Similar to the simple fast path, but we now need a dio structure to
track multiple-bio completions.  It's basically a cut-down version
of the new iomap-based direct I/O code for filesystems, but without
all the logic to call into the filesystem for extent lookup or
allocation, and without the complex I/O completion workqueue handler
for AIO - instead we just use the FUA bit on the bios to ensure
data is flushed to stable storage.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

Split the op setting code into a helper, use it in both places.
Signed-off-by: Jens Axboe <axboe@fb.com>

Just alloc the bio_vec array if we exceed the inline limit.
Signed-off-by: Jens Axboe <axboe@fb.com>

The previous commit introduced the hybrid sleep/poll mode. Take
that one step further, and use the completion latencies to
automatically sleep for half the mean completion time. This is
a good approximation.

This changes the 'io_poll_delay' sysfs file a bit to expose the
various options. Depending on the value, the polling code will
behave differently:

-1	Never enter hybrid sleep mode
 0	Use half of the completion mean for the sleep delay
>0	Use this specific value as the sleep delay
Signed-off-by: Jens Axboe <axboe@fb.com>
Tested-By: Stephen Bates <sbates@raithlin.com>
Reviewed-By: Stephen Bates <sbates@raithlin.com>

This patch enables a hybrid polling mode. Instead of polling after IO
submission, we can induce an artificial delay, and then poll after that.
For example, if the IO is presumed to complete in 8 usecs from now, we
can sleep for 4 usecs, wake up, and then do our polling. This still puts
a sleep/wakeup cycle in the IO path, but instead of the wakeup happening
after the IO has completed, it'll happen before. With this hybrid
scheme, we can achieve big latency reductions while still using the same
(or less) amount of CPU.
Signed-off-by: Jens Axboe <axboe@fb.com>
Tested-By: Stephen Bates <sbates@raithlin.com>
Reviewed-By: Stephen Bates <sbates@raithlin.com>

This patch adds a small and simple fast patch for small direct I/O
requests on block devices that don't use AIO.  Between the neat
bio_iov_iter_get_pages helper that avoids allocating a page array
for get_user_pages and the on-stack bio and biovec this avoid memory
allocations and atomic operations entirely in the direct I/O code
(lower levels might still do memory allocations and will usually
have at least some atomic operations, though).
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Tested-By: Stephen Bates <sbates@raithlin.com>
Reviewed-By: Stephen Bates <sbates@raithlin.com>

For writes, we can get a completion in while we're still iterating
the request and bio chain. If that happens, we're reading freed
memory and we can crash.

Break out after the last segment and avoid having the iterator
read freed memory.
Reviewed-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

The newly added driver causes a harmless warning in some configurations:

block/blk-wbt.c:250:1: error: ‘inline’ is not at beginning of declaration [-Werror=old-style-declaration]
 static bool inline stat_sample_valid(struct blk_rq_stat *stat)

This makes it use the expected format for the declaration.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

If CONFIG_NVM is disabled, loading null_block module with use_lightnvm=1
fails. But there are no messages and documents related to the failure.

Add the appropriate error message.
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>

Massaged the text a bit.
Signed-off-by: Jens Axboe <axboe@fb.com>

In both legacy and mq path, req count of plug list is computed
before allocating request, so the number can be stale when falling
back to slept allocation, also the new introduced wbt can sleep
too.

This patch deals with the case by checking if plug list becomes
empty, and fixes the KASAN report of 'BUG: KASAN: stack-out-of-bounds'
which is introduced by Shaohua's patches of dispatching big request.

Fixes: 600271d9(blk-mq: immediately dispatch big size request)
Fixes: 50d24c34(block: immediately dispatch big size request)
Cc: Shaohua Li <shli@fb.com>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

Let's not depend on any of the BLK_MQ_RQ_QUEUE_* constants having
specific values. No functional change.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

Let's not depend on any of the BLK_MQ_RQ_QUEUE_* constants having
specific values. No functional change.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

->queue_rq() should return one of the BLK_MQ_RQ_QUEUE_* constants, not
an errno.

f4aa4c7b ("block: loop: convert to per-device workqueue")
Signed-off-by: Omar Sandoval <osandov@fb.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@fb.com>

Normally, sd_read_capacity sets sdp->use_16_for_rw to 1 based on the
disk capacity so that READ16/WRITE16 are used for large drives.
However, for a zoned disk with RC_BASIS set to 0, the capacity reported
through READ_CAPACITY may be very small, leading to use_16_for_rw not being
set and READ10/WRITE10 commands being used, even after the actual zoned disk
capacity is corrected in sd_zbc_read_zones. This causes LBA offset overflow for
accesses beyond 2TB.

As the ZBC standard makes it mandatory for ZBC drives to support
the READ16/WRITE16 commands anyway, make sure that use_16_for_rw is set.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
eviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

Avoid that sparse complains about unbalanced lock actions.
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

Since we have proper enums for the stats directions, use them.
Signed-off-by: Jens Axboe <axboe@fb.com>

Again a leftover from when the throttling code was generic. Now that we
just have the block user, get rid of the stat ops and indirections.
Signed-off-by: Jens Axboe <axboe@fb.com>

The bdi was a leftover from when the code was block layer agnostic.
Now that we just support a block layer user, store the queue directly.
Signed-off-by: Jens Axboe <axboe@fb.com>

The poll code is blk-mq specific, let's move it to blk-mq.c. This
is a prep patch for improving the polling code.
Signed-off-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

There is no need to call kfree() if memdup_user() fails, as no memory
was allocated and the error in the error-valued pointer should be returned.
Signed-off-by: Sachin Shukla <sachin.s5@samsung.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

A previous commit changed this to pass in the hardware queue, but
it was using the wrong hardware queue. Hence a request that was
allocated on one hardware queue ended up being issued on another
one, and that caused IO timeouts and oopses on some drivers. Since
the request holds hardware queue private resources, like a tag,
we can't just issue it on a different hardware queue.

Fixes: 2253efc8 ("blk-mq: Move more code into blk_mq_direct_issue_request()")
Signed-off-by: Jens Axboe <axboe@fb.com>

Enable throttling of buffered writeback to make it a lot
more smooth, and has way less impact on other system activity.
Background writeback should be, by definition, background
activity. The fact that we flush huge bundles of it at the time
means that it potentially has heavy impacts on foreground workloads,
which isn't ideal. We can't easily limit the sizes of writes that
we do, since that would impact file system layout in the presence
of delayed allocation. So just throttle back buffered writeback,
unless someone is waiting for it.

The algorithm for when to throttle takes its inspiration in the
CoDel networking scheduling algorithm. Like CoDel, blk-wb monitors
the minimum latencies of requests over a window of time. In that
window of time, if the minimum latency of any request exceeds a
given target, then a scale count is incremented and the queue depth
is shrunk. The next monitoring window is shrunk accordingly. Unlike
CoDel, if we hit a window that exhibits good behavior, then we
simply increment the scale count and re-calculate the limits for that
scale value. This prevents us from oscillating between a
close-to-ideal value and max all the time, instead remaining in the
windows where we get good behavior.

Unlike CoDel, blk-wb allows the scale count to to negative. This
happens if we primarily have writes going on. Unlike positive
scale counts, this doesn't change the size of the monitoring window.
When the heavy writers finish, blk-bw quickly snaps back to it's
stable state of a zero scale count.

The patch registers a sysfs entry, 'wb_lat_usec'. This sets the latency
target to me met. It defaults to 2 msec for non-rotational storage, and
75 msec for rotational storage. Setting this value to '0' disables
blk-wb. Generally, a user would not have to touch this setting.

We don't enable WBT on devices that are managed with CFQ, and have
a non-root block cgroup attached. If we have a proportional share setup
on this particular disk, then the wbt throttling will interfere with
that. We don't have a strong need for wbt for that case, since we will
rely on CFQ doing that for us.
Signed-off-by: Jens Axboe <axboe@fb.com>

We can hook this up to the block layer, to help throttle buffered
writes.

wbt registers a few trace points that can be used to track what is
happening in the system:

wbt_lat: 259:0: latency 2446318
wbt_stat: 259:0: rmean=2446318, rmin=2446318, rmax=2446318, rsamples=1,
               wmean=518866, wmin=15522, wmax=5330353, wsamples=57
wbt_step: 259:0: step down: step=1, window=72727272, background=8, normal=16, max=32

This shows a sync issue event (wbt_lat) that exceeded it's time. wbt_stat
dumps the current read/write stats for that window, and wbt_step shows a
step down event where we now scale back writes. Each trace includes the
device, 259:0 in this case.
Signed-off-by: Jens Axboe <axboe@fb.com>

For legacy block, we simply track them in the request queue. For
blk-mq, we track them on a per-sw queue basis, which we can then
sum up through the hardware queues and finally to a per device
state.

The stats are tracked in, roughly, 0.1s interval windows.

Add sysfs files to display the stats.

The feature is off by default, to avoid any extra overhead. In-kernel
users of it can turn it on by setting QUEUE_FLAG_STATS in the queue
flags. We currently don't turn it on if someone just reads any of
the stats files, that is something we could add as well.
Signed-off-by: Jens Axboe <axboe@fb.com>

cfq_cpd_alloc() which is the cpd_alloc_fn implementation for cfq was
incorrectly hard coding GFP_KERNEL instead of using the mask specified
through the @gfp parameter.  This currently doesn't cause any actual
issues because all current callers specify GFP_KERNEL.  Fix it.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: e4a9bde9 ("blkcg: replace blkcg_policy->cpd_size with ->cpd_alloc/free_fn() methods")
Signed-off-by: Jens Axboe <axboe@fb.com>

We only need the status and result fields, and passing them explicitly
makes life a lot easier for the Fibre Channel transport which doesn't
have a full CQE for the fast path case.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

This adds a shared per-request structure for all NVMe I/O.  This structure
is embedded as the first member in all NVMe transport drivers request
private data and allows to implement common functionality between the
drivers.

The first use is to replace the current abuse of the SCSI command
passthrough fields in struct request for the NVMe command passthrough,
but it will grow a field more fields to allow implementing things
like common abort handlers in the future.

The passthrough commands are handled by having a pointer to the SQE
(struct nvme_command) in struct nvme_request, and the union of the
possible result fields, which had to be turned from an anonymous
into a named union for that purpose.  This avoids having to pass
a reference to a full CQE around and thus makes checking the result
a lot more lightweight.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

Building with W=1 shows a harmless warning for the skd driver:

drivers/block/skd_main.c:2959:1: error: ‘static’ is not at beginning of declaration [-Werror=old-style-declaration]

This changes the prototype to the expected formatting.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

As reported by gcc -Wmaybe-uninitialized, the cleanup path for
skd_acquire_msix tries to free the already allocated msi-x vectors
in reverse order, but the index variable may not have been
used yet:

drivers/block/skd_main.c: In function ‘skd_acquire_irq’:
drivers/block/skd_main.c:3890:8: error: ‘i’ may be used uninitialized in this function [-Werror=maybe-uninitialized]

This changes the failure path to skip releasing the interrupts
if we have not started requesting them yet.

Fixes: 180b0ae7 ("skd: use pci_alloc_irq_vectors")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

If we insert a flush request, we clear REQ_PREFLUSH and/or REQ_FUA,
depending on flush settings. Since op_is_sync() factors those flags
in for deciding whether this request is sync or not, we should
set REQ_SYNC to avoid screwing up this accounting.

This should be less fragile.
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Fixes: b685d3d6 ("block: treat REQ_FUA and REQ_PREFLUSH as synchronous")
Signed-off-by: Jens Axboe <axboe@fb.com>

Note in the bdi_writeback structure whenever a task ends up sleeping
waiting for progress. We can use that information in the lower layers
to increase the priority of writes.
Signed-off-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Jan Kara <jack@suse.cz>

Replace custom approach by %*ph specifier to dump small buffers in hex format.

Unfortunately we can't use print_hex_dump_bytes() here since tha gap is
present, though one familiar with the code may change this.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

Switch the skd driver to use pci_alloc_irq_vectors.  We need to two calls to
pci_alloc_irq_vectors as skd only supports multiple MSI-X vectors, but not
multiple MSI vectors.

Otherwise this cleans up a lot of cruft and allows to a lot more common code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

Hi Peter, hi Jens,

I've been looking over the multi page bio vec work again recently, and
one of the stumbling blocks is raw biovec access in the pktcdvd.

The first issue is that it directly sets up the page and offset pointers
in the biovec just before calling bio_add_page.  As bio_add_page already
does the setup it's trivial to just switch it to stack variables for the
arguments.

The second issue is the copy code in pkt_make_local_copy, which
effectively is an opencoded version of bio_copy_data except that it
skips pages that already are the same in the ѕource and destination.
But we look at the only calleer we just set up the bio using bio_add_page
to point exactly to the page array that pkt_make_local_copy compares,
so the pages will always be the same and we can just remove this function.

Note that all this is done based on code inspection, I don't have any
packet writing hardware myself.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

Commit 0e87e58b ("blk-mq: improve warning for running a queue on the
wrong CPU") attempts to avoid triggering the WARN_ON in
__blk_mq_run_hw_queue when the expected CPU is dead.  Problem is, in the
last batch execution before round robin, blk_mq_hctx_next_cpu can
schedule a dead CPU and also update next_cpu to the next alive CPU in
the mask, which will trigger the WARN_ON despite the previous
workaround.

The following patch fixes this scenario by always scheduling the value
in hctx->next_cpu.  This changes the moment when we round-robin the CPU
running the hctx, but it really doesn't matter, since it still executes
BLK_MQ_CPU_WORK_BATCH times in a row before switching to another CPU.

Fixes: 0e87e58b ("blk-mq: improve warning for running a queue on the wrong CPU")
Signed-off-by: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

For blk-mq, ->nr_requests does track queue depth, at least at init
time. But for the older queue paths, it's simply a soft setting.
On top of that, it's generally larger than the hardware setting
on purpose, to allow backup of requests for merging.

Fill a hole in struct request with a 'queue_depth' member, that
drivers can call to more closely inform the block layer of the
real queue depth.
Signed-off-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Jan Kara <jack@suse.cz>

This is corresponding part for blk-mq. Disk with multiple hardware
queues doesn't need this as we only hold 1 request at most.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

Currently block plug holds up to 16 non-mergeable requests. This makes
sense if the request size is small, eg, reduce lock contention. But if
request size is big enough, we don't need to worry about lock
contention. Holding such request makes no sense and it lows the disk
utilization.

In practice, this improves 10% throughput for my raid5 sequential write
workload.

The size (128k) is arbitrary right now, but it makes sure lock
contention is small. This probably could be more intelligent, eg, check
average request size holded. Since this is mainly for sequential IO,
probably not worthy.

V2: check the last request instead of the first request, so as long as
there is one big size request we flush the plug.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

bsg_validate_sgv4_hdr() doesn't care about the request_queue, so drop it
from it's arguments.
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

Make nvme_requeue_req() check BLK_MQ_S_STOPPED instead of
QUEUE_FLAG_STOPPED. Remove the QUEUE_FLAG_STOPPED manipulations
that became superfluous because of this change. Change
blk_queue_stopped() tests into blk_mq_queue_stopped().

This patch fixes a race condition: using queue_flag_clear_unlocked()
is not safe if any other function that manipulates the queue flags
can be called concurrently, e.g. blk_cleanup_queue().
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>