05 Oct, 2016
1 commit
-
Add missing dmaengine_unmap_put(), so we don't OOM during RAID6 sync.
Fixes: 1786b943dad0 ("async_pq_val: convert to dmaengine_unmap_data")
Signed-off-by: Justin Maggard
Reviewed-by: Dan Williams
Cc:
Signed-off-by: Vinod Koul
18 Mar, 2016
1 commit
-
CMA allocation should be guaranteed to succeed by definition, but,
unfortunately, it would be failed sometimes. It is hard to track down
the problem, because it is related to page reference manipulation and we
don't have any facility to analyze it.This patch adds tracepoints to track down page reference manipulation.
With it, we can find exact reason of failure and can fix the problem.
Following is an example of tracepoint output. (note: this example is
stale version that printing flags as the number. Recent version will
print it as human readable string.)-9018 [004] 92.678375: page_ref_set: pfn=0x17ac9 flags=0x0 count=1 mapcount=0 mapping=(nil) mt=4 val=1
-9018 [004] 92.678378: kernel_stack:
=> get_page_from_freelist (ffffffff81176659)
=> __alloc_pages_nodemask (ffffffff81176d22)
=> alloc_pages_vma (ffffffff811bf675)
=> handle_mm_fault (ffffffff8119e693)
=> __do_page_fault (ffffffff810631ea)
=> trace_do_page_fault (ffffffff81063543)
=> do_async_page_fault (ffffffff8105c40a)
=> async_page_fault (ffffffff817581d8)
[snip]
-9018 [004] 92.678379: page_ref_mod: pfn=0x17ac9 flags=0x40048 count=2 mapcount=1 mapping=0xffff880015a78dc1 mt=4 val=1
[snip]
...
...
-9131 [001] 93.174468: test_pages_isolated: start_pfn=0x17800 end_pfn=0x17c00 fin_pfn=0x17ac9 ret=fail
[snip]
-9018 [004] 93.174843: page_ref_mod_and_test: pfn=0x17ac9 flags=0x40068 count=0 mapcount=0 mapping=0xffff880015a78dc1 mt=4 val=-1 ret=1
=> release_pages (ffffffff8117c9e4)
=> free_pages_and_swap_cache (ffffffff811b0697)
=> tlb_flush_mmu_free (ffffffff81199616)
=> tlb_finish_mmu (ffffffff8119a62c)
=> exit_mmap (ffffffff811a53f7)
=> mmput (ffffffff81073f47)
=> do_exit (ffffffff810794e9)
=> do_group_exit (ffffffff81079def)
=> SyS_exit_group (ffffffff81079e74)
=> entry_SYSCALL_64_fastpath (ffffffff817560b6)This output shows that problem comes from exit path. In exit path, to
improve performance, pages are not freed immediately. They are gathered
and processed by batch. During this process, migration cannot be
possible and CMA allocation is failed. This problem is hard to find
without this page reference tracepoint facility.Enabling this feature bloat kernel text 30 KB in my configuration.
text data bss dec hex filename
12127327 2243616 1507328 15878271 f2487f vmlinux_disabled
12157208 2258880 1507328 15923416 f2f8d8 vmlinux_enabledNote that, due to header file dependency problem between mm.h and
tracepoint.h, this feature has to open code the static key functions for
tracepoints. Proposed by Steven Rostedt in following link.https://lkml.org/lkml/2015/12/9/699
[arnd@arndb.de: crypto/async_pq: use __free_page() instead of put_page()]
[iamjoonsoo.kim@lge.com: fix build failure for xtensa]
[akpm@linux-foundation.org: tweak Kconfig text, per Vlastimil]
Signed-off-by: Joonsoo Kim
Acked-by: Michal Nazarewicz
Acked-by: Vlastimil Babka
Cc: Minchan Kim
Cc: Mel Gorman
Cc: "Kirill A. Shutemov"
Cc: Sergey Senozhatsky
Acked-by: Steven Rostedt
Signed-off-by: Arnd Bergmann
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
07 Jan, 2016
1 commit
-
These async_XX functions are called from md/raid5 in an atomic
section, between get_cpu() and put_cpu(), so they must not sleep.
So use GFP_NOWAIT rather than GFP_IO.Dan Williams writes: Longer term async_tx needs to be merged into md
directly as we can allocate this unmap data statically per-stripe
rather than per request.Fixed: 7476bd79fc01 ("async_pq: convert to dmaengine_unmap_data")
Cc: stable@vger.kernel.org (v3.13+)
Reported-and-tested-by: Stanislav Samsonov
Acked-by: Dan Williams
Signed-off-by: NeilBrown
Signed-off-by: Vinod Koul
22 Apr, 2015
1 commit
-
Glue it altogehter. The raid6 rmw path should work the same as the
already existing raid5 logic. So emulate the prexor handling/flags
and split functions as needed.1) Enable xor_syndrome() in the async layer.
2) Split ops_run_prexor() into RAID4/5 and RAID6 logic. Xor the syndrome
at the start of a rmw run as we did it before for the single parity.3) Take care of rmw run in ops_run_reconstruct6(). Again process only
the changed pages to get syndrome back into sync.4) Enhance set_syndrome_sources() to fill NULL pages if we are in a rmw
run. The lower layers will calculate start & end pages from that and
call the xor_syndrome() correspondingly.5) Adapt the several places where we ignored Q handling up to now.
Performance numbers for a single E5630 system with a mix of 10 7200k
desktop/server disks. 300 seconds random write with 8 threads onto a
3,2TB (10*400GB) RAID6 64K chunk without spare (group_thread_cnt=4)bsize rmw_level=1 rmw_level=0 rmw_level=1 rmw_level=0
skip_copy=1 skip_copy=1 skip_copy=0 skip_copy=0
4K 115 KB/s 141 KB/s 165 KB/s 140 KB/s
8K 225 KB/s 275 KB/s 324 KB/s 274 KB/s
16K 434 KB/s 536 KB/s 640 KB/s 534 KB/s
32K 751 KB/s 1,051 KB/s 1,234 KB/s 1,045 KB/s
64K 1,339 KB/s 1,958 KB/s 2,282 KB/s 1,962 KB/s
128K 2,673 KB/s 3,862 KB/s 4,113 KB/s 3,898 KB/s
256K 7,685 KB/s 7,539 KB/s 7,557 KB/s 7,638 KB/s
512K 19,556 KB/s 19,558 KB/s 19,652 KB/s 19,688 Kb/sSigned-off-by: Markus Stockhausen
Signed-off-by: NeilBrown
22 Aug, 2014
1 commit
-
the partial xor result must be kept until the next
tx is generated.Cc:
Signed-off-by: Xuelin Shi
Signed-off-by: Dan Williams
16 Nov, 2013
1 commit
-
Pull dmaengine changes from Dan
1/ Bartlomiej and Dan finalized a rework of the dma address unmap
implementation.2/ In the course of testing 1/ a collection of enhancements to dmatest
fell out. Notably basic performance statistics, and fixed / enhanced
test control through new module parameters 'run', 'wait', 'noverify',
and 'verbose'. Thanks to Andriy and Linus for their review.3/ Testing the raid related corner cases of 1/ triggered bugs in the
recently added 16-source operation support in the ioatdma driver.4/ Some minor fixes / cleanups to mv_xor and ioatdma.
Conflicts:
drivers/dma/dmatest.cSigned-off-by: Vinod Koul
15 Nov, 2013
8 commits
-
With 24 disks and an ioatdma instance with 16 source support there is a
corner case where the driver needs to be careful to account for the
number of implied sources in the continuation case.Also bump the default case to test more than 16 sources now that it
triggers different paths in offload drivers.Cc: Dave Jiang
Acked-by: Dave Jiang
Signed-off-by: Dan Williams -
Remove no longer needed DMA unmap flags:
- DMA_COMPL_SKIP_SRC_UNMAP
- DMA_COMPL_SKIP_DEST_UNMAP
- DMA_COMPL_SRC_UNMAP_SINGLE
- DMA_COMPL_DEST_UNMAP_SINGLECc: Vinod Koul
Cc: Tomasz Figa
Cc: Dave Jiang
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Acked-by: Jon Mason
Acked-by: Mark Brown
[djbw: clean up straggling skip unmap flags in ntb]
Signed-off-by: Dan Williams -
Use the generic unmap object to unmap dma buffers.
Cc: Vinod Koul
Cc: Tomasz Figa
Cc: Dave Jiang
Reported-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Signed-off-by: Dan Williams -
Use the generic unmap object to unmap dma buffers.
Cc: Vinod Koul
Cc: Tomasz Figa
Cc: Dave Jiang
Reported-by: Bartlomiej Zolnierkiewicz
[bzolnier: keep temporary dma_dest array in do_async_gen_syndrome()]
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Signed-off-by: Dan Williams -
Use the generic unmap object to unmap dma buffers.
Cc: Vinod Koul
Cc: Tomasz Figa
Cc: Dave Jiang
Reported-by: Bartlomiej Zolnierkiewicz
[bzolnier: keep temporary dma_dest array in async_mult()]
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Signed-off-by: Dan Williams -
Use the generic unmap object to unmap dma buffers.
Cc: Vinod Koul
Cc: Tomasz Figa
Cc: Dave Jiang
Reported-by: Bartlomiej Zolnierkiewicz
[bzolnier: minor cleanups]
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Signed-off-by: Dan Williams -
Use the generic unmap object to unmap dma buffers.
Later we can push this unmap object up to the raid layer and get rid of
the 'scribble' parameter.Cc: Vinod Koul
Cc: Tomasz Figa
Cc: Dave Jiang
Reported-by: Bartlomiej Zolnierkiewicz
[bzolnier: minor cleanups]
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Signed-off-by: Dan Williams -
Use the generic unmap object to unmap dma buffers.
Cc: Vinod Koul
Cc: Tomasz Figa
Cc: Dave Jiang
Reported-by: Bartlomiej Zolnierkiewicz
[bzolnier: add missing unmap->len initialization]
[bzolnier: fix whitespace damage]
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
[djbw: add DMA_ENGINE=n support]
Signed-off-by: Dan Williams
25 Oct, 2013
1 commit
-
Acked-by: Dan Williams
Acked-by: Linus Walleij
Signed-off-by: Vinod Koul
04 Jul, 2013
1 commit
-
There have never been any real users of MEMSET operations since they
have been introduced in January 2007 by commit 7405f74badf4 ("dmaengine:
refactor dmaengine around dma_async_tx_descriptor"). Therefore remove
support for them for now, it can be always brought back when needed.[sebastian.hesselbarth@gmail.com: fix drivers/dma/mv_xor]
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Signed-off-by: Sebastian Hesselbarth
Cc: Vinod Koul
Acked-by: Dan Williams
Cc: Tomasz Figa
Cc: Herbert Xu
Cc: Olof Johansson
Cc: Kevin Hilman
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
30 Apr, 2013
1 commit
-
Use prandom_bytes() to generate random bytes for test data.
Signed-off-by: Akinobu Mita
Cc: Dan Williams
Cc: Vinod Koul
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
08 Jan, 2013
4 commits
-
dma_wait_for_async_tx() can also return DMA_PAUSED (which
should be considered as error).Cc: Vinod Koul
Cc: Dan Williams
Cc: Tomasz Figa
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Signed-off-by: Dan Williams -
Add missing include.
Cc: Dan Williams
Cc: Tomasz Figa
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Signed-off-by: Dan Williams -
Do DMA unmap on ->device_prep_dma_memcpy failure.
Cc: Dan Williams
Cc: Tomasz Figa
Signed-off-by: Bartlomiej Zolnierkiewicz
Signed-off-by: Kyungmin Park
Signed-off-by: Dan Williams -
Use memchr_inv() to check the specified page is filled with zero.
Signed-off-by: Akinobu Mita
Cc: Vinod Koul
Cc: Dan Williams
Signed-off-by: Vinod Koul
20 Mar, 2012
1 commit
-
Signed-off-by: Cong Wang
01 Nov, 2011
1 commit
-
Part of the include cleanups means that the implicit
inclusion of module.h via device.h is going away. So
fix things up in advance.Signed-off-by: Paul Gortmaker
22 Jun, 2011
1 commit
-
Remove linux/mm.h inclusion from netdevice.h -- it's unused (I've checked manually).
To prevent mm.h inclusion via other channels also extract "enum dma_data_direction"
definition into separate header. This tiny piece is what gluing netdevice.h with mm.h
via "netdevice.h => dmaengine.h => dma-mapping.h => scatterlist.h => mm.h".
Removal of mm.h from scatterlist.h was tried and was found not feasible
on most archs, so the link was cutoff earlier.Hope people are OK with tiny include file.
Note, that mm_types.h is still dragged in, but it is a separate story.
Signed-off-by: Alexey Dobriyan
Signed-off-by: David S. Miller
31 Mar, 2011
1 commit
-
Fixes generated by 'codespell' and manually reviewed.
Signed-off-by: Lucas De Marchi
28 Oct, 2010
1 commit
-
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx: (48 commits)
DMAENGINE: move COH901318 to arch_initcall
dma: imx-dma: fix signedness bug
dma/timberdale: simplify conditional
ste_dma40: remove channel_type
ste_dma40: remove enum for endianess
ste_dma40: remove TIM_FOR_LINK option
ste_dma40: move mode_opt to separate config
ste_dma40: move channel mode to a separate field
ste_dma40: move priority to separate field
ste_dma40: add variable to indicate valid dma_cfg
async_tx: make async_tx channel switching opt-in
move async raid6 test to lib/Kconfig.debug
dmaengine: Add Freescale i.MX1/21/27 DMA driver
intel_mid_dma: change the slave interface
intel_mid_dma: fix the WARN_ONs
intel_mid_dma: Add sg list support to DMA driver
intel_mid_dma: Allow DMAC2 to share interrupt
intel_mid_dma: Allow IRQ sharing
intel_mid_dma: Add runtime PM support
DMAENGINE: define a dummy filter function for ste_dma40
...
27 Oct, 2010
1 commit
-
Ensure kmap_atomic() usage is strictly nested
Signed-off-by: Peter Zijlstra
Reviewed-by: Rik van Riel
Acked-by: Chris Metcalf
Cc: David Howells
Cc: Hugh Dickins
Cc: Ingo Molnar
Cc: Thomas Gleixner
Cc: "H. Peter Anvin"
Cc: Steven Rostedt
Cc: Russell King
Cc: Ralf Baechle
Cc: David Miller
Cc: Paul Mackerras
Cc: Benjamin Herrenschmidt
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
08 Oct, 2010
1 commit
-
The prompt for "Self test for hardware accelerated raid6 recovery" does not
belong in the top level configuration menu. All the options in
crypto/async_tx/Kconfig are selected and do not depend on CRYPTO.
Kconfig.debug seems like a reasonable fit.Cc: Herbert Xu
Cc: David Woodhouse
Signed-off-by: Dan Williams
09 Aug, 2010
1 commit
-
Conflicts:
drivers/md/Makefile
lib/raid6/unroll.pl
22 May, 2010
1 commit
-
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx:
DMAENGINE: extend the control command to include an arg
async_tx: trim dma_async_tx_descriptor in 'no channel switch' case
DMAENGINE: DMA40 fix for allocation of logical channel 0
DMAENGINE: DMA40 support paused channel status
dmaengine: mpc512x: Use resource_size
DMA ENGINE: Do not reset 'private' of channel
ioat: Remove duplicated devm_kzalloc() calls for ioatdma_device
ioat3: disable cacheline-unaligned transfers for raid operations
ioat2,3: convert to producer/consumer locking
ioat: convert to circ_buf
DMAENGINE: Support for ST-Ericssons DMA40 block v3
async_tx: use of kzalloc/kfree requires the include of slab.h
dmaengine: provide helper for setting txstate
DMAENGINE: generic channel status v2
DMAENGINE: generic slave control v2
dma: timb-dma: Update comment and fix compiler warning
dma: Add timb-dma
DMAENGINE: COH 901 318 fix bytesleft
DMAENGINE: COH 901 318 rename confusing vars
18 May, 2010
1 commit
-
Saves 24 bytes per descriptor (64-bit) when the channel-switching
capabilities of async_tx are not required.Signed-off-by: Dan Williams
05 May, 2010
1 commit
-
The raid6 recovery code should immediately drop back to the optimized
synchronous path when a p+q dma resource is not available. Otherwise we
run the non-optimized/multi-pass async code in sync mode.Verified with raid6test (NDISKS=255)
Applies to kernels >= 2.6.32.
Cc:
Acked-by: NeilBrown
Reported-by: H. Peter Anvin
Signed-off-by: Dan Williams
Signed-off-by: Linus Torvalds
30 Mar, 2010
1 commit
-
…it slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
18 Dec, 2009
1 commit
-
Add explicit 11 and 12 disks cases to exercise the 0 < src_cnt % 8 < 3
corner case in the ioatdma driver.Signed-off-by: Dan Williams
20 Nov, 2009
1 commit
-
ioat3.2 does not support asynchronous error notifications which makes
the driver experience latencies when non-zero pq validate results are
expected. Provide a mechanism for turning off async_xor_val and
async_syndrome_val via Kconfig. This approach is generally useful for
any driver that specifies ASYNC_TX_DISABLE_CHANNEL_SWITCH and would like
to force the async_tx api to fall back to the synchronous path for
certain operations.Signed-off-by: Dan Williams
30 Oct, 2009
1 commit
-
Signed-off-by: David Woodhouse
20 Oct, 2009
3 commits
-
The raid6 recovery code currently requires special handling of the
4-disk and 5-disk recovery scenarios for the native layout. Quoting
from commit 0a82a623:In these situations the default N-disk algorithm will present
0-source or 1-source operations to dma devices. To cover for
dma devices where the minimum source count is 2 we implement
4-disk and 5-disk handling in the recovery code.The ddf layout presents disks=6 and disks=7 to the recovery code in
these situations. Instead of looking at the number of disks count the
number of non-zero sources in the list and call the special case code
when the number of non-failed sources is 0 or 1.[neilb@suse.de: replace 'ddf' flag with counting good sources]
Signed-off-by: Dan Williams -
The global scribble page is used as a temporary destination buffer when
disabling the P or Q result is requested. The local scribble buffer
contains memory for performing address conversions. Rename the global
variable to avoid confusion.Signed-off-by: Dan Williams
-
- update the kernel doc for async_syndrome to indicate what NULL in the
source list means
- whitespace fixupsSigned-off-by: Dan Williams
16 Oct, 2009
1 commit
-
async_syndrome_val check the P and Q blocks used for RAID6
calculations.
With DDF raid6, some of the data blocks might be NULL, so
this needs to be handled in the same way that async_gen_syndrome
handles it.As async_syndrome_val calls async_xor, also enhance async_xor
to detect and skip NULL blocks in the list.Signed-off-by: NeilBrown
