summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/mm/slub.rst2
-rw-r--r--arch/arm/configs/clps711x_defconfig3
-rw-r--r--arch/arm/configs/collie_defconfig3
-rw-r--r--arch/arm/configs/multi_v4t_defconfig3
-rw-r--r--arch/arm/configs/omap1_defconfig3
-rw-r--r--arch/arm/configs/pxa_defconfig3
-rw-r--r--arch/arm/configs/tct_hammer_defconfig3
-rw-r--r--arch/arm/configs/xcep_defconfig3
-rw-r--r--arch/openrisc/configs/or1ksim_defconfig3
-rw-r--r--arch/openrisc/configs/simple_smp_defconfig3
-rw-r--r--arch/riscv/configs/nommu_k210_defconfig3
-rw-r--r--arch/riscv/configs/nommu_k210_sdcard_defconfig3
-rw-r--r--arch/riscv/configs/nommu_virt_defconfig3
-rw-r--r--arch/sh/configs/rsk7201_defconfig3
-rw-r--r--arch/sh/configs/rsk7203_defconfig3
-rw-r--r--arch/sh/configs/se7206_defconfig3
-rw-r--r--arch/sh/configs/shmin_defconfig3
-rw-r--r--arch/sh/configs/shx3_defconfig3
-rw-r--r--include/linux/kasan.h5
-rw-r--r--include/linux/percpu.h2
-rw-r--r--include/linux/slab.h64
-rw-r--r--include/linux/slab_def.h2
-rw-r--r--include/linux/slub_def.h8
-rw-r--r--kernel/configs/tiny.config5
-rw-r--r--lib/Kconfig.kasan2
-rw-r--r--lib/slub_kunit.c57
-rw-r--r--mm/Kconfig38
-rw-r--r--mm/Kconfig.debug2
-rw-r--r--mm/kasan/generic.c19
-rw-r--r--mm/migrate.c15
-rw-r--r--mm/slab.c113
-rw-r--r--mm/slab.h86
-rw-r--r--mm/slab_common.c27
-rw-r--r--mm/slub.c553
-rw-r--r--tools/vm/slabinfo.c6
35 files changed, 713 insertions, 344 deletions
diff --git a/Documentation/mm/slub.rst b/Documentation/mm/slub.rst
index 4e1578186b4f..7f652216dabe 100644
--- a/Documentation/mm/slub.rst
+++ b/Documentation/mm/slub.rst
@@ -116,6 +116,8 @@ options from the ``slub_debug`` parameter translate to the following files::
T trace
A failslab
+failslab file is writable, so writing 1 or 0 will enable or disable
+the option at runtime. Write returns -EINVAL if cache is an alias.
Careful with tracing: It may spew out lots of information and never stop if
used on the wrong slab.
diff --git a/arch/arm/configs/clps711x_defconfig b/arch/arm/configs/clps711x_defconfig
index 92481b2a88fa..adcee238822a 100644
--- a/arch/arm/configs/clps711x_defconfig
+++ b/arch/arm/configs/clps711x_defconfig
@@ -14,7 +14,8 @@ CONFIG_ARCH_EDB7211=y
CONFIG_ARCH_P720T=y
CONFIG_AEABI=y
# CONFIG_COREDUMP is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/arm/configs/collie_defconfig b/arch/arm/configs/collie_defconfig
index 2a2d2cb3ce2e..69341c33e0cc 100644
--- a/arch/arm/configs/collie_defconfig
+++ b/arch/arm/configs/collie_defconfig
@@ -13,7 +13,8 @@ CONFIG_CMDLINE="noinitrd root=/dev/mtdblock2 rootfstype=jffs2 fbcon=rotate:1"
CONFIG_FPE_NWFPE=y
CONFIG_PM=y
# CONFIG_SWAP is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/arm/configs/multi_v4t_defconfig b/arch/arm/configs/multi_v4t_defconfig
index e2fd822f741a..b60000a89aff 100644
--- a/arch/arm/configs/multi_v4t_defconfig
+++ b/arch/arm/configs/multi_v4t_defconfig
@@ -25,7 +25,8 @@ CONFIG_ARM_CLPS711X_CPUIDLE=y
CONFIG_JUMP_LABEL=y
CONFIG_PARTITION_ADVANCED=y
# CONFIG_COREDUMP is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_MTD=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_BLOCK=y
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index 70511fe4b3ec..246f1bba7df5 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -42,7 +42,8 @@ CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_BINFMT_MISC=y
# CONFIG_SWAP is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
# CONFIG_VM_EVENT_COUNTERS is not set
CONFIG_NET=y
CONFIG_PACKET=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index d60cc9cc4c21..0a0f12df40b5 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -49,7 +49,8 @@ CONFIG_PARTITION_ADVANCED=y
CONFIG_LDM_PARTITION=y
CONFIG_CMDLINE_PARTITION=y
CONFIG_BINFMT_MISC=y
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
# CONFIG_COMPACTION is not set
CONFIG_NET=y
CONFIG_PACKET=y
diff --git a/arch/arm/configs/tct_hammer_defconfig b/arch/arm/configs/tct_hammer_defconfig
index 3b29ae1fb750..6bd38b6f22c4 100644
--- a/arch/arm/configs/tct_hammer_defconfig
+++ b/arch/arm/configs/tct_hammer_defconfig
@@ -19,7 +19,8 @@ CONFIG_FPE_NWFPE=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_SWAP is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/arm/configs/xcep_defconfig b/arch/arm/configs/xcep_defconfig
index ea59e4b6bfc5..6bd9f71b71fc 100644
--- a/arch/arm/configs/xcep_defconfig
+++ b/arch/arm/configs/xcep_defconfig
@@ -26,7 +26,8 @@ CONFIG_MODULE_UNLOAD=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
# CONFIG_BLOCK is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
# CONFIG_COMPAT_BRK is not set
# CONFIG_VM_EVENT_COUNTERS is not set
CONFIG_NET=y
diff --git a/arch/openrisc/configs/or1ksim_defconfig b/arch/openrisc/configs/or1ksim_defconfig
index 6e1e004047c7..0116e465238f 100644
--- a/arch/openrisc/configs/or1ksim_defconfig
+++ b/arch/openrisc/configs/or1ksim_defconfig
@@ -10,7 +10,8 @@ CONFIG_EXPERT=y
# CONFIG_AIO is not set
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_COMPAT_BRK is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_MODULES=y
# CONFIG_BLOCK is not set
CONFIG_OPENRISC_BUILTIN_DTB="or1ksim"
diff --git a/arch/openrisc/configs/simple_smp_defconfig b/arch/openrisc/configs/simple_smp_defconfig
index ff49d868e040..b990cb6c9309 100644
--- a/arch/openrisc/configs/simple_smp_defconfig
+++ b/arch/openrisc/configs/simple_smp_defconfig
@@ -16,7 +16,8 @@ CONFIG_EXPERT=y
# CONFIG_AIO is not set
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_COMPAT_BRK is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_MODULES=y
# CONFIG_BLOCK is not set
CONFIG_OPENRISC_BUILTIN_DTB="simple_smp"
diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig
index 96fe8def644c..79b3ccd58ff0 100644
--- a/arch/riscv/configs/nommu_k210_defconfig
+++ b/arch/riscv/configs/nommu_k210_defconfig
@@ -25,7 +25,8 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
CONFIG_EMBEDDED=y
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_COMPAT_BRK is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
# CONFIG_MMU is not set
CONFIG_SOC_CANAAN=y
CONFIG_NONPORTABLE=y
diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig
index 379740654373..6b80bb13b8ed 100644
--- a/arch/riscv/configs/nommu_k210_sdcard_defconfig
+++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig
@@ -17,7 +17,8 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
CONFIG_EMBEDDED=y
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_COMPAT_BRK is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
# CONFIG_MMU is not set
CONFIG_SOC_CANAAN=y
CONFIG_NONPORTABLE=y
diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig
index 1a56eda5ce46..4cf0f297091e 100644
--- a/arch/riscv/configs/nommu_virt_defconfig
+++ b/arch/riscv/configs/nommu_virt_defconfig
@@ -22,7 +22,8 @@ CONFIG_EXPERT=y
# CONFIG_KALLSYMS is not set
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_COMPAT_BRK is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
# CONFIG_MMU is not set
CONFIG_SOC_VIRT=y
CONFIG_NONPORTABLE=y
diff --git a/arch/sh/configs/rsk7201_defconfig b/arch/sh/configs/rsk7201_defconfig
index 619c18699459..376e95fa77bc 100644
--- a/arch/sh/configs/rsk7201_defconfig
+++ b/arch/sh/configs/rsk7201_defconfig
@@ -10,7 +10,8 @@ CONFIG_USER_NS=y
CONFIG_PID_NS=y
CONFIG_BLK_DEV_INITRD=y
# CONFIG_AIO is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_PROFILING=y
CONFIG_MODULES=y
# CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/sh/configs/rsk7203_defconfig b/arch/sh/configs/rsk7203_defconfig
index d00fafc021e1..1d5fd67a3949 100644
--- a/arch/sh/configs/rsk7203_defconfig
+++ b/arch/sh/configs/rsk7203_defconfig
@@ -11,7 +11,8 @@ CONFIG_USER_NS=y
CONFIG_PID_NS=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_KALLSYMS_ALL=y
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_PROFILING=y
CONFIG_MODULES=y
# CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig
index 122216123e63..78e0e7be57ee 100644
--- a/arch/sh/configs/se7206_defconfig
+++ b/arch/sh/configs/se7206_defconfig
@@ -21,7 +21,8 @@ CONFIG_BLK_DEV_INITRD=y
CONFIG_KALLSYMS_ALL=y
# CONFIG_ELF_CORE is not set
# CONFIG_COMPAT_BRK is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_PROFILING=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
diff --git a/arch/sh/configs/shmin_defconfig b/arch/sh/configs/shmin_defconfig
index c0b6f40d01cc..e078b193a78a 100644
--- a/arch/sh/configs/shmin_defconfig
+++ b/arch/sh/configs/shmin_defconfig
@@ -9,7 +9,8 @@ CONFIG_LOG_BUF_SHIFT=14
# CONFIG_FUTEX is not set
# CONFIG_EPOLL is not set
# CONFIG_SHMEM is not set
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
# CONFIG_BLK_DEV_BSG is not set
CONFIG_CPU_SUBTYPE_SH7706=y
CONFIG_MEMORY_START=0x0c000000
diff --git a/arch/sh/configs/shx3_defconfig b/arch/sh/configs/shx3_defconfig
index 32ec6eb1eabc..aa353dff7f19 100644
--- a/arch/sh/configs/shx3_defconfig
+++ b/arch/sh/configs/shx3_defconfig
@@ -20,7 +20,8 @@ CONFIG_USER_NS=y
CONFIG_PID_NS=y
# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
CONFIG_KALLSYMS_ALL=y
-CONFIG_SLOB=y
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
CONFIG_PROFILING=y
CONFIG_KPROBES=y
CONFIG_MODULES=y
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index d811b3d7d2a1..96c9d56e5510 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -302,7 +302,7 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
#ifdef CONFIG_KASAN_GENERIC
-size_t kasan_metadata_size(struct kmem_cache *cache);
+size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object);
slab_flags_t kasan_never_merge(void);
void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
slab_flags_t *flags);
@@ -315,7 +315,8 @@ void kasan_record_aux_stack_noalloc(void *ptr);
#else /* CONFIG_KASAN_GENERIC */
/* Tag-based KASAN modes do not use per-object metadata. */
-static inline size_t kasan_metadata_size(struct kmem_cache *cache)
+static inline size_t kasan_metadata_size(struct kmem_cache *cache,
+ bool in_object)
{
return 0;
}
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index f1ec5ad1351c..3dbb6fb70658 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -42,7 +42,7 @@
* larger than PERCPU_DYNAMIC_EARLY_SIZE.
*/
#define PERCPU_DYNAMIC_EARLY_SLOTS 128
-#define PERCPU_DYNAMIC_EARLY_SIZE (12 << 10)
+#define PERCPU_DYNAMIC_EARLY_SIZE (20 << 10)
/*
* PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
diff --git a/include/linux/slab.h b/include/linux/slab.h
index e7534a7b2daf..45af70315a94 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -140,7 +140,11 @@
/* 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 */
/*
@@ -347,13 +351,18 @@ 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
};
@@ -452,7 +461,18 @@ static_assert(PAGE_SHIFT <= 20);
#endif /* !CONFIG_SLOB */
void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1);
-void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc;
+
+/**
+ * kmem_cache_alloc - Allocate an object
+ * @cachep: The cache to allocate from.
+ * @flags: See kmalloc().
+ *
+ * Allocate an object from this cache.
+ * See kmem_cache_zalloc() for a shortcut of adding __GFP_ZERO to flags.
+ *
+ * Return: pointer to the new object or %NULL in case of error
+ */
+void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) __assume_slab_alignment __malloc;
void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
gfp_t gfpflags) __assume_slab_alignment __malloc;
void kmem_cache_free(struct kmem_cache *s, void *objp);
@@ -494,9 +514,9 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align
__alloc_size(1);
/**
- * kmalloc - allocate memory
+ * kmalloc - allocate kernel memory
* @size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
+ * @flags: describe the allocation context
*
* kmalloc is the normal method of allocating memory
* for objects smaller than page size in the kernel.
@@ -523,12 +543,12 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align
* %GFP_ATOMIC
* Allocation will not sleep. May use emergency pools.
*
- * %GFP_HIGHUSER
- * Allocate memory from high memory on behalf of user.
- *
* Also it is possible to set different flags by OR'ing
* in one or more of the following additional @flags:
*
+ * %__GFP_ZERO
+ * Zero the allocated memory before returning. Also see kzalloc().
+ *
* %__GFP_HIGH
* This allocation has high priority and may use emergency pools.
*
@@ -547,42 +567,42 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align
* Try really hard to succeed the allocation but fail
* eventually.
*/
+#ifndef CONFIG_SLOB
static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags)
{
- if (__builtin_constant_p(size)) {
-#ifndef CONFIG_SLOB
+ if (__builtin_constant_p(size) && size) {
unsigned int index;
-#endif
+
if (size > KMALLOC_MAX_CACHE_SIZE)
return kmalloc_large(size, flags);
-#ifndef CONFIG_SLOB
- index = kmalloc_index(size);
-
- if (!index)
- return ZERO_SIZE_PTR;
+ index = kmalloc_index(size);
return kmalloc_trace(
kmalloc_caches[kmalloc_type(flags)][index],
flags, size);
-#endif
}
return __kmalloc(size, flags);
}
+#else
+static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags)
+{
+ if (__builtin_constant_p(size) && size > KMALLOC_MAX_CACHE_SIZE)
+ return kmalloc_large(size, flags);
+
+ return __kmalloc(size, flags);
+}
+#endif
#ifndef CONFIG_SLOB
static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node)
{
- if (__builtin_constant_p(size)) {
+ if (__builtin_constant_p(size) && size) {
unsigned int index;
if (size > KMALLOC_MAX_CACHE_SIZE)
return kmalloc_large_node(size, flags, node);
index = kmalloc_index(size);
-
- if (!index)
- return ZERO_SIZE_PTR;
-
return kmalloc_node_trace(
kmalloc_caches[kmalloc_type(flags)][index],
flags, node, size);
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..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;
@@ -136,13 +140,15 @@ 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];
};
-#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/kernel/configs/tiny.config b/kernel/configs/tiny.config
index 8a44b93da0f3..c2f9c912df1c 100644
--- a/kernel/configs/tiny.config
+++ b/kernel/configs/tiny.config
@@ -7,5 +7,6 @@ CONFIG_KERNEL_XZ=y
# CONFIG_KERNEL_LZO is not set
# CONFIG_KERNEL_LZ4 is not set
# CONFIG_SLAB is not set
-# CONFIG_SLUB is not set
-CONFIG_SLOB=y
+# CONFIG_SLOB_DEPRECATED is not set
+CONFIG_SLUB=y
+CONFIG_SLUB_TINY=y
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index ca09b1cf8ee9..836f70393e22 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -37,7 +37,7 @@ menuconfig KASAN
(HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS)) && \
CC_HAS_WORKING_NOSANITIZE_ADDRESS) || \
HAVE_ARCH_KASAN_HW_TAGS
- depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
+ depends on (SLUB && SYSFS && !SLUB_TINY) || (SLAB && !DEBUG_SLAB)
select STACKDEPOT_ALWAYS_INIT
help
Enables KASAN (Kernel Address Sanitizer) - a dynamic memory safety
diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c
index 7a0564d7cb7a..bdf358d520b4 100644
--- a/lib/slub_kunit.c
+++ b/lib/slub_kunit.c
@@ -9,10 +9,25 @@
static struct kunit_resource resource;
static int slab_errors;
+/*
+ * Wrapper function for kmem_cache_create(), which reduces 2 parameters:
+ * 'align' and 'ctor', and sets SLAB_SKIP_KFENCE flag to avoid getting an
+ * object from kfence pool, where the operation could be caught by both
+ * our test and kfence sanity check.
+ */
+static struct kmem_cache *test_kmem_cache_create(const char *name,
+ unsigned int size, slab_flags_t flags)
+{
+ struct kmem_cache *s = kmem_cache_create(name, size, 0,
+ (flags | SLAB_NO_USER_FLAGS), NULL);
+ s->flags |= SLAB_SKIP_KFENCE;
+ return s;
+}
+
static void test_clobber_zone(struct kunit *test)
{
- struct kmem_cache *s = kmem_cache_create("TestSlub_RZ_alloc", 64, 0,
- SLAB_RED_ZONE|SLAB_NO_USER_FLAGS, NULL);
+ struct kmem_cache *s = test_kmem_cache_create("TestSlub_RZ_alloc", 64,
+ SLAB_RED_ZONE);
u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
kasan_disable_current();
@@ -29,8 +44,8 @@ static void test_clobber_zone(struct kunit *test)
#ifndef CONFIG_KASAN
static void test_next_pointer(struct kunit *test)
{
- struct kmem_cache *s = kmem_cache_create("TestSlub_next_ptr_free", 64, 0,
- SLAB_POISON|SLAB_NO_USER_FLAGS, NULL);
+ struct kmem_cache *s = test_kmem_cache_create("TestSlub_next_ptr_free",
+ 64, SLAB_POISON);
u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
unsigned long tmp;
unsigned long *ptr_addr;
@@ -74,8 +89,8 @@ static void test_next_pointer(struct kunit *test)
static void test_first_word(struct kunit *test)
{
- struct kmem_cache *s = kmem_cache_create("TestSlub_1th_word_free", 64, 0,
- SLAB_POISON|SLAB_NO_USER_FLAGS, NULL);
+ struct kmem_cache *s = test_kmem_cache_create("TestSlub_1th_word_free",
+ 64, SLAB_POISON);
u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
kmem_cache_free(s, p);
@@ -89,8 +104,8 @@ static void test_first_word(struct kunit *test)
static void test_clobber_50th_byte(struct kunit *test)
{
- struct kmem_cache *s = kmem_cache_create("TestSlub_50th_word_free", 64, 0,
- SLAB_POISON|SLAB_NO_USER_FLAGS, NULL);
+ struct kmem_cache *s = test_kmem_cache_create("TestSlub_50th_word_free",
+ 64, SLAB_POISON);
u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
kmem_cache_free(s, p);
@@ -105,8 +120,8 @@ static void test_clobber_50th_byte(struct kunit *test)
static void test_clobber_redzone_free(struct kunit *test)
{
- struct kmem_cache *s = kmem_cache_create("TestSlub_RZ_free", 64, 0,
- SLAB_RED_ZONE|SLAB_NO_USER_FLAGS, NULL);
+ struct kmem_cache *s = test_kmem_cache_create("TestSlub_RZ_free", 64,
+ SLAB_RED_ZONE);
u8 *p = kmem_cache_alloc(s, GFP_KERNEL);
kasan_disable_current();
@@ -120,6 +135,27 @@ static void test_clobber_redzone_free(struct kunit *test)
kmem_cache_destroy(s);
}
+static void test_kmalloc_redzone_access(struct kunit *test)
+{
+ struct kmem_cache *s = test_kmem_cache_create("TestSlub_RZ_kmalloc", 32,
+ SLAB_KMALLOC|SLAB_STORE_USER|SLAB_RED_ZONE);
+ u8 *p = kmalloc_trace(s, GFP_KERNEL, 18);
+
+ kasan_disable_current();
+
+ /* Suppress the -Warray-bounds warning */
+ OPTIMIZER_HIDE_VAR(p);
+ p[18] = 0xab;
+ p[19] = 0xab;
+
+ validate_slab_cache(s);
+ KUNIT_EXPECT_EQ(test, 2, slab_errors);
+
+ kasan_enable_current();
+ kmem_cache_free(s, p);
+ kmem_cache_destroy(s);
+}
+
static int test_init(struct kunit *test)
{
slab_errors = 0;
@@ -139,6 +175,7 @@ static struct kunit_case test_cases[] = {
#endif
KUNIT_CASE(test_clobber_redzone_free),
+ KUNIT_CASE(test_kmalloc_redzone_access),
{}
};
diff --git a/mm/Kconfig b/mm/Kconfig
index 57e1d8c5b505..623d95659ff9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -219,17 +219,43 @@ config SLUB
and has enhanced diagnostics. SLUB is the default choice for
a slab allocator.
-config SLOB
+config SLOB_DEPRECATED
depends on EXPERT
- bool "SLOB (Simple Allocator)"
+ bool "SLOB (Simple Allocator - DEPRECATED)"
depends on !PREEMPT_RT
help
+ Deprecated and scheduled for removal in a few cycles. SLUB
+ recommended as replacement. CONFIG_SLUB_TINY can be considered
+ on systems with 16MB or less RAM.
+
+ If you need SLOB to stay, please contact linux-mm@kvack.org and
+ people listed in the SLAB ALLOCATOR section of MAINTAINERS file,
+ with your use case.
+
SLOB replaces the stock allocator with a drastically simpler
allocator. SLOB is generally more space efficient but
does not perform as well on large systems.
endchoice
+config SLOB
+ bool
+ default y
+ depends on SLOB_DEPRECATED
+
+config SLUB_TINY
+ bool "Configure SLUB for minimal memory footprint"
+ depends on SLUB && EXPERT
+ select SLAB_MERGE_DEFAULT
+ help
+ Configures the SLUB allocator in a way to achieve minimal memory
+ footprint, sacrificing scalability, debugging and other features.
+ This is intended only for the smallest system that had used the
+ SLOB allocator and is not recommended for systems with more than
+ 16MB RAM.
+
+ If unsure, say N.
+
config SLAB_MERGE_DEFAULT
bool "Allow slab caches to be merged"
default y
@@ -247,7 +273,7 @@ config SLAB_MERGE_DEFAULT
config SLAB_FREELIST_RANDOM
bool "Randomize slab freelist"
- depends on SLAB || SLUB
+ depends on SLAB || (SLUB && !SLUB_TINY)
help
Randomizes the freelist order used on creating new pages. This
security feature reduces the predictability of the kernel slab
@@ -255,7 +281,7 @@ config SLAB_FREELIST_RANDOM
config SLAB_FREELIST_HARDENED
bool "Harden slab freelist metadata"
- depends on SLAB || SLUB
+ depends on SLAB || (SLUB && !SLUB_TINY)
help
Many kernel heap attacks try to target slab cache metadata and
other infrastructure. This options makes minor performance
@@ -267,7 +293,7 @@ config SLAB_FREELIST_HARDENED
config SLUB_STATS
default n
bool "Enable SLUB performance statistics"
- depends on SLUB && SYSFS
+ depends on SLUB && SYSFS && !SLUB_TINY
help
SLUB statistics are useful to debug SLUBs allocation behavior in
order find ways to optimize the allocator. This should never be
@@ -279,7 +305,7 @@ config SLUB_STATS
config SLUB_CPU_PARTIAL
default y
- depends on SLUB && SMP
+ depends on SLUB && SMP && !SLUB_TINY
bool "SLUB per cpu partial cache"
help
Per cpu partial caches accelerate objects allocation and freeing
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index ce8dded36de9..fca699ad1fb0 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -56,7 +56,7 @@ config DEBUG_SLAB
config SLUB_DEBUG
default y
bool "Enable SLUB debugging support" if EXPERT
- depends on SLUB && SYSFS
+ depends on SLUB && SYSFS && !SLUB_TINY
select STACKDEPOT if STACKTRACE_SUPPORT
help
SLUB has extensive debug support features. Disabling these can
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index d8b5590f9484..b076f597a378 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -450,15 +450,22 @@ void kasan_init_object_meta(struct kmem_cache *cache, const void *object)
__memset(alloc_meta, 0, sizeof(*alloc_meta));
}
-size_t kasan_metadata_size(struct kmem_cache *cache)
+size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object)
{
+ struct kasan_cache *info = &cache->kasan_info;
+
if (!kasan_requires_meta())
return 0;
- return (cache->kasan_info.alloc_meta_offset ?
- sizeof(struct kasan_alloc_meta) : 0) +
- ((cache->kasan_info.free_meta_offset &&
- cache->kasan_info.free_meta_offset != KASAN_NO_FREE_META) ?
- sizeof(struct kasan_free_meta) : 0);
+
+ if (in_object)
+ return (info->free_meta_offset ?
+ 0 : sizeof(struct kasan_free_meta));
+ else
+ return (info->alloc_meta_offset ?
+ sizeof(struct kasan_alloc_meta) : 0) +
+ ((info->free_meta_offset &&
+ info->free_meta_offset != KASAN_NO_FREE_META) ?
+ sizeof(struct kasan_free_meta) : 0);
}
static void __kasan_record_aux_stack(void *addr, bool can_alloc)
diff --git a/mm/migrate.c b/mm/migrate.c
index dff333593a8a..1ee0719bd7a1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -74,13 +74,22 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode)
if (unlikely(!get_page_unless_zero(page)))
goto out;
+ if (unlikely(PageSlab(page)))
+ goto out_putpage;
+ /* Pairs with smp_wmb() in slab freeing, e.g. SLUB's __free_slab() */
+ smp_rmb();
/*
- * Check PageMovable before holding a PG_lock because page's owner
- * assumes anybody doesn't touch PG_lock of newly allocated page
- * so unconditionally grabbing the lock ruins page's owner side.
+ * Check movable flag before taking the page lock because
+ * we use non-atomic bitops on newly allocated page flags so
+ * unconditionally grabbing the lock ruins page's owner side.
*/
if (unlikely(!__PageMovable(page)))
goto out_putpage;
+ /* Pairs with smp_wmb() in slab allocation, e.g. SLUB's alloc_slab_page() */
+ smp_rmb();
+ if (unlikely(PageSlab(page)))
+ goto out_putpage;
+
/*
* As movable pages are not isolated from LRU lists, concurrent
* compaction threads can race against page migration functions
diff --git a/mm/slab.c b/mm/slab.c
index 59c8e28f7b6a..7a269db050ee 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -234,7 +234,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent)
parent->shared = NULL;
parent->alien = NULL;
parent->colour_next = 0;
- spin_lock_init(&parent->list_lock);
+ raw_spin_lock_init(&parent->list_lock);
parent->free_objects = 0;
parent->free_touched = 0;
}
@@ -559,9 +559,9 @@ static noinline void cache_free_pfmemalloc(struct kmem_cache *cachep,
slab_node = slab_nid(slab);
n = get_node(cachep, slab_node);
- spin_lock(&n->list_lock);
+ raw_spin_lock(&n->list_lock);
free_block(cachep, &objp, 1, slab_node, &list);
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
slabs_destroy(cachep, &list);
}
@@ -684,7 +684,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
struct kmem_cache_node *n = get_node(cachep, node);
if (ac->avail) {
- spin_lock(&n->list_lock);
+ raw_spin_lock(&n->list_lock);
/*
* Stuff objects into the remote nodes shared array first.
* That way we could avoid the overhead of putting the objects
@@ -695,7 +695,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
free_block(cachep, ac->entry, ac->avail, node, list);
ac->avail = 0;
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
}
}
@@ -768,9 +768,9 @@ static int __cache_free_alien(struct kmem_cache *cachep, void *objp,
slabs_destroy(cachep, &list);
} else {
n = get_node(cachep, slab_node);
- spin_lock(&n->list_lock);
+ raw_spin_lock(&n->list_lock);
free_block(cachep, &objp, 1, slab_node, &list);
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
slabs_destroy(cachep, &list);
}
return 1;
@@ -811,10 +811,10 @@ static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp)
*/
n = get_node(cachep, node);
if (n) {
- spin_lock_irq(&n->list_lock);
+ raw_spin_lock_irq(&n->list_lock);
n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount +
cachep->num;
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
return 0;
}
@@ -893,7 +893,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep,
goto fail;
n = get_node(cachep, node);
- spin_lock_irq(&n->list_lock);
+ raw_spin_lock_irq(&n->list_lock);
if (n->shared && force_change) {
free_block(cachep, n->shared->entry,
n->shared->avail, node, &list);
@@ -911,7 +911,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep,
new_alien = NULL;
}
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
slabs_destroy(cachep, &list);
/*
@@ -950,7 +950,7 @@ static void cpuup_canceled(long cpu)
if (!n)
continue;
- spin_lock_irq(&n->list_lock);
+ raw_spin_lock_irq(&n->list_lock);
/* Free limit for this kmem_cache_node */
n->free_limit -= cachep->batchcount;
@@ -961,7 +961,7 @@ static void cpuup_canceled(long cpu)
nc->avail = 0;
if (!cpumask_empty(mask)) {
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
goto free_slab;
}
@@ -975,7 +975,7 @@ static void cpuup_canceled(long cpu)
alien = n->alien;
n->alien = NULL;
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
kfree(shared);
if (alien) {
@@ -1159,7 +1159,7 @@ static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node *
/*
* Do not assume that spinlocks can be initialized via memcpy:
*/
- spin_lock_init(&ptr->list_lock);
+ raw_spin_lock_init(&ptr->list_lock);
MAKE_ALL_LISTS(cachep, ptr, nodeid);
cachep->node[nodeid] = ptr;
@@ -1330,11 +1330,11 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
for_each_kmem_cache_node(cachep, node, n) {
unsigned long total_slabs, free_slabs, free_objs;
- spin_lock_irqsave(&n->list_lock, flags);
+ raw_spin_lock_irqsave(&n->list_lock, flags);
total_slabs = n->total_slabs;
free_slabs = n->free_slabs;
free_objs = n->free_objects;
- spin_unlock_irqrestore(&n->list_lock, flags);
+ raw_spin_unlock_irqrestore(&n->list_lock, flags);
pr_warn(" node %d: slabs: %ld/%ld, objs: %ld/%ld\n",
node, total_slabs - free_slabs, total_slabs,
@@ -1370,6 +1370,8 @@ static struct slab *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
account_slab(slab, cachep->gfporder, cachep, flags);
__folio_set_slab(folio);
+ /* Make the flag visible before any changes to folio->mapping */
+ smp_wmb();
/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
if (sk_memalloc_socks() && page_is_pfmemalloc(folio_page(folio, 0)))
slab_set_pfmemalloc(slab);
@@ -1387,9 +1389,11 @@ static void kmem_freepages(struct kmem_cache *cachep, struct slab *slab)
BUG_ON(!folio_test_slab(folio));
__slab_clear_pfmemalloc(slab);
- __folio_clear_slab(folio);
page_mapcount_reset(folio_page(folio, 0));
folio->mapping = NULL;
+ /* Make the mapping reset visible before clearing the flag */
+ smp_wmb();
+ __folio_clear_slab(folio);
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += 1 << order;
@@ -2096,7 +2100,7 @@ static void check_spinlock_acquired(struct kmem_cache *cachep)
{
#ifdef CONFIG_SMP
check_irq_off();
- assert_spin_locked(&get_node(cachep, numa_mem_id())->list_lock);
+ assert_raw_spin_locked(&get_node(cachep, numa_mem_id())->list_lock);
#endif
}
@@ -2104,7 +2108,7 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
{
#ifdef CONFIG_SMP
check_irq_off();
- assert_spin_locked(&get_node(cachep, node)->list_lock);
+ assert_raw_spin_locked(&get_node(cachep, node)->list_lock);
#endif
}
@@ -2144,9 +2148,9 @@ static void do_drain(void *arg)
check_irq_off();
ac = cpu_cache_get(cachep);
n = get_node(cachep, node);
- spin_lock(&n->list_lock);
+ raw_spin_lock(&n->list_lock);
free_block(cachep, ac->entry, ac->avail, node, &list);
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
ac->avail = 0;
slabs_destroy(cachep, &list);
}
@@ -2164,9 +2168,9 @@ static void drain_cpu_caches(struct kmem_cache *cachep)
drain_alien_cache(cachep, n->alien);
for_each_kmem_cache_node(cachep, node, n) {
- spin_lock_irq(&n->list_lock);
+ raw_spin_lock_irq(&n->list_lock);
drain_array_locked(cachep, n->shared, node, true, &list);
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
slabs_destroy(cachep, &list);
}
@@ -2188,10 +2192,10 @@ static int drain_freelist(struct kmem_cache *cache,
nr_freed = 0;
while (nr_freed < tofree && !list_empty(&n->slabs_free)) {
- spin_lock_irq(&n->list_lock);
+ raw_spin_lock_irq(&n->list_lock);
p = n->slabs_free.prev;
if (p == &n->slabs_free) {
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
goto out;
}
@@ -2204,7 +2208,7 @@ static int drain_freelist(struct kmem_cache *cache,
* to the cache.
*/
n->free_objects -= cache->num;
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
slab_destroy(cache, slab);
nr_freed++;
}
@@ -2629,7 +2633,7 @@ static void cache_grow_end(struct kmem_cache *cachep, struct slab *slab)
INIT_LIST_HEAD(&slab->slab_list);
n = get_node(cachep, slab_nid(slab));
- spin_lock(&n->list_lock);
+ raw_spin_lock(&n->list_lock);
n->total_slabs++;
if (!slab->active) {
list_add_tail(&slab->slab_list, &n->slabs_free);
@@ -2639,7 +2643,7 @@ static void cache_grow_end(struct kmem_cache *cachep, struct slab *slab)
STATS_INC_GROWN(cachep);
n->free_objects += cachep->num - slab->active;
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
fixup_objfreelist_debug(cachep, &list);
}
@@ -2805,7 +2809,7 @@ static struct slab *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc)
{
struct slab *slab;
- assert_spin_locked(&n->list_lock);
+ assert_raw_spin_locked(&n->list_lock);
slab = list_first_entry_or_null(&n->slabs_partial, struct slab,
slab_list);
if (!slab) {
@@ -2832,10 +2836,10 @@ static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep,
if (!gfp_pfmemalloc_allowed(flags))
return NULL;
- spin_lock(&n->list_lock);
+ raw_spin_lock(&n->list_lock);
slab = get_first_slab(n, true);
if (!slab) {
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
return NULL;
}
@@ -2844,7 +2848,7 @@ static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep,
fixup_slab_list(cachep, n, slab, &list);
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
fixup_objfreelist_debug(cachep, &list);
return obj;
@@ -2903,7 +2907,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
if (!n->free_objects && (!shared || !shared->avail))
goto direct_grow;
- spin_lock(&n->list_lock);
+ raw_spin_lock(&n->list_lock);
shared = READ_ONCE(n->shared);
/* See if we can refill from the shared array */
@@ -2927,7 +2931,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
must_grow:
n->free_objects -= ac->avail;
alloc_done:
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
fixup_objfreelist_debug(cachep, &list);
direct_grow:
@@ -3147,7 +3151,7 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
BUG_ON(!n);
check_irq_off();
- spin_lock(&n->list_lock);
+ raw_spin_lock(&n->list_lock);
slab = get_first_slab(n, false);
if (!slab)
goto must_grow;
@@ -3165,12 +3169,12 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
fixup_slab_list(cachep, n, slab, &list);
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
fixup_objfreelist_debug(cachep, &list);
return obj;
must_grow:
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
slab = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid);
if (slab) {
/* This slab isn't counted yet so don't update free_objects */
@@ -3254,7 +3258,8 @@ slab_alloc_node(struct kmem_cache *cachep, struct list_lru *lru, gfp_t flags,
init = slab_want_init_on_alloc(flags, cachep);
out:
- slab_post_alloc_hook(cachep, objcg, flags, 1, &objp, init);
+ slab_post_alloc_hook(cachep, objcg, flags, 1, &objp, init,
+ cachep->object_size);
return objp;
}
@@ -3325,7 +3330,7 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
check_irq_off();
n = get_node(cachep, node);
- spin_lock(&n->list_lock);
+ raw_spin_lock(&n->list_lock);
if (n->shared) {
struct array_cache *shared_array = n->shared;
int max = shared_array->limit - shared_array->avail;
@@ -3354,7 +3359,7 @@ free_done:
STATS_SET_FREEABLE(cachep, i);
}
#endif
- spin_unlock(&n->list_lock);
+ raw_spin_unlock(&n->list_lock);
ac->avail -= batchcount;
memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail);
slabs_destroy(cachep, &list);
@@ -3446,16 +3451,6 @@ void *__kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
return ret;
}
-/**
- * kmem_cache_alloc - Allocate an object
- * @cachep: The cache to allocate from.
- * @flags: See kmalloc().
- *
- * Allocate an object from this cache. The flags are only relevant
- * if the cache has no available objects.
- *
- * Return: pointer to the new object or %NULL in case of error
- */
void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
return __kmem_cache_alloc_lru(cachep, NULL, flags);
@@ -3507,13 +3502,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
* Done outside of the IRQ disabled section.
*/
slab_post_alloc_hook(s, objcg, flags, size, p,
- slab_want_init_on_alloc(flags, s));
+ slab_want_init_on_alloc(flags, s), s->object_size);
/* FIXME: Trace call missing. Christoph would like a bulk variant */
return size;
error:
local_irq_enable();
cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_);
- slab_post_alloc_hook(s, objcg, flags, i, p, false);
+ slab_post_alloc_hook(s, objcg, flags, i, p, false, s->object_size);
kmem_cache_free_bulk(s, i, p);
return 0;
}
@@ -3721,9 +3716,9 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
node = cpu_to_mem(cpu);
n = get_node(cachep, node);
- spin_lock_irq(&n->list_lock);
+ raw_spin_lock_irq(&n->list_lock);
free_block(cachep, ac->entry, ac->avail, node, &list);
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
slabs_destroy(cachep, &list);
}
free_percpu(prev);
@@ -3815,9 +3810,9 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n,
return;
}
- spin_lock_irq(&n->list_lock);
+ raw_spin_lock_irq(&n->list_lock);
drain_array_locked(cachep, ac, node, false, &list);
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
slabs_destroy(cachep, &list);
}
@@ -3901,7 +3896,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
for_each_kmem_cache_node(cachep, node, n) {
check_irq_on();
- spin_lock_irq(&n->list_lock);
+ raw_spin_lock_irq(&n->list_lock);
total_slabs += n->total_slabs;
free_slabs += n->free_slabs;
@@ -3910,7 +3905,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
if (n->shared)
shared_avail += n->shared->avail;
- spin_unlock_irq(&n->list_lock);
+ raw_spin_unlock_irq(&n->list_lock);
}
num_objs = total_slabs * cachep->num;
active_slabs = total_slabs - free_slabs;
diff --git a/mm/slab.h b/mm/slab.h
index 0202a8c2f0d2..7cc432969945 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -11,37 +11,43 @@ struct slab {
#if defined(CONFIG_SLAB)
+ struct kmem_cache *slab_cache;
union {
- struct list_head slab_list;
+ struct {
+ struct list_head slab_list;
+ void *freelist; /* array of free object indexes */
+ void *s_mem; /* first object */
+ };
struct rcu_head rcu_head;
};
- struct kmem_cache *slab_cache;
- void *freelist; /* array of free object indexes */
- void *s_mem; /* first object */
unsigned int active;
#elif defined(CONFIG_SLUB)
- union {
- struct list_head slab_list;
- struct rcu_head rcu_head;
-#ifdef CONFIG_SLUB_CPU_PARTIAL
- struct {
- struct slab *next;
- int slabs; /* Nr of slabs left */
- };
-#endif
- };
struct kmem_cache *slab_cache;
- /* Double-word boundary */
- void *freelist; /* first free object */
union {
- unsigned long counters;
struct {
- unsigned inuse:16;
- unsigned objects:15;
- unsigned frozen:1;
+ union {
+ struct list_head slab_list;
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+ struct {
+ struct slab *next;
+ int slabs; /* Nr of slabs left */
+ };
+#endif
+ };
+ /* Double-word boundary */
+ void *freelist; /* first free object */
+ union {
+ unsigned long counters;
+ struct {
+ unsigned inuse:16;
+ unsigned objects:15;
+ unsigned frozen:1;
+ };
+ };
};
+ struct rcu_head rcu_head;
};
unsigned int __unused;
@@ -66,9 +72,10 @@ struct slab {
#define SLAB_MATCH(pg, sl) \
static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl))
SLAB_MATCH(flags, __page_flags);
-SLAB_MATCH(compound_head, slab_list); /* Ensure bit 0 is clear */
#ifndef CONFIG_SLOB
-SLAB_MATCH(rcu_head, rcu_head);
+SLAB_MATCH(compound_head, slab_cache); /* Ensure bit 0 is clear */
+#else
+SLAB_MATCH(compound_head, slab_list); /* Ensure bit 0 is clear */
#endif
SLAB_MATCH(_refcount, __page_refcount);
#ifdef CONFIG_MEMCG
@@ -76,6 +83,9 @@ SLAB_MATCH(memcg_data, memcg_data);
#endif
#undef SLAB_MATCH
static_assert(sizeof(struct slab) <= sizeof(struct page));
+#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && defined(CONFIG_SLUB)
+static_assert(IS_ALIGNED(offsetof(struct slab, freelist), 2*sizeof(void *)));
+#endif
/**
* folio_slab - Converts from folio to slab.
@@ -207,8 +217,6 @@ struct kmem_cache {
unsigned int size; /* The aligned/padded/added on size */
unsigned int align; /* Alignment as calculated */
slab_flags_t flags; /* Active flags on the slab */
- unsigned int useroffset;/* Usercopy region offset */
- unsigned int usersize; /* Usercopy region size */
const char *name; /* Slab name for sysfs */
int refcount; /* Use counter */
void (*ctor)(void *); /* Called on object slot creation */
@@ -336,7 +344,8 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
SLAB_ACCOUNT)
#elif defined(CONFIG_SLUB)
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
- SLAB_TEMPORARY | SLAB_ACCOUNT | SLAB_NO_USER_FLAGS)
+ SLAB_TEMPORARY | SLAB_ACCOUNT | \
+ SLAB_NO_USER_FLAGS | SLAB_KMALLOC)
#else
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
#endif
@@ -356,6 +365,7 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
SLAB_RECLAIM_ACCOUNT | \
SLAB_TEMPORARY | \
SLAB_ACCOUNT | \
+ SLAB_KMALLOC | \
SLAB_NO_USER_FLAGS)
bool __kmem_cache_empty(struct kmem_cache *);
@@ -720,13 +730,27 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
static inline void slab_post_alloc_hook(struct kmem_cache *s,
struct obj_cgroup *objcg, gfp_t flags,
- size_t size, void **p, bool init)
+ size_t size, void **p, bool init,
+ unsigned int orig_size)
{
+ unsigned int zero_size = s->object_size;
size_t i;
flags &= gfp_allowed_mask;
/*
+ * For kmalloc object, the allocated memory size(object_size) is likely
+ * larger than the requested size(orig_size). If redzone check is
+ * enabled for the extra space, don't zero it, as it will be redzoned
+ * soon. The redzone operation for this extra space could be seen as a
+ * replacement of current poisoning under certain debug option, and
+ * won't break other sanity checks.
+ */
+ if (kmem_cache_debug_flags(s, SLAB_STORE_USER | SLAB_RED_ZONE) &&
+ (s->flags & SLAB_KMALLOC))
+ zero_size = orig_size;
+
+ /*
* As memory initialization might be integrated into KASAN,
* kasan_slab_alloc and initialization memset must be
* kept together to avoid discrepancies in behavior.
@@ -736,7 +760,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s,
for (i = 0; i < size; i++) {
p[i] = kasan_slab_alloc(s, p[i], flags, init);
if (p[i] && init && !kasan_has_integrated_init())
- memset(p[i], 0, s->object_size);
+ memset(p[i], 0, zero_size);
kmemleak_alloc_recursive(p[i], s->object_size, 1,
s->flags, flags);
kmsan_slab_alloc(s, p[i], flags);
@@ -750,9 +774,8 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s,
* The slab lists for all objects.
*/
struct kmem_cache_node {
- spinlock_t list_lock;
-
#ifdef CONFIG_SLAB
+ raw_spinlock_t list_lock;
struct list_head slabs_partial; /* partial list first, better asm code */
struct list_head slabs_full;
struct list_head slabs_free;
@@ -768,6 +791,7 @@ struct kmem_cache_node {
#endif
#ifdef CONFIG_SLUB
+ spinlock_t list_lock;
unsigned long nr_partial;
struct list_head partial;
#ifdef CONFIG_SLUB_DEBUG
@@ -871,4 +895,8 @@ void __check_heap_object(const void *ptr, unsigned long n,
}
#endif
+#ifdef CONFIG_SLUB_DEBUG
+void skip_orig_size_check(struct kmem_cache *s, const void *object);
+#endif
+
#endif /* MM_SLAB_H */
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 0042fb2730d1..3e49bb830060 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -143,8 +143,10 @@ int slab_unmergeable(struct kmem_cache *s)
if (s->ctor)
return 1;
+#ifdef CONFIG_HARDENED_USERCOPY
if (s->usersize)
return 1;
+#endif
/*
* We may have set a slab to be unmergeable during bootstrap.
@@ -223,8 +225,10 @@ static struct kmem_cache *create_cache(const char *name,
s->size = s->object_size = object_size;
s->align = align;
s->ctor = ctor;
+#ifdef CONFIG_HARDENED_USERCOPY
s->useroffset = useroffset;
s->usersize = usersize;
+#endif
err = __kmem_cache_create(s, flags);
if (err)
@@ -317,7 +321,8 @@ kmem_cache_create_usercopy(const char *name,
flags &= CACHE_CREATE_MASK;
/* Fail closed on bad usersize of useroffset values. */
- if (WARN_ON(!usersize && useroffset) ||
+ if (!IS_ENABLED(CONFIG_HARDENED_USERCOPY) ||
+ WARN_ON(!usersize && useroffset) ||
WARN_ON(size < usersize || size - usersize < useroffset))
usersize = useroffset = 0;
@@ -595,8 +600,8 @@ void kmem_dump_obj(void *object)
ptroffset = ((char *)object - (char *)kp.kp_objp) - kp.kp_data_offset;
pr_cont(" pointer offset %lu", ptroffset);
}
- if (kp.kp_slab_cache && kp.kp_slab_cache->usersize)
- pr_cont(" size %u", kp.kp_slab_cache->usersize);
+ if (kp.kp_slab_cache && kp.kp_slab_cache->object_size)
+ pr_cont(" size %u", kp.kp_slab_cache->object_size);
if (kp.kp_ret)
pr_cont(" allocated at %pS\n", kp.kp_ret);
else
@@ -640,8 +645,10 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name,
align = max(align, size);
s->align = calculate_alignment(flags, align, size);
+#ifdef CONFIG_HARDENED_USERCOPY
s->useroffset = useroffset;
s->usersize = usersize;
+#endif
err = __kmem_cache_create(s, flags);
@@ -766,10 +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, \
@@ -855,7 +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()) {
@@ -1037,6 +1050,10 @@ size_t __ksize(const void *object)
return folio_size(folio);
}
+#ifdef CONFIG_SLUB_DEBUG
+ skip_orig_size_check(folio_slab(folio)->slab_cache, object);
+#endif
+
return slab_ksize(folio_slab(folio)->slab_cache);
}
diff --git a/mm/slub.c b/mm/slub.c
index 157527d7101b..891df05a4d45 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -187,6 +187,12 @@ do { \
#define USE_LOCKLESS_FAST_PATH() (false)
#endif
+#ifndef CONFIG_SLUB_TINY
+#define __fastpath_inline __always_inline
+#else
+#define __fastpath_inline
+#endif
+
#ifdef CONFIG_SLUB_DEBUG
#ifdef CONFIG_SLUB_DEBUG_ON
DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
@@ -241,6 +247,7 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
/* Enable to log cmpxchg failures */
#undef SLUB_DEBUG_CMPXCHG
+#ifndef CONFIG_SLUB_TINY
/*
* Minimum number of partial slabs. These will be left on the partial
* lists even if they are empty. kmem_cache_shrink may reclaim them.
@@ -253,6 +260,10 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
* sort the partial list by the number of objects in use.
*/
#define MAX_PARTIAL 10
+#else
+#define MIN_PARTIAL 0
+#define MAX_PARTIAL 0
+#endif
#define DEBUG_DEFAULT_FLAGS (SLAB_CONSISTENCY_CHECKS | SLAB_RED_ZONE | \
SLAB_POISON | SLAB_STORE_USER)
@@ -298,7 +309,7 @@ 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
@@ -332,10 +343,12 @@ 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
@@ -381,10 +394,12 @@ 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
@@ -829,6 +844,17 @@ static inline void set_orig_size(struct kmem_cache *s,
if (!slub_debug_orig_size(s))
return;
+#ifdef CONFIG_KASAN_GENERIC
+ /*
+ * KASAN could save its free meta data in object's data area at
+ * offset 0, if the size is larger than 'orig_size', it will
+ * overlap the data redzone in [orig_size+1, object_size], and
+ * the check should be skipped.
+ */
+ if (kasan_metadata_size(s, true) > orig_size)
+ orig_size = s->object_size;
+#endif
+
p += get_info_end(s);
p += sizeof(struct track) * 2;
@@ -848,6 +874,11 @@ static inline unsigned int get_orig_size(struct kmem_cache *s, void *object)
return *(unsigned int *)p;
}
+void skip_orig_size_check(struct kmem_cache *s, const void *object)
+{
+ set_orig_size(s, (void *)object, s->object_size);
+}
+
static void slab_bug(struct kmem_cache *s, char *fmt, ...)
{
struct va_format vaf;
@@ -910,7 +941,7 @@ static void print_trailer(struct kmem_cache *s, struct slab *slab, u8 *p)
if (slub_debug_orig_size(s))
off += sizeof(unsigned int);
- off += kasan_metadata_size(s);
+ off += kasan_metadata_size(s, false);
if (off != size_from_object(s))
/* Beginning of the filler is the free pointer */
@@ -966,17 +997,28 @@ static __printf(3, 4) void slab_err(struct kmem_cache *s, struct slab *slab,
static void init_object(struct kmem_cache *s, void *object, u8 val)
{
u8 *p = kasan_reset_tag(object);
+ unsigned int poison_size = s->object_size;
- if (s->flags & SLAB_RED_ZONE)
+ if (s->flags & SLAB_RED_ZONE) {
memset(p - s->red_left_pad, val, s->red_left_pad);
+ if (slub_debug_orig_size(s) && val == SLUB_RED_ACTIVE) {
+ /*
+ * Redzone the extra allocated space by kmalloc than
+ * requested, and the poison size will be limited to
+ * the original request size accordingly.
+ */
+ poison_size = get_orig_size(s, object);
+ }
+ }
+
if (s->flags & __OBJECT_POISON) {
- memset(p, POISON_FREE, s->object_size - 1);
- p[s->object_size - 1] = POISON_END;
+ memset(p, POISON_FREE, poison_size - 1);
+ p[poison_size - 1] = POISON_END;
}
if (s->flags & SLAB_RED_ZONE)
- memset(p + s->object_size, val, s->inuse - s->object_size);
+ memset(p + poison_size, val, s->inuse - poison_size);
}
static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
@@ -1070,7 +1112,7 @@ static int check_pad_bytes(struct kmem_cache *s, struct slab *slab, u8 *p)
off += sizeof(unsigned int);
}
- off += kasan_metadata_size(s);
+ off += kasan_metadata_size(s, false);
if (size_from_object(s) == off)
return 1;
@@ -1120,6 +1162,7 @@ static int check_object(struct kmem_cache *s, struct slab *slab,
{
u8 *p = object;
u8 *endobject = object + s->object_size;
+ unsigned int orig_size;
if (s->flags & SLAB_RED_ZONE) {
if (!check_bytes_and_report(s, slab, object, "Left Redzone",
@@ -1129,6 +1172,17 @@ static int check_object(struct kmem_cache *s, struct slab *slab,
if (!check_bytes_and_report(s, slab, object, "Right Redzone",
endobject, val, s->inuse - s->object_size))
return 0;
+
+ if (slub_debug_orig_size(s) && val == SLUB_RED_ACTIVE) {
+ orig_size = get_orig_size(s, object);
+
+ if (s->object_size > orig_size &&
+ !check_bytes_and_report(s, slab, object,
+ "kmalloc Redzone", p + orig_size,
+ val, s->object_size - orig_size)) {
+ return 0;
+ }
+ }
} else {
if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
check_bytes_and_report(s, slab, p, "Alignment padding",
@@ -1363,7 +1417,7 @@ static inline int alloc_consistency_checks(struct kmem_cache *s,
return 1;
}
-static noinline int alloc_debug_processing(struct kmem_cache *s,
+static noinline bool alloc_debug_processing(struct kmem_cache *s,
struct slab *slab, void *object, int orig_size)
{
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
@@ -1375,7 +1429,7 @@ static noinline int alloc_debug_processing(struct kmem_cache *s,
trace(s, slab, object, 1);
set_orig_size(s, object, orig_size);
init_object(s, object, SLUB_RED_ACTIVE);
- return 1;
+ return true;
bad:
if (folio_test_slab(slab_folio(slab))) {
@@ -1388,7 +1442,7 @@ bad:
slab->inuse = slab->objects;
slab->freelist = NULL;
}
- return 0;
+ return false;
}
static inline int free_consistency_checks(struct kmem_cache *s,
@@ -1641,17 +1695,17 @@ static inline void setup_object_debug(struct kmem_cache *s, void *object) {}
static inline
void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) {}
-static inline int alloc_debug_processing(struct kmem_cache *s,
- struct slab *slab, void *object, int orig_size) { return 0; }
+static inline bool alloc_debug_processing(struct kmem_cache *s,
+ struct slab *slab, void *object, int orig_size) { return true; }
-static inline void free_debug_processing(
- struct kmem_cache *s, struct slab *slab,
- void *head, void *tail, int bulk_cnt,
- unsigned long addr) {}
+static inline bool free_debug_processing(struct kmem_cache *s,
+ struct slab *slab, void *head, void *tail, int *bulk_cnt,
+ unsigned long addr, depot_stack_handle_t handle) { return true; }
static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {}
static inline int check_object(struct kmem_cache *s, struct slab *slab,
void *object, u8 val) { return 1; }
+static inline depot_stack_handle_t set_track_prepare(void) { return 0; }
static inline void set_track(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr) {}
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
@@ -1676,11 +1730,13 @@ 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 */
/*
@@ -1800,6 +1856,8 @@ static inline struct slab *alloc_slab_page(gfp_t flags, int node,
slab = folio_slab(folio);
__folio_set_slab(folio);
+ /* Make the flag visible before any changes to folio->mapping */
+ smp_wmb();
if (page_is_pfmemalloc(folio_page(folio, 0)))
slab_set_pfmemalloc(slab);
@@ -1999,17 +2057,11 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab)
int order = folio_order(folio);
int pages = 1 << order;
- if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
- void *p;
-
- slab_pad_check(s, slab);
- for_each_object(p, s, slab_address(slab), slab->objects)
- check_object(s, slab, p, SLUB_RED_INACTIVE);
- }
-
__slab_clear_pfmemalloc(slab);
- __folio_clear_slab(folio);
folio->mapping = NULL;
+ /* Make the mapping reset visible before clearing the flag */
+ smp_wmb();
+ __folio_clear_slab(folio);
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += pages;
unaccount_slab(slab, order, s);
@@ -2025,9 +2077,17 @@ static void rcu_free_slab(struct rcu_head *h)
static void free_slab(struct kmem_cache *s, struct slab *slab)
{
- if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) {
+ if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
+ void *p;
+
+ slab_pad_check(s, slab);
+ for_each_object(p, s, slab_address(slab), slab->objects)
+ check_object(s, slab, p, SLUB_RED_INACTIVE);
+ }
+
+ if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU))
call_rcu(&slab->rcu_head, rcu_free_slab);
- } else
+ else
__free_slab(s, slab);
}
@@ -2214,7 +2274,7 @@ 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)
@@ -2329,6 +2389,8 @@ 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
@@ -2342,7 +2404,7 @@ 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)
{
@@ -2411,7 +2473,7 @@ static void init_kmem_cache_cpus(struct kmem_cache *s)
static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
void *freelist)
{
- enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE, M_FULL_NOLIST };
+ enum slab_modes { M_NONE, M_PARTIAL, M_FREE, M_FULL_NOLIST };
struct kmem_cache_node *n = get_node(s, slab_nid(slab));
int free_delta = 0;
enum slab_modes mode = M_NONE;
@@ -2487,14 +2549,6 @@ redo:
* acquire_slab() will see a slab that is frozen
*/
spin_lock_irqsave(&n->list_lock, flags);
- } else if (kmem_cache_debug_flags(s, SLAB_STORE_USER)) {
- mode = M_FULL;
- /*
- * This also ensures that the scanning of full
- * slabs from diagnostic functions will not see
- * any frozen slabs.
- */
- spin_lock_irqsave(&n->list_lock, flags);
} else {
mode = M_FULL_NOLIST;
}
@@ -2504,7 +2558,7 @@ redo:
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab")) {
- if (mode == M_PARTIAL || mode == M_FULL)
+ if (mode == M_PARTIAL)
spin_unlock_irqrestore(&n->list_lock, flags);
goto redo;
}
@@ -2518,10 +2572,6 @@ redo:
stat(s, DEACTIVATE_EMPTY);
discard_slab(s, slab);
stat(s, FREE_SLAB);
- } else if (mode == M_FULL) {
- add_full(s, n, slab);
- spin_unlock_irqrestore(&n->list_lock, flags);
- stat(s, DEACTIVATE_FULL);
} else if (mode == M_FULL_NOLIST) {
stat(s, DEACTIVATE_FULL);
}
@@ -2803,6 +2853,13 @@ 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.
@@ -2828,38 +2885,28 @@ static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
}
/* Supports checking bulk free of a constructed freelist */
-static noinline void free_debug_processing(
- struct kmem_cache *s, struct slab *slab,
- void *head, void *tail, int bulk_cnt,
- unsigned long addr)
+static inline bool free_debug_processing(struct kmem_cache *s,
+ struct slab *slab, void *head, void *tail, int *bulk_cnt,
+ unsigned long addr, depot_stack_handle_t handle)
{
- struct kmem_cache_node *n = get_node(s, slab_nid(slab));
- struct slab *slab_free = NULL;
+ bool checks_ok = false;
void *object = head;
int cnt = 0;
- unsigned long flags;
- bool checks_ok = false;
- depot_stack_handle_t handle = 0;
-
- if (s->flags & SLAB_STORE_USER)
- handle = set_track_prepare();
-
- spin_lock_irqsave(&n->list_lock, flags);
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
if (!check_slab(s, slab))
goto out;
}
- if (slab->inuse < bulk_cnt) {
+ if (slab->inuse < *bulk_cnt) {
slab_err(s, slab, "Slab has %d allocated objects but %d are to be freed\n",
- slab->inuse, bulk_cnt);
+ slab->inuse, *bulk_cnt);
goto out;
}
next_object:
- if (++cnt > bulk_cnt)
+ if (++cnt > *bulk_cnt)
goto out_cnt;
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
@@ -2881,61 +2928,22 @@ next_object:
checks_ok = true;
out_cnt:
- if (cnt != bulk_cnt)
+ if (cnt != *bulk_cnt) {
slab_err(s, slab, "Bulk free expected %d objects but found %d\n",
- bulk_cnt, cnt);
-
-out:
- if (checks_ok) {
- void *prior = slab->freelist;
-
- /* Perform the actual freeing while we still hold the locks */
- slab->inuse -= cnt;
- set_freepointer(s, tail, prior);
- slab->freelist = head;
-
- /*
- * If the slab is empty, and node's partial list is full,
- * it should be discarded anyway no matter it's on full or
- * partial list.
- */
- if (slab->inuse == 0 && n->nr_partial >= s->min_partial)
- slab_free = slab;
-
- if (!prior) {
- /* was on full list */
- remove_full(s, n, slab);
- if (!slab_free) {
- add_partial(n, slab, DEACTIVATE_TO_TAIL);
- stat(s, FREE_ADD_PARTIAL);
- }
- } else if (slab_free) {
- remove_partial(n, slab);
- stat(s, FREE_REMOVE_PARTIAL);
- }
+ *bulk_cnt, cnt);
+ *bulk_cnt = cnt;
}
- if (slab_free) {
- /*
- * Update the counters while still holding n->list_lock to
- * prevent spurious validation warnings
- */
- dec_slabs_node(s, slab_nid(slab_free), slab_free->objects);
- }
-
- spin_unlock_irqrestore(&n->list_lock, flags);
+out:
if (!checks_ok)
slab_fix(s, "Object at 0x%p not freed", object);
- if (slab_free) {
- stat(s, FREE_SLAB);
- free_slab(s, slab_free);
- }
+ return checks_ok;
}
#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 *))
{
@@ -2949,12 +2957,12 @@ 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 */
+#ifdef CONFIG_SLUB_DEBUG
static noinline void
slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
{
-#ifdef CONFIG_SLUB_DEBUG
static DEFINE_RATELIMIT_STATE(slub_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
int node;
@@ -2985,8 +2993,11 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
pr_warn(" node %d: slabs: %ld, objs: %ld, free: %ld\n",
node, nr_slabs, nr_objs, nr_free);
}
-#endif
}
+#else /* CONFIG_SLUB_DEBUG */
+static inline void
+slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) { }
+#endif
static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags)
{
@@ -2996,6 +3007,7 @@ 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.
@@ -3283,45 +3295,13 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
return p;
}
-/*
- * If the object has been wiped upon free, make sure it's fully initialized by
- * zeroing out freelist pointer.
- */
-static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
- void *obj)
-{
- if (unlikely(slab_want_init_on_free(s)) && obj)
- memset((void *)((char *)kasan_reset_tag(obj) + s->offset),
- 0, sizeof(void *));
-}
-
-/*
- * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
- * have the fastpath folded into their functions. So no function call
- * overhead for requests that can be satisfied on the fastpath.
- *
- * The fastpath works by first checking if the lockless freelist can be used.
- * If not then __slab_alloc is called for slow processing.
- *
- * Otherwise we can simply pick the next object from the lockless free list.
- */
-static __always_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru,
+static __always_inline void *__slab_alloc_node(struct kmem_cache *s,
gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
{
- void *object;
struct kmem_cache_cpu *c;
struct slab *slab;
unsigned long tid;
- struct obj_cgroup *objcg = NULL;
- bool init = false;
-
- s = slab_pre_alloc_hook(s, lru, &objcg, 1, gfpflags);
- if (!s)
- return NULL;
-
- object = kfence_alloc(s, orig_size, gfpflags);
- if (unlikely(object))
- goto out;
+ void *object;
redo:
/*
@@ -3391,22 +3371,95 @@ redo:
stat(s, ALLOC_FASTPATH);
}
+ 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
+ * zeroing out freelist pointer.
+ */
+static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
+ void *obj)
+{
+ if (unlikely(slab_want_init_on_free(s)) && obj)
+ memset((void *)((char *)kasan_reset_tag(obj) + s->offset),
+ 0, sizeof(void *));
+}
+
+/*
+ * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
+ * have the fastpath folded into their functions. So no function call
+ * overhead for requests that can be satisfied on the fastpath.
+ *
+ * The fastpath works by first checking if the lockless freelist can be used.
+ * If not then __slab_alloc is called for slow processing.
+ *
+ * Otherwise we can simply pick the next object from the lockless free list.
+ */
+static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru,
+ gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
+{
+ void *object;
+ struct obj_cgroup *objcg = NULL;
+ bool init = false;
+
+ s = slab_pre_alloc_hook(s, lru, &objcg, 1, gfpflags);
+ if (!s)
+ return NULL;
+
+ object = kfence_alloc(s, orig_size, gfpflags);
+ if (unlikely(object))
+ goto out;
+
+ object = __slab_alloc_node(s, gfpflags, node, addr, orig_size);
+
maybe_wipe_obj_freeptr(s, object);
init = slab_want_init_on_alloc(gfpflags, s);
out:
- slab_post_alloc_hook(s, objcg, gfpflags, 1, &object, init);
+ /*
+ * When init equals 'true', like for kzalloc() family, only
+ * @orig_size bytes might be zeroed instead of s->object_size
+ */
+ slab_post_alloc_hook(s, objcg, gfpflags, 1, &object, init, orig_size);
return object;
}
-static __always_inline void *slab_alloc(struct kmem_cache *s, struct list_lru *lru,
+static __fastpath_inline void *slab_alloc(struct kmem_cache *s, struct list_lru *lru,
gfp_t gfpflags, unsigned long addr, size_t orig_size)
{
return slab_alloc_node(s, lru, gfpflags, NUMA_NO_NODE, addr, orig_size);
}
-static __always_inline
+static __fastpath_inline
void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
gfp_t gfpflags)
{
@@ -3448,6 +3501,67 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
+static noinline void free_to_partial_list(
+ struct kmem_cache *s, struct slab *slab,
+ void *head, void *tail, int bulk_cnt,
+ unsigned long addr)
+{
+ struct kmem_cache_node *n = get_node(s, slab_nid(slab));
+ struct slab *slab_free = NULL;
+ int cnt = bulk_cnt;
+ unsigned long flags;
+ depot_stack_handle_t handle = 0;
+
+ if (s->flags & SLAB_STORE_USER)
+ handle = set_track_prepare();
+
+ spin_lock_irqsave(&n->list_lock, flags);
+
+ if (free_debug_processing(s, slab, head, tail, &cnt, addr, handle)) {
+ void *prior = slab->freelist;
+
+ /* Perform the actual freeing while we still hold the locks */
+ slab->inuse -= cnt;
+ set_freepointer(s, tail, prior);
+ slab->freelist = head;
+
+ /*
+ * If the slab is empty, and node's partial list is full,
+ * it should be discarded anyway no matter it's on full or
+ * partial list.
+ */
+ if (slab->inuse == 0 && n->nr_partial >= s->min_partial)
+ slab_free = slab;
+
+ if (!prior) {
+ /* was on full list */
+ remove_full(s, n, slab);
+ if (!slab_free) {
+ add_partial(n, slab, DEACTIVATE_TO_TAIL);
+ stat(s, FREE_ADD_PARTIAL);
+ }
+ } else if (slab_free) {
+ remove_partial(n, slab);
+ stat(s, FREE_REMOVE_PARTIAL);
+ }
+ }
+
+ if (slab_free) {
+ /*
+ * Update the counters while still holding n->list_lock to
+ * prevent spurious validation warnings
+ */
+ dec_slabs_node(s, slab_nid(slab_free), slab_free->objects);
+ }
+
+ spin_unlock_irqrestore(&n->list_lock, flags);
+
+ if (slab_free) {
+ stat(s, FREE_SLAB);
+ free_slab(s, slab_free);
+ }
+}
+
/*
* Slow path handling. This may still be called frequently since objects
* have a longer lifetime than the cpu slabs in most processing loads.
@@ -3473,8 +3587,8 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
if (kfence_free(head))
return;
- if (kmem_cache_debug(s)) {
- free_debug_processing(s, slab, head, tail, cnt, addr);
+ if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
+ free_to_partial_list(s, slab, head, tail, cnt, addr);
return;
}
@@ -3574,6 +3688,7 @@ 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.
@@ -3648,8 +3763,18 @@ 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,
+static __fastpath_inline void slab_free(struct kmem_cache *s, struct slab *slab,
void *head, void *tail, void **p, int cnt,
unsigned long addr)
{
@@ -3782,18 +3907,13 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
}
EXPORT_SYMBOL(kmem_cache_free_bulk);
-/* 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,
- void **p)
+#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)
{
struct kmem_cache_cpu *c;
int i;
- struct obj_cgroup *objcg = NULL;
- /* memcg and kmem_cache debug support */
- s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags);
- if (unlikely(!s))
- return false;
/*
* Drain objects in the per cpu slab, while disabling local
* IRQs, which protects against PREEMPT and interrupts
@@ -3847,19 +3967,72 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
local_unlock_irq(&s->cpu_slab->lock);
slub_put_cpu_ptr(s->cpu_slab);
- /*
- * memcg and kmem_cache debug support and memory initialization.
- * Done outside of the IRQ disabled fastpath loop.
- */
- slab_post_alloc_hook(s, objcg, flags, size, p,
- slab_want_init_on_alloc(flags, s));
return i;
+
error:
slub_put_cpu_ptr(s->cpu_slab);
- slab_post_alloc_hook(s, objcg, flags, i, p, false);
+ slab_post_alloc_hook(s, objcg, flags, i, p, false, s->object_size);
+ kmem_cache_free_bulk(s, i, p);
+ 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, s->object_size);
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,
+ void **p)
+{
+ int i;
+ struct obj_cgroup *objcg = NULL;
+
+ if (!size)
+ return 0;
+
+ /* memcg and kmem_cache debug support */
+ s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags);
+ if (unlikely(!s))
+ return 0;
+
+ i = __kmem_cache_alloc_bulk(s, flags, size, p, objcg);
+
+ /*
+ * memcg and kmem_cache debug support and memory initialization.
+ * Done outside of the IRQ disabled fastpath loop.
+ */
+ if (i != 0)
+ slab_post_alloc_hook(s, objcg, flags, size, p,
+ slab_want_init_on_alloc(flags, s), s->object_size);
+ return i;
+}
EXPORT_SYMBOL(kmem_cache_alloc_bulk);
@@ -3883,7 +4056,8 @@ EXPORT_SYMBOL(kmem_cache_alloc_bulk);
* take the list_lock.
*/
static unsigned int slub_min_order;
-static unsigned int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
+static unsigned int slub_max_order =
+ IS_ENABLED(CONFIG_SLUB_TINY) ? 1 : PAGE_ALLOC_COSTLY_ORDER;
static unsigned int slub_min_objects;
/*
@@ -4014,10 +4188,12 @@ 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 <
- KMALLOC_SHIFT_HIGH * sizeof(struct kmem_cache_cpu));
+ NR_KMALLOC_TYPES * KMALLOC_SHIFT_HIGH *
+ sizeof(struct kmem_cache_cpu));
/*
* Must align to double word boundary for the double cmpxchg
@@ -4033,6 +4209,12 @@ 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;
@@ -4095,7 +4277,9 @@ 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);
}
@@ -4202,7 +4386,8 @@ static int calculate_sizes(struct kmem_cache *s)
*/
s->inuse = size;
- if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) ||
+ if (slub_debug_orig_size(s) ||
+ (flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) ||
((flags & SLAB_RED_ZONE) && s->object_size < sizeof(void *)) ||
s->ctor) {
/*
@@ -4872,8 +5057,10 @@ 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 *
@@ -4924,7 +5111,7 @@ 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 +5369,7 @@ 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 */
@@ -5502,11 +5689,13 @@ static ssize_t cache_dma_show(struct kmem_cache *s, char *buf)
SLAB_ATTR_RO(cache_dma);
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
static ssize_t usersize_show(struct kmem_cache *s, char *buf)
{
return sysfs_emit(buf, "%u\n", s->usersize);
}
SLAB_ATTR_RO(usersize);
+#endif
static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
{
@@ -5586,7 +5775,21 @@ static ssize_t failslab_show(struct kmem_cache *s, char *buf)
{
return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_FAILSLAB));
}
-SLAB_ATTR_RO(failslab);
+
+static ssize_t failslab_store(struct kmem_cache *s, const char *buf,
+ size_t length)
+{
+ if (s->refcount > 1)
+ return -EINVAL;
+
+ if (buf[0] == '1')
+ WRITE_ONCE(s->flags, s->flags | SLAB_FAILSLAB);
+ else
+ WRITE_ONCE(s->flags, s->flags & ~SLAB_FAILSLAB);
+
+ return length;
+}
+SLAB_ATTR(failslab);
#endif
static ssize_t shrink_show(struct kmem_cache *s, char *buf)
@@ -5803,7 +6006,9 @@ static struct attribute *slab_attrs[] = {
#ifdef CONFIG_FAILSLAB
&failslab_attr.attr,
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
&usersize_attr.attr,
+#endif
#ifdef CONFIG_KFENCE
&skip_kfence_attr.attr,
#endif
@@ -5920,11 +6125,6 @@ static int sysfs_slab_add(struct kmem_cache *s)
struct kset *kset = cache_kset(s);
int unmergeable = slab_unmergeable(s);
- if (!kset) {
- kobject_init(&s->kobj, &slab_ktype);
- return 0;
- }
-
if (!unmergeable && disable_higher_order_debug &&
(slub_debug & DEBUG_METADATA_FLAGS))
unmergeable = 1;
@@ -6054,9 +6254,8 @@ static int __init slab_sysfs_init(void)
mutex_unlock(&slab_mutex);
return 0;
}
-
-__initcall(slab_sysfs_init);
-#endif /* CONFIG_SYSFS */
+late_initcall(slab_sysfs_init);
+#endif /* SLAB_SUPPORTS_SYSFS */
#if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS)
static int slab_debugfs_show(struct seq_file *seq, void *v)
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 0fffaeedee76..cfaeaea71042 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -157,9 +157,11 @@ static unsigned long read_obj(const char *name)
{
FILE *f = fopen(name, "r");
- if (!f)
+ if (!f) {
buffer[0] = 0;
- else {
+ if (errno == EACCES)
+ fatal("%s, Try using superuser\n", strerror(errno));
+ } else {
if (!fgets(buffer, sizeof(buffer), f))
buffer[0] = 0;
fclose(f);