Pull networking update from David Miller:
"A couple weeks of bug fixing in there. The largest chunk is all the
broken crap Amerigo Wang found in the netpoll layer."
1) netpoll and it's users has several serious bugs:
a) uses GFP_KERNEL with locks held
b) interfaces requiring interrupts disabled are called with them
enabled
c) and vice versa
d) VLAN tag demuxing, as per all other RX packet input paths, is not
applied
All from Amerigo Wang.
2) Hopefully cure the ipv4 mapped ipv6 address TCP early demux bugs for
good, from Neal Cardwell.
3) Unlike AF_UNIX, AF_PACKET sockets don't set a default credentials
when the user doesn't specify one explicitly during sendmsg().
Instead we attach an empty (zero) SCM credential block which is
definitely not what we want. Fix from Eric Dumazet.
4) IPv6 illegally invokes netdevice notifiers with RCU lock held, fix
from Ben Hutchings.
5) inet_csk_route_child_sock() checks wrong inet options pointer, fix
from Christoph Paasch.
6) When AF_PACKET is used for transmit, packet loopback doesn't behave
properly when a socket fanout is enabled, from Eric Leblond.
7) On bluetooth l2cap channel create failure, we leak the socket, from
Jaganath Kanakkassery.
8) Fix all the netprio file handling bugs found by Al Viro, from John
Fastabend.
9) Several error return and NULL deref bug fixes in networking drivers
from Julia Lawall.
10) A large smattering of struct padding et al. kernel memory leaks to
userspace found of Mathias Krause.
11) Conntrack expections in netfilter can access an uninitialized timer,
fix from Pablo Neira Ayuso.
12) Several netfilter SIP tracker bug fixes from Patrick McHardy.
13) IPSEC ipv6 routes are not initialized correctly all the time,
resulting in an OOPS in inet_putpeer(). Also from Patrick McHardy.
14) Bridging does rcu_dereference() outside of RCU protected area, from
Stephen Hemminger.
15) Fix routing cache removal performance regression when looking up
output routes that have a local destination. From Zheng Yan.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
af_netlink: force credentials passing [CVE-2012-3520]
ipv4: fix ip header ident selection in __ip_make_skb()
ipv4: Use newinet->inet_opt in inet_csk_route_child_sock()
tcp: fix possible socket refcount problem
net: tcp: move sk_rx_dst_set call after tcp_create_openreq_child()
net/core/dev.c: fix kernel-doc warning
netconsole: remove a redundant netconsole_target_put()
net: ipv6: fix oops in inet_putpeer()
net/stmmac: fix issue of clk_get for Loongson1B.
caif: Do not dereference NULL in chnl_recv_cb()
af_packet: don't emit packet on orig fanout group
drivers/net/irda: fix error return code
drivers/net/wan/dscc4.c: fix error return code
drivers/net/wimax/i2400m/fw.c: fix error return code
smsc75xx: add missing entry to MAINTAINERS
net: qmi_wwan: new devices: UML290 and K5006-Z
net: sh_eth: Add eth support for R8A7779 device
netdev/phy: skip disabled mdio-mux nodes
dt: introduce for_each_available_child_of_node, of_get_next_available_child
net: netprio: fix cgrp create and write priomap race
...
Jim Schutt reported a problem that pointed at compaction contending
heavily on locks. The workload is straight-forward and in his own words;
The systems in question have 24 SAS drives spread across 3 HBAs,
running 24 Ceph OSD instances, one per drive. FWIW these servers
are dual-socket Intel 5675 Xeons w/48 GB memory. I've got ~160
Ceph Linux clients doing dd simultaneously to a Ceph file system
backed by 12 of these servers.
Early in the test everything looks fine
procs -------------------memory------------------ ---swap-- -----io---- --system-- -----cpu-------
r b swpd free buff cache si so bi bo in cs us sy id wa st
31 15 0 287216 576 38606628 0 0 2 1158 2 14 1 3 95 0 0
27 15 0 225288 576 38583384 0 0 18 2222016 203357 134876 11 56 17 15 0
28 17 0 219256 576 38544736 0 0 11 2305932 203141 146296 11 49 23 17 0
6 18 0 215596 576 38552872 0 0 7 2363207 215264 166502 12 45 22 20 0
22 18 0 226984 576 38596404 0 0 3 2445741 223114 179527 12 43 23 22 0
and then it goes to pot
procs -------------------memory------------------ ---swap-- -----io---- --system-- -----cpu-------
r b swpd free buff cache si so bi bo in cs us sy id wa st
163 8 0 464308 576 36791368 0 0 11 22210 866 536 3 13 79 4 0
207 14 0 917752 576 36181928 0 0 712 1345376 134598 47367 7 90 1 2 0
123 12 0 685516 576 36296148 0 0 429 1386615 158494 60077 8 84 5 3 0
123 12 0 598572 576 36333728 0 0 1107 1233281 147542 62351 7 84 5 4 0
622 7 0 660768 576 36118264 0 0 557 1345548 151394 59353 7 85 4 3 0
223 11 0 283960 576 36463868 0 0 46 1107160 121846 33006 6 93 1 1 0
Note that system CPU usage is very high blocks being written out has
dropped by 42%. He analysed this with perf and found
perf record -g -a sleep 10
perf report --sort symbol --call-graph fractal,5
34.63% [k] _raw_spin_lock_irqsave
|
|--97.30%-- isolate_freepages
| compaction_alloc
| unmap_and_move
| migrate_pages
| compact_zone
| compact_zone_order
| try_to_compact_pages
| __alloc_pages_direct_compact
| __alloc_pages_slowpath
| __alloc_pages_nodemask
| alloc_pages_vma
| do_huge_pmd_anonymous_page
| handle_mm_fault
| do_page_fault
| page_fault
| |
| |--87.39%-- skb_copy_datagram_iovec
| | tcp_recvmsg
| | inet_recvmsg
| | sock_recvmsg
| | sys_recvfrom
| | system_call
| | __recv
| | |
| | --100.00%-- (nil)
| |
| --12.61%-- memcpy
--2.70%-- [...]
There was other data but primarily it is all showing that compaction is
contended heavily on the zone->lock and zone->lru_lock.
commit [b2eef8c0: mm: compaction: minimise the time IRQs are disabled
while isolating pages for migration] noted that it was possible for
migration to hold the lru_lock for an excessive amount of time. Very
broadly speaking this patch expands the concept.
This patch introduces compact_checklock_irqsave() to check if a lock
is contended or the process needs to be scheduled. If either condition
is true then async compaction is aborted and the caller is informed.
The page allocator will fail a THP allocation if compaction failed due
to contention. This patch also introduces compact_trylock_irqsave()
which will acquire the lock only if it is not contended and the process
does not need to schedule.
Reported-by: Jim Schutt <jaschut@sandia.gov>
Tested-by: Jim Schutt <jaschut@sandia.gov>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 7db8889ab0 ("mm: have order > 0 compaction start off where it
left") introduced a caching mechanism to reduce the amount work the free
page scanner does in compaction. However, it has a problem. Consider
two process simultaneously scanning free pages
C
Process A M S F
|---------------------------------------|
Process B M FS
C is zone->compact_cached_free_pfn
S is cc->start_pfree_pfn
M is cc->migrate_pfn
F is cc->free_pfn
In this diagram, Process A has just reached its migrate scanner, wrapped
around and updated compact_cached_free_pfn accordingly.
Simultaneously, Process B finishes isolating in a block and updates
compact_cached_free_pfn again to the location of its free scanner.
Process A moves to "end_of_zone - one_pageblock" and runs this check
if (cc->order > 0 && (!cc->wrapped ||
zone->compact_cached_free_pfn >
cc->start_free_pfn))
pfn = min(pfn, zone->compact_cached_free_pfn);
compact_cached_free_pfn is above where it started so the free scanner
skips almost the entire space it should have scanned. When there are
multiple processes compacting it can end in a situation where the entire
zone is not being scanned at all. Further, it is possible for two
processes to ping-pong update to compact_cached_free_pfn which is just
random.
Overall, the end result wrecks allocation success rates.
There is not an obvious way around this problem without introducing new
locking and state so this patch takes a different approach.
First, it gets rid of the skip logic because it's not clear that it
matters if two free scanners happen to be in the same block but with
racing updates it's too easy for it to skip over blocks it should not.
Second, it updates compact_cached_free_pfn in a more limited set of
circumstances.
If a scanner has wrapped, it updates compact_cached_free_pfn to the end
of the zone. When a wrapped scanner isolates a page, it updates
compact_cached_free_pfn to point to the highest pageblock it
can isolate pages from.
If a scanner has not wrapped when it has finished isolated pages it
checks if compact_cached_free_pfn is pointing to the end of the
zone. If so, the value is updated to point to the highest
pageblock that pages were isolated from. This value will not
be updated again until a free page scanner wraps and resets
compact_cached_free_pfn.
This is not optimal and it can still race but the compact_cached_free_pfn
will be pointing to or very near a pageblock with free pages.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make sure that there is no doorbell messages left behind due to disabled
interrupts during inbound doorbell processing.
The most common case for this bug is loss of rionet JOIN messages in
systems with three or more rionet participants and MSI or MSI-X enabled.
As result, requests for packet transfers may finish with "destination
unreachable" error message.
This patch is applicable to kernel versions starting from v3.2.
Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Correct the offset by subtracting 20 from tm_hour before taking the
modulo 12.
[ "Why 20?" I hear you ask. Or at least I did.
Here's the reason why: RS5C348_BIT_PM is 32, and is - stupidly -
included in the RS5C348_HOURS_MASK define. So it's really subtracting
out that bit to get "hour+12". But then because it does things modulo
12, it needs to add the 12 in again afterwards anyway.
This code is confused. It would be much clearer if RS5C348_HOURS_MASK
just didn't include the RS5C348_BIT_PM bit at all, then it wouldn't
need to do the silly subtract either.
Whatever. It's all just math, the end result is the same. - Linus ]
Reported-by: James Nute <newten82@gmail.com>
Tested-by: James Nute <newten82@gmail.com>
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit cfd19c5a9e ("mm: only set page->pfmemalloc when
ALLOC_NO_WATERMARKS was used") tried to narrow down page->pfmemalloc
setting, but it missed some places the pfmemalloc should be set.
So, in __slab_alloc, the unalignment pfmemalloc and ALLOC_NO_WATERMARKS
cause incorrect deactivate_slab() on our core2 server:
64.73% fio [kernel.kallsyms] [k] _raw_spin_lock
|
--- _raw_spin_lock
|
|---0.34%-- deactivate_slab
| __slab_alloc
| kmem_cache_alloc
| |
That causes our fio sync write performance to have a 40% regression.
Move the checking in get_page_from_freelist() which resolves this issue.
Signed-off-by: Alex Shi <alex.shi@intel.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Sage Weil <sage@inktank.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit aff622495c ("vmscan: only defer compaction for failed order and
higher") fixed bad deferring policy but made mistake about checking
compact_order_failed in __compact_pgdat(). So it can't update
compact_order_failed with the new order. This ends up preventing
correct operation of policy deferral. This patch fixes it.
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On many of our larger systems, CPU 0 has had all of its IRQ resources
consumed before XPC loads. Worst cases on machines with multiple 10
GigE cards and multiple IB cards have depleted the entire first socket
of IRQs.
This patch makes selecting the node upon which IRQs are allocated (as
well as all the other GRU Message Queue structures) specifiable as a
module load param and has a default behavior of searching all nodes/cpus
for an available resources.
[akpm@linux-foundation.org: fix build: include cpu.h and module.h]
Signed-off-by: Robin Holt <holt@sgi.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit f0f57b2b14 ("mm: move hugepage test examples to
tools/testing/selftests/vm") moved map_hugetlb.c, hugepage-shm.c and
hugepage-mmap.c tests into tools/testing/selftests/vm/ directory, but it
didn't update hugetlbpage.txt
Signed-off-by: Zhouping Liu <sanweidaying@gmail.com>
Acked-by: Dave Young <dyoung@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit b13edf7ff2 ("checkpatch: add checks for do {} while (0) macro
misuses") added a test that is overly simplistic for single statement
macros.
Macros that start with control tests should be enclosed in a do {} while
(0) loop.
Add the necessary control tests to the check.
Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Andy Whitcroft <apw@canonical.com>
Tested-by: Franz Schrober <franzschrober@yahoo.de>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Each page mapped in a process's address space must be correctly
accounted for in _mapcount. Normally the rules for this are
straightforward but hugetlbfs page table sharing is different. The page
table pages at the PMD level are reference counted while the mapcount
remains the same.
If this accounting is wrong, it causes bugs like this one reported by
Larry Woodman:
kernel BUG at mm/filemap.c:135!
invalid opcode: 0000 [#1] SMP
CPU 22
Modules linked in: bridge stp llc sunrpc binfmt_misc dcdbas microcode pcspkr acpi_pad acpi]
Pid: 18001, comm: mpitest Tainted: G W 3.3.0+ #4 Dell Inc. PowerEdge R620/07NDJ2
RIP: 0010:[<ffffffff8112cfed>] [<ffffffff8112cfed>] __delete_from_page_cache+0x15d/0x170
Process mpitest (pid: 18001, threadinfo ffff880428972000, task ffff880428b5cc20)
Call Trace:
delete_from_page_cache+0x40/0x80
truncate_hugepages+0x115/0x1f0
hugetlbfs_evict_inode+0x18/0x30
evict+0x9f/0x1b0
iput_final+0xe3/0x1e0
iput+0x3e/0x50
d_kill+0xf8/0x110
dput+0xe2/0x1b0
__fput+0x162/0x240
During fork(), copy_hugetlb_page_range() detects if huge_pte_alloc()
shared page tables with the check dst_pte == src_pte. The logic is if
the PMD page is the same, they must be shared. This assumes that the
sharing is between the parent and child. However, if the sharing is
with a different process entirely then this check fails as in this
diagram:
parent
|
------------>pmd
src_pte----------> data page
^
other--------->pmd--------------------|
^
child-----------|
dst_pte
For this situation to occur, it must be possible for Parent and Other to
have faulted and failed to share page tables with each other. This is
possible due to the following style of race.
PROC A PROC B
copy_hugetlb_page_range copy_hugetlb_page_range
src_pte == huge_pte_offset src_pte == huge_pte_offset
!src_pte so no sharing !src_pte so no sharing
(time passes)
hugetlb_fault hugetlb_fault
huge_pte_alloc huge_pte_alloc
huge_pmd_share huge_pmd_share
LOCK(i_mmap_mutex)
find nothing, no sharing
UNLOCK(i_mmap_mutex)
LOCK(i_mmap_mutex)
find nothing, no sharing
UNLOCK(i_mmap_mutex)
pmd_alloc pmd_alloc
LOCK(instantiation_mutex)
fault
UNLOCK(instantiation_mutex)
LOCK(instantiation_mutex)
fault
UNLOCK(instantiation_mutex)
These two processes are not poing to the same data page but are not
sharing page tables because the opportunity was missed. When either
process later forks, the src_pte == dst pte is potentially insufficient.
As the check falls through, the wrong PTE information is copied in
(harmless but wrong) and the mapcount is bumped for a page mapped by a
shared page table leading to the BUG_ON.
This patch addresses the issue by moving pmd_alloc into huge_pmd_share
which guarantees that the shared pud is populated in the same critical
section as pmd. This also means that huge_pte_offset test in
huge_pmd_share is serialized correctly now which in turn means that the
success of the sharing will be higher as the racing tasks see the pud
and pmd populated together.
Race identified and changelog written mostly by Mel Gorman.
{akpm@linux-foundation.org: attempt to make the huge_pmd_share() comment comprehensible, clean up coding style]
Reported-by: Larry Woodman <lwoodman@redhat.com>
Tested-by: Larry Woodman <lwoodman@redhat.com>
Reviewed-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Ken Chen <kenchen@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Occasionally an isolated BUG_ON(mm->nr_ptes) gets reported, indicating
that not all the page tables allocated could be found and freed when
exit_mmap() tore down the user address space.
There's usually nothing we can say about it, beyond that it's probably a
sign of some bad memory or memory corruption; though it might still
indicate a bug in vma or page table management (and did recently reveal a
race in THP, fixed a few months ago).
But one overdue change we can make is from BUG_ON to WARN_ON.
It's fairly likely that the system will crash shortly afterwards in some
other way (for example, the BUG_ON(page_mapped(page)) in
__delete_from_page_cache(), once an inode mapped into the lost page tables
gets evicted); but might tell us more before that.
Change the BUG_ON(page_mapped) to WARN_ON too? Later perhaps: I'm less
eager, since that one has several times led to fixes.
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fixes the following sparse warning:
drivers/gpu/drm/drm_proc.c:92:5:
warning: symbol 'drm_proc_create_files' was not declared. Should it be static?
drivers/gpu/drm/drm_proc.c:175:5:
warning: symbol 'drm_proc_remove_files' was not declared. Should it be static?
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This turns off the crtc when its been disabled,
fixes it not turning off properly the whole time.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
If you do a page flip with no flags set then event is NULL. If event is
NULL then the vmw_gfx driver likes to go digging into NULL and extracts
NULL->base.file_priv.
On a modern kernel with NULL mapping protection it's just another oops,
without it there are some "intriguing" possibilities.
What it should do is an open question but that for the driver owners to
sort out.
Signed-off-by: Alan Cox <alan@linux.intel.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
Daniel writes:
" Nothing too major:
- A few fixes around the edid handling from Jani, also fixing a regression
in 3.5 due to us using gmbus by default.
- Fixup hsw uncached pte flags.
- Fix suspend/resume crash when using hw contexts, from Ben.
- Try to tune gpu turbo a bit better, seems to help with some oddball
power regressions."
* 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel:
drm/i915: use hsw rps tuning values everywhere on gen6+
drm/i915: fall back to bit-banging if GMBUS fails in CRT EDID reads
drm/i915: extract connector update from intel_ddc_get_modes() for reuse
drm/i915: fix hsw uncached pte
drm/i915/contexts: fix list corruption
drm/i915: fix EDID memory leak in SDVO
Alex writes:
"This is the current set of radeon fixes for 3.6. Nothing too major.
Highlights:
- fix vbios fetch on pure uefi systems
- fix vbios fetch on thunderbolt systems
- MSAA fixes
- lockup timeout fix
- modesetting fix"
* 'drm-fixes-3.6' of git://people.freedesktop.org/~agd5f/linux:
drm/radeon/ss: use num_crtc rather than hardcoded 6
Revert "drm/radeon: fix bo creation retry path"
drm/radeon: split ATRM support out from the ATPX handler (v3)
drm/radeon: convert radeon vfct code to use acpi_get_table_with_size
ACPI: export symbol acpi_get_table_with_size
drm/radeon: implement ACPI VFCT vbios fetch (v3)
drm/radeon/kms: extend the Fujitsu D3003-S2 board connector quirk to cover later silicon stepping
drm/radeon: fix checking of MSAA renderbuffers on r600-r700
drm/radeon: allow CMASK and FMASK in the CS checker on r600-r700
drm/radeon: init lockup timeout on ring init
drm/radeon: avoid turning off spread spectrum for used pll
If "l->stripe_unit" is zero the the mod on the next line will cause a
divide by zero bug. This comes from the copy_from_user() in
ceph_ioctl_set_layout_policy(). Passing 0 is valid, though (it means
"do not change") so avoid the % check in that case.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Linus Torvalds
Mel Gorman
Alexandre Bounine
Atsushi Nemoto
Alex Shi
Ilya Shchepetkov
Minchan Kim
Robin Holt
WANG Cong
Zhouping Liu
Joe Perches
Michal Hocko
Stephen M. Cameron
Namjae Jeon
Hugh Dickins
Jens Rottmann
Sachin Kamat
Dave Airlie
Damien Lespiau
Alan Cox
Sage Weil