority higher than KMALLOC_CGROUP can be aliased with KMALLOC_NORMAL. + */ +static inline bool need_kmalloc_no_objext(void) +{ + if (!mem_alloc_profiling_permanently_disabled()) + return true; + + if (!mem_cgroup_kmem_disabled() && + (KMALLOC_NORMAL == KMALLOC_RECLAIM)) + return true; + + return false; +} + #ifdef CONFIG_SLAB_OBJ_EXT /* diff --git a/mm/slab_common.c b/mm/slab_common.c index b6426d7ceec9..03ecac12cd86 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -783,11 +783,15 @@ u8 kmalloc_size_index[24] __ro_after_init = { size_t kmalloc_size_roundup(size_t size) { if (size && size <= KMALLOC_MAX_CACHE_SIZE) { + struct kmem_cache *s; + /* * The flags don't matter since size_index is common to all. * Neither does the caller for just getting ->object_size. */ - return kmalloc_slab(size, NULL, GFP_KERNEL, __kmalloc_token(0))->object_size; + s = kmalloc_slab(size, NULL, GFP_KERNEL, __kmalloc_token(0), + SLAB_ALLOC_DEFAULT); + return s->object_size; } /* Above the smaller buckets, size is a multiple of page size. */ @@ -843,6 +847,12 @@ EXPORT_SYMBOL(kmalloc_size_roundup); #define KMALLOC_PARTITION_NAME(N, sz) #endif +#ifdef CONFIG_SLAB_OBJ_EXT +#define KMALLOC_NO_OBJ_EXT_NAME(sz) .name[KMALLOC_NO_OBJ_EXT] = "kmalloc-no-objext-" #sz, +#else +#define KMALLOC_NO_OBJ_EXT_NAME(sz) +#endif + #define INIT_KMALLOC_INFO(__size, __short_size) \ { \ .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ @@ -850,6 +860,7 @@ EXPORT_SYMBOL(kmalloc_size_roundup); KMALLOC_CGROUP_NAME(__short_size) \ KMALLOC_DMA_NAME(__short_size) \ KMALLOC_PARTITION_NAME(KMALLOC_PARTITION_CACHES_NR, __short_size) \ + KMALLOC_NO_OBJ_EXT_NAME(__short_size) \ .size = __size, \ } @@ -957,6 +968,12 @@ new_kmalloc_cache(int idx, enum kmalloc_cache_type type) return; } flags |= SLAB_ACCOUNT; + } else if (IS_ENABLED(CONFIG_SLAB_OBJ_EXT) && type == KMALLOC_NO_OBJ_EXT) { + if (!need_kmalloc_no_objext()) { + kmalloc_caches[type][idx] = kmalloc_caches[KMALLOC_NORMAL][idx]; + return; + } + flags |= SLAB_NO_OBJ_EXT | SLAB_NO_MERGE; } else if (IS_ENABLED(CONFIG_ZONE_DMA) && (type == KMALLOC_DMA)) { flags |= SLAB_CACHE_DMA; } diff --git a/mm/slub.c b/mm/slub.c index abe748b7dddb..0337e60db5ac 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2123,42 +2123,6 @@ static inline void init_slab_obj_exts(struct slab *slab) slab->obj_exts = 0; } -/* - * Calculate the allocation size for slabobj_ext array. - * - * When memory allocation profiling is enabled, the obj_exts array - * could be allocated from the same slab cache it's being allocated for. - * This would prevent the slab from ever being freed because it would - * always contain at least one allocated object (its own obj_exts array). - * - * To avoid this, increase the allocation size when we detect the array - * may come from the same cache, forcing it to use a different cache. - */ -static inline size_t obj_exts_alloc_size(struct kmem_cache *s, - struct slab *slab, gfp_t gfp) -{ - size_t sz = sizeof(struct slabobj_ext) * slab->objects; - struct kmem_cache *obj_exts_cache; - - if (sz > KMALLOC_MAX_CACHE_SIZE) - return sz; - - if (!is_kmalloc_normal(s)) - return sz; - - obj_exts_cache = kmalloc_slab(sz, NULL, gfp, __kmalloc_token(0)); - /* - * We can't simply compare s with obj_exts_cache, because partitioned kmalloc - * caches have multiple caches per size, selected by caller address or type. - * Since caller address or type may differ between kmalloc_slab() and actual - * allocation, bump size when sizes are equal. - */ - if (s->object_size == obj_exts_cache->object_size) - return obj_exts_cache->object_size + 1; - - return sz; -} - int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, gfp_t gfp, unsigned int alloc_flags) { @@ -2168,14 +2132,18 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, unsigned long new_exts; unsigned long old_exts; struct slabobj_ext *vec; - size_t sz; + size_t sz = sizeof(struct slabobj_ext) * slab->objects; gfp &= ~OBJCGS_CLEAR_MASK; - /* Prevent recursive extension vector allocation */ - alloc_flags |= SLAB_ALLOC_NO_RECURSE; - alloc_flags &= ~SLAB_ALLOC_NEW_SLAB; + /* + * In most cases, obj_exts arrays are allocated from normal kmalloc. + * However, normal kmalloc caches must allocate them from + * KMALLOC_NO_OBJ_EXT caches to prevent recursion. + */ + if (is_kmalloc_normal(s)) + alloc_flags |= SLAB_ALLOC_NO_OBJ_EXT; - sz = obj_exts_alloc_size(s, slab, gfp); + alloc_flags &= ~SLAB_ALLOC_NEW_SLAB; /* This will use kmalloc_nolock() if alloc_flags say so */ vec = kmalloc_flags(sz, gfp | __GFP_ZERO, alloc_flags, slab_nid(slab)); @@ -2193,8 +2161,21 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, return -ENOMEM; } - VM_WARN_ON_ONCE(virt_to_slab(vec) != NULL && - virt_to_slab(vec)->slab_cache == s); + if (IS_ENABLED(CONFIG_DEBUG_VM)) { + struct kmem_cache *exts_cache; + struct slab *exts_slab; + + exts_slab = virt_to_slab(vec); + if (exts_slab) { + /* + * The vector must be allocated from either normal or + * KMALLOC_NO_OBJ_EXT kmalloc caches to avoid cycles. + */ + exts_cache = exts_slab->slab_cache; + WARN_ON_ONCE(!is_kmalloc_normal(exts_cache) && + !(exts_cache->flags & SLAB_NO_OBJ_EXT)); + } + } new_exts = (unsigned long)vec; #ifdef CONFIG_MEMCG @@ -2217,7 +2198,6 @@ retry: * assign slabobj_exts in parallel. In this case the existing * objcg vector should be reused. */ - mark_obj_codetag_empty(vec); if (unlikely(!allow_spin)) kfree_nolock(vec); else @@ -2253,14 +2233,6 @@ static inline void free_slab_obj_exts(struct slab *slab, bool allow_spin) return; } - /* - * obj_exts was created with SLAB_ALLOC_NO_RECURSE flag, therefore its - * corresponding extension will be NULL. alloc_tag_sub() will throw a - * warning if slab has extensions but the extension of an object is - * NULL, therefore replace NULL with CODETAG_EMPTY to indicate that - * the extension for obj_exts is expected to be NULL. - */ - mark_obj_codetag_empty(obj_exts); if (allow_spin) kfree(obj_exts); else @@ -5356,7 +5328,7 @@ void *__do_kmalloc_node(kmem_buckets *b, gfp_t flags, int node, if (unlikely(!size)) return ZERO_SIZE_PTR; - s = kmalloc_slab(size, b, flags, token); + s = kmalloc_slab(size, b, flags, token, ac->alloc_flags); ret = slab_alloc_node(s, flags, node, ac); ret = kasan_kmalloc(s, ret, size, flags); @@ -5419,7 +5391,9 @@ static void *__kmalloc_nolock_noprof(DECL_TOKEN_PARAMS(size, token), gfp_t gfp_f retry: if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) return NULL; - s = kmalloc_slab(size, NULL, gfp_flags, PASS_TOKEN_PARAM(token)); + + s = kmalloc_slab(size, NULL, gfp_flags, PASS_TOKEN_PARAM(token), + ac->alloc_flags); if (!(s->flags & __CMPXCHG_DOUBLE) && !kmem_cache_debug(s)) /* @@ -7979,10 +7953,10 @@ static int calculate_sizes(struct kmem_cache_args *args, struct kmem_cache *s) s->allocflags |= __GFP_RECLAIMABLE; /* - * For KMALLOC_NORMAL caches we enable sheaves later by - * bootstrap_kmalloc_sheaves() to avoid recursion + * For kmalloc caches we enable sheaves later by + * bootstrap_kmalloc_sheaves() to avoid recursion. */ - if (!is_kmalloc_normal(s)) + if (!is_kmalloc_cache(s)) s->sheaf_capacity = calculate_sheaf_capacity(s, args); /* @@ -8548,7 +8522,7 @@ static void __init bootstrap_kmalloc_sheaves(void) { enum kmalloc_cache_type type; - for (type = KMALLOC_NORMAL; type <= KMALLOC_PARTITION_END; type++) { + for (type = KMALLOC_NORMAL; type < NR_KMALLOC_TYPES; type++) { for (int idx = 0; idx < KMALLOC_SHIFT_HIGH + 1; idx++) { struct kmem_cache *s = kmalloc_caches[type][idx]; -- cgit v1.3.1 From 5ff172f6c94d282d83cb88bdfec5f647ad9c6105 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 21 Jul 2026 11:19:21 +0200 Subject: slab: silence sparse warning with type-based partitioning Sparse does not know __builtin_infer_alloc_token() and complains: sparse: sparse: undefined identifier '__builtin_infer_alloc_token' Fix it by using a dummy variant of __kmalloc_token() if __CHECKER__ is defined. Fixes: feb662d9168b ("slab: support for compiler-assisted type-based slab cache partitioning") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202607110912.nZTqfCrH-lkp@intel.com/ Signed-off-by: Marco Elver Link: https://patch.msgid.link/20260721092005.1986693-1-elver@google.com Acked-by: Harry Yoo (Oracle) Signed-off-by: Vlastimil Babka (SUSE) --- include/linux/slab.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/include/linux/slab.h b/include/linux/slab.h index 3a14df50766a..32c9f8ed7ae2 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -514,8 +514,12 @@ typedef struct { unsigned long v; } kmalloc_token_t; extern unsigned long random_kmalloc_seed; #define __kmalloc_token(...) ((kmalloc_token_t){ .v = _CODE_LOCATION_ }) #elif defined(CONFIG_KMALLOC_PARTITION_TYPED) +#ifdef __CHECKER__ +#define __kmalloc_token(...) ((kmalloc_token_t){ .v = 0 }) +#else /* !__CHECKER__ */ #define __kmalloc_token(...) ((kmalloc_token_t){ .v = __builtin_infer_alloc_token(__VA_ARGS__) }) -#endif +#endif /* __CHECKER__ */ +#endif /* CONFIG_KMALLOC_PARTITION_TYPED */ #define DECL_TOKEN_PARAM(_token) , kmalloc_token_t (_token) #define _PASS_TOKEN_PARAM(_token) , (_token) #define PASS_TOKEN_PARAM(_token) (_token) -- cgit v1.3.1