From f4c8cc652d9f70680dd91be60a7a455040d0a282 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 17 Nov 2010 21:46:25 -0500 Subject: ext4: missing unlock in ext4_clear_request_list() If the the li_request_list was empty then it returned with the lock held. Instead of adding a "goto unlock" I just removed that special case and let it go past the empty list_for_each_safe(). Signed-off-by: Dan Carpenter Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 61182fe6254..ef09d1443d1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2799,9 +2799,6 @@ static void ext4_clear_request_list(void) struct ext4_li_request *elr; mutex_lock(&ext4_li_info->li_list_mtx); - if (list_empty(&ext4_li_info->li_request_list)) - return; - list_for_each_safe(pos, n, &ext4_li_info->li_request_list) { elr = list_entry(pos, struct ext4_li_request, lr_request); -- cgit v1.2.3-18-g5258 From 5a9ae68a349aa076bc8557ee2fcf865574459282 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 19 Nov 2010 09:56:44 -0500 Subject: ext4: ext4_fill_super shouldn't return 0 on corruption At the start of ext4_fill_super, ret is set to -EINVAL, and any failure path out of that function returns ret. However, the generic_check_addressable clause sets ret = 0 (if it passes), which means that a subsequent failure (e.g. a group checksum error) returns 0 even though the mount should fail. This causes vfs_kern_mount in turn to think that the mount succeeded, leading to an oops. A simple fix is to avoid using ret for the generic_check_addressable check, which was last changed in commit 30ca22c70e3ef0a96ff84de69cd7e8561b416cb2. Signed-off-by: Darrick J. Wong Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ef09d1443d1..14ada8c50c4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3265,13 +3265,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. */ - ret = generic_check_addressable(sb->s_blocksize_bits, + err = generic_check_addressable(sb->s_blocksize_bits, ext4_blocks_count(es)); - if (ret) { + if (err) { ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely on this system"); if (sizeof(sector_t) < 8) ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); + ret = err; goto failed_mount; } -- cgit v1.2.3-18-g5258 From 93bb41f4f8b89ac8b4d0a734bc59634cb0a29a89 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Fri, 19 Nov 2010 21:18:35 -0500 Subject: fs: Do not dispatch FITRIM through separate super_operation There was concern that FITRIM ioctl is not common enough to be included in core vfs ioctl, as Christoph Hellwig pointed out there's no real point in dispatching this out to a separate vector instead of just through ->ioctl. So this commit removes ioctl_fstrim() from vfs ioctl and trim_fs from super_operation structure. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 14ada8c50c4..e32195d6aac 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1197,7 +1197,6 @@ static const struct super_operations ext4_sops = { .quota_write = ext4_quota_write, #endif .bdev_try_to_free_page = bdev_try_to_free_page, - .trim_fs = ext4_trim_fs }; static const struct super_operations ext4_nojournal_sops = { -- cgit v1.2.3-18-g5258 From 1449032be17abb69116dbc393f67ceb8bd034f92 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 14 Dec 2010 15:27:50 -0500 Subject: ext4: Turn off multiple page-io submission by default Jon Nelson has found a test case which causes postgresql to fail with the error: psql:t.sql:4: ERROR: invalid page header in block 38269 of relation base/16384/16581 Under memory pressure, it looks like part of a file can end up getting replaced by zero's. Until we can figure out the cause, we'll roll back the change and use block_write_full_page() instead of ext4_bio_write_page(). The new, more efficient writing function can be used via the mount option mblk_io_submit, so we can test and fix the new page I/O code. To reproduce the problem, install postgres 8.4 or 9.0, and pin enough memory such that the system just at the end of triggering writeback before running the following sql script: begin; create temporary table foo as select x as a, ARRAY[x] as b FROM generate_series(1, 10000000 ) AS x; create index foo_a_idx on foo (a); create index foo_b_idx on foo USING GIN (b); rollback; If the temporary table is created on a hard drive partition which is encrypted using dm_crypt, then under memory pressure, approximately 30-40% of the time, pgsql will issue the above failure. This patch should fix this problem, and the problem will come back if the file system is mounted with the mblk_io_submit mount option. Reported-by: Jon Nelson Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e32195d6aac..fb15c9c0be7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1026,6 +1026,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) !(def_mount_opts & EXT4_DEFM_NODELALLOC)) seq_puts(seq, ",nodelalloc"); + if (test_opt(sb, MBLK_IO_SUBMIT)) + seq_puts(seq, ",mblk_io_submit"); if (sbi->s_stripe) seq_printf(seq, ",stripe=%lu", sbi->s_stripe); /* @@ -1239,8 +1241,8 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version, - Opt_stripe, Opt_delalloc, Opt_nodelalloc, - Opt_block_validity, Opt_noblock_validity, + Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit, + Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, @@ -1304,6 +1306,8 @@ static const match_table_t tokens = { {Opt_resize, "resize"}, {Opt_delalloc, "delalloc"}, {Opt_nodelalloc, "nodelalloc"}, + {Opt_mblk_io_submit, "mblk_io_submit"}, + {Opt_nomblk_io_submit, "nomblk_io_submit"}, {Opt_block_validity, "block_validity"}, {Opt_noblock_validity, "noblock_validity"}, {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, @@ -1725,6 +1729,12 @@ set_qf_format: case Opt_nodelalloc: clear_opt(sbi->s_mount_opt, DELALLOC); break; + case Opt_mblk_io_submit: + set_opt(sbi->s_mount_opt, MBLK_IO_SUBMIT); + break; + case Opt_nomblk_io_submit: + clear_opt(sbi->s_mount_opt, MBLK_IO_SUBMIT); + break; case Opt_stripe: if (match_int(&args[0], &option)) return 0; -- cgit v1.2.3-18-g5258