Compaction can provide a wild variation of feedback to the caller. Many
of them are implementation specific and the caller of the compaction
(especially the page allocator) shouldn't be bound to specifics of the
current implementation.
This patch abstracts the feedback into three basic types:
- compaction_made_progress - compaction was active and made some
progress.
- compaction_failed - compaction failed and further attempts to
invoke it would most probably fail and therefore it is not
worth retrying
- compaction_withdrawn - compaction wasn't invoked for an
implementation specific reasons. In the current implementation
it means that the compaction was deferred, contended or the
page scanners met too early without any progress. Retrying is
still worthwhile.
[vbabka@suse.cz: do not change thp back off behavior]
[akpm@linux-foundation.org: fix typo in comment, per Hillf]
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__alloc_pages_direct_compact communicates potential back off by two
variables:
- deferred_compaction tells that the compaction returned
COMPACT_DEFERRED
- contended_compaction is set when there is a contention on
zone->lock resp. zone->lru_lock locks
__alloc_pages_slowpath then backs of for THP allocation requests to
prevent from long stalls. This is rather messy and it would be much
cleaner to return a single compact result value and hide all the nasty
details into __alloc_pages_direct_compact.
This patch shouldn't introduce any functional changes.
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
compaction_result will be used as the primary feedback channel for
compaction users. At the same time try_to_compact_pages (and
potentially others) assume a certain ordering where a more specific
feedback takes precendence.
This gets a bit awkward when we have conflicting feedback from different
zones. E.g one returing COMPACT_COMPLETE meaning the full zone has been
scanned without any outcome while other returns with COMPACT_PARTIAL aka
made some progress. The caller should get COMPACT_PARTIAL because that
means that the compaction still can make some progress. The same
applies for COMPACT_PARTIAL vs COMPACT_PARTIAL_SKIPPED.
Reorder PARTIAL to be the largest one so the larger the value is the
more progress we have done.
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
COMPACT_COMPLETE now means that compaction and free scanner met. This
is not very useful information if somebody just wants to use this
feedback and make any decisions based on that. The current caller might
be a poor guy who just happened to scan tiny portion of the zone and
that could be the reason no suitable pages were compacted. Make sure we
distinguish the full and partial zone walks.
Consumers should treat COMPACT_PARTIAL_SKIPPED as a potential success
and be optimistic in retrying.
The existing users of COMPACT_COMPLETE are conservatively changed to use
COMPACT_PARTIAL_SKIPPED as well but some of them should be probably
reconsidered and only defer the compaction only for COMPACT_COMPLETE
with the new semantic.
This patch shouldn't introduce any functional changes.
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
try_to_compact_pages() can currently return COMPACT_SKIPPED even when
the compaction is defered for some zone just because zone DMA is skipped
in 99% of cases due to watermark checks. This makes COMPACT_DEFERRED
basically unusable for the page allocator as a feedback mechanism.
Make sure we distinguish those two states properly and switch their
ordering in the enum. This would mean that the COMPACT_SKIPPED will be
returned only when all eligible zones are skipped.
As a result COMPACT_DEFERRED handling for THP in __alloc_pages_slowpath
will be more precise and we would bail out rather than reclaim.
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The compiler is complaining after "mm, compaction: change COMPACT_
constants into enum"
mm/compaction.c: In function `compact_zone':
mm/compaction.c:1350:2: warning: enumeration value `COMPACT_DEFERRED' not handled in switch [-Wswitch]
switch (ret) {
^
mm/compaction.c:1350:2: warning: enumeration value `COMPACT_COMPLETE' not handled in switch [-Wswitch]
mm/compaction.c:1350:2: warning: enumeration value `COMPACT_NO_SUITABLE_PAGE' not handled in switch [-Wswitch]
mm/compaction.c:1350:2: warning: enumeration value `COMPACT_NOT_SUITABLE_ZONE' not handled in switch [-Wswitch]
mm/compaction.c:1350:2: warning: enumeration value `COMPACT_CONTENDED' not handled in switch [-Wswitch]
compaction_suitable is allowed to return only COMPACT_PARTIAL,
COMPACT_SKIPPED and COMPACT_CONTINUE so other cases are simply
impossible. Put a VM_BUG_ON to catch an impossible return value.
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Compaction code is doing weird dances between COMPACT_FOO -> int ->
unsigned long
But there doesn't seem to be any reason for that. All functions which
return/use one of those constants are not expecting any other value so it
really makes sense to define an enum for them and make it clear that no
other values are expected.
This is a pure cleanup and shouldn't introduce any functional changes.
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Motivation:
As pointed out by Linus [2][3] relying on zone_reclaimable as a way to
communicate the reclaim progress is rater dubious. I tend to agree,
not only it is really obscure, it is not hard to imagine cases where a
single page freed in the loop keeps all the reclaimers looping without
getting any progress because their gfp_mask wouldn't allow to get that
page anyway (e.g. single GFP_ATOMIC alloc and free loop). This is rather
rare so it doesn't happen in the practice but the current logic which we
have is rather obscure and hard to follow a also non-deterministic.
This is an attempt to make the OOM detection more deterministic and
easier to follow because each reclaimer basically tracks its own
progress which is implemented at the page allocator layer rather spread
out between the allocator and the reclaim. The more on the
implementation is described in the first patch.
I have tested several different scenarios but it should be clear that
testing OOM killer is quite hard to be representative. There is usually
a tiny gap between almost OOM and full blown OOM which is often time
sensitive. Anyway, I have tested the following 2 scenarios and I would
appreciate if there are more to test.
Testing environment: a virtual machine with 2G of RAM and 2CPUs without
any swap to make the OOM more deterministic.
1) 2 writers (each doing dd with 4M blocks to an xfs partition with 1G
file size, removes the files and starts over again) running in
parallel for 10s to build up a lot of dirty pages when 100 parallel
mem_eaters (anon private populated mmap which waits until it gets
signal) with 80M each.
This causes an OOM flood of course and I have compared both patched
and unpatched kernels. The test is considered finished after there
are no OOM conditions detected. This should tell us whether there are
any excessive kills or some of them premature (e.g. due to dirty pages):
I have performed two runs this time each after a fresh boot.
* base kernel
$ grep "Out of memory:" base-oom-run1.log | wc -l
78
$ grep "Out of memory:" base-oom-run2.log | wc -l
78
$ grep "Kill process" base-oom-run1.log | tail -n1
[ 91.391203] Out of memory: Kill process 3061 (mem_eater) score 39 or sacrifice child
$ grep "Kill process" base-oom-run2.log | tail -n1
[ 82.141919] Out of memory: Kill process 3086 (mem_eater) score 39 or sacrifice child
$ grep "DMA32 free:" base-oom-run1.log | sed 's@.*free:\([0-9]*\)kB.*@\1@' | calc_min_max.awk
min: 5376.00 max: 6776.00 avg: 5530.75 std: 166.50 nr: 61
$ grep "DMA32 free:" base-oom-run2.log | sed 's@.*free:\([0-9]*\)kB.*@\1@' | calc_min_max.awk
min: 5416.00 max: 5608.00 avg: 5514.15 std: 42.94 nr: 52
$ grep "DMA32.*all_unreclaimable? no" base-oom-run1.log | wc -l
1
$ grep "DMA32.*all_unreclaimable? no" base-oom-run2.log | wc -l
3
* patched kernel
$ grep "Out of memory:" patched-oom-run1.log | wc -l
78
miso@tiehlicka /mnt/share/devel/miso/kvm $ grep "Out of memory:" patched-oom-run2.log | wc -l
77
e grep "Kill process" patched-oom-run1.log | tail -n1
[ 497.317732] Out of memory: Kill process 3108 (mem_eater) score 39 or sacrifice child
$ grep "Kill process" patched-oom-run2.log | tail -n1
[ 316.169920] Out of memory: Kill process 3093 (mem_eater) score 39 or sacrifice child
$ grep "DMA32 free:" patched-oom-run1.log | sed 's@.*free:\([0-9]*\)kB.*@\1@' | calc_min_max.awk
min: 5420.00 max: 5808.00 avg: 5513.90 std: 60.45 nr: 78
$ grep "DMA32 free:" patched-oom-run2.log | sed 's@.*free:\([0-9]*\)kB.*@\1@' | calc_min_max.awk
min: 5380.00 max: 6384.00 avg: 5520.94 std: 136.84 nr: 77
e grep "DMA32.*all_unreclaimable? no" patched-oom-run1.log | wc -l
2
$ grep "DMA32.*all_unreclaimable? no" patched-oom-run2.log | wc -l
3
The patched kernel run noticeably longer while invoking OOM killer same
number of times. This means that the original implementation is much
more aggressive and triggers the OOM killer sooner. free pages stats
show that neither kernels went OOM too early most of the time, though. I
guess the difference is in the backoff when retries without any progress
do sleep for a while if there is memory under writeback or dirty which
is highly likely considering the parallel IO.
Both kernels have seen races where zone wasn't marked unreclaimable
and we still hit the OOM killer. This is most likely a race where
a task managed to exit between the last allocation attempt and the oom
killer invocation.
2) 2 writers again with 10s of run and then 10 mem_eaters to consume as much
memory as possible without triggering the OOM killer. This required a lot
of tuning but I've considered 3 consecutive runs in three different boots
without OOM as a success.
* base kernel
size=$(awk '/MemFree/{printf "%dK", ($2/10)-(16*1024)}' /proc/meminfo)
* patched kernel
size=$(awk '/MemFree/{printf "%dK", ($2/10)-(12*1024)}' /proc/meminfo)
That means 40M more memory was usable without triggering OOM killer. The
base kernel sometimes managed to handle the same as patched but it
wasn't consistent and failed in at least on of the 3 runs. This seems
like a minor improvement.
I was testing also GPF_REPEAT costly requests (hughetlb) with fragmented
memory and under memory pressure. The results are in patch 11 where the
logic is implemented. In short I can see huge improvement there.
I am certainly interested in other usecases as well as well as any
feedback. Especially those which require higher order requests.
This patch (of 14):
While playing with the oom detection rework [1] I have noticed that my
heavy order-9 (hugetlb) load close to OOM ended up in an endless loop
where the reclaim hasn't made any progress but did_some_progress didn't
reflect that and compaction_suitable was backing off because no zone is
above low wmark + 1 << order.
It turned out that this is in fact an old standing bug in
compaction_ready which ignores the requested_highidx and did the
watermark check for 0 classzone_idx. This succeeds for zone DMA most
of the time as the zone is mostly unused because of lowmem protection.
As a result costly high order allocatios always report a successfull
progress even when there was none. This wasn't a problem so far
because these allocations usually fail quite early or retry only few
times with __GFP_REPEAT but this will change after later patch in this
series so make sure to not lie about the progress and propagate
requested_highidx down to compaction_ready and use it for both the
watermak check and compaction_suitable to fix this issue.
[1] http://lkml.kernel.org/r/1459855533-4600-1-git-send-email-mhocko@kernel.org
[2] https://lkml.org/lkml/2015/10/12/808
[3] https://lkml.org/lkml/2015/10/13/597
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The inactive file list should still be large enough to contain readahead
windows and freshly written file data, but it no longer is the only
source for detecting multiple accesses to file pages. The workingset
refault measurement code causes recently evicted file pages that get
accessed again after a shorter interval to be promoted directly to the
active list.
With that mechanism in place, we can afford to (on a larger system)
dedicate more memory to the active file list, so we can actually cache
more of the frequently used file pages in memory, and not have them
pushed out by streaming writes, once-used streaming file reads, etc.
This can help things like database workloads, where only half the page
cache can currently be used to cache the database working set. This
patch automatically increases that fraction on larger systems, using the
same ratio that has already been used for anonymous memory.
[hannes@cmpxchg.org: cgroup-awareness]
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Andres Freund <andres@anarazel.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Andres observed that his database workload is struggling with the
transaction journal creating pressure on frequently read pages.
Access patterns like transaction journals frequently write the same
pages over and over, but in the majority of cases those pages are never
read back. There are no caching benefits to be had for those pages, so
activating them and having them put pressure on pages that do benefit
from caching is a bad choice.
Leave page activations to read accesses and don't promote pages based on
writes alone.
It could be said that partially written pages do contain cache-worthy
data, because even if *userspace* does not access the unwritten part,
the kernel still has to read it from the filesystem for correctness.
However, a counter argument is that these pages enjoy at least *some*
protection over other inactive file pages through the writeback cache,
in the sense that dirty pages are written back with a delay and cache
reclaim leaves them alone until they have been written back to disk.
Should that turn out to be insufficient and we see increased read IO
from partial writes under memory pressure, we can always go back and
update grab_cache_page_write_begin() to take (pos, len) so that it can
tell partial writes from pages that don't need partial reads. But for
now, keep it simple.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Andres Freund <andres@anarazel.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>
This is a follow-up to
http://www.spinics.net/lists/linux-mm/msg101739.html
where Andres reported his database workingset being pushed out by the
minimum size enforcement of the inactive file list - currently 50% of
cache - as well as repeatedly written file pages that are never actually
read.
Two changes fell out of the discussions. The first change observes that
pages that are only ever written don't benefit from caching beyond what
the writeback cache does for partial page writes, and so we shouldn't
promote them to the active file list where they compete with pages whose
cached data is actually accessed repeatedly. This change comes in two
patches - one for in-cache write accesses and one for refaults triggered
by writes, neither of which should promote a cache page.
Second, with the refault detection we don't need to set 50% of the cache
aside for used-once cache anymore since we can detect frequently used
pages even when they are evicted between accesses. We can allow the
active list to be bigger and thus protect a bigger workingset that isn't
challenged by streamers. Depending on the access patterns, this can
increase major faults during workingset transitions for better
performance during stable phases.
This patch (of 3):
When rewriting a page, the data in that page is replaced with new data.
This means that evicting something else from the active file list, in
order to cache data that will be replaced by something else, is likely
to be a waste of memory.
It is better to save the active list for frequently read pages, because
reads actually use the data that is in the page.
This patch ignores partial writes, because it is unclear whether the
complexity of identifying those is worth any potential performance gain
obtained from better caching pages that see repeated partial writes at
large enough intervals to not get caught by the use-twice promotion code
used for the inactive file list.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Andres Freund <andres@anarazel.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Sam Ravnborg says:
====================
sparc32: kgdb_32 and STRICT_MM_TYPECHECKS updates
A few cosmetic pathes for sparc32 follows.
I noticed some inconsistency in kgdb_32 that triggered a few patches.
The inconsistency in kgdb_32 turned out to have no functional impact.
But I anyway fixed it so kgdb_32 and kgdb_64 became just a tiny
bit more alike.
The STRICT_MM_TYPECHECKS patch was triggered by a
discussion on linux-arch where Arnd considered removing
this cruft.
The resulting benary of srmmu.c (I checked an assembler file)
was _smaller_ when I defined STRICT_MM_TYPECHECKS.
But due to lack of testing I left it undefined.
With the build errors fixed it should be trivial to
try out if defining STRICT_MM_TYPECHECKS breaks anything.
Any takers?
As I miss any working sparc32 gear for the moment this
has only been build tested - so please consider if it
is worth taking the risk to apply the patches.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Based on recent thread on linux-arch (some weeks ago) I
decided to check how much work was required to build sparc32
with STRICT_MM_TYPECHECKS enabled.
The resulting binary (checked srmmu.o) was to my suprise smaller with
STRICT_MM_TYPECHECKS defined, than without.
As I have no working gear to test sparc32 bits at for the moment,
I did not enable STRICT_MM_TYPECHECKS - but was tempeted to do so.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
This killed an extern ... in a .c file.
No functional change.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix this so we pass the trap_level from the actual trap
code like we do in sparc64.
Add use on ENTRY(), ENDPROC() in the assembler function too.
This fixes a bug where the hardcoded value for trap_level
was the sparc64 value.
As the generic code does not use the trap_level argument
(for sparc32) - this patch does not have any functional impact.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Noticed an allocation failure in a network driver the other day on a 32 bit
system:
DMA-API: debugging out of memory - disabling
bnx2fc: adapter_lookup: hba NULL
lldpad: page allocation failure. order:0, mode:0x4120
Pid: 4556, comm: lldpad Not tainted 2.6.32-639.el6.i686.debug #1
Call Trace:
[<c08a4086>] ? printk+0x19/0x23
[<c05166a4>] ? __alloc_pages_nodemask+0x664/0x830
[<c0649d02>] ? free_object+0x82/0xa0
[<fb4e2c9b>] ? ixgbe_alloc_rx_buffers+0x10b/0x1d0 [ixgbe]
[<fb4e2fff>] ? ixgbe_configure_rx_ring+0x29f/0x420 [ixgbe]
[<fb4e228c>] ? ixgbe_configure_tx_ring+0x15c/0x220 [ixgbe]
[<fb4e3709>] ? ixgbe_configure+0x589/0xc00 [ixgbe]
[<fb4e7be7>] ? ixgbe_open+0xa7/0x5c0 [ixgbe]
[<fb503ce6>] ? ixgbe_init_interrupt_scheme+0x5b6/0x970 [ixgbe]
[<fb4e8e54>] ? ixgbe_setup_tc+0x1a4/0x260 [ixgbe]
[<fb505a9f>] ? ixgbe_dcbnl_set_state+0x7f/0x90 [ixgbe]
[<c088d80d>] ? dcb_doit+0x10ed/0x16d0
...
Thought that perhaps the big splat in the logs wasn't really necessecary, as
all call sites for dev_alloc_skb:
a) check the return code for the function
and
b) either print their own error message or have a recovery path that makes the
warning moot.
Fix it by modifying dev_alloc_pages to pass __GFP_NOWARN as a gfp flag to
suppress the warning
applies to the net tree
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <eric.dumazet@gmail.com>
CC: Alexander Duyck <alexander.duyck@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
These structures are defined only if __USE_MISC is set in glibc net/if.h
headers, ie when _BSD_SOURCE or _SVID_SOURCE are defined.
CC: Jan Engelhardt <jengelh@inai.de>
CC: Josh Boyer <jwboyer@fedoraproject.org>
CC: Stephen Hemminger <shemming@brocade.com>
CC: Waldemar Brodkorb <mail@waldemar-brodkorb.de>
CC: Gabriel Laskar <gabriel@lse.epita.fr>
CC: Mikko Rapeli <mikko.rapeli@iki.fi>
Fixes: 4a91cb61bb ("uapi glibc compat: fix compile errors when glibc net/if.h included before linux/if.h")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In case we find a socket with encapsulation enabled we should call
the encap_recv function even if just a udp header without payload is
available. The callbacks are responsible for correctly verifying and
dropping the packets.
Also, in case the header validation fails for geneve and vxlan we
shouldn't put the skb back into the socket queue, no one will pick
them up there. Instead we can simply discard them in the respective
encap_recv functions.
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexei Starovoitov says:
====================
bpf: verifier fixes
Further testing of 'direct packet access' uncovered
several usability issues. Fix them.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Humans don't write C code like:
u8 *ptr = skb->data;
int imm = 4;
imm += ptr;
but from llvm backend point of view 'imm' and 'ptr' are registers and
imm += ptr may be preferred vs ptr += imm depending which register value
will be used further in the code, while verifier can only recognize ptr += imm.
That caused small unrelated changes in the C code of the bpf program to
trigger rejection by the verifier. Therefore teach the verifier to recognize
both ptr += imm and imm += ptr.
For example:
when R6=pkt(id=0,off=0,r=62) R7=imm22
after r7 += r6 instruction
will be R6=pkt(id=0,off=0,r=62) R7=pkt(id=0,off=22,r=62)
Fixes: 969bf05eb3 ("bpf: direct packet access")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
when packet headers are accessed in 'decreasing' order (like TCP port
may be fetched before the program reads IP src) the llvm may generate
the following code:
[...] // R7=pkt(id=0,off=22,r=70)
r2 = *(u32 *)(r7 +0) // good access
[...]
r7 += 40 // R7=pkt(id=0,off=62,r=70)
r8 = *(u32 *)(r7 +0) // good access
[...]
r1 = *(u32 *)(r7 -20) // this one will fail though it's within a safe range
// it's doing *(u32*)(skb->data + 42)
Fix verifier to recognize such code pattern
Alos turned out that 'off > range' condition is not a verifier bug.
It's a buggy program that may do something like:
if (ptr + 50 > data_end)
return 0;
ptr += 60;
*(u32*)ptr;
in such case emit
"invalid access to packet, off=0 size=4, R1(id=0,off=60,r=50)" error message,
so all information is available for the program author to fix the program.
Fixes: 969bf05eb3 ("bpf: direct packet access")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use kmemdup when some other buffer is immediately copied into allocated
region. It replaces call to allocation followed by memcpy, by a single
call to kmemdup.
Signed-off-by: Muhammad Falak R Wani <falakreyaz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use kmemdup when some other buffer is immediately copied into allocated
region. It replaces call to allocation followed by memcpy, by a single
call to kmemdup.
Signed-off-by: Muhammad Falak R Wani <falakreyaz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use kmemdup when some other buffer is immediately copied into allocated
region. It replaces call to allocation followed by memcpy, by a single
call to kmemdup.
Signed-off-by: Muhammad Falak R Wani <falakreyaz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reviewing the filesystems that set FS_USERNS_MOUNT I spotted the
bpf filesystem. Looking at the code I saw a broken usage of mount_ns
with current->nsproxy->mnt_ns. As the code does not acquire a
reference to the mount namespace it can not possibly be correct to
store the mount namespace on the superblock as it does.
Replace mount_ns with mount_nodev so that each mount of the bpf
filesystem returns a distinct instance, and the code is not buggy.
In discussion with Hannes Frederic Sowa it was reported that the use
of mount_ns was an attempt to have one bpf instance per mount
namespace, in an attempt to keep resources that pin resources from
hiding. That intent simply does not work, the vfs is not built to
allow that kind of behavior. Which means that the bpf filesystem
really is buggy both semantically and in it's implemenation as it does
not nor can it implement the original intent.
This change is userspace visible, but my experience with similar
filesystems leads me to believe nothing will break with a model of each
mount of the bpf filesystem is distinct from all others.
Fixes: b2197755b2 ("bpf: add support for persistent maps/progs")
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Major changes:
iwlwifi
* remove IWLWIFI_DEBUG_EXPERIMENTAL_UCODE kconfig option
* work for RX multiqueue continues
* dynamic queue allocation work continues
* add Luca as maintainer
* a bunch of fixes and improvements all over
brcmfmac
* add 4356 sdio support
ath6kl
* add ability to set debug uart baud rate with a module parameter
wil6210
* add debugfs file to configure firmware led functionality
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)
iQEcBAABAgAGBQJXNbEBAAoJEG4XJFUm622bKfAH/2CnQV7dBCT5QwEiKYoOdsCR
eTiH7OYjTPw/rjKaG3laFgFbecnfUnHoGt55WKqRY58JycLza+SPTTv57hFTnOl+
4kDhUEjUggxMs5BRb3H7wtcnQVs/pTkgqKqwUrmFNkG6idENQgorK6DG4SNCwIdf
JrmxiHcN73xSATxlduoA9bGpluW3OvnFfRrJfyT6UBWZaFqFe3qsoKDx08S2WU2z
kUI9ZUO9Ht7Q85QdLfPQI7xo54dXo9a+8v3yc7fNFbcu1s8cqeYuofXfypjK7H/B
DEY96mubDnmDt8YE8yR9wStVzTr5zf39urE3o+/xSKSKhQxmNo8+x2TBSm5nFSQ=
=0HKi
-----END PGP SIGNATURE-----
Merge tag 'wireless-drivers-next-for-davem-2016-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next
Kalle Valo says:
====================
wireless-drivers patches for 4.7
Major changes:
iwlwifi
* remove IWLWIFI_DEBUG_EXPERIMENTAL_UCODE kconfig option
* work for RX multiqueue continues
* dynamic queue allocation work continues
* add Luca as maintainer
* a bunch of fixes and improvements all over
brcmfmac
* add 4356 sdio support
ath6kl
* add ability to set debug uart baud rate with a module parameter
wil6210
* add debugfs file to configure firmware led functionality
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Current implementation updates the mtu size and notify cdc_ncm
device using USB_CDC_SET_MAX_DATAGRAM_SIZE request about datagram
size change instead of changing rx_urb_size.
Whenever mtu is being changed, datagram size should also be
updated. Also updating maxmtu formula so it takes max_datagram_size with
use of cdc_ncm_max_dgram_size() and not ctx.
Signed-off-by: Robert Dobrowolski <robert.dobrowolski@linux.intel.com>
Signed-off-by: Rafal Redzimski <rafal.f.redzimski@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We used to check dev->reg_state against NETREG_REGISTERED after each
time we are woke up. But after commit 9e641bdcfa ("net-tun:
restructure tun_do_read for better sleep/wakeup efficiency"), it uses
skb_recv_datagram() which does not check dev->reg_state. This will
result if we delete a tun/tap device after a process is blocked in the
reading. The device will wait for the reference count which was held
by that process for ever.
Fixes this by using RCV_SHUTDOWN which will be checked during
sk_recv_datagram() before trying to wake up the process during uninit.
Fixes: 9e641bdcfa ("net-tun: restructure tun_do_read for better
sleep/wakeup efficiency")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Xi Wang <xii@google.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck says:
====================
Follow-ups for GUEoIPv6 patches
This patch series is meant to be applied after:
[PATCH v7 net-next 00/16] ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling
The first patch addresses an issue we already resolved in the GREv4 and is
now present in GREv6 with the introduction of FOU/GUE for IPv6 based GRE
tunnels.
The second patch goes through and enables IPv6 tunnel offloads for the Intel
NICs that already support the IPv4 based IP-in-IP tunnel offloads. I have
only done a bit of touch testing but have seen ~20 Gb/s over an i40e
interface using a v4-in-v6 tunnel, and I have verified IPv6 GRE is still
passing traffic at around the same rate. I plan to do further testing but
with these patches present it should enable a wider audience to be able to
test the new features introduced in Tom's patchset with hardware offloads.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for offloading IPXIP6 type packets that represent
either IPv4 or IPv6 encapsulated inside of an IPv6 outer IP header. In
addition with this change we should also be able to support FOU
encapsulated traffic with outer IPv6 headers.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch addresses the same issue we had for IPv4 where enabling GRE with
an inner checksum cannot be supported with FOU/GUE due to the fact that
they will jump past the GRE header at it is treated like a tunnel header.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sowmini Varadhan says:
====================
RDS: TCP: connection spamming fixes
We have been testing the RDS-TCP code with a connection spammer
that sends incoming SYNs to the RDS listen port well after
an rds-tcp connection has been established, and found a few
race-windows that are fixed by this patch series.
Patch 1 avoids a null pointer deref when an incoming SYN
shows up when a netns is being dismantled, or when the
rds-tcp module is being unloaded.
Patch 2 addresses the case when a SYN is received after the
connection arbitration algorithm has converged: the incoming
SYN should not needlessly quiesce the transmit path, and it
should not result in needless TCP connection resets due to
re-execution of the connection arbitration logic.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
When a rogue SYN is received after the connection arbitration
algorithm has converged, the incoming SYN should not needlessly
quiesce the transmit path, and it should not result in needless
TCP connection resets due to re-execution of the connection
arbitration logic.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are two instances where we want to terminate RDS-TCP: when
exiting the netns or during module unload. In either case, the
termination sequence is to stop the listen socket, mark the
rtn->rds_tcp_listen_sock as null, and flush any accept workqs.
Thus any workqs that get flushed at this point will encounter a
null rds_tcp_listen_sock, and must exit gracefully to allow
the RDS-TCP termination to complete successfully.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Abhi Das has two patches that fix a GFS2 splice issue (and an adjustment).
- Ben Marzinski has a patch which allows the proper unmount of a GFS2
file system after hitting a withdraw error.
- I have a patch to fix a problem where GFS2 would dereference an error
value, plus three cosmetic / refactoring patches.
- Daniel DeFreez has a patch to fix two glock reference count problems,
where GFS2 was not properly "uninitializing" its glock holder on error
paths.
- Denys Vlasenko has a patch to change a function to not be inlined,
thus reducing the memory footprint of the GFS2 module.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJXP2KLAAoJENeLYdPf93o7nScH/jlDCv+JzwBwAiFEVelgB657
lFY+Q3bPvmcTaHiOqXzco7U1EeyvAuZ+x9duaFBBEGC2/NydIbkAdCP1XjDOTAGZ
aVVAP8qov4adFiXTfBdzMYjJ7DArOy/JRnlC8WK5OiD/3yxsXJZNlAHTgjjL/ZMq
PkhjxX2Lc9ZHGF9YIFTyeoBlqf1qO6WbhkxvSNefgq3c702QPM+T9XND5T1duGDF
ThEcXS2DRRoE+6wr3h+ruvS5kcfxXRLLausAgqNpj2FYQOFCQ6XXgGK8pyXA5V/t
3Vh8mHW0VmSjAfrRWslCRjd+APXoOf+7QHqOHUAA1dvQ6CGfC9qTETH9Wp32JCI=
=8g+a
-----END PGP SIGNATURE-----
Merge tag 'gfs2-4.7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2
Pull GFS2 updates from Bob Peterson:
"We've got nine patches this time:
- Abhi Das has two patches that fix a GFS2 splice issue (and an
adjustment).
- Ben Marzinski has a patch which allows the proper unmount of a GFS2
file system after hitting a withdraw error.
- I have a patch to fix a problem where GFS2 would dereference an
error value, plus three cosmetic / refactoring patches.
- Daniel DeFreez has a patch to fix two glock reference count
problems, where GFS2 was not properly "uninitializing" its glock
holder on error paths.
- Denys Vlasenko has a patch to change a function to not be inlined,
thus reducing the memory footprint of the GFS2 module"
* tag 'gfs2-4.7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2:
GFS2: Refactor gfs2_remove_from_journal
GFS2: Remove allocation parms from gfs2_rbm_find
gfs2: use inode_lock/unlock instead of accessing i_mutex directly
GFS2: Add calls to gfs2_holder_uninit in two error handlers
GFS2: Don't dereference inode in gfs2_inode_lookup until it's valid
GFS2: fs/gfs2/glock.c: Deinline do_error, save 1856 bytes
gfs2: Use gfs2 wrapper to sync inode before calling generic_file_splice_read()
GFS2: Get rid of dead code in inode_go_demote_ok
GFS2: ignore unlock failures after withdraw
->sk_shutdown bits share one bitfield with some other bits in sock struct,
such as ->sk_no_check_[r,t]x, ->sk_userlocks ...
sock_setsockopt() may write to these bits, while holding the socket lock.
In case of AF_UNIX sockets, we change ->sk_shutdown bits while holding only
unix_state_lock(). So concurrent setsockopt() and shutdown() may lead
to corrupting these bits.
Fix this by moving ->sk_shutdown bits out of bitfield into a separate byte.
This will not change the 'struct sock' size since ->sk_shutdown moved into
previously unused 16-bit hole.
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tom Herbert says:
====================
ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling
This patch set:
- Fixes GRE6 to process translate flags correctly from configuration
- Adds support for GSO and GRO for ip6ip6 and ip4ip6
- Add support for FOU and GUE in IPv6
- Support GRE, ip6ip6 and ip4ip6 over FOU/GUE
- Fixes ip6_input to deal with UDP encapsulations
- Some other minor fixes
v2:
- Removed a check of GSO types in MPLS
- Define GSO type SKB_GSO_IPXIP6 and SKB_GSO_IPXIP4 (based on input
from Alexander)
- Don't define GSO types specifically for IP6IP6 and IP4IP6, above
fix makes that unnecessary
- Don't bother clearing encapsulation flag in UDP tunnel segment
(another item suggested by Alexander).
v3:
- Address some minor comments from Alexander
v4:
- Rebase on changes to fix IP TX tunnels
- Fix MTU issues in ip4ip6, ip6ip6
- Add test data for above
v5:
- Address feedback from Shmulik Ladkani regarding extension header
code that does not return next header but in instead relies
on returning value via nhoff. Solution here is to fix EH
processing to return nexthdr value.
- Refactored IPv4 encaps so that we won't need to create
a ip6_tunnel_core.c when adding encap support IPv6.
v6:
- Fix build issues with regard to new GSO constants
- FIx MTU calculation issues ip6_tunnel.c pointed out byt ALex
- Add encap_hlen into headroom for GREv6 to work with FOU/GUE
v7:
- Added skb_set_inner_ipproto to ip4ip6 and ip6ip6
- Clarified max_headroom in ip6_tnl_xmit
- Set features for IPv6 tunnels
- Other cleanup suggested by Alexander
- Above fixes throughput performance issues in ip4ip6 and ip6ip6,
updated test results to reflect that
Tested: Various cases of IP tunnels with netperf TCP_STREAM and TCP_RR.
- IPv4/GRE/GUE/IPv6 with RCO
1 TCP_STREAM
6616 Mbps
200 TCP_RR
1244043 tps
141/243/446 90/95/99% latencies
86.61% CPU utilization
- IPv6/GRE/GUE/IPv6 with RCO
1 TCP_STREAM
6940 Mbps
200 TCP_RR
1270903 tps
138/236/440 90/95/99% latencies
87.51% CPU utilization
- IP6IP6
1 TCP_STREAM
5307 Mbps
200 TCP_RR
498981 tps
388/498/631 90/95/99% latencies
19.75% CPU utilization (1 CPU saturated)
- IP6IP6/GUE with RCO
1 TCP_STREAM
5575 Mbps
200 TCP_RR
1233818 tps
143/244/451 90/95/99% latencies
87.57 CPU utilization
- IP4IP6
1 TCP_STREAM
5235 Mbps
200 TCP_RR
763774 tps
250/318/466 90/95/99% latencies
35.25% CPU utilization (1 CPU saturated)
- IP4IP6/GUE with RCO
1 TCP_STREAM
5337 Mbps
200 TCP_RR
1196385 tps
148/251/460 90/95/99% latencies
87.56 CPU utilization
- GRE with keyid
200 TCP_RR
744173 tps
258/332/461 90/95/99% latencies
34.59% CPU utilization (1 CPU saturated)
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Since iptunnel_handle_offloads() is called in all paths we can
probably drop the block in ip6_tnl_xmit that was checking for
skb->encapsulation and resetting the inner headers.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Need to set dev features, use same values that are used in GREv6.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch add a new fou6 module that provides encapsulation
operations for IPv6.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add encap_hlen and ip_tunnel_encap structure to ip6_tnl. Add functions
for getting encap hlen, setting up encap on a tunnel, performing
encapsulation operation.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds receive path support for IPv6 with fou.
- Add address family to fou structure for open sockets. This supports
AF_INET and AF_INET6. Lookups for fou ports are performed on both the
port number and family.
- In fou and gue receive adjust tot_len in IPv4 header or payload_len
based on address family.
- Allow AF_INET6 in FOU_ATTR_AF netlink attribute.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Create __fou_build_header and __gue_build_header. These implement the
protocol generic parts of building the fou and gue header.
fou_build_header and gue_build_header implement the IPv4 specific
functions and call the __*_build_header functions.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use helper function to set up UDP tunnel related information for a fou
socket.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
