wait_task_zombie() first does EXIT_ZOMBIE->EXIT_DEAD transition and
drops tasklist_lock. If this task is not the natural child and it is
traced, we change its state back to EXIT_ZOMBIE for ->real_parent.
The last transition is racy, this is even documented in 50b8d257486a
"ptrace: partially fix the do_wait(WEXITED) vs EXIT_DEAD->EXIT_ZOMBIE
race". wait_consider_task() tries to detect this transition and clear
->notask_error but we can't rely on ptrace_reparented(), debugger can
exit and do ptrace_unlink() before its sub-thread sets EXIT_ZOMBIE.
And there is another problem which were missed before: this transition
can also race with reparent_leader() which doesn't reset >exit_signal if
EXIT_DEAD, assuming that this task must be reaped by someone else. So
the tracee can be re-parented with ->exit_signal != SIGCHLD, and if
/sbin/init doesn't use __WALL it becomes unreapable.
Change reparent_leader() to update ->exit_signal even if EXIT_DEAD.
Note: this is the simple temporary hack for -stable, it doesn't try to
solve all problems, it will be reverted by the next changes.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reported-by: Jan Kratochvil <jan.kratochvil@redhat.com> Reported-by: Michal Schmidt <mschmidt@redhat.com> Tested-by: Michal Schmidt <mschmidt@redhat.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Lennart Poettering <lpoetter@redhat.com> Cc: Roland McGrath <roland@hack.frob.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The variable csize in structure jffs2_tmp_dnode_info is of type uint16_t, but it
is used to hold the compressed data length(csize) which is declared as uint32_t.
So, when the value of csize exceeds 16bits, it gets truncated when assigned to
tn->csize. This is causing a kernel BUG.
Changing the definition of csize in jffs2_tmp_dnode_info to uint32_t fixes the issue.
This crash is caused because the 'positions' is declared as an array of signed
short. The value of position is in the range 0..65535, and will be converted
to a negative number when the position is greater than 32767 and causes a
corruption and crash. Changing the definition to 'unsigned short' fixes this
issue
Signed-off-by: Jayachandran C <jchandra@broadcom.com> Signed-off-by: Kamlakant Patel <kamlakant.patel@broadcom.com> Signed-off-by: Brian Norris <computersforpeace@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Xfstests generic/311 and shared/298 fail when run on a bigalloc file
system. Kernel error messages produced during the tests report that
blocks to be freed are already on the to-be-freed list. When e2fsck
is run at the end of the tests, it typically reports bad i_blocks and
bad free blocks counts.
The bug that causes these failures is located in ext4_ext_rm_leaf().
Code at the end of the function frees a partial cluster if it's not
shared with an extent remaining in the leaf. However, if all the
extents in the leaf have been removed, the code dereferences an
invalid extent pointer (off the front of the leaf) when the check for
sharing is made. This generally has the effect of unconditionally
freeing the partial cluster, which leads to the observed failures
when the partial cluster is shared with the last extent in the next
leaf.
Fix this by attempting to free the cluster only if extents remain in
the leaf. Any remaining partial cluster will be freed if possible
when the next leaf is processed or when leaf removal is complete.
Commit 9cb00419fa, which enables hole punching for bigalloc file
systems, exposed a bug introduced by commit 6ae06ff51e in an earlier
release. When run on a bigalloc file system, xfstests generic/013, 068,
075, 083, 091, 100, 112, 127, 263, 269, and 270 fail with e2fsck errors
or cause kernel error messages indicating that previously freed blocks
are being freed again.
The latter commit optimizes the selection of the starting extent in
ext4_ext_rm_leaf() when hole punching by beginning with the extent
supplied in the path argument rather than with the last extent in the
leaf node (as is still done when truncating). However, the code in
rm_leaf that initially sets partial_cluster to track cluster sharing on
extent boundaries is only guaranteed to run if rm_leaf starts with the
last node in the leaf. Consequently, partial_cluster is not correctly
initialized when hole punching, and a cluster on the boundary of a
punched region that should be retained may instead be deallocated.
Commit 3779473246 breaks the return of error codes from
ext4_ext_handle_uninitialized_extents() in ext4_ext_map_blocks(). A
portion of the patch assigns that function's signed integer return
value to an unsigned int. Consequently, negatively valued error codes
are lost and can be treated as a bogus allocated block count.
We could have possibly added an extent_op to the locked_ref while we dropped
locked_ref->lock, so check for this case as well and loop around. Otherwise we
could lose flag updates which would lead to extent tree corruption. Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Chris Mason <clm@fb.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Zach found this deadlock that would happen like this
btrfs_end_transaction <- reduce trans->use_count to 0
btrfs_run_delayed_refs
btrfs_cow_block
find_free_extent
btrfs_start_transaction <- increase trans->use_count to 1
allocate chunk
btrfs_end_transaction <- decrease trans->use_count to 0
btrfs_run_delayed_refs
lock tree block we are cowing above ^^
We need to only decrease trans->use_count if it is above 1, otherwise leave it
alone. This will make nested trans be the only ones who decrease their added
ref, and will let us get rid of the trans->use_count++ hack if we have to commit
the transaction. Thanks,
Reported-by: Zach Brown <zab@redhat.com> Signed-off-by: Josef Bacik <jbacik@fb.com> Tested-by: Zach Brown <zab@redhat.com> Signed-off-by: Chris Mason <clm@fb.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
I got an error on v3.13:
BTRFS error (device sdf1) in write_all_supers:3378: errno=-5 IO failure (errors while submitting device barriers.)
how to reproduce:
> mkfs.btrfs -f -d raid1 /dev/sdf1 /dev/sdf2
> wipefs -a /dev/sdf2
> mount -o degraded /dev/sdf1 /mnt
> btrfs balance start -f -sconvert=single -mconvert=single -dconvert=single /mnt
The reason of the error is that barrier_all_devices() failed to submit
barrier to the missing device. However it is clear that we cannot do
anything on missing device, and also it is not necessary to care chunks
on the missing device.
This patch stops sending/waiting barrier if device is missing.
Commit f5ea1100 ("xfs: add CRCs to dir2/da node blocks") introduced
in 3.10 incorrectly converted the btree hash index array pointer in
xfs_da3_fixhashpath(). It resulted in the the current hash always
being compared against the first entry in the btree rather than the
current block index into the btree block's hash entry array. As a
result, it was comparing the wrong hashes, and so could misorder the
entries in the btree.
For most cases, this doesn't cause any problems as it requires hash
collisions to expose the ordering problem. However, when there are
hash collisions within a directory there is a very good probability
that the entries will be ordered incorrectly and that actually
matters when duplicate hashes are placed into or removed from the
btree block hash entry array.
This bug results in an on-disk directory corruption and that results
in directory verifier functions throwing corruption warnings into
the logs. While no data or directory entries are lost, access to
them may be compromised, and attempts to remove entries from a
directory that has suffered from this corruption may result in a
filesystem shutdown. xfs_repair will fix the directory hash
ordering without data loss occuring.
[dchinner: wrote useful a commit message]
Reported-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Mark Tinguely <tinguely@sgi.com> Reviewed-by: Ben Myers <bpm@sgi.com> Signed-off-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
After commit 839a8e8660b6 ("writeback: replace custom worker pool
implementation with unbound workqueue") when device is removed while we
are writing to it we crash in bdi_writeback_workfn() ->
set_worker_desc() because bdi->dev is NULL.
This can happen because even though bdi_unregister() cancels all pending
flushing work, nothing really prevents new ones from being queued from
balance_dirty_pages() or other places.
Fix the problem by clearing BDI_registered bit in bdi_unregister() and
checking it before scheduling of any flushing work.
Fixes: 839a8e8660b6777e7fe4e80af1a048aebe2b5977 Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jan Kara <jack@suse.cz> Cc: Derek Basehore <dbasehore@chromium.org> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
bdi_wakeup_thread_delayed() used the mod_delayed_work() function to
schedule work to writeback dirty inodes. The problem with this is that
it can delay work that is scheduled for immediate execution, such as the
work from sync_inodes_sb(). This can happen since mod_delayed_work()
can now steal work from a work_queue. This fixes the problem by using
queue_delayed_work() instead. This is a regression caused by commit 839a8e8660b6 ("writeback: replace custom worker pool implementation with
unbound workqueue").
The reason that this causes a problem is that laptop-mode will change
the delay, dirty_writeback_centisecs, to 60000 (10 minutes) by default.
In the case that bdi_wakeup_thread_delayed() races with
sync_inodes_sb(), sync will be stopped for 10 minutes and trigger a hung
task. Even if dirty_writeback_centisecs is not long enough to cause a
hung task, we still don't want to delay sync for that long.
We fix the problem by using queue_delayed_work() when we want to
schedule writeback sometime in future. This function doesn't change the
timer if it is already armed.
For the same reason, we also change bdi_writeback_workfn() to
immediately queue the work again in the case that the work_list is not
empty. The same problem can happen if the sync work is run on the
rescue worker.
[jack@suse.cz: update changelog, add comment, use bdi_wakeup_thread_delayed()] Signed-off-by: Derek Basehore <dbasehore@chromium.org> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Alexander Viro <viro@zento.linux.org.uk> Reviewed-by: Tejun Heo <tj@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Derek Basehore <dbasehore@chromium.org> Cc: Kees Cook <keescook@chromium.org> Cc: Benson Leung <bleung@chromium.org> Cc: Sonny Rao <sonnyrao@chromium.org> Cc: Luigi Semenzato <semenzato@chromium.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
With the new template mechanism introduced in IMA since kernel 3.13,
the format of data sent through the binary_runtime_measurements interface
is slightly changed. Now, for a generic measurement, the format of
template data (after the template name) is:
In addition, fields containing a string now include the '\0' termination
character.
Instead, the format for the 'ima' template should be:
SHA1 digest | event name length | event name
It must be noted that while in the IMA 3.13 code 'event name length' is
'IMA_EVENT_NAME_LEN_MAX + 1' (256 bytes), so that the template digest
is calculated correctly, and 'event name' contains '\0', in the pre 3.13
code 'event name length' is exactly the string length and 'event name'
does not contain the termination character.
The patch restores the behavior of the IMA code pre 3.13 for the 'ima'
template so that legacy userspace tools obtain a consistent behavior
when receiving data from the binary_runtime_measurements interface
regardless of which kernel version is used.
This patch fixes authentication failure on LE link re-connection when
BlueZ acts as slave (peripheral). LTK is removed from the internal list
after its first use causing PIN or Key missing reply when re-connecting
the link. The LE Long Term Key Request event indicates that the master
is attempting to encrypt or re-encrypt the link.
Pre-condition: BlueZ host paired and running as slave.
How to reproduce(master):
1) Establish an ACL LE encrypted link
2) Disconnect the link
3) Try to re-establish the ACL LE encrypted link (fails)
> HCI Event: LE Meta Event (0x3e) plen 19
LE Connection Complete (0x01)
Status: Success (0x00)
Handle: 64
Role: Slave (0x01)
...
@ Device Connected: 00:02:72:DC:29:C9 (1) flags 0x0000
> HCI Event: LE Meta Event (0x3e) plen 13
LE Long Term Key Request (0x05)
Handle: 64
Random number: 875be18439d9aa37
Encryption diversifier: 0x76ed
< HCI Command: LE Long Term Key Request Reply (0x08|0x001a) plen 18
Handle: 64
Long term key: 2aa531db2fce9f00a0569c7d23d17409
> HCI Event: Command Complete (0x0e) plen 6
LE Long Term Key Request Reply (0x08|0x001a) ncmd 1
Status: Success (0x00)
Handle: 64
> HCI Event: Encryption Change (0x08) plen 4
Status: Success (0x00)
Handle: 64
Encryption: Enabled with AES-CCM (0x01)
...
@ Device Disconnected: 00:02:72:DC:29:C9 (1) reason 3
< HCI Command: LE Set Advertise Enable (0x08|0x000a) plen 1
Advertising: Enabled (0x01)
> HCI Event: Command Complete (0x0e) plen 4
LE Set Advertise Enable (0x08|0x000a) ncmd 1
Status: Success (0x00)
> HCI Event: LE Meta Event (0x3e) plen 19
LE Connection Complete (0x01)
Status: Success (0x00)
Handle: 64
Role: Slave (0x01)
...
@ Device Connected: 00:02:72:DC:29:C9 (1) flags 0x0000
> HCI Event: LE Meta Event (0x3e) plen 13
LE Long Term Key Request (0x05)
Handle: 64
Random number: 875be18439d9aa37
Encryption diversifier: 0x76ed
< HCI Command: LE Long Term Key Request Neg Reply (0x08|0x001b) plen 2
Handle: 64
> HCI Event: Command Complete (0x0e) plen 6
LE Long Term Key Request Neg Reply (0x08|0x001b) ncmd 1
Status: Success (0x00)
Handle: 64
> HCI Event: Disconnect Complete (0x05) plen 4
Status: Success (0x00)
Handle: 64
Reason: Authentication Failure (0x05)
@ Device Disconnected: 00:02:72:DC:29:C9 (1) reason 0
pidns_get()->get_pid_ns() can hit ns == NULL. This task_struct can't
go away, but task_active_pid_ns(task) is NULL if release_task(task)
was already called. Alternatively we could change get_pid_ns(ns) to
check ns != NULL, but it seems that other callers are fine.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Eric W. Biederman ebiederm@xmission.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The fact that we can't tell them to drain their caches shouldn't
prevent the system from going into suspend. Therefore sd_sync_cache()
shouldn't return an error if the device replies with an Invalid
Command ASC.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Reported-by: Sven Neumann <s.neumann@raumfeld.com> Tested-by: Daniel Mack <zonque@gmail.com> Signed-off-by: James Bottomley <JBottomley@Parallels.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The user-settable knob, low_latency, has been the source of
several BUG reports which stem from flush_to_ldisc() running
in interrupt context. Since 3.12, which added several sleeping
locks (termios_rwsem and buf->lock) to the input processing path,
the frequency of these BUG reports has increased.
Note that changes in 3.12 did not introduce this regression;
sleeping locks were first added to the input processing path
with the removal of the BKL from N_TTY in commit a88a69c91256418c5907c2f1f8a0ec0a36f9e6cc,
'n_tty: Fix loss of echoed characters and remove bkl from n_tty'
and later in commit 38db89799bdf11625a831c5af33938dcb11908b6,
'tty: throttling race fix'. Since those changes, executing
flush_to_ldisc() in interrupt_context (ie, low_latency set), is unsafe.
However, since most devices do not validate if the low_latency
setting is appropriate for the context (process or interrupt) in
which they receive data, some reports are due to misconfiguration.
Further, serial dma devices for which dma fails, resort to
interrupt receiving as a backup without resetting low_latency.
Historically, low_latency was used to force wake-up the reading
process rather than wait for the next scheduler tick. The
effect was to trim multiple milliseconds of latency from
when the process would receive new data.
Recent tests [1] have shown that the reading process now receives
data with only 10's of microseconds latency without low_latency set.
Remove the low_latency rx steering from tty_flip_buffer_push();
however, leave the knob as an optional hint to drivers that can
tune their rx fifos and such like. Cleanup stale code comments
regarding low_latency.
[1] https://lkml.org/lkml/2014/2/20/434
"Yay.. thats an annoying historical pain in the butt gone."
-- Alan Cox
Reported-by: Beat Bolli <bbolli@ewanet.ch> Reported-by: Pavel Roskin <proski@gnu.org> Acked-by: David Sterba <dsterba@suse.cz> Cc: Grant Edwards <grant.b.edwards@gmail.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Hal Murray <murray+fedora@ip-64-139-1-69.sjc.megapath.net> Signed-off-by: Peter Hurley <peter@hurleysoftware.com> Signed-off-by: Alan Cox <alan@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The 'active' sysfs attribute should refer to the currently active tty
devices the console is running on, not the currently active console. The
console structure doesn't refer to any device in sysfs, only the tty the
console is running on has. So we need to print out the tty names in
'active', not the console names.
There is one special-case, which is tty0. If the console is directed to
it, we want 'tty0' to show up in the file, so user-space knows that the
messages get forwarded to the active VT. The ->device() callback would
resolve tty0, though. Hence, treat it special and don't call into the VT
layer to resolve it (plymouth is known to depend on it).
Cc: Lennart Poettering <lennart@poettering.net> Cc: Kay Sievers <kay@vrfy.org> Cc: Jiri Slaby <jslaby@suse.cz> Signed-off-by: Werner Fink <werner@suse.de> Signed-off-by: Hannes Reinecke <hare@suse.de> Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
kernfs_iattrs is allocated lazily when operations which require it
take place; unfortunately, the lazy allocation and returning weren't
properly synchronized and when there are multiple concurrent
operations, it might end up returning kernfs_iattrs which hasn't
finished initialization yet or different copies to different callers.
Fix it by synchronizing with a mutex. This can be smarter with memory
barriers but let's go there if it actually turns out to be necessary.
The hash values 0 and 1 are reserved for magic directory entries, but
the code only prevents names hashing to 0. This patch fixes the test
to also prevent hash value 1.
Signed-off-by: Richard Cochran <richardcochran@gmail.com> Reviewed-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To avoid the circular dependency, just try to get the lock in
`comedi_mmap()` instead of blocking. Since the comedi device's main mutex
is heavily used, do a down-read of its `attach_lock` rwsemaphore
instead. Trying to down-read `attach_lock` should only fail if
some task has down-write locked it, and that is only done while the
comedi device is being attached to or detached from a low-level hardware
device.
Unfortunately, acquiring the `attach_lock` doesn't prevent another
task replacing the comedi data buffer we are trying to mmap. The
details of the buffer are held in a `struct comedi_buf_map` and pointed
to by `s->async->buf_map` where `s` is the comedi subdevice whose buffer
we are trying to map. The `struct comedi_buf_map` is already reference
counted with a `struct kref`, so we can stop it being freed prematurely.
Modify `comedi_mmap()` to call new function
`comedi_buf_map_from_subdev_get()` to read the subdevice's current
buffer map pointer and increment its reference instead of accessing
`async->buf_map` directly. Call `comedi_buf_map_put()` to decrement the
reference once the buffer map structure has been dealt with. (Note that
`comedi_buf_map_put()` does nothing if passed a NULL pointer.)
`comedi_buf_map_from_subdev_get()` checks the subdevice's buffer map
pointer has been set and the buffer map has been initialized enough for
`comedi_mmap()` to deal with it (specifically, check the `n_pages`
member has been set to a non-zero value). If all is well, the buffer
map's reference is incremented and a pointer to it is returned. The
comedi subdevice's spin-lock is used to protect the checks. Also use
the spin-lock in `__comedi_buf_alloc()` and `__comedi_buf_free()` to
protect changes to the subdevice's buffer map structure pointer and the
buffer map structure's `n_pages` member. (This checking of `n_pages` is
a bit clunky and I [Ian Abbott] plan to deal with it in the future.)
Signed-off-by: Ian Abbott <abbotti@mev.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
According to National Instruments' PCI-DIO-96/PXI-6508/PCI-6503 User
Manual, the physical address in PCI BAR1 needs to be OR'ed with 0x80 and
written to register offset 0xC0 in the "MITE" registers (BAR0). Do so
during initialization of the National Instruments boards handled by the
"8255_pci" driver. The boards were previously handled by the
"ni_pcidio" driver, where the initialization was done by `mite_setup()`
in the "mite" module. The "mite" module comes with too much extra
baggage for the "8255_pci" driver to deal with so use a local, simpler
initialization function.
Signed-off-by: Ian Abbott <abbotti@mev.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Commit 1696d9d (ACPI: Remove the old /proc/acpi/event interface)
removed ACPI Button event which originally was sent to userspace via
/proc/acpi/event. This caused ACPI shutdown regression on gentoo
in VirtualBox. Now ACPI events are sent to userspace via netlink,
so add ACPI Button event back via netlink routine.
References: https://bugzilla.kernel.org/show_bug.cgi?id=71721 Reported-and-tested-by: Richard Musil <richard.musil@gmail.com> Signed-off-by: Lan Tianyu <tianyu.lan@intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Commit 03bbcb2e7e2 (iommu/vt-d: add quirk for broken interrupt
remapping on 55XX chipsets) properly disables irq remapping on the
5500/5520 chipsets that don't correctly perform that feature.
However, when I wrote it, I followed the errata sheet linked in that
commit too closely, and explicitly tied the activation of the quirk to
revision 0x13 of the chip, under the assumption that earlier revisions
were not in the field. Recently a system was reported to be suffering
from this remap bug and the quirk hadn't triggered, because the
revision id register read at a lower value that 0x13, so the quirk
test failed improperly. Given this, it seems only prudent to adjust
this quirk so that any revision less than 0x13 has the quirk asserted.
[ tglx: Removed the 0x12 comparison of pci id 3405 as this is covered
by the <= 0x13 check already ]
Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Link: http://lkml.kernel.org/r/1394649873-14913-1-git-send-email-nhorman@tuxdriver.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch bypass the timer_irq_works() check for hyperv guest since:
- It was guaranteed to work.
- timer_irq_works() may fail sometime due to the lpj calibration were inaccurate
in a hyperv guest or a buggy host.
In the future, we should get the tsc frequency from hypervisor and use preset
lpj instead.
[ hpa: I would prefer to not defer things to "the future" in the future... ]
Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Acked-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Jason Wang <jasowang@redhat.com> Link: http://lkml.kernel.org/r/1393558229-14755-1-git-send-email-jasowang@redhat.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
unsigned char i;
...
bt->read_data[0] = BMC2HOST;
bt->read_count = bt->read_data[0];
...
for (i = 1; i <= bt->read_count; i++)
bt->read_data[i] = BMC2HOST;
If bt->read_data[0] == bt->read_count == 255, we loop infinitely in the
'for' loop. Make 'i' an 'int' instead of 'char' to get rid of the
overflow and finish the loop after 255 iterations every time.
smp_read_barrier_depends() can be used if there is data dependency between
the readers - i.e. if the read operation after the barrier uses address
that was obtained from the read operation before the barrier.
In this file, there is only control dependency, no data dependecy, so the
use of smp_read_barrier_depends() is incorrect. The code could fail in the
following way:
* the cpu predicts that idx < entries is true and starts executing the
body of the for loop
* the cpu fetches map->extent[0].first and map->extent[0].count
* the cpu fetches map->nr_extents
* the cpu verifies that idx < extents is true, so it commits the
instructions in the body of the for loop
The problem is that in this scenario, the cpu read map->extent[0].first
and map->nr_extents in the wrong order. We need a full read memory barrier
to prevent it.
The GHASH setkey() function uses SSE registers but fails to call
kernel_fpu_begin()/kernel_fpu_end(). Instead of adding these calls, and
then having to deal with the restriction that they cannot be called from
interrupt context, move the setkey() implementation to the C domain.
Note that setkey() does not use any particular SSE features and is not
expected to become a performance bottleneck.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Fixes: 0e1227d356e9b (crypto: ghash - Add PCLMULQDQ accelerated implementation) Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If an architecture has futex_atomic_cmpxchg_inatomic() implemented and there
is no runtime check necessary, allow to skip the test within futex_init().
This allows to get rid of some code which would always give the same result,
and also allows the compiler to optimize a couple of if statements away.
The Synopsys APB DW UART has a couple of special features that are not
in the System C model. In 3.8, the 8250_dw driver didn't really use these
features, but from 3.9 onwards, the 8250_dw driver has become incompatible
with our model.
We should explore all possible columns when searching to be
as resilient as possible to changing conditions. This fixes
for example a scenario where even after a sudden creation of
rssi difference between the 2 antennas we would keep doing MIMO
at a low rate instead of switching to SISO at a higher rate using
the better antenna which was the optimal configuration.
The at91_ether driver calls macb_mii_init passing a 'struct macb'
structure whose tx_clk member is initialized to 0. However,
macb_handle_link_change() expects tx_clk to be the result of
a call to clk_get, and so IS_ERR(tx_clk) to be true if the clock
is invalid. This causes an oops when booting Linux 3.14 on the
csb637 board. The following changes avoids this.
Signed-off-by: Gilles Chanteperdrix <gilles.chanteperdrix@xenomai.org> Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Binding might result in a NULL device which is later dereferenced
without checking.
Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There are three buffer overflows addressed in this patch.
1) In isdnloop_fake_err() we add an 'E' to a 60 character string and
then copy it into a 60 character buffer. I have made the destination
buffer 64 characters and I'm changed the sprintf() to a snprintf().
2) In isdnloop_parse_cmd(), p points to a 6 characters into a 60
character buffer so we have 54 characters. The ->eazlist[] is 11
characters long. I have modified the code to return if the source
buffer is too long.
3) In isdnloop_command() the cbuf[] array was 60 characters long but the
max length of the string then can be up to 79 characters. I made the
cbuf array 80 characters long and changed the sprintf() to snprintf().
I also removed the temporary "dial" buffer and changed it to use "p"
directly.
Unfortunately, we pass the "cbuf" string from isdnloop_command() to
isdnloop_writecmd() which truncates anything over 60 characters to make
it fit in card->omsg[]. (It can accept values up to 255 characters so
long as there is a '\n' character every 60 characters). For now I have
just fixed the memory corruption bug and left the other problems in this
driver alone.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Return -EINVAL unless all of user-given strings are correctly
NUL-terminated.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If the vxlan interface is created without explicit group definition,
there are corner cases which may cause kernel panic.
For instance, in the following scenario:
node A:
$ ip link add dev vxlan42 address 2c:c2:60:00:10:20 type vxlan id 42
$ ip addr add dev vxlan42 10.0.0.1/24
$ ip link set up dev vxlan42
$ arp -i vxlan42 -s 10.0.0.2 2c:c2:60:00:01:02
$ bridge fdb add dev vxlan42 to 2c:c2:60:00:01:02 dst <IPv4 address>
$ ping 10.0.0.2
node B:
$ ip link add dev vxlan42 address 2c:c2:60:00:01:02 type vxlan id 42
$ ip addr add dev vxlan42 10.0.0.2/24
$ ip link set up dev vxlan42
$ arp -i vxlan42 -s 10.0.0.1 2c:c2:60:00:10:20
When vxlan interface is created without explicit group definition, the
default_dst protocol family is initialiazed to AF_UNSPEC and the driver
assumes IPv4 configuration. On the other side, the default_dst protocol
family is used to differentiate between IPv4 and IPv6 cases and, since,
AF_UNSPEC != AF_INET, the processing takes the IPv6 path.
Making the IPv4 assumption explicit by settting default_dst protocol
family to AF_INET4 and preventing mixing of IPv4 and IPv6 addresses in
snooped fdb entries fixes the corner case crashes.
Signed-off-by: Mike Rapoport <mike.rapoport@ravellosystems.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When using the "separate_tx_channels=1" module parameter, the TX queues are
initially numbered starting from the first TX-only channel number (after all the
RX-only channels). efx_set_channels() renumbers the queues so that they are
indexed from zero.
On EF10, the TX queues need to be relabelled in this way before calling the
dimension_resources NIC type operation, otherwise the TX queue PIO buffers can be
linked to the wrong VIs when using "separate_tx_channels=1".
Added comments to explain UC/WC mappings for PIO buffers
Signed-off-by: Shradha Shah <sshah@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When netback discovers frontend is sending malformed packet it will
disables the interface which serves that frontend.
However disabling a network interface involving taking a mutex which
cannot be done in softirq context, so we need to defer this process to
kthread context.
This patch does the following:
1. introduce a flag to indicate the interface is disabled.
2. check that flag in TX path, don't do any work if it's true.
3. check that flag in RX path, turn off that interface if it's true.
The reason to disable it in RX path is because RX uses kthread. After
this change the behavior of netback is still consistent -- it won't do
any TX work for a rogue frontend, and the interface will be eventually
turned off.
Also change a "continue" to "break" after xenvif_fatal_tx_err, as it
doesn't make sense to continue processing packets if frontend is rogue.
This is a fix for XSA-90.
Reported-by: Török Edwin <edwin@etorok.net> Signed-off-by: Wei Liu <wei.liu2@citrix.com> Cc: Ian Campbell <ian.campbell@citrix.com> Reviewed-by: David Vrabel <david.vrabel@citrix.com> Acked-by: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
nla_strcmp compares the string length plus one, so it's implicitly
including the nul-termination in the comparison.
int nla_strcmp(const struct nlattr *nla, const char *str)
{
int len = strlen(str) + 1;
...
d = memcmp(nla_data(nla), str, len);
However, if NLA_STRING is used, userspace can send us a string without
the nul-termination. This is a problem since the string
comparison will not match as the last byte may be not the
nul-termination.
Fix this by skipping the comparison of the nul-termination if the
attribute data is nul-terminated. Suggested by Thomas Graf.
Cc: Florian Westphal <fw@strlen.de> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
After commit c15b1ccadb323ea ("ipv6: move DAD and addrconf_verify
processing to workqueue") some counters are now updated in process context
and thus need to disable bh before doing so, otherwise deadlocks can
happen on 32-bit archs. Fabio Estevam noticed this while while mounting
a NFS volume on an ARM board.
As a compensation for missing this I looked after the other *_STATS_BH
and found three other calls which need updating:
1) icmp6_send: ip6_fragment -> icmpv6_send -> icmp6_send (error handling)
2) ip6_push_pending_frames: rawv6_sendmsg -> rawv6_push_pending_frames -> ...
(only in case of icmp protocol with raw sockets in error handling)
3) ping6_v6_sendmsg (error handling)
Fixes: c15b1ccadb323ea ("ipv6: move DAD and addrconf_verify processing to workqueue") Reported-by: Fabio Estevam <festevam@gmail.com> Tested-by: Fabio Estevam <fabio.estevam@freescale.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The BUG_ON to catch ring overflow in xenvif_rx_action() makes the assumption
that meta_slots_used == ring slots used. This is not necessarily the case
for GSO packets, because the non-prefix GSO protocol consumes one more ring
slot than meta-slot for the 'extra_info'. This patch changes the test to
actually check ring slots.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com> Cc: Ian Campbell <ian.campbell@citrix.com> Cc: Wei Liu <wei.liu2@citrix.com> Cc: Sander Eikelenboom <linux@eikelenboom.it> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The worse-case estimate for skb ring slot usage in xenvif_rx_action()
fails to take fragment page_offset into account. The page_offset does,
however, affect the number of times the fragmentation code calls
start_new_rx_buffer() (i.e. consume another slot) and the worse-case
should assume that will always return true. This patch adds the page_offset
into the DIV_ROUND_UP for each frag.
Unfortunately some frontends aggressively limit the number of requests
they post into the shared ring so to avoid an estimate that is 'too'
pessimal it is capped at MAX_SKB_FRAGS.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com> Cc: Ian Campbell <ian.campbell@citrix.com> Cc: Wei Liu <wei.liu2@citrix.com> Cc: Sander Eikelenboom <linux@eikelenboom.it> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch removes a test in start_new_rx_buffer() that checks whether
a copy operation is less than MAX_BUFFER_OFFSET in length, since
MAX_BUFFER_OFFSET is defined to be PAGE_SIZE and the only caller of
start_new_rx_buffer() already limits copy operations to PAGE_SIZE or less.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com> Cc: Ian Campbell <ian.campbell@citrix.com> Cc: Wei Liu <wei.liu2@citrix.com> Cc: Sander Eikelenboom <linux@eikelenboom.it> Reported-By: Sander Eikelenboom <linux@eikelenboom.it> Tested-By: Sander Eikelenboom <linux@eikelenboom.it> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Jan Stancek reported:
"pthread_cond_broadcast/4-1.c testcase from openposix testsuite (LTP)
occasionally fails, because some threads fail to wake up.
Testcase creates 5 threads, which are all waiting on same condition.
Main thread then calls pthread_cond_broadcast() without holding mutex,
which calls:
This immediately wakes up single thread A, which unlocks mutex and
tries to wake up another thread:
futex(uaddr2, FUTEX_WAKE_PRIVATE, 1)
If thread A manages to call futex_wake() before any waiters are
requeued for uaddr2, no other thread is woken up"
The ordering constraints for the hash bucket waiter counting are that
the waiter counts have to be incremented _before_ getting the spinlock
(because the spinlock acts as part of the memory barrier), but the
"requeue" operation didn't honor those rules, and nobody had even
thought about that case.
This fairly simple patch just increments the waiter count for the target
hash bucket (hb2) when requeing a futex before taking the locks. It
then decrements them again after releasing the lock - the code that
actually moves the futex(es) between hash buckets will do the additional
required waiter count housekeeping.
Reported-and-tested-by: Jan Stancek <jstancek@redhat.com> Acked-by: Davidlohr Bueso <davidlohr@hp.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently, running SetVirtualAddressMap() and passing the physical
address of the virtual map array was working only by a lucky coincidence
because the memory was present in the EFI page table too. Until Toshi
went and booted this on a big HP box - the krealloc() manner of resizing
the memmap we're doing did allocate from such physical addresses which
were not mapped anymore and boom:
One way to take care of that issue is to reimplement the krealloc thing
but with pages. We start with contiguous pages of order 1, i.e. 2 pages,
and when we deplete that memory (shouldn't happen all that often but you
know firmware) we realloc the next power-of-two pages.
Having the pages, it is much more handy and easy to map them into the
EFI page table with the already existing mapping code which we're using
for building the virtual mappings.
Thanks to Toshi Kani and Matt for the great debugging help.
This patch is based on an earlier patch by Eric Paris, he describes
the problem below:
"If an inode is accessed before policy load it will get placed on a
list of inodes to be initialized after policy load. After policy
load we call inode_doinit() which calls inode_doinit_with_dentry()
on all inodes accessed before policy load. In the case of inodes
in procfs that means we'll end up at the bottom where it does:
/* Default to the fs superblock SID. */
isec->sid = sbsec->sid;
if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
if (opt_dentry) {
isec->sclass = inode_mode_to_security_class(...)
rc = selinux_proc_get_sid(opt_dentry,
isec->sclass,
&sid);
if (rc)
goto out_unlock;
isec->sid = sid;
}
}
Since opt_dentry is null, we'll never call selinux_proc_get_sid()
and will leave the inode labeled with the label on the superblock.
I believe a fix would be to mimic the behavior of xattrs. Look
for an alias of the inode. If it can't be found, just leave the
inode uninitialized (and pick it up later) if it can be found, we
should be able to call selinux_proc_get_sid() ..."
On a system exhibiting this problem, you will notice a lot of files in
/proc with the generic "proc_t" type (at least the ones that were
accessed early in the boot), for example:
Cc: Eric Paris <eparis@redhat.com> Signed-off-by: Paul Moore <pmoore@redhat.com> Acked-by: Eric Paris <eparis@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The commit [7546abfb: ALSA: hda - Increment default stream numbers for
AMD HDMI controllers] introduced a regression where the AMD HDMI
playback streams don't work properly. As the simplest fix, this patch
reverts that commit.
The upstream code has been changed largely and already contains
another fix (by changing the stream assignment order), this revert
should be applied only to 3.14 kernel where the regression was
introduced.
Linus Torvalds [Mon, 31 Mar 2014 00:26:08 +0000 (17:26 -0700)]
Merge branch 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull vfs fixes from Al Viro:
"Switch mnt_hash to hlist, turning the races between __lookup_mnt() and
hash modifications into false negatives from __lookup_mnt() (instead
of hangs)"
On the false negatives from __lookup_mnt():
"The *only* thing we care about is not getting stuck in __lookup_mnt().
If it misses an entry because something in front of it just got moved
around, etc, we are fine. We'll notice that mount_lock mismatch and
that'll be it"
* 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
switch mnt_hash to hlist
don't bother with propagate_mnt() unless the target is shared
keep shadowed vfsmounts together
resizable namespace.c hashes
Linus Torvalds [Mon, 31 Mar 2014 00:20:40 +0000 (17:20 -0700)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input
Pull input updates from Dmitry Torokhov:
"Some more updates for the input subsystem.
You will get a fix for race in mousedev that has been causing quite a
few oopses lately and a small fixup for force feedback support in
evdev"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
Input: mousedev - fix race when creating mixed device
Input: don't modify the id of ioctl-provided ff effect on upload failure
Eric Paris [Sun, 30 Mar 2014 23:07:54 +0000 (19:07 -0400)]
AUDIT: Allow login in non-init namespaces
It its possible to configure your PAM stack to refuse login if audit
messages (about the login) were unable to be sent. This is common in
many distros and thus normal configuration of many containers. The PAM
modules determine if audit is enabled/disabled in the kernel based on
the return value from sending an audit message on the netlink socket.
If userspace gets back ECONNREFUSED it believes audit is disabled in the
kernel. If it gets any other error else it refuses to let the login
proceed.
Just about ever since the introduction of namespaces the kernel audit
subsystem has returned EPERM if the task sending a message was not in
the init user or pid namespace. So many forms of containers have never
worked if audit was enabled in the kernel.
BUT if the container was not in net_init then the kernel network code
would send ECONNREFUSED (instead of the audit code sending EPERM). Thus
by pure accident/dumb luck/bug if an admin configured the PAM stack to
reject all logins that didn't talk to audit, but then ran the login
untility in the non-init_net namespace, it would work!! Clearly this was
a bug, but it is a bug some people expected.
With the introduction of network namespace support in 3.14-rc1 the two
bugs stopped cancelling each other out. Now, containers in the
non-init_net namespace refused to let users log in (just like PAM was
configfured!) Obviously some people were not happy that what used to let
users log in, now didn't!
This fix is kinda hacky. We return ECONNREFUSED for all non-init
relevant namespaces. That means that not only will the old broken
non-init_net setups continue to work, now the broken non-init_pid or
non-init_user setups will 'work'. They don't really work, since audit
isn't logging things. But it's what most users want.
In 3.15 we should have patches to support not only the non-init_net
(3.14) namespace but also the non-init_pid and non-init_user namespace.
So all will be right in the world. This just opens the doors wide open
on 3.14 and hopefully makes users happy, if not the audit system...
Reported-by: Andre Tomt <andre@tomt.net> Reported-by: Adam Richter <adam_richter2004@yahoo.com> Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Theodore Ts'o [Sun, 30 Mar 2014 14:20:01 +0000 (10:20 -0400)]
ext4: atomically set inode->i_flags in ext4_set_inode_flags()
Use cmpxchg() to atomically set i_flags instead of clearing out the
S_IMMUTABLE, S_APPEND, etc. flags and then setting them from the
EXT4_IMMUTABLE_FL, EXT4_APPEND_FL flags, since this opens up a race
where an immutable file has the immutable flag cleared for a brief
window of time.
Al Viro [Fri, 21 Mar 2014 01:10:51 +0000 (21:10 -0400)]
switch mnt_hash to hlist
fixes RCU bug - walking through hlist is safe in face of element moves,
since it's self-terminating. Cyclic lists are not - if we end up jumping
to another hash chain, we'll loop infinitely without ever hitting the
original list head.
[fix for dumb braino folded]
Spotted by: Max Kellermann <mk@cm4all.com> Cc: stable@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Al Viro [Fri, 21 Mar 2014 14:14:08 +0000 (10:14 -0400)]
don't bother with propagate_mnt() unless the target is shared
If the dest_mnt is not shared, propagate_mnt() does nothing -
there's no mounts to propagate to and thus no copies to create.
Might as well don't bother calling it in that case.
Cc: stable@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Al Viro [Fri, 28 Feb 2014 18:46:44 +0000 (13:46 -0500)]
resizable namespace.c hashes
* switch allocation to alloc_large_system_hash()
* make sizes overridable by boot parameters (mhash_entries=, mphash_entries=)
* switch mountpoint_hashtable from list_head to hlist_head
Cc: stable@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Linus Torvalds [Sat, 29 Mar 2014 22:01:09 +0000 (15:01 -0700)]
Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer fix from Ingo Molnar:
"A late breaking fix from John. (The bug fixed has a hard lockup
potential, but that was not observed, warnings were)"
* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
time: Revert to calling clock_was_set_delayed() while in irq context
Dmitry Torokhov [Thu, 6 Mar 2014 20:57:24 +0000 (12:57 -0800)]
Input: mousedev - fix race when creating mixed device
We should not be using static variable mousedev_mix in methods that can be
called before that singleton gets assigned. While at it let's add open and
close methods to mousedev structure so that we do not need to test if we
are dealing with multiplexor or normal device and simply call appropriate
method directly.
This fixes: https://bugzilla.kernel.org/show_bug.cgi?id=71551
Input: don't modify the id of ioctl-provided ff effect on upload failure
If a new (id == -1) ff effect was uploaded from userspace,
ff-core.c::input_ff_upload() will have assigned a positive number to the
new effect id. Currently, evdev.c::evdev_do_ioctl() will save this new id
to userspace, regardless of whether the upload succeeded or not.
On upload failure, this can be confusing because the dev->ff->effects[]
array will not contain an element at the index of that new effect id.
This patch fixes this by leaving the id unchanged after upload fails.
Note: Unfortunately applications should still expect changed effect id for
quite some time.
This has been discussed on:
http://www.mail-archive.com/linux-input@vger.kernel.org/msg08513.html
("ff-core effect id handling in case of a failed effect upload")
Alex Elder [Tue, 25 Mar 2014 13:36:02 +0000 (15:36 +0200)]
rbd: drop an unsafe assertion
Olivier Bonvalet reported having repeated crashes due to a failed
assertion he was hitting in rbd_img_obj_callback():
Assertion failure in rbd_img_obj_callback() at line 2165:
rbd_assert(which >= img_request->next_completion);
With a lot of help from Olivier with reproducing the problem
we were able to determine the object and image requests had
already been completed (and often freed) at the point the
assertion failed.
There was a great deal of discussion on the ceph-devel mailing list
about this. The problem only arose when there were two (or more)
object requests in an image request, and the problem was always
seen when the second request was being completed.
The problem is due to a race in the window between setting the
"done" flag on an object request and checking the image request's
next completion value. When the first object request completes, it
checks to see if its successor request is marked "done", and if
so, that request is also completed. In the process, the image
request's next_completion value is updated to reflect that both
the first and second requests are completed. By the time the
second request is able to check the next_completion value, it
has been set to a value *greater* than its own "which" value,
which caused an assertion to fail.
Fix this problem by skipping over any completion processing
unless the completing object request is the next one expected.
Test only for inequality (not >=), and eliminate the bad
assertion.
Tested-by: Olivier Bonvalet <ob@daevel.fr> Signed-off-by: Alex Elder <elder@linaro.org> Reviewed-by: Sage Weil <sage@inktank.com> Reviewed-by: Ilya Dryomov <ilya.dryomov@inktank.com>
1) We've discovered a common error in several networking drivers, they
put VLAN offload features into ->vlan_features, which would suggest
that they support offloading 2 or more levels of VLAN encapsulation.
Not only do these devices not do that, but we don't have the
infrastructure yet to handle that at all.
Fixes from Vlad Yasevich.
2) Fix tcpdump crash with bridging and vlans, also from Vlad.
3) Some MAINTAINERS updates for random32 and bonding.
4) Fix late reseeds of prandom generator, from Sasha Levin.
6) Fix deadlock in openvswitch, from Flavio Leitner.
7) get_timewait4_sock() doesn't report delay times correctly, fix from
Eric Dumazet.
8) Duplicate address detection and addrconf verification need to run in
contexts where RTNL can be obtained. Move them to run from a
workqueue. From Hannes Frederic Sowa.
9) Fix route refcount leaking in ip tunnels, from Pravin B Shelar.
10) Don't return -EINTR from non-blocking recvmsg() on AF_UNIX sockets,
from Eric Dumazet.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (28 commits)
vlan: Warn the user if lowerdev has bad vlan features.
veth: Turn off vlan rx acceleration in vlan_features
ifb: Remove vlan acceleration from vlan_features
qlge: Do not propaged vlan tag offloads to vlans
bridge: Fix crash with vlan filtering and tcpdump
net: Account for all vlan headers in skb_mac_gso_segment
MAINTAINERS: bonding: change email address
MAINTAINERS: bonding: change email address
ipv6: move DAD and addrconf_verify processing to workqueue
tcp: fix get_timewait4_sock() delay computation on 64bit
openvswitch: fix a possible deadlock and lockdep warning
bridge: Fix handling stacked vlan tags
bridge: Fix inabillity to retrieve vlan tags when tx offload is disabled
vhost: validate vhost_get_vq_desc return value
vhost: fix total length when packets are too short
random32: avoid attempt to late reseed if in the middle of seeding
random32: assign to network folks in MAINTAINERS
net/mlx4_core: pass pci_device_id.driver_data to __mlx4_init_one during reset
core, nfqueue, openvswitch: Orphan frags in skb_zerocopy and handle errors
vlan: Set hard_header_len according to available acceleration
...
Vlad Yasevich [Fri, 28 Mar 2014 02:14:49 +0000 (22:14 -0400)]
vlan: Warn the user if lowerdev has bad vlan features.
Some drivers incorrectly assign vlan acceleration features to
vlan_features thus causing issues for Q-in-Q vlan configurations.
Warn the user of such cases.
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vlad Yasevich [Fri, 28 Mar 2014 02:14:46 +0000 (22:14 -0400)]
qlge: Do not propaged vlan tag offloads to vlans
qlge driver turns off NETIF_F_HW_CTAG_FILTER, but forgets to
turn off HW_CTAG_TX and HW_CTAG_RX on vlan devices. With the
current settings, q-in-q will only generate a single vlan header.
Remember to mask off CTAG_TX and CTAG_RX features in vlan_features.
CC: Shahed Shaikh <shahed.shaikh@qlogic.com> CC: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com> CC: Ron Mercer <ron.mercer@qlogic.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Acked-by: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Vlad Yasevich [Fri, 28 Mar 2014 01:51:18 +0000 (21:51 -0400)]
bridge: Fix crash with vlan filtering and tcpdump
When the vlan filtering is enabled on the bridge, but
the filter is not configured on the bridge device itself,
running tcpdump on the bridge device will result in a
an Oops with NULL pointer dereference. The reason
is that br_pass_frame_up() will bypass the vlan
check because promisc flag is set. It will then try
to get the table pointer and process the packet based
on the table. Since the table pointer is NULL, we oops.
Catch this special condition in br_handle_vlan().
Reported-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> CC: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Acked-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Signed-off-by: David S. Miller <davem@davemloft.net>
Vlad Yasevich [Thu, 27 Mar 2014 21:26:18 +0000 (17:26 -0400)]
net: Account for all vlan headers in skb_mac_gso_segment
skb_network_protocol() already accounts for multiple vlan
headers that may be present in the skb. However, skb_mac_gso_segment()
doesn't know anything about it and assumes that skb->mac_len
is set correctly to skip all mac headers. That may not
always be the case. If we are simply forwarding the packet (via
bridge or macvtap), all vlan headers may not be accounted for.
A simple solution is to allow skb_network_protocol to return
the vlan depth it has calculated. This way skb_mac_gso_segment
will correctly skip all mac headers.
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Linus Torvalds [Fri, 28 Mar 2014 20:57:13 +0000 (13:57 -0700)]
Merge branch 'akpm' (patches from Andrew Morton)
Merge two fixes from Andrew Morton:
"The x86 fix should come from x86 guys but they appear to be
conferencing or otherwise distracted.
The ocfs2 fix is a bit of a mess - the code runs into an immediate
NULL deref and we're trying to work out how this got through test and
review, but we haven't heard from Goldwyn in the past few days.
Sasha's patch fixes the oops, but the feature as a whole is probably
broken. So this is a stopgap for 3.14 - I'll aim to get the real
fixes into 3.14.x"
* emailed patches from Andrew Morton akpm@linux-foundation.org>:
x86: fix boot on uniprocessor systems
ocfs2: check if cluster name exists before deref
Artem Fetishev [Fri, 28 Mar 2014 20:33:39 +0000 (13:33 -0700)]
x86: fix boot on uniprocessor systems
On x86 uniprocessor systems topology_physical_package_id() returns -1
which causes rapl_cpu_prepare() to leave rapl_pmu variable uninitialized
which leads to GPF in rapl_pmu_init().
See arch/x86/kernel/cpu/perf_event_intel_rapl.c.
It turns out that physical_package_id and core_id can actually be
retreived for uniprocessor systems too. Enabling them also fixes
rapl_pmu code.
Signed-off-by: Artem Fetishev <artem_fetishev@epam.com> Cc: Stephane Eranian <eranian@google.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Sasha Levin [Fri, 28 Mar 2014 20:33:38 +0000 (13:33 -0700)]
ocfs2: check if cluster name exists before deref
Commit c74a3bdd9b52 ("ocfs2: add clustername to cluster connection") is
trying to strlcpy a string which was explicitly passed as NULL in the
very same patch, triggering a NULL ptr deref.
ipv6: move DAD and addrconf_verify processing to workqueue
addrconf_join_solict and addrconf_join_anycast may cause actions which
need rtnl locked, especially on first address creation.
A new DAD state is introduced which defers processing of the initial
DAD processing into a workqueue.
To get rtnl lock we need to push the code paths which depend on those
calls up to workqueues, specifically addrconf_verify and the DAD
processing.
(v2)
addrconf_dad_failure needs to be queued up to the workqueue, too. This
patch introduces a new DAD state and stop the DAD processing in the
workqueue (this is because of the possible ipv6_del_addr processing
which removes the solicited multicast address from the device).
addrconf_verify_lock is removed, too. After the transition it is not
needed any more.
As we are not processing in bottom half anymore we need to be a bit more
careful about disabling bottom half out when we lock spin_locks which are also
used in bh.
Hunks and backtrace stolen from a patch by Stephen Hemminger.
Reported-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Thu, 27 Mar 2014 14:19:19 +0000 (07:19 -0700)]
tcp: fix get_timewait4_sock() delay computation on 64bit
It seems I missed one change in get_timewait4_sock() to compute
the remaining time before deletion of IPV4 timewait socket.
This could result in wrong output in /proc/net/tcp for tm->when field.
Fixes: 96f817fedec4 ("tcp: shrink tcp6_timewait_sock by one cache line") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Flavio Leitner [Thu, 27 Mar 2014 14:05:34 +0000 (11:05 -0300)]
openvswitch: fix a possible deadlock and lockdep warning
There are two problematic situations.
A deadlock can happen when is_percpu is false because it can get
interrupted while holding the spinlock. Then it executes
ovs_flow_stats_update() in softirq context which tries to get
the same lock.
The second sitation is that when is_percpu is true, the code
correctly disables BH but only for the local CPU, so the
following can happen when locking the remote CPU without
disabling BH:
Toshiaki Makita [Thu, 27 Mar 2014 12:46:56 +0000 (21:46 +0900)]
bridge: Fix handling stacked vlan tags
If a bridge with vlan_filtering enabled receives frames with stacked
vlan tags, i.e., they have two vlan tags, br_vlan_untag() strips not
only the outer tag but also the inner tag.
br_vlan_untag() is called only from br_handle_vlan(), and in this case,
it is enough to set skb->vlan_tci to 0 here, because vlan_tci has already
been set before calling br_handle_vlan().
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Acked-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Toshiaki Makita [Thu, 27 Mar 2014 12:46:55 +0000 (21:46 +0900)]
bridge: Fix inabillity to retrieve vlan tags when tx offload is disabled
Bridge vlan code (br_vlan_get_tag()) assumes that all frames have vlan_tci
if they are tagged, but if vlan tx offload is manually disabled on bridge
device and frames are sent from vlan device on the bridge device, the tags
are embedded in skb->data and they break this assumption.
Extract embedded vlan tags and move them to vlan_tci at ingress.
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Acked-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
vhost fails to validate negative error code
from vhost_get_vq_desc causing
a crash: we are using -EFAULT which is 0xfffffff2
as vector size, which exceeds the allocated size.
Sasha Levin [Fri, 28 Mar 2014 16:38:42 +0000 (17:38 +0100)]
random32: avoid attempt to late reseed if in the middle of seeding
Commit 4af712e8df ("random32: add prandom_reseed_late() and call when
nonblocking pool becomes initialized") has added a late reseed stage
that happens as soon as the nonblocking pool is marked as initialized.
This fails in the case that the nonblocking pool gets initialized
during __prandom_reseed()'s call to get_random_bytes(). In that case
we'd double back into __prandom_reseed() in an attempt to do a late
reseed - deadlocking on 'lock' early on in the boot process.
Instead, just avoid even waiting to do a reseed if a reseed is already
occuring.
Fixes: 4af712e8df99 ("random32: add prandom_reseed_late() and call when nonblocking pool becomes initialized") Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Linus Torvalds [Fri, 28 Mar 2014 20:03:00 +0000 (13:03 -0700)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input
Pull input subsystem fixes from Dmitry Torokhov:
"Updates to Synaptics touchpad to better cope with devices in Lenovo
laptops, and a couple more fixes"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
Input: synaptics - add manual min/max quirk for ThinkPad X240
Input: synaptics - add manual min/max quirk
Input: cypress_ps2 - don't report as a button pads
Input: da9052_onkey - use correct register bit for key status
Input: adp5588-keys - get value from data out when dir is out
Linus Torvalds [Fri, 28 Mar 2014 17:58:10 +0000 (10:58 -0700)]
Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux
Pull drm fixes from Dave Airlie:
"I didn't want these to wait for stable cycle.
The nouveau and radeon ones are the same problem, where the runtime pm
stuff broke non-runtime pm managed secondary GPUs.
The udl fix is for an oops on unplug, and the i915 fix is for a
regression on Sandybridge even though it may break haswell (regression
wins)"
Daniel Vetter comments:
"My apologies for the i915 regression fumble, that thing somehow fell
through the cracks here for almost half a year :( Imo that's more than
enough flailing to just go ahead with the revert, and the re-broken
hsw should get peoples attention ..."
* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
drm/i915: Undo gtt scratch pte unmapping again
drm/radeon: fix runtime suspend breaking secondary GPUs
drm/nouveau: fail runtime pm properly.
drm/udl: take reference to device struct for dma-bufs
Linus Torvalds [Fri, 28 Mar 2014 17:52:05 +0000 (10:52 -0700)]
Merge tag 'stable/for-linus-3.14-rc8-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip
Pull Xen bugfixes from David Vrabel:
"Fix two bugs that cause x86 PV guest crashes.
1. Ballooning a 32-bit guest would eventually crash it.
2. Revert a broken fix for a regression with NUMA_BALACING. The bad
fix caused PV guests to crash after migration. This is not ideal
but unpicking the madness that is _PAGE_NUMA == _PAGE_PROTNONE will
take a while longer"
* tag 'stable/for-linus-3.14-rc8-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
Revert "xen: properly account for _PAGE_NUMA during xen pte translations"
xen/balloon: flush persistent kmaps in correct position
projects / linux-stable / log