IOCB_NOWAIT translates to IOMAP_NOWAIT for iomaps.
This is used by XFS in the XFS patch.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NGoldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Find out if the I/O will trigger a wait due to writeback. If yes,
return -EAGAIN.

Return -EINVAL for buffered AIO: there are multiple causes of
delay such as page locks, dirty throttling logic, page loading
from disk etc. which cannot be taken care of.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NGoldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

RWF_NOWAIT informs kernel to bail out if an AIO request will block
for reasons such as file allocations, or a writeback triggered,
or would block while allocating requests while performing
direct I/O.

RWF_NOWAIT is translated to IOCB_NOWAIT for iocb->ki_flags.

FMODE_AIO_NOWAIT is a flag which identifies the file opened is capable
of returning -EAGAIN if the AIO call will block. This must be set by
supporting filesystems in the ->open() call.

Filesystems xfs, btrfs and ext4 would be supported in the following patches.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NGoldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

aio_rw_flags is introduced in struct iocb (using aio_reserved1) which will
carry the RWF_* flags. We cannot use aio_flags because they are not
checked for validity which may break existing applications.

Note, the only place RWF_HIPRI comes in effect is dio_await_one().
All the rest of the locations, aio code return -EIOCBQUEUED before the
checks for RWF_HIPRI.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NGoldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

filemap_range_has_page() return true if the file's mapping has
a page within the range mentioned. This function will be used
to check if a write() call will cause a writeback of previous
writes.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NGoldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Also added RWF_SUPPORTED to encompass all flags.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NGoldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When nvme_kill_queues() is run, queues may be in
quiesced state, so we forcibly unquiesce queues to avoid
blocking dispatch, and I/O hang can be avoided in
remove path.

Peviously we use blk_mq_start_stopped_hw_queues() as
counterpart of blk_mq_quiesce_queue(), now we have
introduced blk_mq_unquiesce_queue(), so use it explicitly.

Cc: linux-nvme@lists.infradead.org
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This patch reverts commit 2719aa21(blk-mq: don't use
sync workqueue flushing from drivers) because only
blk_mq_quiesce_queue() need the sync flush, and now
we don't need to stop queue any more, so revert it.

Also changes to cancel_delayed_work() in blk_mq_stop_hw_queue().
Reviewed-by: NBart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

BLK_MQ_S_STOPPED may not be observed in other concurrent I/O paths,
we can't guarantee that dispatching won't happen after returning
from the APIs of stopping queue.

So clarify the fact and avoid potential misuse.
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NBart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Queue can be started by other blk-mq APIs and can be used in
different cases, this limits uses of blk_mq_quiesce_queue()
if it is based on stopping queue, and make its usage very
difficult, especially users have to use the stop queue APIs
carefully for avoiding to break blk_mq_quiesce_queue().

We have applied the QUIESCED flag for draining and blocking
dispatch, so it isn't necessary to stop queue any more.

After stopping queue is removed, blk_mq_quiesce_queue() can
be used safely and easily, then users won't worry about queue
restarting during quiescing at all.
Reviewed-by: NBart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Actually what we want to get from blk_mq_quiesce_queue()
isn't only to wait for completion of all ongoing .queue_rq().

In the typical context of canceling requests, we need to
make sure that the following is done in the dispatch path
before starting to cancel requests:

	- failed dispatched request is finished
	- busy dispatched request is requeued, and the STARTED
	flag is cleared

So update comment to keep code, doc and our expection consistent.
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

It is required that no dispatch can happen any more once
blk_mq_quiesce_queue() returns, and we don't have such requirement
on APIs of stopping queue.

But blk_mq_quiesce_queue() still may not block/drain dispatch in the
the case of BLK_MQ_S_START_ON_RUN, so use the new introduced flag of
QUEUE_FLAG_QUIESCED and evaluate it inside RCU read-side critical
sections for fixing this issue.

Also blk_mq_quiesce_queue() is implemented via stopping queue, which
limits its uses, and easy to cause race, because any queue restart in
other paths may break blk_mq_quiesce_queue(). With the introduced
flag of QUEUE_FLAG_QUIESCED, we don't need to depend on stopping queue
for quiescing any more.
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NBart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

blk_mq_unquiesce_queue() is used for unquiescing the
queue explicitly, so replace blk_mq_start_stopped_hw_queues()
with it.

For the scsi part, this patch takes Bart's suggestion to
switch to block quiesce/unquiesce API completely.

Cc: linux-nvme@lists.infradead.org
Cc: linux-scsi@vger.kernel.org
Cc: dm-devel@redhat.com
Reviewed-by: NBart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

blk_mq_start_stopped_hw_queues() is used implictly
as counterpart of blk_mq_quiesce_queue() for unquiescing queue,
so we introduce blk_mq_unquiesce_queue() and make it
as counterpart of blk_mq_quiesce_queue() explicitly.

This function is for improving the current quiescing mechanism
in the following patches.
Reviewed-by: NBart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This patch introduces blk_mq_quiesce_queue_nowait() so
that we can workaround mpt3sas for quiescing its queue.

Once mpt3sas is fixed, we can remove this helper.
Reviewed-by: NBart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We usually put blk_mq_*() into include/linux/blk-mq.h, so
move this API into there.
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NBart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

blk_bio_segment_split() makes sure bios have no more than
BIO_MAX_PAGES entries in the bi_io_vec.
This was done because bio_clone_bioset() (when given a
mempool bioset) could not handle larger io_vecs.

No driver uses bio_clone_bioset() any more, they all
use bio_clone_fast() if anything, and bio_clone_fast()
doesn't clone the bi_io_vec.

The main user of of bio_clone_bioset() at this level
is bounce.c, and bouncing now happens before blk_bio_segment_split(),
so that is not of concern.

So remove the big helpful comment and the code.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

bio_clone() is no longer used.
Only bio_clone_bioset() or bio_clone_fast().
This is for the best, as bio_clone() used fs_bio_set,
and filesystems are unlikely to want to use bio_clone().

So remove bio_clone() and all references.
This includes a fix to some incorrect documentation.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This function allocates a bio, then a collection
of pages.  It copes with failure.

It currently uses a mempool() to allocate the bio,
but alloc_page() to allocate the pages.  These fail
in different ways, so the usage is inconsistent.

Change the bio_clone() to bio_clone_kmalloc()
so that no pool is used either for the bio or the pages.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NKent Overstreet <kent.overstreet@gmail.com>
Reviewed-by : Ming Lei <ming.lei@redhat.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

bios that are re-submitted will pass through blk_queue_split() when
blk_queue_bio() is called, and this will split the bio if necessary.
There is no longer any need to do this splitting in xen-blkfront.
Acked-by: NRoger Pau Monné <roger.pau@citrix.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

pblk_submit_read() uses bio_clone_bioset() but doesn't change the
io_vec, so bio_clone_fast() is a better choice.

It also uses fs_bio_set which is intended for filesystems.  Using it
in a device driver can deadlock.
So allocate a new bioset, and and use bio_clone_fast().
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJavier González <javier@cnexlabs.com>
Tested-by: NJavier González <javier@cnexlabs.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

pktcdvd doesn't change the bi_io_vec of the clone bio,
so it is more efficient to use bio_clone_fast(), and not clone
the bi_io_vec.
This requires providing a bio_set, and it is safest to
provide a dedicated bio_set rather than sharing
fs_bio_set, which filesytems use.
This new bio_set, pkt_bio_set, can also be use for the bio_split()
call as the two allocations (bio_clone_fast, and bio_split) are
independent, neither can block a bio allocated by the other.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

drbd does not modify the bi_io_vec of the cloned bio,
so there is no need to clone that part.  So bio_clone_fast()
is the better choice.
For bio_clone_fast() we need to specify a bio_set.
We could use fs_bio_set, which bio_clone() uses, or
drbd_md_io_bio_set, which drbd uses for metadata, but it is
generally best to avoid sharing bio_sets unless you can
be certain that there are no interdependencies.

So create a new bio_set, drbd_io_bio_set, and use bio_clone_fast().

Also remove a "XXX cannot fail ???" comment because it definitely
cannot fail - bio_clone_fast() doesn't fail if the GFP flags allow for
sleeping.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

bio_clone() makes a copy of the bi_io_vec, but rbd never changes that,
so there is no need for a copy.
bio_clone_fast() can be used instead, which avoids making the copy.

This requires that we provide a bio_set.  bio_clone() uses fs_bio_set,
but it isn't, in general, safe to use the same bio_set at different
levels of the stack, as that can lead to deadlocks.  As filesystems
use fs_bio_set, block devices shouldn't.

As rbd never stacks, it is safe to have a single global bio_set for
all rbd devices to use.  So allocate that when the module is
initialised, and use it with bio_clone_fast().
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since commit 23688bf4 ("block: ensure to split after potentially
bouncing a bio") blk_queue_bounce() is called *before*
blk_queue_split().
This means that:
 1/ the comments blk_queue_split() about bounce buffers are
    irrelevant, and
 2/ a very large bio (more than BIO_MAX_PAGES) will no longer be
    split before it arrives at blk_queue_bounce(), leading to the
    possibility that bio_clone_bioset() will fail and a NULL
    will be dereferenced.

Separately, blk_queue_bounce() shouldn't use fs_bio_set as the bio
being copied could be from the same set, and this could lead to a
deadlock.

So:
 - allocate 2 private biosets for blk_queue_bounce, one for
   splitting enormous bios and one for cloning bios.
 - add code to split a bio that exceeds BIO_MAX_PAGES.
 - Fix up the comments in blk_queue_split()

Credit-to: Ming Lei <tom.leiming@gmail.com> (suggested using single bio_for_each_segment loop)
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

A rescuing bioset is only useful if there might be bios from
that same bioset on the bio_list_on_stack queue at a time
when bio_alloc_bioset() is called.  This never applies to
q->bio_split.

Allocations from q->bio_split are only ever made from
blk_queue_split() which is only ever called early in each of
various make_request_fn()s.  The original bio (call this A)
is then passed to generic_make_request() and is placed on
the bio_list_on_stack queue, and the bio that was allocated
from q->bio_split (B) is processed.

The processing of this may cause other bios to be passed to
generic_make_request() or may even cause the bio B itself to
be passed, possible after some prefix has been split off
(using some other bioset).

generic_make_request() now guarantees that all of these bios
(B and dependants) will be fully processed before the tail
of the original bio A gets handled.  None of these early bios
can possible trigger an allocation from the original
q->bio_split as they are either too small to require
splitting or (more likely) are destined for a different queue.

The next time that the original q->bio_split might be used
by this thread is when A is processed again, as it might
still be too big to handle directly.  By this time there
cannot be any other bios allocated from q->bio_split in the
generic_make_request() queue.  So no rescuing will ever be
needed.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This patch converts bioset_create() to not create a workqueue by
default, so alloctions will never trigger punt_bios_to_rescuer().  It
also introduces a new flag BIOSET_NEED_RESCUER which tells
bioset_create() to preserve the old behavior.

All callers of bioset_create() that are inside block device drivers,
are given the BIOSET_NEED_RESCUER flag.

biosets used by filesystems or other top-level users do not
need rescuing as the bio can never be queued behind other
bios.  This includes fs_bio_set, blkdev_dio_pool,
btrfs_bioset, xfs_ioend_bioset, and one allocated by
target_core_iblock.c.

biosets used by md/raid do not need rescuing as
their usage was recently audited and revised to never
risk deadlock.

It is hoped that most, if not all, of the remaining biosets
can end up being the non-rescued version.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Credit-to: Ming Lei <ming.lei@redhat.com> (minor fixes)
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

"flags" arguments are often seen as good API design as they allow
easy extensibility.
bioset_create_nobvec() is implemented internally as a variation in
flags passed to __bioset_create().

To support future extension, make the internal structure part of the
API.
i.e. add a 'flags' argument to bioset_create() and discard
bioset_create_nobvec().

Note that the bio_split allocations in drivers/md/raid* do not need
the bvec mempool - they should have used bioset_create_nobvec().
Suggested-by: NChristoph Hellwig <hch@infradead.org>
Reviewed-by: NChristoph Hellwig <hch@infradead.org>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

blk_queue_split() is always called with the last arg being q->bio_split,
where 'q' is the first arg.

Also blk_queue_split() sometimes uses the passed-in 'bs' and sometimes uses
q->bio_split.

This is inconsistent and unnecessary.  Remove the last arg and always use
q->bio_split inside blk_queue_split()
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Credit-to: Javier González <jg@lightnvm.io> (Noticed that lightnvm was missed)
Reviewed-by: NJavier González <javier@cnexlabs.com>
Tested-by: NJavier González <javier@cnexlabs.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Move most code into blk_mq_rq_ctx_init, and the rest into
blk_mq_get_request.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This patch makes sure we always allocate requests in the core blk-mq
code and use a common prepare_request method to initialize them for
both mq I/O schedulers.  For Kyber and additional limit_depth method
is added that is called before allocating the request.

Also because none of the intializations can really fail the new method
does not return an error - instead the bfq finish method is hardened
to deal with the no-IOC case.

Last but not least this removes the abuse of RQF_QUEUE by the blk-mq
scheduling code as RQF_ELFPRIV is all that is needed now.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

blk_mq_sched_assign_ioc now only handles the assigned of the ioc if
the schedule needs it (bfq only at the moment).  The caller to the
per-request initializer is moved out so that it can be merged with
a similar call for the kyber I/O scheduler.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

icq_to_bic is a container_of operation, so we need to check for NULL
before it.  Also move the check outside the spinlock while we're at
it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Merge three functions only tail-called by blk_mq_free_request into
blk_mq_free_request.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

No need to have two different callouts of bfq vs kyber.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Having these as separate helpers in a header really does not help
readability, or my chances to refactor this code sanely.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Having them out of line in blk-mq-sched.c just makes the code flow
unnecessarily complicated.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When a filesystem is mounted from a loop device, writes are
throttled by balance_dirty_pages() twice: once when writing
to the filesystem and once when the loop_handle_cmd() writes
to the backing file.  This double-throttling can trigger
positive feedback loops that create significant delays.  The
throttling at the lower level is seen by the upper level as
a slow device, so it throttles extra hard.

The PF_LESS_THROTTLE flag was created to handle exactly this
circumstance, though with an NFS filesystem mounted from a
local NFS server.  It reduces the throttling on the lower
layer so that it can proceed largely unthrottled.

To demonstrate this, create a filesystem on a loop device
and write (e.g. with dd) several large files which combine
to consume significantly more than the limit set by
/proc/sys/vm/dirty_ratio or dirty_bytes.  Measure the total
time taken.

When I do this directly on a device (no loop device) the
total time for several runs (mkfs, mount, write 200 files,
umount) is fairly stable: 28-35 seconds.
When I do this over a loop device the times are much worse
and less stable.  52-460 seconds.  Half below 100seconds,
half above.
When I apply this patch, the times become stable again,
though not as fast as the no-loop-back case: 53-72 seconds.

There may be room for further improvement as the total overhead still
seems too high, but this is a big improvement.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <tom.leiming@gmail.com>
Suggested-by: NMichal Hocko <mhocko@suse.com>
Acked-by: NMichal Hocko <mhocko@suse.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>