Fixed regressions (two stability regressions and a performance

regression) introduced during the 3.10-rc1 merge window.  Also
 included is a bug fix relating to allocating blocks after resizing an
 ext3 file system when using the ext4 file system driver.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.12 (GNU/Linux)
 
 iQIcBAABCAAGBQJRkZBlAAoJENNvdpvBGATwLYQP/iWOBs2z93WG23cqkgqvL8o6
 ZyeJdgy9dkFCArVDX5SSnGkJXZ3iqIKi5HoTKTJKfytgMzgiDAZcLsIHVv6NczwR
 UGhjgS3HEdV5tJ46E6JnpB3NLSb+rAdc5kCdlsbzU46CP+JjFiYEhxVpK7ELuM/G
 yctChbIH9FY+1OwxHccacBOaJU2ELhnH6B/8Ry/6gM2H0vfKeTNOdocOHdxvbNqg
 ooGjytMfVopMQEfVG8aXtTfy341NFJH5fAYEahCcXxeO9ta6Unj9yOu5JV2wVrTt
 39+DBsquGX6AVQsc9IxJ6YAN6ldwWN7l3huE9/AI0o/alwGsfVi5M+M/d1MMjDqf
 Fgl2EzzBpZQeKKY9UXNi4LLgYdBiILMgKDOGoRKhRb8ynSSf/JX43+24FvidEi3o
 o//J4aR+oSZfaovGAeikqyF1cumayhoNN8MINRN8igIinBiC4GjBFEl/Kl/1eAY/
 lREGcsmYPXOkVPpM72waRYlP4GwNdOg4QSEY0SGljpwluO+dYtKQjHXcv/s/xL5v
 j3GemzYVyjx4zaq1g3PxGfuD6VKFHr0T6jvzd6cHu17lnPlw9fwznHbEm9BEcXDY
 gbGx9u+a2ZTqDwYVALbeoRpf9Zz6DUCse3ts4N3rbkXUQQiBYo7tybfVopIMAukb
 CexvidDE/ryJrJJFBwoK
 =6cRD
 -----END PGP SIGNATURE-----

Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 update from Ted Ts'o:
 "Fixed regressions (two stability regressions and a performance
  regression) introduced during the 3.10-rc1 merge window.

  Also included is a bug fix relating to allocating blocks after
  resizing an ext3 file system when using the ext4 file system driver"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  jbd,jbd2: fix oops in jbd2_journal_put_journal_head()
  ext4: revert "ext4: use io_end for multiple bios"
  ext4: limit group search loop for non-extent files
  ext4: fix fio regression
This commit is contained in:
Linus Torvalds 2013-05-14 09:30:54 -07:00
commit b973425cbb
10 changed files with 120 additions and 147 deletions

View File

@ -209,7 +209,6 @@ typedef struct ext4_io_end {
ssize_t size; /* size of the extent */
struct kiocb *iocb; /* iocb struct for AIO */
int result; /* error value for AIO */
atomic_t count; /* reference counter */
} ext4_io_end_t;
struct ext4_io_submit {
@ -2651,14 +2650,11 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
/* page-io.c */
extern int __init ext4_init_pageio(void);
extern void ext4_add_complete_io(ext4_io_end_t *io_end);
extern void ext4_exit_pageio(void);
extern void ext4_ioend_shutdown(struct inode *);
extern void ext4_free_io_end(ext4_io_end_t *io);
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end);
extern int ext4_put_io_end(ext4_io_end_t *io_end);
extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
extern void ext4_io_submit_init(struct ext4_io_submit *io,
struct writeback_control *wbc);
extern void ext4_end_io_work(struct work_struct *work);
extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,

View File

@ -3642,7 +3642,7 @@ int ext4_find_delalloc_range(struct inode *inode,
{
struct extent_status es;
ext4_es_find_delayed_extent(inode, lblk_start, &es);
ext4_es_find_delayed_extent_range(inode, lblk_start, lblk_end, &es);
if (es.es_len == 0)
return 0; /* there is no delay extent in this tree */
else if (es.es_lblk <= lblk_start &&
@ -4608,9 +4608,10 @@ static int ext4_find_delayed_extent(struct inode *inode,
struct extent_status es;
ext4_lblk_t block, next_del;
ext4_es_find_delayed_extent(inode, newes->es_lblk, &es);
if (newes->es_pblk == 0) {
ext4_es_find_delayed_extent_range(inode, newes->es_lblk,
newes->es_lblk + newes->es_len - 1, &es);
/*
* No extent in extent-tree contains block @newes->es_pblk,
* then the block may stay in 1)a hole or 2)delayed-extent.
@ -4630,7 +4631,7 @@ static int ext4_find_delayed_extent(struct inode *inode,
}
block = newes->es_lblk + newes->es_len;
ext4_es_find_delayed_extent(inode, block, &es);
ext4_es_find_delayed_extent_range(inode, block, EXT_MAX_BLOCKS, &es);
if (es.es_len == 0)
next_del = EXT_MAX_BLOCKS;
else

View File

@ -232,14 +232,16 @@ static struct extent_status *__es_tree_search(struct rb_root *root,
}
/*
* ext4_es_find_delayed_extent: find the 1st delayed extent covering @es->lblk
* if it exists, otherwise, the next extent after @es->lblk.
* ext4_es_find_delayed_extent_range: find the 1st delayed extent covering
* @es->lblk if it exists, otherwise, the next extent after @es->lblk.
*
* @inode: the inode which owns delayed extents
* @lblk: the offset where we start to search
* @end: the offset where we stop to search
* @es: delayed extent that we found
*/
void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
void ext4_es_find_delayed_extent_range(struct inode *inode,
ext4_lblk_t lblk, ext4_lblk_t end,
struct extent_status *es)
{
struct ext4_es_tree *tree = NULL;
@ -247,7 +249,8 @@ void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
struct rb_node *node;
BUG_ON(es == NULL);
trace_ext4_es_find_delayed_extent_enter(inode, lblk);
BUG_ON(end < lblk);
trace_ext4_es_find_delayed_extent_range_enter(inode, lblk);
read_lock(&EXT4_I(inode)->i_es_lock);
tree = &EXT4_I(inode)->i_es_tree;
@ -270,6 +273,10 @@ void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
if (es1 && !ext4_es_is_delayed(es1)) {
while ((node = rb_next(&es1->rb_node)) != NULL) {
es1 = rb_entry(node, struct extent_status, rb_node);
if (es1->es_lblk > end) {
es1 = NULL;
break;
}
if (ext4_es_is_delayed(es1))
break;
}
@ -285,7 +292,7 @@ void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
read_unlock(&EXT4_I(inode)->i_es_lock);
ext4_es_lru_add(inode);
trace_ext4_es_find_delayed_extent_exit(inode, es);
trace_ext4_es_find_delayed_extent_range_exit(inode, es);
}
static struct extent_status *

View File

@ -62,7 +62,8 @@ extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
unsigned long long status);
extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len);
extern void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
extern void ext4_es_find_delayed_extent_range(struct inode *inode,
ext4_lblk_t lblk, ext4_lblk_t end,
struct extent_status *es);
extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
struct extent_status *es);

View File

@ -465,7 +465,7 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
* If there is a delay extent at this offset,
* it will be as a data.
*/
ext4_es_find_delayed_extent(inode, last, &es);
ext4_es_find_delayed_extent_range(inode, last, last, &es);
if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
if (last != start)
dataoff = last << blkbits;
@ -548,7 +548,7 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
* If there is a delay extent at this offset,
* we will skip this extent.
*/
ext4_es_find_delayed_extent(inode, last, &es);
ext4_es_find_delayed_extent_range(inode, last, last, &es);
if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
last = es.es_lblk + es.es_len;
holeoff = last << blkbits;

View File

@ -1488,10 +1488,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
struct ext4_io_submit io_submit;
BUG_ON(mpd->next_page <= mpd->first_page);
ext4_io_submit_init(&io_submit, mpd->wbc);
io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
if (!io_submit.io_end)
return -ENOMEM;
memset(&io_submit, 0, sizeof(io_submit));
/*
* We need to start from the first_page to the next_page - 1
* to make sure we also write the mapped dirty buffer_heads.
@ -1579,8 +1576,6 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
pagevec_release(&pvec);
}
ext4_io_submit(&io_submit);
/* Drop io_end reference we got from init */
ext4_put_io_end_defer(io_submit.io_end);
return ret;
}
@ -2239,16 +2234,9 @@ static int ext4_writepage(struct page *page,
*/
return __ext4_journalled_writepage(page, len);
ext4_io_submit_init(&io_submit, wbc);
io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
if (!io_submit.io_end) {
redirty_page_for_writepage(wbc, page);
return -ENOMEM;
}
memset(&io_submit, 0, sizeof(io_submit));
ret = ext4_bio_write_page(&io_submit, page, len, wbc);
ext4_io_submit(&io_submit);
/* Drop io_end reference we got from init */
ext4_put_io_end_defer(io_submit.io_end);
return ret;
}
@ -3079,13 +3067,9 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
struct inode *inode = file_inode(iocb->ki_filp);
ext4_io_end_t *io_end = iocb->private;
/* if not async direct IO just return */
if (!io_end) {
inode_dio_done(inode);
if (is_async)
aio_complete(iocb, ret, 0);
return;
}
/* if not async direct IO or dio with 0 bytes write, just return */
if (!io_end || !size)
goto out;
ext_debug("ext4_end_io_dio(): io_end 0x%p "
"for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
@ -3093,13 +3077,25 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
size);
iocb->private = NULL;
/* if not aio dio with unwritten extents, just free io and return */
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
ext4_free_io_end(io_end);
out:
inode_dio_done(inode);
if (is_async)
aio_complete(iocb, ret, 0);
return;
}
io_end->offset = offset;
io_end->size = size;
if (is_async) {
io_end->iocb = iocb;
io_end->result = ret;
}
ext4_put_io_end_defer(io_end);
ext4_add_complete_io(io_end);
}
/*
@ -3133,7 +3129,6 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
get_block_t *get_block_func = NULL;
int dio_flags = 0;
loff_t final_size = offset + count;
ext4_io_end_t *io_end = NULL;
/* Use the old path for reads and writes beyond i_size. */
if (rw != WRITE || final_size > inode->i_size)
@ -3172,16 +3167,13 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
iocb->private = NULL;
ext4_inode_aio_set(inode, NULL);
if (!is_sync_kiocb(iocb)) {
io_end = ext4_init_io_end(inode, GFP_NOFS);
ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS);
if (!io_end) {
ret = -ENOMEM;
goto retake_lock;
}
io_end->flag |= EXT4_IO_END_DIRECT;
/*
* Grab reference for DIO. Will be dropped in ext4_end_io_dio()
*/
iocb->private = ext4_get_io_end(io_end);
iocb->private = io_end;
/*
* we save the io structure for current async direct
* IO, so that later ext4_map_blocks() could flag the
@ -3205,27 +3197,26 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
NULL,
dio_flags);
/*
* Put our reference to io_end. This can free the io_end structure e.g.
* in sync IO case or in case of error. It can even perform extent
* conversion if all bios we submitted finished before we got here.
* Note that in that case iocb->private can be already set to NULL
* here.
*/
if (io_end) {
if (iocb->private)
ext4_inode_aio_set(inode, NULL);
ext4_put_io_end(io_end);
/*
* In case of error or no write ext4_end_io_dio() was not
* called so we have to put iocb's reference.
*/
if (ret <= 0 && ret != -EIOCBQUEUED) {
WARN_ON(iocb->private != io_end);
ext4_put_io_end(io_end);
iocb->private = NULL;
}
}
if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
/*
* The io_end structure takes a reference to the inode, that
* structure needs to be destroyed and the reference to the
* inode need to be dropped, when IO is complete, even with 0
* byte write, or failed.
*
* In the successful AIO DIO case, the io_end structure will
* be destroyed and the reference to the inode will be dropped
* after the end_io call back function is called.
*
* In the case there is 0 byte write, or error case, since VFS
* direct IO won't invoke the end_io call back function, we
* need to free the end_io structure here.
*/
if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
ext4_free_io_end(iocb->private);
iocb->private = NULL;
} else if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN)) {
int err;
/*

View File

@ -2105,7 +2105,11 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
group = ac->ac_g_ex.fe_group;
for (i = 0; i < ngroups; group++, i++) {
if (group == ngroups)
/*
* Artificially restricted ngroups for non-extent
* files makes group > ngroups possible on first loop.
*/
if (group >= ngroups)
group = 0;
/* This now checks without needing the buddy page */

View File

@ -62,28 +62,15 @@ void ext4_ioend_shutdown(struct inode *inode)
cancel_work_sync(&EXT4_I(inode)->i_unwritten_work);
}
static void ext4_release_io_end(ext4_io_end_t *io_end)
void ext4_free_io_end(ext4_io_end_t *io)
{
BUG_ON(!list_empty(&io_end->list));
BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
BUG_ON(!io);
BUG_ON(!list_empty(&io->list));
BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count))
wake_up_all(ext4_ioend_wq(io_end->inode));
if (io_end->flag & EXT4_IO_END_DIRECT)
inode_dio_done(io_end->inode);
if (io_end->iocb)
aio_complete(io_end->iocb, io_end->result, 0);
kmem_cache_free(io_end_cachep, io_end);
}
static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
{
struct inode *inode = io_end->inode;
io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
/* Wake up anyone waiting on unwritten extent conversion */
if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
wake_up_all(ext4_ioend_wq(inode));
if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count))
wake_up_all(ext4_ioend_wq(io->inode));
kmem_cache_free(io_end_cachep, io);
}
/* check a range of space and convert unwritten extents to written. */
@ -106,8 +93,13 @@ static int ext4_end_io(ext4_io_end_t *io)
"(inode %lu, offset %llu, size %zd, error %d)",
inode->i_ino, offset, size, ret);
}
ext4_clear_io_unwritten_flag(io);
ext4_release_io_end(io);
/* Wake up anyone waiting on unwritten extent conversion */
if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
wake_up_all(ext4_ioend_wq(inode));
if (io->flag & EXT4_IO_END_DIRECT)
inode_dio_done(inode);
if (io->iocb)
aio_complete(io->iocb, io->result, 0);
return ret;
}
@ -138,7 +130,7 @@ static void dump_completed_IO(struct inode *inode)
}
/* Add the io_end to per-inode completed end_io list. */
static void ext4_add_complete_io(ext4_io_end_t *io_end)
void ext4_add_complete_io(ext4_io_end_t *io_end)
{
struct ext4_inode_info *ei = EXT4_I(io_end->inode);
struct workqueue_struct *wq;
@ -175,6 +167,8 @@ static int ext4_do_flush_completed_IO(struct inode *inode)
err = ext4_end_io(io);
if (unlikely(!ret && err))
ret = err;
io->flag &= ~EXT4_IO_END_UNWRITTEN;
ext4_free_io_end(io);
}
return ret;
}
@ -206,43 +200,10 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
atomic_inc(&EXT4_I(inode)->i_ioend_count);
io->inode = inode;
INIT_LIST_HEAD(&io->list);
atomic_set(&io->count, 1);
}
return io;
}
void ext4_put_io_end_defer(ext4_io_end_t *io_end)
{
if (atomic_dec_and_test(&io_end->count)) {
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) {
ext4_release_io_end(io_end);
return;
}
ext4_add_complete_io(io_end);
}
}
int ext4_put_io_end(ext4_io_end_t *io_end)
{
int err = 0;
if (atomic_dec_and_test(&io_end->count)) {
if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
err = ext4_convert_unwritten_extents(io_end->inode,
io_end->offset, io_end->size);
ext4_clear_io_unwritten_flag(io_end);
}
ext4_release_io_end(io_end);
}
return err;
}
ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end)
{
atomic_inc(&io_end->count);
return io_end;
}
/*
* Print an buffer I/O error compatible with the fs/buffer.c. This
* provides compatibility with dmesg scrapers that look for a specific
@ -325,7 +286,12 @@ static void ext4_end_bio(struct bio *bio, int error)
bi_sector >> (inode->i_blkbits - 9));
}
ext4_put_io_end_defer(io_end);
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
ext4_free_io_end(io_end);
return;
}
ext4_add_complete_io(io_end);
}
void ext4_io_submit(struct ext4_io_submit *io)
@ -339,37 +305,40 @@ void ext4_io_submit(struct ext4_io_submit *io)
bio_put(io->io_bio);
}
io->io_bio = NULL;
}
void ext4_io_submit_init(struct ext4_io_submit *io,
struct writeback_control *wbc)
{
io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
io->io_bio = NULL;
io->io_op = 0;
io->io_end = NULL;
}
static int io_submit_init_bio(struct ext4_io_submit *io,
struct buffer_head *bh)
static int io_submit_init(struct ext4_io_submit *io,
struct inode *inode,
struct writeback_control *wbc,
struct buffer_head *bh)
{
ext4_io_end_t *io_end;
struct page *page = bh->b_page;
int nvecs = bio_get_nr_vecs(bh->b_bdev);
struct bio *bio;
io_end = ext4_init_io_end(inode, GFP_NOFS);
if (!io_end)
return -ENOMEM;
bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
bio->bi_private = io->io_end = io_end;
bio->bi_end_io = ext4_end_bio;
bio->bi_private = ext4_get_io_end(io->io_end);
if (!io->io_end->size)
io->io_end->offset = (bh->b_page->index << PAGE_CACHE_SHIFT)
+ bh_offset(bh);
io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
io->io_bio = bio;
io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
io->io_next_block = bh->b_blocknr;
return 0;
}
static int io_submit_add_bh(struct ext4_io_submit *io,
struct inode *inode,
struct writeback_control *wbc,
struct buffer_head *bh)
{
ext4_io_end_t *io_end;
@ -380,18 +349,18 @@ static int io_submit_add_bh(struct ext4_io_submit *io,
ext4_io_submit(io);
}
if (io->io_bio == NULL) {
ret = io_submit_init_bio(io, bh);
ret = io_submit_init(io, inode, wbc, bh);
if (ret)
return ret;
}
ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
if (ret != bh->b_size)
goto submit_and_retry;
io_end = io->io_end;
if (test_clear_buffer_uninit(bh))
ext4_set_io_unwritten_flag(inode, io_end);
io_end->size += bh->b_size;
io->io_end->size += bh->b_size;
io->io_next_block++;
ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
if (ret != bh->b_size)
goto submit_and_retry;
return 0;
}
@ -463,7 +432,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
do {
if (!buffer_async_write(bh))
continue;
ret = io_submit_add_bh(io, inode, bh);
ret = io_submit_add_bh(io, inode, wbc, bh);
if (ret) {
/*
* We only get here on ENOMEM. Not much else

View File

@ -30,15 +30,19 @@ struct journal_head {
/*
* Journalling list for this buffer [jbd_lock_bh_state()]
* NOTE: We *cannot* combine this with b_modified into a bitfield
* as gcc would then (which the C standard allows but which is
* very unuseful) make 64-bit accesses to the bitfield and clobber
* b_jcount if its update races with bitfield modification.
*/
unsigned b_jlist:4;
unsigned b_jlist;
/*
* This flag signals the buffer has been modified by
* the currently running transaction
* [jbd_lock_bh_state()]
*/
unsigned b_modified:1;
unsigned b_modified;
/*
* Copy of the buffer data frozen for writing to the log.

View File

@ -2139,7 +2139,7 @@ TRACE_EVENT(ext4_es_remove_extent,
__entry->lblk, __entry->len)
);
TRACE_EVENT(ext4_es_find_delayed_extent_enter,
TRACE_EVENT(ext4_es_find_delayed_extent_range_enter,
TP_PROTO(struct inode *inode, ext4_lblk_t lblk),
TP_ARGS(inode, lblk),
@ -2161,7 +2161,7 @@ TRACE_EVENT(ext4_es_find_delayed_extent_enter,
(unsigned long) __entry->ino, __entry->lblk)
);
TRACE_EVENT(ext4_es_find_delayed_extent_exit,
TRACE_EVENT(ext4_es_find_delayed_extent_range_exit,
TP_PROTO(struct inode *inode, struct extent_status *es),
TP_ARGS(inode, es),