summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-07-03 10:34:51 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-07-03 10:34:51 -0700
commitc6b1e36c8fa04a6680c44fe0321d0370400e90b6 (patch)
tree5110f0639bfa803baa8d213cb21efe37beeaf742 /fs/xfs
parent81e3e044897b0875a52953b3fb6241a33428e4f9 (diff)
parenta84ebb837b419787c2ece74efa566c998929cead (diff)
Merge branch 'for-4.13/block' of git://git.kernel.dk/linux-block
Pull core block/IO updates from Jens Axboe: "This is the main pull request for the block layer for 4.13. Not a huge round in terms of features, but there's a lot of churn related to some core cleanups. Note this depends on the UUID tree pull request, that Christoph already sent out. This pull request contains: - A series from Christoph, unifying the error/stats codes in the block layer. We now use blk_status_t everywhere, instead of using different schemes for different places. - Also from Christoph, some cleanups around request allocation and IO scheduler interactions in blk-mq. - And yet another series from Christoph, cleaning up how we handle and do bounce buffering in the block layer. - A blk-mq debugfs series from Bart, further improving on the support we have for exporting internal information to aid debugging IO hangs or stalls. - Also from Bart, a series that cleans up the request initialization differences across types of devices. - A series from Goldwyn Rodrigues, allowing the block layer to return failure if we will block and the user asked for non-blocking. - Patch from Hannes for supporting setting loop devices block size to that of the underlying device. - Two series of patches from Javier, fixing various issues with lightnvm, particular around pblk. - A series from me, adding support for write hints. This comes with NVMe support as well, so applications can help guide data placement on flash to improve performance, latencies, and write amplification. - A series from Ming, improving and hardening blk-mq support for stopping/starting and quiescing hardware queues. - Two pull requests for NVMe updates. Nothing major on the feature side, but lots of cleanups and bug fixes. From the usual crew. - A series from Neil Brown, greatly improving the bio rescue set support. Most notably, this kills the bio rescue work queues, if we don't really need them. - Lots of other little bug fixes that are all over the place" * 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits) lightnvm: pblk: set line bitmap check under debug lightnvm: pblk: verify that cache read is still valid lightnvm: pblk: add initialization check lightnvm: pblk: remove target using async. I/Os lightnvm: pblk: use vmalloc for GC data buffer lightnvm: pblk: use right metadata buffer for recovery lightnvm: pblk: schedule if data is not ready lightnvm: pblk: remove unused return variable lightnvm: pblk: fix double-free on pblk init lightnvm: pblk: fix bad le64 assignations nvme: Makefile: remove dead build rule blk-mq: map all HWQ also in hyperthreaded system nvmet-rdma: register ib_client to not deadlock in device removal nvme_fc: fix error recovery on link down. nvmet_fc: fix crashes on bad opcodes nvme_fc: Fix crash when nvme controller connection fails. nvme_fc: replace ioabort msleep loop with completion nvme_fc: fix double calls to nvme_cleanup_cmd() nvme-fabrics: verify that a controller returns the correct NQN nvme: simplify nvme_dev_attrs_are_visible ...
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/xfs_aops.c9
-rw-r--r--fs/xfs/xfs_buf.c7
-rw-r--r--fs/xfs/xfs_file.c32
-rw-r--r--fs/xfs/xfs_iomap.c22
-rw-r--r--fs/xfs/xfs_super.c3
5 files changed, 61 insertions, 12 deletions
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 3b91faacc1ba..d20c29b9c95b 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -276,7 +276,7 @@ xfs_end_io(
struct xfs_inode *ip = XFS_I(ioend->io_inode);
xfs_off_t offset = ioend->io_offset;
size_t size = ioend->io_size;
- int error = ioend->io_bio->bi_error;
+ int error;
/*
* Just clean up the in-memory strutures if the fs has been shut down.
@@ -289,6 +289,7 @@ xfs_end_io(
/*
* Clean up any COW blocks on an I/O error.
*/
+ error = blk_status_to_errno(ioend->io_bio->bi_status);
if (unlikely(error)) {
switch (ioend->io_type) {
case XFS_IO_COW:
@@ -332,7 +333,7 @@ xfs_end_bio(
else if (ioend->io_append_trans)
queue_work(mp->m_data_workqueue, &ioend->io_work);
else
- xfs_destroy_ioend(ioend, bio->bi_error);
+ xfs_destroy_ioend(ioend, blk_status_to_errno(bio->bi_status));
}
STATIC int
@@ -500,11 +501,12 @@ xfs_submit_ioend(
* time.
*/
if (status) {
- ioend->io_bio->bi_error = status;
+ ioend->io_bio->bi_status = errno_to_blk_status(status);
bio_endio(ioend->io_bio);
return status;
}
+ ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint;
submit_bio(ioend->io_bio);
return 0;
}
@@ -564,6 +566,7 @@ xfs_chain_bio(
bio_chain(ioend->io_bio, new);
bio_get(ioend->io_bio); /* for xfs_destroy_ioend */
ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
+ ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint;
submit_bio(ioend->io_bio);
ioend->io_bio = new;
}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 16d6a578fc16..438505f395e7 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1227,8 +1227,11 @@ xfs_buf_bio_end_io(
* don't overwrite existing errors - otherwise we can lose errors on
* buffers that require multiple bios to complete.
*/
- if (bio->bi_error)
- cmpxchg(&bp->b_io_error, 0, bio->bi_error);
+ if (bio->bi_status) {
+ int error = blk_status_to_errno(bio->bi_status);
+
+ cmpxchg(&bp->b_io_error, 0, error);
+ }
if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5fb5a0958a14..17f27a2fb5e2 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -237,7 +237,11 @@ xfs_file_dax_read(
if (!count)
return 0; /* skip atime */
- xfs_ilock(ip, XFS_IOLOCK_SHARED);
+ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return -EAGAIN;
+ xfs_ilock(ip, XFS_IOLOCK_SHARED);
+ }
ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
@@ -541,7 +545,11 @@ xfs_file_dio_aio_write(
iolock = XFS_IOLOCK_SHARED;
}
- xfs_ilock(ip, iolock);
+ if (!xfs_ilock_nowait(ip, iolock)) {
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return -EAGAIN;
+ xfs_ilock(ip, iolock);
+ }
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
@@ -553,9 +561,15 @@ xfs_file_dio_aio_write(
* otherwise demote the lock if we had to take the exclusive lock
* for other reasons in xfs_file_aio_write_checks.
*/
- if (unaligned_io)
- inode_dio_wait(inode);
- else if (iolock == XFS_IOLOCK_EXCL) {
+ if (unaligned_io) {
+ /* If we are going to wait for other DIO to finish, bail */
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (atomic_read(&inode->i_dio_count))
+ return -EAGAIN;
+ } else {
+ inode_dio_wait(inode);
+ }
+ } else if (iolock == XFS_IOLOCK_EXCL) {
xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
@@ -585,7 +599,12 @@ xfs_file_dax_write(
size_t count;
loff_t pos;
- xfs_ilock(ip, iolock);
+ if (!xfs_ilock_nowait(ip, iolock)) {
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ return -EAGAIN;
+ xfs_ilock(ip, iolock);
+ }
+
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
@@ -892,6 +911,7 @@ xfs_file_open(
return -EFBIG;
if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb)))
return -EIO;
+ file->f_mode |= FMODE_AIO_NOWAIT;
return 0;
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 94e5bdf7304c..05dc87e8c1f5 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -995,6 +995,11 @@ xfs_file_iomap_begin(
lockmode = xfs_ilock_data_map_shared(ip);
}
+ if ((flags & IOMAP_NOWAIT) && !(ip->i_df.if_flags & XFS_IFEXTENTS)) {
+ error = -EAGAIN;
+ goto out_unlock;
+ }
+
ASSERT(offset <= mp->m_super->s_maxbytes);
if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
length = mp->m_super->s_maxbytes - offset;
@@ -1016,6 +1021,15 @@ xfs_file_iomap_begin(
if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
if (flags & IOMAP_DIRECT) {
+ /*
+ * A reflinked inode will result in CoW alloc.
+ * FIXME: It could still overwrite on unshared extents
+ * and not need allocation.
+ */
+ if (flags & IOMAP_NOWAIT) {
+ error = -EAGAIN;
+ goto out_unlock;
+ }
/* may drop and re-acquire the ilock */
error = xfs_reflink_allocate_cow(ip, &imap, &shared,
&lockmode);
@@ -1033,6 +1047,14 @@ xfs_file_iomap_begin(
if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
/*
+ * If nowait is set bail since we are going to make
+ * allocations.
+ */
+ if (flags & IOMAP_NOWAIT) {
+ error = -EAGAIN;
+ goto out_unlock;
+ }
+ /*
* We cap the maximum length we map here to MAX_WRITEBACK_PAGES
* pages to keep the chunks of work done where somewhat symmetric
* with the work writeback does. This is a completely arbitrary
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 455a575f101d..97df4db13b2e 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1766,7 +1766,8 @@ STATIC int __init
xfs_init_zones(void)
{
xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE,
- offsetof(struct xfs_ioend, io_inline_bio));
+ offsetof(struct xfs_ioend, io_inline_bio),
+ BIOSET_NEED_BVECS);
if (!xfs_ioend_bioset)
goto out;