Sven Schmidt [Fri, 24 Feb 2017 23:01:12 +0000 (15:01 -0800)]
lib: update LZ4 compressor module
Patch series "Update LZ4 compressor module", v7.
This patchset updates the LZ4 compression module to a version based on
LZ4 v1.7.3 allowing to use the fast compression algorithm aka LZ4 fast
which provides an "acceleration" parameter as a tradeoff between high
compression ratio and high compression speed.
We want to use LZ4 fast in order to support compression in lustre and
(mostly, based on that) investigate data reduction techniques in behalf
of storage systems.
Also, it will be useful for other users of LZ4 compression, as with LZ4
fast it is possible to enable applications to use fast and/or high
compression depending on the usecase. For instance, ZRAM is offering a
LZ4 backend and could benefit from an updated LZ4 in the kernel.
[PATCH 1/5] lib: Update LZ4 compressor module
[PATCH 2/5] lib/decompress_unlz4: Change module to work with new LZ4 module version
[PATCH 3/5] crypto: Change LZ4 modules to work with new LZ4 module version
[PATCH 4/5] fs/pstore: fs/squashfs: Change usage of LZ4 to work with new LZ4 version
[PATCH 5/5] lib/lz4: Remove back-compat wrappers
This patch (of 5):
Update the LZ4 kernel module to LZ4 v1.7.3 by Yann Collet. The kernel
module is inspired by the previous work by Chanho Min. The updated LZ4
module will not break existing code since the patchset contains
appropriate changes.
API changes:
New method LZ4_compress_fast which differs from the variant available in
kernel by the new acceleration parameter, allowing to trade compression
ratio for more compression speed and vice versa.
LZ4_decompress_fast is the respective decompression method, featuring a
very fast decoder (multiple GB/s per core), able to reach RAM speed in
multi-core systems. The decompressor allows to decompress data
compressed with LZ4 fast as well as the LZ4 HC (high compression)
algorithm.
Also the useful functions LZ4_decompress_safe_partial and
LZ4_compress_destsize were added. The latter reverses the logic by
trying to compress as much data as possible from source to dest while
the former aims to decompress partial blocks of data.
A bunch of streaming functions were also added which allow
compressig/decompressing data in multiple steps (so called "streaming
mode").
The methods lz4_compress and lz4_decompress_unknownoutputsize are now
known as LZ4_compress_default respectivley LZ4_decompress_safe. The old
methods will be removed since there's no callers left in the code.
...meaning that it currently is not being built as a module by anyone.
Lets remove the couple traces of modular infrastructure use, so that
when reading the code there is no doubt it is builtin-only.
Since module_init translates to device_initcall in the non-modular case,
the init ordering becomes slightly earlier when we change it to use
subsys_initcall as done here. However, since it is a self contained
test, this shouldn't be an issue and subsys_initcall seems like a better
fit for this particular case.
We also delete the MODULE_LICENSE tag since that information is now
contained at the top of the file in the comments.
Link: http://lkml.kernel.org/r/20170124225608.7319-1-paul.gortmaker@windriver.com Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Kostenzer Felix <fkostenzer@live.at> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Kees Cook [Fri, 24 Feb 2017 23:01:04 +0000 (15:01 -0800)]
rbtree: use designated initializers
Prepare to mark sensitive kernel structures for randomization by making
sure they're using designated initializers. These were identified
during allyesconfig builds of x86, arm, and arm64, with most initializer
fixes extracted from grsecurity.
Link: http://lkml.kernel.org/r/20161217010253.GA140470@beast Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David Howells <dhowells@redhat.com> Cc: Jie Chen <fykcee1@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Niklas Söderlund [Fri, 24 Feb 2017 23:01:01 +0000 (15:01 -0800)]
linux/kernel.h: fix DIV_ROUND_CLOSEST to support negative divisors
While working on a thermal driver I encounter a scenario where the
divisor could be negative, instead of adding local code to handle this I
though I first try to add support for this in DIV_ROUND_CLOSEST.
Add support to DIV_ROUND_CLOSEST for negative divisors if both dividend
and divisor variable types are signed. This should not alter current
behavior for users of the macro as previously negative divisors where
not supported.
Matthew Wilcox [Fri, 24 Feb 2017 23:00:58 +0000 (15:00 -0800)]
lib/find_bit.c: micro-optimise find_next_*_bit
This saves 32 bytes on my x86-64 build, mostly due to alignment
considerations and sharing more code between find_next_bit and
find_next_zero_bit, but it does save a couple of instructions.
There's really two parts to this commit:
- First, the first half of the test: (!nbits || start >= nbits) is
trivially a subset of the second half, since nbits and start are both
unsigned
- Second, while looking at the disassembly, I noticed that GCC was
predicting the branch taken. Since this is a failure case, it's
clearly the less likely of the two branches, so add an unlikely() to
override GCC's heuristics.
Bhumika Goyal [Fri, 24 Feb 2017 23:00:46 +0000 (15:00 -0800)]
kernel/ksysfs.c: add __ro_after_init to bin_attribute structure
The object notes_attr of type bin_attribute is not modified after
getting initailized by ksysfs_init. Apart from initialization in
ksysfs_init it is also passed as an argument to the function
sysfs_create_bin_file but this argument is of type const. Therefore,
add __ro_after_init to its declaration.
Viresh Kumar [Fri, 24 Feb 2017 23:00:44 +0000 (15:00 -0800)]
kernel/notifier.c: simplify expression
NOTIFY_STOP_MASK (0x8000) has only one bit set and there is no need to
compare output of "ret & NOTIFY_STOP_MASK" to NOTIFY_STOP_MASK. We just
need to make sure the output is non-zero, that's it.
Yisheng Xie [Fri, 24 Feb 2017 23:00:40 +0000 (15:00 -0800)]
mm balloon: umount balloon_mnt when removing vb device
With CONFIG_BALLOON_COMPACTION=y the kernel will mount balloon_mnt for
balloon page migration when we probe a virtio_balloon device. However
we do not unmount it when removing the device. Fix this.
Fixes: b1123ea6d3b3 ("mm: balloon: use general non-lru movable page feature") Link: http://lkml.kernel.org/r/1486531318-35189-1-git-send-email-xieyisheng1@huawei.com Signed-off-by: Yisheng Xie <xieyisheng1@huawei.com> Acked-by: Minchan Kim <minchan@kernel.org> Cc: Rafael Aquini <aquini@redhat.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Gioh Kim <gi-oh.kim@profitbricks.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Michal Hocko <mhocko@kernel.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Kees Cook [Fri, 24 Feb 2017 23:00:38 +0000 (15:00 -0800)]
bug: switch data corruption check to __must_check
The CHECK_DATA_CORRUPTION() macro was designed to have callers do
something meaningful/protective on failure. However, using "return
false" in the macro too strictly limits the design patterns of callers.
Instead, let callers handle the logic test directly, but make sure that
the result IS checked by forcing __must_check (which appears to not be
able to be used directly on macro expressions).
m68k: replace gcc specific macros with ones from compiler.h
There is <linux/compiler.h> which provides macros for various gcc
specific constructs. Eg: __weak for __attribute__((weak)). I've
cleaned all instances of gcc specific attributes with the right macros
for all files under /arch/m68k
Link: http://lkml.kernel.org/r/1485540901-1988-3-git-send-email-gidisrael@gmail.com Signed-off-by: Gideon Israel Dsouza <gidisrael@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Masahiro Yamada [Fri, 24 Feb 2017 23:00:29 +0000 (15:00 -0800)]
include/linux/iopoll.h: include <linux/ktime.h> instead of <linux/hrtimer.h>
The timer APIs this header needs are ktime_get(), ktime_add_us(), and
ktime_compare(). So, including <linux/ktime.h> seems enough. This
commit will cut unnecessary header file parsing.
Mike Frysinger [Fri, 24 Feb 2017 23:00:26 +0000 (15:00 -0800)]
uapi: mqueue.h: add missing linux/types.h include
Commit 63159f5dcccb ("uapi: Use __kernel_long_t in struct mq_attr")
changed the types from long to __kernel_long_t, but didn't add a
linux/types.h include. Code that tries to include this header directly
breaks:
/usr/include/linux/mqueue.h:26:2: error: unknown type name '__kernel_long_t'
__kernel_long_t mq_flags; /* message queue flags */
This also upsets configure tests for this header:
checking linux/mqueue.h usability... no
checking linux/mqueue.h presence... yes
configure: WARNING: linux/mqueue.h: present but cannot be compiled
configure: WARNING: linux/mqueue.h: check for missing prerequisite headers?
configure: WARNING: linux/mqueue.h: see the Autoconf documentation
configure: WARNING: linux/mqueue.h: section "Present But Cannot Be Compiled"
configure: WARNING: linux/mqueue.h: proceeding with the compiler's result
checking for linux/mqueue.h... no
Lafcadio Wluiki [Fri, 24 Feb 2017 23:00:23 +0000 (15:00 -0800)]
procfs: use an enum for possible hidepid values
Previously, the hidepid parameter was checked by comparing literal
integers 0, 1, 2. Let's add a proper enum for this, to make the
checking more expressive:
Alexey Dobriyan [Fri, 24 Feb 2017 23:00:20 +0000 (15:00 -0800)]
proc: less code duplication in /proc/*/cmdline
After staring at this code for a while I've figured using small 2-entry
array describing ARGV and ENVP is the way to address code duplication
critique.
Greg Thelen [Fri, 24 Feb 2017 23:00:08 +0000 (15:00 -0800)]
kasan: add memcg kmem_cache test
Make a kasan test which uses a SLAB_ACCOUNT slab cache. If the test is
run within a non default memcg, then it uncovers the bug fixed by
"kasan: drain quarantine of memcg slab objects"[1].
If run without fix [1] it shows "Slab cache still has objects", and the
kmem_cache structure is leaked.
Here's an unpatched kernel test:
Greg Thelen [Fri, 24 Feb 2017 23:00:05 +0000 (15:00 -0800)]
kasan: drain quarantine of memcg slab objects
Per memcg slab accounting and kasan have a problem with kmem_cache
destruction.
- kmem_cache_create() allocates a kmem_cache, which is used for
allocations from processes running in root (top) memcg.
- Processes running in non root memcg and allocating with either
__GFP_ACCOUNT or from a SLAB_ACCOUNT cache use a per memcg
kmem_cache.
- Kasan catches use-after-free by having kfree() and kmem_cache_free()
defer freeing of objects. Objects are placed in a quarantine.
- kmem_cache_destroy() destroys root and non root kmem_caches. It takes
care to drain the quarantine of objects from the root memcg's
kmem_cache, but ignores objects associated with non root memcg. This
causes leaks because quarantined per memcg objects refer to per memcg
kmem cache being destroyed.
To see the problem:
1) create a slab cache with kmem_cache_create(,,,SLAB_ACCOUNT,)
2) from non root memcg, allocate and free a few objects from cache
3) dispose of the cache with kmem_cache_destroy() kmem_cache_destroy()
will trigger a "Slab cache still has objects" warning indicating
that the per memcg kmem_cache structure was leaked.
Fix the leak by draining kasan quarantined objects allocated from non
root memcg.
Racing memcg deletion is tricky, but handled. kmem_cache_destroy() =>
shutdown_memcg_caches() => __shutdown_memcg_cache() => shutdown_cache()
flushes per memcg quarantined objects, even if that memcg has been
rmdir'd and gone through memcg_deactivate_kmem_caches().
This leak only affects destroyed SLAB_ACCOUNT kmem caches when kasan is
enabled. So I don't think it's worth patching stable kernels.
Link: http://lkml.kernel.org/r/1482257462-36948-1-git-send-email-gthelen@google.com Signed-off-by: Greg Thelen <gthelen@google.com> Reviewed-by: Vladimir Davydov <vdavydov.dev@gmail.com> Acked-by: Andrey 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: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Nathan Fontenot [Fri, 24 Feb 2017 23:00:02 +0000 (15:00 -0800)]
memory-hotplug: use dev_online for memhp_auto_online
Commit 31bc3858ea3e ("add automatic onlining policy for the newly added
memory") provides the capability to have added memory automatically
onlined during add, but this appears to be slightly broken.
The current implementation uses walk_memory_range() to call
online_memory_block, which uses memory_block_change_state() to online
the memory. Instead, we should be calling device_online() for the
memory block in online_memory_block(). This would online the memory
(the memory bus online routine memory_subsys_online() called from
device_online calls memory_block_change_state()) and properly update the
device struct offline flag.
As a result of the current implementation, attempting to remove a memory
block after adding it using auto online fails. This is because doing a
remove, for instance
Minchan Kim [Fri, 24 Feb 2017 22:59:59 +0000 (14:59 -0800)]
mm: do not access page->mapping directly on page_endio
With rw_page, page_endio is used for completing IO on a page and it
propagates write error to the address space if the IO fails. The
problem is it accesses page->mapping directly which might be okay for
file-backed pages but it shouldn't for anonymous page. Otherwise, it
can corrupt one of field from anon_vma under us and system goes panic
randomly.
swap_writepage
bdev_writepage
ops->rw_page
I encountered the BUG during developing new zram feature and it was
really hard to figure it out because it made random crash, somtime
mmap_sem lockdep, sometime other places where places never related to
zram/zsmalloc, and not reproducible with some configuration.
When I consider how that bug is subtle and people do fast-swap test with
brd, it's worth to add stable mark, I think.
Fixes: dd6bd0d9c7db ("swap: use bdev_read_page() / bdev_write_page()") Signed-off-by: Minchan Kim <minchan@kernel.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We are using the wrong flag value in task_numa_falt function. This can
result in us doing wrong numa fault statistics update, because we update
num_pages_migrate and numa_fault_locality etc based on the flag argument
passed.
mm/gup: check for protnone only if it is a PTE entry
Do the prot_none/FOLL_NUMA check after we are sure this is a THP pte.
Archs can implement prot_none such that it can return true for regular
pmd entries.
Yisheng Xie [Fri, 24 Feb 2017 22:59:48 +0000 (14:59 -0800)]
mm/zsmalloc: fix comment in zsmalloc
The class index and fullness group are not encoded in
(first)page->mapping any more, after commit 3783689a1aa8 ("zsmalloc:
introduce zspage structure"). Instead, they are store in struct zspage.
Yisheng Xie [Fri, 24 Feb 2017 22:59:42 +0000 (14:59 -0800)]
mm/zsmalloc: remove redundant SetPagePrivate2 in create_page_chain
We had used page->lru to link the component pages (except the first
page) of a zspage, and used INIT_LIST_HEAD(&page->lru) to init it.
Therefore, to get the last page's next page, which is NULL, we had to
use page flag PG_Private_2 to identify it.
But now, we use page->freelist to link all of the pages in zspage and
init the page->freelist as NULL for last page, so no need to use
PG_Private_2 anymore.
This remove redundant SetPagePrivate2 in create_page_chain and
ClearPagePrivate2 in reset_page(). Save a few cycles for migration of
zsmalloc page :)
Vinayak Menon [Fri, 24 Feb 2017 22:59:39 +0000 (14:59 -0800)]
mm: vmpressure: fix sending wrong events on underflow
At the end of a window period, if the reclaimed pages is greater than
scanned, an unsigned underflow can result in a huge pressure value and
thus a critical event. Reclaimed pages is found to go higher than
scanned because of the addition of reclaimed slab pages to reclaimed in
shrink_node without a corresponding increment to scanned pages.
Minchan Kim mentioned that this can also happen in the case of a THP
page where the scanned is 1 and reclaimed could be 512.
Link: http://lkml.kernel.org/r/1486641577-11685-1-git-send-email-vinmenon@codeaurora.org Signed-off-by: Vinayak Menon <vinmenon@codeaurora.org> Acked-by: Minchan Kim <minchan@kernel.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Anton Vorontsov <anton.vorontsov@linaro.org> Cc: Shiraz Hashim <shashim@codeaurora.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove the prototypes for shmem_mapping() and shmem_zero_setup() from
linux/mm.h, since they are already provided in linux/shmem_fs.h. But
shmem_fs.h must then provide the inline stub for shmem_mapping() when
CONFIG_SHMEM is not set, and a few more cfiles now need to #include it.
Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1702081658250.1549@eggly.anvils Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Gavin Shan [Fri, 24 Feb 2017 22:59:33 +0000 (14:59 -0800)]
mm/page_alloc: fix nodes for reclaim in fast path
When @node_reclaim_node isn't 0, the page allocator tries to reclaim
pages if the amount of free memory in the zones are below the low
watermark. On Power platform, none of NUMA nodes are scanned for page
reclaim because no nodes match the condition in zone_allows_reclaim().
On Power platform, RECLAIM_DISTANCE is set to 10 which is the distance
of Node-A to Node-A. So the preferred node even won't be scanned for
page reclaim.
size <<= 30;
p = malloc(size);
assert(p);
memset(p, 0, size);
end = time(NULL);
printf("Used time: %ld seconds\n", end - start);
sleep(3600);
return 0;
}
The system I use for testing has two NUMA nodes. Both have 128GB
memory. In below scnario, the page caches on node#0 should be reclaimed
when it encounters pressure to accommodate request of allocation.
zhong jiang [Fri, 24 Feb 2017 22:59:30 +0000 (14:59 -0800)]
mm/memory_hotplug.c: fix overflow in test_pages_in_a_zone()
When mainline introduced commit a96dfddbcc04 ("base/memory, hotplug: fix
a kernel oops in show_valid_zones()"), it obtained the valid start and
end pfn from the given pfn range. The valid start pfn can fix the
actual issue, but it introduced another issue. The valid end pfn will
may exceed the given end_pfn.
Although the incorrect overflow will not result in actual problem at
present, but I think it need to be fixed.
[toshi.kani@hpe.com: remove assumption that end_pfn is aligned by MAX_ORDER_NR_PAGES] Fixes: a96dfddbcc04 ("base/memory, hotplug: fix a kernel oops in show_valid_zones()") Link: http://lkml.kernel.org/r/1486467299-22648-1-git-send-email-zhongjiang@huawei.com Signed-off-by: zhong jiang <zhongjiang@huawei.com> Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
zhouxianrong [Fri, 24 Feb 2017 22:59:27 +0000 (14:59 -0800)]
zram: extend zero pages to same element pages
The idea is that without doing more calculations we extend zero pages to
same element pages for zram. zero page is special case of same element
page with zero element.
1. the test is done under android 7.0
2. startup too many applications circularly
3. sample the zero pages, same pages (none-zero element)
and total pages in function page_zero_filled
from the above data, the benefit is about 2.5% and up to 3% of total
swapout pages.
The defect of the patch is that when we recovery a page from non-zero
element the operations are low efficient for partial read.
This patch extends zero_page to same_page so if there is any user to
have monitored zero_pages, he will be surprised if the number is
increased but it's not harmful, I believe.
mm/page-writeback.c: place "not" inside of unlikely() statement in wb_domain_writeout_inc()
The likely/unlikely profiler noticed that the unlikely statement in
wb_domain_writeout_inc() is constantly wrong. This is due to the "not"
(!) being outside the unlikely statement. It is likely that
dom->period_time will be set, but unlikely that it wont be. Move the
not into the unlikely statement.
Link: http://lkml.kernel.org/r/20170206120035.3c2e2b91@gandalf.local.home Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
powerpc/mm/autonuma: switch ppc64 to its own implementation of saved write
With this our protnone becomes a present pte with READ/WRITE/EXEC bit
cleared. By default we also set _PAGE_PRIVILEGED on such pte. This is
now used to help us identify a protnone pte that as saved write bit.
For such pte, we will clear the _PAGE_PRIVILEGED bit. The pte still
remain non-accessible from both user and kernel.
mm/autonuma: let architecture override how the write bit should be stashed in a protnone pte.
Patch series "Numabalancing preserve write fix", v2.
This patch series address an issue w.r.t THP migration and autonuma
preserve write feature. migrate_misplaced_transhuge_page() cannot deal
with concurrent modification of the page. It does a page copy without
following the migration pte sequence. IIUC, this was done to keep the
migration simpler and at the time of implemenation we didn't had THP
page cache which would have required a more elaborate migration scheme.
That means thp autonuma migration expect the protnone with saved write
to be done such that both kernel and user cannot update the page
content. This patch series enables archs like ppc64 to do that. We are
good with the hash translation mode with the current code, because we
never create a hardware page table entry for a protnone pte.
This patch (of 2):
Autonuma preserves the write permission across numa fault to avoid
taking a writefault after a numa fault (Commit: b191f9b106ea " mm: numa:
preserve PTE write permissions across a NUMA hinting fault").
Architecture can implement protnone in different ways and some may
choose to implement that by clearing Read/ Write/Exec bit of pte.
Setting the write bit on such pte can result in wrong behaviour. Fix
this up by allowing arch to override how to save the write bit on a
protnone pte.
mm/autonuma: don't use set_pte_at when updating protnone ptes
Architectures like ppc64, use privilege access bit to mark pte non
accessible. This implies that kernel can do a copy_to_user to an
address marked for numa fault. This also implies that there can be a
parallel hardware update for the pte. set_pte_at cannot be used in such
scenarios. Hence switch the pte update to use ptep_get_and_clear and
set_pte_at combination.
[akpm@linux-foundation.org: remove unwanted ppc change, per Aneesh] Link: http://lkml.kernel.org/r/1486400776-28114-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/shmem.c: fix unlikely() test of info->seals to test only for WRITE and GROW
Running my likely/unlikely profiler, I discovered that the test in
shmem_write_begin() that tests for info->seals as unlikely, is always
incorrect. This is because shmem_get_inode() sets info->seals to have
F_SEAL_SEAL set by default, and it is unlikely to be cleared when
shmem_write_begin() is called. Thus, the if statement is very likely.
But as the if statement block only cares about F_SEAL_WRITE and
F_SEAL_GROW, change the test to only test those two bits.
Link: http://lkml.kernel.org/r/20170203105656.7aec6237@gandalf.local.home Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Hugh Dickins <hughd@google.com> Cc: David Herrmann <dh.herrmann@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Fri, 24 Feb 2017 22:59:07 +0000 (14:59 -0800)]
mm, vmscan: clear PGDAT_WRITEBACK when zone is balanced
Hillf Danton pointed out that since commit 1d82de618dd ("mm, vmscan:
make kswapd reclaim in terms of nodes") that PGDAT_WRITEBACK is no
longer cleared.
It was not noticed as triggering it requires pages under writeback to
cycle twice through the LRU and before kswapd gets stalled.
Historically, such issues tended to occur on small machines writing
heavily to slow storage such as a USB stick.
Once kswapd stalls, direct reclaim stalls may be higher but due to the
fact that memory pressure is required, it would not be very noticable.
Michal Hocko suggested removing the flag entirely but the conservative
fix is to restore the intended PGDAT_WRITEBACK behaviour and clear the
flag when a suitable zone is balanced.
Fixes: 1d82de618ddd ("mm, vmscan: make kswapd reclaim in terms of nodes") Link: http://lkml.kernel.org/r/20170203203222.gq7hk66yc36lpgtb@suse.de Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ross Zwisler [Fri, 24 Feb 2017 22:59:04 +0000 (14:59 -0800)]
drm: remove unnecessary fault wrappers
The fault wrappers drm_vm_fault(), drm_vm_shm_fault(),
drm_vm_dma_fault() and drm_vm_sg_fault() used to provide extra logic
beyond what was in the "drm_do_*" versions of these functions, but as of
commit ca0b07d9a969 ("drm: convert drm from nopage to fault") they are
just unnecessary wrappers that do nothing.
Remove them, and rename the the drm_do_* fault handlers to remove the
"do_" since they no longer have corresponding wrappers.
Link: http://lkml.kernel.org/r/1486155698-25717-1-git-send-email-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Sean Paul <seanpaul@chromium.org> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Fri, 24 Feb 2017 22:58:53 +0000 (14:58 -0800)]
vmalloc: back off when the current task is killed
__vmalloc_area_node() allocates pages to cover the requested vmalloc
size. This can be a lot of memory. If the current task is killed by
the OOM killer, and thus has an unlimited access to memory reserves, it
can consume all the memory theoretically. Fix this by checking for
fatal_signal_pending and back off early.
Link: http://lkml.kernel.org/r/20170201092706.9966-4-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jaewon Kim [Fri, 24 Feb 2017 22:58:50 +0000 (14:58 -0800)]
mm: cma: print allocation failure reason and bitmap status
There are many reasons of CMA allocation failure such as EBUSY, ENOMEM,
EINTR. But we did not know error reason so far. This patch prints the
error value.
Additionally if CONFIG_CMA_DEBUG is enabled, this patch shows bitmap
status to know available pages. Actually CMA internally tries on all
available regions because some regions can be failed because of EBUSY.
Bitmap status is useful to know in detail on both ENONEM and EBUSY;
ENOMEM: not tried at all because of no available region
it could be too small total region or could be fragmentation issue
EBUSY: tried some region but all failed
If CONFIG_CMA_DEBUG is enabled, avabile pages also will be shown as
concatenated size@position format. So 4@572 means that there are 4
available pages at 572 position starting from 0 position.
[2: Binder:714_1: 744] cma: number of available pages: 4@572+7@585+7@601+8@632+38@730+166@1114+127@1921=> 357 free of 2048 total pages
Link: http://lkml.kernel.org/r/1485909785-3952-1-git-send-email-jaewon31.kim@samsung.com Signed-off-by: Jaewon Kim <jaewon31.kim@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Laura Abbott <labbott@redhat.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>
David Rientjes [Fri, 24 Feb 2017 22:58:47 +0000 (14:58 -0800)]
mm, madvise: fail with ENOMEM when splitting vma will hit max_map_count
If madvise(2) advice will result in the underlying vma being split and
the number of areas mapped by the process will exceed
/proc/sys/vm/max_map_count as a result, return ENOMEM instead of EAGAIN.
EAGAIN is returned by madvise(2) when a kernel resource, such as slab,
is temporarily unavailable. It indicates that userspace should retry
the advice in the near future. This is important for advice such as
MADV_DONTNEED which is often used by malloc implementations to free
memory back to the system: we really do want to free memory back when
madvise(2) returns EAGAIN because slab allocations (for vmas, anon_vmas,
or mempolicies) cannot be allocated.
Encountering /proc/sys/vm/max_map_count is not a temporary failure,
however, so return ENOMEM to indicate this is a more serious issue. A
followup patch to the man page will specify this behavior.
Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1701241431120.42507@chino.kir.corp.google.com Signed-off-by: David Rientjes <rientjes@google.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Lucas Stach [Fri, 24 Feb 2017 22:58:44 +0000 (14:58 -0800)]
mm: wire up GFP flag passing in dma_alloc_from_contiguous
The callers of the DMA alloc functions already provide the proper
context GFP flags. Make sure to pass them through to the CMA allocator,
to make the CMA compaction context aware.
Link: http://lkml.kernel.org/r/20170127172328.18574-3-l.stach@pengutronix.de Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Alexander Graf <agraf@suse.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>
Lucas Stach [Fri, 24 Feb 2017 22:58:41 +0000 (14:58 -0800)]
mm: cma_alloc: allow to specify GFP mask
Most users of this interface just want to use it with the default
GFP_KERNEL flags, but for cases where DMA memory is allocated it may be
called from a different context.
No functional change yet, just passing through the flag to the
underlying alloc_contig_range function.
Link: http://lkml.kernel.org/r/20170127172328.18574-2-l.stach@pengutronix.de Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Alexander Graf <agraf@suse.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>
Lucas Stach [Fri, 24 Feb 2017 22:58:37 +0000 (14:58 -0800)]
mm: alloc_contig_range: allow to specify GFP mask
Currently alloc_contig_range assumes that the compaction should be done
with the default GFP_KERNEL flags. This is probably right for all
current uses of this interface, but may change as CMA is used in more
use-cases (including being the default DMA memory allocator on some
platforms).
Change the function prototype, to allow for passing through the GFP mask
set by upper layers.
Also respect global restrictions by applying memalloc_noio_flags to the
passed in flags.
Link: http://lkml.kernel.org/r/20170127172328.18574-1-l.stach@pengutronix.de Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Alexander Graf <agraf@suse.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>
Mike Rapoport [Fri, 24 Feb 2017 22:58:31 +0000 (14:58 -0800)]
userfaultfd_copy: return -ENOSPC in case mm has gone
In the non-cooperative userfaultfd case, the process exit may race with
outstanding mcopy_atomic called by the uffd monitor. Returning -ENOSPC
instead of -EINVAL when mm is already gone will allow uffd monitor to
distinguish this case from other error conditions.
Link: http://lkml.kernel.org/r/1485542673-24387-6-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mike Rapoport [Fri, 24 Feb 2017 22:58:28 +0000 (14:58 -0800)]
userfaultfd: mcopy_atomic: return -ENOENT when no compatible VMA found
The memory mapping of a process may change between #PF event and the
call to mcopy_atomic that comes to resolve the page fault. In such
case, there will be no VMA covering the range passed to mcopy_atomic or
the VMA will not have userfaultfd context.
To allow uffd monitor to distinguish those case from other errors, let's
return -ENOENT instead of -EINVAL.
Note, that despite availability of UFFD_EVENT_UNMAP there still might be
race between the processing of UFFD_EVENT_UNMAP and outstanding
mcopy_atomic in case of non-cooperative uffd usage.
[rppt@linux.vnet.ibm.com: update cases returning -ENOENT] Link: http://lkml.kernel.org/r/20170207150249.GA6709@rapoport-lnx
[aarcange@redhat.com: merge fix]
[akpm@linux-foundation.org: fix the merge fix] Link: http://lkml.kernel.org/r/1485542673-24387-5-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mike Rapoport [Fri, 24 Feb 2017 22:58:22 +0000 (14:58 -0800)]
userfaultfd: non-cooperative: add event for memory unmaps
When a non-cooperative userfaultfd monitor copies pages in the
background, it may encounter regions that were already unmapped.
Addition of UFFD_EVENT_UNMAP allows the uffd monitor to track precisely
changes in the virtual memory layout.
Since there might be different uffd contexts for the affected VMAs, we
first should create a temporary representation for the unmap event for
each uffd context and then notify them one by one to the appropriate
userfault file descriptors.
The event notification occurs after the mmap_sem has been released.
Mike Rapoport [Fri, 24 Feb 2017 22:58:19 +0000 (14:58 -0800)]
mm: call vm_munmap in munmap syscall instead of using open coded version
Patch series "userfaultfd: non-cooperative: better tracking for mapping
changes", v2.
These patches try to address issues I've encountered during integration
of userfaultfd with CRIU.
Previously added userfaultfd events for fork(), madvise() and mremap()
unfortunately do not cover all possible changes to a process virtual
memory layout required for uffd monitor.
When one or more VMAs is removed from the process mm, the external uffd
monitor has no way to detect those changes and will attempt to fill the
removed regions with userfaultfd_copy.
Another problematic event is the exit() of the process. Here again, the
external uffd monitor will try to use userfaultfd_copy, although mm
owning the memory has already gone.
The first patch in the series is a minor cleanup and it's not strictly
related to the rest of the series.
The patches 2 and 3 below add UFFD_EVENT_UNMAP and UFFD_EVENT_EXIT to
allow the uffd monitor track changes in the memory layout of a process.
The patches 4 and 5 amend error codes returned by userfaultfd_copy to
make the uffd monitor able to cope with races that might occur between
delivery of unmap and exit events and outstanding userfaultfd_copy's.
This patch (of 5):
Commit dc0ef0df7b6a ("mm: make mmap_sem for write waits killable for mm
syscalls") replaced call to vm_munmap in munmap syscall with open coded
version to allow different waits on mmap_sem in munmap syscall and
vm_munmap.
Now both functions use down_write_killable, so we can restore the call
to vm_munmap from the munmap system call.
Link: http://lkml.kernel.org/r/1485542673-24387-2-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm: fix handling PTE-mapped THPs in page_referenced()
For PTE-mapped THP page_check_address_transhuge() is not adequate: it
cannot find all relevant PTEs, only the first one. It means we can miss
some references of the page and it can result in suboptimal decisions by
vmscan.
Let's switch it to page_vma_mapped_walk().
I don't think it's subject for stable@: it's not fatal. The only side
effect is that THP can be swapped out when it shouldn't.
Link: http://lkml.kernel.org/r/20170129173858.45174-4-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Yisheng Xie [Fri, 24 Feb 2017 22:57:39 +0000 (14:57 -0800)]
mm/hotplug: enable memory hotplug for non-lru movable pages
We had considered all of the non-lru pages as unmovable before commit bda807d44454 ("mm: migrate: support non-lru movable page migration").
But now some of non-lru pages like zsmalloc, virtio-balloon pages also
become movable. So we can offline such blocks by using non-lru page
migration.
This patch straightforwardly adds non-lru migration code, which means
adding non-lru related code to the functions which scan over pfn and
collect pages to be migrated and isolate them before migration.
Yisheng Xie [Fri, 24 Feb 2017 22:57:35 +0000 (14:57 -0800)]
HWPOISON: soft offlining for non-lru movable page
Extend soft offlining framework to support non-lru page, which already
support migration after commit bda807d44454 ("mm: migrate: support
non-lru movable page migration")
When memory corrected errors occur on a non-lru movable page, we can
choose to stop using it by migrating data onto another page and disable
the original (maybe half-broken) one.
Yisheng Xie [Fri, 24 Feb 2017 22:57:32 +0000 (14:57 -0800)]
mm/migration: make isolate_movable_page always defined
Define isolate_movable_page as a static inline function when
CONFIG_MIGRATION is not enable. It should return -EBUSY here which
means failed to isolate movable pages.
This patch do not have any functional change but prepare for later
patch.
Yisheng Xie [Fri, 24 Feb 2017 22:57:29 +0000 (14:57 -0800)]
mm/migration: make isolate_movable_page() return int type
Patch series "HWPOISON: soft offlining for non-lru movable page", v6.
After Minchan's commit bda807d44454 ("mm: migrate: support non-lru
movable page migration"), some type of non-lru page like zsmalloc and
virtio-balloon page also support migration.
Therefore, we can:
1) soft offlining no-lru movable pages, which means when memory
corrected errors occur on a non-lru movable page, we can stop to use
it by migrating data onto another page and disable the original
(maybe half-broken) one.
2) enable memory hotplug for non-lru movable pages, i.e. we may offline
blocks, which include such pages, by using non-lru page migration.
This patchset is heavily dependent on non-lru movable page migration.
This patch (of 4):
Change the return type of isolate_movable_page() from bool to int. It
will return 0 when isolate movable page successfully, and return -EBUSY
when it isolates failed.
There is no functional change within this patch but prepare for later
patch.
Vitaly Wool [Fri, 24 Feb 2017 22:57:26 +0000 (14:57 -0800)]
z3fold: add kref refcounting
With both coming and already present locking optimizations, introducing
kref to reference-count z3fold objects is the right thing to do.
Moreover, it makes buddied list no longer necessary, and allows for a
simpler handling of headless pages.
Vitaly Wool [Fri, 24 Feb 2017 22:57:23 +0000 (14:57 -0800)]
z3fold: use per-page spinlock
Most of z3fold operations are in-page, such as modifying z3fold page
header or moving z3fold objects within a page. Taking per-pool spinlock
to protect per-page objects is therefore suboptimal, and the idea of
having a per-page spinlock (or rwlock) has been around for some time.
This patch implements spinlock-based per-page locking mechanism which is
lightweight enough to normally fit ok into the z3fold header.
Link: http://lkml.kernel.org/r/20170131214438.433e0a5fda908337b63206d3@gmail.com Signed-off-by: Vitaly Wool <vitalywool@gmail.com> Reviewed-by: Dan Streetman <ddstreet@ieee.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Vitaly Wool [Fri, 24 Feb 2017 22:57:20 +0000 (14:57 -0800)]
z3fold: extend compaction function
z3fold_compact_page() currently only handles the situation when there's
a single middle chunk within the z3fold page. However it may be worth
it to move middle chunk closer to either first or last chunk, whichever
is there, if the gap between them is big enough.
This patch adds the relevant code, using BIG_CHUNK_GAP define as a
threshold for middle chunk to be worth moving.
Link: http://lkml.kernel.org/r/20170131214334.c4f3eac9a477af0fa9a22c46@gmail.com Signed-off-by: Vitaly Wool <vitalywool@gmail.com> Reviewed-by: Dan Streetman <ddstreet@ieee.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Vitaly Wool [Fri, 24 Feb 2017 22:57:17 +0000 (14:57 -0800)]
z3fold: fix header size related issues
Currently the whole kernel build will be stopped if the size of struct
z3fold_header is greater than the size of one chunk, which is 64 bytes
by default. This patch instead defines the offset for z3fold objects as
the size of the z3fold header in chunks.
Fixed also are the calculation of num_free_chunks() and the address to
move the middle chunk to in case of in-page compaction in
z3fold_compact_page().
Link: http://lkml.kernel.org/r/20170131214057.d98677032bc7b1c6c59a80c9@gmail.com Signed-off-by: Vitaly Wool <vitalywool@gmail.com> Reviewed-by: Dan Streetman <ddstreet@ieee.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dan Williams [Fri, 24 Feb 2017 22:57:12 +0000 (14:57 -0800)]
mm: fix get_user_pages() vs device-dax pud mappings
A new unit test for the device-dax 1GB enabling currently fails with
this warning before hanging the test thread:
WARNING: CPU: 0 PID: 21 at lib/percpu-refcount.c:155 percpu_ref_switch_to_atomic_rcu+0x1e3/0x1f0
percpu ref (dax_pmem_percpu_release [dax_pmem]) <= 0 (0) after switching to atomic
[..]
CPU: 0 PID: 21 Comm: rcuos/1 Tainted: G O 4.10.0-rc7-next-20170207+ #944
[..]
Call Trace:
dump_stack+0x86/0xc3
__warn+0xcb/0xf0
warn_slowpath_fmt+0x5f/0x80
? rcu_nocb_kthread+0x27a/0x510
? dax_pmem_percpu_exit+0x50/0x50 [dax_pmem]
percpu_ref_switch_to_atomic_rcu+0x1e3/0x1f0
? percpu_ref_exit+0x60/0x60
rcu_nocb_kthread+0x339/0x510
? rcu_nocb_kthread+0x27a/0x510
kthread+0x101/0x140
The get_user_pages() path needs to arrange for references to be taken
against the dev_pagemap instance backing the pud mapping. Refactor the
existing __gup_device_huge_pmd() to also account for the pud case.
Link: http://lkml.kernel.org/r/148653181153.38226.9605457830505509385.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Jiang [Fri, 24 Feb 2017 22:57:08 +0000 (14:57 -0800)]
mm: replace FAULT_FLAG_SIZE with parameter to huge_fault
Since the introduction of FAULT_FLAG_SIZE to the vm_fault flag, it has
been somewhat painful with getting the flags set and removed at the
correct locations. More than one kernel oops was introduced due to
difficulties of getting the placement correctly.
Remove the flag values and introduce an input parameter to huge_fault
that indicates the size of the page entry. This makes the code easier
to trace and should avoid the issues we see with the fault flags where
removal of the flag was necessary in the fallback paths.
Link: http://lkml.kernel.org/r/148615748258.43180.1690152053774975329.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Jiang [Fri, 24 Feb 2017 22:57:05 +0000 (14:57 -0800)]
dax: support for transparent PUD pages for device DAX
Add transparent huge PUD pages support for device DAX by adding a
pud_fault handler.
Link: http://lkml.kernel.org/r/148545060002.17912.6765687780007547551.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Wilcox [Fri, 24 Feb 2017 22:57:02 +0000 (14:57 -0800)]
mm, x86: add support for PUD-sized transparent hugepages
The current transparent hugepage code only supports PMDs. This patch
adds support for transparent use of PUDs with DAX. It does not include
support for anonymous pages. x86 support code also added.
Most of this patch simply parallels the work that was done for huge
PMDs. The only major difference is how the new ->pud_entry method in
mm_walk works. The ->pmd_entry method replaces the ->pte_entry method,
whereas the ->pud_entry method works along with either ->pmd_entry or
->pte_entry. The pagewalk code takes care of locking the PUD before
calling ->pud_walk, so handlers do not need to worry whether the PUD is
stable.
Dave Jiang [Fri, 24 Feb 2017 22:56:59 +0000 (14:56 -0800)]
mm,fs,dax: change ->pmd_fault to ->huge_fault
Patch series "1G transparent hugepage support for device dax", v2.
The following series implements support for 1G trasparent hugepage on
x86 for device dax. The bulk of the code was written by Mathew Wilcox a
while back supporting transparent 1G hugepage for fs DAX. I have
forward ported the relevant bits to 4.10-rc. The current submission has
only the necessary code to support device DAX.
Comments from Dan Williams: So the motivation and intended user of this
functionality mirrors the motivation and users of 1GB page support in
hugetlbfs. Given expected capacities of persistent memory devices an
in-memory database may want to reduce tlb pressure beyond what they can
already achieve with 2MB mappings of a device-dax file. We have
customer feedback to that effect as Willy mentioned in his previous
version of these patches [1].
[1]: https://lkml.org/lkml/2016/1/31/52
Comments from Nilesh @ Oracle:
There are applications which have a process model; and if you assume
10,000 processes attempting to mmap all the 6TB memory available on a
server; we are looking at the following:
As you can see with 2M pages, this system will use up an exorbitant
amount of DRAM to hold the page tables; but the 1G pages finally brings
it down to a reasonable level. Memory sizes will keep increasing; so
this number will keep increasing.
An argument can be made to convert the applications from process model
to thread model, but in the real world that may not be always practical.
Hopefully this helps explain the use case where this is valuable.
This patch (of 3):
In preparation for adding the ability to handle PUD pages, convert
vm_operations_struct.pmd_fault to vm_operations_struct.huge_fault. The
vm_fault structure is extended to include a union of the different page
table pointers that may be needed, and three flag bits are reserved to
indicate which type of pointer is in the union.
[ross.zwisler@linux.intel.com: remove unused function ext4_dax_huge_fault()] Link: http://lkml.kernel.org/r/1485813172-7284-1-git-send-email-ross.zwisler@linux.intel.com
[dave.jiang@intel.com: clear PMD or PUD size flags when in fall through path] Link: http://lkml.kernel.org/r/148589842696.5820.16078080610311444794.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545058784.17912.6353162518188733642.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Fri, 24 Feb 2017 22:56:56 +0000 (14:56 -0800)]
mm, page_alloc: use static global work_struct for draining per-cpu pages
As suggested by Vlastimil Babka and Tejun Heo, this patch uses a static
work_struct to co-ordinate the draining of per-cpu pages on the
workqueue. Only one task can drain at a time but this is better than
the previous scheme that allowed multiple tasks to send IPIs at a time.
One consideration is whether parallel requests should synchronise
against each other. This patch does not synchronise for a global drain
as the common case for such callers is expected to be multiple parallel
direct reclaimers competing for pages when the watermark is close to
min. Draining the per-cpu list is unlikely to make much progress and
serialising the drain is of dubious merit. Drains are synchonrised for
callers such as memory hotplug and CMA that care about the drain being
complete when the function returns.
Vlastimil Babka [Fri, 24 Feb 2017 22:56:53 +0000 (14:56 -0800)]
mm, page_alloc: don't check cpuset allowed twice in fast-path
Since commit 682a3385e773 ("mm, page_alloc: inline the fast path of the
zonelist iterator") we replace a NULL nodemask with
cpuset_current_mems_allowed in the fast path, so that
get_page_from_freelist() filters nodes allowed by the cpuset via
for_next_zone_zonelist_nodemask().
In that case it's pointless to additionaly check __cpuset_zone_allowed()
in each iteration, which we can avoid by not adding ALLOC_CPUSET to
alloc_flags in that scenario.
This saves some cycles in the allocator fast path on systems with one or
more non-root cpuset configured. In the slow path, ALLOC_CPUSET is
reset according to __alloc_pages_slowpath(). Without configured
cpusets, this code is disabled by a static key.
Vlastimil Babka [Fri, 24 Feb 2017 22:56:50 +0000 (14:56 -0800)]
mm, page_alloc: remove redundant checks from alloc fastpath
The allocation fast path contains two similar checks for zoneref->zone
being NULL, where zoneref points either to the first zone in the
zonelist, or to the preferred zone. These can be NULL either due to
empty zonelist, or no zone being compatible with given nodemask or
task's cpuset.
These checks are unnecessary, because the zonelist walks in
first_zones_zonelist() and get_page_from_freelist() handle a NULL
starting zoneref->zone or preferred_zoneref->zone safely. It's safe to
fallback to __alloc_pages_slowpath() where we also have the check early
enough.
Minchan Kim [Fri, 24 Feb 2017 22:56:47 +0000 (14:56 -0800)]
zram: remove waitqueue for IO done
zram_reset_device() waits for ongoing writepage pages to be completed by
zram->refcount logic. However, it's pointless because before the reset,
we prevent further opening of zram by zram->claim and flush all of
pending IO by fsync_bdev so there should be no pending IO at the
zram_reset_device().
So let's remove that code which is even broken due to the lack of
wake_up elsewhere.
Link: http://lkml.kernel.org/r/1485145031-11661-1-git-send-email-minchan@kernel.org Signed-off-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Dave Jiang [Fri, 24 Feb 2017 22:56:41 +0000 (14:56 -0800)]
mm, fs: reduce fault, page_mkwrite, and pfn_mkwrite to take only vmf
->fault(), ->page_mkwrite(), and ->pfn_mkwrite() calls do not need to
take a vma and vmf parameter when the vma already resides in vmf.
Remove the vma parameter to simplify things.
[arnd@arndb.de: fix ARM build] Link: http://lkml.kernel.org/r/20170125223558.1451224-1-arnd@arndb.de Link: http://lkml.kernel.org/r/148521301778.19116.10840599906674778980.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Darrick J. Wong <darrick.wong@oracle.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Fri, 24 Feb 2017 22:56:38 +0000 (14:56 -0800)]
mm, page_alloc: only use per-cpu allocator for irq-safe requests
Many workloads that allocate pages are not handling an interrupt at a
time. As allocation requests may be from IRQ context, it's necessary to
disable/enable IRQs for every page allocation. This cost is the bulk of
the free path but also a significant percentage of the allocation path.
This patch alters the locking and checks such that only irq-safe
allocation requests use the per-cpu allocator. All others acquire the
irq-safe zone->lock and allocate from the buddy allocator. It relies on
disabling preemption to safely access the per-cpu structures. It could
be slightly modified to avoid soft IRQs using it but it's not clear it's
worthwhile.
This modification may slow allocations from IRQ context slightly but the
main gain from the per-cpu allocator is that it scales better for
allocations from multiple contexts. There is an implicit assumption
that intensive allocations from IRQ contexts on multiple CPUs from a
single NUMA node are rare and that the fast majority of scaling issues
are encountered in !IRQ contexts such as page faulting. It's worth
noting that this patch is not required for a bulk page allocator but it
significantly reduces the overhead.
The following is results from a page allocator micro-benchmark. Only
order-0 is interesting as higher orders do not use the per-cpu allocator
This is the alloc, free and total overhead of allocating order-0 pages
in batches of 1 page up to 16384 pages. Avoiding disabling/enabling
overhead massively reduces overhead. Alloc overhead is roughly reduced
by 14-20% in most cases. The free path is reduced by 26-46% and the
total reduction is significant.
Many users require zeroing of pages from the page allocator which is the
vast cost of allocation. Hence, the impact on a basic page faulting
benchmark is not that significant
This is from aim9 and the most notable outcome is that fault variability
is reduced by the patch. The headline improvement is small as the
overall fault cost, zeroing, page table insertion etc dominate relative
to disabling/enabling IRQs in the per-cpu allocator.
Similarly, little benefit was seen on networking benchmarks both
localhost and between physical server/clients where other costs
dominate. It's possible that this will only be noticable on very high
speed networks.
Jesper Dangaard Brouer independently tested this with a separate
microbenchmark from
https://github.com/netoptimizer/prototype-kernel/tree/master/kernel/mm/bench
Pulling cpu hotplug locks inside the page allocator is just too
dangerous. Let's remove the dependency by dropping get_online_cpus()
from drain_all_pages. This is not so simple though because now we do
not have a protection against cpu hotplug which means 2 things:
- the work item might be executed on a different cpu in worker from
unbound pool so it doesn't run on pinned on the cpu
- we have to make sure that we do not race with page_alloc_cpu_dead
calling drain_pages_zone
Disabling preemption in drain_local_pages_wq will solve the first
problem drain_local_pages will determine its local CPU from the WQ
context which will be stable after that point, page_alloc_cpu_dead is
pinned to the CPU already. The later condition is achieved by disabling
IRQs in drain_pages_zone.
Fixes: mm, page_alloc: drain per-cpu pages from workqueue context Link: http://lkml.kernel.org/r/20170207201950.20482-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mel Gorman [Fri, 24 Feb 2017 22:56:32 +0000 (14:56 -0800)]
mm, page_alloc: drain per-cpu pages from workqueue context
The per-cpu page allocator can be drained immediately via
drain_all_pages() which sends IPIs to every CPU. In the next patch, the
per-cpu allocator will only be used for interrupt-safe allocations which
prevents draining it from IPI context. This patch uses workqueues to
drain the per-cpu lists instead.
This is slower but no slowdown during intensive reclaim was measured and
the paths that use drain_all_pages() are not that sensitive to
performance. This is particularly true as the path would only be
triggered when reclaim is failing. It also makes a some sense to avoid
storming a machine with IPIs when it's under memory pressure. Arguably,
it should be further adjusted so that only one caller at a time is
draining pages but it's beyond the scope of the current patch.
Mel Gorman [Fri, 24 Feb 2017 22:56:29 +0000 (14:56 -0800)]
mm, page_alloc: split alloc_pages_nodemask()
alloc_pages_nodemask does a number of preperation steps that determine
what zones can be used for the allocation depending on a variety of
factors. This is fine but a hypothetical caller that wanted multiple
order-0 pages has to do the preparation steps multiple times. This
patch structures __alloc_pages_nodemask such that it's relatively easy
to build a bulk order-0 page allocator. There is no functional change.
Mel Gorman [Fri, 24 Feb 2017 22:56:26 +0000 (14:56 -0800)]
mm, page_alloc: split buffered_rmqueue()
Patch series "Use per-cpu allocator for !irq requests and prepare for a
bulk allocator", v5.
This series is motivated by a conversation led by Jesper Dangaard Brouer
at the last LSF/MM proposing a generic page pool for DMA-coherent pages.
Part of his motivation was due to the overhead of allocating multiple
order-0 that led some drivers to use high-order allocations and
splitting them. This is very slow in some cases.
The first two patches in this series restructure the page allocator such
that it is relatively easy to introduce an order-0 bulk page allocator.
A patch exists to do that and has been handed over to Jesper until an
in-kernel users is created. The third patch prevents the per-cpu
allocator being drained from IPI context as that can potentially corrupt
the list after patch four is merged. The final patch alters the per-cpu
alloctor to make it exclusive to !irq requests. This cuts
allocation/free overhead by roughly 30%.
Performance tests from both Jesper and me are included in the patch.
This patch (of 4):
buffered_rmqueue removes a page from a given zone and uses the per-cpu
list for order-0. This is fine but a hypothetical caller that wanted
multiple order-0 pages has to disable/reenable interrupts multiple
times. This patch structures buffere_rmqueue such that it's relatively
easy to build a bulk order-0 page allocator. There is no functional
change.
Johannes Weiner [Fri, 24 Feb 2017 22:56:23 +0000 (14:56 -0800)]
mm: vmscan: move dirty pages out of the way until they're flushed
We noticed a performance regression when moving hadoop workloads from
3.10 kernels to 4.0 and 4.6. This is accompanied by increased pageout
activity initiated by kswapd as well as frequent bursts of allocation
stalls and direct reclaim scans. Even lowering the dirty ratios to the
equivalent of less than 1% of memory would not eliminate the issue,
suggesting that dirty pages concentrate where the scanner is looking.
This can be traced back to recent efforts of thrash avoidance. Where
3.10 would not detect refaulting pages and continuously supply clean
cache to the inactive list, a thrashing workload on 4.0+ will detect and
activate refaulting pages right away, distilling used-once pages on the
inactive list much more effectively. This is by design, and it makes
sense for clean cache. But for the most part our workload's cache
faults are refaults and its use-once cache is from streaming writes. We
end up with most of the inactive list dirty, and we don't go after the
active cache as long as we have use-once pages around.
But waiting for writes to avoid reclaiming clean cache that *might*
refault is a bad trade-off. Even if the refaults happen, reads are
faster than writes. Before getting bogged down on writeback, reclaim
should first look at *all* cache in the system, even active cache.
To accomplish this, activate pages that are dirty or under writeback
when they reach the end of the inactive LRU. The pages are marked for
immediate reclaim, meaning they'll get moved back to the inactive LRU
tail as soon as they're written back and become reclaimable. But in the
meantime, by reducing the inactive list to only immediately reclaimable
pages, we allow the scanner to deactivate and refill the inactive list
with clean cache from the active list tail to guarantee forward
progress.
[hannes@cmpxchg.org: update comment] Link: http://lkml.kernel.org/r/20170202191957.22872-8-hannes@cmpxchg.org Link: http://lkml.kernel.org/r/20170123181641.23938-6-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Minchan Kim <minchan@kernel.org> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
projects / karo-tx-linux.git / log