From 5ffd3412ae5536a4c57469cb8ea31887121dcb2e Mon Sep 17 00:00:00 2001 From: Thomas Betker Date: Wed, 17 Oct 2012 22:59:30 +0200 Subject: jffs2: Fix lock acquisition order bug in jffs2_write_begin jffs2_write_begin() first acquires the page lock, then f->sem. This causes an AB-BA deadlock with jffs2_garbage_collect_live(), which first acquires f->sem, then the page lock: jffs2_garbage_collect_live mutex_lock(&f->sem) (A) jffs2_garbage_collect_dnode jffs2_gc_fetch_page read_cache_page_async do_read_cache_page lock_page(page) (B) jffs2_write_begin grab_cache_page_write_begin find_lock_page lock_page(page) (B) mutex_lock(&f->sem) (A) We fix this by restructuring jffs2_write_begin() to take f->sem before the page lock. However, we make sure that f->sem is not held when calling jffs2_reserve_space(), as this is not permitted by the locking rules. The deadlock above was observed multiple times on an SoC with a dual ARMv7 (Cortex-A9), running the long-term 3.4.11 kernel; it occurred when using scp to copy files from a host system to the ARM target system. The fix was heavily tested on the same target system. Cc: stable@vger.kernel.org Signed-off-by: Thomas Betker Acked-by: Joakim Tjernlund Signed-off-by: Artem Bityutskiy --- fs/jffs2/file.c | 39 +++++++++++++++++++++------------------ 1 file changed, 21 insertions(+), 18 deletions(-) (limited to 'fs') diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 60ef3fb707f..1506673c087 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -138,33 +138,39 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); + struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); + struct jffs2_raw_inode ri; + uint32_t alloc_len = 0; pgoff_t index = pos >> PAGE_CACHE_SHIFT; uint32_t pageofs = index << PAGE_CACHE_SHIFT; int ret = 0; + jffs2_dbg(1, "%s()\n", __func__); + + if (pageofs > inode->i_size) { + ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, + ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); + if (ret) + return ret; + } + + mutex_lock(&f->sem); pg = grab_cache_page_write_begin(mapping, index, flags); - if (!pg) + if (!pg) { + if (alloc_len) + jffs2_complete_reservation(c); + mutex_unlock(&f->sem); return -ENOMEM; + } *pagep = pg; - jffs2_dbg(1, "%s()\n", __func__); - - if (pageofs > inode->i_size) { + if (alloc_len) { /* Make new hole frag from old EOF to new page */ - struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); - struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; - uint32_t alloc_len; jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", (unsigned int)inode->i_size, pageofs); - ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, - ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); - if (ret) - goto out_page; - - mutex_lock(&f->sem); memset(&ri, 0, sizeof(ri)); ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); @@ -191,7 +197,6 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, if (IS_ERR(fn)) { ret = PTR_ERR(fn); jffs2_complete_reservation(c); - mutex_unlock(&f->sem); goto out_page; } ret = jffs2_add_full_dnode_to_inode(c, f, fn); @@ -206,12 +211,10 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, jffs2_mark_node_obsolete(c, fn->raw); jffs2_free_full_dnode(fn); jffs2_complete_reservation(c); - mutex_unlock(&f->sem); goto out_page; } jffs2_complete_reservation(c); inode->i_size = pageofs; - mutex_unlock(&f->sem); } /* @@ -220,18 +223,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * case of a short-copy. */ if (!PageUptodate(pg)) { - mutex_lock(&f->sem); ret = jffs2_do_readpage_nolock(inode, pg); - mutex_unlock(&f->sem); if (ret) goto out_page; } + mutex_unlock(&f->sem); jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); return ret; out_page: unlock_page(pg); page_cache_release(pg); + mutex_unlock(&f->sem); return ret; } -- cgit v1.2.3 From 5a8477660d9ddc090203736d7271137265cb25bb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 12 Nov 2012 01:19:02 -0500 Subject: kill bogus BUG_ON() in do_close_on_exec() It can be legitimately triggered via procfs access. Now, at least 2 of 3 of get_files_struct() callers in procfs are useless, but when and if we get rid of those we can always add WARN_ON() here. BUG_ON() at that spot is simply wrong. Signed-off-by: Al Viro --- fs/file.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs') diff --git a/fs/file.c b/fs/file.c index d3b5fa80b71..331e7d24d9d 100644 --- a/fs/file.c +++ b/fs/file.c @@ -685,7 +685,6 @@ void do_close_on_exec(struct files_struct *files) struct fdtable *fdt; /* exec unshares first */ - BUG_ON(atomic_read(&files->count) != 1); spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; -- cgit v1.2.3 From 42e2976f131d65555d5c1d6c3d47facc63577814 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 12 Nov 2012 22:09:44 +1100 Subject: xfs: fix attr tree double split corruption In certain circumstances, a double split of an attribute tree is needed to insert or replace an attribute. In rare situations, this can go wrong, leaving the attribute tree corrupted. In this case, the attr being replaced is the last attr in a leaf node, and the replacement is larger so doesn't fit in the same leaf node. When we have the initial condition of a node format attribute btree with two leaves at index 1 and 2. Call them L1 and L2. The leaf L1 is completely full, there is not a single byte of free space in it. L2 is mostly empty. The attribute being replaced - call it X - is the last attribute in L1. The way an attribute replace is executed is that the replacement attribute - call it Y - is first inserted into the tree, but has an INCOMPLETE flag set on it so that list traversals ignore it. Once this transaction is committed, a second transaction it run to atomically mark Y as COMPLETE and X as INCOMPLETE, so that a traversal will now find Y and skip X. Once that transaction is committed, attribute X is then removed. So, the initial condition is: +--------+ +--------+ | L1 | | L2 | | fwd: 2 |---->| fwd: 0 | | bwd: 0 |<----| bwd: 1 | | fsp: 0 | | fsp: N | |--------| |--------| | attr A | | attr 1 | |--------| |--------| | attr B | | attr 2 | |--------| |--------| .......... .......... |--------| |--------| | attr X | | attr n | +--------+ +--------+ So now we go to replace X, and see that L1:fsp = 0 - it is full so we can't insert Y in the same leaf. So we record the the location of attribute X so we can track it for later use, then we split L1 into L1 and L3 and reblance across the two leafs. We end with: +--------+ +--------+ +--------+ | L1 | | L3 | | L2 | | fwd: 3 |---->| fwd: 2 |---->| fwd: 0 | | bwd: 0 |<----| bwd: 1 |<----| bwd: 3 | | fsp: M | | fsp: J | | fsp: N | |--------| |--------| |--------| | attr A | | attr X | | attr 1 | |--------| +--------+ |--------| | attr B | | attr 2 | |--------| |--------| .......... .......... |--------| |--------| | attr W | | attr n | +--------+ +--------+ And we track that the original attribute is now at L3:0. We then try to insert Y into L1 again, and find that there isn't enough room because the new attribute is larger than the old one. Hence we have to split again to make room for Y. We end up with this: +--------+ +--------+ +--------+ +--------+ | L1 | | L4 | | L3 | | L2 | | fwd: 4 |---->| fwd: 3 |---->| fwd: 2 |---->| fwd: 0 | | bwd: 0 |<----| bwd: 1 |<----| bwd: 4 |<----| bwd: 3 | | fsp: M | | fsp: J | | fsp: J | | fsp: N | |--------| |--------| |--------| |--------| | attr A | | attr Y | | attr X | | attr 1 | |--------| + INCOMP + +--------+ |--------| | attr B | +--------+ | attr 2 | |--------| |--------| .......... .......... |--------| |--------| | attr W | | attr n | +--------+ +--------+ And now we have the new (incomplete) attribute @ L4:0, and the original attribute at L3:0. At this point, the first transaction is committed, and we move to the flipping of the flags. This is where we are supposed to end up with this: +--------+ +--------+ +--------+ +--------+ | L1 | | L4 | | L3 | | L2 | | fwd: 4 |---->| fwd: 3 |---->| fwd: 2 |---->| fwd: 0 | | bwd: 0 |<----| bwd: 1 |<----| bwd: 4 |<----| bwd: 3 | | fsp: M | | fsp: J | | fsp: J | | fsp: N | |--------| |--------| |--------| |--------| | attr A | | attr Y | | attr X | | attr 1 | |--------| +--------+ + INCOMP + |--------| | attr B | +--------+ | attr 2 | |--------| |--------| .......... .......... |--------| |--------| | attr W | | attr n | +--------+ +--------+ But that doesn't happen properly - the attribute tracking indexes are not pointing to the right locations. What we end up with is both the old attribute to be removed pointing at L4:0 and the new attribute at L4:1. On a debug kernel, this assert fails like so: XFS: Assertion failed: args->index2 < be16_to_cpu(leaf2->hdr.count), file: fs/xfs/xfs_attr_leaf.c, line: 2725 because the new attribute location does not exist. On a production kernel, this goes unnoticed and the code proceeds ahead merrily and removes L4 because it thinks that is the block that is no longer needed. This leaves the hash index node pointing to entries L1, L4 and L2, but only blocks L1, L3 and L2 to exist. Further, the leaf level sibling list is L1 <-> L4 <-> L2, but L4 is now free space, and so everything is busted. This corruption is caused by the removal of the old attribute triggering a join - it joins everything correctly but then frees the wrong block. xfs_repair will report something like: bad sibling back pointer for block 4 in attribute fork for inode 131 problem with attribute contents in inode 131 would clear attr fork bad nblocks 8 for inode 131, would reset to 3 bad anextents 4 for inode 131, would reset to 0 The problem lies in the assignment of the old/new blocks for tracking purposes when the double leaf split occurs. The first split tries to place the new attribute inside the current leaf (i.e. "inleaf == true") and moves the old attribute (X) to the new block. This sets up the old block/index to L1:X, and newly allocated block to L3:0. It then moves attr X to the new block and tries to insert attr Y at the old index. That fails, so it splits again. With the second split, the rebalance ends up placing the new attr in the second new block - L4:0 - and this is where the code goes wrong. What is does is it sets both the new and old block index to the second new block. Hence it inserts attr Y at the right place (L4:0) but overwrites the current location of the attr to replace that is held in the new block index (currently L3:0). It over writes it with L4:1 - the index we later assert fail on. Hopefully this table will show this in a foramt that is a bit easier to understand: Split old attr index new attr index vanilla patched vanilla patched before 1st L1:26 L1:26 N/A N/A after 1st L3:0 L3:0 L1:26 L1:26 after 2nd L4:0 L3:0 L4:1 L4:0 ^^^^ ^^^^ wrong wrong The fix is surprisingly simple, for all this analysis - just stop the rebalance on the out-of leaf case from overwriting the new attr index - it's already correct for the double split case. Signed-off-by: Dave Chinner Reviewed-by: Mark Tinguely Signed-off-by: Ben Myers --- fs/xfs/xfs_attr_leaf.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index d330111ca73..70eec182977 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -1291,6 +1291,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, leaf2 = blk2->bp->b_addr; ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); + ASSERT(leaf2->hdr.count == 0); args = state->args; trace_xfs_attr_leaf_rebalance(args); @@ -1361,6 +1362,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, * I assert that since all callers pass in an empty * second buffer, this code should never execute. */ + ASSERT(0); /* * Figure the total bytes to be added to the destination leaf. @@ -1422,10 +1424,24 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, args->index2 = 0; args->blkno2 = blk2->blkno; } else { + /* + * On a double leaf split, the original attr location + * is already stored in blkno2/index2, so don't + * overwrite it overwise we corrupt the tree. + */ blk2->index = blk1->index - be16_to_cpu(leaf1->hdr.count); - args->index = args->index2 = blk2->index; - args->blkno = args->blkno2 = blk2->blkno; + args->index = blk2->index; + args->blkno = blk2->blkno; + if (!state->extravalid) { + /* + * set the new attr location to match the old + * one and let the higher level split code + * decide where in the leaf to place it. + */ + args->index2 = blk2->index; + args->blkno2 = blk2->blkno; + } } } else { ASSERT(state->inleaf == 1); -- cgit v1.2.3 From 3daed8bc3e49b9695ae931b9f472b5b90d1965b3 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 12 Nov 2012 22:09:45 +1100 Subject: xfs: fix broken error handling in xfs_vm_writepage When we shut down the filesystem, it might first be detected in writeback when we are allocating a inode size transaction. This happens after we have moved all the pages into the writeback state and unlocked them. Unfortunately, if we fail to set up the transaction we then abort writeback and try to invalidate the current page. This then triggers are BUG() in block_invalidatepage() because we are trying to invalidate an unlocked page. Fixing this is a bit of a chicken and egg problem - we can't allocate the transaction until we've clustered all the pages into the IO and we know the size of it (i.e. whether the last block of the IO is beyond the current EOF or not). However, we don't want to hold pages locked for long periods of time, especially while we lock other pages to cluster them into the write. To fix this, we need to make a clear delineation in writeback where errors can only be handled by IO completion processing. That is, once we have marked a page for writeback and unlocked it, we have to report errors via IO completion because we've already started the IO. We may not have submitted any IO, but we've changed the page state to indicate that it is under IO so we must now use the IO completion path to report errors. To do this, add an error field to xfs_submit_ioend() to pass it the error that occurred during the building on the ioend chain. When this is non-zero, mark each ioend with the error and call xfs_finish_ioend() directly rather than building bios. This will immediately push the ioends through completion processing with the error that has occurred. Signed-off-by: Dave Chinner Reviewed-by: Mark Tinguely Signed-off-by: Ben Myers --- fs/xfs/xfs_aops.c | 54 +++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 39 insertions(+), 15 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index e562dd43f41..e57e2daa357 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -481,11 +481,17 @@ static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh) * * The fix is two passes across the ioend list - one to start writeback on the * buffer_heads, and then submit them for I/O on the second pass. + * + * If @fail is non-zero, it means that we have a situation where some part of + * the submission process has failed after we have marked paged for writeback + * and unlocked them. In this situation, we need to fail the ioend chain rather + * than submit it to IO. This typically only happens on a filesystem shutdown. */ STATIC void xfs_submit_ioend( struct writeback_control *wbc, - xfs_ioend_t *ioend) + xfs_ioend_t *ioend, + int fail) { xfs_ioend_t *head = ioend; xfs_ioend_t *next; @@ -506,6 +512,18 @@ xfs_submit_ioend( next = ioend->io_list; bio = NULL; + /* + * If we are failing the IO now, just mark the ioend with an + * error and finish it. This will run IO completion immediately + * as there is only one reference to the ioend at this point in + * time. + */ + if (fail) { + ioend->io_error = -fail; + xfs_finish_ioend(ioend); + continue; + } + for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) { if (!bio) { @@ -1060,7 +1078,18 @@ xfs_vm_writepage( xfs_start_page_writeback(page, 1, count); - if (ioend && imap_valid) { + /* if there is no IO to be submitted for this page, we are done */ + if (!ioend) + return 0; + + ASSERT(iohead); + + /* + * Any errors from this point onwards need tobe reported through the IO + * completion path as we have marked the initial page as under writeback + * and unlocked it. + */ + if (imap_valid) { xfs_off_t end_index; end_index = imap.br_startoff + imap.br_blockcount; @@ -1079,20 +1108,15 @@ xfs_vm_writepage( wbc, end_index); } - if (iohead) { - /* - * Reserve log space if we might write beyond the on-disk - * inode size. - */ - if (ioend->io_type != XFS_IO_UNWRITTEN && - xfs_ioend_is_append(ioend)) { - err = xfs_setfilesize_trans_alloc(ioend); - if (err) - goto error; - } - xfs_submit_ioend(wbc, iohead); - } + /* + * Reserve log space if we might write beyond the on-disk inode size. + */ + err = 0; + if (ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend)) + err = xfs_setfilesize_trans_alloc(ioend); + + xfs_submit_ioend(wbc, iohead, err); return 0; -- cgit v1.2.3 From d69043c42d8c6414fa28ad18d99973aa6c1c2e24 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 12 Nov 2012 22:09:46 +1100 Subject: xfs: drop buffer io reference when a bad bio is built Error handling in xfs_buf_ioapply_map() does not handle IO reference counts correctly. We increment the b_io_remaining count before building the bio, but then fail to decrement it in the failure case. This leads to the buffer never running IO completion and releasing the reference that the IO holds, so at unmount we can leak the buffer. This leak is captured by this assert failure during unmount: XFS: Assertion failed: atomic_read(&pag->pag_ref) == 0, file: fs/xfs/xfs_mount.c, line: 273 This is not a new bug - the b_io_remaining accounting has had this problem for a long, long time - it's just very hard to get a zero length bio being built by this code... Further, the buffer IO error can be overwritten on a multi-segment buffer by subsequent bio completions for partial sections of the buffer. Hence we should only set the buffer error status if the buffer is not already carrying an error status. This ensures that a partial IO error on a multi-segment buffer will not be lost. This part of the problem is a regression, however. cc: Signed-off-by: Dave Chinner Reviewed-by: Mark Tinguely Signed-off-by: Ben Myers --- fs/xfs/xfs_buf.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 933b7930b86..4b0b8dd1b7b 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1197,9 +1197,14 @@ xfs_buf_bio_end_io( { xfs_buf_t *bp = (xfs_buf_t *)bio->bi_private; - xfs_buf_ioerror(bp, -error); + /* + * don't overwrite existing errors - otherwise we can lose errors on + * buffers that require multiple bios to complete. + */ + if (!bp->b_error) + xfs_buf_ioerror(bp, -error); - if (!error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) + if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); _xfs_buf_ioend(bp, 1); @@ -1279,6 +1284,11 @@ next_chunk: if (size) goto next_chunk; } else { + /* + * This is guaranteed not to be the last io reference count + * because the caller (xfs_buf_iorequest) holds a count itself. + */ + atomic_dec(&bp->b_io_remaining); xfs_buf_ioerror(bp, EIO); bio_put(bio); } -- cgit v1.2.3 From 3587b1b097d70c2eb9fee95ea7995d13c05f66e5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 18 Nov 2012 19:19:00 +0000 Subject: fanotify: fix FAN_Q_OVERFLOW case of fanotify_read() If the FAN_Q_OVERFLOW bit set in event->mask, the fanotify event metadata will not contain a valid file descriptor, but copy_event_to_user() didn't check for that, and unconditionally does a fd_install() on the file descriptor. Which in turn will cause a BUG_ON() in __fd_install(). Introduced by commit 352e3b249284 ("fanotify: sanitize failure exits in copy_event_to_user()") Mea culpa - missed that path ;-/ Reported-by: Alex Shi Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify_user.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 721d692fa8d..6fcaeb8c902 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -258,7 +258,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, if (ret) goto out_close_fd; - fd_install(fd, f); + if (fd != FAN_NOFD) + fd_install(fd, f); return fanotify_event_metadata.event_len; out_close_fd: -- cgit v1.2.3 From 3bb3e1fc47aca554e7e2cc4deeddc24750987ac2 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Nov 2012 14:55:52 +0100 Subject: reiserfs: Fix lock ordering during remount When remounting reiserfs dquot_suspend() or dquot_resume() can be called. These functions take dqonoff_mutex which ranks above write lock so we have to drop it before calling into quota code. CC: stable@vger.kernel.org # >= 3.0 Signed-off-by: Jan Kara --- fs/reiserfs/super.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 1078ae17999..5372980ec45 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1335,7 +1335,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) kfree(qf_names[i]); #endif err = -EINVAL; - goto out_err; + goto out_unlock; } #ifdef CONFIG_QUOTA handle_quota_files(s, qf_names, &qfmt); @@ -1379,7 +1379,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) if (blocks) { err = reiserfs_resize(s, blocks); if (err != 0) - goto out_err; + goto out_unlock; } if (*mount_flags & MS_RDONLY) { @@ -1389,9 +1389,15 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) /* it is read-only already */ goto out_ok; + /* + * Drop write lock. Quota will retake it when needed and lock + * ordering requires calling dquot_suspend() without it. + */ + reiserfs_write_unlock(s); err = dquot_suspend(s, -1); if (err < 0) goto out_err; + reiserfs_write_lock(s); /* try to remount file system with read-only permissions */ if (sb_umount_state(rs) == REISERFS_VALID_FS @@ -1401,7 +1407,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) err = journal_begin(&th, s, 10); if (err) - goto out_err; + goto out_unlock; /* Mounting a rw partition read-only. */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); @@ -1416,7 +1422,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) if (reiserfs_is_journal_aborted(journal)) { err = journal->j_errno; - goto out_err; + goto out_unlock; } handle_data_mode(s, mount_options); @@ -1425,7 +1431,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) s->s_flags &= ~MS_RDONLY; /* now it is safe to call journal_begin */ err = journal_begin(&th, s, 10); if (err) - goto out_err; + goto out_unlock; /* Mount a partition which is read-only, read-write */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); @@ -1442,10 +1448,16 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) SB_JOURNAL(s)->j_must_wait = 1; err = journal_end(&th, s, 10); if (err) - goto out_err; + goto out_unlock; if (!(*mount_flags & MS_RDONLY)) { + /* + * Drop write lock. Quota will retake it when needed and lock + * ordering requires calling dquot_resume() without it. + */ + reiserfs_write_unlock(s); dquot_resume(s, -1); + reiserfs_write_lock(s); finish_unfinished(s); reiserfs_xattr_init(s, *mount_flags); } @@ -1455,9 +1467,10 @@ out_ok: reiserfs_write_unlock(s); return 0; +out_unlock: + reiserfs_write_unlock(s); out_err: kfree(new_opts); - reiserfs_write_unlock(s); return err; } -- cgit v1.2.3 From b9e06ef2e8706fe669b51f4364e3aeed58639eb2 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Nov 2012 16:34:17 +0100 Subject: reiserfs: Protect reiserfs_quota_on() with write lock In reiserfs_quota_on() we do quite some work - for example unpacking tail of a quota file. Thus we have to hold write lock until a moment we call back into the quota code. CC: stable@vger.kernel.org # >= 3.0 Signed-off-by: Jan Kara --- fs/reiserfs/super.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 5372980ec45..e59d6ddcc69 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -2216,8 +2216,11 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, struct reiserfs_transaction_handle th; int opt = type == USRQUOTA ? REISERFS_USRQUOTA : REISERFS_GRPQUOTA; - if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt))) - return -EINVAL; + reiserfs_write_lock(sb); + if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt))) { + err = -EINVAL; + goto out; + } /* Quotafile not on the same filesystem? */ if (path->dentry->d_sb != sb) { @@ -2259,8 +2262,10 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, if (err) goto out; } - err = dquot_quota_on(sb, type, format_id, path); + reiserfs_write_unlock(sb); + return dquot_quota_on(sb, type, format_id, path); out: + reiserfs_write_unlock(sb); return err; } -- cgit v1.2.3 From 361d94a338a3fd0cee6a4ea32bbc427ba228e628 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Nov 2012 18:25:38 +0100 Subject: reiserfs: Protect reiserfs_quota_write() with write lock Calls into reiserfs journalling code and reiserfs_get_block() need to be protected with write lock. We remove write lock around calls to high level quota code in the next patch so these paths would suddently become unprotected. CC: stable@vger.kernel.org # >= 3.0 Signed-off-by: Jan Kara --- fs/reiserfs/super.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs') diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index e59d6ddcc69..c101704ece4 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -2338,7 +2338,9 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type, tocopy = sb->s_blocksize - offset < towrite ? sb->s_blocksize - offset : towrite; tmp_bh.b_state = 0; + reiserfs_write_lock(sb); err = reiserfs_get_block(inode, blk, &tmp_bh, GET_BLOCK_CREATE); + reiserfs_write_unlock(sb); if (err) goto out; if (offset || tocopy != sb->s_blocksize) @@ -2354,10 +2356,12 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type, flush_dcache_page(bh->b_page); set_buffer_uptodate(bh); unlock_buffer(bh); + reiserfs_write_lock(sb); reiserfs_prepare_for_journal(sb, bh, 1); journal_mark_dirty(current->journal_info, sb, bh); if (!journal_quota) reiserfs_add_ordered_list(inode, bh); + reiserfs_write_unlock(sb); brelse(bh); offset = 0; towrite -= tocopy; -- cgit v1.2.3 From 7af11686933726e99af22901d622f9e161404e6b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Nov 2012 17:05:14 +0100 Subject: reiserfs: Move quota calls out of write lock Calls into highlevel quota code cannot happen under the write lock. These calls take dqio_mutex which ranks above write lock. So drop write lock before calling back into quota code. CC: stable@vger.kernel.org # >= 3.0 Signed-off-by: Jan Kara --- fs/reiserfs/inode.c | 10 +++++++--- fs/reiserfs/stree.c | 4 ++++ fs/reiserfs/super.c | 18 ++++++++++++++---- 3 files changed, 25 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index f27f01a98aa..d83736fbc26 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1782,8 +1782,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, BUG_ON(!th->t_trans_id); - dquot_initialize(inode); + reiserfs_write_unlock(inode->i_sb); err = dquot_alloc_inode(inode); + reiserfs_write_lock(inode->i_sb); if (err) goto out_end_trans; if (!dir->i_nlink) { @@ -1979,8 +1980,10 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, out_end_trans: journal_end(th, th->t_super, th->t_blocks_allocated); + reiserfs_write_unlock(inode->i_sb); /* Drop can be outside and it needs more credits so it's better to have it outside */ dquot_drop(inode); + reiserfs_write_lock(inode->i_sb); inode->i_flags |= S_NOQUOTA; make_bad_inode(inode); @@ -3103,10 +3106,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) /* must be turned off for recursive notify_change calls */ ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID); - depth = reiserfs_write_lock_once(inode->i_sb); if (is_quota_modification(inode, attr)) dquot_initialize(inode); - + depth = reiserfs_write_lock_once(inode->i_sb); if (attr->ia_valid & ATTR_SIZE) { /* version 2 items will be caught by the s_maxbytes check ** done for us in vmtruncate @@ -3170,7 +3172,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) error = journal_begin(&th, inode->i_sb, jbegin_count); if (error) goto out; + reiserfs_write_unlock_once(inode->i_sb, depth); error = dquot_transfer(inode, attr); + depth = reiserfs_write_lock_once(inode->i_sb); if (error) { journal_end(&th, inode->i_sb, jbegin_count); goto out; diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index f8afa4b162b..2f40a4c70a4 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -1968,7 +1968,9 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree key2type(&(key->on_disk_key))); #endif + reiserfs_write_unlock(inode->i_sb); retval = dquot_alloc_space_nodirty(inode, pasted_size); + reiserfs_write_lock(inode->i_sb); if (retval) { pathrelse(search_path); return retval; @@ -2061,9 +2063,11 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th, "reiserquota insert_item(): allocating %u id=%u type=%c", quota_bytes, inode->i_uid, head2type(ih)); #endif + reiserfs_write_unlock(inode->i_sb); /* We can't dirty inode here. It would be immediately written but * appropriate stat item isn't inserted yet... */ retval = dquot_alloc_space_nodirty(inode, quota_bytes); + reiserfs_write_lock(inode->i_sb); if (retval) { pathrelse(path); return retval; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index c101704ece4..418bdc3a57d 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -298,7 +298,9 @@ static int finish_unfinished(struct super_block *s) retval = remove_save_link_only(s, &save_link_key, 0); continue; } + reiserfs_write_unlock(s); dquot_initialize(inode); + reiserfs_write_lock(s); if (truncate && S_ISDIR(inode->i_mode)) { /* We got a truncate request for a dir which is impossible. @@ -2108,13 +2110,15 @@ static int reiserfs_write_dquot(struct dquot *dquot) REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (ret) goto out; + reiserfs_write_unlock(dquot->dq_sb); ret = dquot_commit(dquot); + reiserfs_write_lock(dquot->dq_sb); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (!ret && err) ret = err; - out: +out: reiserfs_write_unlock(dquot->dq_sb); return ret; } @@ -2130,13 +2134,15 @@ static int reiserfs_acquire_dquot(struct dquot *dquot) REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (ret) goto out; + reiserfs_write_unlock(dquot->dq_sb); ret = dquot_acquire(dquot); + reiserfs_write_lock(dquot->dq_sb); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (!ret && err) ret = err; - out: +out: reiserfs_write_unlock(dquot->dq_sb); return ret; } @@ -2150,19 +2156,21 @@ static int reiserfs_release_dquot(struct dquot *dquot) ret = journal_begin(&th, dquot->dq_sb, REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb)); + reiserfs_write_unlock(dquot->dq_sb); if (ret) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); goto out; } ret = dquot_release(dquot); + reiserfs_write_lock(dquot->dq_sb); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (!ret && err) ret = err; - out: reiserfs_write_unlock(dquot->dq_sb); +out: return ret; } @@ -2187,11 +2195,13 @@ static int reiserfs_write_info(struct super_block *sb, int type) ret = journal_begin(&th, sb, 2); if (ret) goto out; + reiserfs_write_unlock(sb); ret = dquot_commit_info(sb, type); + reiserfs_write_lock(sb); err = journal_end(&th, sb, 2); if (!ret && err) ret = err; - out: +out: reiserfs_write_unlock(sb); return ret; } -- cgit v1.2.3 From ae49eeec785025373e28dc24c8351c6bba688d99 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Thu, 11 Oct 2012 12:28:38 +0200 Subject: ext3: Avoid underflow of in ext3_trim_fs() Currently if len argument in ext3_trim_fs() is smaller than one block, the 'end' variable underflow. Avoid that by returning EINVAL if len is smaller than file system block. Also remove useless unlikely(). Signed-off-by: Lukas Czerner Signed-off-by: Jan Kara --- fs/ext3/balloc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index 7320a66e958..22548f56197 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -2101,8 +2101,9 @@ int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range) end = start + (range->len >> sb->s_blocksize_bits) - 1; minlen = range->minlen >> sb->s_blocksize_bits; - if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)) || - unlikely(start >= max_blks)) + if (minlen > EXT3_BLOCKS_PER_GROUP(sb) || + start >= max_blks || + range->len < sb->s_blocksize) return -EINVAL; if (end >= max_blks) end = max_blks - 1; -- cgit v1.2.3