Re: [PATCH] io_uring: Try to merge io requests only for regular files

- stable@ 19.03.2021, 08:29, "Dmitry Monakhov" : > Otherwise we may endup blocking on pipe or socket. > > Fixes: 6d5d5ac ("io_uring: extend async work merge") > Testcase: > https://github.com/dmonakhov/liburing/commit/16d171b6ef9d68e6db66650a83d98c5c721d01

[PATCH] io_uring: Try to merge io requests only for regular files

Otherwise we may endup blocking on pipe or socket. Fixes: 6d5d5ac ("io_uring: extend async work merge") Testcase: https://github.com/dmonakhov/liburing/commit/16d171b6ef9d68e6db66650a83d98c5c721d01f6 Signed-off-by: Dmitry Monakhov --- fs/io_uring.c | 3 +++ 1 file changed, 3

Re: [PATCH 1/1] nvme-pci: add the DISABLE_WRITE_ZEROES quirk for a Samsung PM1725a

10.03.2021, 16:41, "Christoph Hellwig" : > On Wed, Mar 10, 2021 at 02:21:56PM +0100, Christoph Hellwig wrote: >>  Can you try this patch instead? >> >>  http://lists.infradead.org/pipermail/linux-nvme/2021-February/023183.html > > Actually, please try the patch below instead, it looks like our e

[RESEND][PATCH] nvme-pci: add the DISABLE_WRITE_ZEROES quirk for a Samsung PM1725a

:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Signed-off-by: Dmitry Monakhov --- drivers/nvme/host/pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 17ab332..7249ae7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c

Re: [PATCH] bfq: fix blkio cgroup leakage

Paolo Valente writes: >> Il giorno 9 lug 2020, alle ore 10:19, Dmitry Monakhov >> ha scritto: >> >> Paolo Valente writes: >> >>>> Il giorno 8 lug 2020, alle ore 19:48, Dmitry Monakhov >>>> ha scritto: >>>> >>&

[PATCH] bfq: fix blkio cgroup leakage v4

v grep blkio /proc/cgroups truncate -s 1M img losetup /dev/loop0 img echo bfq > /sys/block/loop0/queue/scheduler grep blkio /proc/cgroups for ((i=0;i /sys/fs/cgroup/blkio/a/cgroup.procs dd if=/dev/loop0 bs=4k count=1 of=/dev/null iflag=direct 2> /dev/null echo 0 > /sys/fs/cgroup/

[PATCH 1/2] lib/test_lockup.c: add measure_alloc_pages_wait option

measure_alloc_pages_wait=Y measure maximum page allocation wait time Signed-off-by: Dmitry Monakhov --- lib/test_lockup.c | 27 +-- 1 file changed, 25 insertions(+), 2 deletions(-) diff --git a/lib/test_lockup.c b/lib/test_lockup.c index 0f81252..867b2f4 100644 --- a

[PATCH 2/2] lib/test_lockup.c: allow cond_resched inside iteration

r=$CGROUP_MUTEX reacquire_locks=Y\ cond_resched_inside=Y measure_lockup=Y & stress-ng -c $(nproc) --timeout 10s& time mkdir /sys/fs/cgroup/blkio/a time rmdir /sys/fs/cgroup/blkio/a Signed-off-by: Dmitry Monakhov --- lib/test_lockup.c | 45 + 1 fi

[PATCH] lib/test_lockup.c: add parameters for cond_resched inside loop

--timeout 10s& time mkdir /sys/fs/cgroup/blkio/a Signed-off-by: Dmitry Monakhov --- lib/test_lockup.c | 44 +++- 1 file changed, 43 insertions(+), 1 deletion(-) diff --git a/lib/test_lockup.c b/lib/test_lockup.c index 0f81252..3e05d6e 100644 --- a/lib

[PATCH] block: bfq fix blkio cgroup leakage v3

dir /sys/fs/cgroup/blkio/a grep blkio /proc/cgroups done ##TESTCASE_END: changes since v2: - use safe iteration macro to prevent freed object dereference. Signed-off-by: Dmitry Monakhov --- block/bfq-wf2q.c | 24 ++-- 1 file changed, 14 insertions(+), 10 deletions(-) diff --

[PATCH] block: bfq fix blkio cgroup leakage v2

truncate -s 1M img losetup /dev/loop0 img echo bfq > /sys/block/loop0/queue/scheduler grep blkio /proc/cgroups for ((i=0;i /sys/fs/cgroup/blkio/a/cgroup.procs dd if=/dev/loop0 bs=4k count=1 of=/dev/null iflag=direct 2> /dev/null echo 0 > /sys/fs/cgroup/blkio/cgroup.procs rmdir /

Re: [PATCH] bfq: fix blkio cgroup leakage

Paolo Valente writes: >> Il giorno 9 lug 2020, alle ore 10:19, Dmitry Monakhov >> ha scritto: >> >> Paolo Valente writes: >> >>>> Il giorno 8 lug 2020, alle ore 19:48, Dmitry Monakhov >>>> ha scritto: >>>> >>>>

Re: [PATCH] bfq: fix blkio cgroup leakage

Paolo Valente writes: >> Il giorno 8 lug 2020, alle ore 19:48, Dmitry Monakhov >> ha scritto: >> >> Paolo Valente writes: >> >>> Hi, >>> sorry for the delay. The commit you propose to drop fix the issues >>> reported in [1]. >&

Re: [PATCH] bfq: fix blkio cgroup leakage

e real one. Please correct me if I'm wrong. > > I'll check it ASAP, unless you do it before me. > > Thanks, > Paolo > > [1] https://lkml.org/lkml/2020/1/31/94 > >> Il giorno 2 lug 2020, alle ore 12:57, Dmitry Monakhov >> ha scritto: >> >>

Re: [PATCH] bfq: fix blkio cgroup leakage

Dmitry Monakhov writes: Ping. Do you have any objections against this patch? > commit db37a34c563b ("block, bfq: get a ref to a group when adding it to a > service tree") > introduce leak forbfq_group and blkcg_gq objects because of get/put > imbalance. See trace

[PATCH] bfq: fix blkio cgroup leakage

ck/loop0/queue/scheduler grep blkio /proc/cgroups for ((i=0;i /sys/fs/cgroup/blkio/a/cgroup.procs dd if=/dev/loop0 bs=4k count=1 of=/dev/null iflag=direct 2> /dev/null echo 0 > /sys/fs/cgroup/blkio/cgroup.procs rmdir /sys/fs/cgroup/blkio/a grep blkio /proc/cgroups done ##TESTCASE_E

[PATCH] bfq: fix blkio cgroup leakage

ck/loop0/queue/scheduler grep blkio /proc/cgroups for ((i=0;i /sys/fs/cgroup/blkio/a/cgroup.procs dd if=/dev/loop0 bs=4k count=1 of=/dev/null iflag=direct 2> /dev/null echo 0 > /sys/fs/cgroup/blkio/cgroup.procs rmdir /sys/fs/cgroup/blkio/a grep blkio /proc/cgroups done ##TESTCASE_E

Re: [PATCH 0/9] block: T10/DIF Fixes and cleanups v3

Christoph Hellwig writes: > Hi Dmitry, > > can you resend this series? Sorry for a very long delay, I'm in the middle of honeymoon and this is not a good time for a work :) > I really think we should get this into 4.12 at least. Please see updated version in the LKML list.

Re: [PATCH 3/9] bio-integrity: bio_integrity_advance must update integrity seed

"Martin K. Petersen" writes: > Dmitry Monakhov writes: > >> SCSI drivers do care about bip_seed so we must update it accordingly. > >> +bip->bip_iter.bi_sector += bytes_done >> 9; > > This needs to count protection intervals. Otherwise things w

Re: [PATCH 1/5] bh: Prevent panic on invalid BHs

Christoph Hellwig writes: > This look ok, but how did you manage to trigger this case? # testcases # TEST1 # Via bug in fallocate truncate -l 1G img losetup /dev/loop img mkfs.ext4 -qF /dev/loop0 mkdir m mount /dev/loop0 m # command above truncate bdevs pagecache xfs_io -c "falloc -k 0 32G" -d

Re: [PATCH 5/5] block: truncate page cache only when necessary on fallocate

MHO (mode == FALLOC_FL_KEEP_SIZE) is sane API for thin-provision blkdevs to preallocate space in advance. Nobody use it at the moment, but it may be usefull in future. > > On Thu, Apr 06, 2017 at 04:02:49PM +0400, Dmitry Monakhov wrote: >> Signed-off-by: Dmitry Monakhov >> --- &

[PATCH 2/5] block: protect bdevname from null pointer bdev

Some callers (usually error paths) call bdevname with null bdev. Signed-off-by: Dmitry Monakhov --- block/partition-generic.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block/partition-generic.c b/block/partition-generic.c index 7afb990..284de18 100644 --- a/block/partition-generic.c

[PATCH 3/5] bio: Protect submit_bio from bdevless bio-s

Idially this type of check should be handled at generic_make_request_checks , but it is too late for bdevless bios, bad pointer was already dereferenced at that point. Signed-off-by: Dmitry Monakhov --- block/blk-core.c | 5 + 1 file changed, 5 insertions(+) diff --git a/block/blk-core.c b

[PATCH 1/5] bh: Prevent panic on invalid BHs

ard __find_get_block from null pointer bdev. Signed-off-by: Dmitry Monakhov --- fs/buffer.c | 24 +++- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index 9196f2a..4c8ce74 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1355,8 +1355,12 @@ lookup_bh_

[PATCH 5/5] block: truncate page cache only when necessary on fallocate

Signed-off-by: Dmitry Monakhov --- fs/block_dev.c | 9 - 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 2eca00e..f4b13e1 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -2075,7 +2075,7 @@ static long blkdev_fallocate(struct file

[PATCH 4/5] jbd2: use stable bdev pointer

This prevent us from panic if someone invalidate bh under us. Signed-off-by: Dmitry Monakhov --- fs/jbd2/revoke.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index f9aefcd..e3b791d 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c

[PATCH 0/5] falloc on blockdevice: what possibly can go whong?

If you saw a command "fallocate -k -l 1G /dev/vda" you probably think that user want to preallocate space on thin-provision blkdev. Right? What possibly can go wrong? Unfortunately you may destroy your filesystem and kernel panic. The reason is the bug in blkdev_fallocate() which unconditionally tr

[PATCH 1/9] bio-integrity: Do not allocate integrity context for bio w/o data

blkdev_issue_flush+0x7a/0x85 blkdev_fsync+0x35/0x42 vfs_fsync_range+0x8e/0x9f vfs_fsync+0x1c/0x1e do_fsync+0x31/0x4a SyS_fsync+0x10/0x14 entry_SYSCALL_64_fastpath+0x1f/0xc2 Reviewed-by: Christoph Hellwig Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 3 +++ 1 file changed, 3

[PATCH 3/9] bio-integrity: bio_integrity_advance must update integrity seed

SCSI drivers do care about bip_seed so we must update it accordingly. Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index b5009a8..82a6ffb 100644 --- a/block/bio-integrity.c +++ b/block

[PATCH 4/9] bio-integrity: fix interface for bio_integrity_trim v2

0, sectors == bio_sectors(bio) Let's just remove them completely. changes from v1: - remove 'sectors' arguments Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 11 ++- block/bio.c | 4 ++-- drivers/md/dm.c | 2 +- include/linux/bio.h | 5

[PATCH 8/9] bio: add bvec_iter rewind API

ts number of bytes iterator was advanced during it's evolution. Later end_io handler may easily restore original iterator by rewinding iterator to iter->bi_done. Note: this change makes sizeof (struct bvec_iter) multiple to 8 Signed-off-by: Dmitry Monakhov --- include/linux/bio.h | 21 ++

[PATCH 7/9] Guard bvec iteration logic v3

ecs, not others. This patch does: - Return error back to caller with hope that it will react on this - Truncate iterator size Code was added long time ago here 4550dd6c, luckily no one hit it in real life :) changes since V1: - Replace BUG_ON with error logic. Signed-off-by: Dmitry Monakho

[PATCH 6/9] T10: Move opencoded contants to common header

Signed-off-by: Dmitry Monakhov --- block/t10-pi.c | 9 +++-- drivers/scsi/lpfc/lpfc_scsi.c| 5 +++-- drivers/scsi/qla2xxx/qla_isr.c | 8 drivers/target/target_core_sbc.c | 2 +- include/linux/t10-pi.h | 2 ++ 5 files changed, 13 insertions(+), 13

[PATCH 9/9] bio-integrity: Restore original iterator on verify stage

ub.com/dmonakhov/xfstests/commit/3c6509eaa83b9c17cd0bc95d73fcdd76e1c54a85 Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 22 +++--- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index f2b9f09..f08096d 100644 --- a

[PATCH 5/9] bio-integrity: fold bio_integrity_enabled to bio_integrity_prep

le to fold it in to one function. Signed-off-by: Dmitry Monakhov --- Documentation/block/data-integrity.txt | 3 -- block/bio-integrity.c | 88 ++ block/blk-core.c | 5 +- block/blk-mq.c | 8 +--

[PATCH 0/9] block: T10/DIF Fixes and cleanups v3

This patch set fix various problems spotted during T10/DIF integrity machinery testing. TOC: ## Fix various bugs in T10/DIF/DIX infrastructure 0001-bio-integrity-Do-not-allocate-integrity-context-for 0002-bio-integrity-bio_trim-should-truncate-integrity-vec 0003-bio-integrity-bio_integrity_advanc

[PATCH 2/9] bio-integrity: bio_trim should truncate integrity vector accordingly

Reviewed-by: Christoph Hellwig Signed-off-by: Dmitry Monakhov --- block/bio.c | 4 1 file changed, 4 insertions(+) diff --git a/block/bio.c b/block/bio.c index e75878f..fa84323 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1907,6 +1907,10 @@ void bio_trim(struct bio *bio, int offset, int

Re: [PATCH 7/7] Guard bvec iteration logic v2

Ming Lei writes: > On Mon, Apr 3, 2017 at 3:23 PM, Dmitry Monakhov wrote: >> Currently if some one try to advance bvec beyond it's size we simply >> dump WARN_ONCE and continue to iterate beyond bvec array boundaries. >> This simply means that we endup dereferencin

Re: [PATCH 2/7] bio-integrity: save original iterator for verify stage

Christoph Hellwig writes: > This is a pretty big increase in the bio_integrity_payload size, > but I guess we can't get around it.. Yes, everybody hate this solution, me too, but I've stated with other approach and it is appeaded to be very ugly. My idea was that we have two types of iterator i

[PATCH 1/7] bio-integrity: Do not allocate integrity context for bio w/o data

blkdev_issue_flush+0x7a/0x85 blkdev_fsync+0x35/0x42 vfs_fsync_range+0x8e/0x9f vfs_fsync+0x1c/0x1e do_fsync+0x31/0x4a SyS_fsync+0x10/0x14 entry_SYSCALL_64_fastpath+0x1f/0xc2 Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/block

[PATCH 3/7] bio-integrity: bio_trim should truncate integrity vector accordingly

Signed-off-by: Dmitry Monakhov --- block/bio.c | 4 1 file changed, 4 insertions(+) diff --git a/block/bio.c b/block/bio.c index e75878f..fa84323 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1907,6 +1907,10 @@ void bio_trim(struct bio *bio, int offset, int size) bio_advance(bio

[PATCH 4/7] bio-integrity: fix interface for bio_integrity_trim

just remove it completely. TODO: add xfstests testcase here Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 8 +--- block/bio.c | 4 ++-- drivers/md/dm.c | 2 +- include/linux/bio.h | 5 ++--- 4 files changed, 6 insertions(+), 13 deletions(-) diff --git a/block/bi

[PATCH 2/7] bio-integrity: save original iterator for verify stage

bio->bi_iter.bi_size == 0 The simplest way to fix that is to save original data vector and treat is as immutable. Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 6 -- include/linux/bio.h | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/block/bio-integrity.c b/blo

[PATCH 5/7] bio-integrity: add bio_integrity_setup helper

Currently all integrity prep hooks are open-coded, and if prepare fails we ignore it's code and fail bio with EIO. Let's return real error to upper layer, so later caller may react accordingly. For example retry in case of ENOMEM. Signed-off-by: Dmitry Monakhov --- block/blk-core.

[PATCH 0/7] block: T10/DIF Fixes and cleanups v2

This patch set fix various problems spotted during T10/DIF integrity machinery testing. TOC: ## Fix various bugs in T10/DIF/DIX infrastructure 0001-bio-integrity-Do-not-allocate-integrity-context-for-fsync 0002-bio-integrity-save-original-iterator-for-verify-stage 0003-bio-integrity-bio_trim-shou

[PATCH 6/7] T10: Move opencoded contants to common header

Signed-off-by: Dmitry Monakhov --- block/t10-pi.c | 9 +++-- drivers/scsi/lpfc/lpfc_scsi.c| 5 +++-- drivers/scsi/qla2xxx/qla_isr.c | 8 drivers/target/target_core_sbc.c | 2 +- include/linux/t10-pi.h | 3 +++ 5 files changed, 14 insertions(+), 13

[PATCH 7/7] Guard bvec iteration logic v2

ecs, not others. This patch does: - Return error back to caller with hope that it will react on this - Truncate iterator size Code was added long time ago here 4550dd6c, luckily no one hit it in real life :) changes since V1: - Replace BUG_ON with error logic. Signed-off-by: Dmitry Monakho

[PATCH 3/8] bio-integrity: save original iterator for verify stage

bio->bi_iter.bi_size == 0 The simplest way to fix that is to save original data vector and treat is as immutable. Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 6 -- include/linux/bio.h | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/block/bio-integrity.c b/blo

[PATCH 4/8] bio-integrity: bio_trim should truncate integrity vector accordingly

Signed-off-by: Dmitry Monakhov --- block/bio.c | 4 1 file changed, 4 insertions(+) diff --git a/block/bio.c b/block/bio.c index e75878f..fa84323 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1907,6 +1907,10 @@ void bio_trim(struct bio *bio, int offset, int size) bio_advance(bio

[PATCH 7/8] T10: Move opencoded contants to common header

Signed-off-by: Dmitry Monakhov --- block/t10-pi.c | 9 +++-- drivers/scsi/lpfc/lpfc_scsi.c| 4 ++-- drivers/scsi/qla2xxx/qla_isr.c | 8 drivers/target/target_core_sbc.c | 2 +- include/linux/t10-pi.h | 3 +++ 5 files changed, 13 insertions(+), 13

[PATCH 5/8] bio-integrity: fix interface for bio_integrity_trim

just remove it completely. Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 8 +--- block/bio.c | 4 ++-- drivers/md/dm.c | 2 +- include/linux/bio.h | 5 ++--- 4 files changed, 6 insertions(+), 13 deletions(-) diff --git a/block/bio-integrity.c b/block/bio-in

[PATCH 1/8] Guard bvec iteration logic

life :) Signed-off-by: Dmitry Monakhov --- include/linux/bvec.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 89b65b8..86b914f 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -70,8 +70,7 @@ static inline

[PATCH 6/8] bio-integrity: add bio_integrity_setup helper

Currently all integrity prep hooks are open-coded, and if prepare fails we ignore it's code and fail bio with EIO. Let's return real error to upper layer, so later caller may react accordingly. For example retry in case of ENOMEM. Signed-off-by: Dmitry Monakhov --- block/blk-core.

[PATCH 8/8] tcm_fileio: Prevent information leak for short reads

/marc.info/?l=linux-scsi&m=149087996913448&w=2 Signed-off-by: Dmitry Monakhov --- drivers/target/target_core_file.c | 21 +++-- 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 87aa3

[PATCH 2/8] bio-integrity: Do not allocate integrity context for bio w/o data

blkdev_issue_flush+0x7a/0x85 blkdev_fsync+0x35/0x42 vfs_fsync_range+0x8e/0x9f vfs_fsync+0x1c/0x1e do_fsync+0x31/0x4a SyS_fsync+0x10/0x14 entry_SYSCALL_64_fastpath+0x1f/0xc2 Signed-off-by: Dmitry Monakhov --- block/bio-integrity.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/block

[PATCH 0/8] block: T10/DIF Fixes and cleanups

This patch set fix various problems spotted during T10/DIF integrity machinery testing. TOC: ## General bulletproof protection for block layer 0001 Guard bvec iteration logic ## Fix various bugs in T10/DIF/DIX infrastructure 0002 bio integrity: Do not allocate integrity context for 0003 bio inte

Re: scsi_debug: shared dev context, BUG or FEATURE?

"Martin K. Petersen" writes: > Dmitry Monakhov writes: > > Dmitry, > >> scsi_debug has very strange structure from one point it supports >> dynamic number of devices but from other point context is common for >> all devices: > >> So basically w

scsi_debug: shared dev context, BUG or FEATURE?

Hi scsi_debug has very strange structure from one point it supports dynamic number of devices but from other point context is common for all devices: - dif_storep (array of t10 dif tuples) - map_storep (block map for thinprovision) - fake_storep (in memory data storage) - sdebug_q_arr (queue ar

[PATCH] block: Invalidate cache on discard v2

It is reasonable drop page cache on discard, otherwise that pages may be written by writeback second later, so thin provision devices will not be happy. This seems to be a security leak in case of secure discard case. Also add check for queue_discard flag on early stage. Signed-off-by: Dmitry

[PATCH] block: Invalidate cache on discard

It is reasonable drop page cache on discard, otherwise that pages may be written by writeback second later, so thin provision devices will not be happy. This seems to be a security leak in case of secure discard case. Also add check for queue_discard flag on early stage. Signed-off-by: Dmitry

[PATCH 1/2] tools: format octets properly

Currently "%o" not parsed properly and printed as '>o<' # perf record -e ext4:ext4* touch new_file; perf script | grep "mode" Signed-off-by: Dmitry Monakhov --- tools/lib/traceevent/event-parse.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/lib/t

[PATCH 2/2] perf: dump warning on unknown formaters

This will help us to catch missed format specifiers much quicker. Signed-off-by: Dmitry Monakhov --- tools/lib/traceevent/event-parse.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 27dc1f8..546a0f9 100644

Re: [PATCH 6/6] Add dockerfile

Theodore Ts'o writes: > On Sun, Aug 21, 2016 at 03:02:38PM +0300, Dmitry Monakhov wrote: >> Probably it it reasonable to create dedicated directory ./docker >> and place all docker related crap there: >> # build scripts >> docker/Dockerfile.build-env >> d

Re: [PATCH 6/6] Add dockerfile

Theodore Ts'o writes: > On Sat, Aug 20, 2016 at 02:31:26PM +0300, Dmitry Monakhov wrote: >> > I'm not sure I see the advantage of doing this in a container, I >> > guess. I just do in my standard laptop environment today. >> I can not because I laptop

Re: [PATCH 6/6] Add dockerfile

Theodore Ts'o writes: > On Fri, Aug 19, 2016 at 12:27:43PM +0300, Dmitry Monakhov wrote: >> Actually main idea is to have build environment for xfstests-bld development >> plus automatic builds gives us CI. This is important because >> xfstests-blk build is silently

Re: [PATCH 6/6] Add dockerfile

Theodore Ts'o writes: > On Fri, Aug 19, 2016 at 12:54:11AM +0400, Dmitry Monakhov wrote: >> Dockerfile is good way to create build environments >> Let's keep it as a reference build script. >> >> XXX: Currently Ted does not have hub.docker account >>

[PATCH] nbd: ratelimit error messages from disconnected devices

ndb can be explicitly disconnected via NBD_DISCONNECT while active user still exists this result in massive spam to logs. Let's ratelimits such messages. Signed-off-by: Dmitry Monakhov --- drivers/block/nbd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/dr

Re: [PATCH] kvm: do not SetPageDirty from kvm_set_pfn_dirty for file mappings

Maxim Patlasov writes: > The patch solves the following problem: file system specific routines > involved in ordinary routine writeback process BUG_ON page_buffers() > because a page goes to writeback without buffer-heads attached. > > The way how kvm_set_pfn_dirty calls SetPageDirty works only f

Re: Another proposal for DAX fault locking

Jan Kara writes: > Hello, > > I was thinking about current issues with DAX fault locking [1] (data > corruption due to racing faults allocating blocks) and also races which > currently don't allow us to clear dirty tags in the radix tree due to races > between faults and cache flushing [2]. Both

Re: [PATCH v8 6/9] dax: add support for fsync/msync

Ross Zwisler writes: > To properly handle fsync/msync in an efficient way DAX needs to track dirty > pages so it is able to flush them durably to media on demand. Please see coments below > > The tracking of dirty pages is done via the radix tree in struct > address_space. This radix tree is alr

[PATCH] dax: dirty inode only if required

Signed-off-by: Dmitry Monakhov --- fs/dax.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/dax.c b/fs/dax.c index e0e9358..fc2e314 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -358,7 +358,8 @@ static int dax_radix_entry(struct address_space *mapping, pgoff_t index

Re: could you respin the "add blkdev name format specifier" series?

Al Viro writes: > It had been posted back in April and got acked by Jan; I'm also > fine with it and I'd like to apply at least generic + fs/* parts. Could > you rebase it to the current mainline and post it? Ok, in progress. signature.asc Description: PGP signature

Re: submit bio directly from userspace

Mike Krinkin writes: > Hi, > > i'm developing block layer workload simulator/player and need to > generate bios as close as possible to the ones in original workload. > To play workload i employ aio + O_DIRECT, but all IOs end up as bios > with SYNC flag set. So i wonder is there any way to cont

Re: [RFC v3 1/4] fs: Add generic file system event notifications

Beata Michalska writes: > Introduce configurable generic interface for file > system-wide event notifications, to provide file > systems with a common way of reporting any potential > issues as they emerge. > > The notifications are to be issued through generic > netlink interface by newly introd

Re: [PATCH] blk: optimize blk_trace macros for cgroup case PING..

Hi Jens, do you have any objections against this patch? Please let me know if you have any and I'll fix it. Dmitry Monakhov writes: > Usually blk_trace is not active, but cfq_log_xxx macros unconditionally > prepare cgroup path via blkg_path() which is suboptimal. This provoke &g

[PATCH 5/7] md: use block_device name vsprintf helper v2

changes from V1: -fix use bio after free on raid10 error path (spotted by Jan Kara) Signed-off-by: Dmitry Monakhov --- drivers/md/bcache/debug.c|6 +- drivers/md/bcache/io.c |8 +-- drivers/md/bcache/super.c| 32 -- drivers/md/dm-cache-target.c |5

[PATCH 7/7] drivers: use block_device name vsprintf helper

Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov --- drivers/block/drbd/drbd_req.c |6 ++ drivers/block/pktcdvd.c | 14 -- drivers/scsi/wd7000.c |6 +- drivers/target/target_core_iblock.c |4 +--- 4 files changed, 8

[PATCH 3/7] block: use block_device name vsprintf helper

Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov --- block/blk-core.c | 30 -- block/blk-settings.c |9 ++--- 2 files changed, 14 insertions(+), 25 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 794c3e7..88a4c94 100644 --- a

[PATCH 4/7] fs: use block_device name vsprintf helper

Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov --- fs/btrfs/super.c |4 +--- fs/buffer.c | 21 ++--- fs/ext2/xattr.c |6 ++ fs/ext3/super.c |5 ++--- fs/ext3/xattr.c |5 ++--- fs/ext4/page-io.c |5 ++--- fs

[PATCH 1/7] fs: use gendisk->disk_name where possible

gendisk with part==0 is obviously gendisk->disk_name. Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov --- fs/block_dev.c | 12 +++- 1 files changed, 3 insertions(+), 9 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index c7e4163..874a8d1 100644 --- a/fs/block_de

[PATCH 6/7] block/partitions: use block_device name vsprintf helper

Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov --- block/partition-generic.c |3 ++- block/partitions/amiga.c | 13 ++--- block/partitions/sgi.c|9 - block/partitions/sun.c|9 - 4 files changed, 16 insertions(+), 18 deletions(-) diff --git a

[PATCH 2/7] lib/vsprintf: add %*pg format specifier

This allow to directly print block_device name. Currently one should use bdevname() with temporal char buffer. This is very ineffective because bloat stack usage for deep IO call-traces Example: %pg ->sda, sda1 or loop0p1 Reviewed-by: Jan Kara Signed-off-by: Dmitry Monak

[PATCH 0/7] fs: add blkdev name format specifier v2

Currently in order to print block_device name one should use blkdev() helper which requires temproral buffer of size BDEVNAME_SIZE (32bytes). This is very ineffective because result in stack usage bloating for deep IO call traces where stack usage is close to maximum values. It is reasonable to i

[PATCH 1/7] fs: use gendisk->disk_name where possible

gendisk with part==0 is obviously gendisk->disk_name. Signed-off-by: Dmitry Monakhov --- fs/block_dev.c | 12 +++- 1 files changed, 3 insertions(+), 9 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 79b4fa3..f123b02 100644 --- a/fs/block_dev.c +++ b/fs/block_de

[PATCH 4/7] fs: use block_device name vsprintf helper

Signed-off-by: Dmitry Monakhov --- fs/btrfs/super.c |4 +--- fs/buffer.c | 21 ++--- fs/ext2/xattr.c |6 ++ fs/ext3/super.c |5 ++--- fs/ext3/xattr.c |5 ++--- fs/ext4/page-io.c |5 ++--- fs/ext4/xattr.c |6

[PATCH 0/7] fs: add blkdev name format specifier v2

Currently in order to print block_device name one should use blkdev() helper which requires temproral buffer of size BDEVNAME_SIZE (32bytes). This is very ineffective because result in stack usage bloating for deep IO call traces where stack usage is close to maximum values. It is reasonable to i

[PATCH 6/7] block/partitions: use block_device name vsprintf helper v2

- bdevname() now works via "%pg" format specifier (in responce to Joe's comments) Signed-off-by: Dmitry Monakhov --- block/partition-generic.c |3 ++- block/partitions/amiga.c | 13 ++--- block/partitions/sgi.c|9 - block/partitions/sun.c|

[PATCH 2/7] lib/vsprintf: add %*pg format specifier

This allow to directly print block_device name. Currently one should use bdevname() with temporal char buffer. This is very ineffective because bloat stack usage for deep IO call-traces Example: %pg ->sda, sda1 or loop0p1 Signed-off-by: Dmitry Monakhov --- Documentation/pri

[PATCH 3/7] block: use block_device name vsprintf helper

Signed-off-by: Dmitry Monakhov --- block/blk-core.c | 30 -- block/blk-settings.c |9 ++--- 2 files changed, 14 insertions(+), 25 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 794c3e7..88a4c94 100644 --- a/block/blk-core.c +++ b

[PATCH 5/7] md: use block_device name vsprintf helper

Signed-off-by: Dmitry Monakhov --- drivers/md/bcache/debug.c|6 +- drivers/md/bcache/io.c |8 +-- drivers/md/bcache/super.c| 32 -- drivers/md/dm-cache-target.c |5 +- drivers/md/dm-table.c| 32 - drivers/md/dm-thin.c |8

[PATCH 7/7] drivers: use block_device name vsprintf helper

Signed-off-by: Dmitry Monakhov --- drivers/block/drbd/drbd_req.c |6 ++ drivers/block/pktcdvd.c | 14 -- drivers/scsi/wd7000.c |6 +- drivers/target/target_core_iblock.c |4 +--- 4 files changed, 8 insertions(+), 22 deletions

Re: [PATCH 1/2] pipe: fix race with fcntl

Al Viro writes: > On Sun, Apr 12, 2015 at 09:08:21PM +0400, Dmitry Monakhov wrote: >> Fix other long standing issues caused by fcntl(,F_SETFL,): >> - User can disable O_DIRECT for pipe[1] (paketized IO), but can not enable >> it again. >> - Currently we do not set O

[PATCH 2/2] splice: fix race beween splice_write vs fcntl

nd flag after kiocb was constructed (where ->ki_flags is stable), for that reason we should use special analog of vfs_write_iter() which asserts non-append behaviour. Signed-off-by: Dmitry Monakhov --- fs/splice.c | 23 ++- 1 files changed, 22 insertions(+), 1 deletions(

[PATCH 0/2] fs: make pipe/splice fcntl safe

Al Viro already made most vfs/write_iters fcntl safe, but pipe and splice are still affected. Patchset against vfs.git#for-next f1d36c2d711166aaa84f37 TOC: 0001-pipe-fix-race-with-fcntl 0002-splice-fix-race-beween-splice_write-vs-fcntl -- To unsubscribe from this list: send the line "unsubscribe li

[PATCH 1/2] pipe: fix race with fcntl

end's of pipe. Add ->check_flags method in order to diallow O_APPEND toggling. Signed-off-by: Dmitry Monakhov --- fs/fcntl.c |6 -- fs/pipe.c | 16 +--- 2 files changed, 17 insertions(+), 5 deletions(-) diff --git a/fs/fcntl.c b/fs/fcntl.c index ee85cd4..0bdc9c

Re: [PATCH 1/6] block: add support for carrying a stream ID in a bio

Dave Chinner writes: > On Tue, Mar 24, 2015 at 09:26:58AM -0600, Jens Axboe wrote: >> The top bits of bio->bi_flags are reserved for keeping the >> allocation pool, set aside the next four bits for carrying >> a stream ID. That leaves us with support for 15 streams, >> 0 is reserved as a "stream

[PATCH] blk: optimize blk_trace macros for cgroup case

t=1 --group_reporting --filename=/dev/nullb0 \ --rw=write --iodepth=64 --bs=4k --numjobs=8 --size=4G | | baseline | w/ patch | gain | | WR iops | 161483 | 189989 | +17% | | stddev |14.36 |13.19 | | Signed-off-by: Dmitry Monakhov --- block/blk-throttle.c |

Re: [PATCH 2/7] Add support for per-file stream ID

Jens Axboe writes: One small question. You states that all IDs are equals but can we reserve some IDs for internal kernel purposes. For example very short lived data (files opened with O_TEMP) and so on. Also small nitpicking see below. > Writing on flash devices can be much more efficient, if w

Re: [PATCH 02/16] vfs: check kiocb->ki_flags instead filp->fl_flags

Al Viro writes: > On Sat, Apr 04, 2015 at 11:13:11PM +0400, Dmitry Monakhov wrote: >> generic_write_checks now accept kiocb as an argument >> Unfortunetly it is impossible to get rid of old interface because some crappy >> do not support write_iter interface so leave __ge

[PATCH 02/16] vfs: check kiocb->ki_flags instead filp->fl_flags

generic_write_checks now accept kiocb as an argument Unfortunetly it is impossible to get rid of old interface because some crappy do not support write_iter interface so leave __generic_write_checks as backward compatibility helper. Signed-off-by: Dmitry Monakhov --- include/linux/fs.h |8

  1   2   3   >