aboutsummaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/compiler_attributes.h3
-rw-r--r--include/linux/compiler_types.h8
-rw-r--r--include/linux/slab.h188
-rw-r--r--include/trace/events/kmem.h74
4 files changed, 115 insertions, 158 deletions
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 445e80517cab..96a4ed11b4be 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -35,7 +35,8 @@
/*
* Note: do not use this directly. Instead, use __alloc_size() since it is conditionally
- * available and includes other attributes.
+ * available and includes other attributes. For GCC < 9.1, __alloc_size__ gets undefined
+ * in compiler-gcc.h, due to misbehaviors.
*
* gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alloc_005fsize-function-attribute
* clang: https://clang.llvm.org/docs/AttributeReference.html#alloc-size
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 4f2a819fd60a..0717534f8364 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -271,14 +271,16 @@ struct ftrace_likely_data {
/*
* Any place that could be marked with the "alloc_size" attribute is also
- * a place to be marked with the "malloc" attribute. Do this as part of the
- * __alloc_size macro to avoid redundant attributes and to avoid missing a
- * __malloc marking.
+ * a place to be marked with the "malloc" attribute, except those that may
+ * be performing a _reallocation_, as that may alias the existing pointer.
+ * For these, use __realloc_size().
*/
#ifdef __alloc_size__
# define __alloc_size(x, ...) __alloc_size__(x, ## __VA_ARGS__) __malloc
+# define __realloc_size(x, ...) __alloc_size__(x, ## __VA_ARGS__)
#else
# define __alloc_size(x, ...) __malloc
+# define __realloc_size(x, ...)
#endif
#ifndef asm_volatile_goto
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 0fefdf528e0d..6a613e65e78d 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -29,6 +29,8 @@
#define SLAB_RED_ZONE ((slab_flags_t __force)0x00000400U)
/* DEBUG: Poison objects */
#define SLAB_POISON ((slab_flags_t __force)0x00000800U)
+/* Indicate a kmalloc slab */
+#define SLAB_KMALLOC ((slab_flags_t __force)0x00001000U)
/* Align objs on cache lines */
#define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U)
/* Use GFP_DMA memory */
@@ -184,11 +186,25 @@ int kmem_cache_shrink(struct kmem_cache *s);
/*
* Common kmalloc functions provided by all allocators
*/
-void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __alloc_size(2);
+void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __realloc_size(2);
void kfree(const void *objp);
void kfree_sensitive(const void *objp);
size_t __ksize(const void *objp);
+
+/**
+ * ksize - Report actual allocation size of associated object
+ *
+ * @objp: Pointer returned from a prior kmalloc()-family allocation.
+ *
+ * This should not be used for writing beyond the originally requested
+ * allocation size. Either use krealloc() or round up the allocation size
+ * with kmalloc_size_roundup() prior to allocation. If this is used to
+ * access beyond the originally requested allocation size, UBSAN_BOUNDS
+ * and/or FORTIFY_SOURCE may trip, since they only know about the
+ * originally allocated size via the __alloc_size attribute.
+ */
size_t ksize(const void *objp);
+
#ifdef CONFIG_PRINTK
bool kmem_valid_obj(void *object);
void kmem_dump_obj(void *object);
@@ -243,27 +259,17 @@ static inline unsigned int arch_slab_minalign(void)
#ifdef CONFIG_SLAB
/*
- * The largest kmalloc size supported by the SLAB allocators is
- * 32 megabyte (2^25) or the maximum allocatable page order if that is
- * less than 32 MB.
- *
- * WARNING: Its not easy to increase this value since the allocators have
- * to do various tricks to work around compiler limitations in order to
- * ensure proper constant folding.
+ * SLAB and SLUB directly allocates requests fitting in to an order-1 page
+ * (PAGE_SIZE*2). Larger requests are passed to the page allocator.
*/
-#define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \
- (MAX_ORDER + PAGE_SHIFT - 1) : 25)
-#define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH
+#define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1)
+#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1)
#ifndef KMALLOC_SHIFT_LOW
#define KMALLOC_SHIFT_LOW 5
#endif
#endif
#ifdef CONFIG_SLUB
-/*
- * SLUB directly allocates requests fitting in to an order-1 page
- * (PAGE_SIZE*2). Larger requests are passed to the page allocator.
- */
#define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1)
#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1)
#ifndef KMALLOC_SHIFT_LOW
@@ -415,10 +421,6 @@ static __always_inline unsigned int __kmalloc_index(size_t size,
if (size <= 512 * 1024) return 19;
if (size <= 1024 * 1024) return 20;
if (size <= 2 * 1024 * 1024) return 21;
- if (size <= 4 * 1024 * 1024) return 22;
- if (size <= 8 * 1024 * 1024) return 23;
- if (size <= 16 * 1024 * 1024) return 24;
- if (size <= 32 * 1024 * 1024) return 25;
if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant)
BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()");
@@ -428,6 +430,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size,
/* Will never be reached. Needed because the compiler may complain */
return -1;
}
+static_assert(PAGE_SHIFT <= 20);
#define kmalloc_index(s) __kmalloc_index(s, true)
#endif /* !CONFIG_SLOB */
@@ -456,42 +459,22 @@ static __always_inline void kfree_bulk(size_t size, void **p)
kmem_cache_free_bulk(NULL, size, p);
}
-#ifdef CONFIG_NUMA
void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment
__alloc_size(1);
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment
__malloc;
-#else
-static __always_inline __alloc_size(1) void *__kmalloc_node(size_t size, gfp_t flags, int node)
-{
- return __kmalloc(size, flags);
-}
-
-static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node)
-{
- return kmem_cache_alloc(s, flags);
-}
-#endif
#ifdef CONFIG_TRACING
-extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size)
- __assume_slab_alignment __alloc_size(3);
-
-#ifdef CONFIG_NUMA
-extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
- int node, size_t size) __assume_slab_alignment
- __alloc_size(4);
-#else
-static __always_inline __alloc_size(4) void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
- gfp_t gfpflags, int node, size_t size)
-{
- return kmem_cache_alloc_trace(s, gfpflags, size);
-}
-#endif /* CONFIG_NUMA */
+void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size)
+ __assume_kmalloc_alignment __alloc_size(3);
+void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
+ int node, size_t size) __assume_kmalloc_alignment
+ __alloc_size(4);
#else /* CONFIG_TRACING */
-static __always_inline __alloc_size(3) void *kmem_cache_alloc_trace(struct kmem_cache *s,
- gfp_t flags, size_t size)
+/* Save a function call when CONFIG_TRACING=n */
+static __always_inline __alloc_size(3)
+void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size)
{
void *ret = kmem_cache_alloc(s, flags);
@@ -499,8 +482,9 @@ static __always_inline __alloc_size(3) void *kmem_cache_alloc_trace(struct kmem_
return ret;
}
-static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
- int node, size_t size)
+static __always_inline __alloc_size(4)
+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);
@@ -509,25 +493,11 @@ static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, g
}
#endif /* CONFIG_TRACING */
-extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment
- __alloc_size(1);
+void *kmalloc_large(size_t size, gfp_t flags) __assume_page_alignment
+ __alloc_size(1);
-#ifdef CONFIG_TRACING
-extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
- __assume_page_alignment __alloc_size(1);
-#else
-static __always_inline __alloc_size(1) void *kmalloc_order_trace(size_t size, gfp_t flags,
- unsigned int order)
-{
- return kmalloc_order(size, flags, order);
-}
-#endif
-
-static __always_inline __alloc_size(1) void *kmalloc_large(size_t size, gfp_t flags)
-{
- unsigned int order = get_order(size);
- return kmalloc_order_trace(size, flags, order);
-}
+void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_alignment
+ __alloc_size(1);
/**
* kmalloc - allocate memory
@@ -597,7 +567,7 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags)
if (!index)
return ZERO_SIZE_PTR;
- return kmem_cache_alloc_trace(
+ return kmalloc_trace(
kmalloc_caches[kmalloc_type(flags)][index],
flags, size);
#endif
@@ -605,23 +575,35 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags)
return __kmalloc(size, flags);
}
+#ifndef CONFIG_SLOB
static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node)
{
-#ifndef CONFIG_SLOB
- if (__builtin_constant_p(size) &&
- size <= KMALLOC_MAX_CACHE_SIZE) {
- unsigned int i = kmalloc_index(size);
+ if (__builtin_constant_p(size)) {
+ unsigned int index;
- if (!i)
+ if (size > KMALLOC_MAX_CACHE_SIZE)
+ return kmalloc_large_node(size, flags, node);
+
+ index = kmalloc_index(size);
+
+ if (!index)
return ZERO_SIZE_PTR;
- return kmem_cache_alloc_node_trace(
- kmalloc_caches[kmalloc_type(flags)][i],
- flags, node, size);
+ return kmalloc_node_trace(
+ kmalloc_caches[kmalloc_type(flags)][index],
+ flags, node, size);
}
-#endif
return __kmalloc_node(size, flags, node);
}
+#else
+static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node)
+{
+ if (__builtin_constant_p(size) && size > KMALLOC_MAX_CACHE_SIZE)
+ return kmalloc_large_node(size, flags, node);
+
+ return __kmalloc_node(size, flags, node);
+}
+#endif
/**
* kmalloc_array - allocate memory for an array.
@@ -647,10 +629,10 @@ static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_
* @new_size: new size of a single member of the array
* @flags: the type of memory to allocate (see kmalloc)
*/
-static inline __alloc_size(2, 3) void * __must_check krealloc_array(void *p,
- size_t new_n,
- size_t new_size,
- gfp_t flags)
+static inline __realloc_size(2, 3) void * __must_check krealloc_array(void *p,
+ size_t new_n,
+ size_t new_size,
+ gfp_t flags)
{
size_t bytes;
@@ -671,6 +653,12 @@ static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flag
return kmalloc_array(n, size, flags | __GFP_ZERO);
}
+void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node,
+ unsigned long caller) __alloc_size(1);
+#define kmalloc_node_track_caller(size, flags, node) \
+ __kmalloc_node_track_caller(size, flags, node, \
+ _RET_IP_)
+
/*
* kmalloc_track_caller is a special version of kmalloc that records the
* calling function of the routine calling it for slab leak tracking instead
@@ -679,9 +667,9 @@ static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flag
* allocator where we care about the real place the memory allocation
* request comes from.
*/
-extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller);
#define kmalloc_track_caller(size, flags) \
- __kmalloc_track_caller(size, flags, _RET_IP_)
+ __kmalloc_node_track_caller(size, flags, \
+ NUMA_NO_NODE, _RET_IP_)
static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags,
int node)
@@ -700,21 +688,6 @@ static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t
return kmalloc_array_node(n, size, flags | __GFP_ZERO, node);
}
-
-#ifdef CONFIG_NUMA
-extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node,
- unsigned long caller) __alloc_size(1);
-#define kmalloc_node_track_caller(size, flags, node) \
- __kmalloc_node_track_caller(size, flags, node, \
- _RET_IP_)
-
-#else /* CONFIG_NUMA */
-
-#define kmalloc_node_track_caller(size, flags, node) \
- kmalloc_track_caller(size, flags)
-
-#endif /* CONFIG_NUMA */
-
/*
* Shortcuts
*/
@@ -774,11 +747,28 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla
}
extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
- __alloc_size(3);
+ __realloc_size(3);
extern void kvfree(const void *addr);
extern void kvfree_sensitive(const void *addr, size_t len);
unsigned int kmem_cache_size(struct kmem_cache *s);
+
+/**
+ * kmalloc_size_roundup - Report allocation bucket size for the given size
+ *
+ * @size: Number of bytes to round up from.
+ *
+ * This returns the number of bytes that would be available in a kmalloc()
+ * allocation of @size bytes. For example, a 126 byte request would be
+ * rounded up to the next sized kmalloc bucket, 128 bytes. (This is strictly
+ * for the general-purpose kmalloc()-based allocations, and is not for the
+ * pre-sized kmem_cache_alloc()-based allocations.)
+ *
+ * Use this to kmalloc() the full bucket size ahead of time instead of using
+ * ksize() to query the size after an allocation.
+ */
+size_t kmalloc_size_roundup(size_t size);
+
void __init kmem_cache_init_late(void);
#if defined(CONFIG_SMP) && defined(CONFIG_SLAB)
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 4cb51ace600d..243073cfc29d 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -9,16 +9,15 @@
#include <linux/tracepoint.h>
#include <trace/events/mmflags.h>
-DECLARE_EVENT_CLASS(kmem_alloc,
+TRACE_EVENT(kmem_cache_alloc,
TP_PROTO(unsigned long call_site,
const void *ptr,
struct kmem_cache *s,
- size_t bytes_req,
- size_t bytes_alloc,
- gfp_t gfp_flags),
+ gfp_t gfp_flags,
+ int node),
- TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags),
+ TP_ARGS(call_site, ptr, s, gfp_flags, node),
TP_STRUCT__entry(
__field( unsigned long, call_site )
@@ -26,56 +25,42 @@ DECLARE_EVENT_CLASS(kmem_alloc,
__field( size_t, bytes_req )
__field( size_t, bytes_alloc )
__field( unsigned long, gfp_flags )
+ __field( int, node )
__field( bool, accounted )
),
TP_fast_assign(
__entry->call_site = call_site;
__entry->ptr = ptr;
- __entry->bytes_req = bytes_req;
- __entry->bytes_alloc = bytes_alloc;
+ __entry->bytes_req = s->object_size;
+ __entry->bytes_alloc = s->size;
__entry->gfp_flags = (__force unsigned long)gfp_flags;
+ __entry->node = node;
__entry->accounted = IS_ENABLED(CONFIG_MEMCG_KMEM) ?
((gfp_flags & __GFP_ACCOUNT) ||
- (s && s->flags & SLAB_ACCOUNT)) : false;
+ (s->flags & SLAB_ACCOUNT)) : false;
),
- TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s accounted=%s",
+ TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s",
(void *)__entry->call_site,
__entry->ptr,
__entry->bytes_req,
__entry->bytes_alloc,
show_gfp_flags(__entry->gfp_flags),
+ __entry->node,
__entry->accounted ? "true" : "false")
);
-DEFINE_EVENT(kmem_alloc, kmalloc,
-
- TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s,
- size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
-
- TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags)
-);
-
-DEFINE_EVENT(kmem_alloc, kmem_cache_alloc,
-
- TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s,
- size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
-
- TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags)
-);
-
-DECLARE_EVENT_CLASS(kmem_alloc_node,
+TRACE_EVENT(kmalloc,
TP_PROTO(unsigned long call_site,
const void *ptr,
- struct kmem_cache *s,
size_t bytes_req,
size_t bytes_alloc,
gfp_t gfp_flags,
int node),
- TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node),
+ TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
TP_STRUCT__entry(
__field( unsigned long, call_site )
@@ -84,7 +69,6 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
__field( size_t, bytes_alloc )
__field( unsigned long, gfp_flags )
__field( int, node )
- __field( bool, accounted )
),
TP_fast_assign(
@@ -94,9 +78,6 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
__entry->bytes_alloc = bytes_alloc;
__entry->gfp_flags = (__force unsigned long)gfp_flags;
__entry->node = node;
- __entry->accounted = IS_ENABLED(CONFIG_MEMCG_KMEM) ?
- ((gfp_flags & __GFP_ACCOUNT) ||
- (s && s->flags & SLAB_ACCOUNT)) : false;
),
TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s",
@@ -106,25 +87,8 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
__entry->bytes_alloc,
show_gfp_flags(__entry->gfp_flags),
__entry->node,
- __entry->accounted ? "true" : "false")
-);
-
-DEFINE_EVENT(kmem_alloc_node, kmalloc_node,
-
- TP_PROTO(unsigned long call_site, const void *ptr,
- struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc,
- gfp_t gfp_flags, int node),
-
- TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node)
-);
-
-DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node,
-
- TP_PROTO(unsigned long call_site, const void *ptr,
- struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc,
- gfp_t gfp_flags, int node),
-
- TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node)
+ (IS_ENABLED(CONFIG_MEMCG_KMEM) &&
+ (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false")
);
TRACE_EVENT(kfree,
@@ -149,20 +113,20 @@ TRACE_EVENT(kfree,
TRACE_EVENT(kmem_cache_free,
- TP_PROTO(unsigned long call_site, const void *ptr, const char *name),
+ TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s),
- TP_ARGS(call_site, ptr, name),
+ TP_ARGS(call_site, ptr, s),
TP_STRUCT__entry(
__field( unsigned long, call_site )
__field( const void *, ptr )
- __string( name, name )
+ __string( name, s->name )
),
TP_fast_assign(
__entry->call_site = call_site;
__entry->ptr = ptr;
- __assign_str(name, name);
+ __assign_str(name, s->name);
),
TP_printk("call_site=%pS ptr=%p name=%s",
generated by cgit (git 2.34.1) at 2025-05-28 12:38:36 +0000