Zhang Wensheng [Thu, 10 Mar 2022 09:32:24 +0000 (17:32 +0800)]
nbd: fix possible overflow on 'first_minor' in nbd_dev_add()
When 'index' is a big numbers, it may become negative which forced
to 'int'. then 'index << part_shift' might overflow to a positive
value that is not greater than '0xfffff', then sysfs might complains
about duplicate creation. Because of this, move the 'index' judgment
to the front will fix it and be better.
Fixes: 3d709b092efb ("nbd: use an idr to keep track of nbd devices") Fixes: 759c2f288f48 ("nbd: fix possible overflow for 'first_minor' in nbd_dev_add()") Signed-off-by: Zhang Wensheng <zhangwensheng5@huawei.com> Reviewed-by: Josef Bacik <josef@toxicpanda.com> Link: https://lore.kernel.org/r/20220310093224.4002895-1-zhangwensheng5@huawei.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
In light of the recent controversy surrounding the (lack of)
maintenance of the in-tree DRBD driver, we have decided to add myself
as co-maintainer. This allows us to better distribute the workload and
reduce the chance of patches getting lost.
I will be keeping an eye on the mailing list in order to ensure that all
patches get the attention they need.
Lars Ellenberg [Wed, 30 Mar 2022 18:55:51 +0000 (20:55 +0200)]
drbd: fix potential silent data corruption
Scenario:
---------
bio chain generated by blk_queue_split().
Some split bio fails and propagates its error status to the "parent" bio.
But then the (last part of the) parent bio itself completes without error.
We would clobber the already recorded error status with BLK_STS_OK,
causing silent data corruption.
Reproducer:
-----------
How to trigger this in the real world within seconds:
DRBD on top of degraded parity raid,
small stripe_cache_size, large read_ahead setting.
Drop page cache (sysctl vm.drop_caches=1, fadvise "DONTNEED",
umount and mount again, "reboot").
Cause significant read ahead.
Large read ahead request is split by blk_queue_split().
Parts of the read ahead that are already in the stripe cache,
or find an available stripe cache to use, can be serviced.
Parts of the read ahead that would need "too much work",
would need to wait for a "stripe_head" to become available,
are rejected immediately.
For larger read ahead requests that are split in many pieces, it is very
likely that some "splits" will be serviced, but then the stripe cache is
exhausted/busy, and the remaining ones will be rejected.
Carlos Llamas [Tue, 29 Mar 2022 20:18:15 +0000 (20:18 +0000)]
loop: fix ioctl calls using compat_loop_info
Support for cryptoloop was deleted in commit 4edc575348fd ("block:
remove support for cryptoloop and the xor transfer"), making the usage
of loop_info->lo_encrypt_type obsolete. However, this member was also
removed from the compat_loop_info definition and this breaks userspace
ioctl calls for 32-bit binaries and CONFIG_COMPAT=y.
This patch restores the compat_loop_info->lo_encrypt_type member and
marks it obsolete as well as in the uapi header definitions.
Fixes: 4edc575348fd ("block: remove support for cryptoloop and the xor transfer") Signed-off-by: Carlos Llamas <cmllamas@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/20220329201815.1347500-1-cmllamas@google.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 29 Mar 2022 12:22:38 +0000 (06:22 -0600)]
Merge tag 'nvme-5.18-2022-03-29' of git://git.infradead.org/nvme into for-5.18/drivers
Pull NVMe fixes from Christoph:
"- fix multipath hang when disk goes live over reconnect (Anton Eidelman)
- fix RCU hole that allowed for endless looping in multipath round robin
(Chris Leech)
- remove redundant assignment after left shift (Colin Ian King)
- add quirks for Samsung X5 SSDs (Monish Kumar R)
- fix the read-only state for zoned namespaces with unsupposed features
(Pankaj Raghav)
- use a private workqueue instead of the system workqueue in nvmet
(Sagi Grimberg)
- allow duplicate NSIDs for private namespaces (Sungup Moon)
- expose use_threaded_interrupts read-only in sysfs (Xin Hao)"
* tag 'nvme-5.18-2022-03-29' of git://git.infradead.org/nvme:
nvme-multipath: fix hang when disk goes live over reconnect
nvme: fix RCU hole that allowed for endless looping in multipath round robin
nvme: allow duplicate NSIDs for private namespaces
nvmet: remove redundant assignment after left shift
nvmet: use a private workqueue instead of the system workqueue
nvme-pci: add quirks for Samsung X5 SSDs
nvme-pci: expose use_threaded_interrupts read-only in sysfs
nvme: fix the read-only state for zoned namespaces with unsupposed features
Anton Eidelman [Thu, 24 Mar 2022 19:05:11 +0000 (13:05 -0600)]
nvme-multipath: fix hang when disk goes live over reconnect
nvme_mpath_init_identify() invoked from nvme_init_identify() fetches a
fresh ANA log from the ctrl. This is essential to have an up to date
path states for both existing namespaces and for those scan_work may
discover once the ctrl is up.
This happens in the following cases:
1) A new ctrl is being connected.
2) An existing ctrl is successfully reconnected.
3) An existing ctrl is being reset.
While in (1) ctrl->namespaces is empty, (2 & 3) may have namespaces, and
nvme_read_ana_log() may call nvme_update_ns_ana_state().
This result in a hang when the ANA state of an existing namespace changes
and makes the disk live: nvme_mpath_set_live() issues IO to the namespace
through the ctrl, which does NOT have IO queues yet.
See sample hang below.
Solution:
- nvme_update_ns_ana_state() to call set_live only if ctrl is live
- nvme_read_ana_log() call from nvme_mpath_init_identify()
therefore only fetches and parses the ANA log;
any erros in this process will fail the ctrl setup as appropriate;
- a separate function nvme_mpath_update()
is called in nvme_start_ctrl();
this parses the ANA log without fetching it.
At this point the ctrl is live,
therefore, disks can be set live normally.
Chris Leech [Mon, 21 Mar 2022 22:43:04 +0000 (15:43 -0700)]
nvme: fix RCU hole that allowed for endless looping in multipath round robin
Make nvme_ns_remove match the assumptions elsewhere.
1) !NVME_NS_READY needs to be srcu synchronized to make sure nothing is
running in __nvme_find_path or nvme_round_robin_path that will
re-assign this ns to current_path.
2) Any matching current_path entries need to be cleared before removing
from the siblings list, to prevent calling nvme_round_robin_path with
an "old" ns that's off list.
3) Finally the list_del_rcu can happen, and then synchronize again
before releasing any reference counts.
Sungup Moon [Mon, 14 Mar 2022 11:05:45 +0000 (20:05 +0900)]
nvme: allow duplicate NSIDs for private namespaces
A NVMe subsystem with multiple controller can have private namespaces
that use the same NSID under some conditions:
"If Namespace Management, ANA Reporting, or NVM Sets are supported, the
NSIDs shall be unique within the NVM subsystem. If the Namespace
Management, ANA Reporting, and NVM Sets are not supported, then NSIDs:
a) for shared namespace shall be unique; and
b) for private namespace are not required to be unique."
Colin Ian King [Fri, 18 Mar 2022 01:30:14 +0000 (01:30 +0000)]
nvmet: remove redundant assignment after left shift
The left shift is followed by a re-assignment back to cc_css, the
assignment is redundant. Fix this by replacing the "<<=" operator with
"<<" instead.
This cleans up the clang scan build warning:
drivers/nvme/target/core.c:1124:10: warning: Although the value stored to 'cc_css' is used in the enclosing expression, the value is never actually read from 'cc_css' [deadcode.DeadStores]
Signed-off-by: Colin Ian King <colin.i.king@gmail.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Sagi Grimberg [Mon, 21 Mar 2022 11:57:27 +0000 (13:57 +0200)]
nvmet: use a private workqueue instead of the system workqueue
Any attempt to flush kernel-global WQs has possibility of deadlock
so we should simply stop using them, instead introduce nvmet_wq
which is the generic nvmet workqueue for work elements that
don't explicitly require a dedicated workqueue (by the mere fact
that they are using the system_wq).
Pankaj Raghav [Tue, 22 Mar 2022 09:20:48 +0000 (10:20 +0100)]
nvme: fix the read-only state for zoned namespaces with unsupposed features
commit c3f71a6072cd ("nvme: export zoned namespaces without Zone Append
support read-only") marks zoned namespaces without append support
read-only. It does iso by setting NVME_NS_FORCE_RO in ns->flags in
nvme_update_zone_info and checking for that flag later in
nvme_update_disk_info to mark the disk as read-only.
But commit d2b3e8601a3b ("nvme: cleanup zone information initialization")
rearranged nvme_update_disk_info to be called before
nvme_update_zone_info and thus not marking the disk as read-only.
The call order cannot be just reverted because nvme_update_zone_info sets
certain queue parameters such as zone_write_granularity that depend on the
prior call to nvme_update_disk_info.
Remove the call to set_disk_ro in nvme_update_disk_info. and call
set_disk_ro after nvme_update_zone_info and nvme_update_disk_info to set
the permission for ZNS drives correctly. The same applies to the
multipath disk path.
Fixes: d2b3e8601a3b ("nvme: cleanup zone information initialization") Signed-off-by: Pankaj Raghav <p.raghav@samsung.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Jackie Liu [Mon, 21 Mar 2022 07:12:16 +0000 (15:12 +0800)]
n64cart: convert bi_disk to bi_bdev->bd_disk fix build
My kernel robot report below:
drivers/block/n64cart.c: In function ‘n64cart_submit_bio’:
drivers/block/n64cart.c:91:26: error: ‘struct bio’ has no member named ‘bi_disk’
91 | struct device *dev = bio->bi_disk->private_data;
| ^~
CC drivers/slimbus/qcom-ctrl.o
CC drivers/auxdisplay/hd44780.o
CC drivers/watchdog/watchdog_core.o
CC drivers/nvme/host/fault_inject.o
AR drivers/accessibility/braille/built-in.a
make[2]: *** [scripts/Makefile.build:288: drivers/block/n64cart.o] Error 1
Fixes: 15f21b295a4d ("block: store a block_device pointer in struct bio"); Reported-by: k2ci <kernel-bot@kylinos.cn> Signed-off-by: Jackie Liu <liuyun01@kylinos.cn> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> Link: https://lore.kernel.org/r/20220321071216.1549596-1-liu.yun@linux.dev Signed-off-by: Jens Axboe <axboe@kernel.dk>
Colin Ian King [Thu, 17 Mar 2022 23:46:46 +0000 (23:46 +0000)]
xen-blkback: remove redundant assignment to variable i
Variable i is being assigned a value that is never read, it is being
re-assigned later in a for-loop. The assignment is redundant and can
be removed.
Cleans up clang scan build warning:
drivers/block/xen-blkback/blkback.c:934:14: warning: Although the value
stored to 'i' is used in the enclosing expression, the value is never
actually read from 'i' [deadcode.DeadStores]
Jens Axboe [Fri, 18 Mar 2022 02:46:22 +0000 (20:46 -0600)]
Merge tag 'nvme-5.18-2022-03-17' of git://git.infradead.org/nvme into for-5.18/drivers
Pull NVMe updates from Christoph:
"Second round of nvme updates for Linux 5.18
- add lockdep annotations for in-kernel sockets (Chris Leech)
- use vmalloc for ANA log buffer (Hannes Reinecke)
- kerneldoc fixes (Chaitanya Kulkarni)
- cleanups (Guoqing Jiang, Chaitanya Kulkarni, me)
- warn about shared namespaces without multipathing (me)"
* tag 'nvme-5.18-2022-03-17' of git://git.infradead.org/nvme:
nvme: warn about shared namespaces without CONFIG_NVME_MULTIPATH
nvme: remove nvme_alloc_request and nvme_alloc_request_qid
nvme: cleanup how disk->disk_name is assigned
nvmet: move the call to nvmet_ns_changed out of nvmet_ns_revalidate
nvmet: use snprintf() with PAGE_SIZE in configfs
nvmet: don't fold lines
nvmet-rdma: fix kernel-doc warning for nvmet_rdma_device_removal
nvmet-fc: fix kernel-doc warning for nvmet_fc_unregister_targetport
nvmet-fc: fix kernel-doc warning for nvmet_fc_register_targetport
nvme-tcp: lockdep: annotate in-kernel sockets
nvme-tcp: don't fold the line
nvme-tcp: don't initialize ret variable
nvme-multipath: call bio_io_error in nvme_ns_head_submit_bio
nvme-multipath: use vmalloc for ANA log buffer
Eliminate anonymous module_init() and module_exit(), which can lead to
confusion or ambiguity when reading System.map, crashes/oops/bugs,
or an initcall_debug log.
Give each of these init and exit functions unique driver-specific
names to eliminate the anonymous names.
Example 2: (initcall_debug log)
calling init+0x0/0x12 @ 1
initcall init+0x0/0x12 returned 0 after 15 usecs
calling init+0x0/0x60 @ 1
initcall init+0x0/0x60 returned 0 after 2 usecs
calling init+0x0/0x9a @ 1
initcall init+0x0/0x9a returned 0 after 74 usecs
Fixes: 7ce92704e0e1 ("Block driver using virtio.") Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Stefan Hajnoczi <stefanha@redhat.com> Cc: virtualization@lists.linux-foundation.org Cc: Jens Axboe <axboe@kernel.dk> Cc: linux-block@vger.kernel.org Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Jason Wang <jasowang@redhat.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/20220316192010.19001-2-rdunlap@infradead.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
nvmet: move the call to nvmet_ns_changed out of nvmet_ns_revalidate
nvmet_ns_changed states via lockdep that the ns->subsys->lock must be
held. The only caller of nvmet_ns_changed which does not acquire that
lock is nvmet_ns_revalidate. nvmet_ns_revalidate has 3 callers,
of which 2 do not acquire that lock: nvmet_execute_identify_cns_cs_ns
and nvmet_execute_identify_ns. The other caller
nvmet_ns_revalidate_size_store does acquire the lock.
Move the call to nvmet_ns_changed from nvmet_ns_revalidate to the callers
so that they can perform the correct locking as needed.
This issue was found using a static type-based analyser and manually
verified.
nvmet-fc: fix kernel-doc warning for nvmet_fc_unregister_targetport
This fixes following kernel-doc warning:-
drivers/nvme/target/fc.c:1619: warning: expecting prototype for nvme_fc_unregister_targetport(). Prototype was for nvmet_fc_unregister_targetport() instead
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
nvmet-fc: fix kernel-doc warning for nvmet_fc_register_targetport
This fixes following kernel-doc warning :-
drivers/nvme/target/fc.c:1365: warning: expecting prototype for nvme_fc_register_targetport(). Prototype was for nvmet_fc_register_targetport() instead
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Chris Leech [Wed, 16 Feb 2022 02:22:49 +0000 (18:22 -0800)]
nvme-tcp: lockdep: annotate in-kernel sockets
Put NVMe/TCP sockets in their own class to avoid some lockdep warnings.
Sockets created by nvme-tcp are not exposed to user-space, and will not
trigger certain code paths that the general socket API exposes.
Lockdep complains about a circular dependency between the socket and
filesystem locks, because setsockopt can trigger a page fault with a
socket lock held, but nvme-tcp sends requests on the socket while file
system locks are held.
======================================================
WARNING: possible circular locking dependency detected
5.15.0-rc3 #1 Not tainted
------------------------------------------------------
fio/1496 is trying to acquire lock:
(sk_lock-AF_INET){+.+.}-{0:0}, at: tcp_sendpage+0x23/0x80
but task is already holding lock:
(&xfs_dir_ilock_class/5){+.+.}-{3:3}, at: xfs_ilock+0xcf/0x290 [xfs]
Hannes Reinecke [Wed, 9 Mar 2022 13:29:00 +0000 (14:29 +0100)]
nvme-multipath: use vmalloc for ANA log buffer
The ANA log buffer can get really large, as it depends on the
controller configuration. So to avoid an out-of-memory issue
during scanning use kvmalloc() instead of the kmalloc().
Signed-off-by: Hannes Reinecke <hare@suse.de> Tested-by: Daniel Wagner <dwagner@suse.de> Signed-off-by: Daniel Wagner <dwagner@suse.de> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Juergen Gross [Fri, 11 Mar 2022 10:35:27 +0000 (11:35 +0100)]
xen/blkfront: speed up purge_persistent_grants()
purge_persistent_grants() is scanning the grants list for persistent
grants being no longer in use by the backend. When having found such a
grant, it will be set to "invalid" and pushed to the tail of the list.
Instead of pushing it directly to the end of the list, add it first to
a temporary list, avoiding to scan those entries again in the main
list traversal. After having finished the scan, append the temporary
list to the grant list.
Suggested-by: Jan Beulich <jbeulich@suse.com> Signed-off-by: Juergen Gross <jgross@suse.com> Reviewed-by: Roger Pau Monné <roger.pau@citrix.com> Reviewed-by: Jan Beulich <jbeulich@suse.com> Link: https://lore.kernel.org/r/20220311103527.12931-1-jgross@suse.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 10 Mar 2022 23:04:03 +0000 (16:04 -0700)]
Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.18/drivers
Pull MD updates from Song:
"This set contains raid5 bio handling cleanups for raid5."
* 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
raid5: initialize the stripe_head embeeded bios as needed
raid5-cache: statically allocate the recovery ra bio
raid5-cache: fully initialize flush_bio when needed
raid5-ppl: fully initialize the bio in ppl_new_iounit
Jens Axboe [Tue, 8 Mar 2022 23:40:12 +0000 (16:40 -0700)]
Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.18/drivers
Pull MD fixes from Song:
"Most of these changes are minor fixes and clean-ups."
* 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
md: use msleep() in md_notify_reboot()
lib/raid6: Include <asm/ppc-opcode.h> for VPERMXOR
lib/raid6/test/Makefile: Use $(pound) instead of \# for Make 4.3
lib/raid6/test: fix multiple definition linking error
md: raid1/raid10: drop pending_cnt
Paul Menzel [Tue, 8 Feb 2022 15:21:48 +0000 (16:21 +0100)]
lib/raid6/test/Makefile: Use $(pound) instead of \# for Make 4.3
Buidling raid6test on Ubuntu 21.10 (ppc64le) with GNU Make 4.3 shows the
errors below:
$ cd lib/raid6/test/
$ make
<stdin>:1:1: error: stray ‘\’ in program
<stdin>:1:2: error: stray ‘#’ in program
<stdin>:1:11: error: expected ‘=’, ‘,’, ‘;’, ‘asm’ or ‘__attribute__’ \
before ‘<’ token
[...]
The errors come from the HAS_ALTIVEC test, which fails, and the POWER
optimized versions are not built. That’s also reason nobody noticed on the
other architectures.
GNU Make 4.3 does not remove the backslash anymore. From the 4.3 release
announcment:
> * WARNING: Backward-incompatibility!
> Number signs (#) appearing inside a macro reference or function invocation
> no longer introduce comments and should not be escaped with backslashes:
> thus a call such as:
> foo := $(shell echo '#')
> is legal. Previously the number sign needed to be escaped, for example:
> foo := $(shell echo '\#')
> Now this latter will resolve to "\#". If you want to write makefiles
> portable to both versions, assign the number sign to a variable:
> H := \#
> foo := $(shell echo '$H')
> This was claimed to be fixed in 3.81, but wasn't, for some reason.
> To detect this change search for 'nocomment' in the .FEATURES variable.
So, do the same as commit a9a62b426c5b ("Kbuild: fix # escaping in .cmd
files for future Make") and commit 70ea19c5829e ("bpf: Use $(pound) instead
of \# in Makefiles") and define and use a $(pound) variable.
Reference for the change in make:
https://git.savannah.gnu.org/cgit/make.git/commit/?id=c6966b323811c37acedff05b57
Cc: Matt Brown <matthew.brown.dev@gmail.com> Signed-off-by: Paul Menzel <pmenzel@molgen.mpg.de> Signed-off-by: Song Liu <song@kernel.org>
GCC 10+ defaults to -fno-common, which enforces proper declaration of
external references using "extern". without this change a link would
fail with:
lib/raid6/test/algos.c:28: multiple definition of `raid6_call';
lib/raid6/test/test.c:22: first defined here
the pq.h header that is included already includes an extern declaration
so we can just remove the redundant one here.
Cc: <stable@vger.kernel.org> Signed-off-by: Dirk Müller <dmueller@suse.de> Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de> Signed-off-by: Song Liu <song@kernel.org>
Mariusz Tkaczyk [Mon, 17 Jan 2022 11:38:47 +0000 (12:38 +0100)]
md: raid1/raid10: drop pending_cnt
Those counters are not necessary after commit 11bb45e8aaf6 ("md: drop queue
limitation for RAID1 and RAID10"). Remove them from all code (conf and
plug structs). raid1_plug_cb and raid10_plug_cb are identical, so move
definition of raid1_plug_cb to common raid1-10 definitions and use it for
RAID10 too.
Signed-off-by: Mariusz Tkaczyk <mariusz.tkaczyk@linux.intel.com> Signed-off-by: Song Liu <song@kernel.org>
Jens Axboe [Sun, 6 Mar 2022 15:13:09 +0000 (08:13 -0700)]
Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/colyli/linux-bcache into for-5.18/drivers
Pull bcache updates from Coly:
"We have 2 patches for Linux v5.18, both of them are from Mingzhe Zou.
The first patch improves bcache initialization speed by avoid
unnecessary cost of cache consistency, the second one fixes a potential
NULL pointer deference in bcache initialization time."
* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/colyli/linux-bcache:
bcache: fixup multiple threads crash
bcache: fixup bcache_dev_sectors_dirty_add() multithreaded CPU false sharing
However, the bch_btree_node_read and bch_btree_node_read_done
maybe call bch_cache_set_error, then the CACHE_SET_IO_DISABLE
will be set. If the flag already set, the main thread return
error. At the same time, maybe some threads still running and
read NULL pointer, the kernel will crash.
This patch change the event wait condition, the main thread must
wait for all threads to stop.
Fixes: e9a65c2979cc3 ("bcache: make bch_btree_check() to be multithreaded") Signed-off-by: Mingzhe Zou <mingzhe.zou@easystack.cn> Cc: stable@vger.kernel.org # v5.7+ Signed-off-by: Coly Li <colyli@suse.de>
Mingzhe Zou [Fri, 7 Jan 2022 08:21:13 +0000 (16:21 +0800)]
bcache: fixup bcache_dev_sectors_dirty_add() multithreaded CPU false sharing
When attaching a cached device (a.k.a backing device) to a cache
device, bch_sectors_dirty_init() is called to count dirty sectors
and stripes (see what bcache_dev_sectors_dirty_add() does) on the
cache device.
When bcache_dev_sectors_dirty_add() is called, set_bit(stripe,
d->full_dirty_stripes) or clear_bit(stripe, d->full_dirty_stripes)
operation will always be performed. In full_dirty_stripes, each 1bit
represents stripe_size (8192) sectors (512B), so 1bit=4MB (8192*512),
and each CPU cache line=64B=512bit=2048MB. When 20 threads process
a cached disk with 100G dirty data, a single thread processes about
23M at a time, and 20 threads total 460M. These full_dirty_stripes
bits corresponding to the 460M data is likely to fall in the same CPU
cache line. When one of these threads performs a set_bit or clear_bit
operation, the same CPU cache line of other threads will become invalid
and must read the full_dirty_stripes from the main memory again. Compared
with single thread, the time of a bcache_dev_sectors_dirty_add()
call is increased by about 50 times in our test (100G dirty data,
20 threads, bcache_dev_sectors_dirty_add() is called more than
20 million times).
This patch tries to test_bit before set_bit or clear_bit operation.
Therefore, a lot of force set and clear operations will be avoided,
and most of bcache_dev_sectors_dirty_add() calls will only read CPU
cache line.
Signed-off-by: Mingzhe Zou <mingzhe.zou@easystack.cn> Signed-off-by: Coly Li <colyli@suse.de>
Jens Axboe [Thu, 3 Mar 2022 15:51:48 +0000 (08:51 -0700)]
Merge tag 'nvme-5.18-2022-03-03' of git://git.infradead.org/nvme into for-5.18/drivers
Pull NVMe updates from Christoph:
"nvme updates for Linux 5.18
- add vectored-io support for user-passthrough (Kanchan Joshi)
- add verbose error logging (Alan Adamson)
- support buffered I/O on block devices in nvmet (Chaitanya Kulkarni)
- central discovery controller support (Martin Belanger)
- fix and extended the globally unique idenfier validation (me)
- move away from the deprecated IDA APIs (Sagi Grimberg)
- misc code cleanup (Keith Busch, Max Gurtovoy, Qinghua Jin,
Chaitanya Kulkarni)"
* tag 'nvme-5.18-2022-03-03' of git://git.infradead.org/nvme: (27 commits)
nvme: check that EUI/GUID/UUID are globally unique
nvme: check for duplicate identifiers earlier
nvme: fix the check for duplicate unique identifiers
nvme: cleanup __nvme_check_ids
nvme: remove nssa from struct nvme_ctrl
nvme: explicitly set non-error for directives
nvme: expose cntrltype and dctype through sysfs
nvme: send uevent on connection up
nvme: add vectored-io support for user-passthrough
nvme: add verbose error logging
nvme: add a helper to initialize connect_q
nvme-rdma: add helpers for mapping/unmapping request
nvmet-tcp: replace ida_simple[get|remove] with the simler ida_[alloc|free]
nvmet-rdma: replace ida_simple[get|remove] with the simler ida_[alloc|free]
nvmet-fc: replace ida_simple[get|remove] with the simler ida_[alloc|free]
nvmet: replace ida_simple[get|remove] with the simler ida_[alloc|free]
nvme-fc: replace ida_simple[get|remove] with the simler ida_[alloc|free]
nvme: replace ida_simple[get|remove] with the simler ida_[alloc|free]
nvmet: allow bdev in buffered_io mode
nvmet: use i_size_read() to set size for file-ns
...
nvme: check that EUI/GUID/UUID are globally unique
Add a check to verify that the unique identifiers are unique globally
in addition to the existing check that verifies that they are unique
inside a single subsystem.
Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Lift the check for duplicate identifiers into nvme_init_ns_head, which
avoids pointless error unwinding in case they don't match, and also
matches where we check identifier validity for the multipath case.
Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
nvme: fix the check for duplicate unique identifiers
nvme_subsys_check_duplicate_ids should needs to return an error if any of
the identifiers matches, not just if all of them match. But it does not
need to and should not look at the CSI value for this sanity check.
Rewrite the logic to be separate from nvme_ns_ids_equal and optimize it
by reducing duplicate checks for non-present identifiers.
Fixes: 25a47702dbaf ("nvme: track shared namespaces") Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Keith Busch [Tue, 15 Feb 2022 15:37:19 +0000 (07:37 -0800)]
nvme: remove nssa from struct nvme_ctrl
The reported number of streams is not used outside the function that
gets it, so no need to stash it in the controller structure. Use a local
variable instead.
Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Keith Busch [Tue, 15 Feb 2022 15:03:08 +0000 (07:03 -0800)]
nvme: explicitly set non-error for directives
Stream directives is an optional feature. It is not an error if a
controller doesn't support as many as the kernel can optionally use.
Explicitly set the non-error return value on this condition with a
comment explaining why.
Note, the return value was already 0 in this condition, so the setting
is redundant. This patch should just silence bots that falsely believe
the condition contains an error omission.
Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Martin Belanger [Tue, 8 Feb 2022 19:33:46 +0000 (14:33 -0500)]
nvme: expose cntrltype and dctype through sysfs
TP8010 introduces the Discovery Controller Type attribute (dctype).
The dctype is returned in the response to the Identify command. This
patch exposes the dctype through the sysfs. Since the dctype depends on
the Controller Type (cntrltype), another attribute of the Identify
response, the patch also exposes the cntrltype as well. The dctype will
only be displayed for discovery controllers.
A note about the naming of this attribute:
Although TP8010 calls this attribute the Discovery Controller Type,
note that the dctype is now part of the response to the Identify
command for all controller types. I/O, Discovery, and Admin controllers
all share the same Identify response PDU structure. Non-discovery
controllers as well as pre-TP8010 discovery controllers will continue
to set this field to 0 (which has always been the default for reserved
bytes). Per TP8010, the value 0 now means "Discovery controller type is
not reported" instead of "Reserved". One could argue that this
definition is correct even for non-discovery controllers, and by
extension, exposing it in the sysfs for non-discovery controllers is
appropriate.
Signed-off-by: Martin Belanger <martin.belanger@dell.com> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> Reviewed-by: John Meneghini <jmeneghi@redhat.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Christoph Hellwig <hch@lst.de>
Martin Belanger [Tue, 8 Feb 2022 19:33:45 +0000 (14:33 -0500)]
nvme: send uevent on connection up
When connectivity with a controller is lost, the driver will keep
trying to reconnect once every 10 sec. When connection is restored,
user-space apps need to be informed so that they can take proper
action. For example, TP8010 introduces the DIM PDU, which is used to
register with a discovery controller (DC). The DIM PDU is sent from
user-space. The DIM PDU must be sent every time a connection is
established with a DC. Therefore, the kernel must tell user-space apps
when connection is restored so that registration can happen.
The uevent sent is a "change" uevent with environmental data
set to: "NVME_EVENT=connected".
Signed-off-by: Martin Belanger <martin.belanger@dell.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> Reviewed-by: John Meneghini <jmeneghi@redhat.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Christoph Hellwig <hch@lst.de>
Kanchan Joshi [Thu, 10 Feb 2022 05:37:55 +0000 (11:07 +0530)]
nvme: add vectored-io support for user-passthrough
Add a new NVME_IOCTL_IO64_CMD_VEC ioctl that works like the existing
NVME_IOCTL_IO64_CMD ioctl except that it takes and array of iovecs
and thus supports vectored I/O.
- cmd.addr is base address of user iovec array
- cmd.vec_cnt is count of iovec array elements
This patch does not include vectored-variant for admin-commands as most
of them are light on buffers and likely to have low invocation frequency.
Alan Adamson [Thu, 3 Feb 2022 08:11:53 +0000 (00:11 -0800)]
nvme: add verbose error logging
Improves logging of NVMe errors. If NVME_VERBOSE_ERRORS is configured,
a verbose description of the error is logged, otherwise only status
codes/bits is logged.
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
[kch]: fix several nits, cosmetics, and trim down code. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Alan Adamson <alan.adamson@oracle.com> Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Christoph Hellwig <hch@lst.de>
Allow block device to be configured in the buffered I/O mode by using
the file backend. In this way now we can use cache for the block
device namespace which shows significant performance improvement.
We update the block device ns enable function and return early when
buffered_io flag is set.
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Instead of calling vfs_getattr() use i_size_read() to read the size of
file so we can read the size of not only file type but also block type
with one call. This is needed to implement buffered_io support for the
NVMeOF block device backend.
We also change return type of function nvmet_file_ns_revalidate() from
int to void, since this function does not return any meaning value.
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Remove zeroout memeset call & zeroout local variable cmd at the time
of declaration in nvmf_ref_read32() similar to what we have done in
nvmf_reg_read64(), nvmf_reg_write32(), nvmf_connect_admin_queue(), and
nvmf_connect_io_queue().
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Christoph Hellwig <hch@lst.de>
Remove goto labels and use direct returns as error unwinding code only
needs to free t_page variable if we alloc_pages() call fails as having
two labels for one kfree() can be avoided easily.
Only caller of null_alloc_page() is null_insert_page() unconditionally
sets only parameter to GFP_NOIO and that is statically hard-coded in
null_blk. There is no point in having statically hardcoded function
parameter.
Remove the unnecessary parameter gfp_flags and adjust the code, so it
can retain existing behavior null_alloc_page() with GFP_NOIO.
Only caller of alloc_cmd() is null_submit_bio() unconditionally sets
second parameter to true and that is statically hard-coded in null_blk.
There is no point in having statically hardcoded function parameter.
Remove the unnecessary parameter can_wait and adjust the code so it
can retain existing behavior of waiting when we don't get valid
nullb_cmd from __alloc_cmd() in alloc_cmd().
The restructured code avoids multiple return statements, multiple
calls to __alloc_cmd() and resulting a fast path call to
prepare_to_wait() due to removal of first alloc_cmd() call.
Follow the pattern that we have in bio_alloc() to set the structure
members in the structure allocation function in alloc_cmd() and pass
bio to initialize newly allocated cmd->bio member.
Follow the pattern in copy_to_nullb() to use result of one function call
(null_cache_active()) to be used as a parameter to another function call
(null_insert_page()), use result of alloc_cmd() as a first parameter to
the null_handle_cmd() in null_submit_bio() function. This allow us to
remove the local variable cmd on stack in null_submit_bio() that is in
fast path.
Instead of hardcoding queue depth allow user to set the hw queue depth
using module parameter. Set default value to 128 to retain the existing
behavior.
The local variable file is used to pass it to the vfs_fsync(). We can
get away with using lo->lo_backing_file instead of storing in a local
variable which is not used anywhere else.
The local variable q is used to pass it to the blk_queue_discard(). We
can get away with using lo->lo_queue instead of storing in a local
variable which is not used anywhere else.
sprintf does not know the PAGE_SIZE maximum of the temporary buffer
used for outputting sysfs content and it's possible to overrun the
PAGE_SIZE buffer length.
Use a generic sysfs_emit function that knows the size of the
temporary buffer and ensures that no overrun is done for offset
attribute in
loop_attr_[offset|sizelimit|autoclear|partscan|dio]_show() callbacks.
The function nullb_device_power_store() returns -ENOMEM when
null_add_dev() fails. null_add_dev() can fail with return value
other than -ENOMEM such as -EINVAL when Zoned Block Device option
is used, see :
As Luis reported, losetup currently doesn't properly create the loop
device without this if the device node already exists because old
scripts created it manually. So default to y for now and remove the
aggressive removal schedule.
Reported-by: Luis Chamberlain <mcgrof@kernel.org> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> Link: https://lore.kernel.org/r/20220225181440.1351591-1-hch@lst.de Signed-off-by: Jens Axboe <axboe@kernel.dk>
Zhang Wensheng [Thu, 17 Feb 2022 06:42:47 +0000 (14:42 +0800)]
block: update io_ticks when io hang
When the inflight IOs are slow and no new IOs are issued, we expect
iostat could manifest the IO hang problem. However after
commit 524572368e0f ("block: delete part_round_stats and switch to less
precise counting"), io_tick and time_in_queue will not be updated until
the end of IO, and the avgqu-sz and %util columns of iostat will be zero.
Because it has using stat.nsecs accumulation to express time_in_queue
which is not suitable to change, and may %util will express the status
better when io hang occur. To fix io_ticks, we use update_io_ticks and
inflight to update io_ticks when diskstats_show and part_stat_show
been called.
Fixes: 524572368e0f ("block: delete part_round_stats and switch to less precise counting") Signed-off-by: Zhang Wensheng <zhangwensheng5@huawei.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/20220217064247.4041435-1-zhangwensheng5@huawei.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
projects / kernel.git / log