linux/fs, branch v3.2.22

nilfs2: ensure proper cache clearing for gc-inodes

2012-07-04T04:44:10Z

commit fbb24a3a915f105016f1c828476be11aceac8504 upstream. A gc-inode is a pseudo inode used to buffer the blocks to be moved by garbage collection. Block caches of gc-inodes must be cleared every time a garbage collection function (nilfs_clean_segments) completes. Otherwise, stale blocks buffered in the caches may be wrongly reused in successive calls of the GC function. For user files, this is not a problem because their gc-inodes are distinguished by a checkpoint number as well as an inode number. They never buffer different blocks if either an inode number, a checkpoint number, or a block offset differs. However, gc-inodes of sufile, cpfile and DAT file can store different data for the same block offset. Thus, the nilfs_clean_segments function can move incorrect block for these meta-data files if an old block is cached. I found this is really causing meta-data corruption in nilfs. This fixes the issue by ensuring cache clear of gc-inodes and resolves reported GC problems including checkpoint file corruption, b-tree corruption, and the following warning during GC. nilfs_palloc_freev: entry number 307234 already freed. ... Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Ben Hutchings

NFSv4: Fix unnecessary delegation returns in nfs4_do_open

2012-06-19T22:18:16Z

commit 2d0dbc6ae8a5194aaecb9cfffb9053f38fce8b86 upstream. While nfs4_do_open() expects the fmode argument to be restricted to combinations of FMODE_READ and FMODE_WRITE, both nfs4_atomic_open() and nfs4_proc_create will pass the nfs_open_context->mode, which contains the full fmode_t. This patch ensures that nfs4_do_open strips the other fmode_t bits, fixing a problem in which the nfs4_do_open call would result in an unnecessary delegation return. Reported-by: Fred Isaman Signed-off-by: Trond Myklebust Signed-off-by: Ben Hutchings

fuse: fix stat call on 32 bit platforms

2012-06-19T22:18:05Z

commit 45c72cd73c788dd18c8113d4a404d6b4a01decf1 upstream. Now we store attr->ino at inode->i_ino, return attr->ino at the first time and then return inode->i_ino if the attribute timeout isn't expired. That's wrong on 32 bit platforms because attr->ino is 64 bit and inode->i_ino is 32 bit in this case. Fix this by saving 64 bit ino in fuse_inode structure and returning it every time we call getattr. Also squash attr->ino into inode->i_ino explicitly. Signed-off-by: Pavel Shilovsky Signed-off-by: Miklos Szeredi Signed-off-by: Ben Hutchings

ext4: fix the free blocks calculation for ext3 file systems w/ uninit_bg

2012-06-10T13:42:12Z

commit b0dd6b70f0fda17ae9762fbb72d98e40a4f66556 upstream. Ext3 filesystems that are converted to use as many ext4 file system features as possible will enable uninit_bg to speed up e2fsck times. These file systems will have a native ext3 layout of inode tables and block allocation bitmaps (as opposed to ext4's flex_bg layout). Unfortunately, in these cases, when first allocating a block in an uninitialized block group, ext4 would incorrectly calculate the number of free blocks in that block group, and then errorneously report that the file system was corrupt: EXT4-fs error (device vdd): ext4_mb_generate_buddy:741: group 30, 32254 clusters in bitmap, 32258 in gd This problem can be reproduced via: mke2fs -q -t ext4 -O ^flex_bg /dev/vdd 5g mount -t ext4 /dev/vdd /mnt fallocate -l 4600m /mnt/test The problem was caused by a bone headed mistake in the check to see if a particular metadata block was part of the block group. Many thanks to Kees Cook for finding and bisecting the buggy commit which introduced this bug (commit fd034a84e1, present since v3.2). Reported-by: Sander Eikelenboom Reported-by: Kees Cook Signed-off-by: "Theodore Ts'o" Tested-by: Kees Cook Signed-off-by: Ben Hutchings

ext4: don't set i_flags in EXT4_IOC_SETFLAGS

2012-06-10T13:42:11Z

commit b22b1f178f6799278d3178d894f37facb2085765 upstream. Commit 7990696 uses the ext4_{set,clear}_inode_flags() functions to change the i_flags automatically but fails to remove the error setting of i_flags. So we still have the problem of trashing state flags. Fix this by removing the assignment. Signed-off-by: Tao Ma Signed-off-by: "Theodore Ts'o" Signed-off-by: Ben Hutchings

ext4: don't trash state flags in EXT4_IOC_SETFLAGS

2012-06-10T13:42:11Z

commit 79906964a187c405db72a3abc60eb9b50d804fbc upstream. In commit 353eb83c we removed i_state_flags with 64-bit longs, But when handling the EXT4_IOC_SETFLAGS ioctl, we replace i_flags directly, which trashes the state flags which are stored in the high 32-bits of i_flags on 64-bit platforms. So use the the ext4_{set,clear}_inode_flags() functions which use atomic bit manipulation functions instead. Reported-by: Tao Ma Signed-off-by: "Theodore Ts'o" Signed-off-by: Ben Hutchings

ext4: remove mb_groups before tearing down the buddy_cache

2012-06-10T13:41:53Z

commit 95599968d19db175829fb580baa6b68939b320fb upstream. We can't have references held on pages in the s_buddy_cache while we are trying to truncate its pages and put the inode. All the pages must be gone before we reach clear_inode. This can only be gauranteed if we can prevent new users from grabbing references to s_buddy_cache's pages. The original bug can be reproduced and the bug fix can be verified by: while true; do mount -t ext4 /dev/ram0 /export/hda3/ram0; \ umount /export/hda3/ram0; done & while true; do cat /proc/fs/ext4/ram0/mb_groups; done Signed-off-by: Salman Qazi Signed-off-by: "Theodore Ts'o" Signed-off-by: Ben Hutchings

ext4: add ext4_mb_unload_buddy in the error path

2012-06-10T13:41:52Z

commit 02b7831019ea4e7994968c84b5826fa8b248ffc8 upstream. ext4_free_blocks fails to pair an ext4_mb_load_buddy with a matching ext4_mb_unload_buddy when it fails a memory allocation. Signed-off-by: Salman Qazi Signed-off-by: "Theodore Ts'o" Signed-off-by: Ben Hutchings

ext4: add missing save_error_info() to ext4_error()

2012-06-10T13:41:51Z

commit f3fc0210c0fc91900766c995f089c39170e68305 upstream. The ext4_error() function is missing a call to save_error_info(). Since this is the function which marks the file system as containing an error, this oversight (which was introduced in 2.6.36) is quite significant, and should be backported to older stable kernels with high urgency. Reported-by: Ken Sumrall Signed-off-by: "Theodore Ts'o" Cc: ksumrall@google.com Signed-off-by: Ben Hutchings

vfs: umount_tree() might be called on subtree that had never made it

2012-06-10T13:41:51Z

commit 63d37a84ab6004c235314ffd7a76c5eb28c2fae0 upstream. __mnt_make_shortterm() in there undoes the effect of __mnt_make_longterm() we'd done back when we set ->mnt_ns non-NULL; it should not be done to vfsmounts that had never gone through commit_tree() and friends. Kudos to lczerner for catching that one... Signed-off-by: Al Viro Signed-off-by: Ben Hutchings