From 08da1193d2c8c7a25d0cef7f85d0b9f1ad7c583a Mon Sep 17 00:00:00 2001 From: Markus Trippelsdorf Date: Wed, 17 Nov 2010 21:46:06 -0500 Subject: ext4: fix setting random pages PageUptodate ext4_end_bio calls put_page and kmem_cache_free before calling SetPageUpdate(). This can result in setting the PageUptodate bit on random pages and causes the following BUG: BUG: Bad page state in process rm pfn:52e54 page:ffffea0001222260 count:0 mapcount:0 mapping: (null) index:0x0 arch kernel: page flags: 0x4000000000000008(uptodate) Fix the problem by moving put_io_page() after the SetPageUpdate() call. Thanks to Hugh Dickins for analyzing this problem. Reported-by: Markus Trippelsdorf Tested-by: Markus Trippelsdorf Signed-off-by: Markus Trippelsdorf Signed-off-by: "Theodore Ts'o" --- fs/ext4/page-io.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 7f5451cd1d3..beacce11ac5 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -237,8 +237,6 @@ static void ext4_end_bio(struct bio *bio, int error) } while (bh != head); } - put_io_page(io_end->pages[i]); - /* * If this is a partial write which happened to make * all buffers uptodate then we can optimize away a @@ -248,6 +246,8 @@ static void ext4_end_bio(struct bio *bio, int error) */ if (!partial_write) SetPageUptodate(page); + + put_io_page(io_end->pages[i]); } io_end->num_io_pages = 0; inode = io_end->inode; -- cgit v1.2.3-18-g5258 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(-) 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 0587aa3d11f9769a301b21bff2c3ed8365606b8d Mon Sep 17 00:00:00 2001 From: yangsheng Date: Wed, 17 Nov 2010 21:46:26 -0500 Subject: jbd2: fix /proc/fs/jbd2/ when using an external journal In jbd2_journal_init_dev(), we need make sure the journal structure is fully initialzied before calling jbd2_stats_proc_init(). Reviewed-by: Andreas Dilger Signed-off-by: yangsheng Signed-off-by: "Theodore Ts'o" --- fs/jbd2/journal.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index c590d155c09..f837ba95352 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -899,6 +899,14 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, /* journal descriptor can store up to n blocks -bzzz */ journal->j_blocksize = blocksize; + journal->j_dev = bdev; + journal->j_fs_dev = fs_dev; + journal->j_blk_offset = start; + journal->j_maxlen = len; + bdevname(journal->j_dev, journal->j_devname); + p = journal->j_devname; + while ((p = strchr(p, '/'))) + *p = '!'; jbd2_stats_proc_init(journal); n = journal->j_blocksize / sizeof(journal_block_tag_t); journal->j_wbufsize = n; @@ -908,14 +916,6 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, __func__); goto out_err; } - journal->j_dev = bdev; - journal->j_fs_dev = fs_dev; - journal->j_blk_offset = start; - journal->j_maxlen = len; - bdevname(journal->j_dev, journal->j_devname); - p = journal->j_devname; - while ((p = strchr(p, '/'))) - *p = '!'; bh = __getblk(journal->j_dev, start, journal->j_blocksize); if (!bh) { -- 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(-) 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 - fs/ioctl.c | 39 --------------------------------------- include/linux/fs.h | 1 - 3 files changed, 41 deletions(-) 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 = { diff --git a/fs/ioctl.c b/fs/ioctl.c index e92fdbb3bc3..f855ea4fc88 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -530,41 +530,6 @@ static int ioctl_fsthaw(struct file *filp) return thaw_super(sb); } -static int ioctl_fstrim(struct file *filp, void __user *argp) -{ - struct super_block *sb = filp->f_path.dentry->d_inode->i_sb; - struct fstrim_range range; - int ret = 0; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - /* If filesystem doesn't support trim feature, return. */ - if (sb->s_op->trim_fs == NULL) - return -EOPNOTSUPP; - - /* If a blockdevice-backed filesystem isn't specified, return EINVAL. */ - if (sb->s_bdev == NULL) - return -EINVAL; - - if (argp == NULL) { - range.start = 0; - range.len = ULLONG_MAX; - range.minlen = 0; - } else if (copy_from_user(&range, argp, sizeof(range))) - return -EFAULT; - - ret = sb->s_op->trim_fs(sb, &range); - if (ret < 0) - return ret; - - if ((argp != NULL) && - (copy_to_user(argp, &range, sizeof(range)))) - return -EFAULT; - - return 0; -} - /* * When you add any new common ioctls to the switches above and below * please update compat_sys_ioctl() too. @@ -615,10 +580,6 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, error = ioctl_fsthaw(filp); break; - case FITRIM: - error = ioctl_fstrim(filp, argp); - break; - case FS_IOC_FIEMAP: return ioctl_fiemap(filp, arg); diff --git a/include/linux/fs.h b/include/linux/fs.h index 334d68a1710..eedc00b7b1e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1612,7 +1612,6 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); - int (*trim_fs) (struct super_block *, struct fstrim_range *); }; /* -- cgit v1.2.3-18-g5258 From e681c047e47c0abe67bf95857f23814372793cb0 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Fri, 19 Nov 2010 21:47:07 -0500 Subject: ext4: Add EXT4_IOC_TRIM ioctl to handle batched discard Filesystem independent ioctl was rejected as not common enough to be in core vfs ioctl. Since we still need to access to this functionality this commit adds ext4 specific ioctl EXT4_IOC_TRIM to dispatch ext4_trim_fs(). It takes fstrim_range structure as an argument. fstrim_range is definec in the include/linux/fs.h and its definition is as follows. struct fstrim_range { __u64 start; __u64 len; __u64 minlen; } start - first Byte to trim len - number of Bytes to trim from start minlen - minimum extent length to trim, free extents shorter than this number of Bytes will be ignored. This will be rounded up to fs block size. After the FITRIM is done, the number of actually discarded Bytes is stored in fstrim_range.len to give the user better insight on how much storage space has been really released for wear-leveling. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/ioctl.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index bf5ae883b1b..eb3bc2fe647 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -331,6 +331,30 @@ mext_out: return err; } + case FITRIM: + { + struct super_block *sb = inode->i_sb; + struct fstrim_range range; + int ret = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (copy_from_user(&range, (struct fstrim_range *)arg, + sizeof(range))) + return -EFAULT; + + ret = ext4_trim_fs(sb, &range); + if (ret < 0) + return ret; + + if (copy_to_user((struct fstrim_range *)arg, &range, + sizeof(range))) + return -EFAULT; + + return 0; + } + default: return -ENOTTY; } -- cgit v1.2.3-18-g5258