11 Apr, 2020
1 commit
-
Pull block fixes from Jens Axboe:
"Here's a set of fixes that should go into this merge window. This
contains:- NVMe pull request from Christoph with various fixes
- Better discard support for loop (Evan)
- Only call ->commit_rqs() if we have queued IO (Keith)
- blkcg offlining fixes (Tejun)
- fix (and fix the fix) for busy partitions"
* tag 'block-5.7-2020-04-10' of git://git.kernel.dk/linux-block:
block: fix busy device checking in blk_drop_partitions again
block: fix busy device checking in blk_drop_partitions
nvmet-rdma: fix double free of rdma queue
blk-mq: don't commit_rqs() if none were queued
nvme-fc: Revert "add module to ops template to allow module references"
nvme: fix deadlock caused by ANA update wrong locking
nvmet-rdma: fix bonding failover possible NULL deref
loop: Better discard support for block devices
loop: Report EOPNOTSUPP properly
nvmet: fix NULL dereference when removing a referral
nvme: inherit stable pages constraint in the mpath stack device
blkcg: don't offline parent blkcg first
blkcg: rename blkcg->cgwb_refcnt to ->online_pin and always use it
nvme-tcp: fix possible crash in recv error flow
nvme-tcp: don't poll a non-live queue
nvme-tcp: fix possible crash in write_zeroes processing
nvmet-fc: fix typo in comment
nvme-rdma: Replace comma with a semicolon
nvme-fcloop: fix deallocation of working context
nvme: fix compat address handling in several ioctls
09 Apr, 2020
1 commit
-
Pull ceph updates from Ilya Dryomov:
"The main items are:- support for asynchronous create and unlink (Jeff Layton).
Creates and unlinks are satisfied locally, without waiting for a
reply from the MDS, provided the client has been granted
appropriate caps (new in v15.y.z ("Octopus") release). This can be
a big help for metadata heavy workloads such as tar and rsync.
Opt-in with the new nowsync mount option.- multiple blk-mq queues for rbd (Hannes Reinecke and myself).
When the driver was converted to blk-mq, we settled on a single
blk-mq queue because of a global lock in libceph and some other
technical debt. These have since been addressed, so allocate a
queue per CPU to enhance parallelism.- don't hold onto caps that aren't actually needed (Zheng Yan).
This has been our long-standing behavior, but it causes issues with
some active/standby applications (synchronous I/O, stalls if the
standby goes down, etc).- .snap directory timestamps consistent with ceph-fuse (Luis
Henriques)"* tag 'ceph-for-5.7-rc1' of git://github.com/ceph/ceph-client: (49 commits)
ceph: fix snapshot directory timestamps
ceph: wait for async creating inode before requesting new max size
ceph: don't skip updating wanted caps when cap is stale
ceph: request new max size only when there is auth cap
ceph: cleanup return error of try_get_cap_refs()
ceph: return ceph_mdsc_do_request() errors from __get_parent()
ceph: check all mds' caps after page writeback
ceph: update i_requested_max_size only when sending cap msg to auth mds
ceph: simplify calling of ceph_get_fmode()
ceph: remove delay check logic from ceph_check_caps()
ceph: consider inode's last read/write when calculating wanted caps
ceph: always renew caps if mds_wanted is insufficient
ceph: update dentry lease for async create
ceph: attempt to do async create when possible
ceph: cache layout in parent dir on first sync create
ceph: add new MDS req field to hold delegated inode number
ceph: decode interval_sets for delegated inos
ceph: make ceph_fill_inode non-static
ceph: perform asynchronous unlink if we have sufficient caps
ceph: don't take refs to want mask unless we have all bits
...
04 Apr, 2020
2 commits
-
If the backing device for a loop device is itself a block device,
then mirror the "write zeroes" capabilities of the underlying
block device into the loop device. Copy this capability into both
max_write_zeroes_sectors and max_discard_sectors of the loop device.The reason for this is that REQ_OP_DISCARD on a loop device translates
into blkdev_issue_zeroout(), rather than blkdev_issue_discard(). This
presents a consistent interface for loop devices (that discarded data
is zeroed), regardless of the backing device type of the loop device.
There should be no behavior change for loop devices backed by regular
files.This change fixes blktest block/003, and removes an extraneous
error print in block/013 when testing on a loop device backed
by a block device that does not support discard.Signed-off-by: Evan Green
Reviewed-by: Gwendal Grignou
Reviewed-by: Chaitanya Kulkarni
[used updated version of Evan's comment in loop_config_discard()]
[moved backingq to local scope, removed redundant braces]
Signed-off-by: Andrzej Pietrasiewicz
Reviewed-by: Christoph Hellwig
Signed-off-by: Jens Axboe -
Properly plumb out EOPNOTSUPP from loop driver operations, which may
get returned when for instance a discard operation is attempted but not
supported by the underlying block device. Before this change, everything
was reported in the log as an I/O error, which is scary and not
helpful in debugging.Signed-off-by: Evan Green
Reviewed-by: Gwendal Grignou
Reviewed-by: Bart Van Assche
Signed-off-by: Andrzej Pietrasiewicz
Reviewed-by: Christoph Hellwig
Signed-off-by: Jens Axboe
31 Mar, 2020
2 commits
-
Pull block driver updates from Jens Axboe:
- floppy driver cleanup series from Willy
- NVMe updates and fixes (Various)
- null_blk trace improvements (Chaitanya)
- bcache fixes (Coly)
- md fixes (via Song)
- loop block size change optimizations (Martijn)
- scnprintf() use (Takashi)
* tag 'for-5.7/drivers-2020-03-29' of git://git.kernel.dk/linux-block: (81 commits)
null_blk: add trace in null_blk_zoned.c
null_blk: add tracepoint helpers for zoned mode
block: add a zone condition debug helper
nvme: cleanup namespace identifier reporting in nvme_init_ns_head
nvme: rename __nvme_find_ns_head to nvme_find_ns_head
nvme: refactor nvme_identify_ns_descs error handling
nvme-tcp: Add warning on state change failure at nvme_tcp_setup_ctrl
nvme-rdma: Add warning on state change failure at nvme_rdma_setup_ctrl
nvme: Fix controller creation races with teardown flow
nvme: Make nvme_uninit_ctrl symmetric to nvme_init_ctrl
nvme: Fix ctrl use-after-free during sysfs deletion
nvme-pci: Re-order nvme_pci_free_ctrl
nvme: Remove unused return code from nvme_delete_ctrl_sync
nvme: Use nvme_state_terminal helper
nvme: release ida resources
nvme: Add compat_ioctl handler for NVME_IOCTL_SUBMIT_IO
nvmet-tcp: optimize tcp stack TX when data digest is used
nvme-fabrics: Use scnprintf() for avoiding potential buffer overflow
nvme-multipath: do not reset on unknown status
nvmet-rdma: allocate RW ctxs according to mdts
... -
Pull block updates from Jens Axboe:
- Online capacity resizing (Balbir)
- Number of hardware queue change fixes (Bart)
- null_blk fault injection addition (Bart)
- Cleanup of queue allocation, unifying the node/no-node API
(Christoph)- Cleanup of genhd, moving code to where it makes sense (Christoph)
- Cleanup of the partition handling code (Christoph)
- disk stat fixes/improvements (Konstantin)
- BFQ improvements (Paolo)
- Various fixes and improvements
* tag 'for-5.7/block-2020-03-29' of git://git.kernel.dk/linux-block: (72 commits)
block: return NULL in blk_alloc_queue() on error
block: move bio_map_* to blk-map.c
Revert "blkdev: check for valid request queue before issuing flush"
block: simplify queue allocation
bcache: pass the make_request methods to blk_queue_make_request
null_blk: use blk_mq_init_queue_data
block: add a blk_mq_init_queue_data helper
block: move the ->devnode callback to struct block_device_operations
block: move the part_stat* helpers from genhd.h to a new header
block: move block layer internals out of include/linux/genhd.h
block: move guard_bio_eod to bio.c
block: unexport get_gendisk
block: unexport disk_map_sector_rcu
block: unexport disk_get_part
block: mark part_in_flight and part_in_flight_rw static
block: mark block_depr static
block: factor out requeue handling from dispatch code
block/diskstats: replace time_in_queue with sum of request times
block/diskstats: accumulate all per-cpu counters in one pass
block/diskstats: more accurate approximation of io_ticks for slow disks
...
30 Mar, 2020
6 commits
-
Allocate one queue per CPU and get a performance boost from
higher parallelism.Signed-off-by: Hannes Reinecke
Reviewed-by: Ilya Dryomov
Signed-off-by: Ilya Dryomov -
Avoid making allocations for !IMG_REQ_CHILD image requests. Only
IMG_REQ_CHILD image requests need to be freed now.Move the initial request checks to rbd_queue_rq(). Unfortunately we
can't fill the image request and kick the state machine directly from
rbd_queue_rq() because ->queue_rq() isn't allowed to block.Signed-off-by: Ilya Dryomov
-
Currently header_rwsem is acquired twice: once in rbd_dev_parent_get()
when the image request is being created and then in rbd_queue_workfn()
to capture mapping_size and snapc. Introduce rbd_img_capture_header()
and move image request allocation so that header_rwsem can be acquired
just once.Signed-off-by: Ilya Dryomov
-
No need to clear IMG_REQ_LAYERED before destroying the request.
Signed-off-by: Ilya Dryomov
-
The reference counter is never increased, so we can as well call
rbd_img_request_destroy() directly and drop the kref.Signed-off-by: Hannes Reinecke
Reviewed-by: Ilya Dryomov
Signed-off-by: Ilya Dryomov -
IMG_REQ_LAYERED is set in rbd_img_request_create(), and tested and
cleared in rbd_img_request_destroy() when the image request is about to
be destroyed. The barriers are unnecessary.Signed-off-by: Ilya Dryomov
28 Mar, 2020
4 commits
-
With the help of previously added tracepoints we can now trace
report-zones, zone-write and zone-mgmt ops in null_blk_zoned.c.Signed-off-by: Chaitanya Kulkarni
Reviewed-by: Damien Le Moal
Signed-off-by: Jens Axboe -
This patch adds two new tracpoints for null_blk_zoned.c that allows us
to trace report-zones, zone-mgmt-op and zone-write operations which has
direct effect on the zone condition state machine.Also, we update drivers/block/Makefile so that new null_blk related
tracefiles can be compiled.Signed-off-by: Chaitanya Kulkarni
Reviewed-by: Damien Le Moal
Signed-off-by: Jens Axboe -
Current make_request based drivers use either blk_alloc_queue_node or
blk_alloc_queue to allocate a queue, and then set up the make_request_fn
function pointer and a few parameters using the blk_queue_make_request
helper. Simplify this by passing the make_request pointer to
blk_alloc_queue, and while at it merge the _node variant into the main
helper by always passing a node_id, and remove the superfluous gfp_mask
parameter. A lower-level __blk_alloc_queue is kept for the blk-mq case.Signed-off-by: Christoph Hellwig
Signed-off-by: Jens Axboe -
Use the new blk_mq_init_queue_data instead of open coding the queue
allocation and initialization.Reviewed-by: Johannes Thumshirn
Signed-off-by: Christoph Hellwig
Signed-off-by: Jens Axboe
27 Mar, 2020
1 commit
-
There really isn't any good reason to stash a method directly into
struct gendisk. Move it together with the other block device
operations.Signed-off-by: Christoph Hellwig
Signed-off-by: Jens Axboe
25 Mar, 2020
1 commit
-
These macros are just used by a few files. Move them out of genhd.h,
which is included everywhere into a new standalone header.Signed-off-by: Christoph Hellwig
Signed-off-by: Jens Axboe
20 Mar, 2020
1 commit
-
The current codebase makes use of the zero-length array language
extension to the C90 standard, but the preferred mechanism to declare
variable-length types such as these ones is a flexible array member[1][2],
introduced in C99:struct foo {
int stuff;
struct boo array[];
};By making use of the mechanism above, we will get a compiler warning
in case the flexible array does not occur last in the structure, which
will help us prevent some kind of undefined behavior bugs from being
inadvertenly introduced[3] to the codebase from now on.Also, notice that, dynamic memory allocations won't be affected by
this change:"Flexible array members have incomplete type, and so the sizeof operator
may not be applied. As a quirk of the original implementation of
zero-length arrays, sizeof evaluates to zero."[1]This issue was found with the help of Coccinelle.
[1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html
[2] https://github.com/KSPP/linux/issues/21
[3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour")Signed-off-by: Gustavo A. R. Silva
Signed-off-by: Jens Axboe
19 Mar, 2020
2 commits
-
block/genhd provides set_capacity_revalidate_and_notify() for
sending RESIZE notifications via uevents.Signed-off-by: Balbir Singh
Reviewed-by: Christoph Hellwig
Signed-off-by: Jens Axboe -
block/genhd provides set_capacity_revalidate_and_notify() for sending RESIZE
notifications via uevents.Signed-off-by: Balbir Singh
Signed-off-by: Jens Axboe
16 Mar, 2020
13 commits
-
This is done in order to remove the confusion that arises at some places
in the code where local variables or arguments shadow the global variable.
It is already visible that some places are a bit awkward and iterate over
the global variable, for the sole reason that they used to rely on it being
named "fdc" in order to get the correct address when using FD_DOR. These
ones are easy to spot by searching for "for (current_fdc...".Some more cleanup is definitely possible. For example
"fdc_state[current_fdc].somefield" is used all over the code and would
probably be better with "fdc_state->somefield" with fdc_state being set
when current_fdc is assigned. This would require to pass the pointer to
the current state instead of the current_fdc to the I/O functions.Link: https://lore.kernel.org/r/20200301195555.11154-7-w@1wt.eu
Cc: Linus Torvalds
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
FDC registers FD_STATUS, FD_DATA, FD_DOR, FD_DIR and FD_DCR used to be
defined relative to FD_IOPORT, which is the FDC's base address, itself
a macro depending on the "fdc" local or global variable.This patch changes this so that the register macros above now only
reference the address offset, and that the FDC's address is explicitly
passed in each call to fd_inb() and fd_outb(), thus removing the macro.
With this change there is no more implicit usage of the local/global
"fdc" variable.One place in the ARM code used to check if the port was equal to FD_DOR,
this was changed to testing the register by applying a mask to the port,
as was already done in the sparc code.There are still occurrences of fd_inb() and fd_outb() in the PARISC
code and these ones remain unaffected since they already used to work
with a base address and a register offset.The sparc, m68k and parisc code could now be slightly cleaned up to
benefit from the macro definitions above instead of the equivalent
hard-coded values.Link: https://lore.kernel.org/r/20200301195555.11154-6-w@1wt.eu
Cc: Ian Molton
Cc: Russell King
Cc: Linus Torvalds
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
These two functions replace fd_inb() and fd_outb() in that they take
the FDC in argument. This will ease the separation of the base address
and the port everywhere the code is used.Link: https://lore.kernel.org/r/20200301195555.11154-5-w@1wt.eu
Cc: Linus Torvalds
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
Several macros were used to access reply_buffer[] at discrete positions
without making it obvious they were relying on this. These ones have
been replaced by their offset in the reply buffer to make these accesses
more obvious.Link: https://lore.kernel.org/r/20200224212352.8640-11-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
Various macros were used to access raw_cmd for R/W or format commands
without making it obvious that raw_cmd->cmd[] was used. Let's expand
the macros to make this more obvious.Link: https://lore.kernel.org/r/20200224212352.8640-10-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
This macro doesn't bring much value and only slightly obfuscates the
code by silently using global variable "current_drive", let's expand it.Link: https://lore.kernel.org/r/20200224212352.8640-9-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
This macro doesn't bring much value and only slightly obfuscates the
code by silently using global variable "current_drive", let's expand it.Link: https://lore.kernel.org/r/20200224212352.8640-8-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
This macro doesn't bring much value and only slightly obfuscates the
code by silently using global variable "current_drive", let's expand it.Link: https://lore.kernel.org/r/20200224212352.8640-7-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
This macro doesn't bring much value and only slightly obfuscates the
code by silently using local variable "drive", let's expand it.Link: https://lore.kernel.org/r/20200224212352.8640-6-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
This macro doesn't bring much value and only slightly obfuscates the
code by silently using local variable "drive", let's expand it.Link: https://lore.kernel.org/r/20200224212352.8640-5-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
This macro doesn't bring much value and only slightly obfuscates the
code by silently using local variable "drive", let's expand it.Link: https://lore.kernel.org/r/20200224212352.8640-4-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
This macro doesn't bring much value and only slightly obfuscates the
code by silently using local variable "drive", let's expand it.Link: https://lore.kernel.org/r/20200224212352.8640-3-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe -
Macro FDCS silently uses identifier "fdc" which may be either the
global one or a local one. Let's expand the macro to make this more
obvious.Link: https://lore.kernel.org/r/20200224212352.8640-2-w@1wt.eu
Signed-off-by: Willy Tarreau
Signed-off-by: Denis Efremov
Signed-off-by: Jens Axboe
13 Mar, 2020
1 commit
-
As null_blk is a very good start point to test block layer, this patch
adds description and comments to 'timeout', 'requeue' and 'init_hctx' to
explain how to use fault injection with null_blk.The nvme has similar with nvme_core.fail_request in the form of comment.
Reviewed-by: Chaitanya Kulkarni
Signed-off-by: Dongli Zhang
Signed-off-by: Jens Axboe
12 Mar, 2020
5 commits
-
Steps to reproduce:
BLKRESETZONE zone 0
// force EIO
pwrite(fd, buf, 4096, 4096);[issue more IO including zone ioctls]
It will start failing randomly including IO to unrelated zones because of
->error "reuse". Trigger can be partition detection as well if test is not
run immediately which is even more entertaining.The fix is of course to clear ->error where necessary.
Reviewed-by: Christoph Hellwig
Signed-off-by: Alexey Dobriyan (SK hynix)
Signed-off-by: Jens Axboe -
In commit 2da22da5734 (nbd: fix zero cmd timeout handling v2),
it is allowed to reset timer when it fires if tag_set.timeout
is set to zero. If the server is shutdown and a new socket
is reconfigured, the request should be requeued to be processed by
new server instead of waiting for response from the old one.Reviewed-by: Josef Bacik
Signed-off-by: Hou Pu
Signed-off-by: Jens Axboe -
Nbd server with multiple connections could be upgraded since
560bc4b (nbd: handle dead connections). But if only one conncection
is configured, after we take down nbd server, all inflight IO
would finally timeout and return error. We could requeue them
like what we do with multiple connections and wait for new socket
in submit path.Reviewed-by: Josef Bacik
Signed-off-by: Hou Pu
Signed-off-by: Jens Axboe -
We deleted last_md_mark_dirty long ago, this function no longer needs to
exist, delete it, otherwise a compilation error will occur when DEBUG is
opened.Fixes: ac0acb9e39ac ("drbd: use drbd_device_post_work() in more place")
Signed-off-by: Jackie Liu
Signed-off-by: Jens Axboe -
Since snprintf() returns the would-be-output size instead of the
actual output size, the succeeding calls may go beyond the given
buffer limit. Fix it by replacing with scnprintf().Signed-off-by: Takashi Iwai
Signed-off-by: Jens Axboe
