From 20f504e43df28604711bf5679ab592395eb1cb0c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 14 Dec 2009 09:49:53 -0800 Subject: [PATCH] actually remove the queue for .32, oops... --- ...al-buffer-head-leak-when-add_dirent_.patch | 122 - ...e-by-zero-when-trying-to-mount-a-cor.patch | 43 - ...urned-block-count-if-EXT4_IOC_MOVE_E.patch | 353 -- ...k-order-problem-in-ext4_move_extents.patch | 314 -- ...e-recursive-locking-warning-in-EXT4_.patch | 36 - ...er_head-leak-in-an-error-path-of-ext.patch | 86 - ...irectory-and-symlink-blocks-are-revo.patch | 62 - ...-access-in-ext4_da_writepages_trans_.patch | 29 - ...-modifications-in-ext4_xattr_set_han.patch | 43 - ...update-the-superblock-in-ext4_statfs.patch | 35 - ...block-bitmap-initialization-when-s_m.patch | 33 - ...alidity-checks-so-they-work-correctl.patch | 43 - ...4-avoid-issuing-unnecessary-barriers.patch | 41 - ...rror-handling-in-ext4_ind_get_blocks.patch | 29 - ...-discard-optional-and-off-by-default.patch | 128 - ...-make-norecovery-an-alias-for-noload.patch | 57 - ...free-of-blocks-with-EXT4_IOC_MOVE_EX.patch | 79 - ...moved_len-before-calling-ext4_move_e.patch | 76 - ...19-ext4-move_extent_per_page-cleanup.patch | 91 - ...checking-in-and-for-jbd2_journal_wri.patch | 42 - ...PTR_ERR-of-the-correct-pointer-in-se.patch | 25 - ...filesystem-corruption-when-write-fai.patch | 88 - ...ait-for-log-to-commit-when-umounting.patch | 50 - ...ks-from-inode-prealloc-list-on-failu.patch | 53 - ...served_space-must-return-bytes-inste.patch | 27 - .../0026-ext4-quota-macros-cleanup.patch | 142 - ...ct-block-reservation-on-quota-transf.patch | 31 - ...r-proper-transaction-commit-on-fsync.patch | 256 -- ...fficient-checks-in-EXT4_IOC_MOVE_EXT.patch | 98 - ...al-fiemap-deadlock-mmap_sem-vs.-i_da.patch | 119 - queue-2.6.32/mbox | 3730 ----------------- ...-fix-64-bit-sense-pointer-truncation.patch | 51 - ...i-osd_protocol.h-add-missing-include.patch | 28 - ...with-dma-maps-on-nested-scsi-objects.patch | 153 - queue-2.6.32/series | 34 - ...nal-fix-alternate-signal-stack-check.patch | 87 - 36 files changed, 6714 deletions(-) delete mode 100644 queue-2.6.32/0001-ext4-fix-potential-buffer-head-leak-when-add_dirent_.patch delete mode 100644 queue-2.6.32/0002-ext4-avoid-divide-by-zero-when-trying-to-mount-a-cor.patch delete mode 100644 queue-2.6.32/0003-ext4-fix-the-returned-block-count-if-EXT4_IOC_MOVE_E.patch delete mode 100644 queue-2.6.32/0004-ext4-fix-lock-order-problem-in-ext4_move_extents.patch delete mode 100644 queue-2.6.32/0005-ext4-fix-possible-recursive-locking-warning-in-EXT4_.patch delete mode 100644 queue-2.6.32/0006-ext4-plug-a-buffer_head-leak-in-an-error-path-of-ext.patch delete mode 100644 queue-2.6.32/0007-ext4-make-sure-directory-and-symlink-blocks-are-revo.patch delete mode 100644 queue-2.6.32/0008-ext4-fix-i_flags-access-in-ext4_da_writepages_trans_.patch delete mode 100644 queue-2.6.32/0009-ext4-journal-all-modifications-in-ext4_xattr_set_han.patch delete mode 100644 queue-2.6.32/0010-ext4-don-t-update-the-superblock-in-ext4_statfs.patch delete mode 100644 queue-2.6.32/0011-ext4-fix-uninit-block-bitmap-initialization-when-s_m.patch delete mode 100644 queue-2.6.32/0012-ext4-fix-block-validity-checks-so-they-work-correctl.patch delete mode 100644 queue-2.6.32/0013-ext4-avoid-issuing-unnecessary-barriers.patch delete mode 100644 queue-2.6.32/0014-ext4-fix-error-handling-in-ext4_ind_get_blocks.patch delete mode 100644 queue-2.6.32/0015-ext4-make-trim-discard-optional-and-off-by-default.patch delete mode 100644 queue-2.6.32/0016-ext4-make-norecovery-an-alias-for-noload.patch delete mode 100644 queue-2.6.32/0017-ext4-Fix-double-free-of-blocks-with-EXT4_IOC_MOVE_EX.patch delete mode 100644 queue-2.6.32/0018-ext4-initialize-moved_len-before-calling-ext4_move_e.patch delete mode 100644 queue-2.6.32/0019-ext4-move_extent_per_page-cleanup.patch delete mode 100644 queue-2.6.32/0020-jbd2-Add-ENOMEM-checking-in-and-for-jbd2_journal_wri.patch delete mode 100644 queue-2.6.32/0021-ext4-Return-the-PTR_ERR-of-the-correct-pointer-in-se.patch delete mode 100644 queue-2.6.32/0022-ext4-Avoid-data-filesystem-corruption-when-write-fai.patch delete mode 100644 queue-2.6.32/0023-ext4-wait-for-log-to-commit-when-umounting.patch delete mode 100644 queue-2.6.32/0024-ext4-remove-blocks-from-inode-prealloc-list-on-failu.patch delete mode 100644 queue-2.6.32/0025-ext4-ext4_get_reserved_space-must-return-bytes-inste.patch delete mode 100644 queue-2.6.32/0026-ext4-quota-macros-cleanup.patch delete mode 100644 queue-2.6.32/0027-ext4-fix-incorrect-block-reservation-on-quota-transf.patch delete mode 100644 queue-2.6.32/0028-ext4-Wait-for-proper-transaction-commit-on-fsync.patch delete mode 100644 queue-2.6.32/0029-ext4-Fix-insufficient-checks-in-EXT4_IOC_MOVE_EXT.patch delete mode 100644 queue-2.6.32/0030-ext4-Fix-potential-fiemap-deadlock-mmap_sem-vs.-i_da.patch delete mode 100644 queue-2.6.32/mbox delete mode 100644 queue-2.6.32/scsi-megaraid_sas-fix-64-bit-sense-pointer-truncation.patch delete mode 100644 queue-2.6.32/scsi-osd_protocol.h-add-missing-include.patch delete mode 100644 queue-2.6.32/scsi-scsi_lib_dma-fix-bug-with-dma-maps-on-nested-scsi-objects.patch delete mode 100644 queue-2.6.32/series delete mode 100644 queue-2.6.32/signal-fix-alternate-signal-stack-check.patch diff --git a/queue-2.6.32/0001-ext4-fix-potential-buffer-head-leak-when-add_dirent_.patch b/queue-2.6.32/0001-ext4-fix-potential-buffer-head-leak-when-add_dirent_.patch deleted file mode 100644 index 291e49c84b9..00000000000 --- a/queue-2.6.32/0001-ext4-fix-potential-buffer-head-leak-when-add_dirent_.patch +++ /dev/null @@ -1,122 +0,0 @@ -From 4df5b14f4bea734ff3d9c721eb331540ad142de3 Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Mon, 23 Nov 2009 07:25:49 -0500 -Subject: [PATCH 01/30] ext4: fix potential buffer head leak when add_dirent_to_buf() returns ENOSPC - -(cherry picked from commit 2de770a406b06dfc619faabbf5d85c835ed3f2e1) - -Previously add_dirent_to_buf() did not free its passed-in buffer head -in the case of ENOSPC, since in some cases the caller still needed it. -However, this led to potential buffer head leaks since not all callers -dealt with this correctly. Fix this by making simplifying the freeing -convention; now add_dirent_to_buf() *never* frees the passed-in buffer -head, and leaves that to the responsibility of its caller. This makes -things cleaner and easier to prove that the code is neither leaking -buffer heads or calling brelse() one time too many. - -Signed-off-by: "Theodore Ts'o" -Cc: Curt Wohlgemuth -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/namei.c | 30 ++++++++++++------------------ - 1 file changed, 12 insertions(+), 18 deletions(-) - ---- a/fs/ext4/namei.c -+++ b/fs/ext4/namei.c -@@ -1292,9 +1292,6 @@ errout: - * add_dirent_to_buf will attempt search the directory block for - * space. It will return -ENOSPC if no space is available, and -EIO - * and -EEXIST if directory entry already exists. -- * -- * NOTE! bh is NOT released in the case where ENOSPC is returned. In -- * all other cases bh is released. - */ - static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, - struct inode *inode, struct ext4_dir_entry_2 *de, -@@ -1315,14 +1312,10 @@ static int add_dirent_to_buf(handle_t *h - top = bh->b_data + blocksize - reclen; - while ((char *) de <= top) { - if (!ext4_check_dir_entry("ext4_add_entry", dir, de, -- bh, offset)) { -- brelse(bh); -+ bh, offset)) - return -EIO; -- } -- if (ext4_match(namelen, name, de)) { -- brelse(bh); -+ if (ext4_match(namelen, name, de)) - return -EEXIST; -- } - nlen = EXT4_DIR_REC_LEN(de->name_len); - rlen = ext4_rec_len_from_disk(de->rec_len, blocksize); - if ((de->inode? rlen - nlen: rlen) >= reclen) -@@ -1337,7 +1330,6 @@ static int add_dirent_to_buf(handle_t *h - err = ext4_journal_get_write_access(handle, bh); - if (err) { - ext4_std_error(dir->i_sb, err); -- brelse(bh); - return err; - } - -@@ -1377,7 +1369,6 @@ static int add_dirent_to_buf(handle_t *h - err = ext4_handle_dirty_metadata(handle, dir, bh); - if (err) - ext4_std_error(dir->i_sb, err); -- brelse(bh); - return 0; - } - -@@ -1471,7 +1462,9 @@ static int make_indexed_dir(handle_t *ha - if (!(de)) - return retval; - -- return add_dirent_to_buf(handle, dentry, inode, de, bh); -+ retval = add_dirent_to_buf(handle, dentry, inode, de, bh); -+ brelse(bh); -+ return retval; - } - - /* -@@ -1514,8 +1507,10 @@ static int ext4_add_entry(handle_t *hand - if(!bh) - return retval; - retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh); -- if (retval != -ENOSPC) -+ if (retval != -ENOSPC) { -+ brelse(bh); - return retval; -+ } - - if (blocks == 1 && !dx_fallback && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) -@@ -1528,7 +1523,9 @@ static int ext4_add_entry(handle_t *hand - de = (struct ext4_dir_entry_2 *) bh->b_data; - de->inode = 0; - de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize); -- return add_dirent_to_buf(handle, dentry, inode, de, bh); -+ retval = add_dirent_to_buf(handle, dentry, inode, de, bh); -+ brelse(bh); -+ return retval; - } - - /* -@@ -1561,10 +1558,8 @@ static int ext4_dx_add_entry(handle_t *h - goto journal_error; - - err = add_dirent_to_buf(handle, dentry, inode, NULL, bh); -- if (err != -ENOSPC) { -- bh = NULL; -+ if (err != -ENOSPC) - goto cleanup; -- } - - /* Block full, should compress but for now just split */ - dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n", -@@ -1657,7 +1652,6 @@ static int ext4_dx_add_entry(handle_t *h - if (!de) - goto cleanup; - err = add_dirent_to_buf(handle, dentry, inode, de, bh); -- bh = NULL; - goto cleanup; - - journal_error: diff --git a/queue-2.6.32/0002-ext4-avoid-divide-by-zero-when-trying-to-mount-a-cor.patch b/queue-2.6.32/0002-ext4-avoid-divide-by-zero-when-trying-to-mount-a-cor.patch deleted file mode 100644 index 9a611a6c247..00000000000 --- a/queue-2.6.32/0002-ext4-avoid-divide-by-zero-when-trying-to-mount-a-cor.patch +++ /dev/null @@ -1,43 +0,0 @@ -From 833f693f0cf8059bcda7ddff3434473b2a5d4d69 Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Mon, 23 Nov 2009 07:24:46 -0500 -Subject: [PATCH 02/30] ext4: avoid divide by zero when trying to mount a corrupted file system - -(cherry picked from commit 503358ae01b70ce6909d19dd01287093f6b6271c) - -If s_log_groups_per_flex is greater than 31, then groups_per_flex will -will overflow and cause a divide by zero error. This can cause kernel -BUG if such a file system is mounted. - -Thanks to Nageswara R Sastry for analyzing the failure and providing -an initial patch. - -http://bugzilla.kernel.org/show_bug.cgi?id=14287 - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/super.c | 8 ++++---- - 1 file changed, 4 insertions(+), 4 deletions(-) - ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -1673,14 +1673,14 @@ static int ext4_fill_flex_info(struct su - size_t size; - int i; - -- if (!sbi->s_es->s_log_groups_per_flex) { -+ sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; -+ groups_per_flex = 1 << sbi->s_log_groups_per_flex; -+ -+ if (groups_per_flex < 2) { - sbi->s_log_groups_per_flex = 0; - return 1; - } - -- sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; -- groups_per_flex = 1 << sbi->s_log_groups_per_flex; -- - /* We allocate both existing and potentially added groups */ - flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) + - ((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) << diff --git a/queue-2.6.32/0003-ext4-fix-the-returned-block-count-if-EXT4_IOC_MOVE_E.patch b/queue-2.6.32/0003-ext4-fix-the-returned-block-count-if-EXT4_IOC_MOVE_E.patch deleted file mode 100644 index 610a2a3cfda..00000000000 --- a/queue-2.6.32/0003-ext4-fix-the-returned-block-count-if-EXT4_IOC_MOVE_E.patch +++ /dev/null @@ -1,353 +0,0 @@ -From 30a07c3105210d4d88e1ddb80fdd11a98ad2b281 Mon Sep 17 00:00:00 2001 -From: Akira Fujita -Date: Mon, 23 Nov 2009 07:25:48 -0500 -Subject: [PATCH 03/30] ext4: fix the returned block count if EXT4_IOC_MOVE_EXT fails - -(cherry picked from commit f868a48d06f8886cb0367568a12367fa4f21ea0d) - -If the EXT4_IOC_MOVE_EXT ioctl fails, the number of blocks that were -exchanged before the failure should be returned to the userspace -caller. Unfortunately, currently if the block size is not the same as -the page size, the returned block count that is returned is the -page-aligned block count instead of the actual block count. This -commit addresses this bug. - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 139 ++++++++++++++++++++++++++------------------------ - 1 file changed, 73 insertions(+), 66 deletions(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -661,6 +661,7 @@ mext_calc_swap_extents(struct ext4_exten - * @donor_inode: donor inode - * @from: block offset of orig_inode - * @count: block count to be replaced -+ * @err: pointer to save return value - * - * Replace original inode extents and donor inode extents page by page. - * We implement this replacement in the following three steps: -@@ -671,19 +672,18 @@ mext_calc_swap_extents(struct ext4_exten - * 3. Change the block information of donor inode to point at the saved - * original inode blocks in the dummy extents. - * -- * Return 0 on success, or a negative error value on failure. -+ * Return replaced block count. - */ - static int - mext_replace_branches(handle_t *handle, struct inode *orig_inode, - struct inode *donor_inode, ext4_lblk_t from, -- ext4_lblk_t count) -+ ext4_lblk_t count, int *err) - { - struct ext4_ext_path *orig_path = NULL; - struct ext4_ext_path *donor_path = NULL; - struct ext4_extent *oext, *dext; - struct ext4_extent tmp_dext, tmp_oext; - ext4_lblk_t orig_off = from, donor_off = from; -- int err = 0; - int depth; - int replaced_count = 0; - int dext_alen; -@@ -691,13 +691,13 @@ mext_replace_branches(handle_t *handle, - mext_double_down_write(orig_inode, donor_inode); - - /* Get the original extent for the block "orig_off" */ -- err = get_ext_path(orig_inode, orig_off, &orig_path); -- if (err) -+ *err = get_ext_path(orig_inode, orig_off, &orig_path); -+ if (*err) - goto out; - - /* Get the donor extent for the head */ -- err = get_ext_path(donor_inode, donor_off, &donor_path); -- if (err) -+ *err = get_ext_path(donor_inode, donor_off, &donor_path); -+ if (*err) - goto out; - depth = ext_depth(orig_inode); - oext = orig_path[depth].p_ext; -@@ -707,9 +707,9 @@ mext_replace_branches(handle_t *handle, - dext = donor_path[depth].p_ext; - tmp_dext = *dext; - -- err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, -+ *err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, - donor_off, count); -- if (err) -+ if (*err) - goto out; - - /* Loop for the donor extents */ -@@ -718,7 +718,7 @@ mext_replace_branches(handle_t *handle, - if (!dext) { - ext4_error(donor_inode->i_sb, __func__, - "The extent for donor must be found"); -- err = -EIO; -+ *err = -EIO; - goto out; - } else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) { - ext4_error(donor_inode->i_sb, __func__, -@@ -726,20 +726,20 @@ mext_replace_branches(handle_t *handle, - "extent(%u) should be equal", - donor_off, - le32_to_cpu(tmp_dext.ee_block)); -- err = -EIO; -+ *err = -EIO; - goto out; - } - - /* Set donor extent to orig extent */ -- err = mext_leaf_block(handle, orig_inode, -+ *err = mext_leaf_block(handle, orig_inode, - orig_path, &tmp_dext, &orig_off); -- if (err < 0) -+ if (*err) - goto out; - - /* Set orig extent to donor extent */ -- err = mext_leaf_block(handle, donor_inode, -+ *err = mext_leaf_block(handle, donor_inode, - donor_path, &tmp_oext, &donor_off); -- if (err < 0) -+ if (*err) - goto out; - - dext_alen = ext4_ext_get_actual_len(&tmp_dext); -@@ -753,35 +753,25 @@ mext_replace_branches(handle_t *handle, - - if (orig_path) - ext4_ext_drop_refs(orig_path); -- err = get_ext_path(orig_inode, orig_off, &orig_path); -- if (err) -+ *err = get_ext_path(orig_inode, orig_off, &orig_path); -+ if (*err) - goto out; - depth = ext_depth(orig_inode); - oext = orig_path[depth].p_ext; -- if (le32_to_cpu(oext->ee_block) + -- ext4_ext_get_actual_len(oext) <= orig_off) { -- err = 0; -- goto out; -- } - tmp_oext = *oext; - - if (donor_path) - ext4_ext_drop_refs(donor_path); -- err = get_ext_path(donor_inode, donor_off, &donor_path); -- if (err) -+ *err = get_ext_path(donor_inode, donor_off, &donor_path); -+ if (*err) - goto out; - depth = ext_depth(donor_inode); - dext = donor_path[depth].p_ext; -- if (le32_to_cpu(dext->ee_block) + -- ext4_ext_get_actual_len(dext) <= donor_off) { -- err = 0; -- goto out; -- } - tmp_dext = *dext; - -- err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, -+ *err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, - donor_off, count - replaced_count); -- if (err) -+ if (*err) - goto out; - } - -@@ -796,7 +786,7 @@ out: - } - - mext_double_up_write(orig_inode, donor_inode); -- return err; -+ return replaced_count; - } - - /** -@@ -808,16 +798,17 @@ out: - * @data_offset_in_page: block index where data swapping starts - * @block_len_in_page: the number of blocks to be swapped - * @uninit: orig extent is uninitialized or not -+ * @err: pointer to save return value - * - * Save the data in original inode blocks and replace original inode extents - * with donor inode extents by calling mext_replace_branches(). -- * Finally, write out the saved data in new original inode blocks. Return 0 -- * on success, or a negative error value on failure. -+ * Finally, write out the saved data in new original inode blocks. Return -+ * replaced block count. - */ - static int - move_extent_per_page(struct file *o_filp, struct inode *donor_inode, - pgoff_t orig_page_offset, int data_offset_in_page, -- int block_len_in_page, int uninit) -+ int block_len_in_page, int uninit, int *err) - { - struct inode *orig_inode = o_filp->f_dentry->d_inode; - struct address_space *mapping = orig_inode->i_mapping; -@@ -829,9 +820,11 @@ move_extent_per_page(struct file *o_filp - long long offs = orig_page_offset << PAGE_CACHE_SHIFT; - unsigned long blocksize = orig_inode->i_sb->s_blocksize; - unsigned int w_flags = 0; -- unsigned int tmp_data_len, data_len; -+ unsigned int tmp_data_size, data_size, replaced_size; - void *fsdata; -- int ret, i, jblocks; -+ int i, jblocks; -+ int err2 = 0; -+ int replaced_count = 0; - int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; - - /* -@@ -841,8 +834,8 @@ move_extent_per_page(struct file *o_filp - jblocks = ext4_writepage_trans_blocks(orig_inode) * 2; - handle = ext4_journal_start(orig_inode, jblocks); - if (IS_ERR(handle)) { -- ret = PTR_ERR(handle); -- return ret; -+ *err = PTR_ERR(handle); -+ return 0; - } - - if (segment_eq(get_fs(), KERNEL_DS)) -@@ -858,9 +851,9 @@ move_extent_per_page(struct file *o_filp - * Just swap data blocks between orig and donor. - */ - if (uninit) { -- ret = mext_replace_branches(handle, orig_inode, -- donor_inode, orig_blk_offset, -- block_len_in_page); -+ replaced_count = mext_replace_branches(handle, orig_inode, -+ donor_inode, orig_blk_offset, -+ block_len_in_page, err); - - /* Clear the inode cache not to refer to the old data */ - ext4_ext_invalidate_cache(orig_inode); -@@ -870,27 +863,28 @@ move_extent_per_page(struct file *o_filp - - offs = (long long)orig_blk_offset << orig_inode->i_blkbits; - -- /* Calculate data_len */ -+ /* Calculate data_size */ - if ((orig_blk_offset + block_len_in_page - 1) == - ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) { - /* Replace the last block */ -- tmp_data_len = orig_inode->i_size & (blocksize - 1); -+ tmp_data_size = orig_inode->i_size & (blocksize - 1); - /* -- * If data_len equal zero, it shows data_len is multiples of -+ * If data_size equal zero, it shows data_size is multiples of - * blocksize. So we set appropriate value. - */ -- if (tmp_data_len == 0) -- tmp_data_len = blocksize; -+ if (tmp_data_size == 0) -+ tmp_data_size = blocksize; - -- data_len = tmp_data_len + -+ data_size = tmp_data_size + - ((block_len_in_page - 1) << orig_inode->i_blkbits); -- } else { -- data_len = block_len_in_page << orig_inode->i_blkbits; -- } -+ } else -+ data_size = block_len_in_page << orig_inode->i_blkbits; -+ -+ replaced_size = data_size; - -- ret = a_ops->write_begin(o_filp, mapping, offs, data_len, w_flags, -+ *err = a_ops->write_begin(o_filp, mapping, offs, data_size, w_flags, - &page, &fsdata); -- if (unlikely(ret < 0)) -+ if (unlikely(*err < 0)) - goto out; - - if (!PageUptodate(page)) { -@@ -911,10 +905,17 @@ move_extent_per_page(struct file *o_filp - /* Release old bh and drop refs */ - try_to_release_page(page, 0); - -- ret = mext_replace_branches(handle, orig_inode, donor_inode, -- orig_blk_offset, block_len_in_page); -- if (ret < 0) -- goto out; -+ replaced_count = mext_replace_branches(handle, orig_inode, donor_inode, -+ orig_blk_offset, block_len_in_page, -+ &err2); -+ if (err2) { -+ if (replaced_count) { -+ block_len_in_page = replaced_count; -+ replaced_size = -+ block_len_in_page << orig_inode->i_blkbits; -+ } else -+ goto out; -+ } - - /* Clear the inode cache not to refer to the old data */ - ext4_ext_invalidate_cache(orig_inode); -@@ -928,16 +929,16 @@ move_extent_per_page(struct file *o_filp - bh = bh->b_this_page; - - for (i = 0; i < block_len_in_page; i++) { -- ret = ext4_get_block(orig_inode, -+ *err = ext4_get_block(orig_inode, - (sector_t)(orig_blk_offset + i), bh, 0); -- if (ret < 0) -+ if (*err < 0) - goto out; - - if (bh->b_this_page != NULL) - bh = bh->b_this_page; - } - -- ret = a_ops->write_end(o_filp, mapping, offs, data_len, data_len, -+ *err = a_ops->write_end(o_filp, mapping, offs, data_size, replaced_size, - page, fsdata); - page = NULL; - -@@ -951,7 +952,10 @@ out: - out2: - ext4_journal_stop(handle); - -- return ret < 0 ? ret : 0; -+ if (err2) -+ *err = err2; -+ -+ return replaced_count; - } - - /** -@@ -1367,15 +1371,17 @@ ext4_move_extents(struct file *o_filp, s - while (orig_page_offset <= seq_end_page) { - - /* Swap original branches with new branches */ -- ret1 = move_extent_per_page(o_filp, donor_inode, -+ block_len_in_page = move_extent_per_page( -+ o_filp, donor_inode, - orig_page_offset, - data_offset_in_page, -- block_len_in_page, uninit); -- if (ret1 < 0) -- goto out; -- orig_page_offset++; -+ block_len_in_page, uninit, -+ &ret1); -+ - /* Count how many blocks we have exchanged */ - *moved_len += block_len_in_page; -+ if (ret1 < 0) -+ goto out; - if (*moved_len > len) { - ext4_error(orig_inode->i_sb, __func__, - "We replaced blocks too much! " -@@ -1385,6 +1391,7 @@ ext4_move_extents(struct file *o_filp, s - goto out; - } - -+ orig_page_offset++; - data_offset_in_page = 0; - rest_blocks -= block_len_in_page; - if (rest_blocks > blocks_per_page) diff --git a/queue-2.6.32/0004-ext4-fix-lock-order-problem-in-ext4_move_extents.patch b/queue-2.6.32/0004-ext4-fix-lock-order-problem-in-ext4_move_extents.patch deleted file mode 100644 index 6573b743153..00000000000 --- a/queue-2.6.32/0004-ext4-fix-lock-order-problem-in-ext4_move_extents.patch +++ /dev/null @@ -1,314 +0,0 @@ -From 28e1746b954e72a90c00fec39fa3e131e2a3d640 Mon Sep 17 00:00:00 2001 -From: Akira Fujita -Date: Mon, 23 Nov 2009 07:24:43 -0500 -Subject: [PATCH 04/30] ext4: fix lock order problem in ext4_move_extents() - -(cherry picked from commit fc04cb49a898c372a22b21fffc47f299d8710801) - -ext4_move_extents() checks the logical block contiguousness -of original file with ext4_find_extent() and mext_next_extent(). -Therefore the extent which ext4_ext_path structure indicates -must not be changed between above functions. - -But in current implementation, there is no i_data_sem protection -between ext4_ext_find_extent() and mext_next_extent(). So the extent -which ext4_ext_path structure indicates may be overwritten by -delalloc. As a result, ext4_move_extents() will exchange wrong blocks -between original and donor files. I change the place where -acquire/release i_data_sem to solve this problem. - -Moreover, I changed move_extent_per_page() to start transaction first, -and then acquire i_data_sem. Without this change, there is a -possibility of the deadlock between mmap() and ext4_move_extents(): - -* NOTE: "A", "B" and "C" mean different processes - -A-1: ext4_ext_move_extents() acquires i_data_sem of two inodes. - -B: do_page_fault() starts the transaction (T), - and then tries to acquire i_data_sem. - But process "A" is already holding it, so it is kept waiting. - -C: While "A" and "B" running, kjournald2 tries to commit transaction (T) - but it is under updating, so kjournald2 waits for it. - -A-2: Call ext4_journal_start with holding i_data_sem, - but transaction (T) is locked. - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 117 ++++++++++++++++++++++---------------------------- - 1 file changed, 53 insertions(+), 64 deletions(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -77,12 +77,14 @@ static int - mext_next_extent(struct inode *inode, struct ext4_ext_path *path, - struct ext4_extent **extent) - { -+ struct ext4_extent_header *eh; - int ppos, leaf_ppos = path->p_depth; - - ppos = leaf_ppos; - if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) { - /* leaf block */ - *extent = ++path[ppos].p_ext; -+ path[ppos].p_block = ext_pblock(path[ppos].p_ext); - return 0; - } - -@@ -119,9 +121,18 @@ mext_next_extent(struct inode *inode, st - ext_block_hdr(path[cur_ppos+1].p_bh); - } - -+ path[leaf_ppos].p_ext = *extent = NULL; -+ -+ eh = path[leaf_ppos].p_hdr; -+ if (le16_to_cpu(eh->eh_entries) == 0) -+ /* empty leaf is found */ -+ return -ENODATA; -+ - /* leaf block */ - path[leaf_ppos].p_ext = *extent = - EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr); -+ path[leaf_ppos].p_block = -+ ext_pblock(path[leaf_ppos].p_ext); - return 0; - } - } -@@ -155,40 +166,15 @@ mext_check_null_inode(struct inode *inod - } - - /** -- * mext_double_down_read - Acquire two inodes' read semaphore -- * -- * @orig_inode: original inode structure -- * @donor_inode: donor inode structure -- * Acquire read semaphore of the two inodes (orig and donor) by i_ino order. -- */ --static void --mext_double_down_read(struct inode *orig_inode, struct inode *donor_inode) --{ -- struct inode *first = orig_inode, *second = donor_inode; -- -- /* -- * Use the inode number to provide the stable locking order instead -- * of its address, because the C language doesn't guarantee you can -- * compare pointers that don't come from the same array. -- */ -- if (donor_inode->i_ino < orig_inode->i_ino) { -- first = donor_inode; -- second = orig_inode; -- } -- -- down_read(&EXT4_I(first)->i_data_sem); -- down_read(&EXT4_I(second)->i_data_sem); --} -- --/** -- * mext_double_down_write - Acquire two inodes' write semaphore -+ * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem - * - * @orig_inode: original inode structure - * @donor_inode: donor inode structure -- * Acquire write semaphore of the two inodes (orig and donor) by i_ino order. -+ * Acquire write lock of i_data_sem of the two inodes (orig and donor) by -+ * i_ino order. - */ - static void --mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode) -+double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) - { - struct inode *first = orig_inode, *second = donor_inode; - -@@ -207,28 +193,14 @@ mext_double_down_write(struct inode *ori - } - - /** -- * mext_double_up_read - Release two inodes' read semaphore -+ * double_up_write_data_sem - Release two inodes' write lock of i_data_sem - * - * @orig_inode: original inode structure to be released its lock first - * @donor_inode: donor inode structure to be released its lock second -- * Release read semaphore of two inodes (orig and donor). -+ * Release write lock of i_data_sem of two inodes (orig and donor). - */ - static void --mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode) --{ -- up_read(&EXT4_I(orig_inode)->i_data_sem); -- up_read(&EXT4_I(donor_inode)->i_data_sem); --} -- --/** -- * mext_double_up_write - Release two inodes' write semaphore -- * -- * @orig_inode: original inode structure to be released its lock first -- * @donor_inode: donor inode structure to be released its lock second -- * Release write semaphore of two inodes (orig and donor). -- */ --static void --mext_double_up_write(struct inode *orig_inode, struct inode *donor_inode) -+double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) - { - up_write(&EXT4_I(orig_inode)->i_data_sem); - up_write(&EXT4_I(donor_inode)->i_data_sem); -@@ -688,8 +660,6 @@ mext_replace_branches(handle_t *handle, - int replaced_count = 0; - int dext_alen; - -- mext_double_down_write(orig_inode, donor_inode); -- - /* Get the original extent for the block "orig_off" */ - *err = get_ext_path(orig_inode, orig_off, &orig_path); - if (*err) -@@ -785,7 +755,6 @@ out: - kfree(donor_path); - } - -- mext_double_up_write(orig_inode, donor_inode); - return replaced_count; - } - -@@ -851,6 +820,11 @@ move_extent_per_page(struct file *o_filp - * Just swap data blocks between orig and donor. - */ - if (uninit) { -+ /* -+ * Protect extent trees against block allocations -+ * via delalloc -+ */ -+ double_down_write_data_sem(orig_inode, donor_inode); - replaced_count = mext_replace_branches(handle, orig_inode, - donor_inode, orig_blk_offset, - block_len_in_page, err); -@@ -858,6 +832,7 @@ move_extent_per_page(struct file *o_filp - /* Clear the inode cache not to refer to the old data */ - ext4_ext_invalidate_cache(orig_inode); - ext4_ext_invalidate_cache(donor_inode); -+ double_up_write_data_sem(orig_inode, donor_inode); - goto out2; - } - -@@ -905,6 +880,8 @@ move_extent_per_page(struct file *o_filp - /* Release old bh and drop refs */ - try_to_release_page(page, 0); - -+ /* Protect extent trees against block allocations via delalloc */ -+ double_down_write_data_sem(orig_inode, donor_inode); - replaced_count = mext_replace_branches(handle, orig_inode, donor_inode, - orig_blk_offset, block_len_in_page, - &err2); -@@ -913,14 +890,18 @@ move_extent_per_page(struct file *o_filp - block_len_in_page = replaced_count; - replaced_size = - block_len_in_page << orig_inode->i_blkbits; -- } else -+ } else { -+ double_up_write_data_sem(orig_inode, donor_inode); - goto out; -+ } - } - - /* Clear the inode cache not to refer to the old data */ - ext4_ext_invalidate_cache(orig_inode); - ext4_ext_invalidate_cache(donor_inode); - -+ double_up_write_data_sem(orig_inode, donor_inode); -+ - if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0); - -@@ -1236,16 +1217,16 @@ ext4_move_extents(struct file *o_filp, s - return -EINVAL; - } - -- /* protect orig and donor against a truncate */ -+ /* Protect orig and donor inodes against a truncate */ - ret1 = mext_inode_double_lock(orig_inode, donor_inode); - if (ret1 < 0) - return ret1; - -- mext_double_down_read(orig_inode, donor_inode); -+ /* Protect extent tree against block allocations via delalloc */ -+ double_down_write_data_sem(orig_inode, donor_inode); - /* Check the filesystem environment whether move_extent can be done */ - ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start, - donor_start, &len, *moved_len); -- mext_double_up_read(orig_inode, donor_inode); - if (ret1) - goto out; - -@@ -1308,6 +1289,10 @@ ext4_move_extents(struct file *o_filp, s - ext4_ext_get_actual_len(ext_cur), block_end + 1) - - max(le32_to_cpu(ext_cur->ee_block), block_start); - -+ /* Discard preallocations of two inodes */ -+ ext4_discard_preallocations(orig_inode); -+ ext4_discard_preallocations(donor_inode); -+ - while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) { - seq_blocks += add_blocks; - -@@ -1359,14 +1344,14 @@ ext4_move_extents(struct file *o_filp, s - seq_start = le32_to_cpu(ext_cur->ee_block); - rest_blocks = seq_blocks; - -- /* Discard preallocations of two inodes */ -- down_write(&EXT4_I(orig_inode)->i_data_sem); -- ext4_discard_preallocations(orig_inode); -- up_write(&EXT4_I(orig_inode)->i_data_sem); -- -- down_write(&EXT4_I(donor_inode)->i_data_sem); -- ext4_discard_preallocations(donor_inode); -- up_write(&EXT4_I(donor_inode)->i_data_sem); -+ /* -+ * Up semaphore to avoid following problems: -+ * a. transaction deadlock among ext4_journal_start, -+ * ->write_begin via pagefault, and jbd2_journal_commit -+ * b. racing with ->readpage, ->write_begin, and ext4_get_block -+ * in move_extent_per_page -+ */ -+ double_up_write_data_sem(orig_inode, donor_inode); - - while (orig_page_offset <= seq_end_page) { - -@@ -1381,14 +1366,14 @@ ext4_move_extents(struct file *o_filp, s - /* Count how many blocks we have exchanged */ - *moved_len += block_len_in_page; - if (ret1 < 0) -- goto out; -+ break; - if (*moved_len > len) { - ext4_error(orig_inode->i_sb, __func__, - "We replaced blocks too much! " - "sum of replaced: %llu requested: %llu", - *moved_len, len); - ret1 = -EIO; -- goto out; -+ break; - } - - orig_page_offset++; -@@ -1400,6 +1385,10 @@ ext4_move_extents(struct file *o_filp, s - block_len_in_page = rest_blocks; - } - -+ double_down_write_data_sem(orig_inode, donor_inode); -+ if (ret1 < 0) -+ break; -+ - /* Decrease buffer counter */ - if (holecheck_path) - ext4_ext_drop_refs(holecheck_path); -@@ -1429,7 +1418,7 @@ out: - ext4_ext_drop_refs(holecheck_path); - kfree(holecheck_path); - } -- -+ double_up_write_data_sem(orig_inode, donor_inode); - ret2 = mext_inode_double_unlock(orig_inode, donor_inode); - - if (ret1) diff --git a/queue-2.6.32/0005-ext4-fix-possible-recursive-locking-warning-in-EXT4_.patch b/queue-2.6.32/0005-ext4-fix-possible-recursive-locking-warning-in-EXT4_.patch deleted file mode 100644 index 86da634a2fa..00000000000 --- a/queue-2.6.32/0005-ext4-fix-possible-recursive-locking-warning-in-EXT4_.patch +++ /dev/null @@ -1,36 +0,0 @@ -From 2af090b9487c1259525876fe4f3a2605594ac413 Mon Sep 17 00:00:00 2001 -From: Akira Fujita -Date: Mon, 23 Nov 2009 07:24:41 -0500 -Subject: [PATCH 05/30] ext4: fix possible recursive locking warning in EXT4_IOC_MOVE_EXT - -(cherry picked from commit 49bd22bc4d603a2a4fc2a6a60e156cbea52eb494) - -If CONFIG_PROVE_LOCKING is enabled, the double_down_write_data_sem() -will trigger a false-positive warning of a recursive lock. Since we -take i_data_sem for the two inodes ordered by their inode numbers, -this isn't a problem. Use of down_write_nested() will notify the lock -dependency checker machinery that there is no problem here. - -This problem was reported by Brian Rogers: - - http://marc.info/?l=linux-ext4&m=125115356928011&w=1 - -Reported-by: Brian Rogers -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -189,7 +189,7 @@ double_down_write_data_sem(struct inode - } - - down_write(&EXT4_I(first)->i_data_sem); -- down_write(&EXT4_I(second)->i_data_sem); -+ down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING); - } - - /** diff --git a/queue-2.6.32/0006-ext4-plug-a-buffer_head-leak-in-an-error-path-of-ext.patch b/queue-2.6.32/0006-ext4-plug-a-buffer_head-leak-in-an-error-path-of-ext.patch deleted file mode 100644 index ade9f8cebba..00000000000 --- a/queue-2.6.32/0006-ext4-plug-a-buffer_head-leak-in-an-error-path-of-ext.patch +++ /dev/null @@ -1,86 +0,0 @@ -From a712d4ea6545e04d90dd0ca788cd2380a93ce7dc Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Sat, 14 Nov 2009 08:19:05 -0500 -Subject: [PATCH 06/30] ext4: plug a buffer_head leak in an error path of ext4_iget() - -(cherry picked from commit 567f3e9a70d71e5c9be03701b8578be77857293b) - -One of the invalid error paths in ext4_iget() forgot to brelse() the -inode buffer head. Fix it by adding a brelse() in the common error -return path, which also simplifies function. - -Thanks to Andi Kleen reporting the problem. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 11 +++-------- - 1 file changed, 3 insertions(+), 8 deletions(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -4781,7 +4781,6 @@ struct inode *ext4_iget(struct super_blo - struct ext4_iloc iloc; - struct ext4_inode *raw_inode; - struct ext4_inode_info *ei; -- struct buffer_head *bh; - struct inode *inode; - long ret; - int block; -@@ -4793,11 +4792,11 @@ struct inode *ext4_iget(struct super_blo - return inode; - - ei = EXT4_I(inode); -+ iloc.bh = 0; - - ret = __ext4_get_inode_loc(inode, &iloc, 0); - if (ret < 0) - goto bad_inode; -- bh = iloc.bh; - raw_inode = ext4_raw_inode(&iloc); - inode->i_mode = le16_to_cpu(raw_inode->i_mode); - inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); -@@ -4820,7 +4819,6 @@ struct inode *ext4_iget(struct super_blo - if (inode->i_mode == 0 || - !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) { - /* this inode is deleted */ -- brelse(bh); - ret = -ESTALE; - goto bad_inode; - } -@@ -4852,7 +4850,6 @@ struct inode *ext4_iget(struct super_blo - ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); - if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > - EXT4_INODE_SIZE(inode->i_sb)) { -- brelse(bh); - ret = -EIO; - goto bad_inode; - } -@@ -4905,10 +4902,8 @@ struct inode *ext4_iget(struct super_blo - /* Validate block references which are part of inode */ - ret = ext4_check_inode_blockref(inode); - } -- if (ret) { -- brelse(bh); -+ if (ret) - goto bad_inode; -- } - - if (S_ISREG(inode->i_mode)) { - inode->i_op = &ext4_file_inode_operations; -@@ -4936,7 +4931,6 @@ struct inode *ext4_iget(struct super_blo - init_special_inode(inode, inode->i_mode, - new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); - } else { -- brelse(bh); - ret = -EIO; - ext4_error(inode->i_sb, __func__, - "bogus i_mode (%o) for inode=%lu", -@@ -4949,6 +4943,7 @@ struct inode *ext4_iget(struct super_blo - return inode; - - bad_inode: -+ brelse(iloc.bh); - iget_failed(inode); - return ERR_PTR(ret); - } diff --git a/queue-2.6.32/0007-ext4-make-sure-directory-and-symlink-blocks-are-revo.patch b/queue-2.6.32/0007-ext4-make-sure-directory-and-symlink-blocks-are-revo.patch deleted file mode 100644 index 1cd419f8a7c..00000000000 --- a/queue-2.6.32/0007-ext4-make-sure-directory-and-symlink-blocks-are-revo.patch +++ /dev/null @@ -1,62 +0,0 @@ -From 766191a641ba219a4152ce3cfbb24cc15426e025 Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Mon, 23 Nov 2009 07:17:34 -0500 -Subject: [PATCH 07/30] ext4: make sure directory and symlink blocks are revoked - -(cherry picked from commit 50689696867d95b38d9c7be640a311494a04fb86) - -When an inode gets unlinked, the functions ext4_clear_blocks() and -ext4_remove_blocks() call ext4_forget() for all the buffer heads -corresponding to the deleted inode's data blocks. If the inode is a -directory or a symlink, the is_metadata parameter must be non-zero so -ext4_forget() will revoke them via jbd2_journal_revoke(). Otherwise, -if these blocks are reused for a data file, and the system crashes -before a journal checkpoint, the journal replay could end up -corrupting these data blocks. - -Thanks to Curt Wohlgemuth for pointing out potential problems in this -area. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/extents.c | 2 +- - fs/ext4/inode.c | 6 ++++-- - 2 files changed, 5 insertions(+), 3 deletions(-) - ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -2074,7 +2074,7 @@ static int ext4_remove_blocks(handle_t * - ext_debug("free last %u blocks starting %llu\n", num, start); - for (i = 0; i < num; i++) { - bh = sb_find_get_block(inode->i_sb, start + i); -- ext4_forget(handle, 0, inode, bh, start + i); -+ ext4_forget(handle, metadata, inode, bh, start + i); - } - ext4_free_blocks(handle, inode, start, num, metadata); - } else if (from == le32_to_cpu(ex->ee_block) ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -4120,6 +4120,8 @@ static void ext4_clear_blocks(handle_t * - __le32 *last) - { - __le32 *p; -+ int is_metadata = S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode); -+ - if (try_to_extend_transaction(handle, inode)) { - if (bh) { - BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); -@@ -4150,11 +4152,11 @@ static void ext4_clear_blocks(handle_t * - - *p = 0; - tbh = sb_find_get_block(inode->i_sb, nr); -- ext4_forget(handle, 0, inode, tbh, nr); -+ ext4_forget(handle, is_metadata, inode, tbh, nr); - } - } - -- ext4_free_blocks(handle, inode, block_to_free, count, 0); -+ ext4_free_blocks(handle, inode, block_to_free, count, is_metadata); - } - - /** diff --git a/queue-2.6.32/0008-ext4-fix-i_flags-access-in-ext4_da_writepages_trans_.patch b/queue-2.6.32/0008-ext4-fix-i_flags-access-in-ext4_da_writepages_trans_.patch deleted file mode 100644 index 6826dab2867..00000000000 --- a/queue-2.6.32/0008-ext4-fix-i_flags-access-in-ext4_da_writepages_trans_.patch +++ /dev/null @@ -1,29 +0,0 @@ -From 7606c163cb096dfda150e6bd7323d60bbda9ea0d Mon Sep 17 00:00:00 2001 -From: Julia Lawall -Date: Sun, 15 Nov 2009 15:30:58 -0500 -Subject: [PATCH 08/30] ext4: fix i_flags access in ext4_da_writepages_trans_blocks() - -(cherry picked from commit 30c6e07a92ea4cb87160d32ffa9bce172576ae4c) - -We need to be testing the i_flags field in the ext4 specific portion -of the inode, instead of the (confusingly aliased) i_flags field in -the generic struct inode. - -Signed-off-by: Julia Lawall -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -2788,7 +2788,7 @@ static int ext4_da_writepages_trans_bloc - * number of contiguous block. So we will limit - * number of contiguous block to a sane value - */ -- if (!(inode->i_flags & EXT4_EXTENTS_FL) && -+ if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) && - (max_blocks > EXT4_MAX_TRANS_DATA)) - max_blocks = EXT4_MAX_TRANS_DATA; - diff --git a/queue-2.6.32/0009-ext4-journal-all-modifications-in-ext4_xattr_set_han.patch b/queue-2.6.32/0009-ext4-journal-all-modifications-in-ext4_xattr_set_han.patch deleted file mode 100644 index 15b8e0706f0..00000000000 --- a/queue-2.6.32/0009-ext4-journal-all-modifications-in-ext4_xattr_set_han.patch +++ /dev/null @@ -1,43 +0,0 @@ -From 22d31ce67bb060aba86bf20ba6f69cb9e39a1fa2 Mon Sep 17 00:00:00 2001 -From: Eric Sandeen -Date: Sun, 15 Nov 2009 15:30:52 -0500 -Subject: [PATCH 09/30] ext4: journal all modifications in ext4_xattr_set_handle - -(cherry picked from commit 86ebfd08a1930ccedb8eac0aeb1ed4b8b6a41dbc) - -ext4_xattr_set_handle() was zeroing out an inode outside -of journaling constraints; this is one of the accesses that -was causing the crc errors in journal replay as seen in -kernel.org bugzilla #14354. - -Reviewed-by: Andreas Dilger -Signed-off-by: Eric Sandeen -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/xattr.c | 7 ++++--- - 1 file changed, 4 insertions(+), 3 deletions(-) - ---- a/fs/ext4/xattr.c -+++ b/fs/ext4/xattr.c -@@ -988,6 +988,10 @@ ext4_xattr_set_handle(handle_t *handle, - if (error) - goto cleanup; - -+ error = ext4_journal_get_write_access(handle, is.iloc.bh); -+ if (error) -+ goto cleanup; -+ - if (EXT4_I(inode)->i_state & EXT4_STATE_NEW) { - struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc); - memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); -@@ -1013,9 +1017,6 @@ ext4_xattr_set_handle(handle_t *handle, - if (flags & XATTR_CREATE) - goto cleanup; - } -- error = ext4_journal_get_write_access(handle, is.iloc.bh); -- if (error) -- goto cleanup; - if (!value) { - if (!is.s.not_found) - error = ext4_xattr_ibody_set(handle, inode, &i, &is); diff --git a/queue-2.6.32/0010-ext4-don-t-update-the-superblock-in-ext4_statfs.patch b/queue-2.6.32/0010-ext4-don-t-update-the-superblock-in-ext4_statfs.patch deleted file mode 100644 index 61a0e755b88..00000000000 --- a/queue-2.6.32/0010-ext4-don-t-update-the-superblock-in-ext4_statfs.patch +++ /dev/null @@ -1,35 +0,0 @@ -From cd0201f1e2b91358cf15c234482645381ad183b7 Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Mon, 23 Nov 2009 07:24:52 -0500 -Subject: [PATCH 10/30] ext4: don't update the superblock in ext4_statfs() - -(cherry picked from commit 3f8fb9490efbd300887470a2a880a64e04dcc3f5) - -commit a71ce8c6c9bf269b192f352ea555217815cf027e updated ext4_statfs() -to update the on-disk superblock counters, but modified this buffer -directly without any journaling of the change. This is one of the -accesses that was causing the crc errors in journal replay as seen in -kernel.org bugzilla #14354. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/super.c | 2 -- - 1 file changed, 2 deletions(-) - ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -3668,13 +3668,11 @@ static int ext4_statfs(struct dentry *de - buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last; - buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) - - percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter); -- ext4_free_blocks_count_set(es, buf->f_bfree); - buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es); - if (buf->f_bfree < ext4_r_blocks_count(es)) - buf->f_bavail = 0; - buf->f_files = le32_to_cpu(es->s_inodes_count); - buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter); -- es->s_free_inodes_count = cpu_to_le32(buf->f_ffree); - buf->f_namelen = EXT4_NAME_LEN; - fsid = le64_to_cpup((void *)es->s_uuid) ^ - le64_to_cpup((void *)es->s_uuid + sizeof(u64)); diff --git a/queue-2.6.32/0011-ext4-fix-uninit-block-bitmap-initialization-when-s_m.patch b/queue-2.6.32/0011-ext4-fix-uninit-block-bitmap-initialization-when-s_m.patch deleted file mode 100644 index ffb2aebf146..00000000000 --- a/queue-2.6.32/0011-ext4-fix-uninit-block-bitmap-initialization-when-s_m.patch +++ /dev/null @@ -1,33 +0,0 @@ -From de7685f1b6efddd2fcf54f9fa94fee73b1a98f67 Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Mon, 23 Nov 2009 07:24:38 -0500 -Subject: [PATCH 11/30] ext4: fix uninit block bitmap initialization when s_meta_first_bg is non-zero - -(cherry picked from commit 8dadb198cb70ef811916668fe67eeec82e8858dd) - -The number of old-style block group descriptor blocks is -s_meta_first_bg when the meta_bg feature flag is set. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/balloc.c | 8 +++++++- - 1 file changed, 7 insertions(+), 1 deletion(-) - ---- a/fs/ext4/balloc.c -+++ b/fs/ext4/balloc.c -@@ -761,7 +761,13 @@ static unsigned long ext4_bg_num_gdb_met - static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, - ext4_group_t group) - { -- return ext4_bg_has_super(sb, group) ? EXT4_SB(sb)->s_gdb_count : 0; -+ if (!ext4_bg_has_super(sb, group)) -+ return 0; -+ -+ if (EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG)) -+ return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); -+ else -+ return EXT4_SB(sb)->s_gdb_count; - } - - /** diff --git a/queue-2.6.32/0012-ext4-fix-block-validity-checks-so-they-work-correctl.patch b/queue-2.6.32/0012-ext4-fix-block-validity-checks-so-they-work-correctl.patch deleted file mode 100644 index 302343a816e..00000000000 --- a/queue-2.6.32/0012-ext4-fix-block-validity-checks-so-they-work-correctl.patch +++ /dev/null @@ -1,43 +0,0 @@ -From c2388358cfbf01a0f2b57fe0549791004fb1c72c Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Sun, 15 Nov 2009 15:29:56 -0500 -Subject: [PATCH 12/30] ext4: fix block validity checks so they work correctly with meta_bg - -(cherry picked from commit 1032988c71f3f85483b2b4319684d1205a704c02) - -The block validity checks used by ext4_data_block_valid() wasn't -correctly written to check file systems with the meta_bg feature. Fix -this. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/block_validity.c | 2 +- - fs/ext4/inode.c | 5 +---- - 2 files changed, 2 insertions(+), 5 deletions(-) - ---- a/fs/ext4/block_validity.c -+++ b/fs/ext4/block_validity.c -@@ -160,7 +160,7 @@ int ext4_setup_system_zone(struct super_ - if (ext4_bg_has_super(sb, i) && - ((i < 5) || ((i % flex_size) == 0))) - add_system_zone(sbi, ext4_group_first_block_no(sb, i), -- sbi->s_gdb_count + 1); -+ ext4_bg_num_gdb(sb, i) + 1); - gdp = ext4_get_group_desc(sb, i, NULL); - ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1); - if (ret) ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -4883,10 +4883,7 @@ struct inode *ext4_iget(struct super_blo - - ret = 0; - if (ei->i_file_acl && -- ((ei->i_file_acl < -- (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) + -- EXT4_SB(sb)->s_gdb_count)) || -- (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) { -+ !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { - ext4_error(sb, __func__, - "bad extended attribute block %llu in inode #%lu", - ei->i_file_acl, inode->i_ino); diff --git a/queue-2.6.32/0013-ext4-avoid-issuing-unnecessary-barriers.patch b/queue-2.6.32/0013-ext4-avoid-issuing-unnecessary-barriers.patch deleted file mode 100644 index 646d50e37f4..00000000000 --- a/queue-2.6.32/0013-ext4-avoid-issuing-unnecessary-barriers.patch +++ /dev/null @@ -1,41 +0,0 @@ -From c5e9fda54109d93439f7ee3224e0421edbed6c4b Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Mon, 23 Nov 2009 07:24:57 -0500 -Subject: [PATCH 13/30] ext4: avoid issuing unnecessary barriers - -(cherry picked from commit 6b17d902fdd241adfa4ce780df20547b28bf5801) - -We don't to issue an I/O barrier on an error or if we force commit -because we are doing data journaling. - -Signed-off-by: "Theodore Ts'o" -Cc: Jan Kara -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/fsync.c | 8 +++----- - 1 file changed, 3 insertions(+), 5 deletions(-) - ---- a/fs/ext4/fsync.c -+++ b/fs/ext4/fsync.c -@@ -60,7 +60,7 @@ int ext4_sync_file(struct file *file, st - - ret = flush_aio_dio_completed_IO(inode); - if (ret < 0) -- goto out; -+ return ret; - /* - * data=writeback: - * The caller's filemap_fdatawrite()/wait will sync the data. -@@ -79,10 +79,8 @@ int ext4_sync_file(struct file *file, st - * (they were dirtied by commit). But that's OK - the blocks are - * safe in-journal, which is all fsync() needs to ensure. - */ -- if (ext4_should_journal_data(inode)) { -- ret = ext4_force_commit(inode->i_sb); -- goto out; -- } -+ if (ext4_should_journal_data(inode)) -+ return ext4_force_commit(inode->i_sb); - - if (!journal) - ret = sync_mapping_buffers(inode->i_mapping); diff --git a/queue-2.6.32/0014-ext4-fix-error-handling-in-ext4_ind_get_blocks.patch b/queue-2.6.32/0014-ext4-fix-error-handling-in-ext4_ind_get_blocks.patch deleted file mode 100644 index 666ea01a734..00000000000 --- a/queue-2.6.32/0014-ext4-fix-error-handling-in-ext4_ind_get_blocks.patch +++ /dev/null @@ -1,29 +0,0 @@ -From 42c6dded3faff003f12dde41715865327590cd6c Mon Sep 17 00:00:00 2001 -From: Jan Kara -Date: Mon, 23 Nov 2009 07:24:48 -0500 -Subject: [PATCH 14/30] ext4: fix error handling in ext4_ind_get_blocks() - -(cherry picked from commit 2bba702d4f88d7b010ec37e2527b552588404ae7) - -When an error happened in ext4_splice_branch we failed to notice that -in ext4_ind_get_blocks and mapped the buffer anyway. Fix the problem -by checking for error properly. - -Signed-off-by: Jan Kara -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -1021,7 +1021,7 @@ static int ext4_ind_get_blocks(handle_t - if (!err) - err = ext4_splice_branch(handle, inode, iblock, - partial, indirect_blks, count); -- else -+ if (err) - goto cleanup; - - set_buffer_new(bh_result); diff --git a/queue-2.6.32/0015-ext4-make-trim-discard-optional-and-off-by-default.patch b/queue-2.6.32/0015-ext4-make-trim-discard-optional-and-off-by-default.patch deleted file mode 100644 index 7549d4b614d..00000000000 --- a/queue-2.6.32/0015-ext4-make-trim-discard-optional-and-off-by-default.patch +++ /dev/null @@ -1,128 +0,0 @@ -From a48fc8df1871ad50bef2476e76ad5038f5a927ce Mon Sep 17 00:00:00 2001 -From: Eric Sandeen -Date: Thu, 19 Nov 2009 14:25:42 -0500 -Subject: [PATCH 15/30] ext4: make trim/discard optional (and off by default) - -(cherry picked from commit 5328e635315734d42080de9a5a1ee87bf4cae0a4) - -It is anticipated that when sb_issue_discard starts doing -real work on trim-capable devices, we may see issues. Make -this mount-time optional, and default it to off until we know -that things are working out OK. - -Signed-off-by: Eric Sandeen -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - Documentation/filesystems/ext4.txt | 6 ++++++ - fs/ext4/ext4.h | 1 + - fs/ext4/mballoc.c | 21 +++++++++++++-------- - fs/ext4/super.c | 14 +++++++++++++- - 4 files changed, 33 insertions(+), 9 deletions(-) - ---- a/Documentation/filesystems/ext4.txt -+++ b/Documentation/filesystems/ext4.txt -@@ -353,6 +353,12 @@ noauto_da_alloc replacing existing file - system crashes before the delayed allocation - blocks are forced to disk. - -+discard Controls whether ext4 should issue discard/TRIM -+nodiscard(*) commands to the underlying block device when -+ blocks are freed. This is useful for SSD devices -+ and sparse/thinly-provisioned LUNs, but it is off -+ by default until sufficient testing has been done. -+ - Data Mode - ========= - There are 3 different data modes: ---- a/fs/ext4/ext4.h -+++ b/fs/ext4/ext4.h -@@ -750,6 +750,7 @@ struct ext4_inode_info { - #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ - #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ - #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ -+#define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */ - - #define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt - #define set_opt(o, opt) o |= EXT4_MOUNT_##opt ---- a/fs/ext4/mballoc.c -+++ b/fs/ext4/mballoc.c -@@ -2529,7 +2529,6 @@ static void release_blocks_on_commit(jou - struct ext4_group_info *db; - int err, count = 0, count2 = 0; - struct ext4_free_data *entry; -- ext4_fsblk_t discard_block; - struct list_head *l, *ltmp; - - list_for_each_safe(l, ltmp, &txn->t_private_list) { -@@ -2559,13 +2558,19 @@ static void release_blocks_on_commit(jou - page_cache_release(e4b.bd_bitmap_page); - } - ext4_unlock_group(sb, entry->group); -- discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb) -- + entry->start_blk -- + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); -- trace_ext4_discard_blocks(sb, (unsigned long long)discard_block, -- entry->count); -- sb_issue_discard(sb, discard_block, entry->count); -- -+ if (test_opt(sb, DISCARD)) { -+ ext4_fsblk_t discard_block; -+ struct ext4_super_block *es = EXT4_SB(sb)->s_es; -+ -+ discard_block = (ext4_fsblk_t)entry->group * -+ EXT4_BLOCKS_PER_GROUP(sb) -+ + entry->start_blk -+ + le32_to_cpu(es->s_first_data_block); -+ trace_ext4_discard_blocks(sb, -+ (unsigned long long)discard_block, -+ entry->count); -+ sb_issue_discard(sb, discard_block, entry->count); -+ } - kmem_cache_free(ext4_free_ext_cachep, entry); - ext4_mb_release_desc(&e4b); - } ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -899,6 +899,9 @@ static int ext4_show_options(struct seq_ - if (test_opt(sb, NO_AUTO_DA_ALLOC)) - seq_puts(seq, ",noauto_da_alloc"); - -+ if (test_opt(sb, DISCARD)) -+ seq_puts(seq, ",discard"); -+ - ext4_show_quota_options(seq, sb); - - return 0; -@@ -1079,7 +1082,8 @@ enum { - Opt_usrquota, Opt_grpquota, Opt_i_version, - Opt_stripe, Opt_delalloc, Opt_nodelalloc, - Opt_block_validity, Opt_noblock_validity, -- Opt_inode_readahead_blks, Opt_journal_ioprio -+ Opt_inode_readahead_blks, Opt_journal_ioprio, -+ Opt_discard, Opt_nodiscard, - }; - - static const match_table_t tokens = { -@@ -1144,6 +1148,8 @@ static const match_table_t tokens = { - {Opt_auto_da_alloc, "auto_da_alloc=%u"}, - {Opt_auto_da_alloc, "auto_da_alloc"}, - {Opt_noauto_da_alloc, "noauto_da_alloc"}, -+ {Opt_discard, "discard"}, -+ {Opt_nodiscard, "nodiscard"}, - {Opt_err, NULL}, - }; - -@@ -1565,6 +1571,12 @@ set_qf_format: - else - set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC); - break; -+ case Opt_discard: -+ set_opt(sbi->s_mount_opt, DISCARD); -+ break; -+ case Opt_nodiscard: -+ clear_opt(sbi->s_mount_opt, DISCARD); -+ break; - default: - ext4_msg(sb, KERN_ERR, - "Unrecognized mount option \"%s\" " diff --git a/queue-2.6.32/0016-ext4-make-norecovery-an-alias-for-noload.patch b/queue-2.6.32/0016-ext4-make-norecovery-an-alias-for-noload.patch deleted file mode 100644 index 2fa498bcf37..00000000000 --- a/queue-2.6.32/0016-ext4-make-norecovery-an-alias-for-noload.patch +++ /dev/null @@ -1,57 +0,0 @@ -From 68ab480b59f296d164526cc51e2876687340c803 Mon Sep 17 00:00:00 2001 -From: Eric Sandeen -Date: Thu, 19 Nov 2009 14:28:50 -0500 -Subject: [PATCH 16/30] ext4: make "norecovery" an alias for "noload" - -(cherry picked from commit e3bb52ae2bb9573e84c17b8e3560378d13a5c798) - -Users on the linux-ext4 list recently complained about differences -across filesystems w.r.t. how to mount without a journal replay. - -In the discussion it was noted that xfs's "norecovery" option is -perhaps more descriptively accurate than "noload," so let's make -that an alias for ext4. - -Also show this status in /proc/mounts - -Signed-off-by: Eric Sandeen -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - Documentation/filesystems/ext4.txt | 4 ++-- - fs/ext4/super.c | 4 ++++ - 2 files changed, 6 insertions(+), 2 deletions(-) - ---- a/Documentation/filesystems/ext4.txt -+++ b/Documentation/filesystems/ext4.txt -@@ -153,8 +153,8 @@ journal_dev=devnum When the external jou - identified through its new major/minor numbers encoded - in devnum. - --noload Don't load the journal on mounting. Note that -- if the filesystem was not unmounted cleanly, -+norecovery Don't load the journal on mounting. Note that -+noload if the filesystem was not unmounted cleanly, - skipping the journal replay will lead to the - filesystem containing inconsistencies that can - lead to any number of problems. ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -902,6 +902,9 @@ static int ext4_show_options(struct seq_ - if (test_opt(sb, DISCARD)) - seq_puts(seq, ",discard"); - -+ if (test_opt(sb, NOLOAD)) -+ seq_puts(seq, ",norecovery"); -+ - ext4_show_quota_options(seq, sb); - - return 0; -@@ -1108,6 +1111,7 @@ static const match_table_t tokens = { - {Opt_acl, "acl"}, - {Opt_noacl, "noacl"}, - {Opt_noload, "noload"}, -+ {Opt_noload, "norecovery"}, - {Opt_nobh, "nobh"}, - {Opt_bh, "bh"}, - {Opt_commit, "commit=%u"}, diff --git a/queue-2.6.32/0017-ext4-Fix-double-free-of-blocks-with-EXT4_IOC_MOVE_EX.patch b/queue-2.6.32/0017-ext4-Fix-double-free-of-blocks-with-EXT4_IOC_MOVE_EX.patch deleted file mode 100644 index fb0b6926ef4..00000000000 --- a/queue-2.6.32/0017-ext4-Fix-double-free-of-blocks-with-EXT4_IOC_MOVE_EX.patch +++ /dev/null @@ -1,79 +0,0 @@ -From 164659d7861e1243dc300c27c63e5918762912eb Mon Sep 17 00:00:00 2001 -From: Akira Fujita -Date: Tue, 24 Nov 2009 10:19:57 -0500 -Subject: [PATCH 17/30] ext4: Fix double-free of blocks with EXT4_IOC_MOVE_EXT - -(cherry picked from commit 94d7c16cbbbd0e03841fcf272bcaf0620ad39618) - -At the beginning of ext4_move_extent(), we call -ext4_discard_preallocations() to discard inode PAs of orig and donor -inodes. But in the following case, blocks can be double freed, so -move ext4_discard_preallocations() to the end of ext4_move_extents(). - -1. Discard inode PAs of orig and donor inodes with - ext4_discard_preallocations() in ext4_move_extents(). - - orig : [ DATA1 ] - donor: [ DATA2 ] - -2. While data blocks are exchanging between orig and donor inodes, new - inode PAs is created to orig by other process's block allocation. - (Since there are semaphore gaps in ext4_move_extents().) And new - inode PAs is used partially (2-1). - - 2-1 Create new inode PAs to orig inode - orig : [ DATA1 | used PA1 | free PA1 ] - donor: [ DATA2 ] - -3. Donor inode which has old orig inode's blocks is deleted after - EXT4_IOC_MOVE_EXT finished (3-1, 3-2). So the block bitmap - corresponds to old orig inode's blocks are freed. - - 3-1 After EXT4_IOC_MOVE_EXT finished - orig : [ DATA2 | free PA1 ] - donor: [ DATA1 | used PA1 ] - - 3-2 Delete donor inode - orig : [ DATA2 | free PA1 ] - donor: [ FREE SPACE(DATA1) | FREE SPACE(used PA1) ] - -4. The double-free of blocks is occurred, when close() is called to - orig inode. Because ext4_discard_preallocations() for orig inode - frees used PA1 and free PA1, though used PA1 is already freed in 3. - - 4-1 Double-free of blocks is occurred - orig : [ DATA2 | FREE SPACE(free PA1) ] - donor: [ FREE SPACE(DATA1) | DOUBLE FREE(used PA1) ] - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 9 +++++---- - 1 file changed, 5 insertions(+), 4 deletions(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -1289,10 +1289,6 @@ ext4_move_extents(struct file *o_filp, s - ext4_ext_get_actual_len(ext_cur), block_end + 1) - - max(le32_to_cpu(ext_cur->ee_block), block_start); - -- /* Discard preallocations of two inodes */ -- ext4_discard_preallocations(orig_inode); -- ext4_discard_preallocations(donor_inode); -- - while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) { - seq_blocks += add_blocks; - -@@ -1410,6 +1406,11 @@ ext4_move_extents(struct file *o_filp, s - - } - out: -+ if (*moved_len) { -+ ext4_discard_preallocations(orig_inode); -+ ext4_discard_preallocations(donor_inode); -+ } -+ - if (orig_path) { - ext4_ext_drop_refs(orig_path); - kfree(orig_path); diff --git a/queue-2.6.32/0018-ext4-initialize-moved_len-before-calling-ext4_move_e.patch b/queue-2.6.32/0018-ext4-initialize-moved_len-before-calling-ext4_move_e.patch deleted file mode 100644 index 3044e4c006b..00000000000 --- a/queue-2.6.32/0018-ext4-initialize-moved_len-before-calling-ext4_move_e.patch +++ /dev/null @@ -1,76 +0,0 @@ -From 4ba9bccde799430e634b6cda8614b13ccb24ef1a Mon Sep 17 00:00:00 2001 -From: Kazuya Mio -Date: Tue, 24 Nov 2009 10:28:48 -0500 -Subject: [PATCH 18/30] ext4: initialize moved_len before calling ext4_move_extents() - -(cherry picked from commit 446aaa6e7e993b38a6f21c6acfa68f3f1af3dbe3) - -The move_extent.moved_len is used to pass back the number of exchanged -blocks count to user space. Currently the caller must clear this -field; but we spend more code space checking for this requirement than -simply zeroing the field ourselves, so let's just make life easier for -everyone all around. - -Signed-off-by: Kazuya Mio -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/ioctl.c | 1 + - fs/ext4/move_extent.c | 14 +++----------- - 2 files changed, 4 insertions(+), 11 deletions(-) - ---- a/fs/ext4/ioctl.c -+++ b/fs/ext4/ioctl.c -@@ -239,6 +239,7 @@ setversion_out: - } - } - -+ me.moved_len = 0; - err = ext4_move_extents(filp, donor_filp, me.orig_start, - me.donor_start, me.len, &me.moved_len); - fput(donor_filp); ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -947,7 +947,6 @@ out2: - * @orig_start: logical start offset in block for orig - * @donor_start: logical start offset in block for donor - * @len: the number of blocks to be moved -- * @moved_len: moved block length - * - * Check the arguments of ext4_move_extents() whether the files can be - * exchanged with each other. -@@ -955,8 +954,8 @@ out2: - */ - static int - mext_check_arguments(struct inode *orig_inode, -- struct inode *donor_inode, __u64 orig_start, -- __u64 donor_start, __u64 *len, __u64 moved_len) -+ struct inode *donor_inode, __u64 orig_start, -+ __u64 donor_start, __u64 *len) - { - ext4_lblk_t orig_blocks, donor_blocks; - unsigned int blkbits = orig_inode->i_blkbits; -@@ -1010,13 +1009,6 @@ mext_check_arguments(struct inode *orig_ - return -EINVAL; - } - -- if (moved_len) { -- ext4_debug("ext4 move extent: moved_len should be 0 " -- "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino, -- donor_inode->i_ino); -- return -EINVAL; -- } -- - if ((orig_start > EXT_MAX_BLOCK) || - (donor_start > EXT_MAX_BLOCK) || - (*len > EXT_MAX_BLOCK) || -@@ -1226,7 +1218,7 @@ ext4_move_extents(struct file *o_filp, s - double_down_write_data_sem(orig_inode, donor_inode); - /* Check the filesystem environment whether move_extent can be done */ - ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start, -- donor_start, &len, *moved_len); -+ donor_start, &len); - if (ret1) - goto out; - diff --git a/queue-2.6.32/0019-ext4-move_extent_per_page-cleanup.patch b/queue-2.6.32/0019-ext4-move_extent_per_page-cleanup.patch deleted file mode 100644 index 89b9e5c3672..00000000000 --- a/queue-2.6.32/0019-ext4-move_extent_per_page-cleanup.patch +++ /dev/null @@ -1,91 +0,0 @@ -From 3aa949f17b315027f4ffb033bfe332cb35af5c3a Mon Sep 17 00:00:00 2001 -From: Akira Fujita -Date: Tue, 24 Nov 2009 10:31:56 -0500 -Subject: [PATCH 19/30] ext4: move_extent_per_page() cleanup - -(cherry picked from commit ac48b0a1d068887141581bea8285de5fcab182b0) - -Integrate duplicate lines (acquire/release semaphore and invalidate -extent cache in move_extent_per_page()) into mext_replace_branches(), -to reduce source and object code size. - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 30 +++++++++--------------------- - 1 file changed, 9 insertions(+), 21 deletions(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -660,6 +660,9 @@ mext_replace_branches(handle_t *handle, - int replaced_count = 0; - int dext_alen; - -+ /* Protect extent trees against block allocations via delalloc */ -+ double_down_write_data_sem(orig_inode, donor_inode); -+ - /* Get the original extent for the block "orig_off" */ - *err = get_ext_path(orig_inode, orig_off, &orig_path); - if (*err) -@@ -755,6 +758,11 @@ out: - kfree(donor_path); - } - -+ ext4_ext_invalidate_cache(orig_inode); -+ ext4_ext_invalidate_cache(donor_inode); -+ -+ double_up_write_data_sem(orig_inode, donor_inode); -+ - return replaced_count; - } - -@@ -820,19 +828,9 @@ move_extent_per_page(struct file *o_filp - * Just swap data blocks between orig and donor. - */ - if (uninit) { -- /* -- * Protect extent trees against block allocations -- * via delalloc -- */ -- double_down_write_data_sem(orig_inode, donor_inode); - replaced_count = mext_replace_branches(handle, orig_inode, - donor_inode, orig_blk_offset, - block_len_in_page, err); -- -- /* Clear the inode cache not to refer to the old data */ -- ext4_ext_invalidate_cache(orig_inode); -- ext4_ext_invalidate_cache(donor_inode); -- double_up_write_data_sem(orig_inode, donor_inode); - goto out2; - } - -@@ -880,8 +878,6 @@ move_extent_per_page(struct file *o_filp - /* Release old bh and drop refs */ - try_to_release_page(page, 0); - -- /* Protect extent trees against block allocations via delalloc */ -- double_down_write_data_sem(orig_inode, donor_inode); - replaced_count = mext_replace_branches(handle, orig_inode, donor_inode, - orig_blk_offset, block_len_in_page, - &err2); -@@ -890,18 +886,10 @@ move_extent_per_page(struct file *o_filp - block_len_in_page = replaced_count; - replaced_size = - block_len_in_page << orig_inode->i_blkbits; -- } else { -- double_up_write_data_sem(orig_inode, donor_inode); -+ } else - goto out; -- } - } - -- /* Clear the inode cache not to refer to the old data */ -- ext4_ext_invalidate_cache(orig_inode); -- ext4_ext_invalidate_cache(donor_inode); -- -- double_up_write_data_sem(orig_inode, donor_inode); -- - if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0); - diff --git a/queue-2.6.32/0020-jbd2-Add-ENOMEM-checking-in-and-for-jbd2_journal_wri.patch b/queue-2.6.32/0020-jbd2-Add-ENOMEM-checking-in-and-for-jbd2_journal_wri.patch deleted file mode 100644 index f3b5f4fe206..00000000000 --- a/queue-2.6.32/0020-jbd2-Add-ENOMEM-checking-in-and-for-jbd2_journal_wri.patch +++ /dev/null @@ -1,42 +0,0 @@ -From 9dd2722f839b69ede127875f490716cb137daa35 Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Tue, 1 Dec 2009 09:04:42 -0500 -Subject: [PATCH 20/30] jbd2: Add ENOMEM checking in and for jbd2_journal_write_metadata_buffer() - -(cherry picked from commit e6ec116b67f46e0e7808276476554727b2e6240b) - -OOM happens. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/jbd2/commit.c | 4 ++++ - fs/jbd2/journal.c | 4 ++++ - 2 files changed, 8 insertions(+) - ---- a/fs/jbd2/commit.c -+++ b/fs/jbd2/commit.c -@@ -636,6 +636,10 @@ void jbd2_journal_commit_transaction(jou - JBUFFER_TRACE(jh, "ph3: write metadata"); - flags = jbd2_journal_write_metadata_buffer(commit_transaction, - jh, &new_jh, blocknr); -+ if (flags < 0) { -+ jbd2_journal_abort(journal, flags); -+ continue; -+ } - set_bit(BH_JWrite, &jh2bh(new_jh)->b_state); - wbuf[bufs++] = jh2bh(new_jh); - ---- a/fs/jbd2/journal.c -+++ b/fs/jbd2/journal.c -@@ -358,6 +358,10 @@ repeat: - - jbd_unlock_bh_state(bh_in); - tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); -+ if (!tmp) { -+ jbd2_journal_put_journal_head(new_jh); -+ return -ENOMEM; -+ } - jbd_lock_bh_state(bh_in); - if (jh_in->b_frozen_data) { - jbd2_free(tmp, bh_in->b_size); diff --git a/queue-2.6.32/0021-ext4-Return-the-PTR_ERR-of-the-correct-pointer-in-se.patch b/queue-2.6.32/0021-ext4-Return-the-PTR_ERR-of-the-correct-pointer-in-se.patch deleted file mode 100644 index f96e6cfef86..00000000000 --- a/queue-2.6.32/0021-ext4-Return-the-PTR_ERR-of-the-correct-pointer-in-se.patch +++ /dev/null @@ -1,25 +0,0 @@ -From 67b269b65fa8620f2a5ba402f4bd49b286e00eb4 Mon Sep 17 00:00:00 2001 -From: Roel Kluin -Date: Mon, 7 Dec 2009 10:38:16 -0500 -Subject: [PATCH 21/30] ext4: Return the PTR_ERR of the correct pointer in setup_new_group_blocks() - -(cherry picked from commit c09eef305dd43846360944ad072f051f964fa383) - -Signed-off-by: Roel Kluin -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/resize.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/resize.c -+++ b/fs/ext4/resize.c -@@ -247,7 +247,7 @@ static int setup_new_group_blocks(struct - goto exit_bh; - - if (IS_ERR(gdb = bclean(handle, sb, block))) { -- err = PTR_ERR(bh); -+ err = PTR_ERR(gdb); - goto exit_bh; - } - ext4_handle_dirty_metadata(handle, NULL, gdb); diff --git a/queue-2.6.32/0022-ext4-Avoid-data-filesystem-corruption-when-write-fai.patch b/queue-2.6.32/0022-ext4-Avoid-data-filesystem-corruption-when-write-fai.patch deleted file mode 100644 index 740ad9cda32..00000000000 --- a/queue-2.6.32/0022-ext4-Avoid-data-filesystem-corruption-when-write-fai.patch +++ /dev/null @@ -1,88 +0,0 @@ -From 968c53cec156cb9a3239969a3686c33a0e5cc9ab Mon Sep 17 00:00:00 2001 -From: Jan Kara -Date: Tue, 8 Dec 2009 21:24:33 -0500 -Subject: [PATCH 22/30] ext4: Avoid data / filesystem corruption when write fails to copy data - -(cherry picked from commit b9a4207d5e911b938f73079a83cc2ae10524ec7f) - -When ext4_write_begin fails after allocating some blocks or -generic_perform_write fails to copy data to write, we truncate blocks -already instantiated beyond i_size. Although these blocks were never -inside i_size, we have to truncate the pagecache of these blocks so -that corresponding buffers get unmapped. Otherwise subsequent -__block_prepare_write (called because we are retrying the write) will -find the buffers mapped, not call ->get_block, and thus the page will -be backed by already freed blocks leading to filesystem and data -corruption. - -Signed-off-by: Jan Kara -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 20 +++++++++++++++----- - 1 file changed, 15 insertions(+), 5 deletions(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -1534,6 +1534,16 @@ static int do_journal_get_write_access(h - return ext4_journal_get_write_access(handle, bh); - } - -+/* -+ * Truncate blocks that were not used by write. We have to truncate the -+ * pagecache as well so that corresponding buffers get properly unmapped. -+ */ -+static void ext4_truncate_failed_write(struct inode *inode) -+{ -+ truncate_inode_pages(inode->i_mapping, inode->i_size); -+ ext4_truncate(inode); -+} -+ - static int ext4_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) -@@ -1599,7 +1609,7 @@ retry: - - ext4_journal_stop(handle); - if (pos + len > inode->i_size) { -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might - * still be on the orphan list; we need to -@@ -1709,7 +1719,7 @@ static int ext4_ordered_write_end(struct - ret = ret2; - - if (pos + len > inode->i_size) { -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might still be - * on the orphan list; we need to make sure the inode -@@ -1751,7 +1761,7 @@ static int ext4_writeback_write_end(stru - ret = ret2; - - if (pos + len > inode->i_size) { -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might still be - * on the orphan list; we need to make sure the inode -@@ -1814,7 +1824,7 @@ static int ext4_journalled_write_end(str - if (!ret) - ret = ret2; - if (pos + len > inode->i_size) { -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might still be - * on the orphan list; we need to make sure the inode -@@ -3091,7 +3101,7 @@ retry: - * i_size_read because we hold i_mutex. - */ - if (pos + len > inode->i_size) -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - } - - if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) diff --git a/queue-2.6.32/0023-ext4-wait-for-log-to-commit-when-umounting.patch b/queue-2.6.32/0023-ext4-wait-for-log-to-commit-when-umounting.patch deleted file mode 100644 index d1a9f6aaa81..00000000000 --- a/queue-2.6.32/0023-ext4-wait-for-log-to-commit-when-umounting.patch +++ /dev/null @@ -1,50 +0,0 @@ -From 2a51ce267e55720f32e089a0d5349d558263ea9a Mon Sep 17 00:00:00 2001 -From: Josef Bacik -Date: Tue, 8 Dec 2009 21:48:58 -0500 -Subject: [PATCH 23/30] ext4: wait for log to commit when umounting - -(cherry picked from commit d4edac314e9ad0b21ba20ba8bc61b61f186f79e1) - -There is a potential race when a transaction is committing right when -the file system is being umounting. This could reduce in a race -because EXT4_SB(sb)->s_group_info could be freed in ext4_put_super -before the commit code calls a callback so the mballoc code can -release freed blocks in the transaction, resulting in a panic trying -to access the freed s_group_info. - -The fix is to wait for the transaction to finish committing before we -shutdown the multiblock allocator. - -Signed-off-by: Josef Bacik -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/super.c | 10 ++++++---- - 1 file changed, 6 insertions(+), 4 deletions(-) - ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -603,10 +603,6 @@ static void ext4_put_super(struct super_ - if (sb->s_dirt) - ext4_commit_super(sb, 1); - -- ext4_release_system_zone(sb); -- ext4_mb_release(sb); -- ext4_ext_release(sb); -- ext4_xattr_put_super(sb); - if (sbi->s_journal) { - err = jbd2_journal_destroy(sbi->s_journal); - sbi->s_journal = NULL; -@@ -614,6 +610,12 @@ static void ext4_put_super(struct super_ - ext4_abort(sb, __func__, - "Couldn't clean up the journal"); - } -+ -+ ext4_release_system_zone(sb); -+ ext4_mb_release(sb); -+ ext4_ext_release(sb); -+ ext4_xattr_put_super(sb); -+ - if (!(sb->s_flags & MS_RDONLY)) { - EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - es->s_state = cpu_to_le16(sbi->s_mount_state); diff --git a/queue-2.6.32/0024-ext4-remove-blocks-from-inode-prealloc-list-on-failu.patch b/queue-2.6.32/0024-ext4-remove-blocks-from-inode-prealloc-list-on-failu.patch deleted file mode 100644 index 8804b02099e..00000000000 --- a/queue-2.6.32/0024-ext4-remove-blocks-from-inode-prealloc-list-on-failu.patch +++ /dev/null @@ -1,53 +0,0 @@ -From f76c3ee1ee414a64d953f59a3f23a23355c6a18c Mon Sep 17 00:00:00 2001 -From: Curt Wohlgemuth -Date: Tue, 8 Dec 2009 22:18:25 -0500 -Subject: [PATCH 24/30] ext4: remove blocks from inode prealloc list on failure - -(cherry picked from commit b844167edc7fcafda9623955c05e4c1b3c32ebc7) - -This fixes a leak of blocks in an inode prealloc list if device failures -cause ext4_mb_mark_diskspace_used() to fail. - -Signed-off-by: Curt Wohlgemuth -Acked-by: Aneesh Kumar K.V -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/mballoc.c | 19 +++++++++++++++++++ - 1 file changed, 19 insertions(+) - ---- a/fs/ext4/mballoc.c -+++ b/fs/ext4/mballoc.c -@@ -3011,6 +3011,24 @@ static void ext4_mb_collect_stats(struct - } - - /* -+ * Called on failure; free up any blocks from the inode PA for this -+ * context. We don't need this for MB_GROUP_PA because we only change -+ * pa_free in ext4_mb_release_context(), but on failure, we've already -+ * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed. -+ */ -+static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) -+{ -+ struct ext4_prealloc_space *pa = ac->ac_pa; -+ int len; -+ -+ if (pa && pa->pa_type == MB_INODE_PA) { -+ len = ac->ac_b_ex.fe_len; -+ pa->pa_free += len; -+ } -+ -+} -+ -+/* - * use blocks preallocated to inode - */ - static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, -@@ -4295,6 +4313,7 @@ repeat: - ac->ac_status = AC_STATUS_CONTINUE; - goto repeat; - } else if (*errp) { -+ ext4_discard_allocated_blocks(ac); - ac->ac_b_ex.fe_len = 0; - ar->len = 0; - ext4_mb_show_ac(ac); diff --git a/queue-2.6.32/0025-ext4-ext4_get_reserved_space-must-return-bytes-inste.patch b/queue-2.6.32/0025-ext4-ext4_get_reserved_space-must-return-bytes-inste.patch deleted file mode 100644 index 4bab5968806..00000000000 --- a/queue-2.6.32/0025-ext4-ext4_get_reserved_space-must-return-bytes-inste.patch +++ /dev/null @@ -1,27 +0,0 @@ -From 89f0a58e7cc53a31325b7409935c8b499ee9a5c9 Mon Sep 17 00:00:00 2001 -From: Dmitry Monakhov -Date: Tue, 8 Dec 2009 22:41:52 -0500 -Subject: [PATCH 25/30] ext4: ext4_get_reserved_space() must return bytes instead of blocks - -(cherry picked from commit 8aa6790f876e81f5a2211fe1711a5fe3fe2d7b20) - -Signed-off-by: Dmitry Monakhov -Reviewed-by: Eric Sandeen -Acked-by: Mingming Cao -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -1052,7 +1052,7 @@ qsize_t ext4_get_reserved_space(struct i - EXT4_I(inode)->i_reserved_meta_blocks; - spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); - -- return total; -+ return (total << inode->i_blkbits); - } - /* - * Calculate the number of metadata blocks need to reserve diff --git a/queue-2.6.32/0026-ext4-quota-macros-cleanup.patch b/queue-2.6.32/0026-ext4-quota-macros-cleanup.patch deleted file mode 100644 index 198b781a500..00000000000 --- a/queue-2.6.32/0026-ext4-quota-macros-cleanup.patch +++ /dev/null @@ -1,142 +0,0 @@ -From 02fa03eb498b59853433cfa40cd152f0f5419729 Mon Sep 17 00:00:00 2001 -From: Dmitry Monakhov -Date: Tue, 8 Dec 2009 22:42:15 -0500 -Subject: [PATCH 26/30] ext4: quota macros cleanup - -(cherry picked from commit 5aca07eb7d8f14d90c740834d15ca15277f4820c) - -Currently all quota block reservation macros contains hard-coded "2" -aka MAXQUOTAS value. This is no good because in some places it is not -obvious to understand what does this digit represent. Let's introduce -new macro with self descriptive name. - -Signed-off-by: Dmitry Monakhov -Acked-by: Mingming Cao -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/ext4_jbd2.h | 8 ++++++-- - fs/ext4/extents.c | 2 +- - fs/ext4/inode.c | 2 +- - fs/ext4/migrate.c | 4 ++-- - fs/ext4/namei.c | 8 ++++---- - 5 files changed, 14 insertions(+), 10 deletions(-) - ---- a/fs/ext4/ext4_jbd2.h -+++ b/fs/ext4/ext4_jbd2.h -@@ -49,7 +49,7 @@ - - #define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ - EXT4_XATTR_TRANS_BLOCKS - 2 + \ -- 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) -+ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) - - /* - * Define the number of metadata blocks we need to account to modify data. -@@ -57,7 +57,7 @@ - * This include super block, inode block, quota blocks and xattr blocks - */ - #define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \ -- 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) -+ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) - - /* Delete operations potentially hit one directory's namespace plus an - * entire inode, plus arbitrary amounts of bitmap/indirection data. Be -@@ -92,6 +92,7 @@ - * but inode, sb and group updates are done only once */ - #define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0) -+ - #define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0) - #else -@@ -99,6 +100,9 @@ - #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 - #define EXT4_QUOTA_DEL_BLOCKS(sb) 0 - #endif -+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb)) -+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) -+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) - - int - ext4_mark_iloc_dirty(handle_t *handle, ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -2167,7 +2167,7 @@ ext4_ext_rm_leaf(handle_t *handle, struc - correct_index = 1; - credits += (ext_depth(inode)) + 1; - } -- credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); -+ credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); - - err = ext4_ext_truncate_extend_restart(handle, inode, credits); - if (err) ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -5231,7 +5231,7 @@ int ext4_setattr(struct dentry *dentry, - - /* (user+group)*(old+new) structure, inode write (sb, - * inode block, ? - but truncate inode update has it) */ -- handle = ext4_journal_start(inode, 2*(EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)+ -+ handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+ - EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3); - if (IS_ERR(handle)) { - error = PTR_ERR(handle); ---- a/fs/ext4/migrate.c -+++ b/fs/ext4/migrate.c -@@ -238,7 +238,7 @@ static int extend_credit_for_blkdel(hand - * So allocate a credit of 3. We may update - * quota (user and group). - */ -- needed = 3 + 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); -+ needed = 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); - - if (ext4_journal_extend(handle, needed) != 0) - retval = ext4_journal_restart(handle, needed); -@@ -477,7 +477,7 @@ int ext4_ext_migrate(struct inode *inode - handle = ext4_journal_start(inode, - EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + -- 2 * EXT4_QUOTA_INIT_BLOCKS(inode->i_sb) -+ EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb) - + 1); - if (IS_ERR(handle)) { - retval = PTR_ERR(handle); ---- a/fs/ext4/namei.c -+++ b/fs/ext4/namei.c -@@ -1769,7 +1769,7 @@ static int ext4_create(struct inode *dir - retry: - handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + -- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); -+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - -@@ -1803,7 +1803,7 @@ static int ext4_mknod(struct inode *dir, - retry: - handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + -- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); -+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - -@@ -1840,7 +1840,7 @@ static int ext4_mkdir(struct inode *dir, - retry: - handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + -- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); -+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - -@@ -2253,7 +2253,7 @@ static int ext4_symlink(struct inode *di - retry: - handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 5 + -- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); -+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - diff --git a/queue-2.6.32/0027-ext4-fix-incorrect-block-reservation-on-quota-transf.patch b/queue-2.6.32/0027-ext4-fix-incorrect-block-reservation-on-quota-transf.patch deleted file mode 100644 index 07e6a61b035..00000000000 --- a/queue-2.6.32/0027-ext4-fix-incorrect-block-reservation-on-quota-transf.patch +++ /dev/null @@ -1,31 +0,0 @@ -From 57a4922aba632b8e4aff05f43ffb0b0d615b79ef Mon Sep 17 00:00:00 2001 -From: Dmitry Monakhov -Date: Tue, 8 Dec 2009 22:42:28 -0500 -Subject: [PATCH 27/30] ext4: fix incorrect block reservation on quota transfer. - -(cherry picked from commit 194074acacebc169ded90a4657193f5180015051) - -Inside ->setattr() call both ATTR_UID and ATTR_GID may be valid -This means that we may end-up with transferring all quotas. Add -we have to reserve QUOTA_DEL_BLOCKS for all quotas, as we do in -case of QUOTA_INIT_BLOCKS. - -Signed-off-by: Dmitry Monakhov -Reviewed-by: Mingming Cao -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -5232,7 +5232,7 @@ int ext4_setattr(struct dentry *dentry, - /* (user+group)*(old+new) structure, inode write (sb, - * inode block, ? - but truncate inode update has it) */ - handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+ -- EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3); -+ EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3); - if (IS_ERR(handle)) { - error = PTR_ERR(handle); - goto err_out; diff --git a/queue-2.6.32/0028-ext4-Wait-for-proper-transaction-commit-on-fsync.patch b/queue-2.6.32/0028-ext4-Wait-for-proper-transaction-commit-on-fsync.patch deleted file mode 100644 index 2569bb744c6..00000000000 --- a/queue-2.6.32/0028-ext4-Wait-for-proper-transaction-commit-on-fsync.patch +++ /dev/null @@ -1,256 +0,0 @@ -From ebe71d4fcb5cad29134efb77a36b11a546616104 Mon Sep 17 00:00:00 2001 -From: Jan Kara -Date: Tue, 8 Dec 2009 23:51:10 -0500 -Subject: [PATCH 28/30] ext4: Wait for proper transaction commit on fsync - -(cherry picked from commit b436b9bef84de6893e86346d8fbf7104bc520645) - -We cannot rely on buffer dirty bits during fsync because pdflush can come -before fsync is called and clear dirty bits without forcing a transaction -commit. What we do is that we track which transaction has last changed -the inode and which transaction last changed allocation and force it to -disk on fsync. - -Signed-off-by: Jan Kara -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/ext4.h | 7 +++++++ - fs/ext4/ext4_jbd2.h | 13 +++++++++++++ - fs/ext4/extents.c | 14 ++++++++++++-- - fs/ext4/fsync.c | 46 +++++++++++++++++----------------------------- - fs/ext4/inode.c | 29 +++++++++++++++++++++++++++++ - fs/ext4/super.c | 2 ++ - fs/jbd2/journal.c | 1 + - 7 files changed, 81 insertions(+), 31 deletions(-) - ---- a/fs/ext4/ext4.h -+++ b/fs/ext4/ext4.h -@@ -703,6 +703,13 @@ struct ext4_inode_info { - struct list_head i_aio_dio_complete_list; - /* current io_end structure for async DIO write*/ - ext4_io_end_t *cur_aio_dio; -+ -+ /* -+ * Transactions that contain inode's metadata needed to complete -+ * fsync and fdatasync, respectively. -+ */ -+ tid_t i_sync_tid; -+ tid_t i_datasync_tid; - }; - - /* ---- a/fs/ext4/ext4_jbd2.h -+++ b/fs/ext4/ext4_jbd2.h -@@ -258,6 +258,19 @@ static inline int ext4_jbd2_file_inode(h - return 0; - } - -+static inline void ext4_update_inode_fsync_trans(handle_t *handle, -+ struct inode *inode, -+ int datasync) -+{ -+ struct ext4_inode_info *ei = EXT4_I(inode); -+ -+ if (ext4_handle_valid(handle)) { -+ ei->i_sync_tid = handle->h_transaction->t_tid; -+ if (datasync) -+ ei->i_datasync_tid = handle->h_transaction->t_tid; -+ } -+} -+ - /* super.c */ - int ext4_force_commit(struct super_block *sb); - ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -3064,6 +3064,8 @@ ext4_ext_handle_uninitialized_extents(ha - if (flags == EXT4_GET_BLOCKS_DIO_CONVERT_EXT) { - ret = ext4_convert_unwritten_extents_dio(handle, inode, - path); -+ if (ret >= 0) -+ ext4_update_inode_fsync_trans(handle, inode, 1); - goto out2; - } - /* buffered IO case */ -@@ -3091,6 +3093,8 @@ ext4_ext_handle_uninitialized_extents(ha - ret = ext4_ext_convert_to_initialized(handle, inode, - path, iblock, - max_blocks); -+ if (ret >= 0) -+ ext4_update_inode_fsync_trans(handle, inode, 1); - out: - if (ret <= 0) { - err = ret; -@@ -3329,10 +3333,16 @@ int ext4_ext_get_blocks(handle_t *handle - allocated = ext4_ext_get_actual_len(&newex); - set_buffer_new(bh_result); - -- /* Cache only when it is _not_ an uninitialized extent */ -- if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) -+ /* -+ * Cache the extent and update transaction to commit on fdatasync only -+ * when it is _not_ an uninitialized extent. -+ */ -+ if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) { - ext4_ext_put_in_cache(inode, iblock, allocated, newblock, - EXT4_EXT_CACHE_EXTENT); -+ ext4_update_inode_fsync_trans(handle, inode, 1); -+ } else -+ ext4_update_inode_fsync_trans(handle, inode, 0); - out: - if (allocated > max_blocks) - allocated = max_blocks; ---- a/fs/ext4/fsync.c -+++ b/fs/ext4/fsync.c -@@ -51,25 +51,30 @@ - int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) - { - struct inode *inode = dentry->d_inode; -+ struct ext4_inode_info *ei = EXT4_I(inode); - journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; -- int err, ret = 0; -+ int ret; -+ tid_t commit_tid; - - J_ASSERT(ext4_journal_current_handle() == NULL); - - trace_ext4_sync_file(file, dentry, datasync); - -+ if (inode->i_sb->s_flags & MS_RDONLY) -+ return 0; -+ - ret = flush_aio_dio_completed_IO(inode); - if (ret < 0) - return ret; -+ -+ if (!journal) -+ return simple_fsync(file, dentry, datasync); -+ - /* -- * data=writeback: -+ * data=writeback,ordered: - * The caller's filemap_fdatawrite()/wait will sync the data. -- * sync_inode() will sync the metadata -- * -- * data=ordered: -- * The caller's filemap_fdatawrite() will write the data and -- * sync_inode() will write the inode if it is dirty. Then the caller's -- * filemap_fdatawait() will wait on the pages. -+ * Metadata is in the journal, we wait for proper transaction to -+ * commit here. - * - * data=journal: - * filemap_fdatawrite won't do anything (the buffers are clean). -@@ -82,27 +87,10 @@ int ext4_sync_file(struct file *file, st - if (ext4_should_journal_data(inode)) - return ext4_force_commit(inode->i_sb); - -- if (!journal) -- ret = sync_mapping_buffers(inode->i_mapping); -- -- if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) -- goto out; -- -- /* -- * The VFS has written the file data. If the inode is unaltered -- * then we need not start a commit. -- */ -- if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) { -- struct writeback_control wbc = { -- .sync_mode = WB_SYNC_ALL, -- .nr_to_write = 0, /* sys_fsync did this */ -- }; -- err = sync_inode(inode, &wbc); -- if (ret == 0) -- ret = err; -- } --out: -- if (journal && (journal->j_flags & JBD2_BARRIER)) -+ commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; -+ if (jbd2_log_start_commit(journal, commit_tid)) -+ jbd2_log_wait_commit(journal, commit_tid); -+ else if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); - return ret; - } ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -1025,6 +1025,8 @@ static int ext4_ind_get_blocks(handle_t - goto cleanup; - - set_buffer_new(bh_result); -+ -+ ext4_update_inode_fsync_trans(handle, inode, 1); - got_it: - map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key)); - if (count > blocks_to_boundary) -@@ -4794,6 +4796,7 @@ struct inode *ext4_iget(struct super_blo - struct ext4_inode *raw_inode; - struct ext4_inode_info *ei; - struct inode *inode; -+ journal_t *journal = EXT4_SB(sb)->s_journal; - long ret; - int block; - -@@ -4858,6 +4861,31 @@ struct inode *ext4_iget(struct super_blo - ei->i_data[block] = raw_inode->i_block[block]; - INIT_LIST_HEAD(&ei->i_orphan); - -+ /* -+ * Set transaction id's of transactions that have to be committed -+ * to finish f[data]sync. We set them to currently running transaction -+ * as we cannot be sure that the inode or some of its metadata isn't -+ * part of the transaction - the inode could have been reclaimed and -+ * now it is reread from disk. -+ */ -+ if (journal) { -+ transaction_t *transaction; -+ tid_t tid; -+ -+ spin_lock(&journal->j_state_lock); -+ if (journal->j_running_transaction) -+ transaction = journal->j_running_transaction; -+ else -+ transaction = journal->j_committing_transaction; -+ if (transaction) -+ tid = transaction->t_tid; -+ else -+ tid = journal->j_commit_sequence; -+ spin_unlock(&journal->j_state_lock); -+ ei->i_sync_tid = tid; -+ ei->i_datasync_tid = tid; -+ } -+ - if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { - ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); - if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > -@@ -5112,6 +5140,7 @@ static int ext4_do_update_inode(handle_t - err = rc; - ei->i_state &= ~EXT4_STATE_NEW; - -+ ext4_update_inode_fsync_trans(handle, inode, 0); - out_brelse: - brelse(bh); - ext4_std_error(inode->i_sb, err); ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -706,6 +706,8 @@ static struct inode *ext4_alloc_inode(st - spin_lock_init(&(ei->i_block_reservation_lock)); - INIT_LIST_HEAD(&ei->i_aio_dio_complete_list); - ei->cur_aio_dio = NULL; -+ ei->i_sync_tid = 0; -+ ei->i_datasync_tid = 0; - - return &ei->vfs_inode; - } ---- a/fs/jbd2/journal.c -+++ b/fs/jbd2/journal.c -@@ -78,6 +78,7 @@ EXPORT_SYMBOL(jbd2_journal_errno); - EXPORT_SYMBOL(jbd2_journal_ack_err); - EXPORT_SYMBOL(jbd2_journal_clear_err); - EXPORT_SYMBOL(jbd2_log_wait_commit); -+EXPORT_SYMBOL(jbd2_log_start_commit); - EXPORT_SYMBOL(jbd2_journal_start_commit); - EXPORT_SYMBOL(jbd2_journal_force_commit_nested); - EXPORT_SYMBOL(jbd2_journal_wipe); diff --git a/queue-2.6.32/0029-ext4-Fix-insufficient-checks-in-EXT4_IOC_MOVE_EXT.patch b/queue-2.6.32/0029-ext4-Fix-insufficient-checks-in-EXT4_IOC_MOVE_EXT.patch deleted file mode 100644 index c0468bf7ba8..00000000000 --- a/queue-2.6.32/0029-ext4-Fix-insufficient-checks-in-EXT4_IOC_MOVE_EXT.patch +++ /dev/null @@ -1,98 +0,0 @@ -From 10b526a22877a621d1c94d5efde29e3fea8214c2 Mon Sep 17 00:00:00 2001 -From: Akira Fujita -Date: Sun, 6 Dec 2009 23:38:31 -0500 -Subject: [PATCH 29/30] ext4: Fix insufficient checks in EXT4_IOC_MOVE_EXT - -(cherry picked from commit 4a58579b9e4e2a35d57e6c9c8483e52f6f1b7fd6) - -This patch fixes three problems in the handling of the -EXT4_IOC_MOVE_EXT ioctl: - -1. In current EXT4_IOC_MOVE_EXT, there are read access mode checks for -original and donor files, but they allow the illegal write access to -donor file, since donor file is overwritten by original file data. To -fix this problem, change access mode checks of original (r->r/w) and -donor (r->w) files. - -2. Disallow the use of donor files that have a setuid or setgid bits. - -3. Call mnt_want_write() and mnt_drop_write() before and after -ext4_move_extents() calling to get write access to a mount. - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/ioctl.c | 30 ++++++++++++++++++------------ - fs/ext4/move_extent.c | 7 +++++++ - 2 files changed, 25 insertions(+), 12 deletions(-) - ---- a/fs/ext4/ioctl.c -+++ b/fs/ext4/ioctl.c -@@ -221,32 +221,38 @@ setversion_out: - struct file *donor_filp; - int err; - -+ if (!(filp->f_mode & FMODE_READ) || -+ !(filp->f_mode & FMODE_WRITE)) -+ return -EBADF; -+ - if (copy_from_user(&me, - (struct move_extent __user *)arg, sizeof(me))) - return -EFAULT; -+ me.moved_len = 0; - - donor_filp = fget(me.donor_fd); - if (!donor_filp) - return -EBADF; - -- if (!capable(CAP_DAC_OVERRIDE)) { -- if ((current->real_cred->fsuid != inode->i_uid) || -- !(inode->i_mode & S_IRUSR) || -- !(donor_filp->f_dentry->d_inode->i_mode & -- S_IRUSR)) { -- fput(donor_filp); -- return -EACCES; -- } -+ if (!(donor_filp->f_mode & FMODE_WRITE)) { -+ err = -EBADF; -+ goto mext_out; - } - -- me.moved_len = 0; -+ err = mnt_want_write(filp->f_path.mnt); -+ if (err) -+ goto mext_out; -+ - err = ext4_move_extents(filp, donor_filp, me.orig_start, - me.donor_start, me.len, &me.moved_len); -- fput(donor_filp); -+ mnt_drop_write(filp->f_path.mnt); -+ if (me.moved_len > 0) -+ file_remove_suid(donor_filp); - - if (copy_to_user((struct move_extent *)arg, &me, sizeof(me))) -- return -EFAULT; -- -+ err = -EFAULT; -+mext_out: -+ fput(donor_filp); - return err; - } - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -957,6 +957,13 @@ mext_check_arguments(struct inode *orig_ - return -EINVAL; - } - -+ if (donor_inode->i_mode & (S_ISUID|S_ISGID)) { -+ ext4_debug("ext4 move extent: suid or sgid is set" -+ " to donor file [ino:orig %lu, donor %lu]\n", -+ orig_inode->i_ino, donor_inode->i_ino); -+ return -EINVAL; -+ } -+ - /* Ext4 move extent does not support swapfile */ - if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) { - ext4_debug("ext4 move extent: The argument files should " diff --git a/queue-2.6.32/0030-ext4-Fix-potential-fiemap-deadlock-mmap_sem-vs.-i_da.patch b/queue-2.6.32/0030-ext4-Fix-potential-fiemap-deadlock-mmap_sem-vs.-i_da.patch deleted file mode 100644 index ebc999aafa7..00000000000 --- a/queue-2.6.32/0030-ext4-Fix-potential-fiemap-deadlock-mmap_sem-vs.-i_da.patch +++ /dev/null @@ -1,119 +0,0 @@ -From 2b26b6f696ad26ae401c395491bd0f7a4611c093 Mon Sep 17 00:00:00 2001 -From: Theodore Ts'o -Date: Wed, 9 Dec 2009 21:30:02 -0500 -Subject: [PATCH 30/30] ext4: Fix potential fiemap deadlock (mmap_sem vs. i_data_sem) - -(cherry picked from commit fab3a549e204172236779f502eccb4f9bf0dc87d) - -Fix the following potential circular locking dependency between -mm->mmap_sem and ei->i_data_sem: - - ======================================================= - [ INFO: possible circular locking dependency detected ] - 2.6.32-04115-gec044c5 #37 - ------------------------------------------------------- - ureadahead/1855 is trying to acquire lock: - (&mm->mmap_sem){++++++}, at: [] might_fault+0x5c/0xac - - but task is already holding lock: - (&ei->i_data_sem){++++..}, at: [] ext4_fiemap+0x11b/0x159 - - which lock already depends on the new lock. - - the existing dependency chain (in reverse order) is: - - -> #1 (&ei->i_data_sem){++++..}: - [] __lock_acquire+0xb67/0xd0f - [] lock_acquire+0xdc/0x102 - [] down_read+0x51/0x84 - [] ext4_get_blocks+0x50/0x2a5 - [] ext4_get_block+0xab/0xef - [] do_mpage_readpage+0x198/0x48d - [] mpage_readpages+0xd0/0x114 - [] ext4_readpages+0x1d/0x1f - [] __do_page_cache_readahead+0x12f/0x1bc - [] ra_submit+0x21/0x25 - [] filemap_fault+0x19f/0x32c - [] __do_fault+0x55/0x3a2 - [] handle_mm_fault+0x327/0x734 - [] do_page_fault+0x292/0x2aa - [] page_fault+0x25/0x30 - [] clear_user+0x38/0x3c - [] padzero+0x20/0x31 - [] load_elf_binary+0x8bc/0x17ed - [] search_binary_handler+0xc2/0x259 - [] load_script+0x1b8/0x1cc - [] search_binary_handler+0xc2/0x259 - [] do_execve+0x1ce/0x2cf - [] sys_execve+0x43/0x5a - [] stub_execve+0x6a/0xc0 - - -> #0 (&mm->mmap_sem){++++++}: - [] __lock_acquire+0xa11/0xd0f - [] lock_acquire+0xdc/0x102 - [] might_fault+0x89/0xac - [] fiemap_fill_next_extent+0x95/0xda - [] ext4_ext_fiemap_cb+0x138/0x157 - [] ext4_ext_walk_space+0x178/0x1f1 - [] ext4_fiemap+0x13c/0x159 - [] do_vfs_ioctl+0x348/0x4d6 - [] sys_ioctl+0x56/0x79 - [] system_call_fastpath+0x16/0x1b - - other info that might help us debug this: - - 1 lock held by ureadahead/1855: - #0: (&ei->i_data_sem){++++..}, at: [] ext4_fiemap+0x11b/0x159 - - stack backtrace: - Pid: 1855, comm: ureadahead Not tainted 2.6.32-04115-gec044c5 #37 - Call Trace: - [] print_circular_bug+0xa8/0xb7 - [] __lock_acquire+0xa11/0xd0f - [] ? sched_clock+0x9/0xd - [] lock_acquire+0xdc/0x102 - [] ? might_fault+0x5c/0xac - [] might_fault+0x89/0xac - [] ? might_fault+0x5c/0xac - [] ? __kmalloc+0x13b/0x18c - [] fiemap_fill_next_extent+0x95/0xda - [] ext4_ext_fiemap_cb+0x138/0x157 - [] ? ext4_ext_fiemap_cb+0x0/0x157 - [] ext4_ext_walk_space+0x178/0x1f1 - [] ext4_fiemap+0x13c/0x159 - [] ? might_fault+0x5c/0xac - [] do_vfs_ioctl+0x348/0x4d6 - [] ? __up_read+0x8d/0x95 - [] ? retint_swapgs+0x13/0x1b - [] sys_ioctl+0x56/0x79 - [] system_call_fastpath+0x16/0x1b - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/extents.c | 4 ++-- - 1 file changed, 2 insertions(+), 2 deletions(-) - ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -1761,7 +1761,9 @@ int ext4_ext_walk_space(struct inode *in - while (block < last && block != EXT_MAX_BLOCK) { - num = last - block; - /* find extent for this block */ -+ down_read(&EXT4_I(inode)->i_data_sem); - path = ext4_ext_find_extent(inode, block, path); -+ up_read(&EXT4_I(inode)->i_data_sem); - if (IS_ERR(path)) { - err = PTR_ERR(path); - path = NULL; -@@ -3730,10 +3732,8 @@ int ext4_fiemap(struct inode *inode, str - * Walk the extent tree gathering extent information. - * ext4_ext_fiemap_cb will push extents back to user. - */ -- down_read(&EXT4_I(inode)->i_data_sem); - error = ext4_ext_walk_space(inode, start_blk, len_blks, - ext4_ext_fiemap_cb, fieinfo); -- up_read(&EXT4_I(inode)->i_data_sem); - } - - return error; diff --git a/queue-2.6.32/mbox b/queue-2.6.32/mbox deleted file mode 100644 index 27686e482df..00000000000 --- a/queue-2.6.32/mbox +++ /dev/null @@ -1,3730 +0,0 @@ -From linux@linux.site Thu Dec 10 21:25:40 2009 -Message-Id: <20091211052540.442199443@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:13 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Sebastian Andrzej Siewior , - Oleg Nesterov , - Roland McGrath , - Kyle McMartin , - Thomas Gleixner , - Greg Kroah-Hartman -Subject: [01/34] signal: Fix alternate signal stack check -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=signal-fix-alternate-signal-stack-check.patch -Content-Length: 2919 -Lines: 83 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -From: Sebastian Andrzej Siewior - -commit 2a855dd01bc1539111adb7233f587c5c468732ac upstream. - -All architectures in the kernel increment/decrement the stack pointer -before storing values on the stack. - -On architectures which have the stack grow down sas_ss_sp == sp is not -on the alternate signal stack while sas_ss_sp + sas_ss_size == sp is -on the alternate signal stack. - -On architectures which have the stack grow up sas_ss_sp == sp is on -the alternate signal stack while sas_ss_sp + sas_ss_size == sp is not -on the alternate signal stack. - -The current implementation fails for architectures which have the -stack grow down on the corner case where sas_ss_sp == sp.This was -reported as Debian bug #544905 on AMD64. -Simplified test case: http://download.breakpoint.cc/tc-sig-stack.c - -The test case creates the following stack scenario: - 0xn0300 stack top - 0xn0200 alt stack pointer top (when switching to alt stack) - 0xn01ff alt stack end - 0xn0100 alt stack start == stack pointer - -If the signal is sent the stack pointer is pointing to the base -address of the alt stack and the kernel erroneously decides that it -has already switched to the alternate stack because of the current -check for "sp - sas_ss_sp < sas_ss_size" - -On parisc (stack grows up) the scenario would be: - 0xn0200 stack pointer - 0xn01ff alt stack end - 0xn0100 alt stack start = alt stack pointer base - (when switching to alt stack) - 0xn0000 stack base - -This is handled correctly by the current implementation. - -[ tglx: Modified for archs which have the stack grow up (parisc) which - would fail with the correct implementation for stack grows - down. Added a check for sp >= current->sas_ss_sp which is - strictly not necessary but makes the code symetric for both - variants ] - -Signed-off-by: Sebastian Andrzej Siewior -Cc: Oleg Nesterov -Cc: Roland McGrath -Cc: Kyle McMartin -LKML-Reference: <20091025143758.GA6653@Chamillionaire.breakpoint.cc> -Signed-off-by: Thomas Gleixner -Signed-off-by: Greg Kroah-Hartman - ---- - include/linux/sched.h | 13 ++++++++++--- - 1 file changed, 10 insertions(+), 3 deletions(-) - ---- a/include/linux/sched.h -+++ b/include/linux/sched.h -@@ -2086,11 +2086,18 @@ static inline int is_si_special(const st - return info <= SEND_SIG_FORCED; - } - --/* True if we are on the alternate signal stack. */ -- -+/* -+ * True if we are on the alternate signal stack. -+ */ - static inline int on_sig_stack(unsigned long sp) - { -- return (sp - current->sas_ss_sp < current->sas_ss_size); -+#ifdef CONFIG_STACK_GROWSUP -+ return sp >= current->sas_ss_sp && -+ sp - current->sas_ss_sp < current->sas_ss_size; -+#else -+ return sp > current->sas_ss_sp && -+ sp - current->sas_ss_sp <= current->sas_ss_size; -+#endif - } - - static inline int sas_ss_flags(unsigned long sp) - - -From linux@linux.site Thu Dec 10 21:25:41 2009 -Message-Id: <20091211052540.941627509@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:14 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - James Smart , - James Bottomley , - Greg Kroah-Hartman -Subject: [02/34] SCSI: scsi_lib_dma: fix bug with dma maps on nested scsi objects -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=scsi-scsi_lib_dma-fix-bug-with-dma-maps-on-nested-scsi-objects.patch -Content-Length: 5210 -Lines: 149 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -From: James Bottomley - -commit d139b9bd0e52dda14fd13412e7096e68b56d0076 upstream. - -Some of our virtual SCSI hosts don't have a proper bus parent at the -top, which can be a problem for doing DMA on them - -This patch makes the host device cache a pointer to the physical bus -device and provides an extra API for setting it (the normal API picks -it up from the parent). This patch also modifies the qla2xxx and lpfc -vport logic to use the new DMA host setting API. - -Acked-By: James Smart -Signed-off-by: James Bottomley -Signed-off-by: Greg Kroah-Hartman - ---- - drivers/scsi/hosts.c | 13 ++++++++++--- - drivers/scsi/lpfc/lpfc_init.c | 2 +- - drivers/scsi/qla2xxx/qla_attr.c | 3 ++- - drivers/scsi/scsi_lib_dma.c | 4 ++-- - include/scsi/scsi_host.h | 16 +++++++++++++++- - 5 files changed, 30 insertions(+), 8 deletions(-) - ---- a/drivers/scsi/hosts.c -+++ b/drivers/scsi/hosts.c -@@ -180,14 +180,20 @@ void scsi_remove_host(struct Scsi_Host * - EXPORT_SYMBOL(scsi_remove_host); - - /** -- * scsi_add_host - add a scsi host -+ * scsi_add_host_with_dma - add a scsi host with dma device - * @shost: scsi host pointer to add - * @dev: a struct device of type scsi class -+ * @dma_dev: dma device for the host -+ * -+ * Note: You rarely need to worry about this unless you're in a -+ * virtualised host environments, so use the simpler scsi_add_host() -+ * function instead. - * - * Return value: - * 0 on success / != 0 for error - **/ --int scsi_add_host(struct Scsi_Host *shost, struct device *dev) -+int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, -+ struct device *dma_dev) - { - struct scsi_host_template *sht = shost->hostt; - int error = -EINVAL; -@@ -207,6 +213,7 @@ int scsi_add_host(struct Scsi_Host *shos - - if (!shost->shost_gendev.parent) - shost->shost_gendev.parent = dev ? dev : &platform_bus; -+ shost->dma_dev = dma_dev; - - error = device_add(&shost->shost_gendev); - if (error) -@@ -262,7 +269,7 @@ int scsi_add_host(struct Scsi_Host *shos - fail: - return error; - } --EXPORT_SYMBOL(scsi_add_host); -+EXPORT_SYMBOL(scsi_add_host_with_dma); - - static void scsi_host_dev_release(struct device *dev) - { ---- a/drivers/scsi/lpfc/lpfc_init.c -+++ b/drivers/scsi/lpfc/lpfc_init.c -@@ -2408,7 +2408,7 @@ lpfc_create_port(struct lpfc_hba *phba, - vport->els_tmofunc.function = lpfc_els_timeout; - vport->els_tmofunc.data = (unsigned long)vport; - -- error = scsi_add_host(shost, dev); -+ error = scsi_add_host_with_dma(shost, dev, &phba->pcidev->dev); - if (error) - goto out_put_shost; - ---- a/drivers/scsi/qla2xxx/qla_attr.c -+++ b/drivers/scsi/qla2xxx/qla_attr.c -@@ -1654,7 +1654,8 @@ qla24xx_vport_create(struct fc_vport *fc - fc_vport_set_state(fc_vport, FC_VPORT_LINKDOWN); - } - -- if (scsi_add_host(vha->host, &fc_vport->dev)) { -+ if (scsi_add_host_with_dma(vha->host, &fc_vport->dev, -+ &ha->pdev->dev)) { - DEBUG15(printk("scsi(%ld): scsi_add_host failure for VP[%d].\n", - vha->host_no, vha->vp_idx)); - goto vport_create_failed_2; ---- a/drivers/scsi/scsi_lib_dma.c -+++ b/drivers/scsi/scsi_lib_dma.c -@@ -23,7 +23,7 @@ int scsi_dma_map(struct scsi_cmnd *cmd) - int nseg = 0; - - if (scsi_sg_count(cmd)) { -- struct device *dev = cmd->device->host->shost_gendev.parent; -+ struct device *dev = cmd->device->host->dma_dev; - - nseg = dma_map_sg(dev, scsi_sglist(cmd), scsi_sg_count(cmd), - cmd->sc_data_direction); -@@ -41,7 +41,7 @@ EXPORT_SYMBOL(scsi_dma_map); - void scsi_dma_unmap(struct scsi_cmnd *cmd) - { - if (scsi_sg_count(cmd)) { -- struct device *dev = cmd->device->host->shost_gendev.parent; -+ struct device *dev = cmd->device->host->dma_dev; - - dma_unmap_sg(dev, scsi_sglist(cmd), scsi_sg_count(cmd), - cmd->sc_data_direction); ---- a/include/scsi/scsi_host.h -+++ b/include/scsi/scsi_host.h -@@ -677,6 +677,12 @@ struct Scsi_Host { - void *shost_data; - - /* -+ * Points to the physical bus device we'd use to do DMA -+ * Needed just in case we have virtual hosts. -+ */ -+ struct device *dma_dev; -+ -+ /* - * We should ensure that this is aligned, both for better performance - * and also because some compilers (m68k) don't automatically force - * alignment to a long boundary. -@@ -720,7 +726,9 @@ extern int scsi_queue_work(struct Scsi_H - extern void scsi_flush_work(struct Scsi_Host *); - - extern struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *, int); --extern int __must_check scsi_add_host(struct Scsi_Host *, struct device *); -+extern int __must_check scsi_add_host_with_dma(struct Scsi_Host *, -+ struct device *, -+ struct device *); - extern void scsi_scan_host(struct Scsi_Host *); - extern void scsi_rescan_device(struct device *); - extern void scsi_remove_host(struct Scsi_Host *); -@@ -731,6 +739,12 @@ extern const char *scsi_host_state_name( - - extern u64 scsi_calculate_bounce_limit(struct Scsi_Host *); - -+static inline int __must_check scsi_add_host(struct Scsi_Host *host, -+ struct device *dev) -+{ -+ return scsi_add_host_with_dma(host, dev, dev); -+} -+ - static inline struct device *scsi_get_device(struct Scsi_Host *shost) - { - return shost->shost_gendev.parent; - - -From linux@linux.site Thu Dec 10 21:25:42 2009 -Message-Id: <20091211052541.550415868@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:15 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Martin Michlmayr , - Boaz Harrosh , - James Bottomley , - Greg Kroah-Hartman -Subject: [03/34] SCSI: osd_protocol.h: Add missing #include -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=scsi-osd_protocol.h-add-missing-include.patch -Content-Length: 708 -Lines: 24 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -From: Martin Michlmayr - -commit 0899638688f223fd9e9fee60d662665e11693d12 upstream. - -include/scsi/osd_protocol.h uses ALIGN() without an #include -, leading to: -| include/scsi/osd_protocol.h:362: error: implicit declaration of function 'ALIGN' - -Signed-off-by: Martin Michlmayr -Signed-off-by: Boaz Harrosh -Signed-off-by: James Bottomley -Signed-off-by: Greg Kroah-Hartman - ---- a/include/scsi/osd_protocol.h -+++ b/include/scsi/osd_protocol.h -@@ -17,6 +17,7 @@ - #define __OSD_PROTOCOL_H__ - - #include -+#include - #include - #include - - - -From linux@linux.site Thu Dec 10 21:25:42 2009 -Message-Id: <20091211052542.045664905@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:16 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - James Bottomley , - Greg Kroah-Hartman -Subject: [04/34] SCSI: megaraid_sas: fix 64 bit sense pointer truncation -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=scsi-megaraid_sas-fix-64-bit-sense-pointer-truncation.patch -Content-Length: 1456 -Lines: 47 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -From: Yang, Bo - -commit 7b2519afa1abd1b9f63aa1e90879307842422dae upstream. - -The current sense pointer is cast to a u32 pointer, which can truncate -on 64 bits. Fix by using unsigned long instead. - -Signed-off-by Bo Yang -Signed-off-by: James Bottomley -Signed-off-by: Greg Kroah-Hartman - ---- - drivers/scsi/megaraid/megaraid_sas.c | 8 ++++---- - 1 file changed, 4 insertions(+), 4 deletions(-) - ---- a/drivers/scsi/megaraid/megaraid_sas.c -+++ b/drivers/scsi/megaraid/megaraid_sas.c -@@ -3032,7 +3032,7 @@ megasas_mgmt_fw_ioctl(struct megasas_ins - int error = 0, i; - void *sense = NULL; - dma_addr_t sense_handle; -- u32 *sense_ptr; -+ unsigned long *sense_ptr; - - memset(kbuff_arr, 0, sizeof(kbuff_arr)); - -@@ -3109,7 +3109,7 @@ megasas_mgmt_fw_ioctl(struct megasas_ins - } - - sense_ptr = -- (u32 *) ((unsigned long)cmd->frame + ioc->sense_off); -+ (unsigned long *) ((unsigned long)cmd->frame + ioc->sense_off); - *sense_ptr = sense_handle; - } - -@@ -3140,8 +3140,8 @@ megasas_mgmt_fw_ioctl(struct megasas_ins - * sense_ptr points to the location that has the user - * sense buffer address - */ -- sense_ptr = (u32 *) ((unsigned long)ioc->frame.raw + -- ioc->sense_off); -+ sense_ptr = (unsigned long *) ((unsigned long)ioc->frame.raw + -+ ioc->sense_off); - - if (copy_to_user((void __user *)((unsigned long)(*sense_ptr)), - sense, ioc->sense_len)) { - - -From linux@linux.site Thu Dec 10 21:25:43 2009 -Message-Id: <20091211052542.664737460@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:17 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Curt Wohlgemuth , - Greg Kroah-Hartman -Subject: [05/34] ext4: fix potential buffer head leak when add_dirent_to_buf() returns ENOSPC -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0001-ext4-fix-potential-buffer-head-leak-when-add_dirent_.patch -Content-Length: 3833 -Lines: 118 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 2de770a406b06dfc619faabbf5d85c835ed3f2e1) - -Previously add_dirent_to_buf() did not free its passed-in buffer head -in the case of ENOSPC, since in some cases the caller still needed it. -However, this led to potential buffer head leaks since not all callers -dealt with this correctly. Fix this by making simplifying the freeing -convention; now add_dirent_to_buf() *never* frees the passed-in buffer -head, and leaves that to the responsibility of its caller. This makes -things cleaner and easier to prove that the code is neither leaking -buffer heads or calling brelse() one time too many. - -Signed-off-by: "Theodore Ts'o" -Cc: Curt Wohlgemuth -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/namei.c | 30 ++++++++++++------------------ - 1 file changed, 12 insertions(+), 18 deletions(-) - ---- a/fs/ext4/namei.c -+++ b/fs/ext4/namei.c -@@ -1292,9 +1292,6 @@ errout: - * add_dirent_to_buf will attempt search the directory block for - * space. It will return -ENOSPC if no space is available, and -EIO - * and -EEXIST if directory entry already exists. -- * -- * NOTE! bh is NOT released in the case where ENOSPC is returned. In -- * all other cases bh is released. - */ - static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, - struct inode *inode, struct ext4_dir_entry_2 *de, -@@ -1315,14 +1312,10 @@ static int add_dirent_to_buf(handle_t *h - top = bh->b_data + blocksize - reclen; - while ((char *) de <= top) { - if (!ext4_check_dir_entry("ext4_add_entry", dir, de, -- bh, offset)) { -- brelse(bh); -+ bh, offset)) - return -EIO; -- } -- if (ext4_match(namelen, name, de)) { -- brelse(bh); -+ if (ext4_match(namelen, name, de)) - return -EEXIST; -- } - nlen = EXT4_DIR_REC_LEN(de->name_len); - rlen = ext4_rec_len_from_disk(de->rec_len, blocksize); - if ((de->inode? rlen - nlen: rlen) >= reclen) -@@ -1337,7 +1330,6 @@ static int add_dirent_to_buf(handle_t *h - err = ext4_journal_get_write_access(handle, bh); - if (err) { - ext4_std_error(dir->i_sb, err); -- brelse(bh); - return err; - } - -@@ -1377,7 +1369,6 @@ static int add_dirent_to_buf(handle_t *h - err = ext4_handle_dirty_metadata(handle, dir, bh); - if (err) - ext4_std_error(dir->i_sb, err); -- brelse(bh); - return 0; - } - -@@ -1471,7 +1462,9 @@ static int make_indexed_dir(handle_t *ha - if (!(de)) - return retval; - -- return add_dirent_to_buf(handle, dentry, inode, de, bh); -+ retval = add_dirent_to_buf(handle, dentry, inode, de, bh); -+ brelse(bh); -+ return retval; - } - - /* -@@ -1514,8 +1507,10 @@ static int ext4_add_entry(handle_t *hand - if(!bh) - return retval; - retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh); -- if (retval != -ENOSPC) -+ if (retval != -ENOSPC) { -+ brelse(bh); - return retval; -+ } - - if (blocks == 1 && !dx_fallback && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) -@@ -1528,7 +1523,9 @@ static int ext4_add_entry(handle_t *hand - de = (struct ext4_dir_entry_2 *) bh->b_data; - de->inode = 0; - de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize); -- return add_dirent_to_buf(handle, dentry, inode, de, bh); -+ retval = add_dirent_to_buf(handle, dentry, inode, de, bh); -+ brelse(bh); -+ return retval; - } - - /* -@@ -1561,10 +1558,8 @@ static int ext4_dx_add_entry(handle_t *h - goto journal_error; - - err = add_dirent_to_buf(handle, dentry, inode, NULL, bh); -- if (err != -ENOSPC) { -- bh = NULL; -+ if (err != -ENOSPC) - goto cleanup; -- } - - /* Block full, should compress but for now just split */ - dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n", -@@ -1657,7 +1652,6 @@ static int ext4_dx_add_entry(handle_t *h - if (!de) - goto cleanup; - err = add_dirent_to_buf(handle, dentry, inode, de, bh); -- bh = NULL; - goto cleanup; - - journal_error: - - -From linux@linux.site Thu Dec 10 21:25:43 2009 -Message-Id: <20091211052543.277851362@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:18 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [06/34] ext4: avoid divide by zero when trying to mount a corrupted file system -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0002-ext4-avoid-divide-by-zero-when-trying-to-mount-a-cor.patch -Content-Length: 1267 -Lines: 39 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 503358ae01b70ce6909d19dd01287093f6b6271c) - -If s_log_groups_per_flex is greater than 31, then groups_per_flex will -will overflow and cause a divide by zero error. This can cause kernel -BUG if such a file system is mounted. - -Thanks to Nageswara R Sastry for analyzing the failure and providing -an initial patch. - -http://bugzilla.kernel.org/show_bug.cgi?id=14287 - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/super.c | 8 ++++---- - 1 file changed, 4 insertions(+), 4 deletions(-) - ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -1673,14 +1673,14 @@ static int ext4_fill_flex_info(struct su - size_t size; - int i; - -- if (!sbi->s_es->s_log_groups_per_flex) { -+ sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; -+ groups_per_flex = 1 << sbi->s_log_groups_per_flex; -+ -+ if (groups_per_flex < 2) { - sbi->s_log_groups_per_flex = 0; - return 1; - } - -- sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; -- groups_per_flex = 1 << sbi->s_log_groups_per_flex; -- - /* We allocate both existing and potentially added groups */ - flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) + - ((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) << - - -From linux@linux.site Thu Dec 10 21:25:44 2009 -Message-Id: <20091211052543.772152436@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:19 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Akira Fujita , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [07/34] ext4: fix the returned block count if EXT4_IOC_MOVE_EXT fails -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0003-ext4-fix-the-returned-block-count-if-EXT4_IOC_MOVE_E.patch -Content-Length: 10970 -Lines: 349 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit f868a48d06f8886cb0367568a12367fa4f21ea0d) - -If the EXT4_IOC_MOVE_EXT ioctl fails, the number of blocks that were -exchanged before the failure should be returned to the userspace -caller. Unfortunately, currently if the block size is not the same as -the page size, the returned block count that is returned is the -page-aligned block count instead of the actual block count. This -commit addresses this bug. - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 139 ++++++++++++++++++++++++++------------------------ - 1 file changed, 73 insertions(+), 66 deletions(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -661,6 +661,7 @@ mext_calc_swap_extents(struct ext4_exten - * @donor_inode: donor inode - * @from: block offset of orig_inode - * @count: block count to be replaced -+ * @err: pointer to save return value - * - * Replace original inode extents and donor inode extents page by page. - * We implement this replacement in the following three steps: -@@ -671,19 +672,18 @@ mext_calc_swap_extents(struct ext4_exten - * 3. Change the block information of donor inode to point at the saved - * original inode blocks in the dummy extents. - * -- * Return 0 on success, or a negative error value on failure. -+ * Return replaced block count. - */ - static int - mext_replace_branches(handle_t *handle, struct inode *orig_inode, - struct inode *donor_inode, ext4_lblk_t from, -- ext4_lblk_t count) -+ ext4_lblk_t count, int *err) - { - struct ext4_ext_path *orig_path = NULL; - struct ext4_ext_path *donor_path = NULL; - struct ext4_extent *oext, *dext; - struct ext4_extent tmp_dext, tmp_oext; - ext4_lblk_t orig_off = from, donor_off = from; -- int err = 0; - int depth; - int replaced_count = 0; - int dext_alen; -@@ -691,13 +691,13 @@ mext_replace_branches(handle_t *handle, - mext_double_down_write(orig_inode, donor_inode); - - /* Get the original extent for the block "orig_off" */ -- err = get_ext_path(orig_inode, orig_off, &orig_path); -- if (err) -+ *err = get_ext_path(orig_inode, orig_off, &orig_path); -+ if (*err) - goto out; - - /* Get the donor extent for the head */ -- err = get_ext_path(donor_inode, donor_off, &donor_path); -- if (err) -+ *err = get_ext_path(donor_inode, donor_off, &donor_path); -+ if (*err) - goto out; - depth = ext_depth(orig_inode); - oext = orig_path[depth].p_ext; -@@ -707,9 +707,9 @@ mext_replace_branches(handle_t *handle, - dext = donor_path[depth].p_ext; - tmp_dext = *dext; - -- err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, -+ *err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, - donor_off, count); -- if (err) -+ if (*err) - goto out; - - /* Loop for the donor extents */ -@@ -718,7 +718,7 @@ mext_replace_branches(handle_t *handle, - if (!dext) { - ext4_error(donor_inode->i_sb, __func__, - "The extent for donor must be found"); -- err = -EIO; -+ *err = -EIO; - goto out; - } else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) { - ext4_error(donor_inode->i_sb, __func__, -@@ -726,20 +726,20 @@ mext_replace_branches(handle_t *handle, - "extent(%u) should be equal", - donor_off, - le32_to_cpu(tmp_dext.ee_block)); -- err = -EIO; -+ *err = -EIO; - goto out; - } - - /* Set donor extent to orig extent */ -- err = mext_leaf_block(handle, orig_inode, -+ *err = mext_leaf_block(handle, orig_inode, - orig_path, &tmp_dext, &orig_off); -- if (err < 0) -+ if (*err) - goto out; - - /* Set orig extent to donor extent */ -- err = mext_leaf_block(handle, donor_inode, -+ *err = mext_leaf_block(handle, donor_inode, - donor_path, &tmp_oext, &donor_off); -- if (err < 0) -+ if (*err) - goto out; - - dext_alen = ext4_ext_get_actual_len(&tmp_dext); -@@ -753,35 +753,25 @@ mext_replace_branches(handle_t *handle, - - if (orig_path) - ext4_ext_drop_refs(orig_path); -- err = get_ext_path(orig_inode, orig_off, &orig_path); -- if (err) -+ *err = get_ext_path(orig_inode, orig_off, &orig_path); -+ if (*err) - goto out; - depth = ext_depth(orig_inode); - oext = orig_path[depth].p_ext; -- if (le32_to_cpu(oext->ee_block) + -- ext4_ext_get_actual_len(oext) <= orig_off) { -- err = 0; -- goto out; -- } - tmp_oext = *oext; - - if (donor_path) - ext4_ext_drop_refs(donor_path); -- err = get_ext_path(donor_inode, donor_off, &donor_path); -- if (err) -+ *err = get_ext_path(donor_inode, donor_off, &donor_path); -+ if (*err) - goto out; - depth = ext_depth(donor_inode); - dext = donor_path[depth].p_ext; -- if (le32_to_cpu(dext->ee_block) + -- ext4_ext_get_actual_len(dext) <= donor_off) { -- err = 0; -- goto out; -- } - tmp_dext = *dext; - -- err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, -+ *err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, - donor_off, count - replaced_count); -- if (err) -+ if (*err) - goto out; - } - -@@ -796,7 +786,7 @@ out: - } - - mext_double_up_write(orig_inode, donor_inode); -- return err; -+ return replaced_count; - } - - /** -@@ -808,16 +798,17 @@ out: - * @data_offset_in_page: block index where data swapping starts - * @block_len_in_page: the number of blocks to be swapped - * @uninit: orig extent is uninitialized or not -+ * @err: pointer to save return value - * - * Save the data in original inode blocks and replace original inode extents - * with donor inode extents by calling mext_replace_branches(). -- * Finally, write out the saved data in new original inode blocks. Return 0 -- * on success, or a negative error value on failure. -+ * Finally, write out the saved data in new original inode blocks. Return -+ * replaced block count. - */ - static int - move_extent_per_page(struct file *o_filp, struct inode *donor_inode, - pgoff_t orig_page_offset, int data_offset_in_page, -- int block_len_in_page, int uninit) -+ int block_len_in_page, int uninit, int *err) - { - struct inode *orig_inode = o_filp->f_dentry->d_inode; - struct address_space *mapping = orig_inode->i_mapping; -@@ -829,9 +820,11 @@ move_extent_per_page(struct file *o_filp - long long offs = orig_page_offset << PAGE_CACHE_SHIFT; - unsigned long blocksize = orig_inode->i_sb->s_blocksize; - unsigned int w_flags = 0; -- unsigned int tmp_data_len, data_len; -+ unsigned int tmp_data_size, data_size, replaced_size; - void *fsdata; -- int ret, i, jblocks; -+ int i, jblocks; -+ int err2 = 0; -+ int replaced_count = 0; - int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; - - /* -@@ -841,8 +834,8 @@ move_extent_per_page(struct file *o_filp - jblocks = ext4_writepage_trans_blocks(orig_inode) * 2; - handle = ext4_journal_start(orig_inode, jblocks); - if (IS_ERR(handle)) { -- ret = PTR_ERR(handle); -- return ret; -+ *err = PTR_ERR(handle); -+ return 0; - } - - if (segment_eq(get_fs(), KERNEL_DS)) -@@ -858,9 +851,9 @@ move_extent_per_page(struct file *o_filp - * Just swap data blocks between orig and donor. - */ - if (uninit) { -- ret = mext_replace_branches(handle, orig_inode, -- donor_inode, orig_blk_offset, -- block_len_in_page); -+ replaced_count = mext_replace_branches(handle, orig_inode, -+ donor_inode, orig_blk_offset, -+ block_len_in_page, err); - - /* Clear the inode cache not to refer to the old data */ - ext4_ext_invalidate_cache(orig_inode); -@@ -870,27 +863,28 @@ move_extent_per_page(struct file *o_filp - - offs = (long long)orig_blk_offset << orig_inode->i_blkbits; - -- /* Calculate data_len */ -+ /* Calculate data_size */ - if ((orig_blk_offset + block_len_in_page - 1) == - ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) { - /* Replace the last block */ -- tmp_data_len = orig_inode->i_size & (blocksize - 1); -+ tmp_data_size = orig_inode->i_size & (blocksize - 1); - /* -- * If data_len equal zero, it shows data_len is multiples of -+ * If data_size equal zero, it shows data_size is multiples of - * blocksize. So we set appropriate value. - */ -- if (tmp_data_len == 0) -- tmp_data_len = blocksize; -+ if (tmp_data_size == 0) -+ tmp_data_size = blocksize; - -- data_len = tmp_data_len + -+ data_size = tmp_data_size + - ((block_len_in_page - 1) << orig_inode->i_blkbits); -- } else { -- data_len = block_len_in_page << orig_inode->i_blkbits; -- } -+ } else -+ data_size = block_len_in_page << orig_inode->i_blkbits; -+ -+ replaced_size = data_size; - -- ret = a_ops->write_begin(o_filp, mapping, offs, data_len, w_flags, -+ *err = a_ops->write_begin(o_filp, mapping, offs, data_size, w_flags, - &page, &fsdata); -- if (unlikely(ret < 0)) -+ if (unlikely(*err < 0)) - goto out; - - if (!PageUptodate(page)) { -@@ -911,10 +905,17 @@ move_extent_per_page(struct file *o_filp - /* Release old bh and drop refs */ - try_to_release_page(page, 0); - -- ret = mext_replace_branches(handle, orig_inode, donor_inode, -- orig_blk_offset, block_len_in_page); -- if (ret < 0) -- goto out; -+ replaced_count = mext_replace_branches(handle, orig_inode, donor_inode, -+ orig_blk_offset, block_len_in_page, -+ &err2); -+ if (err2) { -+ if (replaced_count) { -+ block_len_in_page = replaced_count; -+ replaced_size = -+ block_len_in_page << orig_inode->i_blkbits; -+ } else -+ goto out; -+ } - - /* Clear the inode cache not to refer to the old data */ - ext4_ext_invalidate_cache(orig_inode); -@@ -928,16 +929,16 @@ move_extent_per_page(struct file *o_filp - bh = bh->b_this_page; - - for (i = 0; i < block_len_in_page; i++) { -- ret = ext4_get_block(orig_inode, -+ *err = ext4_get_block(orig_inode, - (sector_t)(orig_blk_offset + i), bh, 0); -- if (ret < 0) -+ if (*err < 0) - goto out; - - if (bh->b_this_page != NULL) - bh = bh->b_this_page; - } - -- ret = a_ops->write_end(o_filp, mapping, offs, data_len, data_len, -+ *err = a_ops->write_end(o_filp, mapping, offs, data_size, replaced_size, - page, fsdata); - page = NULL; - -@@ -951,7 +952,10 @@ out: - out2: - ext4_journal_stop(handle); - -- return ret < 0 ? ret : 0; -+ if (err2) -+ *err = err2; -+ -+ return replaced_count; - } - - /** -@@ -1367,15 +1371,17 @@ ext4_move_extents(struct file *o_filp, s - while (orig_page_offset <= seq_end_page) { - - /* Swap original branches with new branches */ -- ret1 = move_extent_per_page(o_filp, donor_inode, -+ block_len_in_page = move_extent_per_page( -+ o_filp, donor_inode, - orig_page_offset, - data_offset_in_page, -- block_len_in_page, uninit); -- if (ret1 < 0) -- goto out; -- orig_page_offset++; -+ block_len_in_page, uninit, -+ &ret1); -+ - /* Count how many blocks we have exchanged */ - *moved_len += block_len_in_page; -+ if (ret1 < 0) -+ goto out; - if (*moved_len > len) { - ext4_error(orig_inode->i_sb, __func__, - "We replaced blocks too much! " -@@ -1385,6 +1391,7 @@ ext4_move_extents(struct file *o_filp, s - goto out; - } - -+ orig_page_offset++; - data_offset_in_page = 0; - rest_blocks -= block_len_in_page; - if (rest_blocks > blocks_per_page) - - -From linux@linux.site Thu Dec 10 21:25:44 2009 -Message-Id: <20091211052544.287395070@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:20 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Akira Fujita , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [08/34] ext4: fix lock order problem in ext4_move_extents() -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0004-ext4-fix-lock-order-problem-in-ext4_move_extents.patch -Content-Length: 10372 -Lines: 310 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit fc04cb49a898c372a22b21fffc47f299d8710801) - -ext4_move_extents() checks the logical block contiguousness -of original file with ext4_find_extent() and mext_next_extent(). -Therefore the extent which ext4_ext_path structure indicates -must not be changed between above functions. - -But in current implementation, there is no i_data_sem protection -between ext4_ext_find_extent() and mext_next_extent(). So the extent -which ext4_ext_path structure indicates may be overwritten by -delalloc. As a result, ext4_move_extents() will exchange wrong blocks -between original and donor files. I change the place where -acquire/release i_data_sem to solve this problem. - -Moreover, I changed move_extent_per_page() to start transaction first, -and then acquire i_data_sem. Without this change, there is a -possibility of the deadlock between mmap() and ext4_move_extents(): - -* NOTE: "A", "B" and "C" mean different processes - -A-1: ext4_ext_move_extents() acquires i_data_sem of two inodes. - -B: do_page_fault() starts the transaction (T), - and then tries to acquire i_data_sem. - But process "A" is already holding it, so it is kept waiting. - -C: While "A" and "B" running, kjournald2 tries to commit transaction (T) - but it is under updating, so kjournald2 waits for it. - -A-2: Call ext4_journal_start with holding i_data_sem, - but transaction (T) is locked. - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 117 ++++++++++++++++++++++---------------------------- - 1 file changed, 53 insertions(+), 64 deletions(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -77,12 +77,14 @@ static int - mext_next_extent(struct inode *inode, struct ext4_ext_path *path, - struct ext4_extent **extent) - { -+ struct ext4_extent_header *eh; - int ppos, leaf_ppos = path->p_depth; - - ppos = leaf_ppos; - if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) { - /* leaf block */ - *extent = ++path[ppos].p_ext; -+ path[ppos].p_block = ext_pblock(path[ppos].p_ext); - return 0; - } - -@@ -119,9 +121,18 @@ mext_next_extent(struct inode *inode, st - ext_block_hdr(path[cur_ppos+1].p_bh); - } - -+ path[leaf_ppos].p_ext = *extent = NULL; -+ -+ eh = path[leaf_ppos].p_hdr; -+ if (le16_to_cpu(eh->eh_entries) == 0) -+ /* empty leaf is found */ -+ return -ENODATA; -+ - /* leaf block */ - path[leaf_ppos].p_ext = *extent = - EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr); -+ path[leaf_ppos].p_block = -+ ext_pblock(path[leaf_ppos].p_ext); - return 0; - } - } -@@ -155,40 +166,15 @@ mext_check_null_inode(struct inode *inod - } - - /** -- * mext_double_down_read - Acquire two inodes' read semaphore -- * -- * @orig_inode: original inode structure -- * @donor_inode: donor inode structure -- * Acquire read semaphore of the two inodes (orig and donor) by i_ino order. -- */ --static void --mext_double_down_read(struct inode *orig_inode, struct inode *donor_inode) --{ -- struct inode *first = orig_inode, *second = donor_inode; -- -- /* -- * Use the inode number to provide the stable locking order instead -- * of its address, because the C language doesn't guarantee you can -- * compare pointers that don't come from the same array. -- */ -- if (donor_inode->i_ino < orig_inode->i_ino) { -- first = donor_inode; -- second = orig_inode; -- } -- -- down_read(&EXT4_I(first)->i_data_sem); -- down_read(&EXT4_I(second)->i_data_sem); --} -- --/** -- * mext_double_down_write - Acquire two inodes' write semaphore -+ * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem - * - * @orig_inode: original inode structure - * @donor_inode: donor inode structure -- * Acquire write semaphore of the two inodes (orig and donor) by i_ino order. -+ * Acquire write lock of i_data_sem of the two inodes (orig and donor) by -+ * i_ino order. - */ - static void --mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode) -+double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) - { - struct inode *first = orig_inode, *second = donor_inode; - -@@ -207,28 +193,14 @@ mext_double_down_write(struct inode *ori - } - - /** -- * mext_double_up_read - Release two inodes' read semaphore -+ * double_up_write_data_sem - Release two inodes' write lock of i_data_sem - * - * @orig_inode: original inode structure to be released its lock first - * @donor_inode: donor inode structure to be released its lock second -- * Release read semaphore of two inodes (orig and donor). -+ * Release write lock of i_data_sem of two inodes (orig and donor). - */ - static void --mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode) --{ -- up_read(&EXT4_I(orig_inode)->i_data_sem); -- up_read(&EXT4_I(donor_inode)->i_data_sem); --} -- --/** -- * mext_double_up_write - Release two inodes' write semaphore -- * -- * @orig_inode: original inode structure to be released its lock first -- * @donor_inode: donor inode structure to be released its lock second -- * Release write semaphore of two inodes (orig and donor). -- */ --static void --mext_double_up_write(struct inode *orig_inode, struct inode *donor_inode) -+double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) - { - up_write(&EXT4_I(orig_inode)->i_data_sem); - up_write(&EXT4_I(donor_inode)->i_data_sem); -@@ -688,8 +660,6 @@ mext_replace_branches(handle_t *handle, - int replaced_count = 0; - int dext_alen; - -- mext_double_down_write(orig_inode, donor_inode); -- - /* Get the original extent for the block "orig_off" */ - *err = get_ext_path(orig_inode, orig_off, &orig_path); - if (*err) -@@ -785,7 +755,6 @@ out: - kfree(donor_path); - } - -- mext_double_up_write(orig_inode, donor_inode); - return replaced_count; - } - -@@ -851,6 +820,11 @@ move_extent_per_page(struct file *o_filp - * Just swap data blocks between orig and donor. - */ - if (uninit) { -+ /* -+ * Protect extent trees against block allocations -+ * via delalloc -+ */ -+ double_down_write_data_sem(orig_inode, donor_inode); - replaced_count = mext_replace_branches(handle, orig_inode, - donor_inode, orig_blk_offset, - block_len_in_page, err); -@@ -858,6 +832,7 @@ move_extent_per_page(struct file *o_filp - /* Clear the inode cache not to refer to the old data */ - ext4_ext_invalidate_cache(orig_inode); - ext4_ext_invalidate_cache(donor_inode); -+ double_up_write_data_sem(orig_inode, donor_inode); - goto out2; - } - -@@ -905,6 +880,8 @@ move_extent_per_page(struct file *o_filp - /* Release old bh and drop refs */ - try_to_release_page(page, 0); - -+ /* Protect extent trees against block allocations via delalloc */ -+ double_down_write_data_sem(orig_inode, donor_inode); - replaced_count = mext_replace_branches(handle, orig_inode, donor_inode, - orig_blk_offset, block_len_in_page, - &err2); -@@ -913,14 +890,18 @@ move_extent_per_page(struct file *o_filp - block_len_in_page = replaced_count; - replaced_size = - block_len_in_page << orig_inode->i_blkbits; -- } else -+ } else { -+ double_up_write_data_sem(orig_inode, donor_inode); - goto out; -+ } - } - - /* Clear the inode cache not to refer to the old data */ - ext4_ext_invalidate_cache(orig_inode); - ext4_ext_invalidate_cache(donor_inode); - -+ double_up_write_data_sem(orig_inode, donor_inode); -+ - if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0); - -@@ -1236,16 +1217,16 @@ ext4_move_extents(struct file *o_filp, s - return -EINVAL; - } - -- /* protect orig and donor against a truncate */ -+ /* Protect orig and donor inodes against a truncate */ - ret1 = mext_inode_double_lock(orig_inode, donor_inode); - if (ret1 < 0) - return ret1; - -- mext_double_down_read(orig_inode, donor_inode); -+ /* Protect extent tree against block allocations via delalloc */ -+ double_down_write_data_sem(orig_inode, donor_inode); - /* Check the filesystem environment whether move_extent can be done */ - ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start, - donor_start, &len, *moved_len); -- mext_double_up_read(orig_inode, donor_inode); - if (ret1) - goto out; - -@@ -1308,6 +1289,10 @@ ext4_move_extents(struct file *o_filp, s - ext4_ext_get_actual_len(ext_cur), block_end + 1) - - max(le32_to_cpu(ext_cur->ee_block), block_start); - -+ /* Discard preallocations of two inodes */ -+ ext4_discard_preallocations(orig_inode); -+ ext4_discard_preallocations(donor_inode); -+ - while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) { - seq_blocks += add_blocks; - -@@ -1359,14 +1344,14 @@ ext4_move_extents(struct file *o_filp, s - seq_start = le32_to_cpu(ext_cur->ee_block); - rest_blocks = seq_blocks; - -- /* Discard preallocations of two inodes */ -- down_write(&EXT4_I(orig_inode)->i_data_sem); -- ext4_discard_preallocations(orig_inode); -- up_write(&EXT4_I(orig_inode)->i_data_sem); -- -- down_write(&EXT4_I(donor_inode)->i_data_sem); -- ext4_discard_preallocations(donor_inode); -- up_write(&EXT4_I(donor_inode)->i_data_sem); -+ /* -+ * Up semaphore to avoid following problems: -+ * a. transaction deadlock among ext4_journal_start, -+ * ->write_begin via pagefault, and jbd2_journal_commit -+ * b. racing with ->readpage, ->write_begin, and ext4_get_block -+ * in move_extent_per_page -+ */ -+ double_up_write_data_sem(orig_inode, donor_inode); - - while (orig_page_offset <= seq_end_page) { - -@@ -1381,14 +1366,14 @@ ext4_move_extents(struct file *o_filp, s - /* Count how many blocks we have exchanged */ - *moved_len += block_len_in_page; - if (ret1 < 0) -- goto out; -+ break; - if (*moved_len > len) { - ext4_error(orig_inode->i_sb, __func__, - "We replaced blocks too much! " - "sum of replaced: %llu requested: %llu", - *moved_len, len); - ret1 = -EIO; -- goto out; -+ break; - } - - orig_page_offset++; -@@ -1400,6 +1385,10 @@ ext4_move_extents(struct file *o_filp, s - block_len_in_page = rest_blocks; - } - -+ double_down_write_data_sem(orig_inode, donor_inode); -+ if (ret1 < 0) -+ break; -+ - /* Decrease buffer counter */ - if (holecheck_path) - ext4_ext_drop_refs(holecheck_path); -@@ -1429,7 +1418,7 @@ out: - ext4_ext_drop_refs(holecheck_path); - kfree(holecheck_path); - } -- -+ double_up_write_data_sem(orig_inode, donor_inode); - ret2 = mext_inode_double_unlock(orig_inode, donor_inode); - - if (ret1) - - -From linux@linux.site Thu Dec 10 21:25:45 2009 -Message-Id: <20091211052544.890897126@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:21 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Akira Fujita , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [09/34] ext4: fix possible recursive locking warning in EXT4_IOC_MOVE_EXT -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0005-ext4-fix-possible-recursive-locking-warning-in-EXT4_.patch -Content-Length: 1075 -Lines: 32 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 49bd22bc4d603a2a4fc2a6a60e156cbea52eb494) - -If CONFIG_PROVE_LOCKING is enabled, the double_down_write_data_sem() -will trigger a false-positive warning of a recursive lock. Since we -take i_data_sem for the two inodes ordered by their inode numbers, -this isn't a problem. Use of down_write_nested() will notify the lock -dependency checker machinery that there is no problem here. - -This problem was reported by Brian Rogers: - - http://marc.info/?l=linux-ext4&m=125115356928011&w=1 - -Reported-by: Brian Rogers -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -189,7 +189,7 @@ double_down_write_data_sem(struct inode - } - - down_write(&EXT4_I(first)->i_data_sem); -- down_write(&EXT4_I(second)->i_data_sem); -+ down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING); - } - - /** - - -From linux@linux.site Thu Dec 10 21:25:45 2009 -Message-Id: <20091211052545.443549269@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:22 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [10/34] ext4: plug a buffer_head leak in an error path of ext4_iget() -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0006-ext4-plug-a-buffer_head-leak-in-an-error-path-of-ext.patch -Content-Length: 2427 -Lines: 82 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 567f3e9a70d71e5c9be03701b8578be77857293b) - -One of the invalid error paths in ext4_iget() forgot to brelse() the -inode buffer head. Fix it by adding a brelse() in the common error -return path, which also simplifies function. - -Thanks to Andi Kleen reporting the problem. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 11 +++-------- - 1 file changed, 3 insertions(+), 8 deletions(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -4781,7 +4781,6 @@ struct inode *ext4_iget(struct super_blo - struct ext4_iloc iloc; - struct ext4_inode *raw_inode; - struct ext4_inode_info *ei; -- struct buffer_head *bh; - struct inode *inode; - long ret; - int block; -@@ -4793,11 +4792,11 @@ struct inode *ext4_iget(struct super_blo - return inode; - - ei = EXT4_I(inode); -+ iloc.bh = 0; - - ret = __ext4_get_inode_loc(inode, &iloc, 0); - if (ret < 0) - goto bad_inode; -- bh = iloc.bh; - raw_inode = ext4_raw_inode(&iloc); - inode->i_mode = le16_to_cpu(raw_inode->i_mode); - inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); -@@ -4820,7 +4819,6 @@ struct inode *ext4_iget(struct super_blo - if (inode->i_mode == 0 || - !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) { - /* this inode is deleted */ -- brelse(bh); - ret = -ESTALE; - goto bad_inode; - } -@@ -4852,7 +4850,6 @@ struct inode *ext4_iget(struct super_blo - ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); - if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > - EXT4_INODE_SIZE(inode->i_sb)) { -- brelse(bh); - ret = -EIO; - goto bad_inode; - } -@@ -4905,10 +4902,8 @@ struct inode *ext4_iget(struct super_blo - /* Validate block references which are part of inode */ - ret = ext4_check_inode_blockref(inode); - } -- if (ret) { -- brelse(bh); -+ if (ret) - goto bad_inode; -- } - - if (S_ISREG(inode->i_mode)) { - inode->i_op = &ext4_file_inode_operations; -@@ -4936,7 +4931,6 @@ struct inode *ext4_iget(struct super_blo - init_special_inode(inode, inode->i_mode, - new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); - } else { -- brelse(bh); - ret = -EIO; - ext4_error(inode->i_sb, __func__, - "bogus i_mode (%o) for inode=%lu", -@@ -4949,6 +4943,7 @@ struct inode *ext4_iget(struct super_blo - return inode; - - bad_inode: -+ brelse(iloc.bh); - iget_failed(inode); - return ERR_PTR(ret); - } - - -From linux@linux.site Thu Dec 10 21:25:46 2009 -Message-Id: <20091211052545.995802406@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:23 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [11/34] ext4: make sure directory and symlink blocks are revoked -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0007-ext4-make-sure-directory-and-symlink-blocks-are-revo.patch -Content-Length: 2052 -Lines: 58 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 50689696867d95b38d9c7be640a311494a04fb86) - -When an inode gets unlinked, the functions ext4_clear_blocks() and -ext4_remove_blocks() call ext4_forget() for all the buffer heads -corresponding to the deleted inode's data blocks. If the inode is a -directory or a symlink, the is_metadata parameter must be non-zero so -ext4_forget() will revoke them via jbd2_journal_revoke(). Otherwise, -if these blocks are reused for a data file, and the system crashes -before a journal checkpoint, the journal replay could end up -corrupting these data blocks. - -Thanks to Curt Wohlgemuth for pointing out potential problems in this -area. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/extents.c | 2 +- - fs/ext4/inode.c | 6 ++++-- - 2 files changed, 5 insertions(+), 3 deletions(-) - ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -2074,7 +2074,7 @@ static int ext4_remove_blocks(handle_t * - ext_debug("free last %u blocks starting %llu\n", num, start); - for (i = 0; i < num; i++) { - bh = sb_find_get_block(inode->i_sb, start + i); -- ext4_forget(handle, 0, inode, bh, start + i); -+ ext4_forget(handle, metadata, inode, bh, start + i); - } - ext4_free_blocks(handle, inode, start, num, metadata); - } else if (from == le32_to_cpu(ex->ee_block) ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -4120,6 +4120,8 @@ static void ext4_clear_blocks(handle_t * - __le32 *last) - { - __le32 *p; -+ int is_metadata = S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode); -+ - if (try_to_extend_transaction(handle, inode)) { - if (bh) { - BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); -@@ -4150,11 +4152,11 @@ static void ext4_clear_blocks(handle_t * - - *p = 0; - tbh = sb_find_get_block(inode->i_sb, nr); -- ext4_forget(handle, 0, inode, tbh, nr); -+ ext4_forget(handle, is_metadata, inode, tbh, nr); - } - } - -- ext4_free_blocks(handle, inode, block_to_free, count, 0); -+ ext4_free_blocks(handle, inode, block_to_free, count, is_metadata); - } - - /** - - -From linux@linux.site Thu Dec 10 21:25:47 2009 -Message-Id: <20091211052546.544464652@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:24 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Julia Lawall , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [12/34] ext4: fix i_flags access in ext4_da_writepages_trans_blocks() -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0008-ext4-fix-i_flags-access-in-ext4_da_writepages_trans_.patch -Content-Length: 846 -Lines: 25 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 30c6e07a92ea4cb87160d32ffa9bce172576ae4c) - -We need to be testing the i_flags field in the ext4 specific portion -of the inode, instead of the (confusingly aliased) i_flags field in -the generic struct inode. - -Signed-off-by: Julia Lawall -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -2788,7 +2788,7 @@ static int ext4_da_writepages_trans_bloc - * number of contiguous block. So we will limit - * number of contiguous block to a sane value - */ -- if (!(inode->i_flags & EXT4_EXTENTS_FL) && -+ if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) && - (max_blocks > EXT4_MAX_TRANS_DATA)) - max_blocks = EXT4_MAX_TRANS_DATA; - - - -From linux@linux.site Thu Dec 10 21:25:47 2009 -Message-Id: <20091211052547.065677730@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:25 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Eric Sandeen , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [13/34] ext4: journal all modifications in ext4_xattr_set_handle -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0009-ext4-journal-all-modifications-in-ext4_xattr_set_han.patch -Content-Length: 1254 -Lines: 39 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 86ebfd08a1930ccedb8eac0aeb1ed4b8b6a41dbc) - -ext4_xattr_set_handle() was zeroing out an inode outside -of journaling constraints; this is one of the accesses that -was causing the crc errors in journal replay as seen in -kernel.org bugzilla #14354. - -Reviewed-by: Andreas Dilger -Signed-off-by: Eric Sandeen -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/xattr.c | 7 ++++--- - 1 file changed, 4 insertions(+), 3 deletions(-) - ---- a/fs/ext4/xattr.c -+++ b/fs/ext4/xattr.c -@@ -988,6 +988,10 @@ ext4_xattr_set_handle(handle_t *handle, - if (error) - goto cleanup; - -+ error = ext4_journal_get_write_access(handle, is.iloc.bh); -+ if (error) -+ goto cleanup; -+ - if (EXT4_I(inode)->i_state & EXT4_STATE_NEW) { - struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc); - memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); -@@ -1013,9 +1017,6 @@ ext4_xattr_set_handle(handle_t *handle, - if (flags & XATTR_CREATE) - goto cleanup; - } -- error = ext4_journal_get_write_access(handle, is.iloc.bh); -- if (error) -- goto cleanup; - if (!value) { - if (!is.s.not_found) - error = ext4_xattr_ibody_set(handle, inode, &i, &is); - - -From linux@linux.site Thu Dec 10 21:25:48 2009 -Message-Id: <20091211052547.644399594@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:26 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [14/34] ext4: dont update the superblock in ext4_statfs() -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0010-ext4-don-t-update-the-superblock-in-ext4_statfs.patch -Content-Length: 1341 -Lines: 31 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 3f8fb9490efbd300887470a2a880a64e04dcc3f5) - -commit a71ce8c6c9bf269b192f352ea555217815cf027e updated ext4_statfs() -to update the on-disk superblock counters, but modified this buffer -directly without any journaling of the change. This is one of the -accesses that was causing the crc errors in journal replay as seen in -kernel.org bugzilla #14354. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/super.c | 2 -- - 1 file changed, 2 deletions(-) - ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -3668,13 +3668,11 @@ static int ext4_statfs(struct dentry *de - buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last; - buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) - - percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter); -- ext4_free_blocks_count_set(es, buf->f_bfree); - buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es); - if (buf->f_bfree < ext4_r_blocks_count(es)) - buf->f_bavail = 0; - buf->f_files = le32_to_cpu(es->s_inodes_count); - buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter); -- es->s_free_inodes_count = cpu_to_le32(buf->f_ffree); - buf->f_namelen = EXT4_NAME_LEN; - fsid = le64_to_cpup((void *)es->s_uuid) ^ - le64_to_cpup((void *)es->s_uuid + sizeof(u64)); - - -From linux@linux.site Thu Dec 10 21:25:48 2009 -Message-Id: <20091211052548.201782286@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:27 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [15/34] ext4: fix uninit block bitmap initialization when s_meta_first_bg is non-zero -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0011-ext4-fix-uninit-block-bitmap-initialization-when-s_m.patch -Content-Length: 875 -Lines: 29 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 8dadb198cb70ef811916668fe67eeec82e8858dd) - -The number of old-style block group descriptor blocks is -s_meta_first_bg when the meta_bg feature flag is set. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/balloc.c | 8 +++++++- - 1 file changed, 7 insertions(+), 1 deletion(-) - ---- a/fs/ext4/balloc.c -+++ b/fs/ext4/balloc.c -@@ -761,7 +761,13 @@ static unsigned long ext4_bg_num_gdb_met - static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, - ext4_group_t group) - { -- return ext4_bg_has_super(sb, group) ? EXT4_SB(sb)->s_gdb_count : 0; -+ if (!ext4_bg_has_super(sb, group)) -+ return 0; -+ -+ if (EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG)) -+ return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); -+ else -+ return EXT4_SB(sb)->s_gdb_count; - } - - /** - - -From linux@linux.site Thu Dec 10 21:25:49 2009 -Message-Id: <20091211052548.726431621@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:28 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [16/34] ext4: fix block validity checks so they work correctly with meta_bg -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0012-ext4-fix-block-validity-checks-so-they-work-correctl.patch -Content-Length: 1411 -Lines: 39 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 1032988c71f3f85483b2b4319684d1205a704c02) - -The block validity checks used by ext4_data_block_valid() wasn't -correctly written to check file systems with the meta_bg feature. Fix -this. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/block_validity.c | 2 +- - fs/ext4/inode.c | 5 +---- - 2 files changed, 2 insertions(+), 5 deletions(-) - ---- a/fs/ext4/block_validity.c -+++ b/fs/ext4/block_validity.c -@@ -160,7 +160,7 @@ int ext4_setup_system_zone(struct super_ - if (ext4_bg_has_super(sb, i) && - ((i < 5) || ((i % flex_size) == 0))) - add_system_zone(sbi, ext4_group_first_block_no(sb, i), -- sbi->s_gdb_count + 1); -+ ext4_bg_num_gdb(sb, i) + 1); - gdp = ext4_get_group_desc(sb, i, NULL); - ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1); - if (ret) ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -4883,10 +4883,7 @@ struct inode *ext4_iget(struct super_blo - - ret = 0; - if (ei->i_file_acl && -- ((ei->i_file_acl < -- (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) + -- EXT4_SB(sb)->s_gdb_count)) || -- (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) { -+ !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { - ext4_error(sb, __func__, - "bad extended attribute block %llu in inode #%lu", - ei->i_file_acl, inode->i_ino); - - -From linux@linux.site Thu Dec 10 21:25:49 2009 -Message-Id: <20091211052549.341684525@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:29 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Jan Kara , - Greg Kroah-Hartman -Subject: [17/34] ext4: avoid issuing unnecessary barriers -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0013-ext4-avoid-issuing-unnecessary-barriers.patch -Content-Length: 1115 -Lines: 37 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 6b17d902fdd241adfa4ce780df20547b28bf5801) - -We don't to issue an I/O barrier on an error or if we force commit -because we are doing data journaling. - -Signed-off-by: "Theodore Ts'o" -Cc: Jan Kara -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/fsync.c | 8 +++----- - 1 file changed, 3 insertions(+), 5 deletions(-) - ---- a/fs/ext4/fsync.c -+++ b/fs/ext4/fsync.c -@@ -60,7 +60,7 @@ int ext4_sync_file(struct file *file, st - - ret = flush_aio_dio_completed_IO(inode); - if (ret < 0) -- goto out; -+ return ret; - /* - * data=writeback: - * The caller's filemap_fdatawrite()/wait will sync the data. -@@ -79,10 +79,8 @@ int ext4_sync_file(struct file *file, st - * (they were dirtied by commit). But that's OK - the blocks are - * safe in-journal, which is all fsync() needs to ensure. - */ -- if (ext4_should_journal_data(inode)) { -- ret = ext4_force_commit(inode->i_sb); -- goto out; -- } -+ if (ext4_should_journal_data(inode)) -+ return ext4_force_commit(inode->i_sb); - - if (!journal) - ret = sync_mapping_buffers(inode->i_mapping); - - -From linux@linux.site Thu Dec 10 21:25:50 2009 -Message-Id: <20091211052549.883933582@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:30 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Jan Kara , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [18/34] ext4: fix error handling in ext4_ind_get_blocks() -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0014-ext4-fix-error-handling-in-ext4_ind_get_blocks.patch -Content-Length: 733 -Lines: 25 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 2bba702d4f88d7b010ec37e2527b552588404ae7) - -When an error happened in ext4_splice_branch we failed to notice that -in ext4_ind_get_blocks and mapped the buffer anyway. Fix the problem -by checking for error properly. - -Signed-off-by: Jan Kara -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -1021,7 +1021,7 @@ static int ext4_ind_get_blocks(handle_t - if (!err) - err = ext4_splice_branch(handle, inode, iblock, - partial, indirect_blks, count); -- else -+ if (err) - goto cleanup; - - set_buffer_new(bh_result); - - -From linux@linux.site Thu Dec 10 21:25:50 2009 -Message-Id: <20091211052550.441771142@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:31 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Eric Sandeen , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [19/34] ext4: make trim/discard optional (and off by default) -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0015-ext4-make-trim-discard-optional-and-off-by-default.patch -Content-Length: 4275 -Lines: 124 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 5328e635315734d42080de9a5a1ee87bf4cae0a4) - -It is anticipated that when sb_issue_discard starts doing -real work on trim-capable devices, we may see issues. Make -this mount-time optional, and default it to off until we know -that things are working out OK. - -Signed-off-by: Eric Sandeen -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - Documentation/filesystems/ext4.txt | 6 ++++++ - fs/ext4/ext4.h | 1 + - fs/ext4/mballoc.c | 21 +++++++++++++-------- - fs/ext4/super.c | 14 +++++++++++++- - 4 files changed, 33 insertions(+), 9 deletions(-) - ---- a/Documentation/filesystems/ext4.txt -+++ b/Documentation/filesystems/ext4.txt -@@ -353,6 +353,12 @@ noauto_da_alloc replacing existing file - system crashes before the delayed allocation - blocks are forced to disk. - -+discard Controls whether ext4 should issue discard/TRIM -+nodiscard(*) commands to the underlying block device when -+ blocks are freed. This is useful for SSD devices -+ and sparse/thinly-provisioned LUNs, but it is off -+ by default until sufficient testing has been done. -+ - Data Mode - ========= - There are 3 different data modes: ---- a/fs/ext4/ext4.h -+++ b/fs/ext4/ext4.h -@@ -750,6 +750,7 @@ struct ext4_inode_info { - #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ - #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ - #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ -+#define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */ - - #define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt - #define set_opt(o, opt) o |= EXT4_MOUNT_##opt ---- a/fs/ext4/mballoc.c -+++ b/fs/ext4/mballoc.c -@@ -2529,7 +2529,6 @@ static void release_blocks_on_commit(jou - struct ext4_group_info *db; - int err, count = 0, count2 = 0; - struct ext4_free_data *entry; -- ext4_fsblk_t discard_block; - struct list_head *l, *ltmp; - - list_for_each_safe(l, ltmp, &txn->t_private_list) { -@@ -2559,13 +2558,19 @@ static void release_blocks_on_commit(jou - page_cache_release(e4b.bd_bitmap_page); - } - ext4_unlock_group(sb, entry->group); -- discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb) -- + entry->start_blk -- + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); -- trace_ext4_discard_blocks(sb, (unsigned long long)discard_block, -- entry->count); -- sb_issue_discard(sb, discard_block, entry->count); -- -+ if (test_opt(sb, DISCARD)) { -+ ext4_fsblk_t discard_block; -+ struct ext4_super_block *es = EXT4_SB(sb)->s_es; -+ -+ discard_block = (ext4_fsblk_t)entry->group * -+ EXT4_BLOCKS_PER_GROUP(sb) -+ + entry->start_blk -+ + le32_to_cpu(es->s_first_data_block); -+ trace_ext4_discard_blocks(sb, -+ (unsigned long long)discard_block, -+ entry->count); -+ sb_issue_discard(sb, discard_block, entry->count); -+ } - kmem_cache_free(ext4_free_ext_cachep, entry); - ext4_mb_release_desc(&e4b); - } ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -899,6 +899,9 @@ static int ext4_show_options(struct seq_ - if (test_opt(sb, NO_AUTO_DA_ALLOC)) - seq_puts(seq, ",noauto_da_alloc"); - -+ if (test_opt(sb, DISCARD)) -+ seq_puts(seq, ",discard"); -+ - ext4_show_quota_options(seq, sb); - - return 0; -@@ -1079,7 +1082,8 @@ enum { - Opt_usrquota, Opt_grpquota, Opt_i_version, - Opt_stripe, Opt_delalloc, Opt_nodelalloc, - Opt_block_validity, Opt_noblock_validity, -- Opt_inode_readahead_blks, Opt_journal_ioprio -+ Opt_inode_readahead_blks, Opt_journal_ioprio, -+ Opt_discard, Opt_nodiscard, - }; - - static const match_table_t tokens = { -@@ -1144,6 +1148,8 @@ static const match_table_t tokens = { - {Opt_auto_da_alloc, "auto_da_alloc=%u"}, - {Opt_auto_da_alloc, "auto_da_alloc"}, - {Opt_noauto_da_alloc, "noauto_da_alloc"}, -+ {Opt_discard, "discard"}, -+ {Opt_nodiscard, "nodiscard"}, - {Opt_err, NULL}, - }; - -@@ -1565,6 +1571,12 @@ set_qf_format: - else - set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC); - break; -+ case Opt_discard: -+ set_opt(sbi->s_mount_opt, DISCARD); -+ break; -+ case Opt_nodiscard: -+ clear_opt(sbi->s_mount_opt, DISCARD); -+ break; - default: - ext4_msg(sb, KERN_ERR, - "Unrecognized mount option \"%s\" " - - -From linux@linux.site Thu Dec 10 21:25:51 2009 -Message-Id: <20091211052551.004437667@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:32 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Eric Sandeen , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [20/34] ext4: make "norecovery" an alias for "noload" -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0016-ext4-make-norecovery-an-alias-for-noload.patch -Content-Length: 1856 -Lines: 53 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit e3bb52ae2bb9573e84c17b8e3560378d13a5c798) - -Users on the linux-ext4 list recently complained about differences -across filesystems w.r.t. how to mount without a journal replay. - -In the discussion it was noted that xfs's "norecovery" option is -perhaps more descriptively accurate than "noload," so let's make -that an alias for ext4. - -Also show this status in /proc/mounts - -Signed-off-by: Eric Sandeen -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - Documentation/filesystems/ext4.txt | 4 ++-- - fs/ext4/super.c | 4 ++++ - 2 files changed, 6 insertions(+), 2 deletions(-) - ---- a/Documentation/filesystems/ext4.txt -+++ b/Documentation/filesystems/ext4.txt -@@ -153,8 +153,8 @@ journal_dev=devnum When the external jou - identified through its new major/minor numbers encoded - in devnum. - --noload Don't load the journal on mounting. Note that -- if the filesystem was not unmounted cleanly, -+norecovery Don't load the journal on mounting. Note that -+noload if the filesystem was not unmounted cleanly, - skipping the journal replay will lead to the - filesystem containing inconsistencies that can - lead to any number of problems. ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -902,6 +902,9 @@ static int ext4_show_options(struct seq_ - if (test_opt(sb, DISCARD)) - seq_puts(seq, ",discard"); - -+ if (test_opt(sb, NOLOAD)) -+ seq_puts(seq, ",norecovery"); -+ - ext4_show_quota_options(seq, sb); - - return 0; -@@ -1108,6 +1111,7 @@ static const match_table_t tokens = { - {Opt_acl, "acl"}, - {Opt_noacl, "noacl"}, - {Opt_noload, "noload"}, -+ {Opt_noload, "norecovery"}, - {Opt_nobh, "nobh"}, - {Opt_bh, "bh"}, - {Opt_commit, "commit=%u"}, - - -From linux@linux.site Thu Dec 10 21:25:52 2009 -Message-Id: <20091211052551.564396025@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:33 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Akira Fujita , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [21/34] ext4: Fix double-free of blocks with EXT4_IOC_MOVE_EXT -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0017-ext4-Fix-double-free-of-blocks-with-EXT4_IOC_MOVE_EX.patch -Content-Length: 2565 -Lines: 75 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 94d7c16cbbbd0e03841fcf272bcaf0620ad39618) - -At the beginning of ext4_move_extent(), we call -ext4_discard_preallocations() to discard inode PAs of orig and donor -inodes. But in the following case, blocks can be double freed, so -move ext4_discard_preallocations() to the end of ext4_move_extents(). - -1. Discard inode PAs of orig and donor inodes with - ext4_discard_preallocations() in ext4_move_extents(). - - orig : [ DATA1 ] - donor: [ DATA2 ] - -2. While data blocks are exchanging between orig and donor inodes, new - inode PAs is created to orig by other process's block allocation. - (Since there are semaphore gaps in ext4_move_extents().) And new - inode PAs is used partially (2-1). - - 2-1 Create new inode PAs to orig inode - orig : [ DATA1 | used PA1 | free PA1 ] - donor: [ DATA2 ] - -3. Donor inode which has old orig inode's blocks is deleted after - EXT4_IOC_MOVE_EXT finished (3-1, 3-2). So the block bitmap - corresponds to old orig inode's blocks are freed. - - 3-1 After EXT4_IOC_MOVE_EXT finished - orig : [ DATA2 | free PA1 ] - donor: [ DATA1 | used PA1 ] - - 3-2 Delete donor inode - orig : [ DATA2 | free PA1 ] - donor: [ FREE SPACE(DATA1) | FREE SPACE(used PA1) ] - -4. The double-free of blocks is occurred, when close() is called to - orig inode. Because ext4_discard_preallocations() for orig inode - frees used PA1 and free PA1, though used PA1 is already freed in 3. - - 4-1 Double-free of blocks is occurred - orig : [ DATA2 | FREE SPACE(free PA1) ] - donor: [ FREE SPACE(DATA1) | DOUBLE FREE(used PA1) ] - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 9 +++++---- - 1 file changed, 5 insertions(+), 4 deletions(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -1289,10 +1289,6 @@ ext4_move_extents(struct file *o_filp, s - ext4_ext_get_actual_len(ext_cur), block_end + 1) - - max(le32_to_cpu(ext_cur->ee_block), block_start); - -- /* Discard preallocations of two inodes */ -- ext4_discard_preallocations(orig_inode); -- ext4_discard_preallocations(donor_inode); -- - while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) { - seq_blocks += add_blocks; - -@@ -1410,6 +1406,11 @@ ext4_move_extents(struct file *o_filp, s - - } - out: -+ if (*moved_len) { -+ ext4_discard_preallocations(orig_inode); -+ ext4_discard_preallocations(donor_inode); -+ } -+ - if (orig_path) { - ext4_ext_drop_refs(orig_path); - kfree(orig_path); - - -From linux@linux.site Thu Dec 10 21:25:52 2009 -Message-Id: <20091211052552.134440580@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:34 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Kazuya Mio , - Akira Fujita , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [22/34] ext4: initialize moved_len before calling ext4_move_extents() -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0018-ext4-initialize-moved_len-before-calling-ext4_move_e.patch -Content-Length: 2439 -Lines: 72 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 446aaa6e7e993b38a6f21c6acfa68f3f1af3dbe3) - -The move_extent.moved_len is used to pass back the number of exchanged -blocks count to user space. Currently the caller must clear this -field; but we spend more code space checking for this requirement than -simply zeroing the field ourselves, so let's just make life easier for -everyone all around. - -Signed-off-by: Kazuya Mio -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/ioctl.c | 1 + - fs/ext4/move_extent.c | 14 +++----------- - 2 files changed, 4 insertions(+), 11 deletions(-) - ---- a/fs/ext4/ioctl.c -+++ b/fs/ext4/ioctl.c -@@ -239,6 +239,7 @@ setversion_out: - } - } - -+ me.moved_len = 0; - err = ext4_move_extents(filp, donor_filp, me.orig_start, - me.donor_start, me.len, &me.moved_len); - fput(donor_filp); ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -947,7 +947,6 @@ out2: - * @orig_start: logical start offset in block for orig - * @donor_start: logical start offset in block for donor - * @len: the number of blocks to be moved -- * @moved_len: moved block length - * - * Check the arguments of ext4_move_extents() whether the files can be - * exchanged with each other. -@@ -955,8 +954,8 @@ out2: - */ - static int - mext_check_arguments(struct inode *orig_inode, -- struct inode *donor_inode, __u64 orig_start, -- __u64 donor_start, __u64 *len, __u64 moved_len) -+ struct inode *donor_inode, __u64 orig_start, -+ __u64 donor_start, __u64 *len) - { - ext4_lblk_t orig_blocks, donor_blocks; - unsigned int blkbits = orig_inode->i_blkbits; -@@ -1010,13 +1009,6 @@ mext_check_arguments(struct inode *orig_ - return -EINVAL; - } - -- if (moved_len) { -- ext4_debug("ext4 move extent: moved_len should be 0 " -- "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino, -- donor_inode->i_ino); -- return -EINVAL; -- } -- - if ((orig_start > EXT_MAX_BLOCK) || - (donor_start > EXT_MAX_BLOCK) || - (*len > EXT_MAX_BLOCK) || -@@ -1226,7 +1218,7 @@ ext4_move_extents(struct file *o_filp, s - double_down_write_data_sem(orig_inode, donor_inode); - /* Check the filesystem environment whether move_extent can be done */ - ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start, -- donor_start, &len, *moved_len); -+ donor_start, &len); - if (ret1) - goto out; - - - -From linux@linux.site Thu Dec 10 21:25:53 2009 -Message-Id: <20091211052552.682377360@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:35 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Akira Fujita , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [23/34] ext4: move_extent_per_page() cleanup -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0019-ext4-move_extent_per_page-cleanup.patch -Content-Length: 2733 -Lines: 87 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit ac48b0a1d068887141581bea8285de5fcab182b0) - -Integrate duplicate lines (acquire/release semaphore and invalidate -extent cache in move_extent_per_page()) into mext_replace_branches(), -to reduce source and object code size. - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/move_extent.c | 30 +++++++++--------------------- - 1 file changed, 9 insertions(+), 21 deletions(-) - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -660,6 +660,9 @@ mext_replace_branches(handle_t *handle, - int replaced_count = 0; - int dext_alen; - -+ /* Protect extent trees against block allocations via delalloc */ -+ double_down_write_data_sem(orig_inode, donor_inode); -+ - /* Get the original extent for the block "orig_off" */ - *err = get_ext_path(orig_inode, orig_off, &orig_path); - if (*err) -@@ -755,6 +758,11 @@ out: - kfree(donor_path); - } - -+ ext4_ext_invalidate_cache(orig_inode); -+ ext4_ext_invalidate_cache(donor_inode); -+ -+ double_up_write_data_sem(orig_inode, donor_inode); -+ - return replaced_count; - } - -@@ -820,19 +828,9 @@ move_extent_per_page(struct file *o_filp - * Just swap data blocks between orig and donor. - */ - if (uninit) { -- /* -- * Protect extent trees against block allocations -- * via delalloc -- */ -- double_down_write_data_sem(orig_inode, donor_inode); - replaced_count = mext_replace_branches(handle, orig_inode, - donor_inode, orig_blk_offset, - block_len_in_page, err); -- -- /* Clear the inode cache not to refer to the old data */ -- ext4_ext_invalidate_cache(orig_inode); -- ext4_ext_invalidate_cache(donor_inode); -- double_up_write_data_sem(orig_inode, donor_inode); - goto out2; - } - -@@ -880,8 +878,6 @@ move_extent_per_page(struct file *o_filp - /* Release old bh and drop refs */ - try_to_release_page(page, 0); - -- /* Protect extent trees against block allocations via delalloc */ -- double_down_write_data_sem(orig_inode, donor_inode); - replaced_count = mext_replace_branches(handle, orig_inode, donor_inode, - orig_blk_offset, block_len_in_page, - &err2); -@@ -890,18 +886,10 @@ move_extent_per_page(struct file *o_filp - block_len_in_page = replaced_count; - replaced_size = - block_len_in_page << orig_inode->i_blkbits; -- } else { -- double_up_write_data_sem(orig_inode, donor_inode); -+ } else - goto out; -- } - } - -- /* Clear the inode cache not to refer to the old data */ -- ext4_ext_invalidate_cache(orig_inode); -- ext4_ext_invalidate_cache(donor_inode); -- -- double_up_write_data_sem(orig_inode, donor_inode); -- - if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0); - - - -From linux@linux.site Thu Dec 10 21:25:53 2009 -Message-Id: <20091211052553.196951652@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:36 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [24/34] jbd2: Add ENOMEM checking in and for jbd2_journal_write_metadata_buffer() -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0020-jbd2-Add-ENOMEM-checking-in-and-for-jbd2_journal_wri.patch -Content-Length: 1035 -Lines: 38 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit e6ec116b67f46e0e7808276476554727b2e6240b) - -OOM happens. - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/jbd2/commit.c | 4 ++++ - fs/jbd2/journal.c | 4 ++++ - 2 files changed, 8 insertions(+) - ---- a/fs/jbd2/commit.c -+++ b/fs/jbd2/commit.c -@@ -636,6 +636,10 @@ void jbd2_journal_commit_transaction(jou - JBUFFER_TRACE(jh, "ph3: write metadata"); - flags = jbd2_journal_write_metadata_buffer(commit_transaction, - jh, &new_jh, blocknr); -+ if (flags < 0) { -+ jbd2_journal_abort(journal, flags); -+ continue; -+ } - set_bit(BH_JWrite, &jh2bh(new_jh)->b_state); - wbuf[bufs++] = jh2bh(new_jh); - ---- a/fs/jbd2/journal.c -+++ b/fs/jbd2/journal.c -@@ -358,6 +358,10 @@ repeat: - - jbd_unlock_bh_state(bh_in); - tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); -+ if (!tmp) { -+ jbd2_journal_put_journal_head(new_jh); -+ return -ENOMEM; -+ } - jbd_lock_bh_state(bh_in); - if (jh_in->b_frozen_data) { - jbd2_free(tmp, bh_in->b_size); - - -From linux@linux.site Thu Dec 10 21:25:54 2009 -Message-Id: <20091211052553.749907435@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:37 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Roel Kluin , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [25/34] ext4: Return the PTR_ERR of the correct pointer in setup_new_group_blocks() -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0021-ext4-Return-the-PTR_ERR-of-the-correct-pointer-in-se.patch -Content-Length: 595 -Lines: 21 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit c09eef305dd43846360944ad072f051f964fa383) - -Signed-off-by: Roel Kluin -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/resize.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/resize.c -+++ b/fs/ext4/resize.c -@@ -247,7 +247,7 @@ static int setup_new_group_blocks(struct - goto exit_bh; - - if (IS_ERR(gdb = bclean(handle, sb, block))) { -- err = PTR_ERR(bh); -+ err = PTR_ERR(gdb); - goto exit_bh; - } - ext4_handle_dirty_metadata(handle, NULL, gdb); - - -From linux@linux.site Thu Dec 10 21:25:54 2009 -Message-Id: <20091211052554.355331485@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:38 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Jan Kara , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [26/34] ext4: Avoid data / filesystem corruption when write fails to copy data -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0022-ext4-Avoid-data-filesystem-corruption-when-write-fai.patch -Content-Length: 2923 -Lines: 84 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit b9a4207d5e911b938f73079a83cc2ae10524ec7f) - -When ext4_write_begin fails after allocating some blocks or -generic_perform_write fails to copy data to write, we truncate blocks -already instantiated beyond i_size. Although these blocks were never -inside i_size, we have to truncate the pagecache of these blocks so -that corresponding buffers get unmapped. Otherwise subsequent -__block_prepare_write (called because we are retrying the write) will -find the buffers mapped, not call ->get_block, and thus the page will -be backed by already freed blocks leading to filesystem and data -corruption. - -Signed-off-by: Jan Kara -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 20 +++++++++++++++----- - 1 file changed, 15 insertions(+), 5 deletions(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -1534,6 +1534,16 @@ static int do_journal_get_write_access(h - return ext4_journal_get_write_access(handle, bh); - } - -+/* -+ * Truncate blocks that were not used by write. We have to truncate the -+ * pagecache as well so that corresponding buffers get properly unmapped. -+ */ -+static void ext4_truncate_failed_write(struct inode *inode) -+{ -+ truncate_inode_pages(inode->i_mapping, inode->i_size); -+ ext4_truncate(inode); -+} -+ - static int ext4_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) -@@ -1599,7 +1609,7 @@ retry: - - ext4_journal_stop(handle); - if (pos + len > inode->i_size) { -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might - * still be on the orphan list; we need to -@@ -1709,7 +1719,7 @@ static int ext4_ordered_write_end(struct - ret = ret2; - - if (pos + len > inode->i_size) { -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might still be - * on the orphan list; we need to make sure the inode -@@ -1751,7 +1761,7 @@ static int ext4_writeback_write_end(stru - ret = ret2; - - if (pos + len > inode->i_size) { -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might still be - * on the orphan list; we need to make sure the inode -@@ -1814,7 +1824,7 @@ static int ext4_journalled_write_end(str - if (!ret) - ret = ret2; - if (pos + len > inode->i_size) { -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - /* - * If truncate failed early the inode might still be - * on the orphan list; we need to make sure the inode -@@ -3091,7 +3101,7 @@ retry: - * i_size_read because we hold i_mutex. - */ - if (pos + len > inode->i_size) -- ext4_truncate(inode); -+ ext4_truncate_failed_write(inode); - } - - if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - - -From linux@linux.site Thu Dec 10 21:25:55 2009 -Message-Id: <20091211052554.925382177@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:39 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Josef Bacik , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [27/34] ext4: wait for log to commit when umounting -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0023-ext4-wait-for-log-to-commit-when-umounting.patch -Content-Length: 1540 -Lines: 46 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit d4edac314e9ad0b21ba20ba8bc61b61f186f79e1) - -There is a potential race when a transaction is committing right when -the file system is being umounting. This could reduce in a race -because EXT4_SB(sb)->s_group_info could be freed in ext4_put_super -before the commit code calls a callback so the mballoc code can -release freed blocks in the transaction, resulting in a panic trying -to access the freed s_group_info. - -The fix is to wait for the transaction to finish committing before we -shutdown the multiblock allocator. - -Signed-off-by: Josef Bacik -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/super.c | 10 ++++++---- - 1 file changed, 6 insertions(+), 4 deletions(-) - ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -603,10 +603,6 @@ static void ext4_put_super(struct super_ - if (sb->s_dirt) - ext4_commit_super(sb, 1); - -- ext4_release_system_zone(sb); -- ext4_mb_release(sb); -- ext4_ext_release(sb); -- ext4_xattr_put_super(sb); - if (sbi->s_journal) { - err = jbd2_journal_destroy(sbi->s_journal); - sbi->s_journal = NULL; -@@ -614,6 +610,12 @@ static void ext4_put_super(struct super_ - ext4_abort(sb, __func__, - "Couldn't clean up the journal"); - } -+ -+ ext4_release_system_zone(sb); -+ ext4_mb_release(sb); -+ ext4_ext_release(sb); -+ ext4_xattr_put_super(sb); -+ - if (!(sb->s_flags & MS_RDONLY)) { - EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - es->s_state = cpu_to_le16(sbi->s_mount_state); - - -From linux@linux.site Thu Dec 10 21:25:55 2009 -Message-Id: <20091211052555.487338959@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:40 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Curt Wohlgemuth , - "Aneesh Kumar K.V" , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [28/34] ext4: remove blocks from inode prealloc list on failure -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0024-ext4-remove-blocks-from-inode-prealloc-list-on-failu.patch -Content-Length: 1476 -Lines: 49 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit b844167edc7fcafda9623955c05e4c1b3c32ebc7) - -This fixes a leak of blocks in an inode prealloc list if device failures -cause ext4_mb_mark_diskspace_used() to fail. - -Signed-off-by: Curt Wohlgemuth -Acked-by: Aneesh Kumar K.V -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/mballoc.c | 19 +++++++++++++++++++ - 1 file changed, 19 insertions(+) - ---- a/fs/ext4/mballoc.c -+++ b/fs/ext4/mballoc.c -@@ -3011,6 +3011,24 @@ static void ext4_mb_collect_stats(struct - } - - /* -+ * Called on failure; free up any blocks from the inode PA for this -+ * context. We don't need this for MB_GROUP_PA because we only change -+ * pa_free in ext4_mb_release_context(), but on failure, we've already -+ * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed. -+ */ -+static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) -+{ -+ struct ext4_prealloc_space *pa = ac->ac_pa; -+ int len; -+ -+ if (pa && pa->pa_type == MB_INODE_PA) { -+ len = ac->ac_b_ex.fe_len; -+ pa->pa_free += len; -+ } -+ -+} -+ -+/* - * use blocks preallocated to inode - */ - static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, -@@ -4295,6 +4313,7 @@ repeat: - ac->ac_status = AC_STATUS_CONTINUE; - goto repeat; - } else if (*errp) { -+ ext4_discard_allocated_blocks(ac); - ac->ac_b_ex.fe_len = 0; - ar->len = 0; - ext4_mb_show_ac(ac); - - -From linux@linux.site Thu Dec 10 21:25:56 2009 -Message-Id: <20091211052556.043172197@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:41 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Dmitry Monakhov , - Mingming Cao , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [29/34] ext4: ext4_get_reserved_space() must return bytes instead of blocks -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0025-ext4-ext4_get_reserved_space-must-return-bytes-inste.patch -Content-Length: 718 -Lines: 23 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 8aa6790f876e81f5a2211fe1711a5fe3fe2d7b20) - -Signed-off-by: Dmitry Monakhov -Reviewed-by: Eric Sandeen -Acked-by: Mingming Cao -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -1052,7 +1052,7 @@ qsize_t ext4_get_reserved_space(struct i - EXT4_I(inode)->i_reserved_meta_blocks; - spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); - -- return total; -+ return (total << inode->i_blkbits); - } - /* - * Calculate the number of metadata blocks need to reserve - - -From linux@linux.site Thu Dec 10 21:25:57 2009 -Message-Id: <20091211052556.560487193@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:42 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Dmitry Monakhov , - Mingming Cao , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [30/34] ext4: quota macros cleanup -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0026-ext4-quota-macros-cleanup.patch -Content-Length: 5167 -Lines: 138 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 5aca07eb7d8f14d90c740834d15ca15277f4820c) - -Currently all quota block reservation macros contains hard-coded "2" -aka MAXQUOTAS value. This is no good because in some places it is not -obvious to understand what does this digit represent. Let's introduce -new macro with self descriptive name. - -Signed-off-by: Dmitry Monakhov -Acked-by: Mingming Cao -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/ext4_jbd2.h | 8 ++++++-- - fs/ext4/extents.c | 2 +- - fs/ext4/inode.c | 2 +- - fs/ext4/migrate.c | 4 ++-- - fs/ext4/namei.c | 8 ++++---- - 5 files changed, 14 insertions(+), 10 deletions(-) - ---- a/fs/ext4/ext4_jbd2.h -+++ b/fs/ext4/ext4_jbd2.h -@@ -49,7 +49,7 @@ - - #define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ - EXT4_XATTR_TRANS_BLOCKS - 2 + \ -- 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) -+ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) - - /* - * Define the number of metadata blocks we need to account to modify data. -@@ -57,7 +57,7 @@ - * This include super block, inode block, quota blocks and xattr blocks - */ - #define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \ -- 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) -+ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) - - /* Delete operations potentially hit one directory's namespace plus an - * entire inode, plus arbitrary amounts of bitmap/indirection data. Be -@@ -92,6 +92,7 @@ - * but inode, sb and group updates are done only once */ - #define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0) -+ - #define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0) - #else -@@ -99,6 +100,9 @@ - #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 - #define EXT4_QUOTA_DEL_BLOCKS(sb) 0 - #endif -+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb)) -+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) -+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) - - int - ext4_mark_iloc_dirty(handle_t *handle, ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -2167,7 +2167,7 @@ ext4_ext_rm_leaf(handle_t *handle, struc - correct_index = 1; - credits += (ext_depth(inode)) + 1; - } -- credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); -+ credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); - - err = ext4_ext_truncate_extend_restart(handle, inode, credits); - if (err) ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -5231,7 +5231,7 @@ int ext4_setattr(struct dentry *dentry, - - /* (user+group)*(old+new) structure, inode write (sb, - * inode block, ? - but truncate inode update has it) */ -- handle = ext4_journal_start(inode, 2*(EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)+ -+ handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+ - EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3); - if (IS_ERR(handle)) { - error = PTR_ERR(handle); ---- a/fs/ext4/migrate.c -+++ b/fs/ext4/migrate.c -@@ -238,7 +238,7 @@ static int extend_credit_for_blkdel(hand - * So allocate a credit of 3. We may update - * quota (user and group). - */ -- needed = 3 + 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); -+ needed = 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); - - if (ext4_journal_extend(handle, needed) != 0) - retval = ext4_journal_restart(handle, needed); -@@ -477,7 +477,7 @@ int ext4_ext_migrate(struct inode *inode - handle = ext4_journal_start(inode, - EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + -- 2 * EXT4_QUOTA_INIT_BLOCKS(inode->i_sb) -+ EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb) - + 1); - if (IS_ERR(handle)) { - retval = PTR_ERR(handle); ---- a/fs/ext4/namei.c -+++ b/fs/ext4/namei.c -@@ -1769,7 +1769,7 @@ static int ext4_create(struct inode *dir - retry: - handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + -- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); -+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - -@@ -1803,7 +1803,7 @@ static int ext4_mknod(struct inode *dir, - retry: - handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + -- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); -+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - -@@ -1840,7 +1840,7 @@ static int ext4_mkdir(struct inode *dir, - retry: - handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + -- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); -+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - -@@ -2253,7 +2253,7 @@ static int ext4_symlink(struct inode *di - retry: - handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 5 + -- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); -+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - - - -From linux@linux.site Thu Dec 10 21:25:57 2009 -Message-Id: <20091211052557.153813326@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:43 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Dmitry Monakhov , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [31/34] ext4: fix incorrect block reservation on quota transfer. -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0027-ext4-fix-incorrect-block-reservation-on-quota-transf.patch -Content-Length: 1036 -Lines: 27 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 194074acacebc169ded90a4657193f5180015051) - -Inside ->setattr() call both ATTR_UID and ATTR_GID may be valid -This means that we may end-up with transferring all quotas. Add -we have to reserve QUOTA_DEL_BLOCKS for all quotas, as we do in -case of QUOTA_INIT_BLOCKS. - -Signed-off-by: Dmitry Monakhov -Reviewed-by: Mingming Cao -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/inode.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -5232,7 +5232,7 @@ int ext4_setattr(struct dentry *dentry, - /* (user+group)*(old+new) structure, inode write (sb, - * inode block, ? - but truncate inode update has it) */ - handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+ -- EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3); -+ EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3); - if (IS_ERR(handle)) { - error = PTR_ERR(handle); - goto err_out; - - -From linux@linux.site Thu Dec 10 21:25:58 2009 -Message-Id: <20091211052557.723287400@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:44 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Jan Kara , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [32/34] ext4: Wait for proper transaction commit on fsync -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0028-ext4-Wait-for-proper-transaction-commit-on-fsync.patch -Content-Length: 7849 -Lines: 252 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit b436b9bef84de6893e86346d8fbf7104bc520645) - -We cannot rely on buffer dirty bits during fsync because pdflush can come -before fsync is called and clear dirty bits without forcing a transaction -commit. What we do is that we track which transaction has last changed -the inode and which transaction last changed allocation and force it to -disk on fsync. - -Signed-off-by: Jan Kara -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/ext4.h | 7 +++++++ - fs/ext4/ext4_jbd2.h | 13 +++++++++++++ - fs/ext4/extents.c | 14 ++++++++++++-- - fs/ext4/fsync.c | 46 +++++++++++++++++----------------------------- - fs/ext4/inode.c | 29 +++++++++++++++++++++++++++++ - fs/ext4/super.c | 2 ++ - fs/jbd2/journal.c | 1 + - 7 files changed, 81 insertions(+), 31 deletions(-) - ---- a/fs/ext4/ext4.h -+++ b/fs/ext4/ext4.h -@@ -703,6 +703,13 @@ struct ext4_inode_info { - struct list_head i_aio_dio_complete_list; - /* current io_end structure for async DIO write*/ - ext4_io_end_t *cur_aio_dio; -+ -+ /* -+ * Transactions that contain inode's metadata needed to complete -+ * fsync and fdatasync, respectively. -+ */ -+ tid_t i_sync_tid; -+ tid_t i_datasync_tid; - }; - - /* ---- a/fs/ext4/ext4_jbd2.h -+++ b/fs/ext4/ext4_jbd2.h -@@ -258,6 +258,19 @@ static inline int ext4_jbd2_file_inode(h - return 0; - } - -+static inline void ext4_update_inode_fsync_trans(handle_t *handle, -+ struct inode *inode, -+ int datasync) -+{ -+ struct ext4_inode_info *ei = EXT4_I(inode); -+ -+ if (ext4_handle_valid(handle)) { -+ ei->i_sync_tid = handle->h_transaction->t_tid; -+ if (datasync) -+ ei->i_datasync_tid = handle->h_transaction->t_tid; -+ } -+} -+ - /* super.c */ - int ext4_force_commit(struct super_block *sb); - ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -3064,6 +3064,8 @@ ext4_ext_handle_uninitialized_extents(ha - if (flags == EXT4_GET_BLOCKS_DIO_CONVERT_EXT) { - ret = ext4_convert_unwritten_extents_dio(handle, inode, - path); -+ if (ret >= 0) -+ ext4_update_inode_fsync_trans(handle, inode, 1); - goto out2; - } - /* buffered IO case */ -@@ -3091,6 +3093,8 @@ ext4_ext_handle_uninitialized_extents(ha - ret = ext4_ext_convert_to_initialized(handle, inode, - path, iblock, - max_blocks); -+ if (ret >= 0) -+ ext4_update_inode_fsync_trans(handle, inode, 1); - out: - if (ret <= 0) { - err = ret; -@@ -3329,10 +3333,16 @@ int ext4_ext_get_blocks(handle_t *handle - allocated = ext4_ext_get_actual_len(&newex); - set_buffer_new(bh_result); - -- /* Cache only when it is _not_ an uninitialized extent */ -- if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) -+ /* -+ * Cache the extent and update transaction to commit on fdatasync only -+ * when it is _not_ an uninitialized extent. -+ */ -+ if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) { - ext4_ext_put_in_cache(inode, iblock, allocated, newblock, - EXT4_EXT_CACHE_EXTENT); -+ ext4_update_inode_fsync_trans(handle, inode, 1); -+ } else -+ ext4_update_inode_fsync_trans(handle, inode, 0); - out: - if (allocated > max_blocks) - allocated = max_blocks; ---- a/fs/ext4/fsync.c -+++ b/fs/ext4/fsync.c -@@ -51,25 +51,30 @@ - int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) - { - struct inode *inode = dentry->d_inode; -+ struct ext4_inode_info *ei = EXT4_I(inode); - journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; -- int err, ret = 0; -+ int ret; -+ tid_t commit_tid; - - J_ASSERT(ext4_journal_current_handle() == NULL); - - trace_ext4_sync_file(file, dentry, datasync); - -+ if (inode->i_sb->s_flags & MS_RDONLY) -+ return 0; -+ - ret = flush_aio_dio_completed_IO(inode); - if (ret < 0) - return ret; -+ -+ if (!journal) -+ return simple_fsync(file, dentry, datasync); -+ - /* -- * data=writeback: -+ * data=writeback,ordered: - * The caller's filemap_fdatawrite()/wait will sync the data. -- * sync_inode() will sync the metadata -- * -- * data=ordered: -- * The caller's filemap_fdatawrite() will write the data and -- * sync_inode() will write the inode if it is dirty. Then the caller's -- * filemap_fdatawait() will wait on the pages. -+ * Metadata is in the journal, we wait for proper transaction to -+ * commit here. - * - * data=journal: - * filemap_fdatawrite won't do anything (the buffers are clean). -@@ -82,27 +87,10 @@ int ext4_sync_file(struct file *file, st - if (ext4_should_journal_data(inode)) - return ext4_force_commit(inode->i_sb); - -- if (!journal) -- ret = sync_mapping_buffers(inode->i_mapping); -- -- if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) -- goto out; -- -- /* -- * The VFS has written the file data. If the inode is unaltered -- * then we need not start a commit. -- */ -- if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) { -- struct writeback_control wbc = { -- .sync_mode = WB_SYNC_ALL, -- .nr_to_write = 0, /* sys_fsync did this */ -- }; -- err = sync_inode(inode, &wbc); -- if (ret == 0) -- ret = err; -- } --out: -- if (journal && (journal->j_flags & JBD2_BARRIER)) -+ commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; -+ if (jbd2_log_start_commit(journal, commit_tid)) -+ jbd2_log_wait_commit(journal, commit_tid); -+ else if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); - return ret; - } ---- a/fs/ext4/inode.c -+++ b/fs/ext4/inode.c -@@ -1025,6 +1025,8 @@ static int ext4_ind_get_blocks(handle_t - goto cleanup; - - set_buffer_new(bh_result); -+ -+ ext4_update_inode_fsync_trans(handle, inode, 1); - got_it: - map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key)); - if (count > blocks_to_boundary) -@@ -4794,6 +4796,7 @@ struct inode *ext4_iget(struct super_blo - struct ext4_inode *raw_inode; - struct ext4_inode_info *ei; - struct inode *inode; -+ journal_t *journal = EXT4_SB(sb)->s_journal; - long ret; - int block; - -@@ -4858,6 +4861,31 @@ struct inode *ext4_iget(struct super_blo - ei->i_data[block] = raw_inode->i_block[block]; - INIT_LIST_HEAD(&ei->i_orphan); - -+ /* -+ * Set transaction id's of transactions that have to be committed -+ * to finish f[data]sync. We set them to currently running transaction -+ * as we cannot be sure that the inode or some of its metadata isn't -+ * part of the transaction - the inode could have been reclaimed and -+ * now it is reread from disk. -+ */ -+ if (journal) { -+ transaction_t *transaction; -+ tid_t tid; -+ -+ spin_lock(&journal->j_state_lock); -+ if (journal->j_running_transaction) -+ transaction = journal->j_running_transaction; -+ else -+ transaction = journal->j_committing_transaction; -+ if (transaction) -+ tid = transaction->t_tid; -+ else -+ tid = journal->j_commit_sequence; -+ spin_unlock(&journal->j_state_lock); -+ ei->i_sync_tid = tid; -+ ei->i_datasync_tid = tid; -+ } -+ - if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { - ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); - if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > -@@ -5112,6 +5140,7 @@ static int ext4_do_update_inode(handle_t - err = rc; - ei->i_state &= ~EXT4_STATE_NEW; - -+ ext4_update_inode_fsync_trans(handle, inode, 0); - out_brelse: - brelse(bh); - ext4_std_error(inode->i_sb, err); ---- a/fs/ext4/super.c -+++ b/fs/ext4/super.c -@@ -706,6 +706,8 @@ static struct inode *ext4_alloc_inode(st - spin_lock_init(&(ei->i_block_reservation_lock)); - INIT_LIST_HEAD(&ei->i_aio_dio_complete_list); - ei->cur_aio_dio = NULL; -+ ei->i_sync_tid = 0; -+ ei->i_datasync_tid = 0; - - return &ei->vfs_inode; - } ---- a/fs/jbd2/journal.c -+++ b/fs/jbd2/journal.c -@@ -78,6 +78,7 @@ EXPORT_SYMBOL(jbd2_journal_errno); - EXPORT_SYMBOL(jbd2_journal_ack_err); - EXPORT_SYMBOL(jbd2_journal_clear_err); - EXPORT_SYMBOL(jbd2_log_wait_commit); -+EXPORT_SYMBOL(jbd2_log_start_commit); - EXPORT_SYMBOL(jbd2_journal_start_commit); - EXPORT_SYMBOL(jbd2_journal_force_commit_nested); - EXPORT_SYMBOL(jbd2_journal_wipe); - - -From linux@linux.site Thu Dec 10 21:25:58 2009 -Message-Id: <20091211052558.272572522@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:45 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - Akira Fujita , - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [33/34] ext4: Fix insufficient checks in EXT4_IOC_MOVE_EXT -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0029-ext4-Fix-insufficient-checks-in-EXT4_IOC_MOVE_EXT.patch -Content-Length: 2732 -Lines: 94 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit 4a58579b9e4e2a35d57e6c9c8483e52f6f1b7fd6) - -This patch fixes three problems in the handling of the -EXT4_IOC_MOVE_EXT ioctl: - -1. In current EXT4_IOC_MOVE_EXT, there are read access mode checks for -original and donor files, but they allow the illegal write access to -donor file, since donor file is overwritten by original file data. To -fix this problem, change access mode checks of original (r->r/w) and -donor (r->w) files. - -2. Disallow the use of donor files that have a setuid or setgid bits. - -3. Call mnt_want_write() and mnt_drop_write() before and after -ext4_move_extents() calling to get write access to a mount. - -Signed-off-by: Akira Fujita -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/ioctl.c | 30 ++++++++++++++++++------------ - fs/ext4/move_extent.c | 7 +++++++ - 2 files changed, 25 insertions(+), 12 deletions(-) - ---- a/fs/ext4/ioctl.c -+++ b/fs/ext4/ioctl.c -@@ -221,32 +221,38 @@ setversion_out: - struct file *donor_filp; - int err; - -+ if (!(filp->f_mode & FMODE_READ) || -+ !(filp->f_mode & FMODE_WRITE)) -+ return -EBADF; -+ - if (copy_from_user(&me, - (struct move_extent __user *)arg, sizeof(me))) - return -EFAULT; -+ me.moved_len = 0; - - donor_filp = fget(me.donor_fd); - if (!donor_filp) - return -EBADF; - -- if (!capable(CAP_DAC_OVERRIDE)) { -- if ((current->real_cred->fsuid != inode->i_uid) || -- !(inode->i_mode & S_IRUSR) || -- !(donor_filp->f_dentry->d_inode->i_mode & -- S_IRUSR)) { -- fput(donor_filp); -- return -EACCES; -- } -+ if (!(donor_filp->f_mode & FMODE_WRITE)) { -+ err = -EBADF; -+ goto mext_out; - } - -- me.moved_len = 0; -+ err = mnt_want_write(filp->f_path.mnt); -+ if (err) -+ goto mext_out; -+ - err = ext4_move_extents(filp, donor_filp, me.orig_start, - me.donor_start, me.len, &me.moved_len); -- fput(donor_filp); -+ mnt_drop_write(filp->f_path.mnt); -+ if (me.moved_len > 0) -+ file_remove_suid(donor_filp); - - if (copy_to_user((struct move_extent *)arg, &me, sizeof(me))) -- return -EFAULT; -- -+ err = -EFAULT; -+mext_out: -+ fput(donor_filp); - return err; - } - ---- a/fs/ext4/move_extent.c -+++ b/fs/ext4/move_extent.c -@@ -957,6 +957,13 @@ mext_check_arguments(struct inode *orig_ - return -EINVAL; - } - -+ if (donor_inode->i_mode & (S_ISUID|S_ISGID)) { -+ ext4_debug("ext4 move extent: suid or sgid is set" -+ " to donor file [ino:orig %lu, donor %lu]\n", -+ orig_inode->i_ino, donor_inode->i_ino); -+ return -EINVAL; -+ } -+ - /* Ext4 move extent does not support swapfile */ - if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) { - ext4_debug("ext4 move extent: The argument files should " - - -From linux@linux.site Thu Dec 10 21:25:59 2009 -Message-Id: <20091211052558.863762484@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:46 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk, - "Theodore Tso" , - Greg Kroah-Hartman -Subject: [34/34] ext4: Fix potential fiemap deadlock (mmap_sem vs. i_data_sem) -References: <20091211052312.805428372@linux.site> -Content-Disposition: inline; filename=0030-ext4-Fix-potential-fiemap-deadlock-mmap_sem-vs.-i_da.patch -Content-Length: 5029 -Lines: 115 - -2.6.32-stable review patch. If anyone has any objections, please let us know. - ------------------- - -(cherry picked from commit fab3a549e204172236779f502eccb4f9bf0dc87d) - -Fix the following potential circular locking dependency between -mm->mmap_sem and ei->i_data_sem: - - ======================================================= - [ INFO: possible circular locking dependency detected ] - 2.6.32-04115-gec044c5 #37 - ------------------------------------------------------- - ureadahead/1855 is trying to acquire lock: - (&mm->mmap_sem){++++++}, at: [] might_fault+0x5c/0xac - - but task is already holding lock: - (&ei->i_data_sem){++++..}, at: [] ext4_fiemap+0x11b/0x159 - - which lock already depends on the new lock. - - the existing dependency chain (in reverse order) is: - - -> #1 (&ei->i_data_sem){++++..}: - [] __lock_acquire+0xb67/0xd0f - [] lock_acquire+0xdc/0x102 - [] down_read+0x51/0x84 - [] ext4_get_blocks+0x50/0x2a5 - [] ext4_get_block+0xab/0xef - [] do_mpage_readpage+0x198/0x48d - [] mpage_readpages+0xd0/0x114 - [] ext4_readpages+0x1d/0x1f - [] __do_page_cache_readahead+0x12f/0x1bc - [] ra_submit+0x21/0x25 - [] filemap_fault+0x19f/0x32c - [] __do_fault+0x55/0x3a2 - [] handle_mm_fault+0x327/0x734 - [] do_page_fault+0x292/0x2aa - [] page_fault+0x25/0x30 - [] clear_user+0x38/0x3c - [] padzero+0x20/0x31 - [] load_elf_binary+0x8bc/0x17ed - [] search_binary_handler+0xc2/0x259 - [] load_script+0x1b8/0x1cc - [] search_binary_handler+0xc2/0x259 - [] do_execve+0x1ce/0x2cf - [] sys_execve+0x43/0x5a - [] stub_execve+0x6a/0xc0 - - -> #0 (&mm->mmap_sem){++++++}: - [] __lock_acquire+0xa11/0xd0f - [] lock_acquire+0xdc/0x102 - [] might_fault+0x89/0xac - [] fiemap_fill_next_extent+0x95/0xda - [] ext4_ext_fiemap_cb+0x138/0x157 - [] ext4_ext_walk_space+0x178/0x1f1 - [] ext4_fiemap+0x13c/0x159 - [] do_vfs_ioctl+0x348/0x4d6 - [] sys_ioctl+0x56/0x79 - [] system_call_fastpath+0x16/0x1b - - other info that might help us debug this: - - 1 lock held by ureadahead/1855: - #0: (&ei->i_data_sem){++++..}, at: [] ext4_fiemap+0x11b/0x159 - - stack backtrace: - Pid: 1855, comm: ureadahead Not tainted 2.6.32-04115-gec044c5 #37 - Call Trace: - [] print_circular_bug+0xa8/0xb7 - [] __lock_acquire+0xa11/0xd0f - [] ? sched_clock+0x9/0xd - [] lock_acquire+0xdc/0x102 - [] ? might_fault+0x5c/0xac - [] might_fault+0x89/0xac - [] ? might_fault+0x5c/0xac - [] ? __kmalloc+0x13b/0x18c - [] fiemap_fill_next_extent+0x95/0xda - [] ext4_ext_fiemap_cb+0x138/0x157 - [] ? ext4_ext_fiemap_cb+0x0/0x157 - [] ext4_ext_walk_space+0x178/0x1f1 - [] ext4_fiemap+0x13c/0x159 - [] ? might_fault+0x5c/0xac - [] do_vfs_ioctl+0x348/0x4d6 - [] ? __up_read+0x8d/0x95 - [] ? retint_swapgs+0x13/0x1b - [] sys_ioctl+0x56/0x79 - [] system_call_fastpath+0x16/0x1b - -Signed-off-by: "Theodore Ts'o" -Signed-off-by: Greg Kroah-Hartman ---- - fs/ext4/extents.c | 4 ++-- - 1 file changed, 2 insertions(+), 2 deletions(-) - ---- a/fs/ext4/extents.c -+++ b/fs/ext4/extents.c -@@ -1761,7 +1761,9 @@ int ext4_ext_walk_space(struct inode *in - while (block < last && block != EXT_MAX_BLOCK) { - num = last - block; - /* find extent for this block */ -+ down_read(&EXT4_I(inode)->i_data_sem); - path = ext4_ext_find_extent(inode, block, path); -+ up_read(&EXT4_I(inode)->i_data_sem); - if (IS_ERR(path)) { - err = PTR_ERR(path); - path = NULL; -@@ -3730,10 +3732,8 @@ int ext4_fiemap(struct inode *inode, str - * Walk the extent tree gathering extent information. - * ext4_ext_fiemap_cb will push extents back to user. - */ -- down_read(&EXT4_I(inode)->i_data_sem); - error = ext4_ext_walk_space(inode, start_blk, len_blks, - ext4_ext_fiemap_cb, fieinfo); -- up_read(&EXT4_I(inode)->i_data_sem); - } - - return error; - - -From linux@linux.site Thu Dec 10 21:25:40 2009 -Message-Id: <20091211052312.805428372@linux.site> -User-Agent: quilt/0.47-14.9 -Date: Thu, 10 Dec 2009 21:23:12 -0800 -From: Greg KH -To: linux-kernel@vger.kernel.org, - stable@kernel.org -Cc: stable-review@kernel.org, - torvalds@linux-foundation.org, - akpm@linux-foundation.org, - alan@lxorguk.ukuu.org.uk -Subject: [00/34] 2.6.32.1-stable review -Content-Length: 2372 -Lines: 51 - -This is the start of the stable review cycle for the 2.6.32.1 release. -There are 34 patches in this series, all will be posted as a response to -this one. If anyone has any issues with these being applied, please let -us know. If anyone is a maintainer of the proper subsystem, and wants -to add a Signed-off-by: line to the patch, please respond with it. - -As was done with the 2.6.31.8-rc1 release, this is not all of the -patches in the -stable queue, just a huge chunk of ext4 patches here, -and a few scsi ones, which should all get out sooner rather than later. -So note that there will be more 2.6.32-stable releases coming, this is -just the first in the series. - -Responses should be made by Sunday, Dec 13 04:00:00 UTC 2009 -Anything received after that time might be too late. - -The whole patch series can be found in one patch at: - kernel.org/pub/linux/kernel/v2.6/stable-review/patch-2.6.32.1-rc1.gz -and the diffstat can be found below. - -thanks, - -greg k-h - - Documentation/filesystems/ext4.txt | 10 +- - Makefile | 2 +- - drivers/scsi/hosts.c | 13 ++- - drivers/scsi/lpfc/lpfc_init.c | 2 +- - drivers/scsi/megaraid/megaraid_sas.c | 8 +- - drivers/scsi/qla2xxx/qla_attr.c | 3 +- - drivers/scsi/scsi_lib_dma.c | 4 +- - fs/ext4/balloc.c | 8 +- - fs/ext4/block_validity.c | 2 +- - fs/ext4/ext4.h | 8 + - fs/ext4/ext4_jbd2.h | 21 +++- - fs/ext4/extents.c | 22 ++- - fs/ext4/fsync.c | 54 +++---- - fs/ext4/inode.c | 81 +++++++--- - fs/ext4/ioctl.c | 29 +++-- - fs/ext4/mballoc.c | 40 ++++- - fs/ext4/migrate.c | 4 +- - fs/ext4/move_extent.c | 278 ++++++++++++++++------------------ - fs/ext4/namei.c | 38 ++--- - fs/ext4/resize.c | 2 +- - fs/ext4/super.c | 40 ++++-- - fs/ext4/xattr.c | 7 +- - fs/jbd2/commit.c | 4 + - fs/jbd2/journal.c | 5 + - include/linux/sched.h | 13 ++- - include/scsi/osd_protocol.h | 1 + - include/scsi/scsi_host.h | 16 ++- - 27 files changed, 424 insertions(+), 291 deletions(-) - diff --git a/queue-2.6.32/scsi-megaraid_sas-fix-64-bit-sense-pointer-truncation.patch b/queue-2.6.32/scsi-megaraid_sas-fix-64-bit-sense-pointer-truncation.patch deleted file mode 100644 index f936137a3fb..00000000000 --- a/queue-2.6.32/scsi-megaraid_sas-fix-64-bit-sense-pointer-truncation.patch +++ /dev/null @@ -1,51 +0,0 @@ -From 7b2519afa1abd1b9f63aa1e90879307842422dae Mon Sep 17 00:00:00 2001 -From: Yang, Bo -Date: Tue, 6 Oct 2009 14:52:20 -0600 -Subject: SCSI: megaraid_sas: fix 64 bit sense pointer truncation - -From: Yang, Bo - -commit 7b2519afa1abd1b9f63aa1e90879307842422dae upstream. - -The current sense pointer is cast to a u32 pointer, which can truncate -on 64 bits. Fix by using unsigned long instead. - -Signed-off-by Bo Yang -Signed-off-by: James Bottomley -Signed-off-by: Greg Kroah-Hartman - ---- - drivers/scsi/megaraid/megaraid_sas.c | 8 ++++---- - 1 file changed, 4 insertions(+), 4 deletions(-) - ---- a/drivers/scsi/megaraid/megaraid_sas.c -+++ b/drivers/scsi/megaraid/megaraid_sas.c -@@ -3032,7 +3032,7 @@ megasas_mgmt_fw_ioctl(struct megasas_ins - int error = 0, i; - void *sense = NULL; - dma_addr_t sense_handle; -- u32 *sense_ptr; -+ unsigned long *sense_ptr; - - memset(kbuff_arr, 0, sizeof(kbuff_arr)); - -@@ -3109,7 +3109,7 @@ megasas_mgmt_fw_ioctl(struct megasas_ins - } - - sense_ptr = -- (u32 *) ((unsigned long)cmd->frame + ioc->sense_off); -+ (unsigned long *) ((unsigned long)cmd->frame + ioc->sense_off); - *sense_ptr = sense_handle; - } - -@@ -3140,8 +3140,8 @@ megasas_mgmt_fw_ioctl(struct megasas_ins - * sense_ptr points to the location that has the user - * sense buffer address - */ -- sense_ptr = (u32 *) ((unsigned long)ioc->frame.raw + -- ioc->sense_off); -+ sense_ptr = (unsigned long *) ((unsigned long)ioc->frame.raw + -+ ioc->sense_off); - - if (copy_to_user((void __user *)((unsigned long)(*sense_ptr)), - sense, ioc->sense_len)) { diff --git a/queue-2.6.32/scsi-osd_protocol.h-add-missing-include.patch b/queue-2.6.32/scsi-osd_protocol.h-add-missing-include.patch deleted file mode 100644 index 6726c96f577..00000000000 --- a/queue-2.6.32/scsi-osd_protocol.h-add-missing-include.patch +++ /dev/null @@ -1,28 +0,0 @@ -From 0899638688f223fd9e9fee60d662665e11693d12 Mon Sep 17 00:00:00 2001 -From: Martin Michlmayr -Date: Mon, 16 Nov 2009 20:49:25 +0200 -Subject: SCSI: osd_protocol.h: Add missing #include - -From: Martin Michlmayr - -commit 0899638688f223fd9e9fee60d662665e11693d12 upstream. - -include/scsi/osd_protocol.h uses ALIGN() without an #include -, leading to: -| include/scsi/osd_protocol.h:362: error: implicit declaration of function 'ALIGN' - -Signed-off-by: Martin Michlmayr -Signed-off-by: Boaz Harrosh -Signed-off-by: James Bottomley -Signed-off-by: Greg Kroah-Hartman - ---- a/include/scsi/osd_protocol.h -+++ b/include/scsi/osd_protocol.h -@@ -17,6 +17,7 @@ - #define __OSD_PROTOCOL_H__ - - #include -+#include - #include - #include - diff --git a/queue-2.6.32/scsi-scsi_lib_dma-fix-bug-with-dma-maps-on-nested-scsi-objects.patch b/queue-2.6.32/scsi-scsi_lib_dma-fix-bug-with-dma-maps-on-nested-scsi-objects.patch deleted file mode 100644 index 57cb6dd1f61..00000000000 --- a/queue-2.6.32/scsi-scsi_lib_dma-fix-bug-with-dma-maps-on-nested-scsi-objects.patch +++ /dev/null @@ -1,153 +0,0 @@ -From d139b9bd0e52dda14fd13412e7096e68b56d0076 Mon Sep 17 00:00:00 2001 -From: James Bottomley -Date: Thu, 5 Nov 2009 13:33:12 -0600 -Subject: SCSI: scsi_lib_dma: fix bug with dma maps on nested scsi objects - -From: James Bottomley - -commit d139b9bd0e52dda14fd13412e7096e68b56d0076 upstream. - -Some of our virtual SCSI hosts don't have a proper bus parent at the -top, which can be a problem for doing DMA on them - -This patch makes the host device cache a pointer to the physical bus -device and provides an extra API for setting it (the normal API picks -it up from the parent). This patch also modifies the qla2xxx and lpfc -vport logic to use the new DMA host setting API. - -Acked-By: James Smart -Signed-off-by: James Bottomley -Signed-off-by: Greg Kroah-Hartman - ---- - drivers/scsi/hosts.c | 13 ++++++++++--- - drivers/scsi/lpfc/lpfc_init.c | 2 +- - drivers/scsi/qla2xxx/qla_attr.c | 3 ++- - drivers/scsi/scsi_lib_dma.c | 4 ++-- - include/scsi/scsi_host.h | 16 +++++++++++++++- - 5 files changed, 30 insertions(+), 8 deletions(-) - ---- a/drivers/scsi/hosts.c -+++ b/drivers/scsi/hosts.c -@@ -180,14 +180,20 @@ void scsi_remove_host(struct Scsi_Host * - EXPORT_SYMBOL(scsi_remove_host); - - /** -- * scsi_add_host - add a scsi host -+ * scsi_add_host_with_dma - add a scsi host with dma device - * @shost: scsi host pointer to add - * @dev: a struct device of type scsi class -+ * @dma_dev: dma device for the host -+ * -+ * Note: You rarely need to worry about this unless you're in a -+ * virtualised host environments, so use the simpler scsi_add_host() -+ * function instead. - * - * Return value: - * 0 on success / != 0 for error - **/ --int scsi_add_host(struct Scsi_Host *shost, struct device *dev) -+int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, -+ struct device *dma_dev) - { - struct scsi_host_template *sht = shost->hostt; - int error = -EINVAL; -@@ -207,6 +213,7 @@ int scsi_add_host(struct Scsi_Host *shos - - if (!shost->shost_gendev.parent) - shost->shost_gendev.parent = dev ? dev : &platform_bus; -+ shost->dma_dev = dma_dev; - - error = device_add(&shost->shost_gendev); - if (error) -@@ -262,7 +269,7 @@ int scsi_add_host(struct Scsi_Host *shos - fail: - return error; - } --EXPORT_SYMBOL(scsi_add_host); -+EXPORT_SYMBOL(scsi_add_host_with_dma); - - static void scsi_host_dev_release(struct device *dev) - { ---- a/drivers/scsi/lpfc/lpfc_init.c -+++ b/drivers/scsi/lpfc/lpfc_init.c -@@ -2408,7 +2408,7 @@ lpfc_create_port(struct lpfc_hba *phba, - vport->els_tmofunc.function = lpfc_els_timeout; - vport->els_tmofunc.data = (unsigned long)vport; - -- error = scsi_add_host(shost, dev); -+ error = scsi_add_host_with_dma(shost, dev, &phba->pcidev->dev); - if (error) - goto out_put_shost; - ---- a/drivers/scsi/qla2xxx/qla_attr.c -+++ b/drivers/scsi/qla2xxx/qla_attr.c -@@ -1654,7 +1654,8 @@ qla24xx_vport_create(struct fc_vport *fc - fc_vport_set_state(fc_vport, FC_VPORT_LINKDOWN); - } - -- if (scsi_add_host(vha->host, &fc_vport->dev)) { -+ if (scsi_add_host_with_dma(vha->host, &fc_vport->dev, -+ &ha->pdev->dev)) { - DEBUG15(printk("scsi(%ld): scsi_add_host failure for VP[%d].\n", - vha->host_no, vha->vp_idx)); - goto vport_create_failed_2; ---- a/drivers/scsi/scsi_lib_dma.c -+++ b/drivers/scsi/scsi_lib_dma.c -@@ -23,7 +23,7 @@ int scsi_dma_map(struct scsi_cmnd *cmd) - int nseg = 0; - - if (scsi_sg_count(cmd)) { -- struct device *dev = cmd->device->host->shost_gendev.parent; -+ struct device *dev = cmd->device->host->dma_dev; - - nseg = dma_map_sg(dev, scsi_sglist(cmd), scsi_sg_count(cmd), - cmd->sc_data_direction); -@@ -41,7 +41,7 @@ EXPORT_SYMBOL(scsi_dma_map); - void scsi_dma_unmap(struct scsi_cmnd *cmd) - { - if (scsi_sg_count(cmd)) { -- struct device *dev = cmd->device->host->shost_gendev.parent; -+ struct device *dev = cmd->device->host->dma_dev; - - dma_unmap_sg(dev, scsi_sglist(cmd), scsi_sg_count(cmd), - cmd->sc_data_direction); ---- a/include/scsi/scsi_host.h -+++ b/include/scsi/scsi_host.h -@@ -677,6 +677,12 @@ struct Scsi_Host { - void *shost_data; - - /* -+ * Points to the physical bus device we'd use to do DMA -+ * Needed just in case we have virtual hosts. -+ */ -+ struct device *dma_dev; -+ -+ /* - * We should ensure that this is aligned, both for better performance - * and also because some compilers (m68k) don't automatically force - * alignment to a long boundary. -@@ -720,7 +726,9 @@ extern int scsi_queue_work(struct Scsi_H - extern void scsi_flush_work(struct Scsi_Host *); - - extern struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *, int); --extern int __must_check scsi_add_host(struct Scsi_Host *, struct device *); -+extern int __must_check scsi_add_host_with_dma(struct Scsi_Host *, -+ struct device *, -+ struct device *); - extern void scsi_scan_host(struct Scsi_Host *); - extern void scsi_rescan_device(struct device *); - extern void scsi_remove_host(struct Scsi_Host *); -@@ -731,6 +739,12 @@ extern const char *scsi_host_state_name( - - extern u64 scsi_calculate_bounce_limit(struct Scsi_Host *); - -+static inline int __must_check scsi_add_host(struct Scsi_Host *host, -+ struct device *dev) -+{ -+ return scsi_add_host_with_dma(host, dev, dev); -+} -+ - static inline struct device *scsi_get_device(struct Scsi_Host *shost) - { - return shost->shost_gendev.parent; diff --git a/queue-2.6.32/series b/queue-2.6.32/series deleted file mode 100644 index 51c31723914..00000000000 --- a/queue-2.6.32/series +++ /dev/null @@ -1,34 +0,0 @@ -signal-fix-alternate-signal-stack-check.patch -scsi-scsi_lib_dma-fix-bug-with-dma-maps-on-nested-scsi-objects.patch -scsi-osd_protocol.h-add-missing-include.patch -scsi-megaraid_sas-fix-64-bit-sense-pointer-truncation.patch -0001-ext4-fix-potential-buffer-head-leak-when-add_dirent_.patch -0002-ext4-avoid-divide-by-zero-when-trying-to-mount-a-cor.patch -0003-ext4-fix-the-returned-block-count-if-EXT4_IOC_MOVE_E.patch -0004-ext4-fix-lock-order-problem-in-ext4_move_extents.patch -0005-ext4-fix-possible-recursive-locking-warning-in-EXT4_.patch -0006-ext4-plug-a-buffer_head-leak-in-an-error-path-of-ext.patch -0007-ext4-make-sure-directory-and-symlink-blocks-are-revo.patch -0008-ext4-fix-i_flags-access-in-ext4_da_writepages_trans_.patch -0009-ext4-journal-all-modifications-in-ext4_xattr_set_han.patch -0010-ext4-don-t-update-the-superblock-in-ext4_statfs.patch -0011-ext4-fix-uninit-block-bitmap-initialization-when-s_m.patch -0012-ext4-fix-block-validity-checks-so-they-work-correctl.patch -0013-ext4-avoid-issuing-unnecessary-barriers.patch -0014-ext4-fix-error-handling-in-ext4_ind_get_blocks.patch -0015-ext4-make-trim-discard-optional-and-off-by-default.patch -0016-ext4-make-norecovery-an-alias-for-noload.patch -0017-ext4-Fix-double-free-of-blocks-with-EXT4_IOC_MOVE_EX.patch -0018-ext4-initialize-moved_len-before-calling-ext4_move_e.patch -0019-ext4-move_extent_per_page-cleanup.patch -0020-jbd2-Add-ENOMEM-checking-in-and-for-jbd2_journal_wri.patch -0021-ext4-Return-the-PTR_ERR-of-the-correct-pointer-in-se.patch -0022-ext4-Avoid-data-filesystem-corruption-when-write-fai.patch -0023-ext4-wait-for-log-to-commit-when-umounting.patch -0024-ext4-remove-blocks-from-inode-prealloc-list-on-failu.patch -0025-ext4-ext4_get_reserved_space-must-return-bytes-inste.patch -0026-ext4-quota-macros-cleanup.patch -0027-ext4-fix-incorrect-block-reservation-on-quota-transf.patch -0028-ext4-Wait-for-proper-transaction-commit-on-fsync.patch -0029-ext4-Fix-insufficient-checks-in-EXT4_IOC_MOVE_EXT.patch -0030-ext4-Fix-potential-fiemap-deadlock-mmap_sem-vs.-i_da.patch diff --git a/queue-2.6.32/signal-fix-alternate-signal-stack-check.patch b/queue-2.6.32/signal-fix-alternate-signal-stack-check.patch deleted file mode 100644 index 73cd5fd018c..00000000000 --- a/queue-2.6.32/signal-fix-alternate-signal-stack-check.patch +++ /dev/null @@ -1,87 +0,0 @@ -From 2a855dd01bc1539111adb7233f587c5c468732ac Mon Sep 17 00:00:00 2001 -From: Sebastian Andrzej Siewior -Date: Sun, 25 Oct 2009 15:37:58 +0100 -Subject: signal: Fix alternate signal stack check - -From: Sebastian Andrzej Siewior - -commit 2a855dd01bc1539111adb7233f587c5c468732ac upstream. - -All architectures in the kernel increment/decrement the stack pointer -before storing values on the stack. - -On architectures which have the stack grow down sas_ss_sp == sp is not -on the alternate signal stack while sas_ss_sp + sas_ss_size == sp is -on the alternate signal stack. - -On architectures which have the stack grow up sas_ss_sp == sp is on -the alternate signal stack while sas_ss_sp + sas_ss_size == sp is not -on the alternate signal stack. - -The current implementation fails for architectures which have the -stack grow down on the corner case where sas_ss_sp == sp.This was -reported as Debian bug #544905 on AMD64. -Simplified test case: http://download.breakpoint.cc/tc-sig-stack.c - -The test case creates the following stack scenario: - 0xn0300 stack top - 0xn0200 alt stack pointer top (when switching to alt stack) - 0xn01ff alt stack end - 0xn0100 alt stack start == stack pointer - -If the signal is sent the stack pointer is pointing to the base -address of the alt stack and the kernel erroneously decides that it -has already switched to the alternate stack because of the current -check for "sp - sas_ss_sp < sas_ss_size" - -On parisc (stack grows up) the scenario would be: - 0xn0200 stack pointer - 0xn01ff alt stack end - 0xn0100 alt stack start = alt stack pointer base - (when switching to alt stack) - 0xn0000 stack base - -This is handled correctly by the current implementation. - -[ tglx: Modified for archs which have the stack grow up (parisc) which - would fail with the correct implementation for stack grows - down. Added a check for sp >= current->sas_ss_sp which is - strictly not necessary but makes the code symetric for both - variants ] - -Signed-off-by: Sebastian Andrzej Siewior -Cc: Oleg Nesterov -Cc: Roland McGrath -Cc: Kyle McMartin -LKML-Reference: <20091025143758.GA6653@Chamillionaire.breakpoint.cc> -Signed-off-by: Thomas Gleixner -Signed-off-by: Greg Kroah-Hartman - ---- - include/linux/sched.h | 13 ++++++++++--- - 1 file changed, 10 insertions(+), 3 deletions(-) - ---- a/include/linux/sched.h -+++ b/include/linux/sched.h -@@ -2086,11 +2086,18 @@ static inline int is_si_special(const st - return info <= SEND_SIG_FORCED; - } - --/* True if we are on the alternate signal stack. */ -- -+/* -+ * True if we are on the alternate signal stack. -+ */ - static inline int on_sig_stack(unsigned long sp) - { -- return (sp - current->sas_ss_sp < current->sas_ss_size); -+#ifdef CONFIG_STACK_GROWSUP -+ return sp >= current->sas_ss_sp && -+ sp - current->sas_ss_sp < current->sas_ss_size; -+#else -+ return sp > current->sas_ss_sp && -+ sp - current->sas_ss_sp <= current->sas_ss_size; -+#endif - } - - static inline int sas_ss_flags(unsigned long sp) -- 2.47.2