Al Viro [Thu, 28 Jul 2011 02:27:33 +0000 (22:27 -0400)]
devtmpfs: missing initialialization in never-hit case
create_path() on something without a single / in it will return err
without initializing it. It actually can't happen (we call that thing
only if create on the same path returns -ENOENT, which won't happen
happen for single-component path), but in this case initializing err
to 0 is more than making compiler to STFU - would be the right thing
to return on such paths; the function creates a parent directory of
given pathname and in that case it has no work to do...
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
merge fchmod() and fchmodat() guts, kill ancient broken kludge
xfs: fix misspelled S_IS...()
xfs: get rid of open-coded S_ISREG(), etc.
vfs: document locking requirements for d_move, __d_move and d_materialise_unique
omfs: fix (mode & S_IFDIR) abuse
btrfs: S_ISREG(mode) is not mode & S_IFREG...
ima: fmode_t misspelled as mode_t...
pci-label.c: size_t misspelled as mode_t
jffs2: S_ISLNK(mode & S_IFMT) is pointless
snd_msnd ->mode is fmode_t, not mode_t
v9fs_iop_get_acl: get rid of unused variable
vfs: dont chain pipe/anon/socket on superblock s_inodes list
Documentation: Exporting: update description of d_splice_alias
fs: add missing unlock in default_llseek()
Merge branch 'next/devel2' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc
* 'next/devel2' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc: (47 commits)
OMAP: Add debugfs node to show the summary of all clocks
OMAP2+: hwmod: Follow the recommended PRCM module enable sequence
OMAP2+: clock: allow per-SoC clock init code to prevent clockdomain calls from clock code
OMAP2+: clockdomain: Add per clkdm lock to prevent concurrent state programming
OMAP2+: PM: idle clkdms only if already in idle
OMAP2+: clockdomain: add clkdm_in_hwsup()
OMAP2+: clockdomain: Add 2 APIs to control clockdomain from hwmod framework
OMAP: clockdomain: Remove redundant call to pwrdm_wait_transition()
OMAP4: hwmod: Introduce the module control in hwmod control
OMAP4: cm: Add two new APIs for modulemode control
OMAP4: hwmod data: Add modulemode entry in omap_hwmod structure
OMAP4: hwmod data: Add PRM context register offset
OMAP4: prm: Remove deprecated functions
OMAP4: prm: Replace warm reset API with the offset based version
OMAP4: hwmod: Replace RSTCTRL absolute address with offset macros
OMAP: hwmod: Wait the idle status to be disabled
OMAP4: hwmod: Replace CLKCTRL absolute address with offset macros
OMAP2+: hwmod: Init clkdm field at boot time
OMAP4: hwmod data: Add clock domain attribute
OMAP4: clock data: Add missing divider selection for auxclks
...
Merge branch 'next/devel' of ssh://master.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc
* 'next/devel' of ssh://master.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc: (128 commits)
ARM: S5P64X0: External Interrupt Support
ARM: EXYNOS4: Enable MFC on Samsung NURI
ARM: EXYNOS4: Enable MFC on universal_c210
ARM: S5PV210: Enable MFC on Goni
ARM: S5P: Add support for MFC device
ARM: EXYNOS4: Add support FIMD on SMDKC210
ARM: EXYNOS4: Add platform device and helper functions for FIMD
ARM: EXYNOS4: Add resource definition for FIMD
ARM: EXYNOS4: Change devname for FIMD clkdev
ARM: SAMSUNG: Add IRQ_I2S0 definition
ARM: SAMSUNG: Add platform device for idma
ARM: EXYNOS4: Add more registers to be saved and restored for PM
ARM: EXYNOS4: Add more register addresses of CMU
ARM: EXYNOS4: Add platform device for dwmci driver
ARM: EXYNOS4: configure rtc-s3c on NURI
ARM: EXYNOS4: configure MAX8903 secondary charger on NURI
ARM: EXYNOS4: configure ADC on NURI
ARM: EXYNOS4: configure MAX17042 fuel gauge on NURI
ARM: EXYNOS4: configure regulators and PMIC(MAX8997) on NURI
ARM: EXYNOS4: Increase NR_IRQS for devices with more IRQs
...
Merge branch 'next/board' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc
* 'next/board' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc:
ARM: S3C64XX: Configure backup battery charger on Cragganmore
ARM: S3C64XX: Fix WM8915 IRQ polarity on Cragganmore
ARM: S3C64XX: Configure supplies for all Cragganmore regulators
ARM: S3C64XX: Refresh Cragganmore support
ARM: S3C64XX: Initial support for Wolfson/Simtec Cragganmore/Banff
OMAP4: Keyboard: Mux changes in the board file
omap: blaze: add mmc5/wl1283 device support
omap: 4430SDP: Register the card detect GPIO properly
arm: omap3: cm-t35: add support for cm-t3730
OMAP3: beagle: add support for beagleboard xM revision C
OMAP3: rx-51: Add full regulator definitions
omap: rx51: Platform support for lp5523 led chip
Merge branch 'next/cross-platform' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc
* 'next/cross-platform' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc:
ARM: Consolidate the clkdev header files
ARM: set vga memory base at run-time
ARM: convert PCI defines to variables
ARM: pci: make pcibios_assign_all_busses use pci_has_flag
ARM: remove unnecessary mach/hardware.h includes
pci: move microblaze and powerpc pci flag functions into asm-generic
powerpc: rename ppc_pci_*_flags to pci_*_flags
Fix up conflicts in arch/microblaze/include/asm/pci-bridge.h
Merge branch 'next/soc' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc
* 'next/soc' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc:
MAINTAINERS: add maintainer of CSR SiRFprimaII machine
ARM: CSR: initializing L2 cache
ARM: CSR: mapping early DEBUG_LL uart
ARM: CSR: Adding CSR SiRFprimaII board support
OMAP4: clocks: Update the clock tree with 4460 clock nodes
OMAP4: PRCM: OMAP4460 specific PRM and CM register bitshifts
OMAP4: ID: add omap_has_feature for max freq supported
OMAP: ID: introduce chip detection for OMAP4460
ARM: Xilinx: merge board file into main platform code
ARM: Xilinx: Adding Xilinx board support
Fix up conflicts in arch/arm/mach-omap2/cm-regbits-44xx.h
Merge branch 'next-i2c' of git://git.fluff.org/bjdooks/linux
* 'next-i2c' of git://git.fluff.org/bjdooks/linux:
i2c-eg20t : Fix the issue of Combined R/W transfer mode
i2c-eg20t : Support Combined R/W transfer mode
i2c: Tegra: Add DeviceTree support
where atomic-long.h could use funcs defined later in linux/atomic.h
without a prototype. This patches moves the code that includes
asm-generic/atomic*.h to linux/atomic.h.
Archs that need <asm-generic/atomic64.h> need to select
CONFIG_GENERIC_ATOMIC64 from now on (some of them used to include it
unconditionally).
Compile tested on i386 and x86_64 with allnoconfig.
Signed-off-by: Arun Sharma <asharma@fb.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: David Miller <davem@davemloft.net> Acked-by: Mike Frysinger <vapier@gentoo.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Akinobu Mita [Tue, 26 Jul 2011 23:09:03 +0000 (16:09 -0700)]
fail_make_request: cleanup should_fail_request
This changes should_fail_request() to more usable wrapper function of
should_fail(). It can avoid putting #ifdef CONFIG_FAIL_MAKE_REQUEST in
the middle of a function.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Akinobu Mita [Tue, 26 Jul 2011 23:09:03 +0000 (16:09 -0700)]
fail_page_alloc: simplify debugfs initialization
Now cleanup_fault_attr_dentries() recursively removes a directory, So we
can simplify the error handling in the initialization code and no need
to hold dentry structs for each debugfs file.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Akinobu Mita [Tue, 26 Jul 2011 23:09:02 +0000 (16:09 -0700)]
failslab: simplify debugfs initialization
Now cleanup_fault_attr_dentries() recursively removes a directory, So we
can simplify the error handling in the initialization code and no need
to hold dentry structs for each debugfs file.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The size of the dump is currently set using the RECORD_SIZE macro which
is set to a page size. This patch makes the record size a module
parameter and allows it to be set through platform data as well to allow
larger dumps if needed.
Signed-off-by: Sergiu Iordache <sergiu@chromium.org> Acked-by: Marco Stornelli <marco.stornelli@gmail.com> Cc: "Ahmed S. Darwish" <darwish.07@gmail.com> Cc: Artem Bityutskiy <Artem.Bityutskiy@nokia.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Marco Stornelli [Tue, 26 Jul 2011 23:08:57 +0000 (16:08 -0700)]
ramoops: use module parameters instead of platform data if not available
Use generic module parameters instead of platform data, if platform data
are not available. This limitation has been introduced with commit c3b92ce9e75 ("ramoops: use the platform data structure instead of module
params").
Vmware balloon: switch to using sysem-wide freezable workqueue
With the arrival of concurrency-managed workqueues there is no need for
our driver to use dedicated workqueue; system-wide one should suffice just
fine.
panic, vt: do not force oops output when panic_timeout < 0
Don't force output if you intend to reboot immediately.
In this patch, I'm disabling the functionality enabled by
vc->vc_panic_force_write if panic_timeout < 0 (i.e. no timeout).
vc_panic_force_write is only enabled for fb video consoles if the
FBINFO_CAN_FORCE_OUTPUT flag is set.
For our application, we're using ram_oops to preserved the panic in
memory. We want to reliably, and as fast as possible, machine_restart.
The vc_panic_force_write flag results in a bunch of graphics driver code
to be invoked which slows down restart and decreases reliability. Since
we're already storing the panic in RAM and are going to reboot
immediately, there is no benefit in mode switching back to the vc in
order to display the panic output. The log buffer will get flushed by
the console_unblank() call so remote management consoles should see all
output.
When a kernel BUG or oops occurs, ChromeOS intends to panic and
immediately reboot, with stacktrace and other messages preserved in RAM
across reboot.
But the longer we delay, the more likely the user is to poweroff and
lose the info.
panic_timeout (seconds before rebooting) is set by panic= boot option or
sysctl or /proc/sys/kernel/panic; but 0 means wait forever, so at
present we have to delay at least 1 second.
Let a negative number mean reboot immediately (with the small cosmetic
benefit of suppressing that newline-less "Rebooting in %d seconds.."
message).
drivers/edac/mpc85xx_edac.c: correct offset_in_page mask bits in edac_mc_handle_ce()
Parameter offset_in_page in edac_mc_handle_ce() should mask the higher
bits above the page size, not the lower bits. The original input
sometimes causes a crash.
Signed-off-by: Kai.Jiang <Kai.Jiang@freescale.com> Signed-off-by: Shaohui Xie <Shaohui.Xie@freescale.com> Cc: Anton Vorontsov <avorontsov@mvista.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: "David S. Miller" <davem@davemloft.net> Cc: Kumar Gala <galak@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add support for the shm_rmid_forced sysctl. If set to 1, all shared
memory objects in current ipc namespace will be automatically forced to
use IPC_RMID.
The POSIX way of handling shmem allows one to create shm objects and
call shmdt(), leaving shm object associated with no process, thus
consuming memory not counted via rlimits.
With shm_rmid_forced=1 the shared memory object is counted at least for
one process, so OOM killer may effectively kill the fat process holding
the shared memory.
It obviously breaks POSIX - some programs relying on the feature would
stop working. So set shm_rmid_forced=1 only if you're sure nobody uses
"orphaned" memory. Use shm_rmid_forced=0 by default for compatability
reasons.
The feature was previously impemented in -ow as a configure option.
[akpm@linux-foundation.org: fix documentation, per Randy]
[akpm@linux-foundation.org: fix warning]
[akpm@linux-foundation.org: readability/conventionality tweaks]
[akpm@linux-foundation.org: fix shm_rmid_forced/shm_forced_rmid confusion, use standard comment layout] Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Cc: Randy Dunlap <rdunlap@xenotime.net> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Serge E. Hallyn" <serge.hallyn@canonical.com> Cc: Daniel Lezcano <daniel.lezcano@free.fr> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Solar Designer <solar@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We return ENOMEM from mqueue_get_inode even when we have enough memory.
Namely in case the system rlimit of mqueue was reached. This error
propagates to mq_queue and user sees the error unexpectedly. So fix
this up to properly return EMFILE as described in the manpage:
EMFILE The process already has the maximum number of files and
message queues open.
instead of:
ENOMEM Insufficient memory.
With the previous patch we just switch to ERR_PTR/PTR_ERR/IS_ERR error
handling here.
If new_inode fails to allocate an inode we need only to return with
NULL. But now we test the opposite and have all the work in a nested
block. So do the opposite to save one indentation level (and remove
unnecessary line breaks).
This is only a preparation/cleanup for the next patch where we fix up
return values from mqueue_get_inode.
fs/exec.c:acct_arg_size(): ptl is no longer needed for add_mm_counter()
acct_arg_size() takes ->page_table_lock around add_mm_counter() if
!SPLIT_RSS_COUNTING. This is not needed after commit 172703b08cd0 ("mm:
delete non-atomic mm counter implementation").
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reviewed-by: Matt Fleming <matt.fleming@linux.intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
exec: do not call request_module() twice from search_binary_handler()
Currently, search_binary_handler() tries to load binary loader module
using request_module() if a loader for the requested program is not yet
loaded. But second attempt of request_module() does not affect the result
of search_binary_handler().
If request_module() triggered recursion, calling request_module() twice
causes 2 to the power of MAX_KMOD_CONCURRENT (= 50) repetitions. It is
not an infinite loop but is sufficient for users to consider as a hang up.
Therefore, this patch changes not to call request_module() twice, making 1
to the power of MAX_KMOD_CONCURRENT repetitions in case of recursion.
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Reported-by: Richard Weinberger <richard@nod.at> Tested-by: Richard Weinberger <richard@nod.at> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Tue, 26 Jul 2011 23:08:40 +0000 (16:08 -0700)]
fs/exec.c: use BUILD_BUG_ON for VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP
Commit a8bef8ff6ea1 ("mm: migration: avoid race between
shift_arg_pages() and rmap_walk() during migration by not migrating
temporary stacks") introduced a BUG_ON() to ensure that VM_STACK_FLAGS
and VM_STACK_INCOMPLETE_SETUP do not overlap. The check is a compile
time one, so BUILD_BUG_ON is more appropriate.
Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Richard Weinberger <richard@nod.at> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Daniel Rebelo de Oliveira <psykon@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If an inode's mode permits opening /proc/PID/io and the resulting file
descriptor is kept across execve() of a setuid or similar binary, the
ptrace_may_access() check tries to prevent using this fd against the
task with escalated privileges.
Unfortunately, there is a race in the check against execve(). If
execve() is processed after the ptrace check, but before the actual io
information gathering, io statistics will be gathered from the
privileged process. At least in theory this might lead to gathering
sensible information (like ssh/ftp password length) that wouldn't be
available otherwise.
Holding task->signal->cred_guard_mutex while gathering the io
information should protect against the race.
The order of locking is similar to the one inside of ptrace_attach():
first goes cred_guard_mutex, then lock_task_sighand().
Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
procfs: return ENOENT on opening a being-removed proc entry
Change the return value to ENOENT. This return value is then returned
when opening the proc entry that have been removed. For example,
open("/proc/bus/pci/XX/YY") when the corresponding device is being
hot-removed.
do_coredump() assumes that if format_corename() fails it should return
-ENOMEM. This is not true, for example cn_print_exe_file() can propagate
the error from d_path. Even if it was true, this is too fragile. Change
the code to check "ispipe < 0".
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Jiri Slaby <jslaby@suse.cz> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Change every occurence of / in comm and hostname to !. If the process
changes its name to contain /, the core is not dumped (if the directory
tree doesn't exist like that). The same with hostname being something
like myhost/3. Fix this behaviour by using the escape loop used in %E.
(We extract it to a separate function.)
Now both with comm == myprocess/1 and hostname == myhost/1, the core is
dumped like (kernel.core_pattern='core.%p.%e.%h):
core.2349.myprocess!1.myhost!1
Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If we don't know the file corresponding to the binary (i.e. exe_file is
unknown), use "task->comm (path unknown)" instead of simple "(unknown)"
as suggested by ak.
The fallback is the same as %e except it will append "(path unknown)".
Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andi Kleen <andi@firstfloor.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mike Frysinger [Tue, 26 Jul 2011 23:08:31 +0000 (16:08 -0700)]
ptrace: unify show_regs() prototype
[ poleg@redhat.com: no need to declare show_regs() in ptrace.h, sched.h does this ] Signed-off-by: Mike Frysinger <vapier@gentoo.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Tue, 26 Jul 2011 23:08:30 +0000 (16:08 -0700)]
cpusets: randomize node rotor used in cpuset_mem_spread_node()
[ This patch has already been accepted as commit 0ac0c0d0f837 but later
reverted (commit 35926ff5fba8) because it itroduced arch specific
__node_random which was defined only for x86 code so it broke other
archs. This is a followup without any arch specific code. Other than
that there are no functional changes.]
Some workloads that create a large number of small files tend to assign
too many pages to node 0 (multi-node systems). Part of the reason is
that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts
at node 0 for newly created tasks.
This patch changes the rotor to be initialized to a random node number
of the cpuset.
[akpm@linux-foundation.org: fix layout]
[Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration]
[mhocko@suse.cz: Make it arch independent]
[akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build] Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Paul Menage <menage@google.com> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: David Rientjes <rientjes@google.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: David Rientjes <rientjes@google.com> Cc: Jack Steiner <steiner@sgi.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Menage <menage@google.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Tue, 26 Jul 2011 23:08:29 +0000 (16:08 -0700)]
memcg: get rid of percpu_charge_mutex lock
percpu_charge_mutex protects from multiple simultaneous per-cpu charge
caches draining because we might end up having too many work items. At
least this was the case until commit 26fe61684449 ("memcg: fix percpu
cached charge draining frequency") when we introduced a more targeted
draining for async mode.
Now that also sync draining is targeted we can safely remove mutex
because we will not send more work than the current number of CPUs.
FLUSHING_CACHED_CHARGE protects from sending the same work multiple
times and stock->nr_pages == 0 protects from pointless sending a work if
there is obviously nothing to be done. This is of course racy but we
can live with it as the race window is really small (we would have to
see FLUSHING_CACHED_CHARGE cleared while nr_pages would be still
non-zero).
The only remaining place where we can race is synchronous mode when we
rely on FLUSHING_CACHED_CHARGE test which might have been set by other
drainer on the same group but we should wait in that case as well.
Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Balbir Singh <bsingharora@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Tue, 26 Jul 2011 23:08:29 +0000 (16:08 -0700)]
memcg: add mem_cgroup_same_or_subtree() helper
We are checking whether a given two groups are same or at least in the
same subtree of a hierarchy at several places. Let's make a helper for
it to make code easier to read.
Signed-off-by: Michal Hocko <mhocko@suse.cz> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <bsingharora@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Tue, 26 Jul 2011 23:08:28 +0000 (16:08 -0700)]
memcg: unify sync and async per-cpu charge cache draining
Currently we have two ways how to drain per-CPU caches for charges.
drain_all_stock_sync will synchronously drain all caches while
drain_all_stock_async will asynchronously drain only those that refer to
a given memory cgroup or its subtree in hierarchy. Targeted async
draining has been introduced by 26fe6168 (memcg: fix percpu cached
charge draining frequency) to reduce the cpu workers number.
sync draining is currently triggered only from mem_cgroup_force_empty
which is triggered only by userspace (mem_cgroup_force_empty_write) or
when a cgroup is removed (mem_cgroup_pre_destroy). Although these are
not usually frequent operations it still makes some sense to do targeted
draining as well, especially if the box has many CPUs.
This patch unifies both methods to use the single code (drain_all_stock)
which relies on the original async implementation and just adds
flush_work to wait on all caches that are still under work for the sync
mode. We are using FLUSHING_CACHED_CHARGE bit check to prevent from
waiting on a work that we haven't triggered. Please note that both sync
and async functions are currently protected by percpu_charge_mutex so we
cannot race with other drainers.
Signed-off-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <bsingharora@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Tue, 26 Jul 2011 23:08:27 +0000 (16:08 -0700)]
memcg: do not try to drain per-cpu caches without pages
drain_all_stock_async tries to optimize a work to be done on the work
queue by excluding any work for the current CPU because it assumes that
the context we are called from already tried to charge from that cache
and it's failed so it must be empty already.
While the assumption is correct we can optimize it even more by checking
the current number of pages in the cache. This will also reduce a work
on other CPUs with an empty stock.
For the current CPU we can simply call drain_local_stock rather than
deferring it to the work queue.
[kamezawa.hiroyu@jp.fujitsu.com: use drain_local_stock for current CPU optimization] Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The commit log of 0ae5e89c60c9 ("memcg: count the soft_limit reclaim
in...") says it adds scanning stats to memory.stat file. But it doesn't
because we considered we needed to make a concensus for such new APIs.
This patch is a trial to add memory.scan_stat. This shows
- the number of scanned pages(total, anon, file)
- the number of rotated pages(total, anon, file)
- the number of freed pages(total, anon, file)
- the number of elaplsed time (including sleep/pause time)
for both of direct/soft reclaim.
The biggest difference with oringinal Ying's one is that this file
can be reset by some write, as
# echo 0 ...../memory.scan_stat
Example of output is here. This is a result after make -j 6 kernel
under 300M limit.
This will be useful for further memcg developments and need to be
developped before we do some complicated rework on LRU/softlimit
management.
This patch adds a new struct memcg_scanrecord into scan_control struct.
sc->nr_scanned at el is not designed for exporting information. For
example, nr_scanned is reset frequentrly and incremented +2 at scanning
mapped pages.
To avoid complexity, I added a new param in scan_control which is for
exporting scanning score.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Michal Hocko <mhocko@suse.cz> Cc: Ying Han <yinghan@google.com> Cc: Andrew Bresticker <abrestic@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 22a668d7c3ef ("memcg: fix behavior under memory.limit equals to
memsw.limit") introduced "memsw_is_minimum" flag, which becomes true
when mem_limit == memsw_limit. The flag is checked at the beginning of
reclaim, and "noswap" is set if the flag is true, because using swap is
meaningless in this case.
This works well in most cases, but when we try to shrink mem_limit,
which is the same as memsw_limit now, we might fail to shrink mem_limit
because swap doesn't used.
This patch fixes this behavior by:
- check MEM_CGROUP_RECLAIM_SHRINK at the begining of reclaim
- If it is set, don't set "noswap" flag even if memsw_is_minimum is true.
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <bsingharora@gmail.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Ying Han <yinghan@google.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 246e87a93934 ("memcg: fix get_scan_count() for small targets")
fixes the memcg/kswapd behavior against small targets and prevent vmscan
priority too high.
But the implementation is too naive and adds another problem to small
memcg. It always force scan to 32 pages of file/anon and doesn't handle
swappiness and other rotate_info. It makes vmscan to scan anon LRU
regardless of swappiness and make reclaim bad. This patch fixes it by
adjusting scanning count with regard to swappiness at el.
At a test "cat 1G file under 300M limit." (swappiness=20)
before patch
scanned_pages_by_limit 360919
scanned_anon_pages_by_limit 180469
scanned_file_pages_by_limit 180450
rotated_pages_by_limit 31
rotated_anon_pages_by_limit 25
rotated_file_pages_by_limit 6
freed_pages_by_limit 180458
freed_anon_pages_by_limit 19
freed_file_pages_by_limit 180439
elapsed_ns_by_limit 429758872
after patch
scanned_pages_by_limit 180674
scanned_anon_pages_by_limit 24
scanned_file_pages_by_limit 180650
rotated_pages_by_limit 35
rotated_anon_pages_by_limit 24
rotated_file_pages_by_limit 11
freed_pages_by_limit 180634
freed_anon_pages_by_limit 0
freed_file_pages_by_limit 180634
elapsed_ns_by_limit 367119089
scanned_pages_by_system 0
the numbers of scanning anon are decreased(as expected), and elapsed time
reduced. By this patch, small memcgs will work better.
(*) Because the amount of file-cache is much bigger than anon,
recalaim_stat's rotate-scan counter make scanning files more.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Michal Hocko <mhocko@suse.cz> Cc: Ying Han <yinghan@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Tue, 26 Jul 2011 23:08:24 +0000 (16:08 -0700)]
memcg: change memcg_oom_mutex to spinlock
memcg_oom_mutex is used to protect memcg OOM path and eventfd interface
for oom_control. None of the critical sections which it protects sleep
(eventfd_signal works from atomic context and the rest are simple linked
list resp. oom_lock atomic operations).
Mutex is also too heavyweight for those code paths because it triggers a
lot of scheduling. It also makes makes convoying effects more visible
when we have a big number of oom killing because we take the lock
mutliple times during mem_cgroup_handle_oom so we have multiple places
where many processes can sleep.
Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Balbir Singh <bsingharora@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Tue, 26 Jul 2011 23:08:23 +0000 (16:08 -0700)]
memcg: make oom_lock 0 and 1 based rather than counter
Commit 867578cb ("memcg: fix oom kill behavior") introduced a oom_lock
counter which is incremented by mem_cgroup_oom_lock when we are about to
handle memcg OOM situation. mem_cgroup_handle_oom falls back to a sleep
if oom_lock > 1 to prevent from multiple oom kills at the same time.
The counter is then decremented by mem_cgroup_oom_unlock called from the
same function.
This works correctly but it can lead to serious starvations when we have
many processes triggering OOM and many CPUs available for them (I have
tested with 16 CPUs).
Consider a process (call it A) which gets the oom_lock (the first one
that got to mem_cgroup_handle_oom and grabbed memcg_oom_mutex) and other
processes that are blocked on the mutex. While A releases the mutex and
calls mem_cgroup_out_of_memory others will wake up (one after another)
and increase the counter and fall into sleep (memcg_oom_waitq).
Once A finishes mem_cgroup_out_of_memory it takes the mutex again and
decreases oom_lock and wakes other tasks (if releasing memory by
somebody else - e.g. killed process - hasn't done it yet).
A testcase would look like:
Assume malloc XXX is a program allocating XXX Megabytes of memory
which touches all allocated pages in a tight loop
# swapoff SWAP_DEVICE
# cgcreate -g memory:A
# cgset -r memory.oom_control=0 A
# cgset -r memory.limit_in_bytes= 200M
# for i in `seq 100`
# do
# cgexec -g memory:A malloc 10 &
# done
The main problem here is that all processes still race for the mutex and
there is no guarantee that we will get counter back to 0 for those that
got back to mem_cgroup_handle_oom. In the end the whole convoy
in/decreases the counter but we do not get to 1 that would enable
killing so nothing useful can be done. The time is basically unbounded
because it highly depends on scheduling and ordering on mutex (I have
seen this taking hours...).
This patch replaces the counter by a simple {un}lock semantic. As
mem_cgroup_oom_{un}lock works on the a subtree of a hierarchy we have to
make sure that nobody else races with us which is guaranteed by the
memcg_oom_mutex.
We have to be careful while locking subtrees because we can encounter a
subtree which is already locked: hierarchy:
A
/ \
B \
/\ \
C D E
B - C - D tree might be already locked. While we want to enable locking
E subtree because OOM situations cannot influence each other we
definitely do not want to allow locking A.
Therefore we have to refuse lock if any subtree is already locked and
clear up the lock for all nodes that have been set up to the failure
point.
On the other hand we have to make sure that the rest of the world will
recognize that a group is under OOM even though it doesn't have a lock.
Therefore we have to introduce under_oom variable which is incremented
and decremented for the whole subtree when we enter resp. leave
mem_cgroup_handle_oom. under_oom, unlike oom_lock, doesn't need be
updated under memcg_oom_mutex because its users only check a single
group and they use atomic operations for that.
This can be checked easily by the following test case:
# cgcreate -g memory:A
# cgset -r memory.use_hierarchy=1 A
# cgset -r memory.oom_control=1 A
# cgset -r memory.limit_in_bytes= 100M
# cgset -r memory.memsw.limit_in_bytes= 100M
# cgcreate -g memory:A/B
# cgset -r memory.oom_control=1 A/B
# cgset -r memory.limit_in_bytes=20M
# cgset -r memory.memsw.limit_in_bytes=20M
# cgexec -g memory:A/B malloc 30 & #->this will be blocked by OOM of group B
# cgexec -g memory:A malloc 80 & #->this will be blocked by OOM of group A
While B gets oom_lock A will not get it. Both of them go into sleep and
wait for an external action. We can make the limit higher for A to
enforce waking it up
# cgset -r memory.memsw.limit_in_bytes=300M A
# cgset -r memory.limit_in_bytes=300M A
malloc in A has to wake up even though it doesn't have oom_lock.
Finally, the unlock path is very easy because we always unlock only the
subtree we have locked previously while we always decrement under_oom.
Signed-off-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <bsingharora@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
memcg: export memory cgroup's swappiness with mem_cgroup_swappiness()
Each memory cgroup has a 'swappiness' value which can be accessed by
get_swappiness(memcg). The major user is try_to_free_mem_cgroup_pages()
and swappiness is passed by argument. It's propagated by scan_control.
get_swappiness() is a static function but some planned updates will need
to get swappiness from files other than memcontrol.c This patch exports
get_swappiness() as mem_cgroup_swappiness(). With this, we can remove the
argument of swapiness from try_to_free... and drop swappiness from
scan_control. only memcg uses it.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Ying Han <yinghan@google.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Thomas Gleixner [Tue, 26 Jul 2011 23:08:20 +0000 (16:08 -0700)]
rtc: fix hrtimer deadlock
Ben reported a lockup related to rtc. The lockup happens due to:
CPU0 CPU1
rtc_irq_set_state() __run_hrtimer()
spin_lock_irqsave(&rtc->irq_task_lock) rtc_handle_legacy_irq();
spin_lock(&rtc->irq_task_lock);
hrtimer_cancel()
while (callback_running);
So the running callback never finishes as it's blocked on
rtc->irq_task_lock.
Use hrtimer_try_to_cancel() instead and drop rtc->irq_task_lock while
waiting for the callback. Fix this for both rtc_irq_set_state() and
rtc_irq_set_freq().
Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reported-by: Ben Greear <greearb@candelatech.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Tomoya MORINAGA [Thu, 23 Jun 2011 07:17:10 +0000 (16:17 +0900)]
i2c-eg20t : Fix the issue of Combined R/W transfer mode
issue-1
In case combined transfer mode fails halfway, the processing must be stopped halfway.
However currently, the processing is continued.
This patch breaks the processing.
issue-2
Currently, pch_i2c_xfer returns read/write size at that time.
However pch_i2c_xfer must return the number of messages to be read/written.
This patch modifies correctly.
Signed-off-by: Tomoya MORINAGA <tomoya-linux@dsn.okisemi.com> Signed-off-by: Ben Dooks <ben-linux@fluff.org>
John Bonesio [Wed, 22 Jun 2011 16:16:56 +0000 (09:16 -0700)]
i2c: Tegra: Add DeviceTree support
This patch modifies the tegra i2c driver so that it can be initiailized
using the device tree along with the devices connected to the i2c bus.
Signed-off-by: John Bonesio <bones@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: OIof Johansson <olof@lixom.net> Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (23 commits)
ceph: document unlocked d_parent accesses
ceph: explicitly reference rename old_dentry parent dir in request
ceph: document locking for ceph_set_dentry_offset
ceph: avoid d_parent in ceph_dentry_hash; fix ceph_encode_fh() hashing bug
ceph: protect d_parent access in ceph_d_revalidate
ceph: protect access to d_parent
ceph: handle racing calls to ceph_init_dentry
ceph: set dir complete frag after adding capability
rbd: set blk_queue request sizes to object size
ceph: set up readahead size when rsize is not passed
rbd: cancel watch request when releasing the device
ceph: ignore lease mask
ceph: fix ceph_lookup_open intent usage
ceph: only link open operations to directory unsafe list if O_CREAT|O_TRUNC
ceph: fix bad parent_inode calc in ceph_lookup_open
ceph: avoid carrying Fw cap during write into page cache
libceph: don't time out osd requests that haven't been received
ceph: report f_bfree based on kb_avail rather than diffing.
ceph: only queue capsnap if caps are dirty
ceph: fix snap writeback when racing with writes
...
Al Viro [Tue, 26 Jul 2011 08:15:54 +0000 (04:15 -0400)]
merge fchmod() and fchmodat() guts, kill ancient broken kludge
The kludge in question is undocumented and doesn't work for 32bit
binaries on amd64, sparc64 and s390. Passing (mode_t)-1 as
mode had (since 0.99.14v and contrary to behaviour of any
other Unix, prescriptions of POSIX, SuS and our own manpages)
was kinda-sorta no-op. Note that any software relying on
that (and looking for examples shows none) would be visibly
broken on sparc64, where practically all userland is built
32bit. No such complaints noticed...
Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs-2.6
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs-2.6:
jbd: change the field "b_cow_tid" of struct journal_head from type unsigned to tid_t
ext3.txt: update the links in the section "useful links" to the latest ones
ext3: Fix data corruption in inodes with journalled data
ext2: check xattr name_len before acquiring xattr_sem in ext2_xattr_get
ext3: Fix compilation with -DDX_DEBUG
quota: Remove unused declaration
jbd: Use WRITE_SYNC in journal checkpoint.
jbd: Fix oops in journal_remove_journal_head()
ext3: Return -EINVAL when start is beyond the end of fs in ext3_trim_fs()
ext3/ioctl.c: silence sparse warnings about different address spaces
ext3/ext4 Documentation: remove bh/nobh since it has been deprecated
ext3: Improve truncate error handling
ext3: use proper little-endian bitops
ext2: include fs.h into ext2_fs.h
ext3: Fix oops in ext3_try_to_allocate_with_rsv()
jbd: fix a bug of leaking jh->b_jcount
jbd: remove dependency on __GFP_NOFAIL
ext3: Convert ext3 to new truncate calling convention
jbd: Add fixed tracepoints
ext3: Add fixed tracepoints
Resolve conflicts in fs/ext3/fsync.c due to fsync locking push-down and
new fixed tracepoints.
Sage Weil [Tue, 26 Jul 2011 18:31:26 +0000 (11:31 -0700)]
ceph: document unlocked d_parent accesses
For the most part we don't care about racing with rename when directing
MDS requests; either the old or new parent is fine. Document that, and
do some minor cleanup.
Reviewed-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Tue, 26 Jul 2011 18:31:14 +0000 (11:31 -0700)]
ceph: explicitly reference rename old_dentry parent dir in request
We carry a pin on the parent directory for the rename source and dest
dentries. For the source it's r_locked_dir; we need to explicitly
reference the old_dentry parent as well, since the dentry's d_parent may
change between when the request was created and pinned and when it is
freed.
Reviewed-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Tue, 26 Jul 2011 18:30:29 +0000 (11:30 -0700)]
ceph: protect access to d_parent
d_parent is protected by d_lock: use it when looking up a dentry's parent
directory inode. Also take a reference and drop it in the caller to avoid
a use-after-free.
Reported-by: Al Viro <viro@ZenIV.linux.org.uk> Reviewed-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Tue, 26 Jul 2011 18:30:15 +0000 (11:30 -0700)]
ceph: handle racing calls to ceph_init_dentry
The ->lookup() and prepopulate_readdir() callers are working with unhashed
dentries, so we don't have to worry. The export.c callers, though, need
to initialize something they got back from d_obtain_alias() and are
potentially racing with other callers. Make sure we don't return unless
the dentry is properly initialized (by us or someone else).
Reported-by: Al Viro <viro@ZenIV.linux.org.uk> Reviewed-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net>
Sage Weil [Tue, 26 Jul 2011 18:30:02 +0000 (11:30 -0700)]
ceph: set dir complete frag after adding capability
Curretly ceph_add_cap clears the complete bit if we are newly issued the
FILE_SHARED cap, which is normally the case for a newly issue cap on a new
directory. That means we clear the just-set bit. Move the check that sets
the flag to after the cap is added/updated.
Reviewed-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net>
rbd: cancel watch request when releasing the device
We were missing this cleanup, so when a device was released
the osd didn't clean up its watchers list, so following notifications
could be slow as osd needed to timeout on the client.
Sage Weil [Tue, 26 Jul 2011 18:28:11 +0000 (11:28 -0700)]
ceph: fix ceph_lookup_open intent usage
We weren't properly calling lookup_instantiate_filp when setting up the
lookup intent, which could lead to file leakage on errors. So:
- use separate helper for the hidden snapdir translation, immediately
following the mds request
- use ceph_finish_lookup for the final dentry/return value dance in the
exit path
- lookup_instantiate_filp on success
Reported-by: Al Viro <viro@ZenIV.linux.org.uk> Reviewed-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net>