Benny Halevy [Sun, 22 May 2011 16:53:48 +0000 (19:53 +0300)]
pnfs: encode_layoutcommit
Add a layout driver method to encode the layout type specific
opaque part of layout commit in-line in the xdr stream.
Currently, the pnfs-objects layout driver uses it to encode metadata hints
to the MDS and the blocks layout driver to commit provisionally allocated
extents to the file.
Boaz Harrosh [Thu, 26 May 2011 18:49:46 +0000 (21:49 +0300)]
pnfs-obj: report errors and .encode_layoutreturn Implementation.
An io_state pre-allocates an error information structure for each
possible osd-device that might error during IO. When IO is done if all
was well the io_state is freed. (as today). If the I/O has ended with an
error, the io_state is queued on a per-layout err_list. When eventually
encode_layoutreturn() is called, each error is properly encoded on the
XDR buffer and only then the io_state is removed from err_list and
de-allocated.
It is up to the io_engine to fill in the segment that fault and the type
of osd_error that occurred. By calling objlayout_io_set_result() for
each failing device.
In objio_osd:
* Allocate io-error descriptors space as part of io_state
* Use generic objlayout error reporting at end of io.
With the objects layout security model, we have object capabilities
that are associated with the layout and we anticipate that the server
will issue a cb_layoutrecall for any setattr that changes security
related attributes (user/group/mode/acl) or truncates the file.
Therefore, the layout is returned before issuing the setattr to avoid
the anticipated cb_layoutrecall.
Benny Halevy [Sun, 22 May 2011 16:52:37 +0000 (19:52 +0300)]
pnfs: layoutreturn
NFSv4.1 LAYOUTRETURN implementation
Currently, does not support layout-type payload encoding.
Signed-off-by: Alexandros Batsakis <[email protected]> Signed-off-by: Andy Adamson <[email protected]> Signed-off-by: Andy Adamson <[email protected]> Signed-off-by: Dean Hildebrand <[email protected]> Signed-off-by: Fred Isaman <[email protected]> Signed-off-by: Fred Isaman <[email protected]> Signed-off-by: Marc Eshel <[email protected]> Signed-off-by: Zhang Jingwang <[email protected]>
[call pnfs_return_layout right before pnfs_destroy_layout]
[remove assert_spin_locked from pnfs_clear_lseg_list]
[remove wait parameter from the layoutreturn path.]
[remove return_type field from nfs4_layoutreturn_args]
[remove range from nfs4_layoutreturn_args]
[no need to send layoutcommit from _pnfs_return_layout]
[don't wait on sync layoutreturn]
[fix layout stateid in layoutreturn args]
[fixed NULL deref in _pnfs_return_layout]
[removed recaim member of nfs4_layoutreturn_args] Signed-off-by: Benny Halevy <[email protected]>
With the use of the in-kernel osd library. Implement read/write
of data from/to osd-objects according to information specified
in the objects-layout.
Support for stripping over mirrors with a received stripe_unit.
There are however a few constrains which are not supported:
1. Stripe Unit must be a multiple of PAGE_SIZE
2. stripe length (stripe_unit * number_of_stripes) can not be
bigger then 32bit.
Also support raid-groups and partial-layout. Partial-layout is
when not all the groups are received on the line, addressing
only a partial range of the file.
TODO:
Only raid0! raid 4/5/6 support will come at later stage
A none supported layout will send IO through the MDS
[Important fallout from the last rebase] Signed-off-by: Boaz Harrosh <[email protected]>
[gfp_flags] Signed-off-by: Benny Halevy <[email protected]>
Benny Halevy [Sun, 22 May 2011 16:52:03 +0000 (19:52 +0300)]
pnfs: support for non-rpc layout drivers
Non-rpc layout driver such as for objects and blocks
implement their own I/O path and error handling logic.
Therefore bypass NFS-based error handling for these layout drivers.
[fix lseg ref-count bugs, and null de-refs]
[Fall out from: non-rpc layout drivers] Signed-off-by: Boaz Harrosh <[email protected]>
[get rid of PNFS_USE_RPC_CODE]
[get rid of __nfs4_write_done_cb]
[revert useless change in nfs4_write_done_cb] Signed-off-by: Benny Halevy <[email protected]>
Boaz Harrosh [Thu, 26 May 2011 18:45:34 +0000 (21:45 +0300)]
pnfs-obj: objio_osd device information retrieval and caching
When a new layout is received in objio_alloc_lseg all device_ids
referenced are retrieved. The device information is queried for from MDS
and then the osd_device is looked-up from the osd-initiator library. The
devices are cached in a per-mount-point list, for later use. At unmount
all devices are "put" back to the library.
objlayout_get_deviceinfo(), objlayout_put_deviceinfo() middleware
API for retrieving device information given a device_id.
TODO: The device cache can get big. Cap its size. Keep an LRU and start
to return devices which were not used, when list gets to big, or
when new entries allocation fail.
[pnfs-obj: Bugs in new global-device-cache code] Signed-off-by: Boaz Harrosh <[email protected]>
[gfp_flags]
[use global device cache]
[use layout driver in global device cache] Signed-off-by: Benny Halevy <[email protected]>
Boaz Harrosh [Sun, 22 May 2011 16:50:20 +0000 (19:50 +0300)]
pnfs-obj: decode layout, alloc/free lseg
objlayout_alloc_lseg prepares an xdr_stream and calls the
raid engins objio_alloc_lseg() to allocate a private
pnfs_layout_segment.
objio_osd.c::objio_alloc_lseg() uses passed xdr_stream to
decode and store the layout_segment information in an
objio_segment struct, using the pnfs_osd_xdr.h API for
the actual parsing the layout xdr.
objlayout_free_lseg calls objio_free_lseg() to free the
allocated space.
Signed-off-by: Boaz Harrosh <[email protected]>
[gfp_flags]
[removed "extern" from function definitions] Signed-off-by: Benny Halevy <[email protected]>
Benny Halevy [Sun, 22 May 2011 16:49:32 +0000 (19:49 +0300)]
pnfs-obj: pnfs_osd XDR definitions
* Add the pnfs_osd_xdr.h header
* defintions the pnfs_osd_layout structure including all it's
sub-types and constants.
* Declare the pnfs_osd_xdr_decode_layout API + all needed
inline helpers.
* Define the pnfs_osd_deviceaddr structure and all its subtypes and
constants.
* Declare API for decoding of a pnfs_osd_deviceaddr from XDR stream.
* Define the pnfs_osd_ioerr structure, its substructures and constants.
* Declare API for encoding of a pnfs_osd_ioerr into XDR stream.
* Define the pnfs_osd_layoutupdate structure and its substructures.
* Declare API for encoding of a pnfs_osd_layoutupdate into XDR stream.
Benny Halevy [Sun, 22 May 2011 16:49:06 +0000 (19:49 +0300)]
pnfs-obj: objlayoutdriver module skeleton
* Define the PNFS_OBJLAYOUT Kconfig option in the nfs
master Kconfig file.
* Add the objlayout driver to the Kernel's Kbuild system.
* Add the fs/nfs/objlayout/Kbuild file for building the
objlayoutdriver.ko driver
* Define fs/nfs/objlayout/objio_osd.c, register the driver on module
initialization and unregister on exit.
J. Bruce Fields [Sun, 22 May 2011 16:48:21 +0000 (19:48 +0300)]
pnfs: client stats
A pNFS client auto-negotiates a lot of features (minorversion level,
pNFS layout type, etc.). This is convenient, but makes certain kinds of
failures hard for a user to detect.
For example, if the client falls back on 4.0, or falls back to MDS IO
because the user didn't connect to the right iscsi disks before
mounting, the only symptoms may be reduced performance, which may not be
noticed till long after the actual failure, and may be difficult for a
user to diagnose.
However, such "failures" may also be perfectly normal in some cases, so
we don't want to spam the system logs with them.
One approach would be to put some more information into
/proc/self/mountstats.
Signed-off-by: J. Bruce Fields <[email protected]> Signed-off-by: Benny Halevy <[email protected]>
[pnfs: add commit client stats]
[fixup data types for "ret" variables in pnfs_try_to* inline funcs.] Signed-off-by: Benny Halevy <[email protected]>
[fix definition of show_pnfs for !CONFIG_PNFS] Signed-off-by: Benny Halevy <[email protected]>
[nfs41: Fix show_sessions in the not CONFIG_NFS_V4_1 case]
There is a build error when CONFIG_NFS_V4 is set but
CONFIG_NFS_V4_1 is *not* set. show_sessions() prototype
was unbalanced between the two cases. Signed-off-by: Boaz Harrosh <[email protected]>
[pnfs: super.c remove CONFIG_PNFS] Signed-off-by: Andy Adamson <[email protected]> Signed-off-by: Benny Halevy <[email protected]>
Benny Halevy [Tue, 24 May 2011 15:04:02 +0000 (18:04 +0300)]
NFSv4.1: use layout driver in global device cache
pnfs deviceids are unique per server, per layout type.
struct nfs_client is currently used to distinguish deviceids from
different nfs servers, yet these may clash between different layout
types on the same server. Therefore, use the layout driver associated
with each deviceid at insertion time to look it up, unhash, or
delete it.
Marc Eshel [Sun, 22 May 2011 16:47:09 +0000 (19:47 +0300)]
pnfs: CB_NOTIFY_DEVICEID
Note: This functionlaity is incomplete as all layout segments referring to
the 'to be removed device id' need to be reaped, and all in flight I/O drained.
[use be32 res in nfs4_callback_devicenotify]
[use nfs_client to qualify deviceid for cb_notify_deviceid]
[use global deviceid cache for CB_NOTIFY_DEVICEID]
[refactor device cache _lookup_deviceid]
[refactor device cache _find_get_deviceid] Signed-off-by: Benny Halevy <[email protected]>
[Bug in new global-device-cache code]
[layout_driver MUST set free_deviceid_node if using dev-cache] Signed-off-by: Boaz Harrosh <[email protected]> Signed-off-by: Benny Halevy <[email protected]>
Tyler Hicks [Tue, 24 May 2011 07:16:51 +0000 (02:16 -0500)]
eCryptfs: Cleanup inode initialization code
The eCryptfs inode get, initialization, and dentry interposition code
has two separate paths. One is for when dentry interposition is needed
after doing things like a mkdir in the lower filesystem and the other
is needed after a lookup. Unlocking new inodes and doing a d_add() needs
to happen at different times, depending on which type of dentry
interposing is being done.
This patch cleans up the inode get and initialization code paths and
splits them up so that the locking and d_add() differences mentioned
above can be handled appropriately in a later patch.
Benny Halevy [Fri, 20 May 2011 11:47:33 +0000 (13:47 +0200)]
NFSv4.1: purge deviceid cache on nfs_free_client
Use the pnfs_layoutdriver_type both as a qualifier for the deviceid,
distinguishing deviceid from different layout types on the server,
and for freeing the layout-driver allocated structure containing the
nfs4_deviceid_node.
[BUG in _deviceid_purge_client]
[layout_driver MUST set free_deviceid_node if using dev-cache]
[let ver < 4.1 compile] Signed-off-by: Boaz Harrosh <[email protected]>
[removed EXPORT_SYMBOL_GPL(nfs4_deviceid_purge_client)] Signed-off-by: Benny Halevy <[email protected]>
Mikulas Patocka [Sun, 29 May 2011 12:03:11 +0000 (13:03 +0100)]
dm kcopyd: reserve fewer pages
Reserve just the minimum of pages needed to process one job.
Because we allocate pages from page allocator, we don't need to reserve
a large number of pages. The maximum job size is SUB_JOB_SIZE and we
calculate the number of reserved pages based on this.
Mikulas Patocka [Sun, 29 May 2011 12:03:09 +0000 (13:03 +0100)]
dm io: use fixed initial mempool size
Replace the arbitrary calculation of an initial io struct mempool size
with a constant.
The code calculated the number of reserved structures based on the request
size and used a "magic" multiplication constant of 4. This patch changes
it to reserve a fixed number - itself still chosen quite arbitrarily.
Further testing might show if there is a better number to choose.
Note that if there is no memory pressure, we can still allocate an
arbitrary number of "struct io" structures. One structure is enough to
process the whole request.
Mikulas Patocka [Sun, 29 May 2011 12:03:07 +0000 (13:03 +0100)]
dm kcopyd: alloc pages from the main page allocator
This patch changes dm-kcopyd so that it allocates pages from the main
page allocator with __GFP_NOWARN | __GFP_NORETRY flags (so that it can
fail in case of memory pressure). If the allocation fails, dm-kcopyd
allocates pages from its own reserve.
Remove the spinlock protecting the pages allocation. The spinlock is only
taken on initialization or from single-threaded workqueue. Therefore, the
spinlock is useless.
The spinlock is taken in kcopyd_get_pages and kcopyd_put_pages.
kcopyd_get_pages is only called from run_pages_job, which is only
called from process_jobs called from do_work.
kcopyd_put_pages is called from client_alloc_pages (which is initialization
function) or from run_complete_job. run_complete_job is only called from
process_jobs called from do_work.
Another spinlock, kc->job_lock is taken each time someone pushes or pops
some work for the worker thread. Once we take kc->job_lock, we
guarantee that any written memory is visible to the other CPUs.
Mikulas Patocka [Sun, 29 May 2011 12:03:00 +0000 (13:03 +0100)]
dm kcopyd: preallocate sub jobs to avoid deadlock
There's a possible theoretical deadlock in dm-kcopyd because multiple
allocations from the same mempool are required to finish a request.
Avoid this by preallocating sub jobs.
There is a mempool of 512 entries. Each request requires up to 9
entries from the mempool. If we have at least 57 concurrent requests
running, the mempool may overflow and mempool allocations may start
blocking until another entry is freed to the mempool. Because the same
thread is used to free entries to the mempool and allocate entries from
the mempool, this may result in a deadlock.
This patch changes it so that one mempool entry contains all 9 "struct
kcopyd_job" required to fulfill the whole request. The allocation is
done only once in dm_kcopyd_copy and no further mempool allocations are
done during request processing.
If dm_kcopyd_copy is not run in the completion thread, this
implementation is deadlock-free.
MIN_JOBS needs reducing accordingly and we've chosen to reduce it
further to 8.
Mikulas Patocka [Sun, 29 May 2011 12:02:58 +0000 (13:02 +0100)]
dm kcopyd: avoid pointless job splitting
Don't split SUB_JOB_SIZE jobs
If the job size equals SUB_JOB_SIZE, there is no point in splitting it.
Splitting it just unnecessarily wastes time, because the split job size
is SUB_JOB_SIZE too.
Milan Broz [Sun, 29 May 2011 12:02:52 +0000 (13:02 +0100)]
dm table: reject devices without request fns
This patch adds a check that a block device has a request function
defined before it is used. Otherwise, misconfiguration can cause an oops.
Because we are allowing devices with zero size e.g. an offline multipath
device as in commit 2cd54d9bedb79a97f014e86c0da393416b264eb3
("dm: allow offline devices") there needs to be an additional check
to ensure devices are initialised. Some block devices, like a loop
device without a backing file, exist but have no request function.
Reproducer is trivial: dm-mirror on unbound loop device
(no backing file on loop devices)
Heiko Carstens [Sun, 29 May 2011 10:40:51 +0000 (12:40 +0200)]
[S390] mm: fix mmu_gather rework
Quite a few functions that get called from the tlb gather code require that
preemption must be disabled. So disable preemption inside of the called
functions instead.
The only drawback is that rcu_table_freelist_finish() doesn't get necessarily
called on the cpu(s) that filled the free lists. So we may see a delay, until
we finally see an rcu callback. However over time this shouldn't matter.
So we get rid of lots of "BUG: using smp_processor_id() in preemptible"
messages.
Heiko Carstens [Sun, 29 May 2011 10:40:50 +0000 (12:40 +0200)]
[S390] mm: fix storage key handling
page_get_storage_key() and page_set_storage_key() expect a page address
and not its page frame number. This got inconsistent with 2d42552d
"[S390] merge page_test_dirty and page_clear_dirty".
Result is that we read/write storage keys from random pages and do not
have a working dirty bit tracking at all.
E.g. SetPageUpdate() doesn't clear the dirty bit of requested pages, which
for example ext4 doesn't like very much and panics after a while.
Benny Halevy [Fri, 20 May 2011 08:45:05 +0000 (10:45 +0200)]
NFSv4.1: use struct nfs_client to qualify deviceid
deviceids are unique per server, per layout type.
Therefore, in the global cache in the files layout driver
deviceids from different servers may clash so we need
to qualify them with a struct nfs_client that represents
the nfs server that returned the deviceid.
Introduced in 2.6.39 commit ea8eecdd
"NFSv4.1 move deviceid cache to filelayout driver"
Len Brown [Fri, 1 Apr 2011 19:46:09 +0000 (15:46 -0400)]
x86 idle: deprecate mwait_idle() and "idle=mwait" cmdline param
mwait_idle() is a C1-only idle loop intended to be more efficient
than HLT on SMP hardware that supports it.
But mwait_idle() has been replaced by the more general
mwait_idle_with_hints(), which handles both C1 and deeper C-states.
ACPI uses only mwait_idle_with_hints(), and never uses mwait_idle().
Deprecate mwait_idle() and the "idle=mwait" cmdline param
to simplify the x86 idle code.
After this change, kernels configured with
(!CONFIG_ACPI=n && !CONFIG_INTEL_IDLE=n) when run on hardware
that support MWAIT will simply use HLT. If MWAIT is desired
on those systems, cpuidle and the cpuidle drivers above
can be used.
Len Brown [Fri, 1 Apr 2011 19:41:17 +0000 (15:41 -0400)]
x86 idle: deprecate "no-hlt" cmdline param
We'd rather that modern machines not check if HLT works on
every entry into idle, for the benefit of machines that had
marginal electricals 15-years ago. If those machines are still running
the upstream kernel, they can use "idle=poll". The only difference
will be that they'll now invoke HLT in machine_hlt().
Len Brown [Fri, 1 Apr 2011 19:19:23 +0000 (15:19 -0400)]
x86 idle APM: deprecate CONFIG_APM_CPU_IDLE
We don't want to export the pm_idle function pointer to modules.
Currently CONFIG_APM_CPU_IDLE w/ CONFIG_APM_MODULE forces us to.
CONFIG_APM_CPU_IDLE is of dubious value, it runs only on 32-bit
uniprocessor laptops that are over 10 years old. It calls into
the BIOS during idle, and is known to cause a number of machines
to fail.
Removing CONFIG_APM_CPU_IDLE and will allow us to stop exporting
pm_idle. Any systems that were calling into the APM BIOS
at run-time will simply use HLT instead.
Len Brown [Fri, 1 Apr 2011 19:28:09 +0000 (15:28 -0400)]
x86 idle: EXPORT_SYMBOL(default_idle, pm_idle) only when APM demands it
In the long run, we don't want default_idle() or (pm_idle)() to
be exported outside of process.c. Start by not exporting them
to modules, unless the APM build demands it.
Len Brown [Fri, 1 Apr 2011 20:59:53 +0000 (16:59 -0400)]
x86 idle: clarify AMD erratum 400 workaround
The workaround for AMD erratum 400 uses the term "c1e" falsely suggesting:
1. Intel C1E is somehow involved
2. All AMD processors with C1E are involved
Use the string "amd_c1e" instead of simply "c1e" to clarify that
this workaround is specific to AMD's version of C1E.
Use the string "e400" to clarify that the workaround is specific
to AMD processors with Erratum 400.
This patch is text-substitution only, with no functional change.
Lin Ming [Wed, 4 May 2011 14:56:43 +0000 (22:56 +0800)]
ACPI: Add D3 cold state
_SxW returns an Integer containing the lowest D-state supported in state
Sx. If OSPM has not indicated that it supports _PR3, then the value “3”
corresponds to D3. If it has indicated _PR3 support, the value “3”
represents D3hot and the value “4” represents D3cold.
Linux does set _OSC._PR3, so we should fix it to expect that _SxW can
return 4.
In UP kernel, acpi_get_cpuid(...) always return -1 and
num_possible_cpus() always return 1, so
processor_physically_present(...) always returns true for all passed in
processor handles.
This is wrong for UP processor or SMP processor running UP kernel.
This patch removes the !SMP version of acpi_get_cpuid(), so both UP and
SMP kernel use the same acpi_get_cpuid function.
Linus Torvalds [Sun, 29 May 2011 06:12:28 +0000 (23:12 -0700)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/vapier/blackfin
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/vapier/blackfin:
Blackfin: debug-mmrs: include RSI_PID[4567] MMRs
Blackfin: bf51x: fix up RSI_PID# MMR defines
Blackfin: bf52x/bf54x: fix up usb MMR defines
Blackfin: debug-mmrs: fix typos with gptimers/mdma/ppi
Blackfin: gptimers: add structure for hardware register layout
Blackfin: wire up new sendmmsg syscall
Blackfin: mach/bfin_serial_5xx.h: punt now-unused header
Blackfin: bfin_serial.h: turn default port wrappers into stubs
Randy Dunlap [Sun, 29 May 2011 00:26:40 +0000 (17:26 -0700)]
scsi: fix scsi_proc new kernel-doc warning
Fix kernel-doc warnings in scsi_proc.c:
Warning(drivers/scsi/scsi_proc.c:390): No description found for parameter 'dev'
Warning(drivers/scsi/scsi_proc.c:390): No description found for parameter 'data'
Warning(drivers/scsi/scsi_proc.c:390): Excess function parameter 's' description in 'always_match'
Warning(drivers/scsi/scsi_proc.c:390): Excess function parameter 'p' description in 'always_match'
Tim Chen [Fri, 11 Feb 2011 20:49:04 +0000 (12:49 -0800)]
idle governor: Avoid lock acquisition to read pm_qos before entering idle
Thanks to the reviews and comments by Rafael, James, Mark and Andi.
Here's version 2 of the patch incorporating your comments and also some
update to my previous patch comments.
I noticed that before entering idle state, the menu idle governor will
look up the current pm_qos target value according to the list of qos
requests received. This look up currently needs the acquisition of a
lock to access the list of qos requests to find the qos target value,
slowing down the entrance into idle state due to contention by multiple
cpus to access this list. The contention is severe when there are a lot
of cpus waking and going into idle. For example, for a simple workload
that has 32 pair of processes ping ponging messages to each other, where
64 cpu cores are active in test system, I see the following profile with
37.82% of cpu cycles spent in contention of pm_qos_lock:
A better approach will be to cache the updated pm_qos target value so
reading it does not require lock acquisition as in the patch below.
With this patch the contention for pm_qos_lock is removed and I saw a
2.2X increase in throughput for my message passing workload.
Tero Kristo [Thu, 24 Feb 2011 15:19:23 +0000 (17:19 +0200)]
cpuidle: menu: fixed wrapping timers at 4.294 seconds
Cpuidle menu governor is using u32 as a temporary datatype for storing
nanosecond values which wrap around at 4.294 seconds. This causes errors
in predicted sleep times resulting in higher than should be C state
selection and increased power consumption. This also breaks cpuidle
state residency statistics.
Hugh Dickins [Sat, 28 May 2011 20:20:21 +0000 (13:20 -0700)]
mm: fix page_lock_anon_vma leaving mutex locked
On one machine I've been getting hangs, a page fault's anon_vma_prepare()
waiting in anon_vma_lock(), other processes waiting for that page's lock.
This is a replay of last year's f18194275c39 "mm: fix hang on
anon_vma->root->lock".
The new page_lock_anon_vma() places too much faith in its refcount: when
it has acquired the mutex_trylock(), it's possible that a racing task in
anon_vma_alloc() has just reallocated the struct anon_vma, set refcount
to 1, and is about to reset its anon_vma->root.
Fix this by saving anon_vma->root, and relying on the usual page_mapped()
check instead of a refcount check: if page is still mapped, the anon_vma
is still ours; if page is not still mapped, we're no longer interested.
Hugh Dickins [Sat, 28 May 2011 20:17:04 +0000 (13:17 -0700)]
mm: fix kernel BUG at mm/rmap.c:1017!
I've hit the "address >= vma->vm_end" check in do_page_add_anon_rmap()
just once. The stack showed khugepaged allocation trying to compact
pages: the call to page_add_anon_rmap() coming from remove_migration_pte().
That path holds anon_vma lock, but does not hold mmap_sem: it can
therefore race with a split_vma(), and in commit 5f70b962ccc2 "mmap:
avoid unnecessary anon_vma lock" we just took away the anon_vma lock
protection when adjusting vma->vm_end.
I don't think that particular BUG_ON ever caught anything interesting,
so better replace it by a comment, than reinstate the anon_vma locking.
Hugh Dickins [Sat, 28 May 2011 20:14:09 +0000 (13:14 -0700)]
tmpfs: fix race between truncate and writepage
While running fsx on tmpfs with a memhog then swapoff, swapoff was hanging
(interruptibly), repeatedly failing to locate the owner of a 0xff entry in
the swap_map.
Although shmem_writepage() does abandon when it sees incoming page index
is beyond eof, there was still a window in which shmem_truncate_range()
could come in between writepage's dropping lock and updating swap_map,
find the half-completed swap_map entry, and in trying to free it,
leave it in a state that swap_shmem_alloc() could not correct.
Arguably a bug in __swap_duplicate()'s and swap_entry_free()'s handling
of the different cases, but easiest to fix by moving swap_shmem_alloc()
under cover of the lock.
More interesting than the bug: it's been there since 2.6.33, why could
I not see it with earlier kernels? The mmotm of two weeks ago seems to
have some magic for generating races, this is just one of three I found.
With yesterday's git I first saw this in mainline, bisected in search of
that magic, but the easy reproducibility evaporated. Oh well, fix the bug.
Mike Frysinger [Thu, 26 May 2011 22:07:11 +0000 (18:07 -0400)]
Blackfin: debug-mmrs: include RSI_PID[4567] MMRs
The documentation is a little iffy as to whether these are actual MMRs,
but reading them on the hardware works, and the previous version of this
logic (the SDH) had PID[4567]. So add it for RSI too.
Mike Frysinger [Thu, 26 May 2011 22:05:15 +0000 (18:05 -0400)]
Blackfin: bf51x: fix up RSI_PID# MMR defines
Looks like the copying of MMR defines from the SDH block missed updating
the addresses of the RSI_PID# registers. So tweak them to reflect the
actual hardware.
Mike Frysinger [Mon, 28 Sep 2009 03:16:01 +0000 (03:16 +0000)]
Blackfin: mach/bfin_serial_5xx.h: punt now-unused header
Now that the serial code has been unified in bfin_serial.h, and the
Blackfin UART driver pushed its resources to the boards files, we
don't need these headers anymore.
Linus Torvalds [Sat, 28 May 2011 20:03:41 +0000 (13:03 -0700)]
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: (36 commits)
Cache xattr security drop check for write v2
fs: block_page_mkwrite should wait for writeback to finish
mm: Wait for writeback when grabbing pages to begin a write
configfs: remove unnecessary dentry_unhash on rmdir, dir rename
fat: remove unnecessary dentry_unhash on rmdir, dir rename
hpfs: remove unnecessary dentry_unhash on rmdir, dir rename
minix: remove unnecessary dentry_unhash on rmdir, dir rename
fuse: remove unnecessary dentry_unhash on rmdir, dir rename
coda: remove unnecessary dentry_unhash on rmdir, dir rename
afs: remove unnecessary dentry_unhash on rmdir, dir rename
affs: remove unnecessary dentry_unhash on rmdir, dir rename
9p: remove unnecessary dentry_unhash on rmdir, dir rename
ncpfs: fix rename over directory with dangling references
ncpfs: document dentry_unhash usage
ecryptfs: remove unnecessary dentry_unhash on rmdir, dir rename
hostfs: remove unnecessary dentry_unhash on rmdir, dir rename
hfsplus: remove unnecessary dentry_unhash on rmdir, dir rename
hfs: remove unnecessary dentry_unhash on rmdir, dir rename
omfs: remove unnecessary dentry_unhash on rmdir, dir rneame
udf: remove unnecessary dentry_unhash from rmdir, dir rename
...
Linus Torvalds [Sat, 28 May 2011 19:57:01 +0000 (12:57 -0700)]
Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, asm: Clean up desc.h a bit
x86, amd: Do not enable ARAT feature on AMD processors below family 0x12
x86: Move do_page_fault()'s error path under unlikely()
x86, efi: Retain boot service code until after switching to virtual mode
x86: Remove unnecessary check in detect_ht()
x86: Reorder mm_context_t to remove x86_64 alignment padding and thus shrink mm_struct
x86, UV: Clean up uv_tlb.c
x86, UV: Add support for SGI UV2 hub chip
x86, cpufeature: Update CPU feature RDRND to RDRAND
Linus Torvalds [Sat, 28 May 2011 19:56:32 +0000 (12:56 -0700)]
Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
rcu: Start RCU kthreads in TASK_INTERRUPTIBLE state
rcu: Remove waitqueue usage for cpu, node, and boost kthreads
rcu: Avoid acquiring rcu_node locks in timer functions
atomic: Add atomic_or()
Documentation: Add statistics about nested locks
rcu: Decrease memory-barrier usage based on semi-formal proof
rcu: Make rcu_enter_nohz() pay attention to nesting
rcu: Don't do reschedule unless in irq
rcu: Remove old memory barriers from rcu_process_callbacks()
rcu: Add memory barriers
rcu: Fix unpaired rcu_irq_enter() from locking selftests
Linus Torvalds [Sat, 28 May 2011 19:55:55 +0000 (12:55 -0700)]
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (25 commits)
perf: Fix SIGIO handling
perf top: Don't stop if no kernel symtab is found
perf top: Handle kptr_restrict
perf top: Remove unused macro
perf events: initialize fd array to -1 instead of 0
perf tools: Make sure kptr_restrict warnings fit 80 col terms
perf tools: Fix build on older systems
perf symbols: Handle /proc/sys/kernel/kptr_restrict
perf: Remove duplicate headers
ftrace: Add internal recursive checks
tracing: Update btrfs's tracepoints to use u64 interface
tracing: Add __print_symbolic_u64 to avoid warnings on 32bit machine
ftrace: Set ops->flag to enabled even on static function tracing
tracing: Have event with function tracer check error return
ftrace: Have ftrace_startup() return failure code
jump_label: Check entries limit in __jump_label_update
ftrace/recordmcount: Avoid STT_FUNC symbols as base on ARM
scripts/tags.sh: Add magic for trace-events for etags too
scripts/tags.sh: Fix ctags for DEFINE_EVENT()
x86/ftrace: Fix compiler warning in ftrace.c
...
Linus Torvalds [Sat, 28 May 2011 19:36:15 +0000 (12:36 -0700)]
Merge branch 'for-usb-next' of git://git.kernel.org/pub/scm/linux/kernel/git/sarah/xhci
* 'for-usb-next' of git://git.kernel.org/pub/scm/linux/kernel/git/sarah/xhci:
Intel xhci: Limit number of active endpoints to 64.
Intel xhci: Ignore spurious successful event.
Intel xhci: Support EHCI/xHCI port switching.
Intel xhci: Add PCI id for Panther Point xHCI host.
xhci: STFU: Be quieter during URB submission and completion.
xhci: STFU: Don't print event ring dequeue pointer.
xhci: STFU: Remove function tracing.
xhci: Don't submit commands when the host is dead.
xhci: Clear stopped_td when Stop Endpoint command completes.
Linus Torvalds [Sat, 28 May 2011 19:35:15 +0000 (12:35 -0700)]
Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx: (33 commits)
x86: poll waiting for I/OAT DMA channel status
maintainers: add dma engine tree details
dmaengine: add TODO items for future work on dma drivers
dmaengine: Add API documentation for slave dma usage
dmaengine/dw_dmac: Update maintainer-ship
dmaengine: move link order
dmaengine/dw_dmac: implement pause and resume in dwc_control
dmaengine/dw_dmac: Replace spin_lock* with irqsave variants and enable submission from callback
dmaengine/dw_dmac: Divide one sg to many desc, if sg len is greater than DWC_MAX_COUNT
dmaengine/dw_dmac: set residue as total len in dwc_tx_status if status is !DMA_SUCCESS
dmaengine/dw_dmac: don't call callback routine in case dmaengine_terminate_all() is called
dmaengine: at_hdmac: pause: no need to wait for FIFO empty
pch_dma: modify pci device table definition
pch_dma: Support new device ML7223 IOH
pch_dma: Support I2S for ML7213 IOH
pch_dma: Fix DMA setting issue
pch_dma: modify for checkpatch
pch_dma: fix dma direction issue for ML7213 IOH video-in
dmaengine: at_hdmac: use descriptor chaining help function
dmaengine: at_hdmac: implement pause and resume in atc_control
...
Linus Torvalds [Sat, 28 May 2011 17:57:39 +0000 (10:57 -0700)]
Merge branch 'spi/next' of git://git.secretlab.ca/git/linux-2.6
* 'spi/next' of git://git.secretlab.ca/git/linux-2.6:
spi/spi_bfin_sport: new driver for a SPI bus via the Blackfin SPORT peripheral
spi/tle620x: add missing device_remove_file()
Linus Torvalds [Sat, 28 May 2011 17:56:34 +0000 (10:56 -0700)]
Merge branch 'gpio/next' of git://git.secretlab.ca/git/linux-2.6
* 'gpio/next' of git://git.secretlab.ca/git/linux-2.6:
gpio/pch_gpio: Support new device ML7223
gpio: make gpio_{request,free}_array gpio array parameter const
GPIO: OMAP: move to drivers/gpio
GPIO: OMAP: move register offset defines into <plat/gpio.h>
gpio: Convert gpio_is_valid to return bool
gpio: Move the s5pc100 GPIO to drivers/gpio
gpio: Move the s5pv210 GPIO to drivers/gpio
gpio: Move the exynos4 GPIO to drivers/gpio
gpio: Move to Samsung common GPIO library to drivers/gpio
gpio/nomadik: add function to read GPIO pull down status
gpio/nomadik: show all pins in debug
gpio: move Nomadik GPIO driver to drivers/gpio
gpio: move U300 GPIO driver to drivers/gpio
langwell_gpio: add runtime pm support
gpio/pca953x: Add support for pca9574 and pca9575 devices
gpio/cs5535: Show explicit dependency between gpio_cs5535 and mfd_cs5535
32bit and 64bit on x86 are tested and working. The rest I have looked
at closely and I can't find any problems.
setns is an easy system call to wire up. It just takes two ints so I
don't expect any weird architecture porting problems.
While doing this I have noticed that we have some architectures that are
very slow to get new system calls. cris seems to be the slowest where
the last system calls wired up were preadv and pwritev. avr32 is weird
in that recvmmsg was wired up but never declared in unistd.h. frv is
behind with perf_event_open being the last syscall wired up. On h8300
the last system call wired up was epoll_wait. On m32r the last system
call wired up was fallocate. mn10300 has recvmmsg as the last system
call wired up. The rest seem to at least have syncfs wired up which was
new in the 2.6.39.
v2: Most of the architecture support added by Daniel Lezcano <[email protected]>
v3: ported to v2.6.36-rc4 by: Eric W. Biederman <[email protected]>
v4: Moved wiring up of the system call to another patch
v5: ported to v2.6.39-rc6
v6: rebased onto parisc-next and net-next to avoid syscall conflicts.
v7: ported to Linus's latest post 2.6.39 tree.
> arch/blackfin/include/asm/unistd.h | 3 ++-
> arch/blackfin/mach-common/entry.S | 1 + Acked-by: Mike Frysinger <[email protected]>
Oh - ia64 wiring looks good. Acked-by: Tony Luck <[email protected]> Signed-off-by: Eric W. Biederman <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
Andi Kleen [Sat, 28 May 2011 15:25:51 +0000 (08:25 -0700)]
Cache xattr security drop check for write v2
Some recent benchmarking on btrfs showed that a major scaling bottleneck
on large systems on btrfs is currently the xattr lookup on every write.
Why xattr lookup on every write I hear you ask?
write wants to drop suid and security related xattrs that could set o
capabilities for executables. To do that it currently looks up
security.capability on EVERY write (even for non executables) to decide
whether to drop it or not.
In btrfs this causes an additional tree walk, hitting some per file system
locks and quite bad scalability. In a simple read workload on a 8S
system I saw over 90% CPU time in spinlocks related to that.
Chris Mason tells me this is also a problem in ext4, where it hits
the global mbcache lock.
This patch adds a simple per inode to avoid this problem. We only
do the lookup once per file and then if there is no xattr cache
the decision. All xattr changes clear the flag.
I also used the same flag to avoid the suid check, although
that one is pretty cheap.
A file system can also set this flag when it creates the inode,
if it has a cheap way to do so. This is done for some common file systems
in followon patches.
With this patch a major part of the lock contention disappears
for btrfs. Some testing on smaller systems didn't show significant
performance changes, but at least it helps the larger systems
and is generally more efficient.
Paul E. McKenney [Wed, 25 May 2011 20:42:06 +0000 (13:42 -0700)]
rcu: Start RCU kthreads in TASK_INTERRUPTIBLE state
Upon creation, kthreads are in TASK_UNINTERRUPTIBLE state, which can
result in softlockup warnings. Because some of RCU's kthreads can
legitimately be idle indefinitely, start them in TASK_INTERRUPTIBLE
state in order to avoid those warnings.
Peter Zijlstra [Fri, 20 May 2011 23:06:29 +0000 (16:06 -0700)]
rcu: Remove waitqueue usage for cpu, node, and boost kthreads
It is not necessary to use waitqueues for the RCU kthreads because
we always know exactly which thread is to be awakened. In addition,
wake_up() only issues an actual wakeup when there is a thread waiting on
the queue, which was why there was an extra explicit wake_up_process()
to get the RCU kthreads started.
Eliminating the waitqueues (and wake_up()) in favor of wake_up_process()
eliminates the need for the initial wake_up_process() and also shrinks
the data structure size a bit. The wakeup logic is placed in a new
rcu_wait() macro.
Paul E. McKenney [Wed, 11 May 2011 12:41:41 +0000 (05:41 -0700)]
rcu: Avoid acquiring rcu_node locks in timer functions
This commit switches manipulations of the rcu_node ->wakemask field
to atomic operations, which allows rcu_cpu_kthread_timer() to avoid
acquiring the rcu_node lock. This should avoid the following lockdep
splat reported by Valdis Kletnieks:
"After pulling the thread off the run-queue during a cgroup change,
the cfs_rq.min_vruntime gets recalculated. The dequeued thread's vruntime
then gets normalized to this new value. This can then lead to the thread
getting an unfair boost in the new group if the vruntime of the next
task in the old run-queue was way further ahead."
Peter Zijlstra [Thu, 26 May 2011 12:21:33 +0000 (14:21 +0200)]
sched: Fix ttwu() for __ARCH_WANT_INTERRUPTS_ON_CTXSW
Marc reported that e4a52bcb9 (sched: Remove rq->lock from the first
half of ttwu()) broke his ARM-SMP machine. Now ARM is one of the few
__ARCH_WANT_INTERRUPTS_ON_CTXSW users, so that exception in the ttwu()
code was suspect.
Yong found that the interrupt could hit after context_switch() changes
current but before it clears p->on_cpu, if that interrupt were to
attempt a wake-up of p we would indeed find ourselves spinning in IRQ
context.
Fix this by reverting to the old behaviour for this situation and
perform a full remote wake-up.
sched_domain iterations needs to be protected by rcu_read_lock() now,
this patch adds another two places which needs the rcu lock, which is
spotted by following suspicious rcu_dereference_check() usage warnings.
kernel/sched_rt.c:1244 invoked rcu_dereference_check() without protection!
kernel/sched_stats.h:41 invoked rcu_dereference_check() without protection!
projects / linux.git / log