summaryrefslogtreecommitdiffstats
path: root/fs/iomap.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-12-28 13:19:59 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-12-28 13:19:59 -0800
commit0e9da3fbf7d81f0f913b491c8de1ba7883d4f217 (patch)
tree2b3d25e3be60bf4ee40b4690c7bb9d6fa499ae69 /fs/iomap.c
parentb12a9124eeb71d766a3e3eb594ebbb3fefc66902 (diff)
parent00203ba40d40d7f33857416adfb18adaf0e40123 (diff)
downloadlinux-0e9da3fbf7d81f0f913b491c8de1ba7883d4f217.tar.gz
linux-0e9da3fbf7d81f0f913b491c8de1ba7883d4f217.tar.bz2
linux-0e9da3fbf7d81f0f913b491c8de1ba7883d4f217.zip
Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block
Pull block updates from Jens Axboe: "This is the main pull request for block/storage for 4.21. Larger than usual, it was a busy round with lots of goodies queued up. Most notable is the removal of the old IO stack, which has been a long time coming. No new features for a while, everything coming in this week has all been fixes for things that were previously merged. This contains: - Use atomic counters instead of semaphores for mtip32xx (Arnd) - Cleanup of the mtip32xx request setup (Christoph) - Fix for circular locking dependency in loop (Jan, Tetsuo) - bcache (Coly, Guoju, Shenghui) * Optimizations for writeback caching * Various fixes and improvements - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith) * host and target support for NVMe over TCP * Error log page support * Support for separate read/write/poll queues * Much improved polling * discard OOM fallback * Tracepoint improvements - lightnvm (Hans, Hua, Igor, Matias, Javier) * Igor added packed metadata to pblk. Now drives without metadata per LBA can be used as well. * Fix from Geert on uninitialized value on chunk metadata reads. * Fixes from Hans and Javier to pblk recovery and write path. * Fix from Hua Su to fix a race condition in the pblk recovery code. * Scan optimization added to pblk recovery from Zhoujie. * Small geometry cleanup from me. - Conversion of the last few drivers that used the legacy path to blk-mq (me) - Removal of legacy IO path in SCSI (me, Christoph) - Removal of legacy IO stack and schedulers (me) - Support for much better polling, now without interrupts at all. blk-mq adds support for multiple queue maps, which enables us to have a map per type. This in turn enables nvme to have separate completion queues for polling, which can then be interrupt-less. Also means we're ready for async polled IO, which is hopefully coming in the next release. - Killing of (now) unused block exports (Christoph) - Unification of the blk-rq-qos and blk-wbt wait handling (Josef) - Support for zoned testing with null_blk (Masato) - sx8 conversion to per-host tag sets (Christoph) - IO priority improvements (Damien) - mq-deadline zoned fix (Damien) - Ref count blkcg series (Dennis) - Lots of blk-mq improvements and speedups (me) - sbitmap scalability improvements (me) - Make core inflight IO accounting per-cpu (Mikulas) - Export timeout setting in sysfs (Weiping) - Cleanup the direct issue path (Jianchao) - Export blk-wbt internals in block debugfs for easier debugging (Ming) - Lots of other fixes and improvements" * tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits) kyber: use sbitmap add_wait_queue/list_del wait helpers sbitmap: add helpers for add/del wait queue handling block: save irq state in blkg_lookup_create() dm: don't reuse bio for flushes nvme-pci: trace SQ status on completions nvme-rdma: implement polling queue map nvme-fabrics: allow user to pass in nr_poll_queues nvme-fabrics: allow nvmf_connect_io_queue to poll nvme-core: optionally poll sync commands block: make request_to_qc_t public nvme-tcp: fix spelling mistake "attepmpt" -> "attempt" nvme-tcp: fix endianess annotations nvmet-tcp: fix endianess annotations nvme-pci: refactor nvme_poll_irqdisable to make sparse happy nvme-pci: only set nr_maps to 2 if poll queues are supported nvmet: use a macro for default error location nvmet: fix comparison of a u16 with -1 blk-mq: enable IO poll if .nr_queues of type poll > 0 blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight() blk-mq: skip zero-queue maps in blk_mq_map_swqueue ...
Diffstat (limited to 'fs/iomap.c')
-rw-r--r--fs/iomap.c16
1 files changed, 12 insertions, 4 deletions
diff --git a/fs/iomap.c b/fs/iomap.c
index ce837d962d47..e87c288cd5ef 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1543,7 +1543,7 @@ static void iomap_dio_bio_end_io(struct bio *bio)
if (dio->wait_for_completion) {
struct task_struct *waiter = dio->submit.waiter;
WRITE_ONCE(dio->submit.waiter, NULL);
- wake_up_process(waiter);
+ blk_wake_io_task(waiter);
} else if (dio->flags & IOMAP_DIO_WRITE) {
struct inode *inode = file_inode(dio->iocb->ki_filp);
@@ -1571,6 +1571,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
unsigned len)
{
struct page *page = ZERO_PAGE(0);
+ int flags = REQ_SYNC | REQ_IDLE;
struct bio *bio;
bio = bio_alloc(GFP_KERNEL, 1);
@@ -1579,9 +1580,12 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
+ if (dio->iocb->ki_flags & IOCB_HIPRI)
+ flags |= REQ_HIPRI;
+
get_page(page);
__bio_add_page(bio, page, len, 0);
- bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC | REQ_IDLE);
+ bio_set_op_attrs(bio, REQ_OP_WRITE, flags);
atomic_inc(&dio->ref);
return submit_bio(bio);
@@ -1687,6 +1691,9 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
bio_set_pages_dirty(bio);
}
+ if (dio->iocb->ki_flags & IOCB_HIPRI)
+ bio->bi_opf |= REQ_HIPRI;
+
iov_iter_advance(dio->submit.iter, n);
dio->size += n;
@@ -1914,14 +1921,15 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
return -EIOCBQUEUED;
for (;;) {
- set_current_state(TASK_UNINTERRUPTIBLE);
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+
if (!READ_ONCE(dio->submit.waiter))
break;
if (!(iocb->ki_flags & IOCB_HIPRI) ||
!dio->submit.last_queue ||
!blk_poll(dio->submit.last_queue,
- dio->submit.cookie))
+ dio->submit.cookie, true))
io_schedule();
}
__set_current_state(TASK_RUNNING);