for-linus-20190726

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl07DGAQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgplf5EADOOvOdsz9N/Iw8ZHHHJXCqKR26zZv75G1z
 0h1PGC7p0JZQbYFo0Zo7mjiRBGlg6tlXc2d4Gyl94XJKDwjeYTcFDvbvERdYa+MH
 d2RiFkAfR967Ri4fb+FP5L3mYOQdMJ/zk0xCDHLv/DcxeFLa5a9EJS1+vBSR+AcB
 0JpJWuHypGqGmbTaL0z9q2pmx0mgA1ERlWQtkMLrsEr2Vqg/rrjGwe2bGFY00lXc
 vKtFkpfugKc4zVAPSzC1YZgojfDDpGNEA4QMtxMsEH4hqyMpHhrtUedNY5QrjC0B
 p9h6aPXXYr2KhGP0grrEytzaYUOzK2crK5h+q+1vu6nOgx2EgmnLM9tBu/LuRH1j
 uUzKJOa3/AE+bU7uZEsaUerTBsHrgEBa1x8G92obYRnjgW3aCD2CaSbjjBhNxTZ4
 1dXyr0DTHFXZmfcfWja5tO26JTPzjwVOrwiRyU0S727UsdVJupoHiYLr5fwaDfgn
 /Du2I/XWvFtflm5i0ND0sdcX1yRlFiGZ9e45z1QFaFmcteKKWzRBDlC6mQzI/lw3
 oc583mhDR3tRtJxow+wn6AuMUehFRh8wj0UhL/MEMjLW8GiqXU5aRtanT+22Xz4L
 saNDQieeEnV7raMYXMP0qIhkJtrNASmJQos+MOJAEGOWcS2ePIUUio2kSXie+071
 BphJd2RamQ==
 =HIzH
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-20190726' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - Several io_uring fixes/improvements:
     - Blocking fix for O_DIRECT (me)
     - Latter page slowness for registered buffers (me)
     - Fix poll hang under certain conditions (me)
     - Defer sequence check fix for wrapped rings (Zhengyuan)
     - Mismatch in async inc/dec accounting (Zhengyuan)
     - Memory ordering issue that could cause stall (Zhengyuan)
      - Track sequential defer in bytes, not pages (Zhengyuan)

 - NVMe pull request from Christoph

 - Set of hang fixes for wbt (Josef)

 - Redundant error message kill for libahci (Ding)

 - Remove unused blk_mq_sched_started_request() and related ops (Marcos)

 - drbd dynamic alloc shash descriptor to reduce stack use (Arnd)

 - blkcg ->pd_stat() non-debug print (Tejun)

 - bcache memory leak fix (Wei)

 - Comment fix (Akinobu)

 - BFQ perf regression fix (Paolo)

* tag 'for-linus-20190726' of git://git.kernel.dk/linux-block: (24 commits)
  io_uring: ensure ->list is initialized for poll commands
  Revert "nvme-pci: don't create a read hctx mapping without read queues"
  nvme: fix multipath crash when ANA is deactivated
  nvme: fix memory leak caused by incorrect subsystem free
  nvme: ignore subnqn for ADATA SX6000LNP
  drbd: dynamically allocate shash descriptor
  block: blk-mq: Remove blk_mq_sched_started_request and started_request
  bcache: fix possible memory leak in bch_cached_dev_run()
  io_uring: track io length in async_list based on bytes
  io_uring: don't use iov_iter_advance() for fixed buffers
  block: properly handle IOCB_NOWAIT for async O_DIRECT IO
  blk-mq: allow REQ_NOWAIT to return an error inline
  io_uring: add a memory barrier before atomic_read
  rq-qos: use a mb for got_token
  rq-qos: set ourself TASK_UNINTERRUPTIBLE after we schedule
  rq-qos: don't reset has_sleepers on spurious wakeups
  rq-qos: fix missed wake-ups in rq_qos_throttle
  wait: add wq_has_single_sleeper helper
  block, bfq: check also in-flight I/O in dispatch plugging
  block: fix sysfs module parameters directory path in comment
  ...
This commit is contained in:
Linus Torvalds 2019-07-26 10:32:12 -07:00
commit 0441281965
20 changed files with 224 additions and 92 deletions

View file

@ -345,15 +345,24 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
struct bio *bio;
bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
bool is_read = (iov_iter_rw(iter) == READ), is_sync;
bool nowait = (iocb->ki_flags & IOCB_NOWAIT) != 0;
loff_t pos = iocb->ki_pos;
blk_qc_t qc = BLK_QC_T_NONE;
int ret = 0;
gfp_t gfp;
ssize_t ret;
if ((pos | iov_iter_alignment(iter)) &
(bdev_logical_block_size(bdev) - 1))
return -EINVAL;
bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
if (nowait)
gfp = GFP_NOWAIT;
else
gfp = GFP_KERNEL;
bio = bio_alloc_bioset(gfp, nr_pages, &blkdev_dio_pool);
if (!bio)
return -EAGAIN;
dio = container_of(bio, struct blkdev_dio, bio);
dio->is_sync = is_sync = is_sync_kiocb(iocb);
@ -375,7 +384,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
if (!is_poll)
blk_start_plug(&plug);
ret = 0;
for (;;) {
int err;
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = pos >> 9;
bio->bi_write_hint = iocb->ki_hint;
@ -383,8 +395,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
bio->bi_end_io = blkdev_bio_end_io;
bio->bi_ioprio = iocb->ki_ioprio;
ret = bio_iov_iter_get_pages(bio, iter);
if (unlikely(ret)) {
err = bio_iov_iter_get_pages(bio, iter);
if (unlikely(err)) {
if (!ret)
ret = err;
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
break;
@ -399,6 +413,14 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
task_io_account_write(bio->bi_iter.bi_size);
}
/*
* Tell underlying layer to not block for resource shortage.
* And if we would have blocked, return error inline instead
* of through the bio->bi_end_io() callback.
*/
if (nowait)
bio->bi_opf |= (REQ_NOWAIT | REQ_NOWAIT_INLINE);
dio->size += bio->bi_iter.bi_size;
pos += bio->bi_iter.bi_size;
@ -412,6 +434,11 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
}
qc = submit_bio(bio);
if (qc == BLK_QC_T_EAGAIN) {
if (!ret)
ret = -EAGAIN;
goto error;
}
if (polled)
WRITE_ONCE(iocb->ki_cookie, qc);
@ -432,8 +459,20 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
atomic_inc(&dio->ref);
}
submit_bio(bio);
bio = bio_alloc(GFP_KERNEL, nr_pages);
qc = submit_bio(bio);
if (qc == BLK_QC_T_EAGAIN) {
if (!ret)
ret = -EAGAIN;
goto error;
}
ret += bio->bi_iter.bi_size;
bio = bio_alloc(gfp, nr_pages);
if (!bio) {
if (!ret)
ret = -EAGAIN;
goto error;
}
}
if (!is_poll)
@ -453,13 +492,16 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
}
__set_current_state(TASK_RUNNING);
out:
if (!ret)
ret = blk_status_to_errno(dio->bio.bi_status);
if (likely(!ret))
ret = dio->size;
bio_put(&dio->bio);
return ret;
error:
if (!is_poll)
blk_finish_plug(&plug);
goto out;
}
static ssize_t