From e4c98d68959e51646c379e157bad36ef0d7bf467 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:15 +0900 Subject: mm/slab_common: fold kmalloc_order_trace() into kmalloc_large() There is no caller of kmalloc_order_trace() except kmalloc_large(). Fold it into kmalloc_large() and remove kmalloc_order{,_trace}(). Also add tracepoint in kmalloc_large() that was previously in kmalloc_order_trace(). Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 17996649cfe3..8b1988544b89 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -905,16 +905,16 @@ gfp_t kmalloc_fix_flags(gfp_t flags) * directly to the page allocator. We use __GFP_COMP, because we will need to * know the allocation order to free the pages properly in kfree. */ -void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) +void *kmalloc_large(size_t size, gfp_t flags) { void *ret = NULL; struct page *page; + unsigned int order = get_order(size); if (unlikely(flags & GFP_SLAB_BUG_MASK)) flags = kmalloc_fix_flags(flags); - flags |= __GFP_COMP; - page = alloc_pages(flags, order); + page = alloc_pages(flags | __GFP_COMP, order); if (likely(page)) { ret = page_address(page); mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, @@ -923,19 +923,10 @@ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) ret = kasan_kmalloc_large(ret, size, flags); /* As ret might get tagged, call kmemleak hook after KASAN. */ kmemleak_alloc(ret, size, 1, flags); - return ret; -} -EXPORT_SYMBOL(kmalloc_order); - -#ifdef CONFIG_TRACING -void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) -{ - void *ret = kmalloc_order(size, flags, order); trace_kmalloc(_RET_IP_, ret, NULL, size, PAGE_SIZE << order, flags); return ret; } -EXPORT_SYMBOL(kmalloc_order_trace); -#endif +EXPORT_SYMBOL(kmalloc_large); #ifdef CONFIG_SLAB_FREELIST_RANDOM /* Randomize a generic freelist */ -- cgit v1.2.1 From a0c3b940023eef3fa005b2bc37d9312712331dcb Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:16 +0900 Subject: mm/slub: move kmalloc_large_node() to slab_common.c In later patch SLAB will also pass requests larger than order-1 page to page allocator. Move kmalloc_large_node() to slab_common.c. Fold kmalloc_large_node_hook() into kmalloc_large_node() as there is no other caller. Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 8b1988544b89..1b9101f9cb21 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -928,6 +928,28 @@ void *kmalloc_large(size_t size, gfp_t flags) } EXPORT_SYMBOL(kmalloc_large); +void *kmalloc_large_node(size_t size, gfp_t flags, int node) +{ + struct page *page; + void *ptr = NULL; + unsigned int order = get_order(size); + + flags |= __GFP_COMP; + page = alloc_pages_node(node, flags, order); + if (page) { + ptr = page_address(page); + mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, + PAGE_SIZE << order); + } + + ptr = kasan_kmalloc_large(ptr, size, flags); + /* As ptr might get tagged, call kmemleak hook after KASAN. */ + kmemleak_alloc(ptr, size, 1, flags); + + return ptr; +} +EXPORT_SYMBOL(kmalloc_large_node); + #ifdef CONFIG_SLAB_FREELIST_RANDOM /* Randomize a generic freelist */ static void freelist_randomize(struct rnd_state *state, unsigned int *list, -- cgit v1.2.1 From bf37d791022ecfb1279ac88c5448a53f1ae40a59 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:17 +0900 Subject: mm/slab_common: kmalloc_node: pass large requests to page allocator Now that kmalloc_large_node() is in common code, pass large requests to page allocator in kmalloc_node() using kmalloc_large_node(). One problem is that currently there is no tracepoint in kmalloc_large_node(). Instead of simply putting tracepoint in it, use kmalloc_large_node{,_notrace} depending on its caller to show useful address for both inlined kmalloc_node() and __kmalloc_node_track_caller() when large objects are allocated. Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 1b9101f9cb21..7a0942d54424 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -928,7 +928,7 @@ void *kmalloc_large(size_t size, gfp_t flags) } EXPORT_SYMBOL(kmalloc_large); -void *kmalloc_large_node(size_t size, gfp_t flags, int node) +void *kmalloc_large_node_notrace(size_t size, gfp_t flags, int node) { struct page *page; void *ptr = NULL; @@ -948,6 +948,15 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) return ptr; } + +void *kmalloc_large_node(size_t size, gfp_t flags, int node) +{ + void *ret = kmalloc_large_node_notrace(size, flags, node); + + trace_kmalloc_node(_RET_IP_, ret, NULL, size, + PAGE_SIZE << get_order(size), flags, node); + return ret; +} EXPORT_SYMBOL(kmalloc_large_node); #ifdef CONFIG_SLAB_FREELIST_RANDOM -- cgit v1.2.1 From c4cab557521a73bd803e5c6f613b4e00bd3c4662 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:18 +0900 Subject: mm/slab_common: cleanup kmalloc_large() Now that kmalloc_large() and kmalloc_large_node() do mostly same job, make kmalloc_large() wrapper of kmalloc_large_node_notrace(). In the meantime, add missing flag fix code in kmalloc_large_node_notrace(). Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 35 +++++++++++++---------------------- 1 file changed, 13 insertions(+), 22 deletions(-) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 7a0942d54424..51ccd0545816 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -905,28 +905,6 @@ gfp_t kmalloc_fix_flags(gfp_t flags) * directly to the page allocator. We use __GFP_COMP, because we will need to * know the allocation order to free the pages properly in kfree. */ -void *kmalloc_large(size_t size, gfp_t flags) -{ - void *ret = NULL; - struct page *page; - unsigned int order = get_order(size); - - if (unlikely(flags & GFP_SLAB_BUG_MASK)) - flags = kmalloc_fix_flags(flags); - - page = alloc_pages(flags | __GFP_COMP, order); - if (likely(page)) { - ret = page_address(page); - mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, - PAGE_SIZE << order); - } - ret = kasan_kmalloc_large(ret, size, flags); - /* As ret might get tagged, call kmemleak hook after KASAN. */ - kmemleak_alloc(ret, size, 1, flags); - trace_kmalloc(_RET_IP_, ret, NULL, size, PAGE_SIZE << order, flags); - return ret; -} -EXPORT_SYMBOL(kmalloc_large); void *kmalloc_large_node_notrace(size_t size, gfp_t flags, int node) { @@ -934,6 +912,9 @@ void *kmalloc_large_node_notrace(size_t size, gfp_t flags, int node) void *ptr = NULL; unsigned int order = get_order(size); + if (unlikely(flags & GFP_SLAB_BUG_MASK)) + flags = kmalloc_fix_flags(flags); + flags |= __GFP_COMP; page = alloc_pages_node(node, flags, order); if (page) { @@ -949,6 +930,16 @@ void *kmalloc_large_node_notrace(size_t size, gfp_t flags, int node) return ptr; } +void *kmalloc_large(size_t size, gfp_t flags) +{ + void *ret = kmalloc_large_node_notrace(size, flags, NUMA_NO_NODE); + + trace_kmalloc(_RET_IP_, ret, NULL, size, + PAGE_SIZE << get_order(size), flags); + return ret; +} +EXPORT_SYMBOL(kmalloc_large); + void *kmalloc_large_node(size_t size, gfp_t flags, int node) { void *ret = kmalloc_large_node_notrace(size, flags, node); -- cgit v1.2.1 From d6a71648dbc0ca5520cba16a8fdce8d37ae74218 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:19 +0900 Subject: mm/slab: kmalloc: pass requests larger than order-1 page to page allocator There is not much benefit for serving large objects in kmalloc(). Let's pass large requests to page allocator like SLUB for better maintenance of common code. Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 51ccd0545816..5a2e81f42ee9 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -744,8 +744,8 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) /* * kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time. - * kmalloc_index() supports up to 2^25=32MB, so the final entry of the table is - * kmalloc-32M. + * kmalloc_index() supports up to 2^21=2MB, so the final entry of the table is + * kmalloc-2M. */ const struct kmalloc_info_struct kmalloc_info[] __initconst = { INIT_KMALLOC_INFO(0, 0), @@ -769,11 +769,7 @@ const struct kmalloc_info_struct kmalloc_info[] __initconst = { INIT_KMALLOC_INFO(262144, 256k), INIT_KMALLOC_INFO(524288, 512k), INIT_KMALLOC_INFO(1048576, 1M), - INIT_KMALLOC_INFO(2097152, 2M), - INIT_KMALLOC_INFO(4194304, 4M), - INIT_KMALLOC_INFO(8388608, 8M), - INIT_KMALLOC_INFO(16777216, 16M), - INIT_KMALLOC_INFO(33554432, 32M) + INIT_KMALLOC_INFO(2097152, 2M) }; /* @@ -886,6 +882,21 @@ void __init create_kmalloc_caches(slab_flags_t flags) /* Kmalloc array is now usable */ slab_state = UP; } + +void free_large_kmalloc(struct folio *folio, void *object) +{ + unsigned int order = folio_order(folio); + + if (WARN_ON_ONCE(order == 0)) + pr_warn_once("object pointer: 0x%p\n", object); + + kmemleak_free(object); + kasan_kfree_large(object); + + mod_lruvec_page_state(folio_page(folio, 0), NR_SLAB_UNRECLAIMABLE_B, + -(PAGE_SIZE << order)); + __free_pages(folio_page(folio, 0), order); +} #endif /* !CONFIG_SLOB */ gfp_t kmalloc_fix_flags(gfp_t flags) -- cgit v1.2.1 From b14051352465a24b3c9ceaccac4e39b3521bb370 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:21 +0900 Subject: mm/sl[au]b: generalize kmalloc subsystem Now everything in kmalloc subsystem can be generalized. Let's do it! Generalize __do_kmalloc_node(), __kmalloc_node_track_caller(), kfree(), __ksize(), __kmalloc(), __kmalloc_node() and move them to slab_common.c. In the meantime, rename kmalloc_large_node_notrace() to __kmalloc_large_node() and make it static as it's now only called in slab_common.c. [ feng.tang@intel.com: adjust kfence skip list to include __kmem_cache_free so that kfence kunit tests do not fail ] Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 109 +++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 106 insertions(+), 3 deletions(-) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 5a2e81f42ee9..6a744fc3d7f2 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -897,6 +897,109 @@ void free_large_kmalloc(struct folio *folio, void *object) -(PAGE_SIZE << order)); __free_pages(folio_page(folio, 0), order); } + +static void *__kmalloc_large_node(size_t size, gfp_t flags, int node); +static __always_inline +void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller) +{ + struct kmem_cache *s; + void *ret; + + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { + ret = __kmalloc_large_node(size, flags, node); + trace_kmalloc_node(caller, ret, NULL, + size, PAGE_SIZE << get_order(size), + flags, node); + return ret; + } + + s = kmalloc_slab(size, flags); + + if (unlikely(ZERO_OR_NULL_PTR(s))) + return s; + + ret = __kmem_cache_alloc_node(s, flags, node, size, caller); + ret = kasan_kmalloc(s, ret, size, flags); + trace_kmalloc_node(caller, ret, s, size, + s->size, flags, node); + return ret; +} + +void *__kmalloc_node(size_t size, gfp_t flags, int node) +{ + return __do_kmalloc_node(size, flags, node, _RET_IP_); +} +EXPORT_SYMBOL(__kmalloc_node); + +void *__kmalloc(size_t size, gfp_t flags) +{ + return __do_kmalloc_node(size, flags, NUMA_NO_NODE, _RET_IP_); +} +EXPORT_SYMBOL(__kmalloc); + +void *__kmalloc_node_track_caller(size_t size, gfp_t flags, + int node, unsigned long caller) +{ + return __do_kmalloc_node(size, flags, node, caller); +} +EXPORT_SYMBOL(__kmalloc_node_track_caller); + +/** + * kfree - free previously allocated memory + * @object: pointer returned by kmalloc. + * + * If @object is NULL, no operation is performed. + * + * Don't free memory not originally allocated by kmalloc() + * or you will run into trouble. + */ +void kfree(const void *object) +{ + struct folio *folio; + struct slab *slab; + struct kmem_cache *s; + + trace_kfree(_RET_IP_, object); + + if (unlikely(ZERO_OR_NULL_PTR(object))) + return; + + folio = virt_to_folio(object); + if (unlikely(!folio_test_slab(folio))) { + free_large_kmalloc(folio, (void *)object); + return; + } + + slab = folio_slab(folio); + s = slab->slab_cache; + __kmem_cache_free(s, (void *)object, _RET_IP_); +} +EXPORT_SYMBOL(kfree); + +/** + * __ksize -- Uninstrumented ksize. + * @object: pointer to the object + * + * Unlike ksize(), __ksize() is uninstrumented, and does not provide the same + * safety checks as ksize() with KASAN instrumentation enabled. + * + * Return: size of the actual memory used by @object in bytes + */ +size_t __ksize(const void *object) +{ + struct folio *folio; + + if (unlikely(object == ZERO_SIZE_PTR)) + return 0; + + folio = virt_to_folio(object); + + if (unlikely(!folio_test_slab(folio))) + return folio_size(folio); + + return slab_ksize(folio_slab(folio)->slab_cache); +} +EXPORT_SYMBOL(__ksize); #endif /* !CONFIG_SLOB */ gfp_t kmalloc_fix_flags(gfp_t flags) @@ -917,7 +1020,7 @@ gfp_t kmalloc_fix_flags(gfp_t flags) * know the allocation order to free the pages properly in kfree. */ -void *kmalloc_large_node_notrace(size_t size, gfp_t flags, int node) +static void *__kmalloc_large_node(size_t size, gfp_t flags, int node) { struct page *page; void *ptr = NULL; @@ -943,7 +1046,7 @@ void *kmalloc_large_node_notrace(size_t size, gfp_t flags, int node) void *kmalloc_large(size_t size, gfp_t flags) { - void *ret = kmalloc_large_node_notrace(size, flags, NUMA_NO_NODE); + void *ret = __kmalloc_large_node(size, flags, NUMA_NO_NODE); trace_kmalloc(_RET_IP_, ret, NULL, size, PAGE_SIZE << get_order(size), flags); @@ -953,7 +1056,7 @@ EXPORT_SYMBOL(kmalloc_large); void *kmalloc_large_node(size_t size, gfp_t flags, int node) { - void *ret = kmalloc_large_node_notrace(size, flags, node); + void *ret = __kmalloc_large_node(size, flags, node); trace_kmalloc_node(_RET_IP_, ret, NULL, size, PAGE_SIZE << get_order(size), flags, node); -- cgit v1.2.1 From 26a40990ba052e6f553256f9d0f112452b992a38 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:22 +0900 Subject: mm/sl[au]b: cleanup kmem_cache_alloc[_node]_trace() Despite its name, kmem_cache_alloc[_node]_trace() is hook for inlined kmalloc. So rename it to kmalloc[_node]_trace(). Move its implementation to slab_common.c by using __kmem_cache_alloc_node(), but keep CONFIG_TRACING=n varients to save a function call when CONFIG_TRACING=n. Use __assume_kmalloc_alignment for kmalloc[_node]_trace instead of __assume_slab_alignement. Generally kmalloc has larger alignment requirements. Suggested-by: Vlastimil Babka Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 6a744fc3d7f2..2eab19043940 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1000,6 +1000,33 @@ size_t __ksize(const void *object) return slab_ksize(folio_slab(folio)->slab_cache); } EXPORT_SYMBOL(__ksize); + +#ifdef CONFIG_TRACING +void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) +{ + void *ret = __kmem_cache_alloc_node(s, gfpflags, NUMA_NO_NODE, + size, _RET_IP_); + + trace_kmalloc_node(_RET_IP_, ret, s, size, s->size, + gfpflags, NUMA_NO_NODE); + + ret = kasan_kmalloc(s, ret, size, gfpflags); + return ret; +} +EXPORT_SYMBOL(kmalloc_trace); + +void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) +{ + void *ret = __kmem_cache_alloc_node(s, gfpflags, node, size, _RET_IP_); + + trace_kmalloc_node(_RET_IP_, ret, s, size, s->size, gfpflags, node); + + ret = kasan_kmalloc(s, ret, size, gfpflags); + return ret; +} +EXPORT_SYMBOL(kmalloc_node_trace); +#endif /* !CONFIG_TRACING */ #endif /* !CONFIG_SLOB */ gfp_t kmalloc_fix_flags(gfp_t flags) -- cgit v1.2.1 From 11e9734bcb6a7361943f993eba4e97f5812120d8 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:23 +0900 Subject: mm/slab_common: unify NUMA and UMA version of tracepoints Drop kmem_alloc event class, rename kmem_alloc_node to kmem_alloc, and remove _node postfix for NUMA version of tracepoints. This will break some tools that depend on {kmem_cache_alloc,kmalloc}_node, but at this point maintaining both kmem_alloc and kmem_alloc_node event classes does not makes sense at all. Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 2eab19043940..3d7ad992ece1 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -907,9 +907,8 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { ret = __kmalloc_large_node(size, flags, node); - trace_kmalloc_node(caller, ret, NULL, - size, PAGE_SIZE << get_order(size), - flags, node); + trace_kmalloc(_RET_IP_, ret, NULL, size, + PAGE_SIZE << get_order(size), flags, node); return ret; } @@ -920,8 +919,7 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller ret = __kmem_cache_alloc_node(s, flags, node, size, caller); ret = kasan_kmalloc(s, ret, size, flags); - trace_kmalloc_node(caller, ret, s, size, - s->size, flags, node); + trace_kmalloc(_RET_IP_, ret, s, size, s->size, flags, node); return ret; } @@ -1007,8 +1005,7 @@ void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) void *ret = __kmem_cache_alloc_node(s, gfpflags, NUMA_NO_NODE, size, _RET_IP_); - trace_kmalloc_node(_RET_IP_, ret, s, size, s->size, - gfpflags, NUMA_NO_NODE); + trace_kmalloc(_RET_IP_, ret, s, size, s->size, gfpflags, NUMA_NO_NODE); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; @@ -1020,7 +1017,7 @@ void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, { void *ret = __kmem_cache_alloc_node(s, gfpflags, node, size, _RET_IP_); - trace_kmalloc_node(_RET_IP_, ret, s, size, s->size, gfpflags, node); + trace_kmalloc(_RET_IP_, ret, s, size, s->size, gfpflags, node); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; @@ -1076,7 +1073,7 @@ void *kmalloc_large(size_t size, gfp_t flags) void *ret = __kmalloc_large_node(size, flags, NUMA_NO_NODE); trace_kmalloc(_RET_IP_, ret, NULL, size, - PAGE_SIZE << get_order(size), flags); + PAGE_SIZE << get_order(size), flags, NUMA_NO_NODE); return ret; } EXPORT_SYMBOL(kmalloc_large); @@ -1085,8 +1082,8 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) { void *ret = __kmalloc_large_node(size, flags, node); - trace_kmalloc_node(_RET_IP_, ret, NULL, size, - PAGE_SIZE << get_order(size), flags, node); + trace_kmalloc(_RET_IP_, ret, NULL, size, + PAGE_SIZE << get_order(size), flags, node); return ret; } EXPORT_SYMBOL(kmalloc_large_node); @@ -1421,8 +1418,6 @@ EXPORT_SYMBOL(ksize); /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); -EXPORT_TRACEPOINT_SYMBOL(kmalloc_node); -EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node); EXPORT_TRACEPOINT_SYMBOL(kfree); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free); -- cgit v1.2.1 From 2c1d697fb8ba6d2d44f914d4268ae1ccdf025f1b Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:24 +0900 Subject: mm/slab_common: drop kmem_alloc & avoid dereferencing fields when not using Drop kmem_alloc event class, and define kmalloc and kmem_cache_alloc using TRACE_EVENT() macro. And then this patch does: - Do not pass pointer to struct kmem_cache to trace_kmalloc. gfp flag is enough to know if it's accounted or not. - Avoid dereferencing s->object_size and s->size when not using kmem_cache_alloc event. - Avoid dereferencing s->name in when not using kmem_cache_free event. - Adjust s->size to SLOB_UNITS(s->size) * SLOB_UNIT in SLOB Cc: Vasily Averin Suggested-by: Vlastimil Babka Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 3d7ad992ece1..ad4c36fb697c 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -907,7 +907,7 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { ret = __kmalloc_large_node(size, flags, node); - trace_kmalloc(_RET_IP_, ret, NULL, size, + trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size), flags, node); return ret; } @@ -919,7 +919,7 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller ret = __kmem_cache_alloc_node(s, flags, node, size, caller); ret = kasan_kmalloc(s, ret, size, flags); - trace_kmalloc(_RET_IP_, ret, s, size, s->size, flags, node); + trace_kmalloc(_RET_IP_, ret, size, s->size, flags, node); return ret; } @@ -1005,7 +1005,7 @@ void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) void *ret = __kmem_cache_alloc_node(s, gfpflags, NUMA_NO_NODE, size, _RET_IP_); - trace_kmalloc(_RET_IP_, ret, s, size, s->size, gfpflags, NUMA_NO_NODE); + trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags, NUMA_NO_NODE); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; @@ -1017,7 +1017,7 @@ void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, { void *ret = __kmem_cache_alloc_node(s, gfpflags, node, size, _RET_IP_); - trace_kmalloc(_RET_IP_, ret, s, size, s->size, gfpflags, node); + trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags, node); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; @@ -1072,8 +1072,8 @@ void *kmalloc_large(size_t size, gfp_t flags) { void *ret = __kmalloc_large_node(size, flags, NUMA_NO_NODE); - trace_kmalloc(_RET_IP_, ret, NULL, size, - PAGE_SIZE << get_order(size), flags, NUMA_NO_NODE); + trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size), + flags, NUMA_NO_NODE); return ret; } EXPORT_SYMBOL(kmalloc_large); @@ -1082,8 +1082,8 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) { void *ret = __kmalloc_large_node(size, flags, node); - trace_kmalloc(_RET_IP_, ret, NULL, size, - PAGE_SIZE << get_order(size), flags, node); + trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << get_order(size), + flags, node); return ret; } EXPORT_SYMBOL(kmalloc_large_node); -- cgit v1.2.1 From 8dfa9d554061873f96335730fb1d403698b2b1b4 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:25 +0900 Subject: mm/slab_common: move declaration of __ksize() to mm/slab.h __ksize() is only called by KASAN. Remove export symbol and move declaration to mm/slab.h as we don't want to grow its callers. Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index ad4c36fb697c..500eb777faca 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -974,15 +974,7 @@ void kfree(const void *object) } EXPORT_SYMBOL(kfree); -/** - * __ksize -- Uninstrumented ksize. - * @object: pointer to the object - * - * Unlike ksize(), __ksize() is uninstrumented, and does not provide the same - * safety checks as ksize() with KASAN instrumentation enabled. - * - * Return: size of the actual memory used by @object in bytes - */ +/* Uninstrumented ksize. Only called by KASAN. */ size_t __ksize(const void *object) { struct folio *folio; @@ -997,7 +989,6 @@ size_t __ksize(const void *object) return slab_ksize(folio_slab(folio)->slab_cache); } -EXPORT_SYMBOL(__ksize); #ifdef CONFIG_TRACING void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) -- cgit v1.2.1 From d5eff736902d5565a24f1b571b5987b3e5ee9a5b Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 17 Aug 2022 19:18:26 +0900 Subject: mm/sl[au]b: check if large object is valid in __ksize() If address of large object is not beginning of folio or size of the folio is too small, it must be invalid. WARN() and return 0 in such cases. Cc: Marco Elver Suggested-by: Vlastimil Babka Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Vlastimil Babka Signed-off-by: Vlastimil Babka --- mm/slab_common.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'mm/slab_common.c') diff --git a/mm/slab_common.c b/mm/slab_common.c index 500eb777faca..7972ec4b9ca4 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -984,8 +984,13 @@ size_t __ksize(const void *object) folio = virt_to_folio(object); - if (unlikely(!folio_test_slab(folio))) + if (unlikely(!folio_test_slab(folio))) { + if (WARN_ON(folio_size(folio) <= KMALLOC_MAX_CACHE_SIZE)) + return 0; + if (WARN_ON(object != folio_address(folio))) + return 0; return folio_size(folio); + } return slab_ksize(folio_slab(folio)->slab_cache); } -- cgit v1.2.1