-----BEGIN PGP SIGNATURE-----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=QWC+
-----END PGP SIGNATURE-----
Merge tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block
Pull block updates from Jens Axboe:
- mq-deadline accounting improvements (Bart)
- blk-wbt timer fix (Andrea)
- Untangle the block layer includes (Christoph)
- Rework the poll support to be bio based, which will enable adding
support for polling for bio based drivers (Christoph)
- Block layer core support for multi-actuator drives (Damien)
- blk-crypto improvements (Eric)
- Batched tag allocation support (me)
- Request completion batching support (me)
- Plugging improvements (me)
- Shared tag set improvements (John)
- Concurrent queue quiesce support (Ming)
- Cache bdev in ->private_data for block devices (Pavel)
- bdev dio improvements (Pavel)
- Block device invalidation and block size improvements (Xie)
- Various cleanups, fixes, and improvements (Christoph, Jackie,
Masahira, Tejun, Yu, Pavel, Zheng, me)
* tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block: (174 commits)
blk-mq-debugfs: Show active requests per queue for shared tags
block: improve readability of blk_mq_end_request_batch()
virtio-blk: Use blk_validate_block_size() to validate block size
loop: Use blk_validate_block_size() to validate block size
nbd: Use blk_validate_block_size() to validate block size
block: Add a helper to validate the block size
block: re-flow blk_mq_rq_ctx_init()
block: prefetch request to be initialized
block: pass in blk_mq_tags to blk_mq_rq_ctx_init()
block: add rq_flags to struct blk_mq_alloc_data
block: add async version of bio_set_polled
block: kill DIO_MULTI_BIO
block: kill unused polling bits in __blkdev_direct_IO()
block: avoid extra iter advance with async iocb
block: Add independent access ranges support
blk-mq: don't issue request directly in case that current is to be blocked
sbitmap: silence data race warning
blk-cgroup: synchronize blkg creation against policy deactivation
block: refactor bio_iov_bvec_set()
block: add single bio async direct IO helper
...
Pass the correct length to nvmet_tcp_verify_hdgst, which is the pdu
header length. This fixes a wrong behaviour where header digest
verification passes although the digest is wrong.
Signed-off-by: Amit Engel <amit.engel@dell.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
In an effort to avoid open-coded arithmetic in the kernel [1], use the
flex_array_size() and struct_size() helpers instead of an open-coded
calculation.
[1] https://github.com/KSPP/linux/issues/160
Signed-off-by: Len Baker <len.baker@gmx.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Register the discovery subsystem as the 'current' discovery subsystem,
and add a new discovery log page entry for it.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Invert the check for discovery subsystem type to allow for additional
discovery subsystem types.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
exp_ddgst is of type __le32, &cmd->exp_ddgst + cmd->offset increases
&cmd->exp_ddgst by 4 * cmd->offset, fix this by type casting
&cmd->exp_ddgst to u8 *.
Fixes: 872d26a391 ("nvmet-tcp: add NVMe over TCP target driver")
Signed-off-by: Varun Prakash <varun@chelsio.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
ddgst is of type __le32, &req->ddgst + req->offset
increases &req->ddgst by 4 * req->offset, fix this by
type casting &req->ddgst to u8 *.
Fixes: 3f2304f8c6 ("nvme-tcp: add NVMe over TCP host driver")
Signed-off-by: Varun Prakash <varun@chelsio.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
With commit db5ad6b7f8 ("nvme-tcp: try to send request in queue_rq
context") r2t and response PDU can get processed while send function
is executing.
Current data digest send code uses req->offset after kernel_sendmsg(),
this creates a race condition where req->offset gets reset before it
is used in send function.
This can happen in two cases -
1. Target sends r2t PDU which resets req->offset.
2. Target send response PDU which completes the req and then req is
used for a new command, nvme_tcp_setup_cmd_pdu() resets req->offset.
Fix this by storing req->offset in a local variable and using
this local variable after kernel_sendmsg().
Fixes: db5ad6b7f8 ("nvme-tcp: try to send request in queue_rq context")
Signed-off-by: Varun Prakash <varun@chelsio.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We should not access request members after the last send, even to
determine if indeed it was the last data payload send. The reason is
that a completion could have arrived and trigger a new execution of the
request which overridden these members. This was fixed by commit
825619b09a ("nvme-tcp: fix possible use-after-completion").
Commit e371af033c broke that assumption again to address cases where
multiple r2t pdus are sent per request. To fix it, we need to record the
request data_sent and data_len and after the payload network send we
reference these counters to determine weather we should advance the
request iterator.
Fixes: e371af033c ("nvme-tcp: fix incorrect h2cdata pdu offset accounting")
Reported-by: Keith Busch <kbusch@kernel.org>
Cc: stable@vger.kernel.org # 5.10+
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
page_frag_free() won't completely release the memory
allocated for the commands, the cache page must be explicitly
freed by calling __page_frag_cache_drain().
This bug can be easily reproduced by repeatedly
executing the following command on the initiator:
$echo 1 > /sys/devices/virtual/nvme-fabrics/ctl/nvme0/reset_controller
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The second argument was only used by the USB gadget code, yet everyone
pays the overhead of passing a zero to be passed into aio, where it
ends up being part of the aio res2 value.
Now that everybody is passing in zero, kill off the extra argument.
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
As noted in the "Deprecated Interfaces, Language Features, Attributes,
and Conventions" documentation [1], size calculations (especially
multiplication) should not be performed in memory allocator (or similar)
function arguments due to the risk of them overflowing. This could lead
to values wrapping around and a smaller allocation being made than the
caller was expecting. Using those allocations could lead to linear
overflows of heap memory and other misbehaviors.
In this case this is not actually dynamic size: all the operands
involved in the calculation are constant values. However it is better to
refactor this anyway, just to keep the open-coded math idiom out of
code.
So, use the struct_size() helper to do the arithmetic instead of the
argument "size + count * size" in the kmalloc() function.
This code was detected with the help of Coccinelle and audited and fixed
manually.
[1] https://www.kernel.org/doc/html/latest/process/deprecated.html#open-coded-arithmetic-in-allocator-arguments
Signed-off-by: Len Baker <len.baker@gmx.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
When reading the partition table on initial scan hits an I/O error the
I/O will hang with the scan_mutex held:
[<0>] do_read_cache_page+0x49b/0x790
[<0>] read_part_sector+0x39/0xe0
[<0>] read_lba+0xf9/0x1d0
[<0>] efi_partition+0xf1/0x7f0
[<0>] bdev_disk_changed+0x1ee/0x550
[<0>] blkdev_get_whole+0x81/0x90
[<0>] blkdev_get_by_dev+0x128/0x2e0
[<0>] device_add_disk+0x377/0x3c0
[<0>] nvme_mpath_set_live+0x130/0x1b0 [nvme_core]
[<0>] nvme_mpath_add_disk+0x150/0x160 [nvme_core]
[<0>] nvme_alloc_ns+0x417/0x950 [nvme_core]
[<0>] nvme_validate_or_alloc_ns+0xe9/0x1e0 [nvme_core]
[<0>] nvme_scan_work+0x168/0x310 [nvme_core]
[<0>] process_one_work+0x231/0x420
and trying to delete the controller will deadlock as it tries to grab
the scan mutex:
[<0>] nvme_mpath_clear_ctrl_paths+0x25/0x80 [nvme_core]
[<0>] nvme_remove_namespaces+0x31/0xf0 [nvme_core]
[<0>] nvme_do_delete_ctrl+0x4b/0x80 [nvme_core]
As we're now properly ordering the namespace list there is no need to
hold the scan_mutex in nvme_mpath_clear_ctrl_paths() anymore.
And we always need to kick the requeue list as the path will be marked
as unusable and I/O will be requeued _without_ a current path.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The host memory doorbell and event buffers need to be initialized on
each reset so the driver doesn't observe stale values from the previous
instantiation.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Tested-by: John Levon <john.levon@nutanix.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
In case that icdoff is not zero or mandatory keyed sgls are not
supported by the NVMe/RDMA target, we'll go to error flow but we'll
return 0 to the caller. Fix it by returning an appropriate error code.
Fixes: c66e2998c8 ("nvme-rdma: centralize controller setup sequence")
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
We never checked for errors on add_disk() as this function
returned void. Now that this is fixed, use the shiny new
error handling.
Since we now can tell for sure when a disk was added, move
setting the bit NVME_NSHEAD_DISK_LIVE only when we did
add the disk successfully.
Nothing to do here as the cleanup is done elsewhere. We take
care and use test_and_set_bit() because it is protects against
two nvme paths simultaneously calling device_add_disk() on the
same namespace head.
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This makes the code more readable.
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This makes the code more readable.
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.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>
With discovery controllers supporting unique subsystem NQNs the
actual subsystem NQN might be different from that one passed in
via the connect args. So add a helper to display the resulting
subsystem NQN.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Add a connect option 'discovery' to specify that the connection
should be made to a discovery controller, not a normal I/O controller.
With discovery controllers supporting unique subsystem NQNs we
cannot easily distinguish by the subsystem NQN if this should be
a discovery connection, but we need this information to blank out
options not supported by discovery controllers.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
With unique discovery controller NQNs we cannot distinguish the
subsystem type by the NQN alone, but need to check the subsystem
type, too.
So expose the subsystem type in a new sysfs attribute 'subsystype'.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Set the correct 'CNTRLTYPE' field in the identify controller data.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Add a helper function to determine if a given subsystem is a discovery
subsystem.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
TPAR8013 allows for unique discovery NQNs, so make the discovery
controller NQN configurable by exposing a subsys attribute
'discovery_nqn'.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Limit the maximal queue size for RDMA controllers. Today, the target
reports a limit of 1024 and this limit isn't valid for some of the RDMA
based controllers. For now, limit RDMA transport to 128 entries (the
max queue depth configured for Linux NVMe/RDMA host).
Future general solution should use RDMA/core API to calculate this size
according to device capabilities and number of WRs needed per NVMe IO
request.
Reported-by: Mark Ruijter <mruijter@primelogic.nl>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Some transports, such as RDMA, would like to set the queue size
according to device/port/ctrl characteristics. Add a new nvmet transport
op that is called during ctrl initialization. This will not effect
transports that don't implement this option.
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Corrent limit of 1024 isn't valid for some of the RDMA based ctrls. In
case the target expose a cap of larger amount of entries (e.g. 1024),
the initiator may fail to create a QP with this size. Thus limit to a
value that works for all RDMA adapters.
Future general solution should use RDMA/core API to calculate this size
according to device capabilities and number of WRs needed per NVMe IO
request.
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
When removing a port, all its controllers are being removed, but there
are queues on the port that doesn't belong to any controller (during
connection time). This causes a use-after-free bug for any command
that dereferences req->port (like in nvmet_alloc_ctrl). Those queues
should be destroyed before freeing the port via configfs. Destroy
the remaining queues after the accept_work was cancelled guarantees
that no new queue will be created.
Signed-off-by: Israel Rukshin <israelr@nvidia.com>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
When removing a port, all its controllers are being removed, but there
are queues on the port that doesn't belong to any controller (during
connection time). This causes a use-after-free bug for any command
that dereferences req->port (like in nvmet_alloc_ctrl). Those queues
should be destroyed before freeing the port via configfs. Destroy the
remaining queues after the RDMA-CM was destroyed guarantees that no
new queue will be created.
Signed-off-by: Israel Rukshin <israelr@nvidia.com>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
When a port is removed through configfs, any connected controllers
are starting teardown flow asynchronously and can still send commands.
This causes a use-after-free bug for any command that dereferences
req->port (like in nvmet_parse_io_cmd).
To fix this, wait for all the teardown scheduled works to complete
(like release_work at rdma/tcp drivers). This ensures there are no
active controllers when the port is eventually removed.
Signed-off-by: Israel Rukshin <israelr@nvidia.com>
Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
NVMe FC don't have support for map queues, unlike the PCI, RDMA and TCP
transports. Add a ->map_queues callout for the LLDDs to provide such
functionality.
Signed-off-by: Saurav Kashyap <skashyap@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
When fast_io_fail_tmo is set I/O will be aborted while recovery is
still ongoing. This causes MD to set the namespace to failed, and
no futher I/O will be submitted to that namespace.
However, once the recovery succeeds and the namespace becomes
operational again the NVMe subsystem doesn't send a notification,
so MD cannot automatically reinstate operation and requires
manual interaction.
This patch will send a KOBJ_CHANGE uevent per multipathed namespace
once the underlying controller transitions to LIVE, allowing an automatic
MD reassembly with these udev rules:
/etc/udev/rules.d/65-md-auto-re-add.rules:
SUBSYSTEM!="block", GOTO="md_end"
ACTION!="change", GOTO="md_end"
ENV{ID_FS_TYPE}!="linux_raid_member", GOTO="md_end"
PROGRAM="/sbin/md_raid_auto_readd.sh $devnode"
LABEL="md_end"
/sbin/md_raid_auto_readd.sh:
MDADM=/sbin/mdadm
DEVNAME=$1
export $(${MDADM} --examine --export ${DEVNAME})
if [ -z "${MD_UUID}" ]; then
exit 1
fi
UUID_LINK=$(readlink /dev/disk/by-id/md-uuid-${MD_UUID})
MD_DEVNAME=${UUID_LINK##*/}
export $(${MDADM} --detail --export /dev/${MD_DEVNAME})
if [ -z "${MD_METADATA}" ] ; then
exit 1
fi
if [ $(cat /sys/block/${MD_DEVNAME}/md/degraded) != 1 ]; then
echo "${MD_DEVNAME}: array not degraded, nothing to do"
exit 0
fi
MD_STATE=$(cat /sys/block/${MD_DEVNAME}/md/array_state)
if [ ${MD_STATE} != "clean" ] ; then
echo "${MD_DEVNAME}: array state ${MD_STATE}, cannot re-add"
exit 1
fi
MD_VARNAME="MD_DEVICE_dev_${DEVNAME##*/}_ROLE"
if [ ${!MD_VARNAME} = "spare" ] ; then
${MDADM} --manage /dev/${MD_DEVNAME} --re-add ${DEVNAME}
fi
Changes to v2:
- Add udev rules example to description
Changes to v1:
- use disk_uevent() as suggested by hch
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The nvme-loop's admin queue may be freed and reallocated, and we have to
reset the flag of NVME_CTRL_ADMIN_Q_STOPPED so that the flag can match
with the quiesce state of the admin queue.
nvme-loop is the only driver to reallocate request queue, and not see
such usage in other nvme drivers.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211014081710.1871747-6-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The current blk_mq_quiesce_queue() and blk_mq_unquiesce_queue() always
stops and starts the queue unconditionally. And there can be concurrent
quiesce/unquiesce coming from different unrelated code paths, so
unquiesce may come unexpectedly and start queue too early.
Prepare for supporting concurrent quiesce/unquiesce from multiple
contexts, so that we can address the above issue.
NVMe has very complicated quiesce/unquiesce use pattern, add one atomic
bit for makeiing sure that blk-mq quiece/unquiesce is always called in
pair.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211014081710.1871747-5-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add two helpers so that we can prepare for pairing quiescing and
unquiescing which will be done in next patch.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211014081710.1871747-4-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This memset in the fast path costs a lot of cycles on my setup. Here's a
top-of-profile of doing ~6.7M IOPS:
+ 5.90% io_uring [nvme] [k] nvme_queue_rq
+ 5.32% io_uring [nvme_core] [k] nvme_setup_cmd
+ 5.17% io_uring [kernel.vmlinux] [k] io_submit_sqes
+ 4.97% io_uring [kernel.vmlinux] [k] blkdev_direct_IO
and a perf diff with this patch:
0.92% +4.40% [nvme_core] [k] nvme_setup_cmd
reducing it from 5.3% to only 0.9%. This takes it from the 2nd most
cycle consumer to something that's mostly irrelevant.
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We don't have to worry about doing extra memsets by moving it outside
the protection of RQF_DONTPREP, as nvme doesn't do partial completions.
This is in preparation for making the read/write fast path not do a full
memset of the command.
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Trivial to do now, just need our own io_comp_batch on the stack and pass
that in to the usual command completion handling.
I pondered making this dependent on how many entries we had to process,
but even for a single entry there's no discernable difference in
performance or latency. Running a sync workload over io_uring:
t/io_uring -b512 -d1 -s1 -c1 -p0 -F1 -B1 -n2 /dev/nvme1n1 /dev/nvme2n1
yields the below performance before the patch:
IOPS=254820, BW=124MiB/s, IOS/call=1/1, inflight=(1 1)
IOPS=251174, BW=122MiB/s, IOS/call=1/1, inflight=(1 1)
IOPS=250806, BW=122MiB/s, IOS/call=1/1, inflight=(1 1)
and the following after:
IOPS=255972, BW=124MiB/s, IOS/call=1/1, inflight=(1 1)
IOPS=251920, BW=123MiB/s, IOS/call=1/1, inflight=(1 1)
IOPS=251794, BW=122MiB/s, IOS/call=1/1, inflight=(1 1)
which definitely isn't slower, about the same if you factor in a bit of
variance. For peak performance workloads, benchmarking shows a 2%
improvement.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Take advantage of struct io_comp_batch, if passed in to the nvme poll
handler. If it's set, rather than complete each request individually
inline, store them in the io_comp_batch list. We only do so for requests
that will complete successfully, anything else will be completed inline as
before.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
struct io_comp_batch contains a list head and a completion handler, which
will allow completions to more effciently completed batches of IO.
For now, no functional changes in this patch, we just define the
io_comp_batch structure and add the argument to the file_operations iopoll
handler.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Set the poll queue flag to enable polling, given that the multipath
node just dispatches the bios to a lower queue.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
Link: https://lore.kernel.org/r/20211012111226.760968-17-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Replace the blk_poll interface that requires the caller to keep a queue
and cookie from the submissions with polling based on the bio.
Polling for the bio itself leads to a few advantages:
- the cookie construction can made entirely private in blk-mq.c
- the caller does not need to remember the request_queue and cookie
separately and thus sidesteps their lifetime issues
- keeping the device and the cookie inside the bio allows to trivially
support polling BIOs remapping by stacking drivers
- a lot of code to propagate the cookie back up the submission path can
be removed entirely.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
Link: https://lore.kernel.org/r/20211012111226.760968-15-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Unlike the RWF_HIPRI userspace ABI which is intentionally kept vague,
the bio flag is specific to the polling implementation, so rename and
document it properly.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
Link: https://lore.kernel.org/r/20211012111226.760968-12-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Split the integrity/metadata handling definitions out into a new header.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20210920123328.1399408-17-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Decrease reference count of chardevice during char device deletion in
order to fix a memory leak. Add a release callabck for the device
associated chardev and move ida_simple_remove into the release function.
Fixes: 2637baed78 ("nvme: introduce generic per-namespace chardev")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Suggested-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Adam Manzanares <a.manzanares@samsung.com>
Reviewed-by: Javier González <javier@javigon.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The request tag is no longer the only component of the command id.
Fixes: e7006de6c2 ("nvme: code command_id with a genctr for use-after-free validation")
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
