linux_dsm_epyc7002/include/linux/slab.h

692 lines
21 KiB
C
Raw Normal View History

/*
* Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk).
*
* (C) SGI 2006, Christoph Lameter
* Cleaned up and restructured to ease the addition of alternative
* implementations of SLAB allocators.
* (C) Linux Foundation 2008-2013
* Unified interface for all slab allocators
*/
#ifndef _LINUX_SLAB_H
#define _LINUX_SLAB_H
#include <linux/gfp.h>
#include <linux/types.h>
#include <linux/workqueue.h>
/*
* Flags to pass to kmem_cache_create().
* The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set.
*/
#define SLAB_CONSISTENCY_CHECKS 0x00000100UL /* DEBUG: Perform (expensive) checks on alloc/free */
#define SLAB_RED_ZONE 0x00000400UL /* DEBUG: Red zone objs in a cache */
#define SLAB_POISON 0x00000800UL /* DEBUG: Poison objects */
#define SLAB_HWCACHE_ALIGN 0x00002000UL /* Align objs on cache lines */
#define SLAB_CACHE_DMA 0x00004000UL /* Use GFP_DMA memory */
#define SLAB_STORE_USER 0x00010000UL /* DEBUG: Store the last owner for bug hunting */
#define SLAB_PANIC 0x00040000UL /* Panic if kmem_cache_create() fails */
/*
* SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
*
* This delays freeing the SLAB page by a grace period, it does _NOT_
* delay object freeing. This means that if you do kmem_cache_free()
* that memory location is free to be reused at any time. Thus it may
* be possible to see another object there in the same RCU grace period.
*
* This feature only ensures the memory location backing the object
* stays valid, the trick to using this is relying on an independent
* object validation pass. Something like:
*
* rcu_read_lock()
* again:
* obj = lockless_lookup(key);
* if (obj) {
* if (!try_get_ref(obj)) // might fail for free objects
* goto again;
*
* if (obj->key != key) { // not the object we expected
* put_ref(obj);
* goto again;
* }
* }
* rcu_read_unlock();
*
* This is useful if we need to approach a kernel structure obliquely,
* from its address obtained without the usual locking. We can lock
* the structure to stabilize it and check it's still at the given address,
* only if we can be sure that the memory has not been meanwhile reused
* for some other kind of object (which our subsystem's lock might corrupt).
*
* rcu_read_lock before reading the address, then rcu_read_unlock after
* taking the spinlock within the structure expected at that address.
*
* Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
*/
#define SLAB_TYPESAFE_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */
[PATCH] cpuset memory spread slab cache implementation Provide the slab cache infrastructure to support cpuset memory spreading. See the previous patches, cpuset_mem_spread, for an explanation of cpuset memory spreading. This patch provides a slab cache SLAB_MEM_SPREAD flag. If set in the kmem_cache_create() call defining a slab cache, then any task marked with the process state flag PF_MEMSPREAD will spread memory page allocations for that cache over all the allowed nodes, instead of preferring the local (faulting) node. On systems not configured with CONFIG_NUMA, this results in no change to the page allocation code path for slab caches. On systems with cpusets configured in the kernel, but the "memory_spread" cpuset option not enabled for the current tasks cpuset, this adds a call to a cpuset routine and failed bit test of the processor state flag PF_SPREAD_SLAB. For tasks so marked, a second inline test is done for the slab cache flag SLAB_MEM_SPREAD, and if that is set and if the allocation is not in_interrupt(), this adds a call to to a cpuset routine that computes which of the tasks mems_allowed nodes should be preferred for this allocation. ==> This patch adds another hook into the performance critical code path to allocating objects from the slab cache, in the ____cache_alloc() chunk, below. The next patch optimizes this hook, reducing the impact of the combined mempolicy plus memory spreading hooks on this critical code path to a single check against the tasks task_struct flags word. This patch provides the generic slab flags and logic needed to apply memory spreading to a particular slab. A subsequent patch will mark a few specific slab caches for this placement policy. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 18:16:07 +07:00
#define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */
SLUB core This is a new slab allocator which was motivated by the complexity of the existing code in mm/slab.c. It attempts to address a variety of concerns with the existing implementation. A. Management of object queues A particular concern was the complex management of the numerous object queues in SLAB. SLUB has no such queues. Instead we dedicate a slab for each allocating CPU and use objects from a slab directly instead of queueing them up. B. Storage overhead of object queues SLAB Object queues exist per node, per CPU. The alien cache queue even has a queue array that contain a queue for each processor on each node. For very large systems the number of queues and the number of objects that may be caught in those queues grows exponentially. On our systems with 1k nodes / processors we have several gigabytes just tied up for storing references to objects for those queues This does not include the objects that could be on those queues. One fears that the whole memory of the machine could one day be consumed by those queues. C. SLAB meta data overhead SLAB has overhead at the beginning of each slab. This means that data cannot be naturally aligned at the beginning of a slab block. SLUB keeps all meta data in the corresponding page_struct. Objects can be naturally aligned in the slab. F.e. a 128 byte object will be aligned at 128 byte boundaries and can fit tightly into a 4k page with no bytes left over. SLAB cannot do this. D. SLAB has a complex cache reaper SLUB does not need a cache reaper for UP systems. On SMP systems the per CPU slab may be pushed back into partial list but that operation is simple and does not require an iteration over a list of objects. SLAB expires per CPU, shared and alien object queues during cache reaping which may cause strange hold offs. E. SLAB has complex NUMA policy layer support SLUB pushes NUMA policy handling into the page allocator. This means that allocation is coarser (SLUB does interleave on a page level) but that situation was also present before 2.6.13. SLABs application of policies to individual slab objects allocated in SLAB is certainly a performance concern due to the frequent references to memory policies which may lead a sequence of objects to come from one node after another. SLUB will get a slab full of objects from one node and then will switch to the next. F. Reduction of the size of partial slab lists SLAB has per node partial lists. This means that over time a large number of partial slabs may accumulate on those lists. These can only be reused if allocator occur on specific nodes. SLUB has a global pool of partial slabs and will consume slabs from that pool to decrease fragmentation. G. Tunables SLAB has sophisticated tuning abilities for each slab cache. One can manipulate the queue sizes in detail. However, filling the queues still requires the uses of the spin lock to check out slabs. SLUB has a global parameter (min_slab_order) for tuning. Increasing the minimum slab order can decrease the locking overhead. The bigger the slab order the less motions of pages between per CPU and partial lists occur and the better SLUB will be scaling. G. Slab merging We often have slab caches with similar parameters. SLUB detects those on boot up and merges them into the corresponding general caches. This leads to more effective memory use. About 50% of all caches can be eliminated through slab merging. This will also decrease slab fragmentation because partial allocated slabs can be filled up again. Slab merging can be switched off by specifying slub_nomerge on boot up. Note that merging can expose heretofore unknown bugs in the kernel because corrupted objects may now be placed differently and corrupt differing neighboring objects. Enable sanity checks to find those. H. Diagnostics The current slab diagnostics are difficult to use and require a recompilation of the kernel. SLUB contains debugging code that is always available (but is kept out of the hot code paths). SLUB diagnostics can be enabled via the "slab_debug" option. Parameters can be specified to select a single or a group of slab caches for diagnostics. This means that the system is running with the usual performance and it is much more likely that race conditions can be reproduced. I. Resiliency If basic sanity checks are on then SLUB is capable of detecting common error conditions and recover as best as possible to allow the system to continue. J. Tracing Tracing can be enabled via the slab_debug=T,<slabcache> option during boot. SLUB will then protocol all actions on that slabcache and dump the object contents on free. K. On demand DMA cache creation. Generally DMA caches are not needed. If a kmalloc is used with __GFP_DMA then just create this single slabcache that is needed. For systems that have no ZONE_DMA requirement the support is completely eliminated. L. Performance increase Some benchmarks have shown speed improvements on kernbench in the range of 5-10%. The locking overhead of slub is based on the underlying base allocation size. If we can reliably allocate larger order pages then it is possible to increase slub performance much further. The anti-fragmentation patches may enable further performance increases. Tested on: i386 UP + SMP, x86_64 UP + SMP + NUMA emulation, IA64 NUMA + Simulator SLUB Boot options slub_nomerge Disable merging of slabs slub_min_order=x Require a minimum order for slab caches. This increases the managed chunk size and therefore reduces meta data and locking overhead. slub_min_objects=x Mininum objects per slab. Default is 8. slub_max_order=x Avoid generating slabs larger than order specified. slub_debug Enable all diagnostics for all caches slub_debug=<options> Enable selective options for all caches slub_debug=<o>,<cache> Enable selective options for a certain set of caches Available Debug options F Double Free checking, sanity and resiliency R Red zoning P Object / padding poisoning U Track last free / alloc T Trace all allocs / frees (only use for individual slabs). To use SLUB: Apply this patch and then select SLUB as the default slab allocator. [hugh@veritas.com: fix an oops-causing locking error] [akpm@linux-foundation.org: various stupid cleanups and small fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-07 04:49:36 +07:00
#define SLAB_TRACE 0x00200000UL /* Trace allocations and frees */
/* Flag to prevent checks on free */
#ifdef CONFIG_DEBUG_OBJECTS
# define SLAB_DEBUG_OBJECTS 0x00400000UL
#else
# define SLAB_DEBUG_OBJECTS 0x00000000UL
#endif
#define SLAB_NOLEAKTRACE 0x00800000UL /* Avoid kmemleak tracing */
2008-05-31 20:56:17 +07:00
/* Don't track use of uninitialized memory */
#ifdef CONFIG_KMEMCHECK
# define SLAB_NOTRACK 0x01000000UL
#else
# define SLAB_NOTRACK 0x00000000UL
#endif
#ifdef CONFIG_FAILSLAB
# define SLAB_FAILSLAB 0x02000000UL /* Fault injection mark */
#else
# define SLAB_FAILSLAB 0x00000000UL
#endif
#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
# define SLAB_ACCOUNT 0x04000000UL /* Account to memcg */
#else
# define SLAB_ACCOUNT 0x00000000UL
#endif
2008-05-31 20:56:17 +07:00
#ifdef CONFIG_KASAN
#define SLAB_KASAN 0x08000000UL
#else
#define SLAB_KASAN 0x00000000UL
#endif
/* The following flags affect the page allocator grouping pages by mobility */
#define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */
#define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */
/*
* ZERO_SIZE_PTR will be returned for zero sized kmalloc requests.
*
* Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault.
*
* ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can.
* Both make kfree a no-op.
*/
#define ZERO_SIZE_PTR ((void *)16)
#define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \
(unsigned long)ZERO_SIZE_PTR)
#include <linux/kmemleak.h>
mm: slub: add kernel address sanitizer support for slub allocator With this patch kasan will be able to catch bugs in memory allocated by slub. Initially all objects in newly allocated slab page, marked as redzone. Later, when allocation of slub object happens, requested by caller number of bytes marked as accessible, and the rest of the object (including slub's metadata) marked as redzone (inaccessible). We also mark object as accessible if ksize was called for this object. There is some places in kernel where ksize function is called to inquire size of really allocated area. Such callers could validly access whole allocated memory, so it should be marked as accessible. Code in slub.c and slab_common.c files could validly access to object's metadata, so instrumentation for this files are disabled. Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com> Signed-off-by: Dmitry Chernenkov <dmitryc@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Konstantin Serebryany <kcc@google.com> Signed-off-by: Andrey Konovalov <adech.fo@gmail.com> Cc: Yuri Gribov <tetra2005@gmail.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-14 05:39:42 +07:00
#include <linux/kasan.h>
struct mem_cgroup;
/*
* struct kmem_cache related prototypes
*/
void __init kmem_cache_init(void);
bool slab_is_available(void);
struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
unsigned long,
void (*)(void *));
void kmem_cache_destroy(struct kmem_cache *);
int kmem_cache_shrink(struct kmem_cache *);
void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
void memcg_deactivate_kmem_caches(struct mem_cgroup *);
void memcg_destroy_kmem_caches(struct mem_cgroup *);
/*
* Please use this macro to create slab caches. Simply specify the
* name of the structure and maybe some flags that are listed above.
*
* The alignment of the struct determines object alignment. If you
* f.e. add ____cacheline_aligned_in_smp to the struct declaration
* then the objects will be properly aligned in SMP configurations.
*/
#define KMEM_CACHE(__struct, __flags) kmem_cache_create(#__struct,\
sizeof(struct __struct), __alignof__(struct __struct),\
(__flags), NULL)
/*
* Common kmalloc functions provided by all allocators
*/
void * __must_check __krealloc(const void *, size_t, gfp_t);
void * __must_check krealloc(const void *, size_t, gfp_t);
void kfree(const void *);
void kzfree(const void *);
size_t ksize(const void *);
#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
const char *__check_heap_object(const void *ptr, unsigned long n,
struct page *page);
#else
static inline const char *__check_heap_object(const void *ptr,
unsigned long n,
struct page *page)
{
return NULL;
}
#endif
slab: Handle ARCH_DMA_MINALIGN correctly James Hogan hit boot problems in next-20130204 on Meta: META213-Thread0 DSP [LogF] kobject (4fc03980): tried to init an initialized object, something is seriously wrong. META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] Call trace: META213-Thread0 DSP [LogF] [<4000888c>] _show_stack+0x68/0x7c META213-Thread0 DSP [LogF] [<400088b4>] _dump_stack+0x14/0x28 META213-Thread0 DSP [LogF] [<40103794>] _kobject_init+0x58/0x9c META213-Thread0 DSP [LogF] [<40103810>] _kobject_create+0x38/0x64 META213-Thread0 DSP [LogF] [<40103eac>] _kobject_create_and_add+0x14/0x8c META213-Thread0 DSP [LogF] [<40190ac4>] _mnt_init+0xd8/0x220 META213-Thread0 DSP [LogF] [<40190508>] _vfs_caches_init+0xb0/0x160 META213-Thread0 DSP [LogF] [<401851f4>] _start_kernel+0x274/0x340 META213-Thread0 DSP [LogF] [<40188424>] _metag_start_kernel+0x58/0x6c META213-Thread0 DSP [LogF] [<40000044>] __start+0x44/0x48 META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] devtmpfs: initialized META213-Thread0 DSP [LogF] L2 Cache: Not present META213-Thread0 DSP [LogF] BUG: failure at fs/sysfs/dir.c:736/sysfs_read_ns_type()! META213-Thread0 DSP [LogF] Kernel panic - not syncing: BUG! META213-Thread0 DSP [Thread Exit] Thread has exited - return code = 4294967295 And bisected the problem to commit 95a05b4 ("slab: Common constants for kmalloc boundaries"). As it turns out, a fixed KMALLOC_SHIFT_LOW does not work for arches with higher alignment requirements. Determine KMALLOC_SHIFT_LOW from ARCH_DMA_MINALIGN instead. Reported-and-tested-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
2013-02-05 23:36:47 +07:00
/*
* Some archs want to perform DMA into kmalloc caches and need a guaranteed
* alignment larger than the alignment of a 64-bit integer.
* Setting ARCH_KMALLOC_MINALIGN in arch headers allows that.
*/
#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8
#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN
#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN
#define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN)
#else
#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
#endif
slab.h: sprinkle __assume_aligned attributes The various allocators return aligned memory. Telling the compiler that allows it to generate better code in many cases, for example when the return value is immediately passed to memset(). Some code does become larger, but at least we win twice as much as we lose: $ scripts/bloat-o-meter /tmp/vmlinux vmlinux add/remove: 0/0 grow/shrink: 13/52 up/down: 995/-2140 (-1145) An example of the different (and smaller) code can be seen in mm_alloc(). Before: : 48 8d 78 08 lea 0x8(%rax),%rdi : 48 89 c1 mov %rax,%rcx : 48 89 c2 mov %rax,%rdx : 48 c7 00 00 00 00 00 movq $0x0,(%rax) : 48 c7 80 48 03 00 00 movq $0x0,0x348(%rax) : 00 00 00 00 : 31 c0 xor %eax,%eax : 48 83 e7 f8 and $0xfffffffffffffff8,%rdi : 48 29 f9 sub %rdi,%rcx : 81 c1 50 03 00 00 add $0x350,%ecx : c1 e9 03 shr $0x3,%ecx : f3 48 ab rep stos %rax,%es:(%rdi) After: : 48 89 c2 mov %rax,%rdx : b9 6a 00 00 00 mov $0x6a,%ecx : 31 c0 xor %eax,%eax : 48 89 d7 mov %rdx,%rdi : f3 48 ab rep stos %rax,%es:(%rdi) So gcc's strategy is to do two possibly (but not really, of course) unaligned stores to the first and last word, then do an aligned rep stos covering the middle part with a little overlap. Maybe arches which do not allow unaligned stores gain even more. I don't know if gcc can actually make use of alignments greater than 8 for anything, so one could probably drop the __assume_xyz_alignment macros and just use __assume_aligned(8). The increases in code size are mostly caused by gcc deciding to opencode strlen() using the check-four-bytes-at-a-time trick when it knows the buffer is sufficiently aligned (one function grew by 200 bytes). Now it turns out that many of these strlen() calls showing up were in fact redundant, and they're gone from -next. Applying the two patches to next-20151001 bloat-o-meter instead says add/remove: 0/0 grow/shrink: 6/52 up/down: 244/-2140 (-1896) Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-21 06:56:48 +07:00
/*
* Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment.
* Intended for arches that get misalignment faults even for 64 bit integer
* aligned buffers.
*/
#ifndef ARCH_SLAB_MINALIGN
#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
#endif
/*
* kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned
* pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN
* aligned pointers.
*/
#define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN)
#define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN)
#define __assume_page_alignment __assume_aligned(PAGE_SIZE)
/*
* Kmalloc array related definitions
*/
#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.
*/
#define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \
(MAX_ORDER + PAGE_SHIFT - 1) : 25)
#define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH
slab: Handle ARCH_DMA_MINALIGN correctly James Hogan hit boot problems in next-20130204 on Meta: META213-Thread0 DSP [LogF] kobject (4fc03980): tried to init an initialized object, something is seriously wrong. META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] Call trace: META213-Thread0 DSP [LogF] [<4000888c>] _show_stack+0x68/0x7c META213-Thread0 DSP [LogF] [<400088b4>] _dump_stack+0x14/0x28 META213-Thread0 DSP [LogF] [<40103794>] _kobject_init+0x58/0x9c META213-Thread0 DSP [LogF] [<40103810>] _kobject_create+0x38/0x64 META213-Thread0 DSP [LogF] [<40103eac>] _kobject_create_and_add+0x14/0x8c META213-Thread0 DSP [LogF] [<40190ac4>] _mnt_init+0xd8/0x220 META213-Thread0 DSP [LogF] [<40190508>] _vfs_caches_init+0xb0/0x160 META213-Thread0 DSP [LogF] [<401851f4>] _start_kernel+0x274/0x340 META213-Thread0 DSP [LogF] [<40188424>] _metag_start_kernel+0x58/0x6c META213-Thread0 DSP [LogF] [<40000044>] __start+0x44/0x48 META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] devtmpfs: initialized META213-Thread0 DSP [LogF] L2 Cache: Not present META213-Thread0 DSP [LogF] BUG: failure at fs/sysfs/dir.c:736/sysfs_read_ns_type()! META213-Thread0 DSP [LogF] Kernel panic - not syncing: BUG! META213-Thread0 DSP [Thread Exit] Thread has exited - return code = 4294967295 And bisected the problem to commit 95a05b4 ("slab: Common constants for kmalloc boundaries"). As it turns out, a fixed KMALLOC_SHIFT_LOW does not work for arches with higher alignment requirements. Determine KMALLOC_SHIFT_LOW from ARCH_DMA_MINALIGN instead. Reported-and-tested-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
2013-02-05 23:36:47 +07:00
#ifndef KMALLOC_SHIFT_LOW
#define KMALLOC_SHIFT_LOW 5
slab: Handle ARCH_DMA_MINALIGN correctly James Hogan hit boot problems in next-20130204 on Meta: META213-Thread0 DSP [LogF] kobject (4fc03980): tried to init an initialized object, something is seriously wrong. META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] Call trace: META213-Thread0 DSP [LogF] [<4000888c>] _show_stack+0x68/0x7c META213-Thread0 DSP [LogF] [<400088b4>] _dump_stack+0x14/0x28 META213-Thread0 DSP [LogF] [<40103794>] _kobject_init+0x58/0x9c META213-Thread0 DSP [LogF] [<40103810>] _kobject_create+0x38/0x64 META213-Thread0 DSP [LogF] [<40103eac>] _kobject_create_and_add+0x14/0x8c META213-Thread0 DSP [LogF] [<40190ac4>] _mnt_init+0xd8/0x220 META213-Thread0 DSP [LogF] [<40190508>] _vfs_caches_init+0xb0/0x160 META213-Thread0 DSP [LogF] [<401851f4>] _start_kernel+0x274/0x340 META213-Thread0 DSP [LogF] [<40188424>] _metag_start_kernel+0x58/0x6c META213-Thread0 DSP [LogF] [<40000044>] __start+0x44/0x48 META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] devtmpfs: initialized META213-Thread0 DSP [LogF] L2 Cache: Not present META213-Thread0 DSP [LogF] BUG: failure at fs/sysfs/dir.c:736/sysfs_read_ns_type()! META213-Thread0 DSP [LogF] Kernel panic - not syncing: BUG! META213-Thread0 DSP [Thread Exit] Thread has exited - return code = 4294967295 And bisected the problem to commit 95a05b4 ("slab: Common constants for kmalloc boundaries"). As it turns out, a fixed KMALLOC_SHIFT_LOW does not work for arches with higher alignment requirements. Determine KMALLOC_SHIFT_LOW from ARCH_DMA_MINALIGN instead. Reported-and-tested-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
2013-02-05 23:36:47 +07:00
#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)
mm, slab: make sure that KMALLOC_MAX_SIZE will fit into MAX_ORDER Andrey Konovalov has reported the following warning triggered by the syzkaller fuzzer. WARNING: CPU: 1 PID: 9935 at mm/page_alloc.c:3511 __alloc_pages_nodemask+0x159c/0x1e20 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 9935 Comm: syz-executor0 Not tainted 4.9.0-rc7+ #34 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __alloc_pages_slowpath mm/page_alloc.c:3511 __alloc_pages_nodemask+0x159c/0x1e20 mm/page_alloc.c:3781 alloc_pages_current+0x1c7/0x6b0 mm/mempolicy.c:2072 alloc_pages include/linux/gfp.h:469 kmalloc_order+0x1f/0x70 mm/slab_common.c:1015 kmalloc_order_trace+0x1f/0x160 mm/slab_common.c:1026 kmalloc_large include/linux/slab.h:422 __kmalloc+0x210/0x2d0 mm/slub.c:3723 kmalloc include/linux/slab.h:495 ep_write_iter+0x167/0xb50 drivers/usb/gadget/legacy/inode.c:664 new_sync_write fs/read_write.c:499 __vfs_write+0x483/0x760 fs/read_write.c:512 vfs_write+0x170/0x4e0 fs/read_write.c:560 SYSC_write fs/read_write.c:607 SyS_write+0xfb/0x230 fs/read_write.c:599 entry_SYSCALL_64_fastpath+0x1f/0xc2 The issue is caused by a lack of size check for the request size in ep_write_iter which should be fixed. It, however, points to another problem, that SLUB defines KMALLOC_MAX_SIZE too large because the its KMALLOC_SHIFT_MAX is (MAX_ORDER + PAGE_SHIFT) which means that the resulting page allocator request might be MAX_ORDER which is too large (see __alloc_pages_slowpath). The same applies to the SLOB allocator which allows even larger sizes. Make sure that they are capped properly and never request more than MAX_ORDER order. Link: http://lkml.kernel.org/r/20161220130659.16461-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Andrey Konovalov <andreyknvl@google.com> Acked-by: Christoph Lameter <cl@linux.com> Cc: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-11 07:57:27 +07:00
#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1)
slab: Handle ARCH_DMA_MINALIGN correctly James Hogan hit boot problems in next-20130204 on Meta: META213-Thread0 DSP [LogF] kobject (4fc03980): tried to init an initialized object, something is seriously wrong. META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] Call trace: META213-Thread0 DSP [LogF] [<4000888c>] _show_stack+0x68/0x7c META213-Thread0 DSP [LogF] [<400088b4>] _dump_stack+0x14/0x28 META213-Thread0 DSP [LogF] [<40103794>] _kobject_init+0x58/0x9c META213-Thread0 DSP [LogF] [<40103810>] _kobject_create+0x38/0x64 META213-Thread0 DSP [LogF] [<40103eac>] _kobject_create_and_add+0x14/0x8c META213-Thread0 DSP [LogF] [<40190ac4>] _mnt_init+0xd8/0x220 META213-Thread0 DSP [LogF] [<40190508>] _vfs_caches_init+0xb0/0x160 META213-Thread0 DSP [LogF] [<401851f4>] _start_kernel+0x274/0x340 META213-Thread0 DSP [LogF] [<40188424>] _metag_start_kernel+0x58/0x6c META213-Thread0 DSP [LogF] [<40000044>] __start+0x44/0x48 META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] devtmpfs: initialized META213-Thread0 DSP [LogF] L2 Cache: Not present META213-Thread0 DSP [LogF] BUG: failure at fs/sysfs/dir.c:736/sysfs_read_ns_type()! META213-Thread0 DSP [LogF] Kernel panic - not syncing: BUG! META213-Thread0 DSP [Thread Exit] Thread has exited - return code = 4294967295 And bisected the problem to commit 95a05b4 ("slab: Common constants for kmalloc boundaries"). As it turns out, a fixed KMALLOC_SHIFT_LOW does not work for arches with higher alignment requirements. Determine KMALLOC_SHIFT_LOW from ARCH_DMA_MINALIGN instead. Reported-and-tested-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
2013-02-05 23:36:47 +07:00
#ifndef KMALLOC_SHIFT_LOW
#define KMALLOC_SHIFT_LOW 3
#endif
slab: Handle ARCH_DMA_MINALIGN correctly James Hogan hit boot problems in next-20130204 on Meta: META213-Thread0 DSP [LogF] kobject (4fc03980): tried to init an initialized object, something is seriously wrong. META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] Call trace: META213-Thread0 DSP [LogF] [<4000888c>] _show_stack+0x68/0x7c META213-Thread0 DSP [LogF] [<400088b4>] _dump_stack+0x14/0x28 META213-Thread0 DSP [LogF] [<40103794>] _kobject_init+0x58/0x9c META213-Thread0 DSP [LogF] [<40103810>] _kobject_create+0x38/0x64 META213-Thread0 DSP [LogF] [<40103eac>] _kobject_create_and_add+0x14/0x8c META213-Thread0 DSP [LogF] [<40190ac4>] _mnt_init+0xd8/0x220 META213-Thread0 DSP [LogF] [<40190508>] _vfs_caches_init+0xb0/0x160 META213-Thread0 DSP [LogF] [<401851f4>] _start_kernel+0x274/0x340 META213-Thread0 DSP [LogF] [<40188424>] _metag_start_kernel+0x58/0x6c META213-Thread0 DSP [LogF] [<40000044>] __start+0x44/0x48 META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] devtmpfs: initialized META213-Thread0 DSP [LogF] L2 Cache: Not present META213-Thread0 DSP [LogF] BUG: failure at fs/sysfs/dir.c:736/sysfs_read_ns_type()! META213-Thread0 DSP [LogF] Kernel panic - not syncing: BUG! META213-Thread0 DSP [Thread Exit] Thread has exited - return code = 4294967295 And bisected the problem to commit 95a05b4 ("slab: Common constants for kmalloc boundaries"). As it turns out, a fixed KMALLOC_SHIFT_LOW does not work for arches with higher alignment requirements. Determine KMALLOC_SHIFT_LOW from ARCH_DMA_MINALIGN instead. Reported-and-tested-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
2013-02-05 23:36:47 +07:00
#endif
#ifdef CONFIG_SLOB
/*
* SLOB passes all requests larger than one page to the page allocator.
* No kmalloc array is necessary since objects of different sizes can
* be allocated from the same page.
*/
#define KMALLOC_SHIFT_HIGH PAGE_SHIFT
mm, slab: make sure that KMALLOC_MAX_SIZE will fit into MAX_ORDER Andrey Konovalov has reported the following warning triggered by the syzkaller fuzzer. WARNING: CPU: 1 PID: 9935 at mm/page_alloc.c:3511 __alloc_pages_nodemask+0x159c/0x1e20 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 9935 Comm: syz-executor0 Not tainted 4.9.0-rc7+ #34 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __alloc_pages_slowpath mm/page_alloc.c:3511 __alloc_pages_nodemask+0x159c/0x1e20 mm/page_alloc.c:3781 alloc_pages_current+0x1c7/0x6b0 mm/mempolicy.c:2072 alloc_pages include/linux/gfp.h:469 kmalloc_order+0x1f/0x70 mm/slab_common.c:1015 kmalloc_order_trace+0x1f/0x160 mm/slab_common.c:1026 kmalloc_large include/linux/slab.h:422 __kmalloc+0x210/0x2d0 mm/slub.c:3723 kmalloc include/linux/slab.h:495 ep_write_iter+0x167/0xb50 drivers/usb/gadget/legacy/inode.c:664 new_sync_write fs/read_write.c:499 __vfs_write+0x483/0x760 fs/read_write.c:512 vfs_write+0x170/0x4e0 fs/read_write.c:560 SYSC_write fs/read_write.c:607 SyS_write+0xfb/0x230 fs/read_write.c:599 entry_SYSCALL_64_fastpath+0x1f/0xc2 The issue is caused by a lack of size check for the request size in ep_write_iter which should be fixed. It, however, points to another problem, that SLUB defines KMALLOC_MAX_SIZE too large because the its KMALLOC_SHIFT_MAX is (MAX_ORDER + PAGE_SHIFT) which means that the resulting page allocator request might be MAX_ORDER which is too large (see __alloc_pages_slowpath). The same applies to the SLOB allocator which allows even larger sizes. Make sure that they are capped properly and never request more than MAX_ORDER order. Link: http://lkml.kernel.org/r/20161220130659.16461-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Andrey Konovalov <andreyknvl@google.com> Acked-by: Christoph Lameter <cl@linux.com> Cc: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-11 07:57:27 +07:00
#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1)
#ifndef KMALLOC_SHIFT_LOW
#define KMALLOC_SHIFT_LOW 3
#endif
#endif
/* Maximum allocatable size */
#define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX)
/* Maximum size for which we actually use a slab cache */
#define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH)
/* Maximum order allocatable via the slab allocagtor */
#define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT)
/*
* Kmalloc subsystem.
*/
slab: Handle ARCH_DMA_MINALIGN correctly James Hogan hit boot problems in next-20130204 on Meta: META213-Thread0 DSP [LogF] kobject (4fc03980): tried to init an initialized object, something is seriously wrong. META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] Call trace: META213-Thread0 DSP [LogF] [<4000888c>] _show_stack+0x68/0x7c META213-Thread0 DSP [LogF] [<400088b4>] _dump_stack+0x14/0x28 META213-Thread0 DSP [LogF] [<40103794>] _kobject_init+0x58/0x9c META213-Thread0 DSP [LogF] [<40103810>] _kobject_create+0x38/0x64 META213-Thread0 DSP [LogF] [<40103eac>] _kobject_create_and_add+0x14/0x8c META213-Thread0 DSP [LogF] [<40190ac4>] _mnt_init+0xd8/0x220 META213-Thread0 DSP [LogF] [<40190508>] _vfs_caches_init+0xb0/0x160 META213-Thread0 DSP [LogF] [<401851f4>] _start_kernel+0x274/0x340 META213-Thread0 DSP [LogF] [<40188424>] _metag_start_kernel+0x58/0x6c META213-Thread0 DSP [LogF] [<40000044>] __start+0x44/0x48 META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] devtmpfs: initialized META213-Thread0 DSP [LogF] L2 Cache: Not present META213-Thread0 DSP [LogF] BUG: failure at fs/sysfs/dir.c:736/sysfs_read_ns_type()! META213-Thread0 DSP [LogF] Kernel panic - not syncing: BUG! META213-Thread0 DSP [Thread Exit] Thread has exited - return code = 4294967295 And bisected the problem to commit 95a05b4 ("slab: Common constants for kmalloc boundaries"). As it turns out, a fixed KMALLOC_SHIFT_LOW does not work for arches with higher alignment requirements. Determine KMALLOC_SHIFT_LOW from ARCH_DMA_MINALIGN instead. Reported-and-tested-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Pekka Enberg <penberg@kernel.org>
2013-02-05 23:36:47 +07:00
#ifndef KMALLOC_MIN_SIZE
#define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW)
#endif
/*
* This restriction comes from byte sized index implementation.
* Page size is normally 2^12 bytes and, in this case, if we want to use
* byte sized index which can represent 2^8 entries, the size of the object
* should be equal or greater to 2^12 / 2^8 = 2^4 = 16.
* If minimum size of kmalloc is less than 16, we use it as minimum object
* size and give up to use byte sized index.
*/
#define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \
(KMALLOC_MIN_SIZE) : 16)
#ifndef CONFIG_SLOB
extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
#ifdef CONFIG_ZONE_DMA
extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
#endif
/*
* Figure out which kmalloc slab an allocation of a certain size
* belongs to.
* 0 = zero alloc
* 1 = 65 .. 96 bytes
* 2 = 129 .. 192 bytes
* n = 2^(n-1)+1 .. 2^n
*/
static __always_inline int kmalloc_index(size_t size)
{
if (!size)
return 0;
if (size <= KMALLOC_MIN_SIZE)
return KMALLOC_SHIFT_LOW;
if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96)
return 1;
if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192)
return 2;
if (size <= 8) return 3;
if (size <= 16) return 4;
if (size <= 32) return 5;
if (size <= 64) return 6;
if (size <= 128) return 7;
if (size <= 256) return 8;
if (size <= 512) return 9;
if (size <= 1024) return 10;
if (size <= 2 * 1024) return 11;
if (size <= 4 * 1024) return 12;
if (size <= 8 * 1024) return 13;
if (size <= 16 * 1024) return 14;
if (size <= 32 * 1024) return 15;
if (size <= 64 * 1024) return 16;
if (size <= 128 * 1024) return 17;
if (size <= 256 * 1024) return 18;
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 (size <= 64 * 1024 * 1024) return 26;
BUG();
/* Will never be reached. Needed because the compiler may complain */
return -1;
}
#endif /* !CONFIG_SLOB */
void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc;
void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc;
void kmem_cache_free(struct kmem_cache *, void *);
/*
* Bulk allocation and freeing operations. These are accelerated in an
* allocator specific way to avoid taking locks repeatedly or building
* metadata structures unnecessarily.
*
* Note that interrupts must be enabled when calling these functions.
*/
void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
mm: new API kfree_bulk() for SLAB+SLUB allocators This patch introduce a new API call kfree_bulk() for bulk freeing memory objects not bound to a single kmem_cache. Christoph pointed out that it is possible to implement freeing of objects, without knowing the kmem_cache pointer as that information is available from the object's page->slab_cache. Proposing to remove the kmem_cache argument from the bulk free API. Jesper demonstrated that these extra steps per object comes at a performance cost. It is only in the case CONFIG_MEMCG_KMEM is compiled in and activated runtime that these steps are done anyhow. The extra cost is most visible for SLAB allocator, because the SLUB allocator does the page lookup (virt_to_head_page()) anyhow. Thus, the conclusion was to keep the kmem_cache free bulk API with a kmem_cache pointer, but we can still implement a kfree_bulk() API fairly easily. Simply by handling if kmem_cache_free_bulk() gets called with a kmem_cache NULL pointer. This does increase the code size a bit, but implementing a separate kfree_bulk() call would likely increase code size even more. Below benchmarks cost of alloc+free (obj size 256 bytes) on CPU i7-4790K @ 4.00GHz, no PREEMPT and CONFIG_MEMCG_KMEM=y. Code size increase for SLAB: add/remove: 0/0 grow/shrink: 1/0 up/down: 74/0 (74) function old new delta kmem_cache_free_bulk 660 734 +74 SLAB fastpath: 87 cycles(tsc) 21.814 sz - fallback - kmem_cache_free_bulk - kfree_bulk 1 - 103 cycles 25.878 ns - 41 cycles 10.498 ns - 81 cycles 20.312 ns 2 - 94 cycles 23.673 ns - 26 cycles 6.682 ns - 42 cycles 10.649 ns 3 - 92 cycles 23.181 ns - 21 cycles 5.325 ns - 39 cycles 9.950 ns 4 - 90 cycles 22.727 ns - 18 cycles 4.673 ns - 26 cycles 6.693 ns 8 - 89 cycles 22.270 ns - 14 cycles 3.664 ns - 23 cycles 5.835 ns 16 - 88 cycles 22.038 ns - 14 cycles 3.503 ns - 22 cycles 5.543 ns 30 - 89 cycles 22.284 ns - 13 cycles 3.310 ns - 20 cycles 5.197 ns 32 - 88 cycles 22.249 ns - 13 cycles 3.420 ns - 20 cycles 5.166 ns 34 - 88 cycles 22.224 ns - 14 cycles 3.643 ns - 20 cycles 5.170 ns 48 - 88 cycles 22.088 ns - 14 cycles 3.507 ns - 20 cycles 5.203 ns 64 - 88 cycles 22.063 ns - 13 cycles 3.428 ns - 20 cycles 5.152 ns 128 - 89 cycles 22.483 ns - 15 cycles 3.891 ns - 23 cycles 5.885 ns 158 - 89 cycles 22.381 ns - 15 cycles 3.779 ns - 22 cycles 5.548 ns 250 - 91 cycles 22.798 ns - 16 cycles 4.152 ns - 23 cycles 5.967 ns SLAB when enabling MEMCG_KMEM runtime: - kmemcg fastpath: 130 cycles(tsc) 32.684 ns (step:0) 1 - 148 cycles 37.220 ns - 66 cycles 16.622 ns - 66 cycles 16.583 ns 2 - 141 cycles 35.510 ns - 51 cycles 12.820 ns - 58 cycles 14.625 ns 3 - 140 cycles 35.017 ns - 37 cycles 9.326 ns - 33 cycles 8.474 ns 4 - 137 cycles 34.507 ns - 31 cycles 7.888 ns - 33 cycles 8.300 ns 8 - 140 cycles 35.069 ns - 25 cycles 6.461 ns - 25 cycles 6.436 ns 16 - 138 cycles 34.542 ns - 23 cycles 5.945 ns - 22 cycles 5.670 ns 30 - 136 cycles 34.227 ns - 22 cycles 5.502 ns - 22 cycles 5.587 ns 32 - 136 cycles 34.253 ns - 21 cycles 5.475 ns - 21 cycles 5.324 ns 34 - 136 cycles 34.254 ns - 21 cycles 5.448 ns - 20 cycles 5.194 ns 48 - 136 cycles 34.075 ns - 21 cycles 5.458 ns - 21 cycles 5.367 ns 64 - 135 cycles 33.994 ns - 21 cycles 5.350 ns - 21 cycles 5.259 ns 128 - 137 cycles 34.446 ns - 23 cycles 5.816 ns - 22 cycles 5.688 ns 158 - 137 cycles 34.379 ns - 22 cycles 5.727 ns - 22 cycles 5.602 ns 250 - 138 cycles 34.755 ns - 24 cycles 6.093 ns - 23 cycles 5.986 ns Code size increase for SLUB: function old new delta kmem_cache_free_bulk 717 799 +82 SLUB benchmark: SLUB fastpath: 46 cycles(tsc) 11.691 ns (step:0) sz - fallback - kmem_cache_free_bulk - kfree_bulk 1 - 61 cycles 15.486 ns - 53 cycles 13.364 ns - 57 cycles 14.464 ns 2 - 54 cycles 13.703 ns - 32 cycles 8.110 ns - 33 cycles 8.482 ns 3 - 53 cycles 13.272 ns - 25 cycles 6.362 ns - 27 cycles 6.947 ns 4 - 51 cycles 12.994 ns - 24 cycles 6.087 ns - 24 cycles 6.078 ns 8 - 50 cycles 12.576 ns - 21 cycles 5.354 ns - 22 cycles 5.513 ns 16 - 49 cycles 12.368 ns - 20 cycles 5.054 ns - 20 cycles 5.042 ns 30 - 49 cycles 12.273 ns - 18 cycles 4.748 ns - 19 cycles 4.758 ns 32 - 49 cycles 12.401 ns - 19 cycles 4.821 ns - 19 cycles 4.810 ns 34 - 98 cycles 24.519 ns - 24 cycles 6.154 ns - 24 cycles 6.157 ns 48 - 83 cycles 20.833 ns - 21 cycles 5.446 ns - 21 cycles 5.429 ns 64 - 75 cycles 18.891 ns - 20 cycles 5.247 ns - 20 cycles 5.238 ns 128 - 93 cycles 23.271 ns - 27 cycles 6.856 ns - 27 cycles 6.823 ns 158 - 102 cycles 25.581 ns - 30 cycles 7.714 ns - 30 cycles 7.695 ns 250 - 107 cycles 26.917 ns - 38 cycles 9.514 ns - 38 cycles 9.506 ns SLUB when enabling MEMCG_KMEM runtime: - kmemcg fastpath: 71 cycles(tsc) 17.897 ns (step:0) 1 - 85 cycles 21.484 ns - 78 cycles 19.569 ns - 75 cycles 18.938 ns 2 - 81 cycles 20.363 ns - 45 cycles 11.258 ns - 44 cycles 11.076 ns 3 - 78 cycles 19.709 ns - 33 cycles 8.354 ns - 32 cycles 8.044 ns 4 - 77 cycles 19.430 ns - 28 cycles 7.216 ns - 28 cycles 7.003 ns 8 - 101 cycles 25.288 ns - 23 cycles 5.849 ns - 23 cycles 5.787 ns 16 - 76 cycles 19.148 ns - 20 cycles 5.162 ns - 20 cycles 5.081 ns 30 - 76 cycles 19.067 ns - 19 cycles 4.868 ns - 19 cycles 4.821 ns 32 - 76 cycles 19.052 ns - 19 cycles 4.857 ns - 19 cycles 4.815 ns 34 - 121 cycles 30.291 ns - 25 cycles 6.333 ns - 25 cycles 6.268 ns 48 - 108 cycles 27.111 ns - 21 cycles 5.498 ns - 21 cycles 5.458 ns 64 - 100 cycles 25.164 ns - 20 cycles 5.242 ns - 20 cycles 5.229 ns 128 - 155 cycles 38.976 ns - 27 cycles 6.886 ns - 27 cycles 6.892 ns 158 - 132 cycles 33.034 ns - 30 cycles 7.711 ns - 30 cycles 7.728 ns 250 - 130 cycles 32.612 ns - 38 cycles 9.560 ns - 38 cycles 9.549 ns Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Vladimir Davydov <vdavydov@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-16 04:54:00 +07:00
/*
* Caller must not use kfree_bulk() on memory not originally allocated
* by kmalloc(), because the SLOB allocator cannot handle this.
*/
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 __malloc;
void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc;
#else
static __always_inline 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 *, gfp_t, size_t) __assume_slab_alignment __malloc;
#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 __malloc;
#else
static __always_inline 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 */
#else /* CONFIG_TRACING */
static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s,
gfp_t flags, size_t size)
{
mm: slub: add kernel address sanitizer support for slub allocator With this patch kasan will be able to catch bugs in memory allocated by slub. Initially all objects in newly allocated slab page, marked as redzone. Later, when allocation of slub object happens, requested by caller number of bytes marked as accessible, and the rest of the object (including slub's metadata) marked as redzone (inaccessible). We also mark object as accessible if ksize was called for this object. There is some places in kernel where ksize function is called to inquire size of really allocated area. Such callers could validly access whole allocated memory, so it should be marked as accessible. Code in slub.c and slab_common.c files could validly access to object's metadata, so instrumentation for this files are disabled. Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com> Signed-off-by: Dmitry Chernenkov <dmitryc@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Konstantin Serebryany <kcc@google.com> Signed-off-by: Andrey Konovalov <adech.fo@gmail.com> Cc: Yuri Gribov <tetra2005@gmail.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-14 05:39:42 +07:00
void *ret = kmem_cache_alloc(s, flags);
kasan_kmalloc(s, ret, size, flags);
mm: slub: add kernel address sanitizer support for slub allocator With this patch kasan will be able to catch bugs in memory allocated by slub. Initially all objects in newly allocated slab page, marked as redzone. Later, when allocation of slub object happens, requested by caller number of bytes marked as accessible, and the rest of the object (including slub's metadata) marked as redzone (inaccessible). We also mark object as accessible if ksize was called for this object. There is some places in kernel where ksize function is called to inquire size of really allocated area. Such callers could validly access whole allocated memory, so it should be marked as accessible. Code in slub.c and slab_common.c files could validly access to object's metadata, so instrumentation for this files are disabled. Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com> Signed-off-by: Dmitry Chernenkov <dmitryc@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Konstantin Serebryany <kcc@google.com> Signed-off-by: Andrey Konovalov <adech.fo@gmail.com> Cc: Yuri Gribov <tetra2005@gmail.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-14 05:39:42 +07:00
return ret;
}
static __always_inline void *
kmem_cache_alloc_node_trace(struct kmem_cache *s,
gfp_t gfpflags,
int node, size_t size)
{
mm: slub: add kernel address sanitizer support for slub allocator With this patch kasan will be able to catch bugs in memory allocated by slub. Initially all objects in newly allocated slab page, marked as redzone. Later, when allocation of slub object happens, requested by caller number of bytes marked as accessible, and the rest of the object (including slub's metadata) marked as redzone (inaccessible). We also mark object as accessible if ksize was called for this object. There is some places in kernel where ksize function is called to inquire size of really allocated area. Such callers could validly access whole allocated memory, so it should be marked as accessible. Code in slub.c and slab_common.c files could validly access to object's metadata, so instrumentation for this files are disabled. Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com> Signed-off-by: Dmitry Chernenkov <dmitryc@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Konstantin Serebryany <kcc@google.com> Signed-off-by: Andrey Konovalov <adech.fo@gmail.com> Cc: Yuri Gribov <tetra2005@gmail.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-14 05:39:42 +07:00
void *ret = kmem_cache_alloc_node(s, gfpflags, node);
kasan_kmalloc(s, ret, size, gfpflags);
mm: slub: add kernel address sanitizer support for slub allocator With this patch kasan will be able to catch bugs in memory allocated by slub. Initially all objects in newly allocated slab page, marked as redzone. Later, when allocation of slub object happens, requested by caller number of bytes marked as accessible, and the rest of the object (including slub's metadata) marked as redzone (inaccessible). We also mark object as accessible if ksize was called for this object. There is some places in kernel where ksize function is called to inquire size of really allocated area. Such callers could validly access whole allocated memory, so it should be marked as accessible. Code in slub.c and slab_common.c files could validly access to object's metadata, so instrumentation for this files are disabled. Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com> Signed-off-by: Dmitry Chernenkov <dmitryc@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Konstantin Serebryany <kcc@google.com> Signed-off-by: Andrey Konovalov <adech.fo@gmail.com> Cc: Yuri Gribov <tetra2005@gmail.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-14 05:39:42 +07:00
return ret;
}
#endif /* CONFIG_TRACING */
extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc;
#ifdef CONFIG_TRACING
extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc;
#else
static __always_inline void *
kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
{
return kmalloc_order(size, flags, order);
}
#endif
static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
{
unsigned int order = get_order(size);
return kmalloc_order_trace(size, flags, order);
}
/**
* kmalloc - allocate memory
* @size: how many bytes of memory are required.
* @flags: the type of memory to allocate.
*
* kmalloc is the normal method of allocating memory
* for objects smaller than page size in the kernel.
*
* The @flags argument may be one of:
*
* %GFP_USER - Allocate memory on behalf of user. May sleep.
*
* %GFP_KERNEL - Allocate normal kernel ram. May sleep.
*
* %GFP_ATOMIC - Allocation will not sleep. May use emergency pools.
* For example, use this inside interrupt handlers.
*
* %GFP_HIGHUSER - Allocate pages from high memory.
*
* %GFP_NOIO - Do not do any I/O at all while trying to get memory.
*
* %GFP_NOFS - Do not make any fs calls while trying to get memory.
*
* %GFP_NOWAIT - Allocation will not sleep.
*
* %__GFP_THISNODE - Allocate node-local memory only.
*
* %GFP_DMA - Allocation suitable for DMA.
* Should only be used for kmalloc() caches. Otherwise, use a
* slab created with SLAB_DMA.
*
* Also it is possible to set different flags by OR'ing
* in one or more of the following additional @flags:
*
* %__GFP_COLD - Request cache-cold pages instead of
* trying to return cache-warm pages.
*
* %__GFP_HIGH - This allocation has high priority and may use emergency pools.
*
* %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail
* (think twice before using).
*
* %__GFP_NORETRY - If memory is not immediately available,
* then give up at once.
*
* %__GFP_NOWARN - If allocation fails, don't issue any warnings.
*
mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more useful semantic __GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to the page allocator. This has been true but only for allocations requests larger than PAGE_ALLOC_COSTLY_ORDER. It has been always ignored for smaller sizes. This is a bit unfortunate because there is no way to express the same semantic for those requests and they are considered too important to fail so they might end up looping in the page allocator for ever, similarly to GFP_NOFAIL requests. Now that the whole tree has been cleaned up and accidental or misled usage of __GFP_REPEAT flag has been removed for !costly requests we can give the original flag a better name and more importantly a more useful semantic. Let's rename it to __GFP_RETRY_MAYFAIL which tells the user that the allocator would try really hard but there is no promise of a success. This will work independent of the order and overrides the default allocator behavior. Page allocator users have several levels of guarantee vs. cost options (take GFP_KERNEL as an example) - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_ attempt to free memory at all. The most light weight mode which even doesn't kick the background reclaim. Should be used carefully because it might deplete the memory and the next user might hit the more aggressive reclaim - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic allocation without any attempt to free memory from the current context but can wake kswapd to reclaim memory if the zone is below the low watermark. Can be used from either atomic contexts or when the request is a performance optimization and there is another fallback for a slow path. - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) - non sleeping allocation with an expensive fallback so it can access some portion of memory reserves. Usually used from interrupt/bh context with an expensive slow path fallback. - GFP_KERNEL - both background and direct reclaim are allowed and the _default_ page allocator behavior is used. That means that !costly allocation requests are basically nofail but there is no guarantee of that behavior so failures have to be checked properly by callers (e.g. OOM killer victim is allowed to fail currently). - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior and all allocation requests fail early rather than cause disruptive reclaim (one round of reclaim in this implementation). The OOM killer is not invoked. - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator behavior and all allocation requests try really hard. The request will fail if the reclaim cannot make any progress. The OOM killer won't be triggered. - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior and all allocation requests will loop endlessly until they succeed. This might be really dangerous especially for larger orders. Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL because they already had their semantic. No new users are added. __alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if there is no progress and we have already passed the OOM point. This means that all the reclaim opportunities have been exhausted except the most disruptive one (the OOM killer) and a user defined fallback behavior is more sensible than keep retrying in the page allocator. [akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c] [mhocko@suse.com: semantic fix] Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz [mhocko@kernel.org: address other thing spotted by Vlastimil] Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Alex Belits <alex.belits@cavium.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Darrick J. Wong <darrick.wong@oracle.com> Cc: David Daney <david.daney@cavium.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: NeilBrown <neilb@suse.com> Cc: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-13 04:36:45 +07:00
* %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail
* eventually.
*
* There are other flags available as well, but these are not intended
* for general use, and so are not documented here. For a full list of
* potential flags, always refer to linux/gfp.h.
*/
static __always_inline void *kmalloc(size_t size, gfp_t flags)
{
if (__builtin_constant_p(size)) {
if (size > KMALLOC_MAX_CACHE_SIZE)
return kmalloc_large(size, flags);
#ifndef CONFIG_SLOB
if (!(flags & GFP_DMA)) {
int index = kmalloc_index(size);
if (!index)
return ZERO_SIZE_PTR;
return kmem_cache_alloc_trace(kmalloc_caches[index],
flags, size);
}
#endif
}
return __kmalloc(size, flags);
}
/*
* Determine size used for the nth kmalloc cache.
* return size or 0 if a kmalloc cache for that
* size does not exist
*/
static __always_inline int kmalloc_size(int n)
{
#ifndef CONFIG_SLOB
if (n > 2)
return 1 << n;
if (n == 1 && KMALLOC_MIN_SIZE <= 32)
return 96;
if (n == 2 && KMALLOC_MIN_SIZE <= 64)
return 192;
#endif
return 0;
}
static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
#ifndef CONFIG_SLOB
if (__builtin_constant_p(size) &&
size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) {
int i = kmalloc_index(size);
if (!i)
return ZERO_SIZE_PTR;
return kmem_cache_alloc_node_trace(kmalloc_caches[i],
flags, node, size);
}
#endif
return __kmalloc_node(size, flags, node);
}
slab: embed memcg_cache_params to kmem_cache Currently, kmem_cache stores a pointer to struct memcg_cache_params instead of embedding it. The rationale is to save memory when kmem accounting is disabled. However, the memcg_cache_params has shrivelled drastically since it was first introduced: * Initially: struct memcg_cache_params { bool is_root_cache; union { struct kmem_cache *memcg_caches[0]; struct { struct mem_cgroup *memcg; struct list_head list; struct kmem_cache *root_cache; bool dead; atomic_t nr_pages; struct work_struct destroy; }; }; }; * Now: struct memcg_cache_params { bool is_root_cache; union { struct { struct rcu_head rcu_head; struct kmem_cache *memcg_caches[0]; }; struct { struct mem_cgroup *memcg; struct kmem_cache *root_cache; }; }; }; So the memory saving does not seem to be a clear win anymore. OTOH, keeping a pointer to memcg_cache_params struct instead of embedding it results in touching one more cache line on kmem alloc/free hot paths. Besides, it makes linking kmem caches in a list chained by a field of struct memcg_cache_params really painful due to a level of indirection, while I want to make them linked in the following patch. That said, let us embed it. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 05:59:20 +07:00
struct memcg_cache_array {
struct rcu_head rcu;
struct kmem_cache *entries[0];
};
/*
* This is the main placeholder for memcg-related information in kmem caches.
* Both the root cache and the child caches will have it. For the root cache,
* this will hold a dynamically allocated array large enough to hold
* information about the currently limited memcgs in the system. To allow the
* array to be accessed without taking any locks, on relocation we free the old
* version only after a grace period.
*
* Root and child caches hold different metadata.
*
* @root_cache: Common to root and child caches. NULL for root, pointer to
* the root cache for children.
*
* The following fields are specific to root caches.
*
* @memcg_caches: kmemcg ID indexed table of child caches. This table is
* used to index child cachces during allocation and cleared
* early during shutdown.
*
slab: implement slab_root_caches list With kmem cgroup support enabled, kmem_caches can be created and destroyed frequently and a great number of near empty kmem_caches can accumulate if there are a lot of transient cgroups and the system is not under memory pressure. When memory reclaim starts under such conditions, it can lead to consecutive deactivation and destruction of many kmem_caches, easily hundreds of thousands on moderately large systems, exposing scalability issues in the current slab management code. This is one of the patches to address the issue. slab_caches currently lists all caches including root and memcg ones. This is the only data structure which lists the root caches and iterating root caches can only be done by walking the list while skipping over memcg caches. As there can be a huge number of memcg caches, this can become very expensive. This also can make /proc/slabinfo behave very badly. seq_file processes reads in 4k chunks and seeks to the previous Nth position on slab_caches list to resume after each chunk. With a lot of memcg cache churns on the list, reading /proc/slabinfo can become very slow and its content often ends up with duplicate and/or missing entries. This patch adds a new list slab_root_caches which lists only the root caches. When memcg is not enabled, it becomes just an alias of slab_caches. memcg specific list operations are collected into memcg_[un]link_cache(). Link: http://lkml.kernel.org/r/20170117235411.9408-7-tj@kernel.org Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Jay Vana <jsvana@fb.com> Acked-by: Vladimir Davydov <vdavydov@tarantool.org> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-23 06:41:24 +07:00
* @root_caches_node: List node for slab_root_caches list.
*
* @children: List of all child caches. While the child caches are also
* reachable through @memcg_caches, a child cache remains on
* this list until it is actually destroyed.
*
* The following fields are specific to child caches.
*
* @memcg: Pointer to the memcg this cache belongs to.
*
* @children_node: List node for @root_cache->children list.
slab: link memcg kmem_caches on their associated memory cgroup With kmem cgroup support enabled, kmem_caches can be created and destroyed frequently and a great number of near empty kmem_caches can accumulate if there are a lot of transient cgroups and the system is not under memory pressure. When memory reclaim starts under such conditions, it can lead to consecutive deactivation and destruction of many kmem_caches, easily hundreds of thousands on moderately large systems, exposing scalability issues in the current slab management code. This is one of the patches to address the issue. While a memcg kmem_cache is listed on its root cache's ->children list, there is no direct way to iterate all kmem_caches which are assocaited with a memory cgroup. The only way to iterate them is walking all caches while filtering out caches which don't match, which would be most of them. This makes memcg destruction operations O(N^2) where N is the total number of slab caches which can be huge. This combined with the synchronous RCU operations can tie up a CPU and affect the whole machine for many hours when memory reclaim triggers offlining and destruction of the stale memcgs. This patch adds mem_cgroup->kmem_caches list which goes through memcg_cache_params->kmem_caches_node of all kmem_caches which are associated with the memcg. All memcg specific iterations, including stat file access, are updated to use the new list instead. Link: http://lkml.kernel.org/r/20170117235411.9408-6-tj@kernel.org Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Jay Vana <jsvana@fb.com> Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-23 06:41:21 +07:00
*
* @kmem_caches_node: List node for @memcg->kmem_caches list.
*/
struct memcg_cache_params {
struct kmem_cache *root_cache;
union {
struct {
struct memcg_cache_array __rcu *memcg_caches;
slab: implement slab_root_caches list With kmem cgroup support enabled, kmem_caches can be created and destroyed frequently and a great number of near empty kmem_caches can accumulate if there are a lot of transient cgroups and the system is not under memory pressure. When memory reclaim starts under such conditions, it can lead to consecutive deactivation and destruction of many kmem_caches, easily hundreds of thousands on moderately large systems, exposing scalability issues in the current slab management code. This is one of the patches to address the issue. slab_caches currently lists all caches including root and memcg ones. This is the only data structure which lists the root caches and iterating root caches can only be done by walking the list while skipping over memcg caches. As there can be a huge number of memcg caches, this can become very expensive. This also can make /proc/slabinfo behave very badly. seq_file processes reads in 4k chunks and seeks to the previous Nth position on slab_caches list to resume after each chunk. With a lot of memcg cache churns on the list, reading /proc/slabinfo can become very slow and its content often ends up with duplicate and/or missing entries. This patch adds a new list slab_root_caches which lists only the root caches. When memcg is not enabled, it becomes just an alias of slab_caches. memcg specific list operations are collected into memcg_[un]link_cache(). Link: http://lkml.kernel.org/r/20170117235411.9408-7-tj@kernel.org Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Jay Vana <jsvana@fb.com> Acked-by: Vladimir Davydov <vdavydov@tarantool.org> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-23 06:41:24 +07:00
struct list_head __root_caches_node;
struct list_head children;
};
struct {
struct mem_cgroup *memcg;
struct list_head children_node;
slab: link memcg kmem_caches on their associated memory cgroup With kmem cgroup support enabled, kmem_caches can be created and destroyed frequently and a great number of near empty kmem_caches can accumulate if there are a lot of transient cgroups and the system is not under memory pressure. When memory reclaim starts under such conditions, it can lead to consecutive deactivation and destruction of many kmem_caches, easily hundreds of thousands on moderately large systems, exposing scalability issues in the current slab management code. This is one of the patches to address the issue. While a memcg kmem_cache is listed on its root cache's ->children list, there is no direct way to iterate all kmem_caches which are assocaited with a memory cgroup. The only way to iterate them is walking all caches while filtering out caches which don't match, which would be most of them. This makes memcg destruction operations O(N^2) where N is the total number of slab caches which can be huge. This combined with the synchronous RCU operations can tie up a CPU and affect the whole machine for many hours when memory reclaim triggers offlining and destruction of the stale memcgs. This patch adds mem_cgroup->kmem_caches list which goes through memcg_cache_params->kmem_caches_node of all kmem_caches which are associated with the memcg. All memcg specific iterations, including stat file access, are updated to use the new list instead. Link: http://lkml.kernel.org/r/20170117235411.9408-6-tj@kernel.org Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Jay Vana <jsvana@fb.com> Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-23 06:41:21 +07:00
struct list_head kmem_caches_node;
slab: remove synchronous synchronize_sched() from memcg cache deactivation path With kmem cgroup support enabled, kmem_caches can be created and destroyed frequently and a great number of near empty kmem_caches can accumulate if there are a lot of transient cgroups and the system is not under memory pressure. When memory reclaim starts under such conditions, it can lead to consecutive deactivation and destruction of many kmem_caches, easily hundreds of thousands on moderately large systems, exposing scalability issues in the current slab management code. This is one of the patches to address the issue. slub uses synchronize_sched() to deactivate a memcg cache. synchronize_sched() is an expensive and slow operation and doesn't scale when a huge number of caches are destroyed back-to-back. While there used to be a simple batching mechanism, the batching was too restricted to be helpful. This patch implements slab_deactivate_memcg_cache_rcu_sched() which slub can use to schedule sched RCU callback instead of performing synchronize_sched() synchronously while holding cgroup_mutex. While this adds online cpus, mems and slab_mutex operations, operating on these locks back-to-back from the same kworker, which is what's gonna happen when there are many to deactivate, isn't expensive at all and this gets rid of the scalability problem completely. Link: http://lkml.kernel.org/r/20170117235411.9408-9-tj@kernel.org Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Jay Vana <jsvana@fb.com> Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-23 06:41:30 +07:00
void (*deact_fn)(struct kmem_cache *);
union {
struct rcu_head deact_rcu_head;
struct work_struct deact_work;
};
};
};
};
int memcg_update_all_caches(int num_memcgs);
/**
* kmalloc_array - allocate memory for an array.
* @n: number of elements.
* @size: element size.
* @flags: the type of memory to allocate (see kmalloc).
*/
static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags)
{
if (size != 0 && n > SIZE_MAX / size)
slob: initial NUMA support This adds preliminary NUMA support to SLOB, primarily aimed at systems with small nodes (tested all the way down to a 128kB SRAM block), whether asymmetric or otherwise. We follow the same conventions as SLAB/SLUB, preferring current node placement for new pages, or with explicit placement, if a node has been specified. Presently on UP NUMA this has the side-effect of preferring node#0 allocations (since numa_node_id() == 0, though this could be reworked if we could hand off a pfn to determine node placement), so single-CPU NUMA systems will want to place smaller nodes further out in terms of node id. Once a page has been bound to a node (via explicit node id typing), we only do block allocations from partial free pages that have a matching node id in the page flags. The current implementation does have some scalability problems, in that all partial free pages are tracked in the global freelist (with contention due to the single spinlock). However, these are things that are being reworked for SMP scalability first, while things like per-node freelists can easily be built on top of this sort of functionality once it's been added. More background can be found in: http://marc.info/?l=linux-mm&m=118117916022379&w=2 http://marc.info/?l=linux-mm&m=118170446306199&w=2 http://marc.info/?l=linux-mm&m=118187859420048&w=2 and subsequent threads. Acked-by: Christoph Lameter <clameter@sgi.com> Acked-by: Matt Mackall <mpm@selenic.com> Signed-off-by: Paul Mundt <lethal@linux-sh.org> Acked-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16 13:38:22 +07:00
return NULL;
if (__builtin_constant_p(n) && __builtin_constant_p(size))
return kmalloc(n * size, flags);
return __kmalloc(n * size, flags);
}
/**
* kcalloc - allocate memory for an array. The memory is set to zero.
* @n: number of elements.
* @size: element size.
* @flags: the type of memory to allocate (see kmalloc).
*/
static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
{
return kmalloc_array(n, size, flags | __GFP_ZERO);
}
/*
* kmalloc_track_caller is a special version of kmalloc that records the
* calling function of the routine calling it for slab leak tracking instead
* of just the calling function (confusing, eh?).
* It's useful when the call to kmalloc comes from a widely-used standard
* allocator where we care about the real place the memory allocation
* request comes from.
*/
extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
#define kmalloc_track_caller(size, flags) \
__kmalloc_track_caller(size, flags, _RET_IP_)
[PATCH] add kmalloc_node, inline cleanup The patch makes the following function calls available to allocate memory on a specific node without changing the basic operation of the slab allocator: kmem_cache_alloc_node(kmem_cache_t *cachep, unsigned int flags, int node); kmalloc_node(size_t size, unsigned int flags, int node); in a similar way to the existing node-blind functions: kmem_cache_alloc(kmem_cache_t *cachep, unsigned int flags); kmalloc(size, flags); kmem_cache_alloc_node was changed to pass flags and the node information through the existing layers of the slab allocator (which lead to some minor rearrangements). The functions at the lowest layer (kmem_getpages, cache_grow) are already node aware. Also __alloc_percpu can call kmalloc_node now. Performance measurements (using the pageset localization patch) yields: w/o patches: Tasks jobs/min jti jobs/min/task real cpu 1 484.27 100 484.2736 12.02 1.97 Wed Mar 30 20:50:43 2005 100 25170.83 91 251.7083 23.12 150.10 Wed Mar 30 20:51:06 2005 200 34601.66 84 173.0083 33.64 294.14 Wed Mar 30 20:51:40 2005 300 37154.47 86 123.8482 46.99 436.56 Wed Mar 30 20:52:28 2005 400 39839.82 80 99.5995 58.43 580.46 Wed Mar 30 20:53:27 2005 500 40036.32 79 80.0726 72.68 728.60 Wed Mar 30 20:54:40 2005 600 44074.21 79 73.4570 79.23 872.10 Wed Mar 30 20:55:59 2005 700 44016.60 78 62.8809 92.56 1015.84 Wed Mar 30 20:57:32 2005 800 40411.05 80 50.5138 115.22 1161.13 Wed Mar 30 20:59:28 2005 900 42298.56 79 46.9984 123.83 1303.42 Wed Mar 30 21:01:33 2005 1000 40955.05 80 40.9551 142.11 1441.92 Wed Mar 30 21:03:55 2005 with pageset localization and slab API patches: Tasks jobs/min jti jobs/min/task real cpu 1 484.19 100 484.1930 12.02 1.98 Wed Mar 30 21:10:18 2005 100 27428.25 92 274.2825 21.22 149.79 Wed Mar 30 21:10:40 2005 200 37228.94 86 186.1447 31.27 293.49 Wed Mar 30 21:11:12 2005 300 41725.42 85 139.0847 41.84 434.10 Wed Mar 30 21:11:54 2005 400 43032.22 82 107.5805 54.10 582.06 Wed Mar 30 21:12:48 2005 500 42211.23 83 84.4225 68.94 722.61 Wed Mar 30 21:13:58 2005 600 40084.49 82 66.8075 87.12 873.11 Wed Mar 30 21:15:25 2005 700 44169.30 79 63.0990 92.24 1008.77 Wed Mar 30 21:16:58 2005 800 43097.94 79 53.8724 108.03 1155.88 Wed Mar 30 21:18:47 2005 900 41846.75 79 46.4964 125.17 1303.38 Wed Mar 30 21:20:52 2005 1000 40247.85 79 40.2478 144.60 1442.21 Wed Mar 30 21:23:17 2005 Signed-off-by: Christoph Lameter <christoph@lameter.com> Signed-off-by: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 22:58:38 +07:00
#ifdef CONFIG_NUMA
extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long);
#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)
[PATCH] add kmalloc_node, inline cleanup The patch makes the following function calls available to allocate memory on a specific node without changing the basic operation of the slab allocator: kmem_cache_alloc_node(kmem_cache_t *cachep, unsigned int flags, int node); kmalloc_node(size_t size, unsigned int flags, int node); in a similar way to the existing node-blind functions: kmem_cache_alloc(kmem_cache_t *cachep, unsigned int flags); kmalloc(size, flags); kmem_cache_alloc_node was changed to pass flags and the node information through the existing layers of the slab allocator (which lead to some minor rearrangements). The functions at the lowest layer (kmem_getpages, cache_grow) are already node aware. Also __alloc_percpu can call kmalloc_node now. Performance measurements (using the pageset localization patch) yields: w/o patches: Tasks jobs/min jti jobs/min/task real cpu 1 484.27 100 484.2736 12.02 1.97 Wed Mar 30 20:50:43 2005 100 25170.83 91 251.7083 23.12 150.10 Wed Mar 30 20:51:06 2005 200 34601.66 84 173.0083 33.64 294.14 Wed Mar 30 20:51:40 2005 300 37154.47 86 123.8482 46.99 436.56 Wed Mar 30 20:52:28 2005 400 39839.82 80 99.5995 58.43 580.46 Wed Mar 30 20:53:27 2005 500 40036.32 79 80.0726 72.68 728.60 Wed Mar 30 20:54:40 2005 600 44074.21 79 73.4570 79.23 872.10 Wed Mar 30 20:55:59 2005 700 44016.60 78 62.8809 92.56 1015.84 Wed Mar 30 20:57:32 2005 800 40411.05 80 50.5138 115.22 1161.13 Wed Mar 30 20:59:28 2005 900 42298.56 79 46.9984 123.83 1303.42 Wed Mar 30 21:01:33 2005 1000 40955.05 80 40.9551 142.11 1441.92 Wed Mar 30 21:03:55 2005 with pageset localization and slab API patches: Tasks jobs/min jti jobs/min/task real cpu 1 484.19 100 484.1930 12.02 1.98 Wed Mar 30 21:10:18 2005 100 27428.25 92 274.2825 21.22 149.79 Wed Mar 30 21:10:40 2005 200 37228.94 86 186.1447 31.27 293.49 Wed Mar 30 21:11:12 2005 300 41725.42 85 139.0847 41.84 434.10 Wed Mar 30 21:11:54 2005 400 43032.22 82 107.5805 54.10 582.06 Wed Mar 30 21:12:48 2005 500 42211.23 83 84.4225 68.94 722.61 Wed Mar 30 21:13:58 2005 600 40084.49 82 66.8075 87.12 873.11 Wed Mar 30 21:15:25 2005 700 44169.30 79 63.0990 92.24 1008.77 Wed Mar 30 21:16:58 2005 800 43097.94 79 53.8724 108.03 1155.88 Wed Mar 30 21:18:47 2005 900 41846.75 79 46.4964 125.17 1303.38 Wed Mar 30 21:20:52 2005 1000 40247.85 79 40.2478 144.60 1442.21 Wed Mar 30 21:23:17 2005 Signed-off-by: Christoph Lameter <christoph@lameter.com> Signed-off-by: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 22:58:38 +07:00
#endif /* CONFIG_NUMA */
[PATCH] slob: introduce the SLOB allocator configurable replacement for slab allocator This adds a CONFIG_SLAB option under CONFIG_EMBEDDED. When CONFIG_SLAB is disabled, the kernel falls back to using the 'SLOB' allocator. SLOB is a traditional K&R/UNIX allocator with a SLAB emulation layer, similar to the original Linux kmalloc allocator that SLAB replaced. It's signicantly smaller code and is more memory efficient. But like all similar allocators, it scales poorly and suffers from fragmentation more than SLAB, so it's only appropriate for small systems. It's been tested extensively in the Linux-tiny tree. I've also stress-tested it with make -j 8 compiles on a 3G SMP+PREEMPT box (not recommended). Here's a comparison for otherwise identical builds, showing SLOB saving nearly half a megabyte of RAM: $ size vmlinux* text data bss dec hex filename 3336372 529360 190812 4056544 3de5e0 vmlinux-slab 3323208 527948 190684 4041840 3dac70 vmlinux-slob $ size mm/{slab,slob}.o text data bss dec hex filename 13221 752 48 14021 36c5 mm/slab.o 1896 52 8 1956 7a4 mm/slob.o /proc/meminfo: SLAB SLOB delta MemTotal: 27964 kB 27980 kB +16 kB MemFree: 24596 kB 25092 kB +496 kB Buffers: 36 kB 36 kB 0 kB Cached: 1188 kB 1188 kB 0 kB SwapCached: 0 kB 0 kB 0 kB Active: 608 kB 600 kB -8 kB Inactive: 808 kB 812 kB +4 kB HighTotal: 0 kB 0 kB 0 kB HighFree: 0 kB 0 kB 0 kB LowTotal: 27964 kB 27980 kB +16 kB LowFree: 24596 kB 25092 kB +496 kB SwapTotal: 0 kB 0 kB 0 kB SwapFree: 0 kB 0 kB 0 kB Dirty: 4 kB 12 kB +8 kB Writeback: 0 kB 0 kB 0 kB Mapped: 560 kB 556 kB -4 kB Slab: 1756 kB 0 kB -1756 kB CommitLimit: 13980 kB 13988 kB +8 kB Committed_AS: 4208 kB 4208 kB 0 kB PageTables: 28 kB 28 kB 0 kB VmallocTotal: 1007312 kB 1007312 kB 0 kB VmallocUsed: 48 kB 48 kB 0 kB VmallocChunk: 1007264 kB 1007264 kB 0 kB (this work has been sponsored in part by CELF) From: Ingo Molnar <mingo@elte.hu> Fix 32-bitness bugs in mm/slob.c. Signed-off-by: Matt Mackall <mpm@selenic.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 16:01:45 +07:00
/*
* Shortcuts
*/
static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags)
{
return kmem_cache_alloc(k, flags | __GFP_ZERO);
}
/**
* kzalloc - allocate memory. The memory is set to zero.
* @size: how many bytes of memory are required.
* @flags: the type of memory to allocate (see kmalloc).
*/
static inline void *kzalloc(size_t size, gfp_t flags)
{
return kmalloc(size, flags | __GFP_ZERO);
}
/**
* kzalloc_node - allocate zeroed memory from a particular memory node.
* @size: how many bytes of memory are required.
* @flags: the type of memory to allocate (see kmalloc).
* @node: memory node from which to allocate
*/
static inline void *kzalloc_node(size_t size, gfp_t flags, int node)
{
return kmalloc_node(size, flags | __GFP_ZERO, node);
}
unsigned int kmem_cache_size(struct kmem_cache *s);
void __init kmem_cache_init_late(void);
#if defined(CONFIG_SMP) && defined(CONFIG_SLAB)
int slab_prepare_cpu(unsigned int cpu);
int slab_dead_cpu(unsigned int cpu);
#else
#define slab_prepare_cpu NULL
#define slab_dead_cpu NULL
#endif
#endif /* _LINUX_SLAB_H */