synchronize_sched() is a heavy operation and calling it per each cache
owned by a memory cgroup being destroyed may take quite some time.  What
is worse, it's currently called under the slab_mutex, stalling all works
doing cache creation/destruction.

Actually, there isn't much point in calling synchronize_sched() for each
cache - it's enough to call it just once - after setting cpu_partial for
all caches and before shrinking them.  This way, we can also move it out
of the slab_mutex, which we have to hold for iterating over the slab
cache list.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=172991
Link: http://lkml.kernel.org/r/0a10d71ecae3db00fb4421bcd3f82bcc911f4be4.1475329751.git.vdavydov.dev@gmail.comSigned-off-by: NVladimir Davydov <vdavydov.dev@gmail.com>
Reported-by: NDoug Smythies <dsmythies@telus.net>
Acked-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

On large systems, when some slab caches grow to millions of objects (and
many gigabytes), running 'cat /proc/slabinfo' can take up to 1-2
seconds.  During this time, interrupts are disabled while walking the
slab lists (slabs_full, slabs_partial, and slabs_free) for each node,
and this sometimes causes timeouts in other drivers (for instance,
Infiniband).

This patch optimizes 'cat /proc/slabinfo' by maintaining a counter for
total number of allocated slabs per node, per cache.  This counter is
updated when a slab is created or destroyed.  This enables us to skip
traversing the slabs_full list while gathering slabinfo statistics, and
since slabs_full tends to be the biggest list when the cache is large,
it results in a dramatic performance improvement.  Getting slabinfo
statistics now only requires walking the slabs_free and slabs_partial
lists, and those lists are usually much smaller than slabs_full.

We tested this after growing the dentry cache to 70GB, and the
performance improved from 2s to 5ms.

Link: http://lkml.kernel.org/r/1472517876-26814-1-git-send-email-aruna.ramakrishna@oracle.comSigned-off-by: NAruna Ramakrishna <aruna.ramakrishna@oracle.com>
Acked-by: NDavid Rientjes <rientjes@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.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: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

There is a bug report that SLAB makes extreme load average due to over
2000 kworker thread.

  https://bugzilla.kernel.org/show_bug.cgi?id=172981

This issue is caused by kmemcg feature that try to create new set of
kmem_caches for each memcg.  Recently, kmem_cache creation is slowed by
synchronize_sched() and futher kmem_cache creation is also delayed since
kmem_cache creation is synchronized by a global slab_mutex lock.  So,
the number of kworker that try to create kmem_cache increases quietly.

synchronize_sched() is for lockless access to node's shared array but
it's not needed when a new kmem_cache is created.  So, this patch rules
out that case.

Fixes: 801faf0d ("mm/slab: lockless decision to grow cache")
Link: http://lkml.kernel.org/r/1475734855-4837-1-git-send-email-iamjoonsoo.kim@lge.comReported-by: NDoug Smythies <dsmythies@telus.net>
Tested-by: NDoug Smythies <dsmythies@telus.net>
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Install the callbacks via the state machine.
Signed-off-by: NRichard Weinberger <richard@nod.at>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: linux-mm@kvack.org
Cc: rt@linutronix.de
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Lameter <cl@linux.com>
Link: http://lkml.kernel.org/r/20160823125319.abeapfjapf2kfezp@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

There was only one use of __initdata_refok and __exit_refok

__init_refok was used 46 times against 82 for __ref.

Those definitions are obsolete since commit 312b1485 ("Introduce new
section reference annotations tags: __ref, __refdata, __refconst")

This patch removes the following compatibility definitions and replaces
them treewide.

/* compatibility defines */
#define __init_refok     __ref
#define __initdata_refok __refdata
#define __exit_refok     __ref

I can also provide separate patches if necessary.
(One patch per tree and check in 1 month or 2 to remove old definitions)

[akpm@linux-foundation.org: coding-style fixes]
Link: http://lkml.kernel.org/r/1466796271-3043-1-git-send-email-fabf@skynet.beSigned-off-by: NFabian Frederick <fabf@skynet.be>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The state of object currently tracked in two places - shadow memory, and
the ->state field in struct kasan_alloc_meta.  We can get rid of the
latter.  The will save us a little bit of memory.  Also, this allow us
to move free stack into struct kasan_alloc_meta, without increasing
memory consumption.  So now we should always know when the last time the
object was freed.  This may be useful for long delayed use-after-free
bugs.

As a side effect this fixes following UBSAN warning:
	UBSAN: Undefined behaviour in mm/kasan/quarantine.c:102:13
	member access within misaligned address ffff88000d1efebc for type 'struct qlist_node'
	which requires 8 byte alignment

Link: http://lkml.kernel.org/r/1470062715-14077-5-git-send-email-aryabinin@virtuozzo.comReported-by: Nkernel test robot <xiaolong.ye@intel.com>
Signed-off-by: NAndrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.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: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Using list_move() instead of list_del() + list_add() to avoid needlessly
poisoning the next and prev values.

Link: http://lkml.kernel.org/r/1468929772-9174-1-git-send-email-weiyj_lk@163.comSigned-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Acked-by: NDavid Rientjes <rientjes@google.com>
Acked-by: NChristoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Both SLAB and SLUB BUG() when a caller provides an invalid gfp_mask.
This is a rather harsh way to announce a non-critical issue.  Allocator
is free to ignore invalid flags.  Let's simply replace BUG() by
dump_stack to tell the offender and fixup the mask to move on with the
allocation request.

This is an example for kmalloc(GFP_KERNEL|__GFP_HIGHMEM) from a test
module:

  Unexpected gfp: 0x2 (__GFP_HIGHMEM). Fixing up to gfp: 0x24000c0 (GFP_KERNEL). Fix your code!
  CPU: 0 PID: 2916 Comm: insmod Tainted: G           O    4.6.0-slabgfp2-00002-g4cdfc2ef4892-dirty #936
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
  Call Trace:
    dump_stack+0x67/0x90
    cache_alloc_refill+0x201/0x617
    kmem_cache_alloc_trace+0xa7/0x24a
    ? 0xffffffffa0005000
    mymodule_init+0x20/0x1000 [test_slab]
    do_one_initcall+0xe7/0x16c
    ? rcu_read_lock_sched_held+0x61/0x69
    ? kmem_cache_alloc_trace+0x197/0x24a
    do_init_module+0x5f/0x1d9
    load_module+0x1a3d/0x1f21
    ? retint_kernel+0x2d/0x2d
    SyS_init_module+0xe8/0x10e
    ? SyS_init_module+0xe8/0x10e
    do_syscall_64+0x68/0x13f
    entry_SYSCALL64_slow_path+0x25/0x25

Link: http://lkml.kernel.org/r/1465548200-11384-2-git-send-email-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@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: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

printk offers %pGg for quite some time so let's use it to get a human
readable list of invalid flags.

The original output would be
  [  429.191962] gfp: 2

after the change
  [  429.191962] Unexpected gfp: 0x2 (__GFP_HIGHMEM)

Link: http://lkml.kernel.org/r/1465548200-11384-1-git-send-email-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@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: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The kernel heap allocators are using a sequential freelist making their
allocation predictable.  This predictability makes kernel heap overflow
easier to exploit.  An attacker can careful prepare the kernel heap to
control the following chunk overflowed.

For example these attacks exploit the predictability of the heap:
 - Linux Kernel CAN SLUB overflow (https://goo.gl/oMNWkU)
 - Exploiting Linux Kernel Heap corruptions (http://goo.gl/EXLn95)

***Problems that needed solving:
 - Randomize the Freelist (singled linked) used in the SLUB allocator.
 - Ensure good performance to encourage usage.
 - Get best entropy in early boot stage.

***Parts:
 - 01/02 Reorganize the SLAB Freelist randomization to share elements
   with the SLUB implementation.
 - 02/02 The SLUB Freelist randomization implementation. Similar approach
   than the SLAB but tailored to the singled freelist used in SLUB.

***Performance data:

slab_test impact is between 3% to 4% on average for 100000 attempts
without smp.  It is a very focused testing, kernbench show the overall
impact on the system is way lower.

Before:

  Single thread testing
  =====================
  1. Kmalloc: Repeatedly allocate then free test
  100000 times kmalloc(8) -> 49 cycles kfree -> 77 cycles
  100000 times kmalloc(16) -> 51 cycles kfree -> 79 cycles
  100000 times kmalloc(32) -> 53 cycles kfree -> 83 cycles
  100000 times kmalloc(64) -> 62 cycles kfree -> 90 cycles
  100000 times kmalloc(128) -> 81 cycles kfree -> 97 cycles
  100000 times kmalloc(256) -> 98 cycles kfree -> 121 cycles
  100000 times kmalloc(512) -> 95 cycles kfree -> 122 cycles
  100000 times kmalloc(1024) -> 96 cycles kfree -> 126 cycles
  100000 times kmalloc(2048) -> 115 cycles kfree -> 140 cycles
  100000 times kmalloc(4096) -> 149 cycles kfree -> 171 cycles
  2. Kmalloc: alloc/free test
  100000 times kmalloc(8)/kfree -> 70 cycles
  100000 times kmalloc(16)/kfree -> 70 cycles
  100000 times kmalloc(32)/kfree -> 70 cycles
  100000 times kmalloc(64)/kfree -> 70 cycles
  100000 times kmalloc(128)/kfree -> 70 cycles
  100000 times kmalloc(256)/kfree -> 69 cycles
  100000 times kmalloc(512)/kfree -> 70 cycles
  100000 times kmalloc(1024)/kfree -> 73 cycles
  100000 times kmalloc(2048)/kfree -> 72 cycles
  100000 times kmalloc(4096)/kfree -> 71 cycles

After:

  Single thread testing
  =====================
  1. Kmalloc: Repeatedly allocate then free test
  100000 times kmalloc(8) -> 57 cycles kfree -> 78 cycles
  100000 times kmalloc(16) -> 61 cycles kfree -> 81 cycles
  100000 times kmalloc(32) -> 76 cycles kfree -> 93 cycles
  100000 times kmalloc(64) -> 83 cycles kfree -> 94 cycles
  100000 times kmalloc(128) -> 106 cycles kfree -> 107 cycles
  100000 times kmalloc(256) -> 118 cycles kfree -> 117 cycles
  100000 times kmalloc(512) -> 114 cycles kfree -> 116 cycles
  100000 times kmalloc(1024) -> 115 cycles kfree -> 118 cycles
  100000 times kmalloc(2048) -> 147 cycles kfree -> 131 cycles
  100000 times kmalloc(4096) -> 214 cycles kfree -> 161 cycles
  2. Kmalloc: alloc/free test
  100000 times kmalloc(8)/kfree -> 66 cycles
  100000 times kmalloc(16)/kfree -> 66 cycles
  100000 times kmalloc(32)/kfree -> 66 cycles
  100000 times kmalloc(64)/kfree -> 66 cycles
  100000 times kmalloc(128)/kfree -> 65 cycles
  100000 times kmalloc(256)/kfree -> 67 cycles
  100000 times kmalloc(512)/kfree -> 67 cycles
  100000 times kmalloc(1024)/kfree -> 64 cycles
  100000 times kmalloc(2048)/kfree -> 67 cycles
  100000 times kmalloc(4096)/kfree -> 67 cycles

Kernbench, before:

  Average Optimal load -j 12 Run (std deviation):
  Elapsed Time 101.873 (1.16069)
  User Time 1045.22 (1.60447)
  System Time 88.969 (0.559195)
  Percent CPU 1112.9 (13.8279)
  Context Switches 189140 (2282.15)
  Sleeps 99008.6 (768.091)

After:

  Average Optimal load -j 12 Run (std deviation):
  Elapsed Time 102.47 (0.562732)
  User Time 1045.3 (1.34263)
  System Time 88.311 (0.342554)
  Percent CPU 1105.8 (6.49444)
  Context Switches 189081 (2355.78)
  Sleeps 99231.5 (800.358)

This patch (of 2):

This commit reorganizes the previous SLAB freelist randomization to
prepare for the SLUB implementation.  It moves functions that will be
shared to slab_common.

The entropy functions are changed to align with the SLUB implementation,
now using get_random_(int|long) functions.  These functions were chosen
because they provide a bit more entropy early on boot and better
performance when specific arch instructions are not available.

[akpm@linux-foundation.org: fix build]
Link: http://lkml.kernel.org/r/1464295031-26375-2-git-send-email-thgarnie@google.comSigned-off-by: NThomas Garnier <thgarnie@google.com>
Reviewed-by: NKees Cook <keescook@chromium.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: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Under CONFIG_HARDENED_USERCOPY, this adds object size checking to the
SLAB allocator to catch any copies that may span objects.

Based on code from PaX and grsecurity.
Signed-off-by: NKees Cook <keescook@chromium.org>
Tested-by: NValdis Kletnieks <valdis.kletnieks@vt.edu>

Instead of calling kasan_krealloc(), which replaces the memory
allocation stack ID (if stack depot is used), just unpoison the whole
memory chunk.
Signed-off-by: NAlexander Potapenko <glider@google.com>
Acked-by: NAndrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Konstantin Serebryany <kcc@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Quarantine isolates freed objects in a separate queue.  The objects are
returned to the allocator later, which helps to detect use-after-free
errors.

When the object is freed, its state changes from KASAN_STATE_ALLOC to
KASAN_STATE_QUARANTINE.  The object is poisoned and put into quarantine
instead of being returned to the allocator, therefore every subsequent
access to that object triggers a KASAN error, and the error handler is
able to say where the object has been allocated and deallocated.

When it's time for the object to leave quarantine, its state becomes
KASAN_STATE_FREE and it's returned to the allocator.  From now on the
allocator may reuse it for another allocation.  Before that happens,
it's still possible to detect a use-after free on that object (it
retains the allocation/deallocation stacks).

When the allocator reuses this object, the shadow is unpoisoned and old
allocation/deallocation stacks are wiped.  Therefore a use of this
object, even an incorrect one, won't trigger ASan warning.

Without the quarantine, it's not guaranteed that the objects aren't
reused immediately, that's why the probability of catching a
use-after-free is lower than with quarantine in place.

Quarantine isolates freed objects in a separate queue.  The objects are
returned to the allocator later, which helps to detect use-after-free
errors.

Freed objects are first added to per-cpu quarantine queues.  When a
cache is destroyed or memory shrinking is requested, the objects are
moved into the global quarantine queue.  Whenever a kmalloc call allows
memory reclaiming, the oldest objects are popped out of the global queue
until the total size of objects in quarantine is less than 3/4 of the
maximum quarantine size (which is a fraction of installed physical
memory).

As long as an object remains in the quarantine, KASAN is able to report
accesses to it, so the chance of reporting a use-after-free is
increased.  Once the object leaves quarantine, the allocator may reuse
it, in which case the object is unpoisoned and KASAN can't detect
incorrect accesses to it.

Right now quarantine support is only enabled in SLAB allocator.
Unification of KASAN features in SLAB and SLUB will be done later.

This patch is based on the "mm: kasan: quarantine" patch originally
prepared by Dmitry Chernenkov.  A number of improvements have been
suggested by Andrey Ryabinin.

[glider@google.com: v9]
  Link: http://lkml.kernel.org/r/1462987130-144092-1-git-send-email-glider@google.comSigned-off-by: NAlexander Potapenko <glider@google.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: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Lots of code does

	node = next_node(node, XXX);
	if (node == MAX_NUMNODES)
		node = first_node(XXX);

so create next_node_in() to do this and use it in various places.

[mhocko@suse.com: use next_node_in() helper]
Acked-by: NVlastimil Babka <vbabka@suse.cz>
Acked-by: NMichal Hocko <mhocko@kernel.org>
Signed-off-by: NMichal Hocko <mhocko@suse.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Laura Abbott <lauraa@codeaurora.org>
Cc: Hui Zhu <zhuhui@xiaomi.com>
Cc: Wang Xiaoqiang <wangxq10@lzu.edu.cn>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Now we have IS_ENABLED helper to check if a Kconfig option is enabled or
not, so ZONE_DMA_FLAG sounds no longer useful.

And, the use of ZONE_DMA_FLAG in slab looks pointless according to the
comment [1] from Johannes Weiner, so remove them and ORing passed in
flags with the cache gfp flags has been done in kmem_getpages().

[1] https://lkml.org/lkml/2014/9/25/553

Link: http://lkml.kernel.org/r/1462381297-11009-1-git-send-email-yang.shi@linaro.orgSigned-off-by: NYang Shi <yang.shi@linaro.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: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Provides an optional config (CONFIG_SLAB_FREELIST_RANDOM) to randomize
the SLAB freelist.  The list is randomized during initialization of a
new set of pages.  The order on different freelist sizes is pre-computed
at boot for performance.  Each kmem_cache has its own randomized
freelist.  Before pre-computed lists are available freelists are
generated dynamically.  This security feature reduces the predictability
of the kernel SLAB allocator against heap overflows rendering attacks
much less stable.

For example this attack against SLUB (also applicable against SLAB)
would be affected:

  https://jon.oberheide.org/blog/2010/09/10/linux-kernel-can-slub-overflow/

Also, since v4.6 the freelist was moved at the end of the SLAB.  It
means a controllable heap is opened to new attacks not yet publicly
discussed.  A kernel heap overflow can be transformed to multiple
use-after-free.  This feature makes this type of attack harder too.

To generate entropy, we use get_random_bytes_arch because 0 bits of
entropy is available in the boot stage.  In the worse case this function
will fallback to the get_random_bytes sub API.  We also generate a shift
random number to shift pre-computed freelist for each new set of pages.

The config option name is not specific to the SLAB as this approach will
be extended to other allocators like SLUB.

Performance results highlighted no major changes:

Hackbench (running 90 10 times):

  Before average: 0.0698
  After average: 0.0663 (-5.01%)

slab_test 1 run on boot.  Difference only seen on the 2048 size test
being the worse case scenario covered by freelist randomization.  New
slab pages are constantly being created on the 10000 allocations.
Variance should be mainly due to getting new pages every few
allocations.

Before:

  Single thread testing
  =====================
  1. Kmalloc: Repeatedly allocate then free test
  10000 times kmalloc(8) -> 99 cycles kfree -> 112 cycles
  10000 times kmalloc(16) -> 109 cycles kfree -> 140 cycles
  10000 times kmalloc(32) -> 129 cycles kfree -> 137 cycles
  10000 times kmalloc(64) -> 141 cycles kfree -> 141 cycles
  10000 times kmalloc(128) -> 152 cycles kfree -> 148 cycles
  10000 times kmalloc(256) -> 195 cycles kfree -> 167 cycles
  10000 times kmalloc(512) -> 257 cycles kfree -> 199 cycles
  10000 times kmalloc(1024) -> 393 cycles kfree -> 251 cycles
  10000 times kmalloc(2048) -> 649 cycles kfree -> 228 cycles
  10000 times kmalloc(4096) -> 806 cycles kfree -> 370 cycles
  10000 times kmalloc(8192) -> 814 cycles kfree -> 411 cycles
  10000 times kmalloc(16384) -> 892 cycles kfree -> 455 cycles
  2. Kmalloc: alloc/free test
  10000 times kmalloc(8)/kfree -> 121 cycles
  10000 times kmalloc(16)/kfree -> 121 cycles
  10000 times kmalloc(32)/kfree -> 121 cycles
  10000 times kmalloc(64)/kfree -> 121 cycles
  10000 times kmalloc(128)/kfree -> 121 cycles
  10000 times kmalloc(256)/kfree -> 119 cycles
  10000 times kmalloc(512)/kfree -> 119 cycles
  10000 times kmalloc(1024)/kfree -> 119 cycles
  10000 times kmalloc(2048)/kfree -> 119 cycles
  10000 times kmalloc(4096)/kfree -> 121 cycles
  10000 times kmalloc(8192)/kfree -> 119 cycles
  10000 times kmalloc(16384)/kfree -> 119 cycles

After:

  Single thread testing
  =====================
  1. Kmalloc: Repeatedly allocate then free test
  10000 times kmalloc(8) -> 130 cycles kfree -> 86 cycles
  10000 times kmalloc(16) -> 118 cycles kfree -> 86 cycles
  10000 times kmalloc(32) -> 121 cycles kfree -> 85 cycles
  10000 times kmalloc(64) -> 176 cycles kfree -> 102 cycles
  10000 times kmalloc(128) -> 178 cycles kfree -> 100 cycles
  10000 times kmalloc(256) -> 205 cycles kfree -> 109 cycles
  10000 times kmalloc(512) -> 262 cycles kfree -> 136 cycles
  10000 times kmalloc(1024) -> 342 cycles kfree -> 157 cycles
  10000 times kmalloc(2048) -> 701 cycles kfree -> 238 cycles
  10000 times kmalloc(4096) -> 803 cycles kfree -> 364 cycles
  10000 times kmalloc(8192) -> 835 cycles kfree -> 404 cycles
  10000 times kmalloc(16384) -> 896 cycles kfree -> 441 cycles
  2. Kmalloc: alloc/free test
  10000 times kmalloc(8)/kfree -> 121 cycles
  10000 times kmalloc(16)/kfree -> 121 cycles
  10000 times kmalloc(32)/kfree -> 123 cycles
  10000 times kmalloc(64)/kfree -> 142 cycles
  10000 times kmalloc(128)/kfree -> 121 cycles
  10000 times kmalloc(256)/kfree -> 119 cycles
  10000 times kmalloc(512)/kfree -> 119 cycles
  10000 times kmalloc(1024)/kfree -> 119 cycles
  10000 times kmalloc(2048)/kfree -> 119 cycles
  10000 times kmalloc(4096)/kfree -> 119 cycles
  10000 times kmalloc(8192)/kfree -> 119 cycles
  10000 times kmalloc(16384)/kfree -> 119 cycles

[akpm@linux-foundation.org: propagate gfp_t into cache_random_seq_create()]
Signed-off-by: NThomas Garnier <thgarnie@google.com>
Acked-by: NChristoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Greg Thelen <gthelen@google.com>
Cc: Laura Abbott <labbott@fedoraproject.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

To check whether free objects exist or not precisely, we need to grab a
lock.  But, accuracy isn't that important because race window would be
even small and if there is too much free object, cache reaper would reap
it.  So, this patch makes the check for free object exisistence not to
hold a lock.  This will reduce lock contention in heavily allocation
case.

Note that until now, n->shared can be freed during the processing by
writing slabinfo, but, with some trick in this patch, we can access it
freely within interrupt disabled period.

Below is the result of concurrent allocation/free in slab allocation
benchmark made by Christoph a long time ago.  I make the output simpler.
The number shows cycle count during alloc/free respectively so less is
better.

  * Before
  Kmalloc N*alloc N*free(32): Average=248/966
  Kmalloc N*alloc N*free(64): Average=261/949
  Kmalloc N*alloc N*free(128): Average=314/1016
  Kmalloc N*alloc N*free(256): Average=741/1061
  Kmalloc N*alloc N*free(512): Average=1246/1152
  Kmalloc N*alloc N*free(1024): Average=2437/1259
  Kmalloc N*alloc N*free(2048): Average=4980/1800
  Kmalloc N*alloc N*free(4096): Average=9000/2078

  * After
  Kmalloc N*alloc N*free(32): Average=344/792
  Kmalloc N*alloc N*free(64): Average=347/882
  Kmalloc N*alloc N*free(128): Average=390/959
  Kmalloc N*alloc N*free(256): Average=393/1067
  Kmalloc N*alloc N*free(512): Average=683/1229
  Kmalloc N*alloc N*free(1024): Average=1295/1325
  Kmalloc N*alloc N*free(2048): Average=2513/1664
  Kmalloc N*alloc N*free(4096): Average=4742/2172

It shows that allocation performance decreases for the object size up to
128 and it may be due to extra checks in cache_alloc_refill().  But,
with considering improvement of free performance, net result looks the
same.  Result for other size class looks very promising, roughly, 50%
performance improvement.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Until now, cache growing makes a free slab on node's slab list and then
we can allocate free objects from it.  This necessarily requires to hold
a node lock which is very contended.  If we refill cpu cache before
attaching it to node's slab list, we can avoid holding a node lock as
much as possible because this newly allocated slab is only visible to
the current task.  This will reduce lock contention.

Below is the result of concurrent allocation/free in slab allocation
benchmark made by Christoph a long time ago.  I make the output simpler.
The number shows cycle count during alloc/free respectively so less is
better.

  * Before
  Kmalloc N*alloc N*free(32): Average=355/750
  Kmalloc N*alloc N*free(64): Average=452/812
  Kmalloc N*alloc N*free(128): Average=559/1070
  Kmalloc N*alloc N*free(256): Average=1176/980
  Kmalloc N*alloc N*free(512): Average=1939/1189
  Kmalloc N*alloc N*free(1024): Average=3521/1278
  Kmalloc N*alloc N*free(2048): Average=7152/1838
  Kmalloc N*alloc N*free(4096): Average=13438/2013

  * After
  Kmalloc N*alloc N*free(32): Average=248/966
  Kmalloc N*alloc N*free(64): Average=261/949
  Kmalloc N*alloc N*free(128): Average=314/1016
  Kmalloc N*alloc N*free(256): Average=741/1061
  Kmalloc N*alloc N*free(512): Average=1246/1152
  Kmalloc N*alloc N*free(1024): Average=2437/1259
  Kmalloc N*alloc N*free(2048): Average=4980/1800
  Kmalloc N*alloc N*free(4096): Average=9000/2078

It shows that contention is reduced for all the object sizes and
performance increases by 30 ~ 40%.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This is a preparation step to implement lockless allocation path when
there is no free objects in kmem_cache.

What we'd like to do here is to refill cpu cache without holding a node
lock.  To accomplish this purpose, refill should be done after new slab
allocation but before attaching the slab to the management list.  So,
this patch separates cache_grow() to two parts, allocation and attaching
to the list in order to add some code inbetween them in the following
patch.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Currently, cache_grow() assumes that allocated page's nodeid would be
same with parameter nodeid which is used for allocation request.  If we
discard this assumption, we can handle fallback_alloc() case gracefully.
So, this patch makes cache_grow() handle the page allocated on arbitrary
node and clean-up relevant code.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Slab color isn't needed to be changed strictly.  Because locking for
changing slab color could cause more lock contention so this patch
implements racy access/modify the slab color.  This is a preparation
step to implement lockless allocation path when there is no free objects
in the kmem_cache.

Below is the result of concurrent allocation/free in slab allocation
benchmark made by Christoph a long time ago.  I make the output simpler.
The number shows cycle count during alloc/free respectively so less is
better.

  * Before
  Kmalloc N*alloc N*free(32): Average=365/806
  Kmalloc N*alloc N*free(64): Average=452/690
  Kmalloc N*alloc N*free(128): Average=736/886
  Kmalloc N*alloc N*free(256): Average=1167/985
  Kmalloc N*alloc N*free(512): Average=2088/1125
  Kmalloc N*alloc N*free(1024): Average=4115/1184
  Kmalloc N*alloc N*free(2048): Average=8451/1748
  Kmalloc N*alloc N*free(4096): Average=16024/2048

  * After
  Kmalloc N*alloc N*free(32): Average=355/750
  Kmalloc N*alloc N*free(64): Average=452/812
  Kmalloc N*alloc N*free(128): Average=559/1070
  Kmalloc N*alloc N*free(256): Average=1176/980
  Kmalloc N*alloc N*free(512): Average=1939/1189
  Kmalloc N*alloc N*free(1024): Average=3521/1278
  Kmalloc N*alloc N*free(2048): Average=7152/1838
  Kmalloc N*alloc N*free(4096): Average=13438/2013

It shows that contention is reduced for object size >= 1024 and
performance increases by roughly 15%.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: NChristoph Lameter <cl@linux.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Currently, determination to free a slab is done whenever each freed
object is put into the slab.  This has a following problem.

Assume free_limit = 10 and nr_free = 9.

Free happens as following sequence and nr_free changes as following.

free(become a free slab) free(not become a free slab) nr_free: 9 -> 10
(at first free) -> 11 (at second free)

If we try to check if we can free current slab or not on each object
free, we can't free any slab in this situation because current slab
isn't a free slab when nr_free exceed free_limit (at second free) even
if there is a free slab.

However, if we check it lastly, we can free 1 free slab.

This problem would cause to keep too much memory in the slab subsystem.
This patch try to fix it by checking number of free object after all
free work is done.  If there is free slab at that time, we can free slab
as much as possible so we keep free slab as minimal.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

There are mostly same code for setting up kmem_cache_node either in
cpuup_prepare() or alloc_kmem_cache_node().  Factor out and clean-up
them.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Tested-by: NNishanth Menon <nm@ti.com>
Tested-by: NJon Hunter <jonathanh@nvidia.com>
Acked-by: NChristoph Lameter <cl@linux.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

It can be reused on other place, so factor out it.  Following patch will
use it.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: NChristoph Lameter <cl@linux.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

slabs_tofree() implies freeing all free slab.  We can do it with just
providing INT_MAX.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: NChristoph Lameter <cl@linux.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Initial attemp to remove BAD_ALIEN_MAGIC is once reverted by 'commit
edcad250 ("Revert "slab: remove BAD_ALIEN_MAGIC"")' because it
causes a problem on m68k which has many node but !CONFIG_NUMA.  In this
case, although alien cache isn't used at all but to cope with some
initialization path, garbage value is used and that is BAD_ALIEN_MAGIC.
Now, this patch set use_alien_caches to 0 when !CONFIG_NUMA, there is no
initialization path problem so we don't need BAD_ALIEN_MAGIC at all.  So
remove it.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Tested-by: NGeert Uytterhoeven <geert@linux-m68k.org>
Acked-by: NChristoph Lameter <cl@linux.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

While processing concurrent allocation, SLAB could be contended a lot
because it did a lots of work with holding a lock.  This patchset try to
reduce the number of critical section to reduce lock contention.  Major
changes are lockless decision to allocate more slab and lockless cpu
cache refill from the newly allocated slab.

Below is the result of concurrent allocation/free in slab allocation
benchmark made by Christoph a long time ago.  I make the output simpler.
The number shows cycle count during alloc/free respectively so less is
better.

  * Before
  Kmalloc N*alloc N*free(32): Average=365/806
  Kmalloc N*alloc N*free(64): Average=452/690
  Kmalloc N*alloc N*free(128): Average=736/886
  Kmalloc N*alloc N*free(256): Average=1167/985
  Kmalloc N*alloc N*free(512): Average=2088/1125
  Kmalloc N*alloc N*free(1024): Average=4115/1184
  Kmalloc N*alloc N*free(2048): Average=8451/1748
  Kmalloc N*alloc N*free(4096): Average=16024/2048

  * After
  Kmalloc N*alloc N*free(32): Average=344/792
  Kmalloc N*alloc N*free(64): Average=347/882
  Kmalloc N*alloc N*free(128): Average=390/959
  Kmalloc N*alloc N*free(256): Average=393/1067
  Kmalloc N*alloc N*free(512): Average=683/1229
  Kmalloc N*alloc N*free(1024): Average=1295/1325
  Kmalloc N*alloc N*free(2048): Average=2513/1664
  Kmalloc N*alloc N*free(4096): Average=4742/2172

It shows that performance improves greatly (roughly more than 50%) for
the object class whose size is more than 128 bytes.

This patch (of 11):

If we don't hold neither the slab_mutex nor the node lock, node's shared
array cache could be freed and re-populated.  If __kmem_cache_shrink()
is called at the same time, it will call drain_array() with n->shared
without holding node lock so problem can happen.  This patch fix the
situation by holding the node lock before trying to drain the shared
array.

In addition, add a debug check to confirm that n->shared access race
doesn't exist.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add GFP flags to KASAN hooks for future patches to use.

This patch is based on the "mm: kasan: unified support for SLUB and SLAB
allocators" patch originally prepared by Dmitry Chernenkov.
Signed-off-by: NAlexander Potapenko <glider@google.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: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add KASAN hooks to SLAB allocator.

This patch is based on the "mm: kasan: unified support for SLUB and SLAB
allocators" patch originally prepared by Dmitry Chernenkov.
Signed-off-by: NAlexander Potapenko <glider@google.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: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Most of the mm subsystem uses pr_<level> so make it consistent.

Miscellanea:

 - Realign arguments
 - Add missing newline to format
 - kmemleak-test.c has a "kmemleak: " prefix added to the
   "Kmemleak testing" logging message via pr_fmt
Signed-off-by: NJoe Perches <joe@perches.com>
Acked-by: Tejun Heo <tj@kernel.org>	[percpu]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Kernel style prefers a single string over split strings when the string is
'user-visible'.

Miscellanea:

 - Add a missing newline
 - Realign arguments
Signed-off-by: NJoe Perches <joe@perches.com>
Acked-by: Tejun Heo <tj@kernel.org>	[percpu]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

THP defrag is enabled by default to direct reclaim/compact but not wake
kswapd in the event of a THP allocation failure.  The problem is that
THP allocation requests potentially enter reclaim/compaction.  This
potentially incurs a severe stall that is not guaranteed to be offset by
reduced TLB misses.  While there has been considerable effort to reduce
the impact of reclaim/compaction, it is still a high cost and workloads
that should fit in memory fail to do so.  Specifically, a simple
anon/file streaming workload will enter direct reclaim on NUMA at least
even though the working set size is 80% of RAM.  It's been years and
it's time to throw in the towel.

First, this patch defines THP defrag as follows;

 madvise: A failed allocation will direct reclaim/compact if the application requests it
 never:   Neither reclaim/compact nor wake kswapd
 defer:   A failed allocation will wake kswapd/kcompactd
 always:  A failed allocation will direct reclaim/compact (historical behaviour)
          khugepaged defrag will enter direct/reclaim but not wake kswapd.

Next it sets the default defrag option to be "madvise" to only enter
direct reclaim/compaction for applications that specifically requested
it.

Lastly, it removes a check from the page allocator slowpath that is
related to __GFP_THISNODE to allow "defer" to work.  The callers that
really cares are slub/slab and they are updated accordingly.  The slab
one may be surprising because it also corrects a comment as kswapd was
never woken up by that path.

This means that a THP fault will no longer stall for most applications
by default and the ideal for most users that get THP if they are
immediately available.  There are still options for users that prefer a
stall at startup of a new application by either restoring historical
behaviour with "always" or pick a half-way point with "defer" where
kswapd does some of the work in the background and wakes kcompactd if
necessary.  THP defrag for khugepaged remains enabled and will enter
direct/reclaim but no wakeup kswapd or kcompactd.

After this patch a THP allocation failure will quickly fallback and rely
on khugepaged to recover the situation at some time in the future.  In
some cases, this will reduce THP usage but the benefit of THP is hard to
measure and not a universal win where as a stall to reclaim/compaction
is definitely measurable and can be painful.

The first test for this is using "usemem" to read a large file and write
a large anonymous mapping (to avoid the zero page) multiple times.  The
total size of the mappings is 80% of RAM and the benchmark simply
measures how long it takes to complete.  It uses multiple threads to see
if that is a factor.  On UMA, the performance is almost identical so is
not reported but on NUMA, we see this

usemem
                                   4.4.0                 4.4.0
                          kcompactd-v1r1         nodefrag-v1r3
Amean    System-1       102.86 (  0.00%)       46.81 ( 54.50%)
Amean    System-4        37.85 (  0.00%)       34.02 ( 10.12%)
Amean    System-7        48.12 (  0.00%)       46.89 (  2.56%)
Amean    System-12       51.98 (  0.00%)       56.96 ( -9.57%)
Amean    System-21       80.16 (  0.00%)       79.05 (  1.39%)
Amean    System-30      110.71 (  0.00%)      107.17 (  3.20%)
Amean    System-48      127.98 (  0.00%)      124.83 (  2.46%)
Amean    Elapsd-1       185.84 (  0.00%)      105.51 ( 43.23%)
Amean    Elapsd-4        26.19 (  0.00%)       25.58 (  2.33%)
Amean    Elapsd-7        21.65 (  0.00%)       21.62 (  0.16%)
Amean    Elapsd-12       18.58 (  0.00%)       17.94 (  3.43%)
Amean    Elapsd-21       17.53 (  0.00%)       16.60 (  5.33%)
Amean    Elapsd-30       17.45 (  0.00%)       17.13 (  1.84%)
Amean    Elapsd-48       15.40 (  0.00%)       15.27 (  0.82%)

For a single thread, the benchmark completes 43.23% faster with this
patch applied with smaller benefits as the thread increases.  Similar,
notice the large reduction in most cases in system CPU usage.  The
overall CPU time is

               4.4.0       4.4.0
        kcompactd-v1r1 nodefrag-v1r3
User        10357.65    10438.33
System       3988.88     3543.94
Elapsed      2203.01     1634.41

Which is substantial. Now, the reclaim figures

                                 4.4.0       4.4.0
                          kcompactd-v1r1nodefrag-v1r3
Minor Faults                 128458477   278352931
Major Faults                   2174976         225
Swap Ins                      16904701           0
Swap Outs                     17359627           0
Allocation stalls                43611           0
DMA allocs                           0           0
DMA32 allocs                  19832646    19448017
Normal allocs                614488453   580941839
Movable allocs                       0           0
Direct pages scanned          24163800           0
Kswapd pages scanned                 0           0
Kswapd pages reclaimed               0           0
Direct pages reclaimed        20691346           0
Compaction stalls                42263           0
Compaction success                 938           0
Compaction failures              41325           0

This patch eliminates almost all swapping and direct reclaim activity.
There is still overhead but it's from NUMA balancing which does not
identify that it's pointless trying to do anything with this workload.

I also tried the thpscale benchmark which forces a corner case where
compaction can be used heavily and measures the latency of whether base
or huge pages were used

thpscale Fault Latencies
                                       4.4.0                 4.4.0
                              kcompactd-v1r1         nodefrag-v1r3
Amean    fault-base-1      5288.84 (  0.00%)     2817.12 ( 46.73%)
Amean    fault-base-3      6365.53 (  0.00%)     3499.11 ( 45.03%)
Amean    fault-base-5      6526.19 (  0.00%)     4363.06 ( 33.15%)
Amean    fault-base-7      7142.25 (  0.00%)     4858.08 ( 31.98%)
Amean    fault-base-12    13827.64 (  0.00%)    10292.11 ( 25.57%)
Amean    fault-base-18    18235.07 (  0.00%)    13788.84 ( 24.38%)
Amean    fault-base-24    21597.80 (  0.00%)    24388.03 (-12.92%)
Amean    fault-base-30    26754.15 (  0.00%)    19700.55 ( 26.36%)
Amean    fault-base-32    26784.94 (  0.00%)    19513.57 ( 27.15%)
Amean    fault-huge-1      4223.96 (  0.00%)     2178.57 ( 48.42%)
Amean    fault-huge-3      2194.77 (  0.00%)     2149.74 (  2.05%)
Amean    fault-huge-5      2569.60 (  0.00%)     2346.95 (  8.66%)
Amean    fault-huge-7      3612.69 (  0.00%)     2997.70 ( 17.02%)
Amean    fault-huge-12     3301.75 (  0.00%)     6727.02 (-103.74%)
Amean    fault-huge-18     6696.47 (  0.00%)     6685.72 (  0.16%)
Amean    fault-huge-24     8000.72 (  0.00%)     9311.43 (-16.38%)
Amean    fault-huge-30    13305.55 (  0.00%)     9750.45 ( 26.72%)
Amean    fault-huge-32     9981.71 (  0.00%)    10316.06 ( -3.35%)

The average time to fault pages is substantially reduced in the majority
of caseds but with the obvious caveat that fewer THPs are actually used
in this adverse workload

                                   4.4.0                 4.4.0
                          kcompactd-v1r1         nodefrag-v1r3
Percentage huge-1         0.71 (  0.00%)       14.04 (1865.22%)
Percentage huge-3        10.77 (  0.00%)       33.05 (206.85%)
Percentage huge-5        60.39 (  0.00%)       38.51 (-36.23%)
Percentage huge-7        45.97 (  0.00%)       34.57 (-24.79%)
Percentage huge-12       68.12 (  0.00%)       40.07 (-41.17%)
Percentage huge-18       64.93 (  0.00%)       47.82 (-26.35%)
Percentage huge-24       62.69 (  0.00%)       44.23 (-29.44%)
Percentage huge-30       43.49 (  0.00%)       55.38 ( 27.34%)
Percentage huge-32       50.72 (  0.00%)       51.90 (  2.35%)

                                 4.4.0       4.4.0
                          kcompactd-v1r1nodefrag-v1r3
Minor Faults                  37429143    47564000
Major Faults                      1916        1558
Swap Ins                          1466        1079
Swap Outs                      2936863      149626
Allocation stalls                62510           3
DMA allocs                           0           0
DMA32 allocs                   6566458     6401314
Normal allocs                216361697   216538171
Movable allocs                       0           0
Direct pages scanned          25977580       17998
Kswapd pages scanned                 0     3638931
Kswapd pages reclaimed               0      207236
Direct pages reclaimed         8833714          88
Compaction stalls               103349           5
Compaction success                 270           4
Compaction failures             103079           1

Note again that while this does swap as it's an aggressive workload, the
direct relcim activity and allocation stalls is substantially reduced.
There is some kswapd activity but ftrace showed that the kswapd activity
was due to normal wakeups from 4K pages being allocated.
Compaction-related stalls and activity are almost eliminated.

I also tried the stutter benchmark.  For this, I do not have figures for
NUMA but it's something that does impact UMA so I'll report what is
available

stutter
                                 4.4.0                 4.4.0
                        kcompactd-v1r1         nodefrag-v1r3
Min         mmap      7.3571 (  0.00%)      7.3438 (  0.18%)
1st-qrtle   mmap      7.5278 (  0.00%)     17.9200 (-138.05%)
2nd-qrtle   mmap      7.6818 (  0.00%)     21.6055 (-181.25%)
3rd-qrtle   mmap     11.0889 (  0.00%)     21.8881 (-97.39%)
Max-90%     mmap     27.8978 (  0.00%)     22.1632 ( 20.56%)
Max-93%     mmap     28.3202 (  0.00%)     22.3044 ( 21.24%)
Max-95%     mmap     28.5600 (  0.00%)     22.4580 ( 21.37%)
Max-99%     mmap     29.6032 (  0.00%)     25.5216 ( 13.79%)
Max         mmap   4109.7289 (  0.00%)   4813.9832 (-17.14%)
Mean        mmap     12.4474 (  0.00%)     19.3027 (-55.07%)

This benchmark is trying to fault an anonymous mapping while there is a
heavy IO load -- a scenario that desktop users used to complain about
frequently.  This shows a mix because the ideal case of mapping with THP
is not hit as often.  However, note that 99% of the mappings complete
13.79% faster.  The CPU usage here is particularly interesting

               4.4.0       4.4.0
        kcompactd-v1r1nodefrag-v1r3
User           67.50        0.99
System       1327.88       91.30
Elapsed      2079.00     2128.98

And once again we look at the reclaim figures

                                 4.4.0       4.4.0
                          kcompactd-v1r1nodefrag-v1r3
Minor Faults                 335241922  1314582827
Major Faults                       715         819
Swap Ins                             0           0
Swap Outs                            0           0
Allocation stalls               532723           0
DMA allocs                           0           0
DMA32 allocs                1822364341  1177950222
Normal allocs               1815640808  1517844854
Movable allocs                       0           0
Direct pages scanned          21892772           0
Kswapd pages scanned          20015890    41879484
Kswapd pages reclaimed        19961986    41822072
Direct pages reclaimed        21892741           0
Compaction stalls              1065755           0
Compaction success                 514           0
Compaction failures            1065241           0

Allocation stalls and all direct reclaim activity is eliminated as well
as compaction-related stalls.

THP gives impressive gains in some cases but only if they are quickly
available.  We're not going to reach the point where they are completely
free so lets take the costs out of the fast paths finally and defer the
cost to kswapd, kcompactd and khugepaged where it belongs.
Signed-off-by: NMel Gorman <mgorman@techsingularity.net>
Acked-by: NRik van Riel <riel@redhat.com>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Acked-by: NVlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Show how much memory is used for storing reclaimable and unreclaimable
in-kernel data structures allocated from slab caches.
Signed-off-by: NVladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

We can now print gfp_flags more human-readable.  Make use of this in
slab_out_of_memory() for SLUB and SLAB.  Also convert the SLAB variant
it to pr_warn() along the way.
Signed-off-by: NVlastimil Babka <vbabka@suse.cz>
Acked-by: NDavid Rientjes <rientjes@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Current implementation of pfmemalloc handling in SLAB has some problems.

1) pfmemalloc_active is set to true when there is just one or more
   pfmemalloc slabs in the system, but it is cleared when there is no
   pfmemalloc slab in one arbitrary kmem_cache.  So, pfmemalloc_active
   could be wrongly cleared.

2) Search to partial and free list doesn't happen when non-pfmemalloc
   object are not found in cpu cache.  Instead, allocating new slab
   happens and it is not optimal.

3) Even after sk_memalloc_socks() is disabled, cpu cache would keep
   pfmemalloc objects tagged with SLAB_OBJ_PFMEMALLOC.  It isn't cleared
   if sk_memalloc_socks() is disabled so it could cause problem.

4) If cpu cache is filled with pfmemalloc objects, it would cause slow
   down non-pfmemalloc allocation.

To me, current pointer tagging approach looks complex and fragile so this
patch re-implement whole thing instead of fixing problems one by one.

Design principle for new implementation is that

1) Don't disrupt non-pfmemalloc allocation in fast path even if
   sk_memalloc_socks() is enabled.  It's more likely case than pfmemalloc
   allocation.

2) Ensure that pfmemalloc slab is used only for pfmemalloc allocation.

3) Don't consider performance of pfmemalloc allocation in memory
   deficiency state.

As a result, all pfmemalloc alloc/free in memory tight state will be
handled in slow-path.  If there is non-pfmemalloc free object, it will be
returned first even for pfmemalloc user in fast-path so that performance
of pfmemalloc user isn't affected in normal case and pfmemalloc objects
will be kept as long as possible.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Tested-by: NMel Gorman <mgorman@techsingularity.net>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Returing values by reference is bad practice.  Instead, just use
function return value.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com>
Suggested-by: NChristoph Lameter <cl@linux.com>
Acked-by: NChristoph Lameter <cl@linux.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

SLAB needs an array to manage freed objects in a slab.  It is only used
if some objects are freed so we can use free object itself as this
array.  This requires additional branch in somewhat critical lock path
to check if it is first freed object or not but that's all we need.
Benefits is that we can save extra memory usage and reduce some
computational overhead by allocating a management array when new slab is
created.

Code change is rather complex than what we can expect from the idea, in
order to handle debugging feature efficiently.  If you want to see core
idea only, please remove '#if DEBUG' block in the patch.

Although this idea can apply to all caches whose size is larger than
management array size, it isn't applied to caches which have a
constructor.  If such cache's object is used for management array,
constructor should be called for it before that object is returned to
user.  I guess that overhead overwhelm benefit in that case so this idea
doesn't applied to them at least now.

For summary, from now on, slab management type is determined by
following logic.

1) if management array size is smaller than object size and no ctor, it
   becomes OBJFREELIST_SLAB.

2) if management array size is smaller than leftover, it becomes
   NORMAL_SLAB which uses leftover as a array.

3) if OFF_SLAB help to save memory than way 4), it becomes OFF_SLAB.
   It allocate a management array from the other cache so memory waste
   happens.

4) others become NORMAL_SLAB.  It uses dedicated internal memory in a
   slab as a management array so it causes memory waste.

In my system, without enabling CONFIG_DEBUG_SLAB, Almost caches become
OBJFREELIST_SLAB and NORMAL_SLAB (using leftover) which doesn't waste
memory.  Following is the result of number of caches with specific slab
management type.

TOTAL = OBJFREELIST + NORMAL(leftover) + NORMAL + OFF

/Before/
126 = 0 + 60 + 25 + 41

/After/
126 = 97 + 12 + 15 + 2

Result shows that number of caches that doesn't waste memory increase
from 60 to 109.

I did some benchmarking and it looks that benefit are more than loss.

Kmalloc: Repeatedly allocate then free test

/Before/
[    0.286809] 1. Kmalloc: Repeatedly allocate then free test
[    1.143674] 100000 times kmalloc(32) -> 116 cycles kfree -> 78 cycles
[    1.441726] 100000 times kmalloc(64) -> 121 cycles kfree -> 80 cycles
[    1.815734] 100000 times kmalloc(128) -> 168 cycles kfree -> 85 cycles
[    2.380709] 100000 times kmalloc(256) -> 287 cycles kfree -> 95 cycles
[    3.101153] 100000 times kmalloc(512) -> 370 cycles kfree -> 117 cycles
[    3.942432] 100000 times kmalloc(1024) -> 413 cycles kfree -> 156 cycles
[    5.227396] 100000 times kmalloc(2048) -> 622 cycles kfree -> 248 cycles
[    7.519793] 100000 times kmalloc(4096) -> 1102 cycles kfree -> 452 cycles

/After/
[    1.205313] 100000 times kmalloc(32) -> 117 cycles kfree -> 78 cycles
[    1.510526] 100000 times kmalloc(64) -> 124 cycles kfree -> 81 cycles
[    1.827382] 100000 times kmalloc(128) -> 130 cycles kfree -> 84 cycles
[    2.226073] 100000 times kmalloc(256) -> 177 cycles kfree -> 92 cycles
[    2.814747] 100000 times kmalloc(512) -> 286 cycles kfree -> 112 cycles
[    3.532952] 100000 times kmalloc(1024) -> 344 cycles kfree -> 141 cycles
[    4.608777] 100000 times kmalloc(2048) -> 519 cycles kfree -> 210 cycles
[    6.350105] 100000 times kmalloc(4096) -> 789 cycles kfree -> 391 cycles

In fact, I tested another idea implementing OBJFREELIST_SLAB with
extendable linked array through another freed object.  It can remove
memory waste completely but it causes more computational overhead in
critical lock path and it seems that overhead outweigh benefit.  So, this
patch doesn't include it.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.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: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

cache_init_objs() will be changed in following patch and current form
doesn't fit well for that change.  So, before doing it, this patch
separates debugging initialization.  This would cause two loop iteration
when debugging is enabled, but, this overhead seems too light than debug
feature itself so effect may not be visible.  This patch will greatly
simplify changes in cache_init_objs() in following patch.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.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: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Slab list should be fixed up after object is detached from the slab and
this happens at two places.  They do exactly same thing.  They will be
changed in the following patch, so, to reduce code duplication, this
patch factor out them and make it common function.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.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: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

To become an off slab, there are some constraints to avoid bootstrapping
problem and recursive call.  This can be avoided differently by simply
checking that corresponding kmalloc cache is ready and it's not a off
slab.  It would be more robust because static size checking can be
affected by cache size change or architecture type but dynamic checking
isn't.

One check 'freelist_cache->size > cachep->size / 2' is added to check
benefit of choosing off slab, because, now, there is no size constraint
which ensures enough advantage when selecting off slab.
Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.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: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>