From 346907ceb9d11b9e22677c142b45ff50dd20a66a Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 16 Nov 2022 15:56:32 +0100 Subject: mm, slab: ignore hardened usercopy parameters when disabled With CONFIG_HARDENED_USERCOPY not enabled, there are no __check_heap_object() checks happening that would use the struct kmem_cache useroffset and usersize fields. Yet the fields are still initialized, preventing merging of otherwise compatible caches. Also the fields contribute to struct kmem_cache size unnecessarily when unused. Thus #ifdef them out completely when CONFIG_HARDENED_USERCOPY is disabled. In kmem_dump_obj() print object_size instead of usersize, as that's actually the intention. In a quick virtme boot test, this has reduced the number of caches in /proc/slabinfo from 131 to 111. Cc: Kees Cook Signed-off-by: Vlastimil Babka Acked-by: Roman Gushchin Acked-by: Mike Rapoport Reviewed-by: Christoph Lameter --- include/linux/slab_def.h | 2 ++ include/linux/slub_def.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index f0ffad6a3365..5834bad8ad78 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -80,8 +80,10 @@ struct kmem_cache { unsigned int *random_seq; #endif +#ifdef CONFIG_HARDENED_USERCOPY unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ +#endif struct kmem_cache_node *node[MAX_NUMNODES]; }; diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index f9c68a9dac04..7ed5e455cbf4 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -136,8 +136,10 @@ struct kmem_cache { struct kasan_cache kasan_info; #endif +#ifdef CONFIG_HARDENED_USERCOPY unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ +#endif struct kmem_cache_node *node[MAX_NUMNODES]; }; -- cgit v1.2.3 From b1a413a39a1a7694acf3636a52c109821148ecdd Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 14 Nov 2022 18:18:39 +0100 Subject: mm, slub: disable SYSFS support with CONFIG_SLUB_TINY Currently SLUB enables its sysfs support depending unconditionally on the general CONFIG_SYSFS setting. To reduce the configuration combination space, make CONFIG_SLUB_TINY disable SLUB's sysfs support by reusing the existing SLAB_SUPPORTS_SYSFS define. It is unlikely that real tiny systems would combine CONFIG_SLUB_TINY with CONFIG_SYSFS, but a randconfig might. Signed-off-by: Vlastimil Babka Acked-by: Mike Rapoport Reviewed-by: Christoph Lameter --- include/linux/slub_def.h | 2 +- mm/slub.c | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 7ed5e455cbf4..95b67863d5cf 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -144,7 +144,7 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -#ifdef CONFIG_SYSFS +#if defined(CONFIG_SYSFS) && !defined(CONFIG_SLUB_TINY) #define SLAB_SUPPORTS_SYSFS void sysfs_slab_unlink(struct kmem_cache *); void sysfs_slab_release(struct kmem_cache *); diff --git a/mm/slub.c b/mm/slub.c index e32db8540767..b81ceeb6e6de 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -298,7 +298,7 @@ struct track { enum track_item { TRACK_ALLOC, TRACK_FREE }; -#ifdef CONFIG_SYSFS +#ifdef SLAB_SUPPORTS_SYSFS static int sysfs_slab_add(struct kmem_cache *); static int sysfs_slab_alias(struct kmem_cache *, const char *); #else @@ -2935,7 +2935,7 @@ out: } #endif /* CONFIG_SLUB_DEBUG */ -#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS) +#if defined(CONFIG_SLUB_DEBUG) || defined(SLAB_SUPPORTS_SYSFS) static unsigned long count_partial(struct kmem_cache_node *n, int (*get_count)(struct slab *)) { @@ -2949,7 +2949,7 @@ static unsigned long count_partial(struct kmem_cache_node *n, spin_unlock_irqrestore(&n->list_lock, flags); return x; } -#endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ +#endif /* CONFIG_SLUB_DEBUG || SLAB_SUPPORTS_SYSFS */ static noinline void slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) @@ -4924,7 +4924,7 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags) return 0; } -#ifdef CONFIG_SYSFS +#ifdef SLAB_SUPPORTS_SYSFS static int count_inuse(struct slab *slab) { return slab->inuse; @@ -5182,7 +5182,7 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s, #endif /* CONFIG_DEBUG_FS */ #endif /* CONFIG_SLUB_DEBUG */ -#ifdef CONFIG_SYSFS +#ifdef SLAB_SUPPORTS_SYSFS enum slab_stat_type { SL_ALL, /* All slabs */ SL_PARTIAL, /* Only partially allocated slabs */ @@ -6060,7 +6060,7 @@ static int __init slab_sysfs_init(void) } __initcall(slab_sysfs_init); -#endif /* CONFIG_SYSFS */ +#endif /* SLAB_SUPPORTS_SYSFS */ #if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS) static int slab_debugfs_show(struct seq_file *seq, void *v) -- cgit v1.2.3 From 2f7c1c1396b587e8cfe18a1f0d628cedaae56b6a Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Nov 2022 18:19:28 +0100 Subject: mm, slub: don't create kmalloc-rcl caches with CONFIG_SLUB_TINY Distinguishing kmalloc(__GFP_RECLAIMABLE) can help against fragmentation by grouping pages by mobility, but on tiny systems the extra memory overhead of separate set of kmalloc-rcl caches will probably be worse, and mobility grouping likely disabled anyway. Thus with CONFIG_SLUB_TINY, don't create kmalloc-rcl caches and use the regular ones. Signed-off-by: Vlastimil Babka Acked-by: Mike Rapoport Reviewed-by: Christoph Lameter --- include/linux/slab.h | 9 +++++++-- mm/slab_common.c | 10 ++++++++-- 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 45efc6c553b8..ae2d19ec8467 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -336,12 +336,17 @@ enum kmalloc_cache_type { #endif #ifndef CONFIG_MEMCG_KMEM KMALLOC_CGROUP = KMALLOC_NORMAL, -#else - KMALLOC_CGROUP, #endif +#ifdef CONFIG_SLUB_TINY + KMALLOC_RECLAIM = KMALLOC_NORMAL, +#else KMALLOC_RECLAIM, +#endif #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, +#endif +#ifdef CONFIG_MEMCG_KMEM + KMALLOC_CGROUP, #endif NR_KMALLOC_TYPES }; diff --git a/mm/slab_common.c b/mm/slab_common.c index af0f370fe7a2..012fc75d3ffa 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -773,10 +773,16 @@ EXPORT_SYMBOL(kmalloc_size_roundup); #define KMALLOC_CGROUP_NAME(sz) #endif +#ifndef CONFIG_SLUB_TINY +#define KMALLOC_RCL_NAME(sz) .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #sz, +#else +#define KMALLOC_RCL_NAME(sz) +#endif + #define INIT_KMALLOC_INFO(__size, __short_size) \ { \ .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ - .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \ + KMALLOC_RCL_NAME(__short_size) \ KMALLOC_CGROUP_NAME(__short_size) \ KMALLOC_DMA_NAME(__short_size) \ .size = __size, \ @@ -862,7 +868,7 @@ void __init setup_kmalloc_cache_index_table(void) static void __init new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags) { - if (type == KMALLOC_RECLAIM) { + if ((KMALLOC_RECLAIM != KMALLOC_NORMAL) && (type == KMALLOC_RECLAIM)) { flags |= SLAB_RECLAIM_ACCOUNT; } else if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_CGROUP)) { if (mem_cgroup_kmem_disabled()) { -- cgit v1.2.3 From 3d97d976e5d58554570003ca5297a67142ae4e29 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 16 Nov 2022 16:48:23 +0100 Subject: mm, slab: ignore SLAB_RECLAIM_ACCOUNT with CONFIG_SLUB_TINY SLAB_RECLAIM_ACCOUNT caches allocate their slab pages with __GFP_RECLAIMABLE and can help against fragmentation by grouping pages by mobility, but on tiny systems mobility grouping is likely disabled anyway and ignoring SLAB_RECLAIM_ACCOUNT might instead lead to merging of caches that are made incompatible just by the flag. Thus with CONFIG_SLUB_TINY, make SLAB_RECLAIM_ACCOUNT ineffective. Signed-off-by: Vlastimil Babka Acked-by: Mike Rapoport Reviewed-by: Christoph Lameter --- include/linux/slab.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index ae2d19ec8467..37fa41af24b6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -129,7 +129,11 @@ /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ +#ifndef CONFIG_SLUB_TINY #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) +#else +#define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0) +#endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* -- cgit v1.2.3 From 0af8489b0216fa1dd83e264bef8063f2632633d7 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 15 Nov 2022 18:14:31 +0100 Subject: mm, slub: remove percpu slabs with CONFIG_SLUB_TINY SLUB gets most of its scalability by percpu slabs. However for CONFIG_SLUB_TINY the goal is minimal memory overhead, not scalability. Thus, #ifdef out the whole kmem_cache_cpu percpu structure and associated code. Additionally to the slab page savings, this reduces percpu allocator usage, and code size. This change builds on recent commit c7323a5ad078 ("mm/slub: restrict sysfs validation to debug caches and make it safe"), as caches with enabled debugging also avoid percpu slabs and all allocations and freeing ends up working with the partial list. With a bit more refactoring by the preceding patches, use the same code paths with CONFIG_SLUB_TINY. Signed-off-by: Vlastimil Babka Acked-by: Mike Rapoport Reviewed-by: Christoph Lameter --- include/linux/slub_def.h | 4 ++ mm/slub.c | 102 +++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 103 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 95b67863d5cf..aa0ee1678d29 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -41,6 +41,7 @@ enum stat_item { CPU_PARTIAL_DRAIN, /* Drain cpu partial to node partial */ NR_SLUB_STAT_ITEMS }; +#ifndef CONFIG_SLUB_TINY /* * When changing the layout, make sure freelist and tid are still compatible * with this_cpu_cmpxchg_double() alignment requirements. @@ -57,6 +58,7 @@ struct kmem_cache_cpu { unsigned stat[NR_SLUB_STAT_ITEMS]; #endif }; +#endif /* CONFIG_SLUB_TINY */ #ifdef CONFIG_SLUB_CPU_PARTIAL #define slub_percpu_partial(c) ((c)->partial) @@ -88,7 +90,9 @@ struct kmem_cache_order_objects { * Slab cache management. */ struct kmem_cache { +#ifndef CONFIG_SLUB_TINY struct kmem_cache_cpu __percpu *cpu_slab; +#endif /* Used for retrieving partial slabs, etc. */ slab_flags_t flags; unsigned long min_partial; diff --git a/mm/slub.c b/mm/slub.c index 88f0ce49caab..00d921bd5417 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -337,10 +337,12 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si) */ static nodemask_t slab_nodes; +#ifndef CONFIG_SLUB_TINY /* * Workqueue used for flush_cpu_slab(). */ static struct workqueue_struct *flushwq; +#endif /******************************************************************** * Core slab cache functions @@ -386,10 +388,12 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object) return freelist_dereference(s, object + s->offset); } +#ifndef CONFIG_SLUB_TINY static void prefetch_freepointer(const struct kmem_cache *s, void *object) { prefetchw(object + s->offset); } +#endif /* * When running under KMSAN, get_freepointer_safe() may return an uninitialized @@ -1681,11 +1685,13 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node, static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) {} +#ifndef CONFIG_SLUB_TINY static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab, void **freelist, void *nextfree) { return false; } +#endif #endif /* CONFIG_SLUB_DEBUG */ /* @@ -2219,7 +2225,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, if (!pfmemalloc_match(slab, pc->flags)) continue; - if (kmem_cache_debug(s)) { + if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) { object = alloc_single_from_partial(s, n, slab, pc->orig_size); if (object) @@ -2334,6 +2340,8 @@ static void *get_partial(struct kmem_cache *s, int node, struct partial_context return get_any_partial(s, pc); } +#ifndef CONFIG_SLUB_TINY + #ifdef CONFIG_PREEMPTION /* * Calculate the next globally unique transaction for disambiguation @@ -2347,7 +2355,7 @@ static void *get_partial(struct kmem_cache *s, int node, struct partial_context * different cpus. */ #define TID_STEP 1 -#endif +#endif /* CONFIG_PREEMPTION */ static inline unsigned long next_tid(unsigned long tid) { @@ -2808,6 +2816,13 @@ static int slub_cpu_dead(unsigned int cpu) return 0; } +#else /* CONFIG_SLUB_TINY */ +static inline void flush_all_cpus_locked(struct kmem_cache *s) { } +static inline void flush_all(struct kmem_cache *s) { } +static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { } +static inline int slub_cpu_dead(unsigned int cpu) { return 0; } +#endif /* CONFIG_SLUB_TINY */ + /* * Check if the objects in a per cpu structure fit numa * locality expectations. @@ -2955,6 +2970,7 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags) return true; } +#ifndef CONFIG_SLUB_TINY /* * Check the slab->freelist and either transfer the freelist to the * per cpu freelist or deactivate the slab. @@ -3320,6 +3336,33 @@ redo: return object; } +#else /* CONFIG_SLUB_TINY */ +static void *__slab_alloc_node(struct kmem_cache *s, + gfp_t gfpflags, int node, unsigned long addr, size_t orig_size) +{ + struct partial_context pc; + struct slab *slab; + void *object; + + pc.flags = gfpflags; + pc.slab = &slab; + pc.orig_size = orig_size; + object = get_partial(s, node, &pc); + + if (object) + return object; + + slab = new_slab(s, gfpflags, node); + if (unlikely(!slab)) { + slab_out_of_memory(s, gfpflags, node); + return NULL; + } + + object = alloc_single_from_new_slab(s, slab, orig_size); + + return object; +} +#endif /* CONFIG_SLUB_TINY */ /* * If the object has been wiped upon free, make sure it's fully initialized by @@ -3503,7 +3546,7 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, if (kfence_free(head)) return; - if (kmem_cache_debug(s)) { + if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) { free_to_partial_list(s, slab, head, tail, cnt, addr); return; } @@ -3604,6 +3647,7 @@ slab_empty: discard_slab(s, slab); } +#ifndef CONFIG_SLUB_TINY /* * Fastpath with forced inlining to produce a kfree and kmem_cache_free that * can perform fastpath freeing without additional function calls. @@ -3678,6 +3722,16 @@ redo: } stat(s, FREE_FASTPATH); } +#else /* CONFIG_SLUB_TINY */ +static void do_slab_free(struct kmem_cache *s, + struct slab *slab, void *head, void *tail, + int cnt, unsigned long addr) +{ + void *tail_obj = tail ? : head; + + __slab_free(s, slab, head, tail_obj, cnt, addr); +} +#endif /* CONFIG_SLUB_TINY */ static __always_inline void slab_free(struct kmem_cache *s, struct slab *slab, void *head, void *tail, void **p, int cnt, @@ -3812,6 +3866,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) } EXPORT_SYMBOL(kmem_cache_free_bulk); +#ifndef CONFIG_SLUB_TINY static inline int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p, struct obj_cgroup *objcg) { @@ -3880,6 +3935,36 @@ error: return 0; } +#else /* CONFIG_SLUB_TINY */ +static int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, + size_t size, void **p, struct obj_cgroup *objcg) +{ + int i; + + for (i = 0; i < size; i++) { + void *object = kfence_alloc(s, s->object_size, flags); + + if (unlikely(object)) { + p[i] = object; + continue; + } + + p[i] = __slab_alloc_node(s, flags, NUMA_NO_NODE, + _RET_IP_, s->object_size); + if (unlikely(!p[i])) + goto error; + + maybe_wipe_obj_freeptr(s, p[i]); + } + + return i; + +error: + slab_post_alloc_hook(s, objcg, flags, i, p, false); + kmem_cache_free_bulk(s, i, p); + return 0; +} +#endif /* CONFIG_SLUB_TINY */ /* Note that interrupts must be enabled when calling this function. */ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, @@ -4062,6 +4147,7 @@ init_kmem_cache_node(struct kmem_cache_node *n) #endif } +#ifndef CONFIG_SLUB_TINY static inline int alloc_kmem_cache_cpus(struct kmem_cache *s) { BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE < @@ -4081,6 +4167,12 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s) return 1; } +#else +static inline int alloc_kmem_cache_cpus(struct kmem_cache *s) +{ + return 1; +} +#endif /* CONFIG_SLUB_TINY */ static struct kmem_cache *kmem_cache_node; @@ -4143,7 +4235,9 @@ static void free_kmem_cache_nodes(struct kmem_cache *s) void __kmem_cache_release(struct kmem_cache *s) { cache_random_seq_destroy(s); +#ifndef CONFIG_SLUB_TINY free_percpu(s->cpu_slab); +#endif free_kmem_cache_nodes(s); } @@ -4920,8 +5014,10 @@ void __init kmem_cache_init(void) void __init kmem_cache_init_late(void) { +#ifndef CONFIG_SLUB_TINY flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM, 0); WARN_ON(!flushwq); +#endif } struct kmem_cache * -- cgit v1.2.3