There is a race condition in detaching as below:
A. detaching			B. Write request
(1) writing back
(2) write back done, set bdev
    state to clean.
(3) cached_dev_put() and
    schedule_work(&dc->detach);
				(4) write data [0 - 4K] directly
				    into backing and ack to user.
(5) power-failure...

When we restart this bcache device, this bdev is clean but not detached,
and read [0 - 4K], we will get unexpected old data from cache device.

To fix this problem, set the bdev state to none when we writeback done
in detaching, and then if power-failure happened as above, the data in
cache will not be used in next bcache device starting, it's detached, we
will read the correct data from backing derectly.
Signed-off-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Currently in the case where dev->blk_symlink_name fails to be allocates
the error return path attempts to set an end-of-string character to
the unallocated dev->blk_symlink_name causing a null pointer dereference
error. Fix this by returning with an explicity ENOMEM error (which also
is missing in the original code as was not initialized).

Fixes: 1eb54f8f ("block/rnbd: client: sysfs interface functions")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Addresses-Coverity: ("Dereference after null check")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

For every rnbd_clt_dev, we alloc the pathname and blk_symlink_name
statically to NAME_MAX which is 255 bytes. In most of the cases we only
need less than 10 bytes, so 500 bytes per block device are wasted.

This commit dynamically allocates memory buffer for pathname and
blk_symlink_name.
Signed-off-by: Md Haris Iqbal <haris.iqbal@cloud.ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Reviewed-by: Lutz Pogrell <lutz.pogrell@cloud.ionos.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Per the comment of kobject_init_and_add, we need to cleanup the memory
by call kobject_put.

Also we need to call kobject_del for the other failure cases if the
kobject_init_and_add doesn't fail.
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Reviewed-by: Md Haris Iqbal <haris.iqbal@cloud.ionos.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

describe force_close of device
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

The forceful close of an exported device is required
for the use case, when the client side hangs, is crashed,
or is not accessible.

There have been cases observed, where only some of
the devices are to be cleaned up, but the session shall
remain.

When the device is to be exported to a different
client host, server side cleanup is required.
Signed-off-by: Lutz Pogrell <lutz.pogrell@cloud.ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Reviewed-by: Gioh Kim <gi-oh.kim@cloud.ionos.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

When mapping a device,
/sys/devices/virtual/rnbd-client/ctl/devices/<device_id> was created.
But we found out that it had a problem when mapping the same file
on different servers. So we append the session name after the
device_id as below.
/sys/devices/virtual/rnbd-client/ctl/devices/<device_id>@<session_name>
Signed-off-by: Gioh Kim <gi-oh.kim@cloud.ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

/sys/block/rnbd<N> is created, not /sys/block/rnbd_client/rnbd<N>
Signed-off-by: Gioh Kim <gi-oh.kim@cloud.ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Previously, we can't map same device name from different sessions
due to the limitation of sysfs naming mechanism.

root@clt2:~# ls -l /sys/class/rnbd-client/ctl/devices/
total 0
lrwxrwxrwx 1 root 0 Sep  2 16:31 !dev!nullb1 -> ../../../block/rnbd0

We only use the device name in above, which caused device with
the same name can't be mapped from another server. To address
the issue, the sessname is appended to the node to differentiate
where the device comes from.

Also, we need to check if the pathname is existed in a specific
session instead of search it in global sess_list.
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Gioh Kim <gi-oh.kim@cloud.ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Reviewed-by: Md Haris Iqbal <haris.iqbal@cloud.ionos.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

During map_device if the given session exists, then the path parameter is
not used. In such a case, the path parameter is redundant.

This commit makes the path parameter optional for map_device. When the
path parameter is not given, if the session exists then that is used to
establish the rtrs connection.

If the session does not exist, and the path parameter is also missing,
then map_device fails.
Signed-off-by: Md Haris Iqbal <haris.iqbal@cloud.ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Pull NVMe updates from Christoph:

"nvme updates for 5.11

 - nvmet passthrough improvements (Chaitanya Kulkarni)
 - fcloop error injection support (James Smart)
 - read-only support for zoned namespaces without Zone Append
   (Javier González)
 - improve some error message (Minwoo Im)
 - reject I/O to offline fabrics namespaces (Victor Gladkov)
 - PCI queue allocation cleanups (Niklas Schnelle)
 - remove an unused allocation in nvmet (Amit Engel)
 - a Kconfig spelling fix (Colin Ian King)
 - nvme_req_qid simplication (Baolin Wang)"

* tag 'nvme-5.11-20201202' of git://git.infradead.org/nvme: (23 commits)
  nvme: export zoned namespaces without Zone Append support read-only
  nvme: rename bdev operations
  nvme: rename controller base dev_t char device
  nvme: remove unnecessary return values
  nvme: print a warning for when listing active namespaces fails
  nvme: improve an error message on Identify failure
  nvme-fabrics: reject I/O to offline device
  nvmet: fix a spelling mistake "incuding" -> "including" in Kconfig
  nvmet: make sure discovery change log event is protected
  nvmet: remove unused ctrl->cqs
  nvme-pci: don't allocate unused I/O queues
  nvme-pci: drop min() from nr_io_queues assignment
  nvmet: use inline bio for passthru fast path
  nvmet: use blk_rq_bio_prep instead of blk_rq_append_bio
  nvmet: remove op_flags for passthru commands
  nvme: split nvme_alloc_request()
  block: move blk_rq_bio_prep() to linux/blk-mq.h
  nvmet: add passthru io timeout value attr
  nvmet: add passthru admin timeout value attr
  nvme: use consistent macro name for timeout
  ...

Allow ZNS NVMe SSDs to present a read-only namespace when append is not
supported, instead of rejecting the namespace directly.

This allows (i) the namespace to be used in read-only mode, which is not
a problem as the append command only affects the write path, and (ii) to
use standard management tools such as nvme-cli to choose a different
format or firmware slot that is compatible with the Linux zoned block
device.
Signed-off-by: Javier González <javier.gonz@samsung.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Remane block device operations in preparation to add char device file
operations.
Signed-off-by: Javier González <javier.gonz@samsung.com>
Reviewed-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Rename controller base dev_t char device in preparation for adding a
namespace char device.
Signed-off-by: Javier González <javier.gonz@samsung.com>
Reviewed-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Cleanup unnecessary ret values that are not checked or used in
nvme_alloc_ns().
Signed-off-by: Javier González <javier.gonz@samsung.com>
Reviewed-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

During the scan_work, an Identify command is issued to figure out which
namespaces are active.  If this command fails, the nvme driver falls back
to scanning namespaces sequentially.  In this situation, we don't see
any warnings and don't even know whether list-ns command has been failed
or not easiliy.

Printa warning when the Identify command executin fail:

[    1.108399] nvme nvme0: Identify NS List failed (status=0x400b)
[    1.109583] nvme0n1: detected capacity change from 0 to 1048576
[    1.112186] nvme nvme0: Identify Descriptors failed (nsid=2, status=0x4002)
[    1.113929] nvme nvme0: Identify Descriptors failed (nsid=3, status=0x4002)
[    1.116537] nvme nvme0: Identify Descriptors failed (nsid=4, status=0x4002)
...
Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Add the namespace ID to the error message when the Identify command used
to retrieve the Namespace Identification Descriptor list fails.

This avoids rather useless and duplicative messages like the following:
[    1.321031] nvme nvme0: Identify Descriptors failed (16386)
[    1.321948] nvme nvme0: Identify Descriptors failed (16386)
[    1.322872] nvme nvme0: Identify Descriptors failed (16386)
[    1.323775] nvme nvme0: Identify Descriptors failed (16386)
[    1.324687] nvme nvme0: Identify Descriptors failed (16386)
...

Also, print the nvme status code in hexadecimal rather than decimal
format rather for better readability.
Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Commands get stuck while Host NVMe-oF controller is in reconnect state.
The controller enters into reconnect state when it loses connection with
the target.  It tries to reconnect every 10 seconds (default) until
a successful reconnect or until the reconnect time-out is reached.
The default reconnect time out is 10 minutes.

Applications are expecting commands to complete with success or error
within a certain timeout (30 seconds by default).  The NVMe host is
enforcing that timeout while it is connected, but during reconnect the
timeout is not enforced and commands may get stuck for a long period or
even forever.

To fix this long delay due to the default timeout, introduce new
"fast_io_fail_tmo" session parameter.  The timeout is measured in seconds
from the controller reconnect and any command beyond that timeout is
rejected.  The new parameter value may be passed during 'connect'.
The default value of -1 means no timeout (similar to current behavior).
Signed-off-by: Victor Gladkov <victor.gladkov@kioxia.com>
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chao Leng <lengchao@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

There is a spelling mistake in the Kconfig help text. Fix it.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Generation counter is protected by nvmet_config_sem. Make sure the
callers that call functions that might change it, are calling it
properly.
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

remove unused cqs from nvmet_ctrl struct
this will reduce the allocated memory.
Signed-off-by: Amit <amit.engel@dell.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

currently the NVME_QUIRK_SHARED_TAGS quirk for Apple devices is handled
during the assignment of nr_io_queues in nvme_setup_io_queues().
This however means that for these devices nvme_max_io_queues() will
actually not return the supported maximum which is confusing and
unexpected and also means that in nvme_probe() we are allocating
for I/O queues that will never be used.
Fix this by moving the quirk handling into nvme_max_io_queues().
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

in nvme_setup_io_queues() the number of I/O queues is set to either 1 in
case of a quirky Apple device or to the min of nvme_max_io_queues() or
dev->nr_allocated_queues - 1.
This is unnecessarily complicated as dev->nr_allocated_queues is only
assigned once and is nvme_max_io_queues() + 1.
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

In nvmet_passthru_execute_cmd() which is a high frequency function
it uses bio_alloc() which leads to memory allocation from the fs pool
for each I/O.

For NVMeoF nvmet_req we already have inline_bvec allocated as a part of
request allocation that can be used with preallocated bio when we
already know the size of request before bio allocation with bio_alloc(),
which we already do.

Introduce a bio member for the nvmet_req passthru anon union. In the
fast path, check if we can get away with inline bvec and bio from
nvmet_req with bio_init() call before actually allocating from the
bio_alloc().

This will be useful to avoid any new memory allocation under high
memory pressure situation and get rid of any extra work of
allocation (bio_alloc()) vs initialization (bio_init()) when
transfer len is < NVMET_MAX_INLINE_DATA_LEN that user can configure at
compile time.
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

The function blk_rq_append_bio() is a genereric API written for all
types driver (having bounce buffers) and different context (where
request is already having a bio i.e. rq->bio != NULL).

It does mainly three things: calculating the segments, bounce queue and
if req->bio == NULL call blk_rq_bio_prep() or handle low level merge()
case.

The NVMe PCIe and fabrics transports currently does not use queue
bounce mechanism. In order to find this for each request processing
in the passthru blk_rq_append_bio() does extra work in the fast path
for each request.

When I ran I/Os with different block sizes on the passthru controller
I found that we can reuse the req->sg_cnt instead of iterating over the
bvecs to find out nr_segs in blk_rq_append_bio(). This calculation in
blk_rq_append_bio() is a duplication of work given that we have the
value in req->sg_cnt. (correct me here if I'm wrong).

With NVMe passthru request based driver we allocate fresh request each
time, so every call to blk_rq_append_bio() rq->bio will be NULL i.e.
we don't really need the second condition in the blk_rq_append_bio()
and the resulting error condition in the caller of blk_rq_append_bio().

So for NVMeOF passthru driver recalculating the segments, bounce check
and ll_back_merge code is not needed such that we can get away with the
minimal version of the blk_rq_append_bio() which removes the error check
in the fast path along with extra variable in nvmet_passthru_map_sg().

This patch updates the nvmet_passthru_map_sg() such that it does only
appending the bio to the request in the context of the NVMeOF Passthru
driver. Following are perf numbers :-

With current implementation (blk_rq_append_bio()) :-
----------------------------------------------------
+    5.80%     0.02%  kworker/0:2-mm_  [nvmet]  [k] nvmet_passthru_execute_cmd
+    5.44%     0.01%  kworker/0:2-mm_  [nvmet]  [k] nvmet_passthru_execute_cmd
+    4.88%     0.00%  kworker/0:2-mm_  [nvmet]  [k] nvmet_passthru_execute_cmd
+    5.44%     0.01%  kworker/0:2-mm_  [nvmet]  [k] nvmet_passthru_execute_cmd
+    4.86%     0.01%  kworker/0:2-mm_  [nvmet]  [k] nvmet_passthru_execute_cmd
+    5.17%     0.00%  kworker/0:2-eve  [nvmet]  [k] nvmet_passthru_execute_cmd

With this patch using blk_rq_bio_prep() :-
----------------------------------------------------
+    3.14%     0.02%  kworker/0:2-eve  [nvmet]  [k] nvmet_passthru_execute_cmd
+    3.26%     0.01%  kworker/0:2-eve  [nvmet]  [k] nvmet_passthru_execute_cmd
+    5.37%     0.01%  kworker/0:2-mm_  [nvmet]  [k] nvmet_passthru_execute_cmd
+    5.18%     0.02%  kworker/0:2-eve  [nvmet]  [k] nvmet_passthru_execute_cmd
+    4.84%     0.02%  kworker/0:2-mm_  [nvmet]  [k] nvmet_passthru_execute_cmd
+    4.87%     0.01%  kworker/0:2-mm_  [nvmet]  [k] nvmet_passthru_execute_cmd
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

For passthru commands setting op_flags has no meaning. Remove the code
that sets the op flags in nvmet_passthru_map_sg().
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Right now nvme_alloc_request() allocates a request from block layer
based on the value of the qid. When qid set to NVME_QID_ANY it used
blk_mq_alloc_request() else blk_mq_alloc_request_hctx().

The function nvme_alloc_request() is called from different context, The
only place where it uses non NVME_QID_ANY value is for fabrics connect
commands :-

nvme_submit_sync_cmd()		NVME_QID_ANY
nvme_features()			NVME_QID_ANY
nvme_sec_submit()		NVME_QID_ANY
nvmf_reg_read32()		NVME_QID_ANY
nvmf_reg_read64()		NVME_QID_ANY
nvmf_reg_write32()		NVME_QID_ANY
nvmf_connect_admin_queue()	NVME_QID_ANY
nvme_submit_user_cmd()		NVME_QID_ANY
	nvme_alloc_request()
nvme_keep_alive()		NVME_QID_ANY
	nvme_alloc_request()
nvme_timeout()			NVME_QID_ANY
	nvme_alloc_request()
nvme_delete_queue()		NVME_QID_ANY
	nvme_alloc_request()
nvmet_passthru_execute_cmd()	NVME_QID_ANY
	nvme_alloc_request()
nvmf_connect_io_queue() 	QID
	__nvme_submit_sync_cmd()
		nvme_alloc_request()

With passthru nvme_alloc_request() now falls into the I/O fast path such
that blk_mq_alloc_request_hctx() is never gets called and that adds
additional branch check in fast path.

Split the nvme_alloc_request() into nvme_alloc_request() and
nvme_alloc_request_qid().

Replace each call of the nvme_alloc_request() with NVME_QID_ANY param
with a call to newly added nvme_alloc_request() without NVME_QID_ANY.

Replace a call to nvme_alloc_request() with QID param with a call to
newly added nvme_alloc_request() and nvme_alloc_request_qid()
based on the qid value set in the __nvme_submit_sync_cmd().
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

This is a preparation patch to have minimal block layer request bio
append functionality in the context of the NVMeOF Passthru driver which
falls in the fast path and doesn't need calls from blk_rq_append_bio().
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

NVMeOF controller in the passsthru mode is capable of handling wide set
of I/O commands including vender specific passhtru io comands.

The vendor specific I/O commands are used to read the large drive
logs and can take longer than default NVMe commands, i.e. for
passthru requests the timeout value may differ from the passthru
controller's default timeout values (nvme-core:io_timeout).

Add a configfs attribute so that user can set the io timeout values.
In case if this configfs value is not set nvme_alloc_request() will set
the NVME_IO_TIMEOUT value when request queuedata is NULL.
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

NVMeOF controller in the passsthru mode is capable of handling wide set
of admin commands including vender specific passhtru admin comands.

The vendor specific admin commands are used to read the large drive
logs and can take longer than default NVMe commands, i.e. for
passthru requests the timeout value may differ from the passthru
controller's default timeout values (nvme-core:admin_timeout).

Add a configfs attribute so that user can set the admin timeout values.
In case if this configfs value is not set nvme_alloc_request() will set
the ADMIN_TIMEOUT value when request queuedata is NULL.
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

This is purely a clenaup patch, add prefix NVME to the ADMIN_TIMEOUT to
make consistent with NVME_IO_TIMEOUT.
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

The function nvme_alloc_request() is called from different context
(I/O and Admin queue) where callers do not consider the I/O timeout when
called from I/O queue context.

Update nvme_alloc_request() to set the default I/O and Admin timeout
value based on whether the queuedata is set or not.
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Use the request's '->mq_hctx->queue_num' directly to simplify the
nvme_req_qid() function.
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Add sysfs attribute to specify parameters for dropping a command.  The
attribute takes a string of:

  <opcode>:<starting a what instance>:<number of times>

Opcode is formatted as lower 8 bits are opcode.  If a fabrics opcode, a
bit above bits 7:0 will be set.

Once set, each sqe is looked at. If the opcode matches the running
instance count is updated. If the instance count is in the range of where
to drop (based on starting and # of times), then drop the command by not
passing it to the target layer.
Signed-off-by: James Smart <james.smart@broadcom.com>

Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.11/drivers

Pull MD changes from Song:

"Summary:
 1. Fix race condition in md_ioctl(), by Dae R. Jeong;
 2. Initialize read_slot properly for raid10, by Kevin Vigor;
 3. Code cleanup, by Pankaj Gupta;
 4. md-cluster resync/reshape fix, by Zhao Heming."

* 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md/cluster: fix deadlock when node is doing resync job
  md/cluster: block reshape with remote resync job
  md: use current request time as base for ktime comparisons
  md: add comments in md_flush_request()
  md: improve variable names in md_flush_request()
  md/raid10: initialize r10_bio->read_slot before use.
  md: fix a warning caused by a race between concurrent md_ioctl()s

md-cluster uses MD_CLUSTER_SEND_LOCK to make node can exclusively send msg.
During sending msg, node can concurrently receive msg from another node.
When node does resync job, grab token_lockres:EX may trigger a deadlock:
```
nodeA                       nodeB
--------------------     --------------------
a.
send METADATA_UPDATED
held token_lockres:EX
                         b.
                         md_do_sync
                          resync_info_update
                            send RESYNCING
                             + set MD_CLUSTER_SEND_LOCK
                             + wait for holding token_lockres:EX

                         c.
                         mdadm /dev/md0 --remove /dev/sdg
                          + held reconfig_mutex
                          + send REMOVE
                             + wait_event(MD_CLUSTER_SEND_LOCK)

                         d.
                         recv_daemon //METADATA_UPDATED from A
                          process_metadata_update
                           + (mddev_trylock(mddev) ||
                              MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD)
                             //this time, both return false forever
```
Explaination:
a. A send METADATA_UPDATED
   This will block another node to send msg

b. B does sync jobs, which will send RESYNCING at intervals.
   This will be block for holding token_lockres:EX lock.

c. B do "mdadm --remove", which will send REMOVE.
   This will be blocked by step <b>: MD_CLUSTER_SEND_LOCK is 1.

d. B recv METADATA_UPDATED msg, which send from A in step <a>.
   This will be blocked by step <c>: holding mddev lock, it makes
   wait_event can't hold mddev lock. (btw,
   MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD keep ZERO in this scenario.)

There is a similar deadlock in commit 0ba95977
("md-cluster: use sync way to handle METADATA_UPDATED msg")
In that commit, step c is "update sb". This patch step c is
"mdadm --remove".

For fixing this issue, we can refer the solution of function:
metadata_update_start. Which does the same grab lock_token action.
lock_comm can use the same steps to avoid deadlock. By moving
MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD from lock_token to lock_comm.
It enlarge a little bit window of MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD,
but it is safe & can break deadlock.

Repro steps (I only triggered 3 times with hundreds tests):

two nodes share 3 iSCSI luns: sdg/sdh/sdi. Each lun size is 1GB.
```
ssh root@node2 "mdadm -S --scan"
mdadm -S --scan
for i in {g,h,i};do dd if=/dev/zero of=/dev/sd$i oflag=direct bs=1M \
count=20; done

mdadm -C /dev/md0 -b clustered -e 1.2 -n 2 -l mirror /dev/sdg /dev/sdh \
 --bitmap-chunk=1M
ssh root@node2 "mdadm -A /dev/md0 /dev/sdg /dev/sdh"

sleep 5

mkfs.xfs /dev/md0
mdadm --manage --add /dev/md0 /dev/sdi
mdadm --wait /dev/md0
mdadm --grow --raid-devices=3 /dev/md0

mdadm /dev/md0 --fail /dev/sdg
mdadm /dev/md0 --remove /dev/sdg
mdadm --grow --raid-devices=2 /dev/md0
```

test script will hung when executing "mdadm --remove".

```
 # dump stacks by "echo t > /proc/sysrq-trigger"
md0_cluster_rec D    0  5329      2 0x80004000
Call Trace:
 __schedule+0x1f6/0x560
 ? _cond_resched+0x2d/0x40
 ? schedule+0x4a/0xb0
 ? process_metadata_update.isra.0+0xdb/0x140 [md_cluster]
 ? wait_woken+0x80/0x80
 ? process_recvd_msg+0x113/0x1d0 [md_cluster]
 ? recv_daemon+0x9e/0x120 [md_cluster]
 ? md_thread+0x94/0x160 [md_mod]
 ? wait_woken+0x80/0x80
 ? md_congested+0x30/0x30 [md_mod]
 ? kthread+0x115/0x140
 ? __kthread_bind_mask+0x60/0x60
 ? ret_from_fork+0x1f/0x40

mdadm           D    0  5423      1 0x00004004
Call Trace:
 __schedule+0x1f6/0x560
 ? __schedule+0x1fe/0x560
 ? schedule+0x4a/0xb0
 ? lock_comm.isra.0+0x7b/0xb0 [md_cluster]
 ? wait_woken+0x80/0x80
 ? remove_disk+0x4f/0x90 [md_cluster]
 ? hot_remove_disk+0xb1/0x1b0 [md_mod]
 ? md_ioctl+0x50c/0xba0 [md_mod]
 ? wait_woken+0x80/0x80
 ? blkdev_ioctl+0xa2/0x2a0
 ? block_ioctl+0x39/0x40
 ? ksys_ioctl+0x82/0xc0
 ? __x64_sys_ioctl+0x16/0x20
 ? do_syscall_64+0x5f/0x150
 ? entry_SYSCALL_64_after_hwframe+0x44/0xa9

md0_resync      D    0  5425      2 0x80004000
Call Trace:
 __schedule+0x1f6/0x560
 ? schedule+0x4a/0xb0
 ? dlm_lock_sync+0xa1/0xd0 [md_cluster]
 ? wait_woken+0x80/0x80
 ? lock_token+0x2d/0x90 [md_cluster]
 ? resync_info_update+0x95/0x100 [md_cluster]
 ? raid1_sync_request+0x7d3/0xa40 [raid1]
 ? md_do_sync.cold+0x737/0xc8f [md_mod]
 ? md_thread+0x94/0x160 [md_mod]
 ? md_congested+0x30/0x30 [md_mod]
 ? kthread+0x115/0x140
 ? __kthread_bind_mask+0x60/0x60
 ? ret_from_fork+0x1f/0x40
```

At last, thanks for Xiao's solution.

Cc: stable@vger.kernel.org
Signed-off-by: Zhao Heming <heming.zhao@suse.com>
Suggested-by: Xiao Ni <xni@redhat.com>
Reviewed-by: Xiao Ni <xni@redhat.com>
Signed-off-by: Song Liu <songliubraving@fb.com>

Reshape request should be blocked with ongoing resync job. In cluster
env, a node can start resync job even if the resync cmd isn't executed
on it, e.g., user executes "mdadm --grow" on node A, sometimes node B
will start resync job. However, current update_raid_disks() only check
local recovery status, which is incomplete. As a result, we see user will
execute "mdadm --grow" successfully on local, while the remote node deny
to do reshape job when it doing resync job. The inconsistent handling
cause array enter unexpected status. If user doesn't observe this issue
and continue executing mdadm cmd, the array doesn't work at last.

Fix this issue by blocking reshape request. When node executes "--grow"
and detects ongoing resync, it should stop and report error to user.

The following script reproduces the issue with ~100% probability.
(two nodes share 3 iSCSI luns: sdg/sdh/sdi. Each lun size is 1GB)
```
 # on node1, node2 is the remote node.
ssh root@node2 "mdadm -S --scan"
mdadm -S --scan
for i in {g,h,i};do dd if=/dev/zero of=/dev/sd$i oflag=direct bs=1M \
count=20; done

mdadm -C /dev/md0 -b clustered -e 1.2 -n 2 -l mirror /dev/sdg /dev/sdh
ssh root@node2 "mdadm -A /dev/md0 /dev/sdg /dev/sdh"

sleep 5

mdadm --manage --add /dev/md0 /dev/sdi
mdadm --wait /dev/md0
mdadm --grow --raid-devices=3 /dev/md0

mdadm /dev/md0 --fail /dev/sdg
mdadm /dev/md0 --remove /dev/sdg
mdadm --grow --raid-devices=2 /dev/md0
```

Cc: stable@vger.kernel.org
Signed-off-by: Zhao Heming <heming.zhao@suse.com>
Signed-off-by: Song Liu <songliubraving@fb.com>

Request coalescing logic uses 'prev_flush_start' as base to
compare the current request start time. 'prev_flush_start' is
updated in other context.

This patch changes this by using ktime comparison base to
'req_start' for better readability of code.
Signed-off-by: Pankaj Gupta <pankaj.gupta@cloud.ionos.com>
Signed-off-by: Song Liu <songliubraving@fb.com>

Request coalescing logic is dependent on flush time update in other
context. This patch adds comments to understand the code flow better.
Signed-off-by: Pankaj Gupta <pankaj.gupta@cloud.ionos.com>
Signed-off-by: Song Liu <songliubraving@fb.com>

This patch improves readability by using better variable names
in flush request coalescing logic.
Signed-off-by: Pankaj Gupta <pankaj.gupta@cloud.ionos.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Song Liu <songliubraving@fb.com>