Since commit 13882a82ee (optimize iso queueing by setting
wake only after the last packet), drivers are required to call
fw_iso_context_queue_flush() after queueing a batch of packets.
The missing call would have an effect only if the controller
queue underruns, but then the DMA would stop completely.
Signed-off-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
There is a problem that kdump(2nd kernel) sometimes hangs up due
to a pending IPI from 1st kernel. Kernel panic occurs because IPI
comes before call_single_queue is initialized.
To fix the crash, rename init_call_single_data() to call_function_init()
and call it in start_kernel() so that call_single_queue can be
initialized before enabling interrupts.
The details of the crash are:
(1) 2nd kernel boots up
(2) A pending IPI from 1st kernel comes when irqs are first enabled
in start_kernel().
(3) Kernel tries to handle the interrupt, but call_single_queue
is not initialized yet at this point. As a result, in the
generic_smp_call_function_single_interrupt(), NULL pointer
dereference occurs when list_replace_init() tries to access
&q->list.next.
Therefore this patch changes the name of init_call_single_data()
to call_function_init() and calls it before local_irq_enable()
in start_kernel().
Signed-off-by: Takao Indoh <indou.takao@jp.fujitsu.com>
Reviewed-by: WANG Cong <xiyou.wangcong@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Milton Miller <miltonm@bga.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: kexec@lists.infradead.org
Link: http://lkml.kernel.org/r/D6CBEE2F420741indou.takao@jp.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The size of the desc array is not the size of the desc structure, so
when we try to free up things, we leak some parts.
Reported-by: Regis Dargent <rdargent@edevice.com>
Signed-off-by: Sonic Zhang <sonic.zhang@analog.com>
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
This patch removes the call to ndo_vlan_rx_register if the underlying
device doesn't have hardware support for VLAN.
Signed-off-by: Antoine Reversat <a.reversat@gmail.com>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
XOFF was mixed up with DOWN indication, causing causing CAIF channel to be
removed from mux and all incoming traffic to be lost after receiving flow-off.
Fix this by replacing FLOW_OFF with DOWN notification.
Signed-off-by: Sjur Brændeland <sjur.brandeland@stericsson.com>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
Commit 8d8fc29d02 changed the behavior of slave
devices in regards to netpoll. Specifically it created a mutually exclusive
relationship between being a slave and a netpoll-capable device. This creates
problems for KVM because guests relied on needing netconsole active on a slave
device to a bridge. Ideally libvirtd could just attach netconsole to the bridge
device instead, but thats currently infeasible, because while the bridge device
supports netpoll, it requires that all slave interface also support it, but the
tun/tap driver currently does not. The most direct solution is to teach tun/tap
to support netpoll, which is implemented by the patch below.
I've not tested this yet, but its pretty straightforward.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Rik van Riel <riel@redhat.com>
CC: Rik van Riel <riel@redhat.com>
CC: Maxim Krasnyansky <maxk@qualcomm.com>
CC: Cong Wang <amwang@redhat.com>
CC: "David S. Miller" <davem@davemloft.net>
Reviewed-by: Rik van Riel <riel@redhat.com>
Tested-by: Rik van Riel <riel@redhat.com>
Reviewed-by: WANG Cong <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
The dp83640 PHY provides time stamp and other information via special
PHY status frames. Previously, the driver decoded the frames and then
let the network stack drop them. This works fine when the PTP messages
come over UDP.
However, when receiving PTP messages via L2 packets, this creates a
problem. The status frames use the official PTP destination MAC address,
and so they are delivered to user space along with the "real" frames,
causing confusion for applications.
This commit fixes the issue by simply dropping the PHY status frames
in the driver.
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
If two eternal time stamp events occur at nearly the same time, the
phyter will add an extra word into the status frame. This commit fixes
the parsing code to recognize and skip over the extra word.
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
This PHY is available integrated into BCM63xx series SOCs only.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
drivers/net/phy/Kconfig | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
Acked-by: Florian Fainelli <ffainelli@freebox.fr>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
Upon reception of a MGM report packet the kernel sets the mrouters_only flag
in a skb that is a clone of the original skb, which means that the bridge
loses track of MGM packets (cb buffers are tied to a specific skb and not
shared) and it ends up forwading join requests to the bridge interface.
This can cause unexpected membership timeouts and intermitent/permanent loss
of connectivity as described in RFC 4541 [2.1.1. IGMP Forwarding Rules]:
A snooping switch should forward IGMP Membership Reports only to
those ports where multicast routers are attached.
[...]
Sending membership reports to other hosts can result, for IGMPv1
and IGMPv2, in unintentionally preventing a host from joining a
specific multicast group.
Signed-off-by: Fernando Luis Vazquez Cao <fernando@oss.ntt.co.jp>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
Upon reception of a IGMP/IGMPv2 membership report the kernel sets the
mrouters_only flag in a skb that may be a clone of the original skb, which
means that sometimes the bridge loses track of membership report packets (cb
buffers are tied to a specific skb and not shared) and it ends up forwading
join requests to the bridge interface.
This can cause unexpected membership timeouts and intermitent/permanent loss
of connectivity as described in RFC 4541 [2.1.1. IGMP Forwarding Rules]:
A snooping switch should forward IGMP Membership Reports only to
those ports where multicast routers are attached.
[...]
Sending membership reports to other hosts can result, for IGMPv1
and IGMPv2, in unintentionally preventing a host from joining a
specific multicast group.
Signed-off-by: Fernando Luis Vazquez Cao <fernando@oss.ntt.co.jp>
Tested-by: Hayato Kakuta <kakuta.hayato@oss.ntt.co.jp>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
Introducing driver for the network port of Samsung Kalmia based USB LTE modems.
It has also an ACM interface that previous patches associates with the "option"
module. To access those interfaces, the modem must first be switched from modem
mode using a tool like usb_modeswitch.
As the proprietary protocol has been discovered by watching the MS Windows driver
behavior, there might be errors in the protocol handling, but stable and fast
connection has been established for hours with Norwegian operator NetCom that
distributes this modem with their LTE/4G subscription.
More and updated information about how to use this driver is available here:
http://www.draisberghof.de/usb_modeswitch/bb/viewtopic.php?t=465https://github.com/mkotsbak/Samsung-GT-B3730-linux-driver
Signed-off-by: Marius B. Kotsbak <marius@kotsbak.com>
Signed-off-by: David S. Miller <davem@conan.davemloft.net>
* 'drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
drm/radeon/kms: use helper functions for fence read/write
drm/radeon/kms: set DP link config properly for DP bridges
drm/radeon/kms/atom: AdjustPixelClock fixes for DP bridges
drm/radeon/kms: fix handling of DP to LVDS bridges
drm/radeon/kms: issue blank/unblank commands for ext encoders
drm/radeon/kms: fix support for DDC on dp bridges
drm/radeon/kms: add support for load detection on dp bridges
drm/radeon/kms: add missing external encoder action
drm/radeon/kms: rework atombios_get_encoder_mode()
drm/radeon/kms: fix num crtcs for Cedar and Caicos
Revert "drm/i915: Enable GMBUS for post-gen2 chipsets"
drivers/gpu/drm: use printk_ratelimited instead of printk_ratelimit
drm/radeon: workaround a hw bug on some radeon chipsets with all-0 EDIDs.
drm: make debug levels match in edid failure code.
drm/radeon/kms: clear wb memory by default
drm/radeon/kms: be more pedantic about the g5 quirk (v2)
drm/radeon/kms: signed fix for evergreen thermal
drm: populate irq_by_busid-member for pci
The existing code assumed scratch registers in a number
of places while in most cases we are be using writeback
and events rather than scratch registers.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
DP clock and lanes were not set properly for DP bridges.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Need to set the external transmitter type properly in
AdjustPixelClock to get the properly output.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
They need to be treated like eDP rather than DP.
May fix:
https://bugzilla.kernel.org/show_bug.cgi?id=34822
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Need to set up the bridge for DDC prior to the
i2c over aux transaction.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This should give us more reliable results if the table
is called before an active device is set.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Revert commit 8f9a3f9b63. This fixes a
hang when loading the eeprom driver (see bug #35572.) GMBUS will be
re-enabled later, differently.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Reported-by: Marek Otahal <markotahal@gmail.com>
Tested-by: Yermandu Patapitafious <yermandu.dev@gmail.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Dave Airlie <airlied@redhat.com>
The commit "use softirq instead of kthreads except when RCU_BOOST=y"
just applied #ifdef in place. This commit is a cleanup that moves
the newly #ifdef'ed code to the header file kernel/rcutree_plugin.h.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
swapcache will reach the below code path in migrate_page_move_mapping,
and swapcache is accounted as NR_FILE_PAGES but it's not accounted as
NR_SHMEM.
Hugh pointed out we must use PageSwapCache instead of comparing
mapping to &swapper_space, to avoid build failure with CONFIG_SWAP=n.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch augments the pstate transition code to error out
(instead of returning 0) when an incorrect pstate is provided.
Suggested-by: Borislav Petkov <bp@alien8.de>
CC: andre.przywara@amd.com
CC: Mark.Langsdorf@amd.com
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Dave Jones <davej@redhat.com>
Before this patch if we failed the vid transition would still try to
submit the "new" frequencies to cpufreq.
That is incorrect - also we could submit a non-existing frequency value
which would cause cpufreq to crash. The ultimate fix is in cpufreq
to deal with incorrect values, but this patch improves the error
recovery in the AMD powernowk8 driver.
The failure that was reported was as follows:
powernow-k8: Found 1 AMD Athlon(tm) 64 Processor 3700+ (1 cpu cores) (version 2.20.00)
powernow-k8: fid 0x2 (1000 MHz), vid 0x12
powernow-k8: fid 0xa (1800 MHz), vid 0xa
powernow-k8: fid 0xc (2000 MHz), vid 0x8
powernow-k8: fid 0xe (2200 MHz), vid 0x8
Marking TSC unstable due to cpufreq changes
powernow-k8: fid trans failed, fid 0x2, curr 0x0
BUG: unable to handle kernel paging request at ffff880807e07b78
IP: [<ffffffff81479163>] cpufreq_stats_update+0x46/0x5b
...
And transition fails and data->currfid ends up with 0. Since
the machine does not support 800Mhz value when the calculation is
done ('find_khz_freq_from_fid(data->currfid);') it reports the
new frequency as 800000 which is bogus. This patch fixes
the issue during target setting.
The patch however does not fix the issue in 'powernowk8_cpu_init'
where the pol->cur can also be set with the 800000 value:
pol->cur = find_khz_freq_from_fid(data->currfid);
dprintk("policy current frequency %d kHz\n", pol->cur);
/* min/max the cpu is capable of */
if (cpufreq_frequency_table_cpuinfo(pol, data->powernow_table)) {
The fix for that looks to update cpufreq_frequency_table_cpuinfo to
check pol->cur.... but that would cause an regression in how the
acpi-cpufreq driver works (it sets cpu->cur after calling
cpufreq_frequency_table_cpuinfo). Instead the fix will be to let
cpufreq gracefully handle bogus data (another patch).
Acked-by: Borislav Petkov <bp@alien8.de>
CC: andre.przywara@amd.com
CC: Mark.Langsdorf@amd.com
Reported-by: Tobias Diedrich <ranma+xen@tdiedrich.de>
Tested-by: Tobias Diedrich <ranma+xen@tdiedrich.de>
[v1: Rebased on v3.0-rc2, reduced patch to deal with vid case]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Dave Jones <davej@redhat.com>
If the driver submitted an non-existing pol>cur value (say it
used the default initialized value of zero), when the cpufreq
stats tries to setup its initial values it incorrectly sets
stat->last_index to -1 (or 0xfffff...). And cpufreq_stats_update
tries to update at that index location and fails.
This can be caused by:
stat->last_index = freq_table_get_index(stat, policy->cur);
not finding the appropiate frequency in the table (b/c the policy->cur
is wrong) and we end up crashing. The fix however is
concentrated in the 'cpufreq_stats_update' as the last_index
(and old_index) are updated there. Which means it can reset
the last_index to -1 again and on the next iteration cause a crash.
Without this patch, the following crash is observed:
powernow-k8: Found 1 AMD Athlon(tm) 64 Processor 3700+ (1 cpu cores) (version 2.20.00)
powernow-k8: fid 0x2 (1000 MHz), vid 0x12
powernow-k8: fid 0xa (1800 MHz), vid 0xa
powernow-k8: fid 0xc (2000 MHz), vid 0x8
powernow-k8: fid 0xe (2200 MHz), vid 0x8
Marking TSC unstable due to cpufreq changes
powernow-k8: fid trans failed, fid 0x2, curr 0x0
BUG: unable to handle kernel paging request at ffff880807e07b78
IP: [<ffffffff81479163>] cpufreq_stats_update+0x46/0x5b
.. snip..
Pid: 1, comm: swapper Not tainted 3.0.0-rc2 #45 MICRO-STAR INTERNATIONAL CO., LTD MS-7094/MS-7094
..snip..
Call Trace:
[<ffffffff81479248>] cpufreq_stat_notifier_trans+0x48/0x7c
[<ffffffff81095d68>] notifier_call_chain+0x32/0x5e
[<ffffffff81095e6b>] __srcu_notifier_call_chain+0x47/0x63
[<ffffffff81095e96>] srcu_notifier_call_chain+0xf/0x11
[<ffffffff81477e7a>] cpufreq_notify_transition+0x111/0x134
[<ffffffff8147b0d4>] powernowk8_target+0x53b/0x617
[<ffffffff8147723a>] __cpufreq_driver_target+0x2e/0x30
[<ffffffff8147a127>] cpufreq_governor_dbs+0x339/0x356
[<ffffffff81477394>] __cpufreq_governor+0xa8/0xe9
[<ffffffff81477525>] __cpufreq_set_policy+0x132/0x13e
[<ffffffff8147848d>] cpufreq_add_dev_interface+0x272/0x28c
Reported-by: Tobias Diedrich <ranma+xen@tdiedrich.de>
Tested-by: Tobias Diedrich <ranma+xen@tdiedrich.de>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Dave Jones <davej@redhat.com>
Fixed remaining issues of the signedness bug discovered by Dan Carpenter.
A check was remaining that tests if unsigned rt->rate is >= 0.
Changed that so that rt->rate now consistently uses ARRAY_SIZE(rates)
as invalid rate value and not -1.
Signed-off-by: Torsten Schenk <torsten.schenk@zoho.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The earlier attempts (24bdb0b62c)
at fixing this problem caused other problems to surface (PV guests
with no PCI passthrough would have SWIOTLB turned on - which meant
64MB of precious contingous DMA32 memory being eaten up per guest).
The problem was: "on xen we add an extra memory region at the end of
the e820, and on this particular machine this extra memory region
would start below 4g and cross over the 4g boundary:
[0xfee01000-0x192655000)
Unfortunately e820_end_of_low_ram_pfn does not expect an
e820 layout like that so it returns 4g, therefore initial_memory_mapping
will map [0 - 0x100000000), that is a memory range that includes some
reserved memory regions."
The memory range was the IOAPIC regions, and with the 1-1 mapping
turned on, it would map them as RAM, not as MMIO regions. This caused
the hypervisor to complain. Fortunately this is experienced only under
the initial domain so we guard for it.
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
The clocksource watchdog code is interruptible and it has been
observed that this can trigger false positives which disable the TSC.
The reason is that an interrupt storm or a long running interrupt
handler between the read of the watchdog source and the read of the
TSC brings the two far enough apart that the delta is larger than the
unstable treshold. Move both reads into a short interrupt disabled
region to avoid that.
Reported-and-tested-by: Vernon Mauery <vernux@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
* 'rc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6:
kbuild: Call depmod.sh via shell
perf: clear out make flags when calling kernel make kernelver
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
AFS: Use i_generation not i_version for the vnode uniquifier
AFS: Set s_id in the superblock to the volume name
vfs: Fix data corruption after failed write in __block_write_begin()
afs: afs_fill_page reads too much, or wrong data
VFS: Fix vfsmount overput on simultaneous automount
fix wrong iput on d_inode introduced by e6bc45d65d
Delay struct net freeing while there's a sysfs instance refering to it
afs: fix sget() races, close leak on umount
ubifs: fix sget races
ubifs: split allocation of ubifs_info into a separate function
fix leak in proc_set_super()
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6:
SELinux: skip file_name_trans_write() when policy downgraded.
selinux: fix case of names with whitespace/multibytes on /selinux/create
There's no reason not to support cache flushing on external log devices.
The only thing this really requires is flushing the data device first
both in fsync and log commits. A side effect is that we also have to
remove the barrier write test during mount, which has been superflous
since the new FLUSH+FUA code anyway. Also use the chance to flush the
RT subvolume write cache before the fsync commit, which is required
for correct semantics.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
Store the AFS vnode uniquifier in the i_generation field, not the i_version
field of the inode struct. i_version can then be given the AFS data version
number.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Set s_id in the superblock to the name of the AFS volume that this superblock
corresponds to.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
I've got a report of a file corruption from fsxlinux on ext3. The important
operations to the page were:
mapwrite to a hole
partial write to the page
read - found the page zeroed from the end of the normal write
The culprit seems to be that if get_block() fails in __block_write_begin()
(e.g. transient ENOSPC in ext3), the function does ClearPageUptodate(page).
Thus when we retry the write, the logic in __block_write_begin() thinks zeroing
of the page is needed and overwrites old data. In fact, I don't see why we
should ever need to zero the uptodate bit here - either the page was uptodate
when we entered __block_write_begin() and it should stay so when we leave it,
or it was not uptodate and noone had right to set it uptodate during
__block_write_begin() so it remains !uptodate when we leave as well. So just
remove clearing of the bit.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
afs_fill_page should read the page that is about to be written but
the current implementation has a number of issues. If we aren't
extending the file we always read PAGE_CACHE_SIZE at offset 0. If we
are extending the file we try to read the entire file.
Change afs_fill_page to read PAGE_CACHE_SIZE at the right offset,
clamped to i_size.
While here, avoid calling afs_fill_page when we are doing a
PAGE_CACHE_SIZE write.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Avoid double seq adjustment for loopback traffic
because it causes silent repetition of TCP data. One
example is passive FTP with DNAT rule and difference in the
length of IP addresses.
This patch adds check if packet is sent and
received via loopback device. As the same conntrack is
used both for outgoing and incoming direction, we restrict
seq adjustment to happen only in POSTROUTING.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Fix build by moving enum list outside of
#ifdef CONFIG_IIO_RING_BUFFER.
drivers/staging/iio/accel/adis16201_core.c:413: error: 'ADIS16201_SCAN_SUPPLY' undeclared here (not in a function)
drivers/staging/iio/accel/adis16201_core.c:417: error: 'ADIS16201_SCAN_TEMP' undeclared here (not in a function)
..
drivers/staging/iio/accel/adis16203_core.c:374: error: 'ADIS16203_SCAN_SUPPLY' undeclared here (not in a function)
drivers/staging/iio/accel/adis16203_core.c:378: error: 'ADIS16203_SCAN_AUX_ADC' undeclared here (not in a function)
..
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Acked-by: Jonathan Cameron <jic23@cam.ac.uk>
Cc: linux-iio@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[Kudos to dhowells for tracking that crap down]
If two processes attempt to cause automounting on the same mountpoint at the
same time, the vfsmount holding the mountpoint will be left with one too few
references on it, causing a BUG when the kernel tries to clean up.
The problem is that lock_mount() drops the caller's reference to the
mountpoint's vfsmount in the case where it finds something already mounted on
the mountpoint as it transits to the mounted filesystem and replaces path->mnt
with the new mountpoint vfsmount.
During a pathwalk, however, we don't take a reference on the vfsmount if it is
the same as the one in the nameidata struct, but do_add_mount() doesn't know
this.
The fix is to make sure we have a ref on the vfsmount of the mountpoint before
calling do_add_mount(). However, if lock_mount() doesn't transit, we're then
left with an extra ref on the mountpoint vfsmount which needs releasing.
We can handle that in follow_managed() by not making assumptions about what
we can and what we cannot get from lookup_mnt() as the current code does.
The callers of follow_managed() expect that reference to path->mnt will be
grabbed iff path->mnt has been changed. follow_managed() and follow_automount()
keep track of whether such reference has been grabbed and assume that it'll
happen in those and only those cases that'll have us return with changed
path->mnt. That assumption is almost correct - it breaks in case of
racing automounts and in even harder to hit race between following a mountpoint
and a couple of mount --move. The thing is, we don't need to make that
assumption at all - after the end of loop in follow_manage() we can check
if path->mnt has ended up unchanged and do mntput() if needed.
The BUG can be reproduced with the following test program:
#include <stdio.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <sys/wait.h>
int main(int argc, char **argv)
{
int pid, ws;
struct stat buf;
pid = fork();
stat(argv[1], &buf);
if (pid > 0) wait(&ws);
return 0;
}
and the following procedure:
(1) Mount an NFS volume that on the server has something else mounted on a
subdirectory. For instance, I can mount / from my server:
mount warthog:/ /mnt -t nfs4 -r
On the server /data has another filesystem mounted on it, so NFS will see
a change in FSID as it walks down the path, and will mark /mnt/data as
being a mountpoint. This will cause the automount code to be triggered.
!!! Do not look inside the mounted fs at this point !!!
(2) Run the above program on a file within the submount to generate two
simultaneous automount requests:
/tmp/forkstat /mnt/data/testfile
(3) Unmount the automounted submount:
umount /mnt/data
(4) Unmount the original mount:
umount /mnt
At this point the kernel should throw a BUG with something like the
following:
BUG: Dentry ffff880032e3c5c0{i=2,n=} still in use (1) [unmount of nfs4 0:12]
Note that the bug appears on the root dentry of the original mount, not the
mountpoint and not the submount because sys_umount() hasn't got to its final
mntput_no_expire() yet, but this isn't so obvious from the call trace:
[<ffffffff8117cd82>] shrink_dcache_for_umount+0x69/0x82
[<ffffffff8116160e>] generic_shutdown_super+0x37/0x15b
[<ffffffffa00fae56>] ? nfs_super_return_all_delegations+0x2e/0x1b1 [nfs]
[<ffffffff811617f3>] kill_anon_super+0x1d/0x7e
[<ffffffffa00d0be1>] nfs4_kill_super+0x60/0xb6 [nfs]
[<ffffffff81161c17>] deactivate_locked_super+0x34/0x83
[<ffffffff811629ff>] deactivate_super+0x6f/0x7b
[<ffffffff81186261>] mntput_no_expire+0x18d/0x199
[<ffffffff811862a8>] mntput+0x3b/0x44
[<ffffffff81186d87>] release_mounts+0xa2/0xbf
[<ffffffff811876af>] sys_umount+0x47a/0x4ba
[<ffffffff8109e1ca>] ? trace_hardirqs_on_caller+0x1fd/0x22f
[<ffffffff816ea86b>] system_call_fastpath+0x16/0x1b
as do_umount() is inlined. However, you can see release_mounts() in there.
Note also that it may be necessary to have multiple CPU cores to be able to
trigger this bug.
Tested-by: Jeff Layton <jlayton@redhat.com>
Tested-by: Ian Kent <raven@themaw.net>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Clemens Ladisch