summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-01-02 21:46:03 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2019-01-02 21:46:03 +0300
commit1ac5cd4978794bd060d448acc0305e9fc996ba92 (patch)
tree8d2cb4d087b6e6c1acc7303cfe336f9f67247b53
parentd9a7fa67b4bfe6ce93ee9aab23ae2e7ca0763e84 (diff)
downloadlinux-1ac5cd4978794bd060d448acc0305e9fc996ba92.tar.xz
block: don't use un-ordered __set_current_state(TASK_UNINTERRUPTIBLE)
This mostly reverts commit 849a370016a5 ("block: avoid ordered task state change for polled IO"). It was wrongly claiming that the ordering wasn't necessary. The memory barrier _is_ necessary. If something is truly polling and not going to sleep, it's the whole state setting that is unnecessary, not the memory barrier. Whenever you set your state to a sleeping state, you absolutely need the memory barrier. Note that sometimes the memory barrier can be elsewhere. For example, the ordering might be provided by an external lock, or by setting the process state to sleeping before adding yourself to the wait queue list that is used for waking up (where the wait queue lock itself will guarantee that any wakeup will correctly see the sleeping state). But none of those cases were true here. NOTE! Some of the polling paths may indeed be able to drop the state setting entirely, at which point the memory barrier also goes away. (Also note that this doesn't revert the TASK_RUNNING cases: there is no race between a wakeup and setting the process state to TASK_RUNNING, since the end result doesn't depend on ordering). Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--fs/block_dev.c7
-rw-r--r--fs/iomap.c3
-rw-r--r--mm/page_io.c3
3 files changed, 4 insertions, 9 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 450be88cffef..c546cdce77e6 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -237,11 +237,9 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
qc = submit_bio(&bio);
for (;;) {
- __set_current_state(TASK_UNINTERRUPTIBLE);
-
+ set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(bio.bi_private))
break;
-
if (!(iocb->ki_flags & IOCB_HIPRI) ||
!blk_poll(bdev_get_queue(bdev), qc, true))
io_schedule();
@@ -426,8 +424,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
return -EIOCBQUEUED;
for (;;) {
- __set_current_state(TASK_UNINTERRUPTIBLE);
-
+ set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(dio->waiter))
break;
diff --git a/fs/iomap.c b/fs/iomap.c
index 3a0cd557b4cf..a3088fae567b 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1921,8 +1921,7 @@ 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;
diff --git a/mm/page_io.c b/mm/page_io.c
index 3475733b1926..d975fa3f02aa 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -405,8 +405,7 @@ int swap_readpage(struct page *page, bool synchronous)
bio_get(bio);
qc = submit_bio(bio);
while (synchronous) {
- __set_current_state(TASK_UNINTERRUPTIBLE);
-
+ set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(bio->bi_private))
break;