Commit 8353a814 authored by Christoph Hellwig's avatar Christoph Hellwig Committed by Darrick J. Wong

xfs: open code end_buffer_async_write in xfs_finish_page_writeback

Our loop in xfs_finish_page_writeback, which iterates over all buffer
heads in a page and then calls end_buffer_async_write, which also
iterates over all buffers in the page to check if any I/O is in flight
is not only inefficient, but also potentially dangerous as
end_buffer_async_write can cause the page and all buffers to be freed.

Replace it with a single loop that does the work of end_buffer_async_write
on a per-page basis.
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
Reviewed-by: default avatarBrian Foster <bfoster@redhat.com>
Reviewed-by: default avatarDarrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: default avatarDarrick J. Wong <darrick.wong@oracle.com>
parent dd60687e
...@@ -85,11 +85,11 @@ xfs_find_bdev_for_inode( ...@@ -85,11 +85,11 @@ xfs_find_bdev_for_inode(
* associated buffer_heads, paying attention to the start and end offsets that * associated buffer_heads, paying attention to the start and end offsets that
* we need to process on the page. * we need to process on the page.
* *
* Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last * Note that we open code the action in end_buffer_async_write here so that we
* buffer in the IO. Once it does this, it is unsafe to access the bufferhead or * only have to iterate over the buffers attached to the page once. This is not
* the page at all, as we may be racing with memory reclaim and it can free both * only more efficient, but also ensures that we only calls end_page_writeback
* the bufferhead chain and the page as it will see the page as clean and * at the end of the iteration, and thus avoids the pitfall of having the page
* unused. * and buffers potentially freed after every call to end_buffer_async_write.
*/ */
static void static void
xfs_finish_page_writeback( xfs_finish_page_writeback(
...@@ -97,29 +97,44 @@ xfs_finish_page_writeback( ...@@ -97,29 +97,44 @@ xfs_finish_page_writeback(
struct bio_vec *bvec, struct bio_vec *bvec,
int error) int error)
{ {
unsigned int end = bvec->bv_offset + bvec->bv_len - 1; struct buffer_head *head = page_buffers(bvec->bv_page), *bh = head;
struct buffer_head *head, *bh, *next; bool busy = false;
unsigned int off = 0; unsigned int off = 0;
unsigned int bsize; unsigned long flags;
ASSERT(bvec->bv_offset < PAGE_SIZE); ASSERT(bvec->bv_offset < PAGE_SIZE);
ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0); ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0);
ASSERT(end < PAGE_SIZE); ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE);
ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0); ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0);
bh = head = page_buffers(bvec->bv_page); local_irq_save(flags);
bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
bsize = bh->b_size;
do { do {
if (off > end) if (off >= bvec->bv_offset &&
break; off < bvec->bv_offset + bvec->bv_len) {
next = bh->b_this_page; ASSERT(buffer_async_write(bh));
if (off < bvec->bv_offset) ASSERT(bh->b_end_io == NULL);
goto next_bh;
bh->b_end_io(bh, !error); if (error) {
next_bh: mark_buffer_write_io_error(bh);
off += bsize; clear_buffer_uptodate(bh);
} while ((bh = next) != head); SetPageError(bvec->bv_page);
} else {
set_buffer_uptodate(bh);
}
clear_buffer_async_write(bh);
unlock_buffer(bh);
} else if (buffer_async_write(bh)) {
ASSERT(buffer_locked(bh));
busy = true;
}
off += bh->b_size;
} while ((bh = bh->b_this_page) != head);
bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
local_irq_restore(flags);
if (!busy)
end_page_writeback(bvec->bv_page);
} }
/* /*
...@@ -133,8 +148,10 @@ xfs_destroy_ioend( ...@@ -133,8 +148,10 @@ xfs_destroy_ioend(
int error) int error)
{ {
struct inode *inode = ioend->io_inode; struct inode *inode = ioend->io_inode;
struct bio *last = ioend->io_bio; struct bio *bio = &ioend->io_inline_bio;
struct bio *bio, *next; struct bio *last = ioend->io_bio, *next;
u64 start = bio->bi_iter.bi_sector;
bool quiet = bio_flagged(bio, BIO_QUIET);
for (bio = &ioend->io_inline_bio; bio; bio = next) { for (bio = &ioend->io_inline_bio; bio; bio = next) {
struct bio_vec *bvec; struct bio_vec *bvec;
...@@ -155,6 +172,11 @@ xfs_destroy_ioend( ...@@ -155,6 +172,11 @@ xfs_destroy_ioend(
bio_put(bio); bio_put(bio);
} }
if (unlikely(error && !quiet)) {
xfs_err_ratelimited(XFS_I(inode)->i_mount,
"writeback error on sector %llu", start);
}
} }
/* /*
...@@ -423,7 +445,8 @@ xfs_start_buffer_writeback( ...@@ -423,7 +445,8 @@ xfs_start_buffer_writeback(
ASSERT(!buffer_delay(bh)); ASSERT(!buffer_delay(bh));
ASSERT(!buffer_unwritten(bh)); ASSERT(!buffer_unwritten(bh));
mark_buffer_async_write(bh); bh->b_end_io = NULL;
set_buffer_async_write(bh);
set_buffer_uptodate(bh); set_buffer_uptodate(bh);
clear_buffer_dirty(bh); clear_buffer_dirty(bh);
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment