| Age | Commit message (Collapse) | Author |
|---|
|
commit 9b15b817f3d62409290fd56fe3cbb076a931bb0a upstream.
Minchan Kim reports that when a system has many swap areas, and tmpfs
swaps out to the ninth or more, shmem_getpage_gfp()'s attempts to read
back the page cannot locate it, and the read fails with -ENOMEM.
Whoops. Yes, I blindly followed read_swap_header()'s pte_to_swp_entry(
swp_entry_to_pte()) technique for determining maximum usable swap
offset, without stopping to realize that that actually depends upon the
pte swap encoding shifting swap offset to the higher bits and truncating
it there. Whereas our radix_tree swap encoding leaves offset in the
lower bits: it's swap "type" (that is, index of swap area) that was
truncated.
Fix it by reducing the SWP_TYPE_SHIFT() in swapops.h, and removing the
broken radix_to_swp_entry(swp_to_radix_entry()) from read_swap_header().
This does not reduce the usable size of a swap area any further, it
leaves it as claimed when making the original commit: no change from 3.0
on x86_64, nor on i386 without PAE; but 3.0's 512GB is reduced to 128GB
per swapfile on i386 with PAE. It's not a change I would have risked
five years ago, but with x86_64 supported for ten years, I believe it's
appropriate now.
Hmm, and what if some architecture implements its swap pte with offset
encoded below type? That would equally break the maximum usable swap
offset check. Happily, they all follow the same tradition of encoding
offset above type, but I'll prepare a check on that for next.
Reported-and-Reviewed-and-Tested-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit c2fb8a3fa25513de8fedb38509b1f15a5bbee47b upstream.
This patch (as1558) fixes a problem affecting several ASUS computers:
The machine crashes or corrupts memory when going into suspend if the
ehci-hcd driver is bound to any controllers. Users have been forced
to unbind or unload ehci-hcd before putting their systems to sleep.
After extensive testing, it was determined that the machines don't
like going into suspend when any EHCI controllers are in the PCI D3
power state. Presumably this is a firmware bug, but there's nothing
we can do about it except to avoid putting the controllers in D3
during system sleep.
The patch adds a new flag to indicate whether the problem is present,
and avoids changing the controller's power state if the flag is set.
Runtime suspend is unaffected; this matters only for system suspend.
However as a side effect, the controller will not respond to remote
wakeup requests while the system is asleep. Hence USB wakeup is not
functional -- but of course, this is already true in the current state
of affairs.
A similar patch has already been applied as commit
151b61284776be2d6f02d48c23c3625678960b97 (USB: EHCI: fix crash during
suspend on ASUS computers). The patch supersedes that one and reverts
it. There are two differences:
The old patch added the flag at the USB level; this patch
adds it at the PCI level.
The old patch applied to all chipsets with the same vendor,
subsystem vendor, and product IDs; this patch makes an
exception for a known-good system (based on DMI information).
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Tested-by: Dâniel Fraga <fragabr@gmail.com>
Tested-by: Andrey Rahmatullin <wrar@wrar.name>
Tested-by: Steven Rostedt <rostedt@goodmis.org>
Reviewed-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 9295b7a07c859a42346221b5839be0ae612333b0 upstream.
Programs using /proc/kpageflags need to know about the various flags. The
<linux/kernel-page-flags.h> provides them and the comments in the file
indicate that it is supposed to be used by user-level code. But the file
is not installed.
Install the headers and mark the unstable flags as out-of-bounds. The
page-type tool is also adjusted to not duplicate the definitions
Signed-off-by: Ulrich Drepper <drepper@gmail.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.2: adjust context; drop change to missing tools/vm/]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit a2bef8ce826dd1e787fd8ad9b6e0566ba59dab43 upstream.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 4a6991cc1fad514745b79181df3ace72d561e7aa upstream.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
[ Upstream commit 617c8c11236716dcbda877e764b7bf37c6fd8063 ]
At the beginning of __skb_cow, headroom gets set to a minimum of
NET_SKB_PAD. This causes unnecessary reallocations if the buffer was not
cloned and the headroom is just below NET_SKB_PAD, but still more than the
amount requested by the caller.
This was showing up frequently in my tests on VLAN tx, where
vlan_insert_tag calls skb_cow_head(skb, VLAN_HLEN).
Locally generated packets should have enough headroom, and for forward
paths, we already have NET_SKB_PAD bytes of headroom, so we don't need to
add any extra space here.
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
[ Upstream commit e0268868ba064980488fc8c194db3d8e9fb2959c ]
dst_check() will take care of SA (and obsolete field), hence
IPsec rekeying scenario is taken into account.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Vlad Yaseivch <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
[ Upstream commit 59b9997baba5242997ddc7bd96b1391f5275a5a4 ]
This reverts commit 8a83a00b0735190384a348156837918271034144.
It causes regressions for S390 devices, because it does an
unconditional DST drop on SKBs for vlans and the QETH device
needs the neighbour entry hung off the DST for certain things
on transmit.
Arnd can't remember exactly why he even needed this change.
Conflicts:
drivers/net/macvlan.c
net/8021q/vlan_dev.c
net/core/dev.c
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
[ Upstream commit 0c1833797a5a6ec23ea9261d979aa18078720b74 ]
Since commit ad0081e43a
"ipv6: Fragment locally generated tunnel-mode IPSec6 packets as needed"
the fragment of packets is incorrect.
because tunnel mode needs IPsec headers and trailer for all fragments,
while on transport mode it is sufficient to add the headers to the
first fragment and the trailer to the last.
so modify mtu and maxfraglen base on ipsec mode and if fragment is first
or last.
with my test,it work well(every fragment's size is the mtu)
and does not trigger slow fragment path.
Changes from v1:
though optimization, mtu_prev and maxfraglen_prev can be delete.
replace xfrm mode codes with dst_entry's new frag DST_XFRM_TUNNEL.
add fuction ip6_append_data_mtu to make codes clearer.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
[ Upstream commit a881e963c7fe1f226e991ee9bbe8907acda93294 ]
bridge: set fake_rtable's dst to NULL to avoid kernel Oops
when bridge is deleted before tap/vif device's delete, kernel may
encounter an oops because of NULL reference to fake_rtable's dst.
Set fake_rtable's dst to NULL before sending packets out can solve
this problem.
v4 reformat, change br_drop_fake_rtable(skb) to {}
v3 enrich commit header
v2 introducing new flag DST_FAKE_RTABLE to dst_entry struct.
[ Use "do { } while (0)" for nop br_drop_fake_rtable()
implementation -DaveM ]
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Peter Huang <peter.huangpeng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 080399aaaf3531f5b8761ec0ac30ff98891e8686 upstream.
Hi,
We have a bug report open where a squashfs image mounted on ppc64 would
exhibit errors due to trying to read beyond the end of the disk. It can
easily be reproduced by doing the following:
[root@ibm-p750e-02-lp3 ~]# ls -l install.img
-rw-r--r-- 1 root root 142032896 Apr 30 16:46 install.img
[root@ibm-p750e-02-lp3 ~]# mount -o loop ./install.img /mnt/test
[root@ibm-p750e-02-lp3 ~]# dd if=/dev/loop0 of=/dev/null
dd: reading `/dev/loop0': Input/output error
277376+0 records in
277376+0 records out
142016512 bytes (142 MB) copied, 0.9465 s, 150 MB/s
In dmesg, you'll find the following:
squashfs: version 4.0 (2009/01/31) Phillip Lougher
[ 43.106012] attempt to access beyond end of device
[ 43.106029] loop0: rw=0, want=277410, limit=277408
[ 43.106039] Buffer I/O error on device loop0, logical block 138704
[ 43.106053] attempt to access beyond end of device
[ 43.106057] loop0: rw=0, want=277412, limit=277408
[ 43.106061] Buffer I/O error on device loop0, logical block 138705
[ 43.106066] attempt to access beyond end of device
[ 43.106070] loop0: rw=0, want=277414, limit=277408
[ 43.106073] Buffer I/O error on device loop0, logical block 138706
[ 43.106078] attempt to access beyond end of device
[ 43.106081] loop0: rw=0, want=277416, limit=277408
[ 43.106085] Buffer I/O error on device loop0, logical block 138707
[ 43.106089] attempt to access beyond end of device
[ 43.106093] loop0: rw=0, want=277418, limit=277408
[ 43.106096] Buffer I/O error on device loop0, logical block 138708
[ 43.106101] attempt to access beyond end of device
[ 43.106104] loop0: rw=0, want=277420, limit=277408
[ 43.106108] Buffer I/O error on device loop0, logical block 138709
[ 43.106112] attempt to access beyond end of device
[ 43.106116] loop0: rw=0, want=277422, limit=277408
[ 43.106120] Buffer I/O error on device loop0, logical block 138710
[ 43.106124] attempt to access beyond end of device
[ 43.106128] loop0: rw=0, want=277424, limit=277408
[ 43.106131] Buffer I/O error on device loop0, logical block 138711
[ 43.106135] attempt to access beyond end of device
[ 43.106139] loop0: rw=0, want=277426, limit=277408
[ 43.106143] Buffer I/O error on device loop0, logical block 138712
[ 43.106147] attempt to access beyond end of device
[ 43.106151] loop0: rw=0, want=277428, limit=277408
[ 43.106154] Buffer I/O error on device loop0, logical block 138713
[ 43.106158] attempt to access beyond end of device
[ 43.106162] loop0: rw=0, want=277430, limit=277408
[ 43.106166] attempt to access beyond end of device
[ 43.106169] loop0: rw=0, want=277432, limit=277408
...
[ 43.106307] attempt to access beyond end of device
[ 43.106311] loop0: rw=0, want=277470, limit=2774
Squashfs manages to read in the end block(s) of the disk during the
mount operation. Then, when dd reads the block device, it leads to
block_read_full_page being called with buffers that are beyond end of
disk, but are marked as mapped. Thus, it would end up submitting read
I/O against them, resulting in the errors mentioned above. I fixed the
problem by modifying init_page_buffers to only set the buffer mapped if
it fell inside of i_size.
Cheers,
Jeff
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Acked-by: Nick Piggin <npiggin@kernel.dk>
--
Changes from v1->v2: re-used max_block, as suggested by Nick Piggin.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 68c2c39a76b094e9b2773e5846424ea674bf2c46 upstream.
PV on HVM guests map GSIs into event channels. At restore time the
event channels are resumed by restore_pirqs.
Device drivers might try to register the same GSI again through ACPI at
restore time, but the GSI has already been mapped and bound by
restore_pirqs. This patch detects these situations and avoids
mapping the same GSI multiple times.
Without this patch we get:
(XEN) irq.c:2235: dom4: pirq 23 or emuirq 28 already mapped
and waste a pirq.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit bbbc4c4d8c5face097d695f9bf3a39647ba6b7e7 upstream.
Commit 06e8935feb ("optimized SDIO IRQ handling for single irq")
introduced some spurious calls to SDIO function interrupt handlers,
such as when the SDIO IRQ thread is started, or the safety check
performed upon a system resume. Let's add a flag to perform the
optimization only when a real interrupt is signaled by the host
driver and we know there is no point confirming it.
Reported-by: Sujit Reddy Thumma <sthumma@codeaurora.org>
Signed-off-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Chris Ball <cjb@laptop.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 2c4d6bf295ae10ffcd84f0df6cb642598eb66603 upstream.
Move usb_translate_errors from usb core to linux/usb.h as it is meant to
be accessed from drivers.
Signed-off-by: Johan Hovold <jhovold@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 05c69d298c96703741cac9a5cbbf6c53bd55a6e2 upstream.
6d1d8050b4bc8 "block, partition: add partition_meta_info to hd_struct"
added part_unpack_uuid() which assumes that the passed in buffer has
enough space for sprintfing "%pU" - 37 characters including '\0'.
Unfortunately, b5af921ec0233 "init: add support for root devices
specified by partition UUID" supplied 33 bytes buffer to the function
leading to the following panic with stackprotector enabled.
Kernel panic - not syncing: stack-protector: Kernel stack corrupted in: ffffffff81b14c7e
[<ffffffff815e226b>] panic+0xba/0x1c6
[<ffffffff81b14c7e>] ? printk_all_partitions+0x259/0x26xb
[<ffffffff810566bb>] __stack_chk_fail+0x1b/0x20
[<ffffffff81b15c7e>] printk_all_paritions+0x259/0x26xb
[<ffffffff81aedfe0>] mount_block_root+0x1bc/0x27f
[<ffffffff81aee0fa>] mount_root+0x57/0x5b
[<ffffffff81aee23b>] prepare_namespace+0x13d/0x176
[<ffffffff8107eec0>] ? release_tgcred.isra.4+0x330/0x30
[<ffffffff81aedd60>] kernel_init+0x155/0x15a
[<ffffffff81087b97>] ? schedule_tail+0x27/0xb0
[<ffffffff815f4d24>] kernel_thread_helper+0x5/0x10
[<ffffffff81aedc0b>] ? start_kernel+0x3c5/0x3c5
[<ffffffff815f4d20>] ? gs_change+0x13/0x13
Increase the buffer size, remove the dangerous part_unpack_uuid() and
use snprintf() directly from printk_all_partitions().
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Szymon Gruszczynski <sz.gruszczynski@googlemail.com>
Cc: Will Drewry <wad@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
(cherry picked from commit 3e515705a1f46beb1c942bb8043c16f8ac7b1e9e)
If some vcpus are created before KVM_CREATE_IRQCHIP, then
irqchip_in_kernel() and vcpu->arch.apic will be inconsistent, leading
to potential NULL pointer dereferences.
Fix by:
- ensuring that no vcpus are installed when KVM_CREATE_IRQCHIP is called
- ensuring that a vcpu has an apic if it is installed after KVM_CREATE_IRQCHIP
This is somewhat long winded because vcpu->arch.apic is created without
kvm->lock held.
Based on earlier patch by Michael Ellerman.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 4a42243886b87cd28a39b192161767c2af851a55 upstream.
This patch fixes the following build failure:
In file included from include/linux/mtd/qinfo.h:4:0,
from include/linux/mtd/pfow.h:7,
from drivers/mtd/lpddr/lpddr_cmds.c:27:
include/linux/mtd/map.h: In function 'inline_map_read':
include/linux/mtd/map.h:409:3: error: implicit declaration of function 'BUILD_BUG_ON' [-Werror=implicit-function-declaration]
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 5b6e9bcdeb65634b4ad604eb4536404bbfc62cfa upstream.
Commit 4231d47e6fe69f061f96c98c30eaf9fb4c14b96d(net/usbnet: avoid
recursive locking in usbnet_stop()) fixes the recursive locking
problem by releasing the skb queue lock before unlink, but may
cause skb traversing races:
- after URB is unlinked and the queue lock is released,
the refered skb and skb->next may be moved to done queue,
even be released
- in skb_queue_walk_safe, the next skb is still obtained
by next pointer of the last skb
- so maybe trigger oops or other problems
This patch extends the usage of entry->state to describe 'start_unlink'
state, so always holding the queue(rx/tx) lock to change the state if
the referd skb is in rx or tx queue because we need to know if the
refered urb has been started unlinking in unlink_urbs.
The other part of this patch is based on Huajun's patch:
always traverse from head of the tx/rx queue to get skb which is
to be unlinked but not been started unlinking.
Signed-off-by: Huajun Li <huajun.li.lee@gmail.com>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Cc: Oliver Neukum <oneukum@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit f5c2347ee20a8d6964d6a6b1ad04f200f8d4dfa7 upstream.
<asm-generic/statfs.h> is exported to userspace, so using
BITS_PER_LONG is invalid. We need to use __BITS_PER_LONG instead.
This is kernel bugzilla 43165.
Reported-by: H.J. Lu <hjl.tools@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1335465916-16965-1-git-send-email-hpa@linux.intel.com
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 2f624278626677bfaf73fef97f86b37981621f5c upstream.
We really need to use a ACCESS_ONCE() on the sequence value read in
__read_seqcount_begin(), because otherwise the compiler might end up
reloading the value in between the test and the return of it. As a
result, it might end up returning an odd value (which means that a write
is in progress).
If the reader is then fast enough that that odd value is still the
current one when the read_seqcount_retry() is done, we might end up with
a "successful" read sequence, even despite the concurrent write being
active.
In practice this probably never really happens - there just isn't
anything else going on around the read of the sequence count, and the
common case is that we end up having a read barrier immediately
afterwards.
So the code sequence in which gcc might decide to reaload from memory is
small, and there's no reason to believe it would ever actually do the
reload. But if the compiler ever were to decide to do so, it would be
incredibly annoying to debug. Let's just make sure.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 41b3254c93acc56adc3c4477fef7c9512d47659e upstream.
More recent versions of the UEFI spec have added new attributes for
variables. Add them.
Signed-off-by: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 9883035ae7edef3ec62ad215611cb8e17d6a1a5d upstream.
The actual internal pipe implementation is already really about
individual packets (called "pipe buffers"), and this simply exposes that
as a special packetized mode.
When we are in the packetized mode (marked by O_DIRECT as suggested by
Alan Cox), a write() on a pipe will not merge the new data with previous
writes, so each write will get a pipe buffer of its own. The pipe
buffer is then marked with the PIPE_BUF_FLAG_PACKET flag, which in turn
will tell the reader side to break the read at that boundary (and throw
away any partial packet contents that do not fit in the read buffer).
End result: as long as you do writes less than PIPE_BUF in size (so that
the pipe doesn't have to split them up), you can now treat the pipe as a
packet interface, where each read() system call will read one packet at
a time. You can just use a sufficiently big read buffer (PIPE_BUF is
sufficient, since bigger than that doesn't guarantee atomicity anyway),
and the return value of the read() will naturally give you the size of
the packet.
NOTE! We do not support zero-sized packets, and zero-sized reads and
writes to a pipe continue to be no-ops. Also note that big packets will
currently be split at write time, but that the size at which that
happens is not really specified (except that it's bigger than PIPE_BUF).
Currently that limit is the system page size, but we might want to
explicitly support bigger packets some day.
The main user for this is going to be the autofs packet interface,
allowing us to stop having to care so deeply about exact packet sizes
(which have had bugs with 32/64-bit compatibility modes). But user
space can create packetized pipes with "pipe2(fd, O_DIRECT)", which will
fail with an EINVAL on kernels that do not support this interface.
Tested-by: Michael Tokarev <mjt@tls.msk.ru>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: David Miller <davem@davemloft.net>
Cc: Ian Kent <raven@themaw.net>
Cc: Thomas Meyer <thomas@m3y3r.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 151b61284776be2d6f02d48c23c3625678960b97 upstream.
This patch (as1545) fixes a problem affecting several ASUS computers:
The machine crashes or corrupts memory when going into suspend if the
ehci-hcd driver is bound to any controllers. Users have been forced
to unbind or unload ehci-hcd before putting their systems to sleep.
After extensive testing, it was determined that the machines don't
like going into suspend when any EHCI controllers are in the PCI D3
power state. Presumably this is a firmware bug, but there's nothing
we can do about it except to avoid putting the controllers in D3
during system sleep.
The patch adds a new flag to indicate whether the problem is present,
and avoids changing the controller's power state if the flag is set.
Runtime suspend is unaffected; this matters only for system suspend.
However as a side effect, the controller will not respond to remote
wakeup requests while the system is asleep. Hence USB wakeup is not
functional -- but of course, this is already true in the current state
of affairs.
This fixes Bugzilla #42728.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Tested-by: Steven Rostedt <rostedt@goodmis.org>
Tested-by: Andrey Rahmatullin <wrar@wrar.name>
Tested-by: Oleksij Rempel (fishor) <bug-track@fisher-privat.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
[ This combines upstream commit
a21d45726acacc963d8baddf74607d9b74e2b723 and the follow-on bug fix
commit 22b4a4f22da4b39c6f7f679fd35f3d35c91bf851 ]
Marc Merlin reported many order-1 allocations failures in TX path on its
wireless setup, that dont make any sense with MTU=1500 network, and non
SG capable hardware.
After investigation, it turns out TCP uses sk_stream_alloc_skb() and
used as a convention skb_tailroom(skb) to know how many bytes of data
payload could be put in this skb (for non SG capable devices)
Note : these skb used kmalloc-4096 (MTU=1500 + MAX_HEADER +
sizeof(struct skb_shared_info) being above 2048)
Later, mac80211 layer need to add some bytes at the tail of skb
(IEEE80211_ENCRYPT_TAILROOM = 18 bytes) and since no more tailroom is
available has to call pskb_expand_head() and request order-1
allocations.
This patch changes sk_stream_alloc_skb() so that only
sk->sk_prot->max_header bytes of headroom are reserved, and use a new
skb field, avail_size to hold the data payload limit.
This way, order-0 allocations done by TCP stack can leave more than 2 KB
of tailroom and no more allocation is performed in mac80211 layer (or
any layer needing some tailroom)
avail_size is unioned with mark/dropcount, since mark will be set later
in IP stack for output packets. Therefore, skb size is unchanged.
Reported-by: Marc MERLIN <marc@merlins.org>
Tested-by: Marc MERLIN <marc@merlins.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[bwh: Correct commit hash for follow-on bug fix]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
[ This combines upstream commit
2f53384424251c06038ae612e56231b96ab610ee and the follow-on bug fix
commit 35f9c09fe9c72eb8ca2b8e89a593e1c151f28fc2 ]
vmsplice()/splice(pipe, socket) call do_tcp_sendpages() one page at a
time, adding at most 4096 bytes to an skb. (assuming PAGE_SIZE=4096)
The call to tcp_push() at the end of do_tcp_sendpages() forces an
immediate xmit when pipe is not already filled, and tso_fragment() try
to split these skb to MSS multiples.
4096 bytes are usually split in a skb with 2 MSS, and a remaining
sub-mss skb (assuming MTU=1500)
This makes slow start suboptimal because many small frames are sent to
qdisc/driver layers instead of big ones (constrained by cwnd and packets
in flight of course)
In fact, applications using sendmsg() (adding an additional memory copy)
instead of vmsplice()/splice()/sendfile() are a bit faster because of
this anomaly, especially if serving small files in environments with
large initial [c]wnd.
Call tcp_push() only if MSG_MORE is not set in the flags parameter.
This bit is automatically provided by splice() internals but for the
last page, or on all pages if user specified SPLICE_F_MORE splice()
flag.
In some workloads, this can reduce number of sent logical packets by an
order of magnitude, making zero-copy TCP actually faster than
one-copy :)
Reported-by: Tom Herbert <therbert@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: H.K. Jerry Chu <hkchu@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
[ Upstream commit 2def16ae6b0c77571200f18ba4be049b03d75579 ]
Commit f04565ddf52 (dev: use name hash for dev_seq_ops) added a second
regression, as some devices are missing from /proc/net/dev if many
devices are defined.
When seq_file buffer is filled, the last ->next/show() method is
canceled (pos value is reverted to value prior ->next() call)
Problem is after above commit, we dont restart the lookup at right
position in ->start() method.
Fix this by removing the internal 'pos' pointer added in commit, since
we need to use the 'loff_t *pos' provided by seq_file layer.
This also reverts commit 5cac98dd0 (net: Fix corruption
in /proc/*/net/dev_mcast), since its not needed anymore.
Reported-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Mihai Maruseac <mmaruseac@ixiacom.com>
Tested-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 32f6daad4651a748a58a3ab6da0611862175722f upstream.
We've been adding new mappings, but not destroying old mappings.
This can lead to a page leak as pages are pinned using
get_user_pages, but only unpinned with put_page if they still
exist in the memslots list on vm shutdown. A memslot that is
destroyed while an iommu domain is enabled for the guest will
therefore result in an elevated page reference count that is
never cleared.
Additionally, without this fix, the iommu is only programmed
with the first translation for a gpa. This can result in
peer-to-peer errors if a mapping is destroyed and replaced by a
new mapping at the same gpa as the iommu will still be pointing
to the original, pinned memory address.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
|
|
commit 94324962066231a938564bebad0f941cd2d06bb2 upstream.
Make sure hci_dev_open returns immediately if hci_dev_unregister has
been called.
This fixes a race between hci_dev_open and hci_dev_unregister which can
lead to a NULL-pointer dereference.
Bug is 100% reproducible using hciattach and a disconnected serial port:
0. # hciattach -n /dev/ttyO1 any noflow
1. hci_dev_open called from hci_power_on grabs req lock
2. hci_init_req executes but device fails to initialise (times out
eventually)
3. hci_dev_open is called from hci_sock_ioctl and sleeps on req lock
4. hci_uart_tty_close calls hci_dev_unregister and sleeps on req lock in
hci_dev_do_close
5. hci_dev_open (1) releases req lock
6. hci_dev_do_close grabs req lock and returns as device is not up
7. hci_dev_unregister sleeps in destroy_workqueue
8. hci_dev_open (3) grabs req lock, calls hci_init_req and eventually sleeps
9. hci_dev_unregister finishes, while hci_dev_open is still running...
[ 79.627136] INFO: trying to register non-static key.
[ 79.632354] the code is fine but needs lockdep annotation.
[ 79.638122] turning off the locking correctness validator.
[ 79.643920] [<c00188bc>] (unwind_backtrace+0x0/0xf8) from [<c00729c4>] (__lock_acquire+0x1590/0x1ab0)
[ 79.653594] [<c00729c4>] (__lock_acquire+0x1590/0x1ab0) from [<c00733f8>] (lock_acquire+0x9c/0x128)
[ 79.663085] [<c00733f8>] (lock_acquire+0x9c/0x128) from [<c0040a88>] (run_timer_softirq+0x150/0x3ac)
[ 79.672668] [<c0040a88>] (run_timer_softirq+0x150/0x3ac) from [<c003a3b8>] (__do_softirq+0xd4/0x22c)
[ 79.682281] [<c003a3b8>] (__do_softirq+0xd4/0x22c) from [<c003a924>] (irq_exit+0x8c/0x94)
[ 79.690856] [<c003a924>] (irq_exit+0x8c/0x94) from [<c0013a50>] (handle_IRQ+0x34/0x84)
[ 79.699157] [<c0013a50>] (handle_IRQ+0x34/0x84) from [<c0008530>] (omap3_intc_handle_irq+0x48/0x4c)
[ 79.708648] [<c0008530>] (omap3_intc_handle_irq+0x48/0x4c) from [<c037499c>] (__irq_usr+0x3c/0x60)
[ 79.718048] Exception stack(0xcf281fb0 to 0xcf281ff8)
[ 79.723358] 1fa0: 0001e6a0 be8dab00 0001e698 00036698
[ 79.731933] 1fc0: 0002df98 0002df38 0000001f 00000000 b6f234d0 00000000 00000004 00000000
[ 79.740509] 1fe0: 0001e6f8 be8d6aa0 be8dac50 0000aab8 80000010 ffffffff
[ 79.747497] Unable to handle kernel NULL pointer dereference at virtual address 00000000
[ 79.756011] pgd = cf3b4000
[ 79.758850] [00000000] *pgd=8f0c7831, *pte=00000000, *ppte=00000000
[ 79.765502] Internal error: Oops: 80000007 [#1]
[ 79.770294] Modules linked in:
[ 79.773529] CPU: 0 Tainted: G W (3.3.0-rc6-00002-gb5d5c87 #421)
[ 79.781066] PC is at 0x0
[ 79.783721] LR is at run_timer_softirq+0x16c/0x3ac
[ 79.788787] pc : [<00000000>] lr : [<c0040aa4>] psr: 60000113
[ 79.788787] sp : cf281ee0 ip : 00000000 fp : cf280000
[ 79.800903] r10: 00000004 r9 : 00000100 r8 : b6f234d0
[ 79.806427] r7 : c0519c28 r6 : cf093488 r5 : c0561a00 r4 : 00000000
[ 79.813323] r3 : 00000000 r2 : c054eee0 r1 : 00000001 r0 : 00000000
[ 79.820190] Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user
[ 79.827728] Control: 10c5387d Table: 8f3b4019 DAC: 00000015
[ 79.833801] Process gpsd (pid: 1265, stack limit = 0xcf2802e8)
[ 79.839965] Stack: (0xcf281ee0 to 0xcf282000)
[ 79.844573] 1ee0: 00000002 00000000 c0040a24 00000000 00000002 cf281f08 00200200 00000000
[ 79.853210] 1f00: 00000000 cf281f18 cf281f08 00000000 00000000 00000000 cf281f18 cf281f18
[ 79.861816] 1f20: 00000000 00000001 c056184c 00000000 00000001 b6f234d0 c0561848 00000004
[ 79.870452] 1f40: cf280000 c003a3b8 c051e79c 00000001 00000000 00000100 3fa9e7b8 0000000a
[ 79.879089] 1f60: 00000025 cf280000 00000025 00000000 00000000 b6f234d0 00000000 00000004
[ 79.887756] 1f80: 00000000 c003a924 c053ad38 c0013a50 fa200000 cf281fb0 ffffffff c0008530
[ 79.896362] 1fa0: 0001e6a0 0000aab8 80000010 c037499c 0001e6a0 be8dab00 0001e698 00036698
[ 79.904998] 1fc0: 0002df98 0002df38 0000001f 00000000 b6f234d0 00000000 00000004 00000000
[ 79.913665] 1fe0: 0001e6f8 be8d6aa0 be8dac50 0000aab8 80000010 ffffffff 00fbf700 04ffff00
[ 79.922302] [<c0040aa4>] (run_timer_softirq+0x16c/0x3ac) from [<c003a3b8>] (__do_softirq+0xd4/0x22c)
[ 79.931945] [<c003a3b8>] (__do_softirq+0xd4/0x22c) from [<c003a924>] (irq_exit+0x8c/0x94)
[ 79.940582] [<c003a924>] (irq_exit+0x8c/0x94) from [<c0013a50>] (handle_IRQ+0x34/0x84)
[ 79.948913] [<c0013a50>] (handle_IRQ+0x34/0x84) from [<c0008530>] (omap3_intc_handle_irq+0x48/0x4c)
[ 79.958404] [<c0008530>] (omap3_intc_handle_irq+0x48/0x4c) from [<c037499c>] (__irq_usr+0x3c/0x60)
[ 79.967773] Exception stack(0xcf281fb0 to 0xcf281ff8)
[ 79.973083] 1fa0: 0001e6a0 be8dab00 0001e698 00036698
[ 79.981658] 1fc0: 0002df98 0002df38 0000001f 00000000 b6f234d0 00000000 00000004 00000000
[ 79.990234] 1fe0: 0001e6f8 be8d6aa0 be8dac50 0000aab8 80000010 ffffffff
[ 79.997161] Code: bad PC value
[ 80.000396] ---[ end trace 6f6739840475f9ee ]---
[ 80.005279] Kernel panic - not syncing: Fatal exception in interrupt
Signed-off-by: Johan Hovold <jhovold@gmail.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 9993bc635d01a6ee7f6b833b4ee65ce7c06350b1 upstream.
When a machine boots up, the TSC generally gets reset. However,
when kexec is used to boot into a kernel, the TSC value would be
carried over from the previous kernel. The computation of
cycns_offset in set_cyc2ns_scale is prone to an overflow, if the
machine has been up more than 208 days prior to the kexec. The
overflow happens when we multiply *scale, even though there is
enough room to store the final answer.
We fix this issue by decomposing tsc_now into the quotient and
remainder of division by CYC2NS_SCALE_FACTOR and then performing
the multiplication separately on the two components.
Refactor code to share the calculation with the previous
fix in __cycles_2_ns().
Signed-off-by: Salman Qazi <sqazi@google.com>
Acked-by: John Stultz <john.stultz@linaro.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Turner <pjt@google.com>
Cc: john stultz <johnstul@us.ibm.com>
Link: http://lkml.kernel.org/r/20120310004027.19291.88460.stgit@dungbeetle.mtv.corp.google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 66189be74ff5f9f3fd6444315b85be210d07cef2 upstream.
We can deadlock if we have a write oplock and two processes
use the same file handle. In this case the first process can't
unlock its lock if the second process blocked on the lock in the
same time.
Fix it by using posix_lock_file rather than posix_lock_file_wait
under cinode->lock_mutex. If we request a blocking lock and
posix_lock_file indicates that there is another lock that prevents
us, wait untill that lock is released and restart our call.
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Pavel Shilovsky <piastry@etersoft.ru>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 3751d3e85cf693e10e2c47c03c8caa65e171099b upstream.
There has long been a limitation using software breakpoints with a
kernel compiled with CONFIG_DEBUG_RODATA going back to 2.6.26. For
this particular patch, it will apply cleanly and has been tested all
the way back to 2.6.36.
The kprobes code uses the text_poke() function which accommodates
writing a breakpoint into a read-only page. The x86 kgdb code can
solve the problem similarly by overriding the default breakpoint
set/remove routines and using text_poke() directly.
The x86 kgdb code will first attempt to use the traditional
probe_kernel_write(), and next try using a the text_poke() function.
The break point install method is tracked such that the correct break
point removal routine will get called later on.
Cc: x86@kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Inspried-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 98b54aa1a2241b59372468bd1e9c2d207bdba54b upstream.
There is extra state information that needs to be exposed in the
kgdb_bpt structure for tracking how a breakpoint was installed. The
debug_core only uses the the probe_kernel_write() to install
breakpoints, but this is not enough for all the archs. Some arch such
as x86 need to use text_poke() in order to install a breakpoint into a
read only page.
Passing the kgdb_bpt structure to kgdb_arch_set_breakpoint() and
kgdb_arch_remove_breakpoint() allows other archs to set the type
variable which indicates how the breakpoint was installed.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 4a649903f91232d02284d53724b0a45728111767 upstream.
Richard Weinberger noticed that on some RTC hardware that
doesn't support UIE mode, due to coarse granular alarms
(like 1minute resolution), the current virtualized RTC
support doesn't properly error out when UIE is enabled.
Instead the current code queues an alarm for the next second,
but it won't fire until up to a miniute later.
This patch provides a generic way to flag this sort of hardware
and fixes the issue on the mpc5121 where Richard noticed the
problem.
Reported-by: Richard Weinberger <richard@nod.at>
Tested-by: Richard Weinberger <richard@nod.at>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 1631fcea8399da5e80a80084b3b8c5bfd99d21e7 upstream.
<asm-generic/unistd.h> was set up to use sys_sendfile() for the 32-bit
compat API instead of sys_sendfile64(), but in fact the right thing to
do is to use sys_sendfile64() in all cases. The 32-bit sendfile64() API
in glibc uses the sendfile64 syscall, so it has to be capable of doing
full 64-bit operations. But the sys_sendfile() kernel implementation
has a MAX_NON_LFS test in it which explicitly limits the offset to 2^32.
So, we need to use the sys_sendfile64() implementation in the kernel
for this case.
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit ce880cb860f36694d2cdebfac9e6ae18176fe4c4 upstream.
The USB graphics card driver delays the unregistering of the framebuffer
device to a workqueue, which breaks the userspace visible remove uevent
sequence. Recent userspace tools started to support USB graphics card
hotplug out-of-the-box and rely on proper events sent by the kernel.
The framebuffer device is a direct child of the USB interface which is
removed immediately after the USB .disconnect() callback. But the fb device
in /sys stays around until its final cleanup, at a time where all the parent
devices have been removed already.
To work around that, we remove the sysfs fb device directly in the USB
.disconnect() callback and leave only the cleanup of the internal fb
data to the delayed work.
Before:
add /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2 (usb)
add /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2/2-1.2:1.0 (usb)
add /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2/2-1.2:1.0/graphics/fb0 (graphics)
remove /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2/2-1.2:1.0 (usb)
remove /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2 (usb)
remove /2-1.2:1.0/graphics/fb0 (graphics)
After:
add /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2 (usb)
add /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2/2-1.2:1.0 (usb)
add /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2/2-1.2:1.0/graphics/fb1 (graphics)
remove /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2/2-1.2:1.0/graphics/fb1 (graphics)
remove /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2/2-1.2:1.0 (usb)
remove /devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.2 (usb)
Tested-by: Bernie Thompson <bernie@plugable.com>
Acked-by: Bernie Thompson <bernie@plugable.com>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Florian Tobias Schandinat <FlorianSchandinat@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 1a5a9906d4e8d1976b701f889d8f35d54b928f25 upstream.
In some cases it may happen that pmd_none_or_clear_bad() is called with
the mmap_sem hold in read mode. In those cases the huge page faults can
allocate hugepmds under pmd_none_or_clear_bad() and that can trigger a
false positive from pmd_bad() that will not like to see a pmd
materializing as trans huge.
It's not khugepaged causing the problem, khugepaged holds the mmap_sem
in write mode (and all those sites must hold the mmap_sem in read mode
to prevent pagetables to go away from under them, during code review it
seems vm86 mode on 32bit kernels requires that too unless it's
restricted to 1 thread per process or UP builds). The race is only with
the huge pagefaults that can convert a pmd_none() into a
pmd_trans_huge().
Effectively all these pmd_none_or_clear_bad() sites running with
mmap_sem in read mode are somewhat speculative with the page faults, and
the result is always undefined when they run simultaneously. This is
probably why it wasn't common to run into this. For example if the
madvise(MADV_DONTNEED) runs zap_page_range() shortly before the page
fault, the hugepage will not be zapped, if the page fault runs first it
will be zapped.
Altering pmd_bad() not to error out if it finds hugepmds won't be enough
to fix this, because zap_pmd_range would then proceed to call
zap_pte_range (which would be incorrect if the pmd become a
pmd_trans_huge()).
The simplest way to fix this is to read the pmd in the local stack
(regardless of what we read, no need of actual CPU barriers, only
compiler barrier needed), and be sure it is not changing under the code
that computes its value. Even if the real pmd is changing under the
value we hold on the stack, we don't care. If we actually end up in
zap_pte_range it means the pmd was not none already and it was not huge,
and it can't become huge from under us (khugepaged locking explained
above).
All we need is to enforce that there is no way anymore that in a code
path like below, pmd_trans_huge can be false, but pmd_none_or_clear_bad
can run into a hugepmd. The overhead of a barrier() is just a compiler
tweak and should not be measurable (I only added it for THP builds). I
don't exclude different compiler versions may have prevented the race
too by caching the value of *pmd on the stack (that hasn't been
verified, but it wouldn't be impossible considering
pmd_none_or_clear_bad, pmd_bad, pmd_trans_huge, pmd_none are all inlines
and there's no external function called in between pmd_trans_huge and
pmd_none_or_clear_bad).
if (pmd_trans_huge(*pmd)) {
if (next-addr != HPAGE_PMD_SIZE) {
VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
split_huge_page_pmd(vma->vm_mm, pmd);
} else if (zap_huge_pmd(tlb, vma, pmd, addr))
continue;
/* fall through */
}
if (pmd_none_or_clear_bad(pmd))
Because this race condition could be exercised without special
privileges this was reported in CVE-2012-1179.
The race was identified and fully explained by Ulrich who debugged it.
I'm quoting his accurate explanation below, for reference.
====== start quote =======
mapcount 0 page_mapcount 1
kernel BUG at mm/huge_memory.c:1384!
At some point prior to the panic, a "bad pmd ..." message similar to the
following is logged on the console:
mm/memory.c:145: bad pmd ffff8800376e1f98(80000000314000e7).
The "bad pmd ..." message is logged by pmd_clear_bad() before it clears
the page's PMD table entry.
143 void pmd_clear_bad(pmd_t *pmd)
144 {
-> 145 pmd_ERROR(*pmd);
146 pmd_clear(pmd);
147 }
After the PMD table entry has been cleared, there is an inconsistency
between the actual number of PMD table entries that are mapping the page
and the page's map count (_mapcount field in struct page). When the page
is subsequently reclaimed, __split_huge_page() detects this inconsistency.
1381 if (mapcount != page_mapcount(page))
1382 printk(KERN_ERR "mapcount %d page_mapcount %d\n",
1383 mapcount, page_mapcount(page));
-> 1384 BUG_ON(mapcount != page_mapcount(page));
The root cause of the problem is a race of two threads in a multithreaded
process. Thread B incurs a page fault on a virtual address that has never
been accessed (PMD entry is zero) while Thread A is executing an madvise()
system call on a virtual address within the same 2 MB (huge page) range.
virtual address space
.---------------------.
| |
| |
.-|---------------------|
| | |
| | |<-- B(fault)
| | |
2 MB | |/////////////////////|-.
huge < |/////////////////////| > A(range)
page | |/////////////////////|-'
| | |
| | |
'-|---------------------|
| |
| |
'---------------------'
- Thread A is executing an madvise(..., MADV_DONTNEED) system call
on the virtual address range "A(range)" shown in the picture.
sys_madvise
// Acquire the semaphore in shared mode.
down_read(¤t->mm->mmap_sem)
...
madvise_vma
switch (behavior)
case MADV_DONTNEED:
madvise_dontneed
zap_page_range
unmap_vmas
unmap_page_range
zap_pud_range
zap_pmd_range
//
// Assume that this huge page has never been accessed.
// I.e. content of the PMD entry is zero (not mapped).
//
if (pmd_trans_huge(*pmd)) {
// We don't get here due to the above assumption.
}
//
// Assume that Thread B incurred a page fault and
.---------> // sneaks in here as shown below.
| //
| if (pmd_none_or_clear_bad(pmd))
| {
| if (unlikely(pmd_bad(*pmd)))
| pmd_clear_bad
| {
| pmd_ERROR
| // Log "bad pmd ..." message here.
| pmd_clear
| // Clear the page's PMD entry.
| // Thread B incremented the map count
| // in page_add_new_anon_rmap(), but
| // now the page is no longer mapped
| // by a PMD entry (-> inconsistency).
| }
| }
|
v
- Thread B is handling a page fault on virtual address "B(fault)" shown
|
