From 024eab4d5bf7e3168a2b71038b3e04e6b1f376ed Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Fri, 17 Jul 2009 09:01:04 -0400 Subject: ext4: Fix memory leak fix when mounting an ext4 filesystem The allocation of the ext4_group_info array was moved to a new function ext4_mb_add_group_info() in commit 5f21b0e6 so that online resize would use a common (and correct) codepath. Unfortunately, the call to the new ext4_mb_add_group_info() function was added without removing the code which originally allocated the array. This caused a memory leak each time an ext4 filesystem was mounted. The fix is simple; remove the code that did the original allocation, since it is no longer needed. Reported-by: Catalin Marinas Tested-by: Catalin Marinas Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index cd258463e2a9..cf9972090ad9 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2571,13 +2571,11 @@ static int ext4_mb_init_backend(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; - int metalen; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int num_meta_group_infos; int num_meta_group_infos_max; int array_size; - struct ext4_group_info **meta_group_info; struct ext4_group_desc *desc; /* This is the number of blocks used by GDT */ @@ -2622,22 +2620,6 @@ static int ext4_mb_init_backend(struct super_block *sb) goto err_freesgi; } EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; - - metalen = sizeof(*meta_group_info) << EXT4_DESC_PER_BLOCK_BITS(sb); - for (i = 0; i < num_meta_group_infos; i++) { - if ((i + 1) == num_meta_group_infos) - metalen = sizeof(*meta_group_info) * - (ngroups - - (i << EXT4_DESC_PER_BLOCK_BITS(sb))); - meta_group_info = kmalloc(metalen, GFP_KERNEL); - if (meta_group_info == NULL) { - printk(KERN_ERR "EXT4-fs: can't allocate mem for a " - "buddy group\n"); - goto err_freemeta; - } - sbi->s_group_info[i] = meta_group_info; - } - for (i = 0; i < ngroups; i++) { desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { @@ -2655,7 +2637,6 @@ err_freebuddy: while (i-- > 0) kfree(ext4_get_group_info(sb, i)); i = num_meta_group_infos; -err_freemeta: while (i-- > 0) kfree(sbi->s_group_info[i]); iput(sbi->s_buddy_cache); -- cgit v1.2.3 From 43b38520296d0c1730c78c878e1d6d1a49122091 Mon Sep 17 00:00:00 2001 From: Manish Katiyar Date: Mon, 27 Jul 2009 21:38:17 -0400 Subject: ext4: Fix typo in ext4/Kconfig Signed-off-by: Manish Katiyar Signed-off-by: "Theodore Ts'o" --- fs/ext4/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 418b6f3b0ae8..152304624644 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -37,7 +37,7 @@ config EXT4DEV_COMPAT To enable backwards compatibility so that systems that are still expecting to mount ext4 filesystems using ext4dev, - chose Y here. This feature will go away by 2.6.31, so + choose Y here. This feature will go away by 2.6.31, so please arrange to get your userspace programs fixed! config EXT4_FS_XATTR -- cgit v1.2.3 From 78f1ddbb498283c2445c11b0dfa666424c301803 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 27 Jul 2009 23:09:47 -0400 Subject: ext4: Avoid null pointer dereference when decoding EROFS w/o a journal We need to check to make sure a journal is present before checking the journal flags in ext4_decode_error(). Signed-off-by: Eric Sesterhenn Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8f4f079e6b9a..fe3f376b7df2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -344,7 +344,8 @@ static const char *ext4_decode_error(struct super_block *sb, int errno, errstr = "Out of memory"; break; case -EROFS: - if (!sb || EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT) + if (!sb || (EXT4_SB(sb)->s_journal && + EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)) errstr = "Journal has aborted"; else errstr = "Readonly filesystem"; -- cgit v1.2.3 From f6f50e28f0cb8d7bcdfaacc83129f005dede11b1 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 17 Jul 2009 10:40:01 -0400 Subject: jbd2: Fail to load a journal if it is too short Due to on disk corruption, it can happen that journal is too short. Fail to load it in such case so that we don't oops somewhere later. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/jbd2/journal.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index e378cb383979..a8a358bc0f21 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1187,6 +1187,12 @@ static int journal_reset(journal_t *journal) first = be32_to_cpu(sb->s_first); last = be32_to_cpu(sb->s_maxlen); + if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) { + printk(KERN_ERR "JBD: Journal too short (blocks %llu-%llu).\n", + first, last); + journal_fail_superblock(journal); + return -EINVAL; + } journal->j_first = first; journal->j_last = last; -- cgit v1.2.3 From 6487a9d3b5476ffd1bbbe97e58cf26dbeb7a5d4a Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Fri, 17 Jul 2009 10:54:08 -0400 Subject: ext4: More buffer head reference leaks After the patch I posted last week regarding buffer head ref leaks in no-journal mode, I looked at all the code that uses buffer heads and searched for more potential leaks. The patch below fixes the issues I found; these can occur even when a journal is present. The change to inode.c fixes a double release if ext4_journal_get_create_access() fails. The changes to namei.c are more complicated. add_dirent_to_buf() will release the input buffer head EXCEPT when it returns -ENOSPC. There are some callers of this routine that don't always do the brelse() in the event that -ENOSPC is returned. Unfortunately, to put this fix into ext4_add_entry() required capturing the return value of make_indexed_dir() and add_dirent_to_buf(). Signed-off-by: Curt Wohlgemuth Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 ++- fs/ext4/namei.c | 16 ++++++++++++---- 2 files changed, 14 insertions(+), 5 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f9c642b22efa..deb14a728791 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -762,8 +762,9 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, BUFFER_TRACE(bh, "call get_create_access"); err = ext4_journal_get_create_access(handle, bh); if (err) { + /* Don't brelse(bh) here; it's done in + * ext4_journal_forget() below */ unlock_buffer(bh); - brelse(bh); goto failed; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 114abe5d2c1d..fea14dbd3c22 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1518,8 +1518,12 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return retval; if (blocks == 1 && !dx_fallback && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) - return make_indexed_dir(handle, dentry, inode, bh); + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { + retval = make_indexed_dir(handle, dentry, inode, bh); + if (retval == -ENOSPC) + brelse(bh); + return retval; + } brelse(bh); } bh = ext4_append(handle, dir, &block, &retval); @@ -1528,7 +1532,10 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, 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); + if (retval == -ENOSPC) + brelse(bh); + return retval; } /* @@ -1657,7 +1664,8 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, if (!de) goto cleanup; err = add_dirent_to_buf(handle, dentry, inode, de, bh); - bh = NULL; + if (err != -ENOSPC) + bh = NULL; goto cleanup; journal_error: -- cgit v1.2.3 From 5a4a798937f92413cb7dbdb6bd554186024092e9 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 5 Jul 2009 22:33:08 -0400 Subject: ext4: Remove unnecessary semicolons in mballoc.c Signed-off-by: Joe Perches Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index cf9972090ad9..ba49e0c596f2 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2532,7 +2532,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list); init_rwsem(&meta_group_info[i]->alloc_sem); - meta_group_info[i]->bb_free_root.rb_node = NULL;; + meta_group_info[i]->bb_free_root.rb_node = NULL; #ifdef DOUBLE_CHECK { -- cgit v1.2.3 From 1c718505171b06dbb60eafcb3fddba877dae5f7b Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Sun, 5 Jul 2009 23:04:36 -0400 Subject: ext4: Fix compile warnings with MB_DEBUG When MB_DEBUG is enabled, we get some compile warnings because ext4_group_t is unsigned int. This patch fixes them. Signed-off-by Akira Fujita Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index ba49e0c596f2..68cde598b3bf 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1851,7 +1851,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) struct inode *inode = sbi->s_buddy_cache; struct page *page = NULL, *bitmap_page = NULL; - mb_debug("init group %lu\n", group); + mb_debug("init group %u\n", group); blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; this_grp = ext4_get_group_info(sb, group); /* @@ -4120,14 +4120,14 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) ext4_get_group_no_and_offset(sb, pa->pa_pstart, NULL, &start); spin_unlock(&pa->pa_lock); - printk(KERN_ERR "PA:%lu:%d:%u \n", i, - start, pa->pa_len); + printk(KERN_ERR "PA:%u:%d:%u \n", i, + start, pa->pa_len); } ext4_unlock_group(sb, i); if (grp->bb_free == 0) continue; - printk(KERN_ERR "%lu: %d/%d \n", + printk(KERN_ERR "%u: %d/%d \n", i, grp->bb_free, grp->bb_fragments); } printk(KERN_ERR "\n"); -- cgit v1.2.3 From 785b4b3a5a992eeb8b495a89b6f690b383010aba Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 27 Jul 2009 21:44:40 -0400 Subject: ext4: fix build warning when EXT4FS_DEBUG is on When compiling with EXT4FS_DEBUG on, gcc will complain with following warnings: linux-2.6/fs/ext4/ialloc.c: In function ‘ext4_count_free_inodes’: linux-2.6/fs/ext4/ialloc.c:1192: warning: format ‘%lu’ expects type ‘long unsigned int’, but argument 2 has type ‘ext4_group_t’ So add a type cast to suppress it. Signed-off-by: Peng Tao Signed-off-by: "Theodore Ts'o" --- fs/ext4/ialloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 29e6dc7299b8..f3624ead4f6c 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1189,7 +1189,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n", - i, ext4_free_inodes_count(sb, gdp), x); + (unsigned long) i, ext4_free_inodes_count(sb, gdp), x); bitmap_count += x; } brelse(bitmap_bh); -- cgit v1.2.3 From c333e073b7bf76dc819a6b4ce6bef88ee5fa5e50 Mon Sep 17 00:00:00 2001 From: Roel Kluin Date: Mon, 10 Aug 2009 22:47:22 -0400 Subject: ext4: remove redundant test on unsigned unsigned i_block cannot be less than 0. Signed-off-by: Roel Kluin Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index deb14a728791..9a4c929b16dc 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -341,9 +341,7 @@ static int ext4_block_to_path(struct inode *inode, int n = 0; int final = 0; - if (i_block < 0) { - ext4_warning(inode->i_sb, "ext4_block_to_path", "block < 0"); - } else if (i_block < direct_blocks) { + if (i_block < direct_blocks) { offsets[n++] = i_block; final = direct_blocks; } else if ((i_block -= direct_blocks) < indirect_blocks) { -- cgit v1.2.3 From b1f485f20eb9b02cc7d2009556287f3939d480cc Mon Sep 17 00:00:00 2001 From: Andreas Dilger Date: Mon, 10 Aug 2009 22:51:53 -0400 Subject: jbd2: round commit timer up to avoid uncommitted transaction fix jiffie rounding in jbd commit timer setup code. Rounding down could cause the timer to be fired before the corresponding transaction has expired. That transaction can stay not committed forever if no new transaction is created or expicit sync/umount happens. Signed-off-by: Alex Zhuravlev (Tomas) Signed-off-by: Andreas Dilger Signed-off-by: "Theodore Ts'o" --- fs/jbd2/transaction.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6213ac728f30..4516a87ca55c 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -57,7 +57,7 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction) INIT_LIST_HEAD(&transaction->t_private_list); /* Set up the commit timer for the new transaction. */ - journal->j_commit_timer.expires = round_jiffies(transaction->t_expires); + journal->j_commit_timer.expires = round_jiffies_up(transaction->t_expires); add_timer(&journal->j_commit_timer); J_ASSERT(journal->j_running_transaction == NULL); -- cgit v1.2.3 From 91cc219ad963731191247c5f2db4118be2bc341a Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 10 Aug 2009 23:05:28 -0400 Subject: ext4: fix journal ref count in move_extent_par_page move_extent_par_page calls a_ops->write_begin() to increase journal handler's reference count. However, if either mext_replace_branches() or ext4_get_block fails, the increased reference count isn't decreased. This will cause a later attempt to umount of the fs to hang forever. The patch addresses the issue by calling ext4_journal_stop() if page is not NULL (which means a_ops->write_end() isn't invoked). Signed-off-by: Peng Tao Signed-off-by: "Theodore Ts'o" --- fs/ext4/move_extent.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index bbf2dd9404dc..5821e0bee917 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -871,6 +871,7 @@ out: if (PageLocked(page)) unlock_page(page); page_cache_release(page); + ext4_journal_stop(handle); } out2: ext4_journal_stop(handle); -- cgit v1.2.3 From 6ba495e9259cd9a0b40ebd6c315143535c92542f Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 18 Sep 2009 13:38:55 -0400 Subject: ext4: Add configurable run-time mballoc debugging Allow mballoc debugging to be enabled at run-time instead of just at compile time. Signed-off-by: "Theodore Ts'o" --- fs/ext4/Kconfig | 9 +++++++ fs/ext4/mballoc.c | 81 ++++++++++++++++++++++++++++++++++++++++--------------- fs/ext4/mballoc.h | 16 ++++++++--- 3 files changed, 80 insertions(+), 26 deletions(-) diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 152304624644..d5c0ea2e8f2d 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -77,3 +77,12 @@ config EXT4_FS_SECURITY If you are not using a security module that requires using extended attributes for file security labels, say N. + +config EXT4_DEBUG + bool "EXT4 debugging support" + depends on EXT4_FS + help + Enables run-time debugging support for the ext4 filesystem. + + If you select Y here, then you will be able to turn on debugging + with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug" diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 68cde598b3bf..d80b300c1779 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -22,6 +22,7 @@ */ #include "mballoc.h" +#include #include /* @@ -743,7 +744,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) char *data; char *bitmap; - mb_debug("init page %lu\n", page->index); + mb_debug(1, "init page %lu\n", page->index); inode = page->mapping->host; sb = inode->i_sb; @@ -822,7 +823,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) set_bitmap_uptodate(bh[i]); bh[i]->b_end_io = end_buffer_read_sync; submit_bh(READ, bh[i]); - mb_debug("read bitmap for group %u\n", first_group + i); + mb_debug(1, "read bitmap for group %u\n", first_group + i); } /* wait for I/O completion */ @@ -862,7 +863,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); - mb_debug("put buddy for group %u in page %lu/%x\n", + mb_debug(1, "put buddy for group %u in page %lu/%x\n", group, page->index, i * blocksize); grinfo = ext4_get_group_info(sb, group); grinfo->bb_fragments = 0; @@ -878,7 +879,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) } else { /* this is block of bitmap */ BUG_ON(incore != NULL); - mb_debug("put bitmap for group %u in page %lu/%x\n", + mb_debug(1, "put bitmap for group %u in page %lu/%x\n", group, page->index, i * blocksize); /* see comments in ext4_mb_put_pa() */ @@ -922,7 +923,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_sb_info *sbi = EXT4_SB(sb); struct inode *inode = sbi->s_buddy_cache; - mb_debug("load group %u\n", group); + mb_debug(1, "load group %u\n", group); blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); @@ -1851,7 +1852,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) struct inode *inode = sbi->s_buddy_cache; struct page *page = NULL, *bitmap_page = NULL; - mb_debug("init group %u\n", group); + mb_debug(1, "init group %u\n", group); blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; this_grp = ext4_get_group_info(sb, group); /* @@ -2739,7 +2740,7 @@ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp) kmem_cache_free(ext4_pspace_cachep, pa); } if (count) - mb_debug("mballoc: %u PAs left\n", count); + mb_debug(1, "mballoc: %u PAs left\n", count); } @@ -2820,7 +2821,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn) list_for_each_safe(l, ltmp, &txn->t_private_list) { entry = list_entry(l, struct ext4_free_data, list); - mb_debug("gonna free %u blocks in group %u (0x%p):", + mb_debug(1, "gonna free %u blocks in group %u (0x%p):", entry->count, entry->group, entry); err = ext4_mb_load_buddy(sb, entry->group, &e4b); @@ -2855,9 +2856,43 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn) ext4_mb_release_desc(&e4b); } - mb_debug("freed %u blocks in %u structures\n", count, count2); + mb_debug(1, "freed %u blocks in %u structures\n", count, count2); } +#ifdef CONFIG_EXT4_DEBUG +u8 mb_enable_debug __read_mostly; + +static struct dentry *debugfs_dir; +static struct dentry *debugfs_debug; + +static void __init ext4_create_debugfs_entry(void) +{ + debugfs_dir = debugfs_create_dir("ext4", NULL); + if (debugfs_dir) + debugfs_debug = debugfs_create_u8("mballoc-debug", + S_IRUGO | S_IWUSR, + debugfs_dir, + &mb_enable_debug); +} + +static void ext4_remove_debugfs_entry(void) +{ + debugfs_remove(debugfs_debug); + debugfs_remove(debugfs_dir); +} + +#else + +static void __init ext4_create_debugfs_entry(void) +{ +} + +static void ext4_remove_debugfs_entry(void) +{ +} + +#endif + int __init init_ext4_mballoc(void) { ext4_pspace_cachep = @@ -2885,6 +2920,7 @@ int __init init_ext4_mballoc(void) kmem_cache_destroy(ext4_ac_cachep); return -ENOMEM; } + ext4_create_debugfs_entry(); return 0; } @@ -2898,6 +2934,7 @@ void exit_ext4_mballoc(void) kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_ext_cachep); + ext4_remove_debugfs_entry(); } @@ -3042,7 +3079,7 @@ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac) ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_stripe; else ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; - mb_debug("#%u: goal %u blocks for locality group\n", + mb_debug(1, "#%u: goal %u blocks for locality group\n", current->pid, ac->ac_g_ex.fe_len); } @@ -3232,7 +3269,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } - mb_debug("goal: %u(was %u) blocks at %u\n", (unsigned) size, + mb_debug(1, "goal: %u(was %u) blocks at %u\n", (unsigned) size, (unsigned) orig_size, (unsigned) start); } @@ -3281,7 +3318,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, BUG_ON(pa->pa_free < len); pa->pa_free -= len; - mb_debug("use %llu/%u from inode pa %p\n", start, len, pa); + mb_debug(1, "use %llu/%u from inode pa %p\n", start, len, pa); } /* @@ -3305,7 +3342,7 @@ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, * in on-disk bitmap -- see ext4_mb_release_context() * Other CPUs are prevented from allocating from this pa by lg_mutex */ - mb_debug("use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa); + mb_debug(1, "use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa); } /* @@ -3484,7 +3521,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, preallocated += len; count++; } - mb_debug("prellocated %u for group %u\n", preallocated, group); + mb_debug(1, "prellocated %u for group %u\n", preallocated, group); } static void ext4_mb_pa_callback(struct rcu_head *head) @@ -3619,7 +3656,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) pa->pa_deleted = 0; pa->pa_type = MB_INODE_PA; - mb_debug("new inode pa %p: %llu/%u for %u\n", pa, + mb_debug(1, "new inode pa %p: %llu/%u for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_inode_pa(ac, pa); @@ -3679,7 +3716,7 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac) pa->pa_deleted = 0; pa->pa_type = MB_GROUP_PA; - mb_debug("new group pa %p: %llu/%u for %u\n", pa, + mb_debug(1, "new group pa %p: %llu/%u for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_group_pa(ac, pa); @@ -3758,7 +3795,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, next = mb_find_next_bit(bitmap_bh->b_data, end, bit); start = group * EXT4_BLOCKS_PER_GROUP(sb) + bit + le32_to_cpu(sbi->s_es->s_first_data_block); - mb_debug(" free preallocated %u/%u in group %u\n", + mb_debug(1, " free preallocated %u/%u in group %u\n", (unsigned) start, (unsigned) next - bit, (unsigned) group); free += next - bit; @@ -3849,7 +3886,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, int busy = 0; int free = 0; - mb_debug("discard preallocation for group %u\n", group); + mb_debug(1, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) return 0; @@ -3973,7 +4010,7 @@ void ext4_discard_preallocations(struct inode *inode) return; } - mb_debug("discard preallocation for inode %lu\n", inode->i_ino); + mb_debug(1, "discard preallocation for inode %lu\n", inode->i_ino); trace_ext4_discard_preallocations(inode); INIT_LIST_HEAD(&list); @@ -4078,7 +4115,7 @@ static void ext4_mb_return_to_preallocation(struct inode *inode, { BUG_ON(!list_empty(&EXT4_I(inode)->i_prealloc_list)); } -#ifdef MB_DEBUG +#ifdef CONFIG_EXT4_DEBUG static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; @@ -4227,7 +4264,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); - mb_debug("init ac: %u blocks @ %u, goal %u, flags %x, 2^%d, " + mb_debug(1, "init ac: %u blocks @ %u, goal %u, flags %x, 2^%d, " "left: %u/%u, right %u/%u to %swritable\n", (unsigned) ar->len, (unsigned) ar->logical, (unsigned) ar->goal, ac->ac_flags, ac->ac_2order, @@ -4249,7 +4286,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, struct ext4_prealloc_space *pa, *tmp; struct ext4_allocation_context *ac; - mb_debug("discard locality group preallocation\n"); + mb_debug(1, "discard locality group preallocation\n"); INIT_LIST_HEAD(&discard_list); ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index c96bb19f58f9..9db890d4d275 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -37,11 +37,19 @@ /* */ -#define MB_DEBUG__ -#ifdef MB_DEBUG -#define mb_debug(fmt, a...) printk(fmt, ##a) +#ifdef CONFIG_EXT4_DEBUG +extern u8 mb_enable_debug; + +#define mb_debug(n, fmt, a...) \ + do { \ + if ((n) <= mb_enable_debug) { \ + printk(KERN_DEBUG "(%s, %d): %s: ", \ + __FILE__, __LINE__, __func__); \ + printk(fmt, ## a); \ + } \ + } while (0) #else -#define mb_debug(fmt, a...) +#define mb_debug(n, fmt, a...) #endif /* -- cgit v1.2.3 From 0ef90db93a4ddfc300af288c2a1bfc1e6c79da64 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 9 Aug 2009 16:46:13 -0400 Subject: ext4: Display the mballoc flags in mb_history in hex instead of decimal Displaying the flags in base 16 makes it easier to see which flags have been set. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 22 +++++++++++----------- fs/ext4/mballoc.c | 4 ++-- 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9714db393efe..e267727cc62d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -67,27 +67,27 @@ typedef unsigned int ext4_group_t; /* prefer goal again. length */ -#define EXT4_MB_HINT_MERGE 1 +#define EXT4_MB_HINT_MERGE 0x0001 /* blocks already reserved */ -#define EXT4_MB_HINT_RESERVED 2 +#define EXT4_MB_HINT_RESERVED 0x0002 /* metadata is being allocated */ -#define EXT4_MB_HINT_METADATA 4 +#define EXT4_MB_HINT_METADATA 0x0004 /* first blocks in the file */ -#define EXT4_MB_HINT_FIRST 8 +#define EXT4_MB_HINT_FIRST 0x0008 /* search for the best chunk */ -#define EXT4_MB_HINT_BEST 16 +#define EXT4_MB_HINT_BEST 0x0010 /* data is being allocated */ -#define EXT4_MB_HINT_DATA 32 +#define EXT4_MB_HINT_DATA 0x0020 /* don't preallocate (for tails) */ -#define EXT4_MB_HINT_NOPREALLOC 64 +#define EXT4_MB_HINT_NOPREALLOC 0x0040 /* allocate for locality group */ -#define EXT4_MB_HINT_GROUP_ALLOC 128 +#define EXT4_MB_HINT_GROUP_ALLOC 0x0080 /* allocate goal blocks or none */ -#define EXT4_MB_HINT_GOAL_ONLY 256 +#define EXT4_MB_HINT_GOAL_ONLY 0x0100 /* goal is meaningful */ -#define EXT4_MB_HINT_TRY_GOAL 512 +#define EXT4_MB_HINT_TRY_GOAL 0x0200 /* blocks already pre-reserved by delayed allocation */ -#define EXT4_MB_DELALLOC_RESERVED 1024 +#define EXT4_MB_DELALLOC_RESERVED 0x0400 struct ext4_allocation_request { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index d80b300c1779..3434c603432d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2157,7 +2157,7 @@ static int ext4_mb_seq_history_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-5s %-8s %-23s %-23s %-23s %-5s " - "%-5s %-2s %-5s %-5s %-5s %-6s\n", + "%-5s %-2s %-6s %-5s %-5s %-6s\n", "pid", "inode", "original", "goal", "result", "found", "grps", "cr", "flags", "merge", "tail", "broken"); return 0; @@ -2165,7 +2165,7 @@ static int ext4_mb_seq_history_show(struct seq_file *seq, void *v) if (hs->op == EXT4_MB_HISTORY_ALLOC) { fmt = "%-5u %-8u %-23s %-23s %-23s %-5u %-5u %-2u " - "%-5u %-5s %-5u %-6u\n"; + "0x%04x %-5s %-5u %-6u\n"; sprintf(buf2, "%u/%d/%u@%u", hs->result.fe_group, hs->result.fe_start, hs->result.fe_len, hs->result.fe_logical); -- cgit v1.2.3 From 4ba74d00a20256e22f159cb288ff34b587608917 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 9 Aug 2009 22:01:13 -0400 Subject: ext4: Fix bugs in mballoc's stream allocation mode The logic around sbi->s_mb_last_group and sbi->s_mb_last_start was all screwed up. These fields were getting unconditionally all the time, set even when stream allocation had not taken place, and if they were being used when the file was smaller than s_mb_stream_request, which is when the allocation should _not_ be doing stream allocation. Fix this by determining whether or not we stream allocation should take place once, in ext4_mb_group_or_file(), and setting a flag which gets used in ext4_mb_regular_allocator() and ext4_mb_use_best_found(). This simplifies the code and assures that we are consistently using (or not using) the stream allocation logic. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 ++ fs/ext4/mballoc.c | 23 ++++++++++------------- 2 files changed, 12 insertions(+), 13 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index e267727cc62d..70aa951ecb3c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -88,6 +88,8 @@ typedef unsigned int ext4_group_t; #define EXT4_MB_HINT_TRY_GOAL 0x0200 /* blocks already pre-reserved by delayed allocation */ #define EXT4_MB_DELALLOC_RESERVED 0x0400 +/* We are doing stream allocation */ +#define EXT4_MB_STREAM_ALLOC 0x0800 struct ext4_allocation_request { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 3434c603432d..90a30ce822fc 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1361,7 +1361,7 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, ac->alloc_semp = e4b->alloc_semp; e4b->alloc_semp = NULL; /* store last allocated for subsequent stream allocation */ - if ((ac->ac_flags & EXT4_MB_HINT_DATA)) { + if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { spin_lock(&sbi->s_md_lock); sbi->s_mb_last_group = ac->ac_f_ex.fe_group; sbi->s_mb_last_start = ac->ac_f_ex.fe_start; @@ -1939,7 +1939,6 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) struct ext4_sb_info *sbi; struct super_block *sb; struct ext4_buddy e4b; - loff_t size, isize; sb = ac->ac_sb; sbi = EXT4_SB(sb); @@ -1975,20 +1974,16 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) } bsbits = ac->ac_sb->s_blocksize_bits; - /* if stream allocation is enabled, use global goal */ - size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len; - isize = i_size_read(ac->ac_inode) >> bsbits; - if (size < isize) - size = isize; - if (size < sbi->s_mb_stream_request && - (ac->ac_flags & EXT4_MB_HINT_DATA)) { + /* if stream allocation is enabled, use global goal */ + if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { /* TBD: may be hot point */ spin_lock(&sbi->s_md_lock); ac->ac_g_ex.fe_group = sbi->s_mb_last_group; ac->ac_g_ex.fe_start = sbi->s_mb_last_start; spin_unlock(&sbi->s_md_lock); } + /* Let's just scan groups to find more-less suitable blocks */ cr = ac->ac_2order ? 0 : 1; /* @@ -4192,16 +4187,18 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; + if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) + return; + size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len; isize = i_size_read(ac->ac_inode) >> bsbits; size = max(size, isize); /* don't use group allocation for large files */ - if (size >= sbi->s_mb_stream_request) - return; - - if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) + if (size >= sbi->s_mb_stream_request) { + ac->ac_flags |= EXT4_MB_STREAM_ALLOC; return; + } BUG_ON(ac->ac_lg != NULL); /* -- cgit v1.2.3 From 50797481a7bdee548589506d7d7b48b08bc14dcd Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 18 Sep 2009 13:34:02 -0400 Subject: ext4: Avoid group preallocation for closed files Currently the group preallocation code tries to find a large (512) free block from which to do per-cpu group allocation for small files. The problem with this scheme is that it leaves the filesystem horribly fragmented. In the worst case, if the filesystem is unmounted and remounted (after a system shutdown, for example) we forget the fact that wee were using a particular (now-partially filled) 512 block extent. So the next time we try to allocate space for a small file, we will find *another* completely free 512 block chunk to allocate small files. Given that there are 32,768 blocks in a block group, after 64 iterations of "mount, write one 4k file in a directory, unmount", the block group will have 64 files, each separated by 511 blocks, and the block group will no longer have any free 512 completely free chunks of blocks for group preallocation space. So if we try to allocate blocks for a file that has been closed, such that we know the final size of the file, and the filesystem is not busy, avoid using group preallocation. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 30 +++++++++++++++++++++++++++++- fs/ext4/mballoc.c | 10 +++++++++- 2 files changed, 38 insertions(+), 2 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 70aa951ecb3c..2e9a2036c114 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -952,6 +952,7 @@ struct ext4_sb_info { atomic_t s_mb_lost_chunks; atomic_t s_mb_preallocated; atomic_t s_mb_discarded; + atomic_t s_lock_busy; /* locality groups */ struct ext4_locality_group *s_locality_groups; @@ -1593,15 +1594,42 @@ struct ext4_group_info { #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) +#define EXT4_MAX_CONTENTION 8 +#define EXT4_CONTENTION_THRESHOLD 2 + static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb, ext4_group_t group) { return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group); } +/* + * Returns true if the filesystem is busy enough that attempts to + * access the block group locks has run into contention. + */ +static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi) +{ + return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD); +} + static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group) { - spin_lock(ext4_group_lock_ptr(sb, group)); + spinlock_t *lock = ext4_group_lock_ptr(sb, group); + if (spin_trylock(lock)) + /* + * We're able to grab the lock right away, so drop the + * lock contention counter. + */ + atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0); + else { + /* + * The lock is busy, so bump the contention counter, + * and then wait on the spin lock. + */ + atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, 1, + EXT4_MAX_CONTENTION); + spin_lock(lock); + } } static inline void ext4_unlock_group(struct super_block *sb, diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 90a30ce822fc..faf5bd056a93 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4191,9 +4191,17 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) return; size = ac->ac_o_ex.fe_logical + ac->ac_o_ex.fe_len; - isize = i_size_read(ac->ac_inode) >> bsbits; + isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) + >> bsbits; size = max(size, isize); + if ((size == isize) && + !ext4_fs_is_busy(sbi) && + (atomic_read(&ac->ac_inode->i_writecount) == 0)) { + ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; + return; + } + /* don't use group allocation for large files */ if (size >= sbi->s_mb_stream_request) { ac->ac_flags |= EXT4_MB_STREAM_ALLOC; -- cgit v1.2.3 From 84fe3bef59dc45a1cb0d2f9b0aefa8f1fbfbdf98 Mon Sep 17 00:00:00 2001 From: Mingming Date: Tue, 1 Sep 2009 08:44:37 -0400 Subject: ext4: Compile warning fix when EXT_DEBUG enabled When EXT_DEBUG is enabled I received the following compile warning on PPC64: CC [M] fs/ext4/inode.o CC [M] fs/ext4/extents.o fs/ext4/extents.c: In function ‘ext4_ext_rm_leaf’: fs/ext4/extents.c:2097: warning: format ‘%lu’ expects type ‘long unsigned int’, but argument 2 has type ‘ext4_lblk_t’ fs/ext4/extents.c: In function ‘ext4_ext_get_blocks’: fs/ext4/extents.c:2789: warning: format ‘%u’ expects type ‘unsigned int’, but argument 4 has type ‘long unsigned int’ fs/ext4/extents.c:2852: warning: format ‘%lu’ expects type ‘long unsigned int’, but argument 3 has type ‘ext4_lblk_t’ fs/ext4/extents.c:2953: warning: format ‘%lu’ expects type ‘long unsigned int’, but argument 4 has type ‘unsigned int’ CC [M] fs/ext4/migrate.o The patch fixes compile warning. Signed-off-by: Mingming Cao Signed-off-by: "Theodore Ts'o" Index: linux-2.6.31-rc4/fs/ext4/extents.c =================================================================== --- fs/ext4/extents.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 73ebfb44ad75..c583ebd1e41f 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2094,7 +2094,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, else uninitialized = 0; - ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len); + ext_debug("remove ext %u:%d\n", ex_ee_block, ex_ee_len); path[depth].p_ext = ex; a = ex_ee_block > start ? ex_ee_block : start; @@ -2786,7 +2786,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, struct ext4_allocation_request ar; __clear_bit(BH_New, &bh_result->b_state); - ext_debug("blocks %u/%u requested for inode %u\n", + ext_debug("blocks %u/%u requested for inode %lu\n", iblock, max_blocks, inode->i_ino); /* check in cache */ @@ -2849,7 +2849,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, newblock = iblock - ee_block + ee_start; /* number of remaining blocks in the extent */ allocated = ee_len - (iblock - ee_block); - ext_debug("%u fit into %lu:%d -> %llu\n", iblock, + ext_debug("%u fit into %u:%d -> %llu\n", iblock, ee_block, ee_len, newblock); /* Do not put uninitialized extent in the cache */ @@ -2950,7 +2950,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, newblock = ext4_mb_new_blocks(handle, &ar, &err); if (!newblock) goto out2; - ext_debug("allocate new block: goal %llu, found %llu/%lu\n", + ext_debug("allocate new block: goal %llu, found %llu/%u\n", ar.goal, newblock, allocated); /* try to insert new extent into found leaf and return */ -- cgit v1.2.3 From 553f9008939638335836eec834f4dea310c17eae Mon Sep 17 00:00:00 2001 From: Mingming Date: Fri, 18 Sep 2009 13:34:55 -0400 Subject: ext4: Show unwritten extent flag in ext4_ext_show_leaf() ext4_ext_show_leaf() will display the leaf extents when extent debugging is enabled. Printing out the unwritten bit is useful for debugging unwritten extent, allow us to see the unwritten extents vs written extents, after the unwritten extents are splitted or converted. Signed-off-by: Mingming Cao --- fs/ext4/ext4_extents.h | 3 +-- fs/ext4/extents.c | 31 ++++++++++++++++++++++--------- 2 files changed, 23 insertions(+), 11 deletions(-) diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 20a84105a10b..9538633879d7 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -43,8 +43,7 @@ #define CHECK_BINSEARCH__ /* - * If EXT_DEBUG is defined you can use the 'extdebug' mount option - * to get lots of info about what's going on. + * Turn on EXT_DEBUG to get lots of info about extents operations. */ #define EXT_DEBUG__ #ifdef EXT_DEBUG diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c583ebd1e41f..13db43408533 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -437,8 +437,9 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block), idx_pblock(path->p_idx)); } else if (path->p_ext) { - ext_debug(" %d:%d:%llu ", + ext_debug(" %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), + ext4_ext_is_uninitialized(path->p_ext), ext4_ext_get_actual_len(path->p_ext), ext_pblock(path->p_ext)); } else @@ -460,8 +461,11 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) eh = path[depth].p_hdr; ex = EXT_FIRST_EXTENT(eh); + ext_debug("Displaying leaf extents for inode %lu\n", inode->i_ino); + for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { - ext_debug("%d:%d:%llu ", le32_to_cpu(ex->ee_block), + ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), + ext4_ext_is_uninitialized(ex), ext4_ext_get_actual_len(ex), ext_pblock(ex)); } ext_debug("\n"); @@ -580,9 +584,10 @@ ext4_ext_binsearch(struct inode *inode, } path->p_ext = l - 1; - ext_debug(" -> %d:%llu:%d ", + ext_debug(" -> %d:%llu:[%d]%d ", le32_to_cpu(path->p_ext->ee_block), ext_pblock(path->p_ext), + ext4_ext_is_uninitialized(path->p_ext), ext4_ext_get_actual_len(path->p_ext)); #ifdef CHECK_BINSEARCH @@ -850,9 +855,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, path[depth].p_ext++; while (path[depth].p_ext <= EXT_MAX_EXTENT(path[depth].p_hdr)) { - ext_debug("move %d:%llu:%d in new leaf %llu\n", + ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n", le32_to_cpu(path[depth].p_ext->ee_block), ext_pblock(path[depth].p_ext), + ext4_ext_is_uninitialized(path[depth].p_ext), ext4_ext_get_actual_len(path[depth].p_ext), newblock); /*memmove(ex++, path[depth].p_ext++, @@ -1580,9 +1586,11 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, /* try to insert block into found extent and return */ if (ex && ext4_can_extents_be_merged(inode, ex, newext)) { - ext_debug("append %d block to %d:%d (from %llu)\n", + ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n", + ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), + ext4_ext_is_uninitialized(ex), ext4_ext_get_actual_len(ex), ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) @@ -1651,9 +1659,10 @@ has_space: if (!nearex) { /* there is no extent in this leaf, create first one */ - ext_debug("first extent in the leaf: %d:%llu:%d\n", + ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), + ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext)); path[depth].p_ext = EXT_FIRST_EXTENT(eh); } else if (le32_to_cpu(newext->ee_block) @@ -1663,10 +1672,11 @@ has_space: len = EXT_MAX_EXTENT(eh) - nearex; len = (len - 1) * sizeof(struct ext4_extent); len = len < 0 ? 0 : len; - ext_debug("insert %d:%llu:%d after: nearest 0x%p, " + ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, " "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), + ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); memmove(nearex + 2, nearex + 1, len); @@ -1676,10 +1686,11 @@ has_space: BUG_ON(newext->ee_block == nearex->ee_block); len = (EXT_MAX_EXTENT(eh) - nearex) * sizeof(struct ext4_extent); len = len < 0 ? 0 : len; - ext_debug("insert %d:%llu:%d before: nearest 0x%p, " + ext_debug("insert %d:%llu:[%d]%d before: nearest 0x%p, " "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), + ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); memmove(nearex + 1, nearex, len); @@ -2094,7 +2105,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, else uninitialized = 0; - ext_debug("remove ext %u:%d\n", ex_ee_block, ex_ee_len); + ext_debug("remove ext %u:[%d]%d\n", ex_ee_block, + uninitialized, ex_ee_len); path[depth].p_ext = ex; a = ex_ee_block > start ? ex_ee_block : start; @@ -2743,6 +2755,7 @@ insert: } else if (err) goto fix_extent_len; out: + ext4_ext_show_leaf(inode, path); return err ? err : allocated; fix_extent_len: -- cgit v1.2.3 From 9599b0e597d810be9b8f759ea6e9619c4f983c5e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 17 Aug 2009 21:23:17 -0400 Subject: jbd2: Annotate transaction start also for jbd2_journal_restart() lockdep annotation for a transaction start has been at the end of jbd2_journal_start(). But a transaction is also started from jbd2_journal_restart(). Move the lockdep annotation to start_this_handle() which covers both cases. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/jbd2/transaction.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 4516a87ca55c..a0512700542f 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -238,6 +238,8 @@ repeat_locked: __jbd2_log_space_left(journal)); spin_unlock(&transaction->t_handle_lock); spin_unlock(&journal->j_state_lock); + + lock_map_acquire(&handle->h_lockdep_map); out: if (unlikely(new_transaction)) /* It's usually NULL */ kfree(new_transaction); @@ -303,8 +305,6 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks) handle = ERR_PTR(err); goto out; } - - lock_map_acquire(&handle->h_lockdep_map); out: return handle; } @@ -426,6 +426,7 @@ int jbd2_journal_restart(handle_t *handle, int nblocks) __jbd2_log_start_commit(journal, transaction->t_tid); spin_unlock(&journal->j_state_lock); + lock_map_release(&handle->h_lockdep_map); handle->h_buffer_credits = nblocks; ret = start_this_handle(journal, handle); return ret; -- cgit v1.2.3 From 487caeef9fc08c0565e082c40a8aaf58dad92bbb Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 17 Aug 2009 22:17:20 -0400 Subject: ext4: Fix possible deadlock between ext4_truncate() and ext4_get_blocks() During truncate we are sometimes forced to start a new transaction as the amount of blocks to be journaled is both quite large and hard to predict. So far we restarted a transaction while holding i_data_sem and that violates lock ordering because i_data_sem ranks below a transaction start (and it can lead to a real deadlock with ext4_get_blocks() mapping blocks in some page while having a transaction open). We fix the problem by dropping the i_data_sem before restarting the transaction and acquire it afterwards. It's slightly subtle that this works: 1) By the time ext4_truncate() is called, all the page cache for the truncated part of the file is dropped so get_block() should not be called on it (we only have to invalidate extent cache after we reacquire i_data_sem because some extent from not-truncated part could extend also into the part we are going to truncate). 2) Writes, migrate or defrag hold i_mutex so they are stopped for all the time of the truncate. This bug has been found and analyzed by Theodore Tso . Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + fs/ext4/extents.c | 15 ++++++++++++--- fs/ext4/inode.c | 23 +++++++++++++++++++---- 3 files changed, 32 insertions(+), 7 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 2e9a2036c114..fb21663ffe54 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1370,6 +1370,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int); extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); extern int ext4_can_truncate(struct inode *inode); extern void ext4_truncate(struct inode *); +extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks); extern void ext4_set_inode_flags(struct inode *); extern void ext4_get_inode_flags(struct ext4_inode_info *); extern int ext4_alloc_da_blocks(struct inode *inode); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 13db43408533..8c20caf4aa5c 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -93,7 +93,9 @@ static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb) ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); } -static int ext4_ext_journal_restart(handle_t *handle, int needed) +static int ext4_ext_truncate_extend_restart(handle_t *handle, + struct inode *inode, + int needed) { int err; @@ -104,7 +106,14 @@ static int ext4_ext_journal_restart(handle_t *handle, int needed) err = ext4_journal_extend(handle, needed); if (err <= 0) return err; - return ext4_journal_restart(handle, needed); + err = ext4_truncate_restart_trans(handle, inode, needed); + /* + * We have dropped i_data_sem so someone might have cached again + * an extent we are going to truncate. + */ + ext4_ext_invalidate_cache(inode); + + return err; } /* @@ -2150,7 +2159,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, } credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); - err = ext4_ext_journal_restart(handle, credits); + err = ext4_ext_truncate_extend_restart(handle, inode, credits); if (err) goto out; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9a4c929b16dc..d61fb523308f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -192,11 +192,24 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode) * so before we call here everything must be consistently dirtied against * this transaction. */ -static int ext4_journal_test_restart(handle_t *handle, struct inode *inode) + int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode, + int nblocks) { + int ret; + + /* + * Drop i_data_sem to avoid deadlock with ext4_get_blocks At this + * moment, get_block can be called only for blocks inside i_size since + * page cache has been already dropped and writes are blocked by + * i_mutex. So we can safely drop the i_data_sem here. + */ BUG_ON(EXT4_JOURNAL(inode) == NULL); jbd_debug(2, "restarting handle %p\n", handle); - return ext4_journal_restart(handle, blocks_for_truncate(inode)); + up_write(&EXT4_I(inode)->i_data_sem); + ret = ext4_journal_restart(handle, blocks_for_truncate(inode)); + down_write(&EXT4_I(inode)->i_data_sem); + + return ret; } /* @@ -3658,7 +3671,8 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode, ext4_handle_dirty_metadata(handle, inode, bh); } ext4_mark_inode_dirty(handle, inode); - ext4_journal_test_restart(handle, inode); + ext4_truncate_restart_trans(handle, inode, + blocks_for_truncate(inode)); if (bh) { BUFFER_TRACE(bh, "retaking write access"); ext4_journal_get_write_access(handle, bh); @@ -3869,7 +3883,8 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, return; if (try_to_extend_transaction(handle, inode)) { ext4_mark_inode_dirty(handle, inode); - ext4_journal_test_restart(handle, inode); + ext4_truncate_restart_trans(handle, inode, + blocks_for_truncate(inode)); } ext4_free_blocks(handle, inode, nr, 1, 1); -- cgit v1.2.3 From 0ccff1a49def92d6b838a6da166c89004b3a4d0c Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Mon, 17 Aug 2009 22:38:04 -0400 Subject: jbd2: bitfields should be unsigned This fixes sparse noise: error: dubious one-bit signed bitfield Signed-off-by: H Hartley Sweeten Signed-off-by: Andrew Morton Signed-off-by: "Theodore Ts'o" Cc: Jan Kara --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d97eb652d6ca..52695d3dfd0b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -652,7 +652,7 @@ struct transaction_s * This transaction is being forced and some process is * waiting for it to finish. */ - int t_synchronous_commit:1; + unsigned int t_synchronous_commit:1; /* * For use by the filesystem to store fs-specific data -- cgit v1.2.3 From bf43d84b185e2ff54598f8c58a5a8e63148b6e90 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Mon, 17 Aug 2009 23:48:51 -0400 Subject: ext4: reject too-large filesystems on 32-bit kernels ext4 will happily mount a > 16T filesystem on a 32-bit box, but this is not safe; writes to the block device will wrap past 16T and the page cache can't index past 16T (232 index * 4k pages). Adding another test to the existing "too many sectors" test should do the trick. Add a comment, a relevant return value, and fix the reference to the CONFIG_LBD(AF) option as well. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index fe3f376b7df2..de67c3657b83 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2550,12 +2550,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (ext4_blocks_count(es) > - (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { + /* + * Test whether we have more sectors than will fit in sector_t, + * and whether the max offset is addressable by the page cache. + */ + if ((ext4_blocks_count(es) > + (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) || + (ext4_blocks_count(es) > + (pgoff_t)(~0ULL) >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits))) { ext4_msg(sb, KERN_ERR, "filesystem" - " too large to mount safely"); + " too large to mount safely on this system"); if (sizeof(sector_t) < 8) ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); + ret = -EFBIG; goto failed_mount; } -- cgit v1.2.3 From 0373130d5bc783751c1fbad948886916a21d4559 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Mon, 17 Aug 2009 23:51:29 -0400 Subject: ext4: open-code ext4_mb_update_group_info ext4_mb_update_group_info is only called in one place, and it's extremely simple. There's no reason to have it in a separate function in a separate file as far as I can tell, it just obfuscates what's really going on. Perhaps it was intended to keep the grp->bb_* manipulation local to mballoc.c but we're already accessing other grp-> fields in balloc.c directly so this seems ok. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 2 +- fs/ext4/ext4.h | 2 -- fs/ext4/mballoc.c | 9 --------- 3 files changed, 1 insertion(+), 12 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index e2126d70dff5..1d0418980f8d 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -478,7 +478,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, * new bitmap information */ set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); - ext4_mb_update_group_info(grp, blocks_freed); + grp->bb_free += blocks_freed; up_write(&grp->alloc_sem); /* We dirtied the bitmap block */ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index fb21663ffe54..02b22885eb02 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1343,8 +1343,6 @@ extern void ext4_mb_free_blocks(handle_t *, struct inode *, ext4_fsblk_t, unsigned long, int, unsigned long *); extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); -extern void ext4_mb_update_group_info(struct ext4_group_info *grp, - ext4_grpblk_t add); extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t); extern void ext4_mb_put_buddy_cache_lock(struct super_block *, ext4_group_t, int); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index faf5bd056a93..833d87236881 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2554,15 +2554,6 @@ exit_meta_group_info: return -ENOMEM; } /* ext4_mb_add_groupinfo */ -/* - * Update an existing group. - * This function is used for online resize - */ -void ext4_mb_update_group_info(struct ext4_group_info *grp, ext4_grpblk_t add) -{ - grp->bb_free += add; -} - static int ext4_mb_init_backend(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); -- cgit v1.2.3 From 38877f4e8dbbec12c6fde85ee1fce1dc27ef3290 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Mon, 17 Aug 2009 23:55:24 -0400 Subject: simplify some logic in ext4_mb_normalize_request While reading through some of the mballoc code it seems that a couple spots in the size normalization function could be streamlined. The test for non-overlapping PAs can be or'd for the start & end conditions, and the tests for adjacent PAs can be else-if'd - it's essentially independently testing: if (A + B <= C) ... if (A > C) ... These cannot both be true so it seems like the else-if might be slightly more efficient and/or informative. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 833d87236881..1a9cd7de04dd 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3184,23 +3184,18 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end || ac->ac_o_ex.fe_logical < pa->pa_lstart)); - /* skip PA normalized request doesn't overlap with */ - if (pa->pa_lstart >= end) { - spin_unlock(&pa->pa_lock); - continue; - } - if (pa_end <= start) { + /* skip PAs this normalized request doesn't overlap with */ + if (pa->pa_lstart >= end || pa_end <= start) { spin_unlock(&pa->pa_lock); continue; } BUG_ON(pa->pa_lstart <= start && pa_end >= end); + /* adjust start or end to be adjacent to this pa */ if (pa_end <= ac->ac_o_ex.fe_logical) { BUG_ON(pa_end < start); start = pa_end; - } - - if (pa->pa_lstart > ac->ac_o_ex.fe_logical) { + } else if (pa->pa_lstart > ac->ac_o_ex.fe_logical) { BUG_ON(pa->pa_lstart > end); end = pa->pa_lstart; } -- cgit v1.2.3 From a13fb1a4533f26c1e2b0204d5283b696689645af Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 18 Aug 2009 00:20:23 -0400 Subject: ext4: Add feature set check helper for mount & remount paths A user reported that although his root ext4 filesystem was mounting fine, other filesystems would not mount, with the: "Filesystem with huge files cannot be mounted RDWR without CONFIG_LBDAF" error on his 32-bit box built without CONFIG_LBDAF. This is because the test at mount time for this situation was not being re-checked on remount, and the normal boot process makes an ro->rw transition, so this was being missed. Refactor to make a common helper function to test the filesystem features against the type of mount request (RO vs. RW) so that we stay consistent. Addresses Red-Hat-Bugzilla: #517650 Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 91 +++++++++++++++++++++++++++++++-------------------------- 1 file changed, 49 insertions(+), 42 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index de67c3657b83..4037fe0b5a5c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2254,6 +2254,49 @@ static struct kobj_type ext4_ktype = { .release = ext4_sb_release, }; +/* + * Check whether this filesystem can be mounted based on + * the features present and the RDONLY/RDWR mount requested. + * Returns 1 if this filesystem can be mounted as requested, + * 0 if it cannot be. + */ +static int ext4_feature_set_ok(struct super_block *sb, int readonly) +{ + if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP)) { + ext4_msg(sb, KERN_ERR, + "Couldn't mount because of " + "unsupported optional features (%x)", + (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) & + ~EXT4_FEATURE_INCOMPAT_SUPP)); + return 0; + } + + if (readonly) + return 1; + + /* Check that feature set is OK for a read-write mount */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) { + ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of " + "unsupported optional features (%x)", + (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & + ~EXT4_FEATURE_RO_COMPAT_SUPP)); + return 0; + } + /* + * Large file size enabled file system can only be mounted + * read-write on 32-bit systems if kernel is built with CONFIG_LBDAF + */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) { + if (sizeof(blkcnt_t) < sizeof(u64)) { + ext4_msg(sb, KERN_ERR, "Filesystem with huge files " + "cannot be mounted RDWR without " + "CONFIG_LBDAF"); + return 0; + } + } + return 1; +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) __releases(kernel_lock) __acquires(kernel_lock) @@ -2275,7 +2318,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) unsigned int db_count; unsigned int i; int needs_recovery, has_huge_files; - int features; __u64 blocks_count; int err; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; @@ -2402,39 +2444,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * previously didn't change the revision level when setting the flags, * so there is a chance incompat flags are set on a rev 0 filesystem. */ - features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP); - if (features) { - ext4_msg(sb, KERN_ERR, - "Couldn't mount because of " - "unsupported optional features (%x)", - (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) & - ~EXT4_FEATURE_INCOMPAT_SUPP)); - goto failed_mount; - } - features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP); - if (!(sb->s_flags & MS_RDONLY) && features) { - ext4_msg(sb, KERN_ERR, - "Couldn't mount RDWR because of " - "unsupported optional features (%x)", - (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & - ~EXT4_FEATURE_RO_COMPAT_SUPP)); + if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY))) goto failed_mount; - } - has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_HUGE_FILE); - if (has_huge_files) { - /* - * Large file size enabled file system can only be - * mount if kernel is build with CONFIG_LBDAF - */ - if (sizeof(root->i_blocks) < sizeof(u64) && - !(sb->s_flags & MS_RDONLY)) { - ext4_msg(sb, KERN_ERR, "Filesystem with huge " - "files cannot be mounted read-write " - "without CONFIG_LBDAF"); - goto failed_mount; - } - } + blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); if (blocksize < EXT4_MIN_BLOCK_SIZE || @@ -2470,6 +2482,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } + has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_HUGE_FILE); sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits, has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); @@ -3485,18 +3499,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal) ext4_mark_recovery_complete(sb, es); } else { - int ret; - if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb, - ~EXT4_FEATURE_RO_COMPAT_SUPP))) { - ext4_msg(sb, KERN_WARNING, "couldn't " - "remount RDWR because of unsupported " - "optional features (%x)", - (le32_to_cpu(sbi->s_es->s_feature_ro_compat) & - ~EXT4_FEATURE_RO_COMPAT_SUPP)); + /* Make sure we can mount this feature set readwrite */ + if (!ext4_feature_set_ok(sb, 0)) { err = -EROFS; goto restore_opts; } - /* * Make sure the group descriptor checksums * are sane. If they aren't, refuse to remount r/w. -- cgit v1.2.3 From a8526e84ac758ac6da45cf273aa1538a6a7aa3de Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Tue, 25 Aug 2009 22:36:05 -0400 Subject: ext4: Add missing unlock_new_inode() call in extent migration code We need to unlock the new inode before iput. This patch fixes the following warning when calling chattr +e to migrate a file to use extents. It also fixes problems in when e4defrag attempts to defragment an inode. [ 470.400044] ------------[ cut here ]------------ [ 470.400065] WARNING: at fs/inode.c:1210 generic_delete_inode+0x65/0x16a() [ 470.400072] Hardware name: N/A ..... ... [ 470.400353] Pid: 4451, comm: chattr Not tainted 2.6.31-rc7-red-debug #4 [ 470.400359] Call Trace: [ 470.400372] [] warn_slowpath_common+0x77/0x8f [ 470.400385] [] warn_slowpath_null+0xf/0x11 [ 470.400395] [] generic_delete_inode+0x65/0x16a [ 470.400405] [] generic_drop_inode+0x17/0x1bd [ 470.400413] [] iput+0x61/0x65 [ 470.400455] [] ext4_ext_migrate+0x5eb/0x66a [ext4] [ 470.400492] [] ext4_ioctl+0x340/0x756 [ext4] [ 470.400507] [] vfs_ioctl+0x1d/0x82 [ 470.400517] [] do_vfs_ioctl+0x483/0x4c9 [ 470.400527] [] ? trace_hardirqs_on+0xd/0xf [ 470.400537] [] sys_ioctl+0x51/0x74 [ 470.400549] [] system_call_fastpath+0x16/0x1b [ 470.400557] ---[ end trace ab85723542352dac ]--- Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 313a50b39741..05361ad5b80a 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -618,7 +618,7 @@ err_out: tmp_inode->i_nlink = 0; ext4_journal_stop(handle); - + unlock_new_inode(tmp_inode); iput(tmp_inode); return retval; -- cgit v1.2.3 From 1927805e6599d8602d2c0af6a0155c85acc0b214 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 25 Aug 2009 22:36:25 -0400 Subject: ext4: use variables not types in sizeofs() for allocations Precursor to changing some types; to keep things in sync, it seems better to allocate/memset based on the size of the variables we are using rather than on some disconnected basic type like "unsigned short" Signed-off-by: Eric Sandeen --- fs/ext4/mballoc.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 1a9cd7de04dd..081eaf7fce89 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -868,7 +868,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore) grinfo = ext4_get_group_info(sb, group); grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, - sizeof(unsigned short)*(sb->s_blocksize_bits+2)); + sizeof(*grinfo->bb_counters) * + (sb->s_blocksize_bits+2)); /* * incore got set to the group block bitmap below */ @@ -2640,14 +2641,14 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) unsigned max; int ret; - i = (sb->s_blocksize_bits + 2) * sizeof(unsigned short); + i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { return -ENOMEM; } - i = (sb->s_blocksize_bits + 2) * sizeof(unsigned int); + i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { kfree(sbi->s_mb_offsets); -- cgit v1.2.3 From a36b44988cef1fc007535107013571fa691a2d7f Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 25 Aug 2009 22:36:45 -0400 Subject: ext4: use ext4_grpblk_t more extensively unsigned short is potentially too small to track blocks within a group; today it is safe due to restrictions in e2fsprogs but we have _lo / _hi bits for group blocks with the intent to go up to 32 bits, so clean this up now. There are many more places where we use unsigned/int/unsigned int to contain a group block but this should at least fix all the short types. I added a few comments to the struct ext4_group_info definition as well. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 11 +++++++---- fs/ext4/mballoc.c | 18 +++++++++--------- fs/ext4/mballoc.h | 6 +++--- 3 files changed, 19 insertions(+), 16 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 02b22885eb02..41a76e163b99 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1577,15 +1577,18 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) struct ext4_group_info { unsigned long bb_state; struct rb_root bb_free_root; - unsigned short bb_first_free; - unsigned short bb_free; - unsigned short bb_fragments; + ext4_grpblk_t bb_first_free; /* first free block */ + ext4_grpblk_t bb_free; /* total free blocks */ + ext4_grpblk_t bb_fragments; /* nr of freespace fragments */ struct list_head bb_prealloc_list; #ifdef DOUBLE_CHECK void *bb_bitmap; #endif struct rw_semaphore alloc_sem; - unsigned short bb_counters[]; + ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block + * regions, index is order. + * bb_counters[3] = 5 means + * 5 free 8-block regions. */ }; #define EXT4_GROUP_INFO_NEED_INIT_BIT 0 diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 081eaf7fce89..3086b3c65adc 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -623,13 +623,13 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, /* FIXME!! need more doc */ static void ext4_mb_mark_free_simple(struct super_block *sb, - void *buddy, unsigned first, int len, + void *buddy, ext4_grpblk_t first, ext4_grpblk_t len, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); - unsigned short min; - unsigned short max; - unsigned short chunk; + ext4_grpblk_t min; + ext4_grpblk_t max; + ext4_grpblk_t chunk; unsigned short border; BUG_ON(len > EXT4_BLOCKS_PER_GROUP(sb)); @@ -663,10 +663,10 @@ void ext4_mb_generate_buddy(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); - unsigned short max = EXT4_BLOCKS_PER_GROUP(sb); - unsigned short i = 0; - unsigned short first; - unsigned short len; + ext4_grpblk_t max = EXT4_BLOCKS_PER_GROUP(sb); + ext4_grpblk_t i = 0; + ext4_grpblk_t first; + ext4_grpblk_t len; unsigned free = 0; unsigned fragments = 0; unsigned long long period = get_cycles(); @@ -2325,7 +2325,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) struct ext4_buddy e4b; struct sg { struct ext4_group_info info; - unsigned short counters[16]; + ext4_grpblk_t counters[16]; } sg; group--; diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 9db890d4d275..188d3d709b24 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -136,8 +136,8 @@ struct ext4_prealloc_space { unsigned pa_deleted; ext4_fsblk_t pa_pstart; /* phys. block */ ext4_lblk_t pa_lstart; /* log. block */ - unsigned short pa_len; /* len of preallocated chunk */ - unsigned short pa_free; /* how many blocks are free */ + ext4_grpblk_t pa_len; /* len of preallocated chunk */ + ext4_grpblk_t pa_free; /* how many blocks are free */ unsigned short pa_type; /* pa type. inode or group */ spinlock_t *pa_obj_lock; struct inode *pa_inode; /* hack, for history only */ @@ -152,7 +152,7 @@ struct ext4_free_extent { ext4_lblk_t fe_logical; ext4_grpblk_t fe_start; ext4_group_t fe_group; - int fe_len; + ext4_grpblk_t fe_len; }; /* -- cgit v1.2.3 From 55ad63bf3a30936aced50f13452735c2f58b234c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 28 Aug 2009 10:40:33 -0400 Subject: ext4: fix extent sanity checking code with AGGRESSIVE_TEST The extents sanity-checking code depends on the ext4_ext_space_*() functions returning the maximum alloable size for eh_max; however, when the debugging #ifdef AGGRESSIVE_TEST is enabled to test the extent tree handling code, this prevents a normally created ext4 filesystem from being mounted with the errors: Aug 26 15:43:50 bsd086 kernel: [ 96.070277] EXT4-fs error (device sda8): ext4_ext_check_inode: bad header/extent in inode #8: too large eh_max - magic f30a, entries 1, max 4(3), depth 0(0) Aug 26 15:43:50 bsd086 kernel: [ 96.070526] EXT4-fs (sda8): no journal found Bug reported by Akira Fujita. Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 60 +++++++++++++++++++++++++++++++------------------------ 1 file changed, 34 insertions(+), 26 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 8c20caf4aa5c..7a3832577923 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -229,57 +229,65 @@ ext4_ext_new_meta_block(handle_t *handle, struct inode *inode, return newblock; } -static int ext4_ext_space_block(struct inode *inode) +static inline int ext4_ext_space_block(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent); + if (!check) { #ifdef AGGRESSIVE_TEST - if (size > 6) - size = 6; + if (size > 6) + size = 6; #endif + } return size; } -static int ext4_ext_space_block_idx(struct inode *inode) +static inline int ext4_ext_space_block_idx(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent_idx); + if (!check) { #ifdef AGGRESSIVE_TEST - if (size > 5) - size = 5; + if (size > 5) + size = 5; #endif + } return size; } -static int ext4_ext_space_root(struct inode *inode) +static inline int ext4_ext_space_root(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent); + if (!check) { #ifdef AGGRESSIVE_TEST - if (size > 3) - size = 3; + if (size > 3) + size = 3; #endif + } return size; } -static int ext4_ext_space_root_idx(struct inode *inode) +static inline int ext4_ext_space_root_idx(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent_idx); + if (!check) { #ifdef AGGRESSIVE_TEST - if (size > 4) - size = 4; + if (size > 4) + size = 4; #endif + } return size; } @@ -293,9 +301,9 @@ int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks) int lcap, icap, rcap, leafs, idxs, num; int newextents = blocks; - rcap = ext4_ext_space_root_idx(inode); - lcap = ext4_ext_space_block(inode); - icap = ext4_ext_space_block_idx(inode); + rcap = ext4_ext_space_root_idx(inode, 0); + lcap = ext4_ext_space_block(inode, 0); + icap = ext4_ext_space_block_idx(inode, 0); /* number of new leaf blocks needed */ num = leafs = (newextents + lcap - 1) / lcap; @@ -320,14 +328,14 @@ ext4_ext_max_entries(struct inode *inode, int depth) if (depth == ext_depth(inode)) { if (depth == 0) - max = ext4_ext_space_root(inode); + max = ext4_ext_space_root(inode, 1); else - max = ext4_ext_space_root_idx(inode); + max = ext4_ext_space_root_idx(inode, 1); } else { if (depth == 0) - max = ext4_ext_space_block(inode); + max = ext4_ext_space_block(inode, 1); else - max = ext4_ext_space_block_idx(inode); + max = ext4_ext_space_block_idx(inode, 1); } return max; @@ -626,7 +634,7 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode) eh->eh_depth = 0; eh->eh_entries = 0; eh->eh_magic = EXT4_EXT_MAGIC; - eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode)); + eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); ext4_mark_inode_dirty(handle, inode); ext4_ext_invalidate_cache(inode); return 0; @@ -851,7 +859,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh = ext_block_hdr(bh); neh->eh_entries = 0; - neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode)); + neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_depth = 0; ex = EXT_FIRST_EXTENT(neh); @@ -927,7 +935,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh = ext_block_hdr(bh); neh->eh_entries = cpu_to_le16(1); neh->eh_magic = EXT4_EXT_MAGIC; - neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode)); + neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); neh->eh_depth = cpu_to_le16(depth - i); fidx = EXT_FIRST_INDEX(neh); fidx->ei_block = border; @@ -1052,9 +1060,9 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, /* old root could have indexes or leaves * so calculate e_max right way */ if (ext_depth(inode)) - neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode)); + neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); else - neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode)); + neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1069,7 +1077,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, goto out; curp->p_hdr->eh_magic = EXT4_EXT_MAGIC; - curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode)); + curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0)); curp->p_hdr->eh_entries = cpu_to_le16(1); curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr); @@ -2348,7 +2356,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start) if (err == 0) { ext_inode_hdr(inode)->eh_depth = 0; ext_inode_hdr(inode)->eh_max = - cpu_to_le16(ext4_ext_space_root(inode)); + cpu_to_le16(ext4_ext_space_root(inode, 0)); err = ext4_ext_dirty(handle, inode, path); } } -- cgit v1.2.3 From 2c94eb86c66e1eaaa1e7d8a2120f4fad5e7e7736 Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Fri, 28 Aug 2009 21:43:15 -0400 Subject: ext4: Allow rename to create more than EXT4_LINK_MAX subdirectories Use EXT4_DIR_LINK_MAX so that rename() can move a directory into new parent directory without running into the EXT4_LINK_MAX limit. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index fea14dbd3c22..ba91bd0f7916 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2421,7 +2421,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; retval = -EMLINK; if (!new_inode && new_dir != old_dir && - new_dir->i_nlink >= EXT4_LINK_MAX) + EXT4_DIR_LINK_MAX(new_dir)) goto end_rename; } if (!new_bh) { -- cgit v1.2.3 From b05ab1dc3795e6f997fb0d34f38fce5012533c3e Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 29 Aug 2009 21:08:08 -0400 Subject: ext4: Limit number of links that can be created by ext4_link() In ext4_link we need to check using EXT4_LINK_MAX, and not EXT4_DIR_LINK_MAX(), since ext4_link() is creating hard links of regular files, and not directories. Signed-off-by: "Theodore Ts'o" --- fs/ext4/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index ba91bd0f7916..f27c8164c1fe 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2318,7 +2318,7 @@ static int ext4_link(struct dentry *old_dentry, struct inode *inode = old_dentry->d_inode; int err, retries = 0; - if (EXT4_DIR_LINK_MAX(inode)) + if (inode->i_nlink >= EXT4_LINK_MAX) return -EMLINK; /* -- cgit v1.2.3 From 98a56ab382079f777e261e14512cbd4fb2107af4 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 17 Sep 2009 08:48:28 -0400 Subject: ext4: Fix spelling typo in the trace format for trace_ext4_da_writepages() Signed-off-by: "Theodore Ts'o" --- include/trace/events/ext4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 8d433c4e3709..15051d2d1219 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -243,7 +243,7 @@ TRACE_EVENT(ext4_da_writepages, __entry->range_cyclic = wbc->range_cyclic; ), - TP_printk("dev %s ino %lu nr_t_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d", + TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d", jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->nonblocking, -- cgit v1.2.3 From de89de6e0cf4b1eb13f27137cf2aa40d287aabdf Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 31 Aug 2009 17:00:59 -0400 Subject: ext4: Restore wbc->range_start in ext4_da_writepages() To solve a lock inversion problem, we implement part of the range_cyclic algorithm in ext4_da_writepages(). (See commit 2acf2c26 for more details.) As part of that change wbc->range_start was modified by ext4's writepages function, which causes its callers to get confused since they aren't expecting the filesystem to modify it. The simplest fix is to save and restore wbc->range_start in ext4_da_writepages. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d61fb523308f..ff659e757578 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2749,6 +2749,7 @@ static int ext4_da_writepages(struct address_space *mapping, long pages_skipped; int range_cyclic, cycled = 1, io_done = 0; int needed_blocks, ret = 0, nr_to_writebump = 0; + loff_t range_start = wbc->range_start; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); trace_ext4_da_writepages(inode, wbc); @@ -2917,6 +2918,7 @@ out_writepages: if (!no_nrwrite_index_update) wbc->no_nrwrite_index_update = 0; wbc->nr_to_write -= nr_to_writebump; + wbc->range_start = range_start; trace_ext4_da_writepages_result(inode, wbc, ret, pages_written); return ret; } -- cgit v1.2.3 From b3a3ca8ca0c3c29abc5b2bfe94bb14f3f4590df9 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 31 Aug 2009 23:13:11 -0400 Subject: ext4: Add new tracepoint: trace_ext4_da_write_pages() Add a new tracepoint which shows the pages that will be written using write_cache_pages() by ext4_da_writepages(). Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 15 +++++++++++++++ fs/ext4/inode.c | 13 +------------ include/trace/events/ext4.h | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 50 insertions(+), 12 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 41a76e163b99..81014f4ed22d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -113,6 +113,21 @@ struct ext4_allocation_request { unsigned int flags; }; +/* + * For delayed allocation tracking + */ +struct mpage_da_data { + struct inode *inode; + sector_t b_blocknr; /* start block number of extent */ + size_t b_size; /* size of extent */ + unsigned long b_state; /* state of the extent */ + unsigned long first_page, next_page; /* extent of pages */ + struct writeback_control *wbc; + int io_done; + int pages_written; + int retval; +}; + /* * Special inodes numbers */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ff659e757578..17802a96af9f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1875,18 +1875,6 @@ static void ext4_da_page_release_reservation(struct page *page, * Delayed allocation stuff */ -struct mpage_da_data { - struct inode *inode; - sector_t b_blocknr; /* start block number of extent */ - size_t b_size; /* size of extent */ - unsigned long b_state; /* state of the extent */ - unsigned long first_page, next_page; /* extent of pages */ - struct writeback_control *wbc; - int io_done; - int pages_written; - int retval; -}; - /* * mpage_da_submit_io - walks through extent of pages and try to write * them with writepage() call back @@ -2863,6 +2851,7 @@ retry: mpd.io_done = 1; ret = MPAGE_DA_EXTENT_TAIL; } + trace_ext4_da_write_pages(inode, &mpd); wbc->nr_to_write -= mpd.pages_written; ext4_journal_stop(handle); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 15051d2d1219..dd43399288ea 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -251,6 +251,40 @@ TRACE_EVENT(ext4_da_writepages, __entry->range_cyclic) ); +TRACE_EVENT(ext4_da_write_pages, + TP_PROTO(struct inode *inode, struct mpage_da_data *mpd), + + TP_ARGS(inode, mpd), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u64, b_blocknr ) + __field( __u32, b_size ) + __field( __u32, b_state ) + __field( unsigned long, first_page ) + __field( int, io_done ) + __field( int, pages_written ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->b_blocknr = mpd->b_blocknr; + __entry->b_size = mpd->b_size; + __entry->b_state = mpd->b_state; + __entry->first_page = mpd->first_page; + __entry->io_done = mpd->io_done; + __entry->pages_written = mpd->pages_written; + ), + + TP_printk("dev %s ino %lu b_blocknr %llu b_size %u b_state 0x%04x first_page %lu io_done %d pages_written %d", + jbd2_dev_to_name(__entry->dev), __entry->ino, + __entry->b_blocknr, __entry->b_size, + __entry->b_state, __entry->first_page, + __entry->io_done, __entry->pages_written) +); + TRACE_EVENT(ext4_da_writepages_result, TP_PROTO(struct inode *inode, struct writeback_control *wbc, int ret, int pages_written), -- cgit v1.2.3 From 7f1346a9de6a689b03f2c1c3a387e49ec64da267 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Sat, 5 Sep 2009 09:28:54 -0400 Subject: ext4: Declare seq_operations and file_operations structures as const Signed-off-by: Tobias Klauser Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 3086b3c65adc..5ef6daf0cdc6 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2202,7 +2202,7 @@ static void ext4_mb_seq_history_stop(struct seq_file *seq, void *v) { } -static struct seq_operations ext4_mb_seq_history_ops = { +static const struct seq_operations ext4_mb_seq_history_ops = { .start = ext4_mb_seq_history_start, .next = ext4_mb_seq_history_next, .stop = ext4_mb_seq_history_stop, @@ -2284,7 +2284,7 @@ static ssize_t ext4_mb_seq_history_write(struct file *file, return count; } -static struct file_operations ext4_mb_seq_history_fops = { +static const struct file_operations ext4_mb_seq_history_fops = { .owner = THIS_MODULE, .open = ext4_mb_seq_history_open, .read = seq_read, @@ -2363,7 +2363,7 @@ static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v) { } -static struct seq_operations ext4_mb_seq_groups_ops = { +static const struct seq_operations ext4_mb_seq_groups_ops = { .start = ext4_mb_seq_groups_start, .next = ext4_mb_seq_groups_next, .stop = ext4_mb_seq_groups_stop, @@ -2384,7 +2384,7 @@ static int ext4_mb_seq_groups_open(struct inode *inode, struct file *file) } -static struct file_operations ext4_mb_seq_groups_fops = { +static const struct file_operations ext4_mb_seq_groups_fops = { .owner = THIS_MODULE, .open = ext4_mb_seq_groups_open, .read = seq_read, -- cgit v1.2.3 From a3710fd1ee8cd542c5de63cf2c39f8912031f867 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 17 Sep 2009 08:50:18 -0400 Subject: ext4: fix tracepoint format string warnings Unlike on some other architectures ino_t is an unsigned int on s390. So add an explicit cast to avoid lots of compile warnings: In file included from include/trace/ftrace.h:285, from include/trace/define_trace.h:61, from include/trace/events/ext4.h:711, from fs/ext4/super.c:50: include/trace/events/ext4.h: In function 'ftrace_raw_output_ext4_free_inode': include/trace/events/ext4.h:12: warning: format '%lu' expects type 'long unsigned int', but argument 4 has type 'ino_t' Signed-off-by: Heiko Carstens Signed-off-by: "Theodore Ts'o" --- include/trace/events/ext4.h | 75 ++++++++++++++++++++++++--------------------- include/trace/events/jbd2.h | 2 +- 2 files changed, 41 insertions(+), 36 deletions(-) diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index dd43399288ea..68b53c7ef8a7 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -33,8 +33,8 @@ TRACE_EVENT(ext4_free_inode, ), TP_printk("dev %s ino %lu mode %d uid %u gid %u blocks %llu", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->mode, - __entry->uid, __entry->gid, + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->mode, __entry->uid, __entry->gid, (unsigned long long) __entry->blocks) ); @@ -56,7 +56,8 @@ TRACE_EVENT(ext4_request_inode, ), TP_printk("dev %s dir %lu mode %d", - jbd2_dev_to_name(__entry->dev), __entry->dir, __entry->mode) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->dir, + __entry->mode) ); TRACE_EVENT(ext4_allocate_inode, @@ -79,7 +80,8 @@ TRACE_EVENT(ext4_allocate_inode, ), TP_printk("dev %s ino %lu dir %lu mode %d", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->dir, __entry->mode) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + (unsigned long) __entry->dir, __entry->mode) ); TRACE_EVENT(ext4_write_begin, @@ -106,8 +108,8 @@ TRACE_EVENT(ext4_write_begin, ), TP_printk("dev %s ino %lu pos %llu len %u flags %u", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, - __entry->flags) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->pos, __entry->len, __entry->flags) ); TRACE_EVENT(ext4_ordered_write_end, @@ -133,8 +135,8 @@ TRACE_EVENT(ext4_ordered_write_end, ), TP_printk("dev %s ino %lu pos %llu len %u copied %u", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, - __entry->copied) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->pos, __entry->len, __entry->copied) ); TRACE_EVENT(ext4_writeback_write_end, @@ -160,8 +162,8 @@ TRACE_EVENT(ext4_writeback_write_end, ), TP_printk("dev %s ino %lu pos %llu len %u copied %u", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, - __entry->copied) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->pos, __entry->len, __entry->copied) ); TRACE_EVENT(ext4_journalled_write_end, @@ -186,8 +188,8 @@ TRACE_EVENT(ext4_journalled_write_end, ), TP_printk("dev %s ino %lu pos %llu len %u copied %u", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, - __entry->copied) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->pos, __entry->len, __entry->copied) ); TRACE_EVENT(ext4_writepage, @@ -209,7 +211,8 @@ TRACE_EVENT(ext4_writepage, ), TP_printk("dev %s ino %lu page_index %lu", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->index) ); TRACE_EVENT(ext4_da_writepages, @@ -244,7 +247,8 @@ TRACE_EVENT(ext4_da_writepages, ), TP_printk("dev %s ino %lu nr_to_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->nr_to_write, + jbd2_dev_to_name(__entry->dev), + (unsigned long) __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->nonblocking, __entry->for_kupdate, __entry->for_reclaim, @@ -279,7 +283,7 @@ TRACE_EVENT(ext4_da_write_pages, ), TP_printk("dev %s ino %lu b_blocknr %llu b_size %u b_state 0x%04x first_page %lu io_done %d pages_written %d", - jbd2_dev_to_name(__entry->dev), __entry->ino, + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, __entry->b_blocknr, __entry->b_size, __entry->b_state, __entry->first_page, __entry->io_done, __entry->pages_written) @@ -314,7 +318,8 @@ TRACE_EVENT(ext4_da_writepages_result, ), TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->ret, + jbd2_dev_to_name(__entry->dev), + (unsigned long) __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, __entry->encountered_congestion, __entry->more_io, __entry->no_nrwrite_index_update) @@ -343,8 +348,8 @@ TRACE_EVENT(ext4_da_write_begin, ), TP_printk("dev %s ino %lu pos %llu len %u flags %u", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, - __entry->flags) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->pos, __entry->len, __entry->flags) ); TRACE_EVENT(ext4_da_write_end, @@ -370,8 +375,8 @@ TRACE_EVENT(ext4_da_write_end, ), TP_printk("dev %s ino %lu pos %llu len %u copied %u", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len, - __entry->copied) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->pos, __entry->len, __entry->copied) ); TRACE_EVENT(ext4_discard_blocks, @@ -421,8 +426,8 @@ TRACE_EVENT(ext4_mb_new_inode_pa, ), TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pa_pstart, - __entry->pa_len, __entry->pa_lstart) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart) ); TRACE_EVENT(ext4_mb_new_group_pa, @@ -449,8 +454,8 @@ TRACE_EVENT(ext4_mb_new_group_pa, ), TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pa_pstart, - __entry->pa_len, __entry->pa_lstart) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart) ); TRACE_EVENT(ext4_mb_release_inode_pa, @@ -476,8 +481,8 @@ TRACE_EVENT(ext4_mb_release_inode_pa, ), TP_printk("dev %s ino %lu block %llu count %u", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block, - __entry->count) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->block, __entry->count) ); TRACE_EVENT(ext4_mb_release_group_pa, @@ -522,7 +527,7 @@ TRACE_EVENT(ext4_discard_preallocations, ), TP_printk("dev %s ino %lu", - jbd2_dev_to_name(__entry->dev), __entry->ino) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino) ); TRACE_EVENT(ext4_mb_discard_preallocations, @@ -577,8 +582,8 @@ TRACE_EVENT(ext4_request_blocks, ), TP_printk("dev %s ino %lu flags %u len %u lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags, - __entry->len, + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->flags, __entry->len, (unsigned long long) __entry->logical, (unsigned long long) __entry->goal, (unsigned long long) __entry->lleft, @@ -621,8 +626,8 @@ TRACE_EVENT(ext4_allocate_blocks, ), TP_printk("dev %s ino %lu flags %u len %u block %llu lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags, - __entry->len, __entry->block, + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->flags, __entry->len, __entry->block, (unsigned long long) __entry->logical, (unsigned long long) __entry->goal, (unsigned long long) __entry->lleft, @@ -655,8 +660,8 @@ TRACE_EVENT(ext4_free_blocks, ), TP_printk("dev %s ino %lu block %llu count %lu metadata %d", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block, - __entry->count, __entry->metadata) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->block, __entry->count, __entry->metadata) ); TRACE_EVENT(ext4_sync_file, @@ -679,8 +684,8 @@ TRACE_EVENT(ext4_sync_file, ), TP_printk("dev %s ino %ld parent %ld datasync %d ", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->parent, - __entry->datasync) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + (unsigned long) __entry->parent, __entry->datasync) ); TRACE_EVENT(ext4_sync_fs, diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index 10813fa0c8d0..b851f0b4701c 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -159,7 +159,7 @@ TRACE_EVENT(jbd2_submit_inode_data, ), TP_printk("dev %s ino %lu", - jbd2_dev_to_name(__entry->dev), __entry->ino) + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino) ); #endif /* _TRACE_JBD2_H */ -- cgit v1.2.3 From d0646f7b636d067d715fab52a2ba9c6f0f46b0d7 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 5 Sep 2009 12:50:43 -0400 Subject: ext4: Remove journal_checksum mount option and enable it by default There's no real cost for the journal checksum feature, and we should make sure it is enabled all the time. Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/ext4.txt | 8 +------- fs/ext4/ext4.h | 1 - fs/ext4/super.c | 20 ++++++-------------- 3 files changed, 7 insertions(+), 22 deletions(-) diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 7be02ac5fa36..3e329dbac785 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -134,15 +134,9 @@ ro Mount filesystem read only. Note that ext4 will mount options "ro,noload" can be used to prevent writes to the filesystem. -journal_checksum Enable checksumming of the journal transactions. - This will allow the recovery code in e2fsck and the - kernel to detect corruption in the kernel. It is a - compatible change and will be ignored by older kernels. - journal_async_commit Commit block can be written to disk without waiting for descriptor blocks. If enabled older kernels cannot - mount the device. This will enable 'journal_checksum' - internally. + mount the device. journal=update Update the ext4 file system's journal to the current format. diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 81014f4ed22d..4dc64ed58d26 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -711,7 +711,6 @@ struct ext4_inode_info { #define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */ #define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ #define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ -#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */ #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4037fe0b5a5c..f1815d3bcfd5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1280,11 +1280,9 @@ static int parse_options(char *options, struct super_block *sb, *journal_devnum = option; break; case Opt_journal_checksum: - set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM); - break; + break; /* Kept for backwards compatibility */ case Opt_journal_async_commit: set_opt(sbi->s_mount_opt, JOURNAL_ASYNC_COMMIT); - set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM); break; case Opt_noload: set_opt(sbi->s_mount_opt, NOLOAD); @@ -2751,20 +2749,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount4; } - if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { - jbd2_journal_set_features(sbi->s_journal, - JBD2_FEATURE_COMPAT_CHECKSUM, 0, + jbd2_journal_set_features(sbi->s_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0); + if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) + jbd2_journal_set_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); - } else if (test_opt(sb, JOURNAL_CHECKSUM)) { - jbd2_journal_set_features(sbi->s_journal, - JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0); + else jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); - } else { - jbd2_journal_clear_features(sbi->s_journal, - JBD2_FEATURE_COMPAT_CHECKSUM, 0, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); - } /* We have now updated the journal if required, so we can * validate the data journaling mode. */ -- cgit v1.2.3 From 5f3481e9a80c240f169b36ea886e2325b9aeb745 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 5 Sep 2009 21:42:42 -0400 Subject: ext4: fix cache flush in ext4_sync_file We need to flush the write cache unconditionally in ->fsync, otherwise writes into already allocated blocks can get lost. Writes into fully allocated files are very common when using disk images for virtualization, and without this fix can easily lose data after an fdatasync, which is the typical implementation for a cache flush on the virtual drive. Signed-off-by: Christoph Hellwig Acked-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/fsync.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 83cf6415f599..ab418c0f502d 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -92,9 +92,9 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) .nr_to_write = 0, /* sys_fsync did this */ }; ret = sync_inode(inode, &wbc); - if (journal && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); } out: + if (journal && (journal->j_flags & JBD2_BARRIER)) + blkdev_issue_flush(inode->i_sb->s_bdev, NULL); return ret; } -- cgit v1.2.3 From 70d5d3dcea47c16058d2b093c29e07fdf61b56ad Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Wed, 16 Sep 2009 14:28:22 -0400 Subject: ext4: Fix wrong comparisons in mext_check_arguments() The mext_check_arguments() function in move_extents.c has wrong comparisons. orig_start which is passed from user-space is block unit, but i_size of inode is byte unit, therefore the checks do not work fine. This mis-check leads to the overflow of 'len' and then hits BUG_ON() in ext4_move_extents(). The patch fixes this issue. Signed-off-by: Akira Fujita Reviewed-by: Greg Freemyer Signed-off-by: "Theodore Ts'o" --- fs/ext4/move_extent.c | 46 +++++++++++++++++++++++++++------------------- 1 file changed, 27 insertions(+), 19 deletions(-) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 5821e0bee917..c593eb2b193a 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -898,6 +898,10 @@ mext_check_arguments(struct inode *orig_inode, struct inode *donor_inode, __u64 orig_start, __u64 donor_start, __u64 *len, __u64 moved_len) { + ext4_lblk_t orig_blocks, donor_blocks; + unsigned int blkbits = orig_inode->i_blkbits; + unsigned int blocksize = 1 << blkbits; + /* Regular file check */ if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) { ext4_debug("ext4 move extent: The argument files should be " @@ -972,43 +976,47 @@ mext_check_arguments(struct inode *orig_inode, } if (orig_inode->i_size > donor_inode->i_size) { - if (orig_start >= donor_inode->i_size) { + donor_blocks = (donor_inode->i_size + blocksize - 1) >> blkbits; + /* TODO: eliminate this artificial restriction */ + if (orig_start >= donor_blocks) { ext4_debug("ext4 move extent: orig start offset " - "[%llu] should be less than donor file size " - "[%lld] [ino:orig %lu, donor_inode %lu]\n", - orig_start, donor_inode->i_size, + "[%llu] should be less than donor file blocks " + "[%u] [ino:orig %lu, donor %lu]\n", + orig_start, donor_blocks, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } - if (orig_start + *len > donor_inode->i_size) { + /* TODO: eliminate this artificial restriction */ + if (orig_start + *len > donor_blocks) { ext4_debug("ext4 move extent: End offset [%llu] should " - "be less than donor file size [%lld]." - "So adjust length from %llu to %lld " + "be less than donor file blocks [%u]." + "So adjust length from %llu to %llu " "[ino:orig %lu, donor %lu]\n", - orig_start + *len, donor_inode->i_size, - *len, donor_inode->i_size - orig_start, + orig_start + *len, donor_blocks, + *len, donor_blocks - orig_start, orig_inode->i_ino, donor_inode->i_ino); - *len = donor_inode->i_size - orig_start; + *len = donor_blocks - orig_start; } } else { - if (orig_start >= orig_inode->i_size) { + orig_blocks = (orig_inode->i_size + blocksize - 1) >> blkbits; + if (orig_start >= orig_blocks) { ext4_debug("ext4 move extent: start offset [%llu] " - "should be less than original file size " - "[%lld] [inode:orig %lu, donor %lu]\n", - orig_start, orig_inode->i_size, + "should be less than original file blocks " + "[%u] [ino:orig %lu, donor %lu]\n", + orig_start, orig_blocks, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } - if (orig_start + *len > orig_inode->i_size) { + if (orig_start + *len > orig_blocks) { ext4_debug("ext4 move extent: Adjust length " - "from %llu to %lld. Because it should be " - "less than original file size " + "from %llu to %llu. Because it should be " + "less than original file blocks " "[ino:orig %lu, donor %lu]\n", - *len, orig_inode->i_size - orig_start, + *len, orig_blocks - orig_start, orig_inode->i_ino, donor_inode->i_ino); - *len = orig_inode->i_size - orig_start; + *len = orig_blocks - orig_start; } } -- cgit v1.2.3 From daea696dbac0e33af3cfe304efbfb8d74e0effe6 Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Sat, 5 Sep 2009 22:11:55 -0400 Subject: ext4: Remove unneeded BUG_ON() in ext4_move_extents() The ext4_move_extents() functions checks with BUG_ON() whether the exchanged blocks count accords with request blocks count. But, if the target range (orig_start + len) includes sparse block(s), 'moved_len' (exchanged blocks count) does not agree with 'len' (request blocks count), since sparse block is not counted in 'moved_len'. This causes us to hit the BUG_ON(), even though the function succeeded. Signed-off-by: Akira Fujita Signed-off-by: "Theodore Ts'o" --- fs/ext4/move_extent.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index c593eb2b193a..c8c66b167cd7 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -1322,8 +1322,5 @@ out2: if (ret) return ret; - /* All of the specified blocks must be exchanged in succeed */ - BUG_ON(*moved_len != len); - return 0; } -- cgit v1.2.3 From 8d6669133d8cdbb7cbe0e1f0f3744e7802a84afe Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Sat, 5 Sep 2009 22:46:29 -0400 Subject: ext4: Return exchanged blocks count to user space in failure Return exchanged blocks count (moved_len) to user space, if ext4_move_extents() failed on the way. Signed-off-by: Akira Fujita Signed-off-by: "Theodore Ts'o" --- fs/ext4/ioctl.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 7050a9cd04a4..c1cdf613e725 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -243,10 +243,9 @@ setversion_out: me.donor_start, me.len, &me.moved_len); fput(donor_filp); - if (!err) - if (copy_to_user((struct move_extent *)arg, - &me, sizeof(me))) - return -EFAULT; + if (copy_to_user((struct move_extent *)arg, &me, sizeof(me))) + return -EFAULT; + return err; } -- cgit v1.2.3 From 44fc48f7048ab9657b524938a832fec4e0acea98 Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Sat, 5 Sep 2009 23:12:41 -0400 Subject: ext4: Fix small typo for move_extent_per_page() This function means moving extents every page, so change its name from move_exgtent_par_page(). Signed-off-by: Akira Fujita Signed-off-by: "Theodore Ts'o" --- fs/ext4/move_extent.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index c8c66b167cd7..4c4491cef357 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -740,7 +740,7 @@ out: * on success, or a negative error value on failure. */ static int -move_extent_par_page(struct file *o_filp, struct inode *donor_inode, +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) { @@ -1267,7 +1267,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, while (orig_page_offset <= seq_end_page) { /* Swap original branches with new branches */ - ret = move_extent_par_page(o_filp, donor_inode, + ret = move_extent_per_page(o_filp, donor_inode, orig_page_offset, data_offset_in_page, block_len_in_page, uninit); -- cgit v1.2.3 From a827eaffff07c7d58a4cb32158cbeb4849f4e33a Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Wed, 9 Sep 2009 22:36:03 -0400 Subject: ext4: Take page lock before looking at attached buffer_heads flags In order to check whether the buffer_heads are mapped we need to hold page lock. Otherwise a reclaim can cleanup the attached buffer_heads. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 17802a96af9f..5c0d17066f4a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5286,12 +5286,21 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) else len = PAGE_CACHE_SIZE; + lock_page(page); + /* + * return if we have all the buffers mapped. This avoid + * the need to call write_begin/write_end which does a + * journal_start/journal_stop which can block and take + * long time + */ if (page_has_buffers(page)) { - /* return if we have all the buffers mapped */ if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped)) + ext4_bh_unmapped)) { + unlock_page(page); goto out_unlock; + } } + unlock_page(page); /* * OK, we need to fill the hole... Do write_begin write_end * to do block allocation/reservation.We are not holding -- cgit v1.2.3 From 80e42468d65475e92651e62175bb7807773321d0 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 8 Sep 2009 08:21:26 -0400 Subject: ext4: print more sysadmin-friendly message in check_block_validity() Drop the WARN_ON(1), as he stack trace is not appropriate, since it is triggered by file system corruption, and it misleads users into thinking there is a kernel bug. In addition, change the message displayed by ext4_error() to make it clear that this is a file system corruption problem. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5c0d17066f4a..6253ecdac67f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1121,16 +1121,15 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) ext4_discard_preallocations(inode); } -static int check_block_validity(struct inode *inode, sector_t logical, - sector_t phys, int len) +static int check_block_validity(struct inode *inode, const char *msg, + sector_t logical, sector_t phys, int len) { if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) { - ext4_error(inode->i_sb, "check_block_validity", + ext4_error(inode->i_sb, msg, "inode #%lu logical block %llu mapped to %llu " "(size %d)", inode->i_ino, (unsigned long long) logical, (unsigned long long) phys, len); - WARN_ON(1); return -EIO; } return 0; @@ -1182,8 +1181,8 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, up_read((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && buffer_mapped(bh)) { - int ret = check_block_validity(inode, block, - bh->b_blocknr, retval); + int ret = check_block_validity(inode, "file system corruption", + block, bh->b_blocknr, retval); if (ret != 0) return ret; } @@ -1264,8 +1263,9 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && buffer_mapped(bh)) { - int ret = check_block_validity(inode, block, - bh->b_blocknr, retval); + int ret = check_block_validity(inode, "file system " + "corruption after allocation", + block, bh->b_blocknr, retval); if (ret != 0) return ret; } -- cgit v1.2.3 From c7acb4c16646943180bd221c167a077e0a084f9c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 9 Sep 2009 21:32:41 -0400 Subject: ext4: Use bforget() in no journal mode for ext4_journal_{forget,revoke}() When ext4 is using a journal, a metadata block which is deallocated must be passed into the journal layer so it can be dropped from the current transaction and/or revoked. This is done by calling the functions ext4_journal_forget() and ext4_journal_revoke(), which call jbd2_journal_forget(), and jbd2_journal_revoke(), respectively. Since the jbd2_journal_forget() and jbd2_journal_revoke() call bforget(), if ext4 is not using a journal, ext4_journal_forget() and ext4_journal_revoke() must call bforget() to avoid a dirty metadata block overwriting a block after it has been reallocated and reused for another inode's data block. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4_jbd2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index eb27fd0f2ee8..ecb9ca455fd5 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -44,7 +44,7 @@ int __ext4_journal_forget(const char *where, handle_t *handle, handle, err); } else - brelse(bh); + bforget(bh); return err; } @@ -60,7 +60,7 @@ int __ext4_journal_revoke(const char *where, handle_t *handle, handle, err); } else - brelse(bh); + bforget(bh); return err; } -- cgit v1.2.3 From fe188c0e084bdf3038dc0ac963c21d764f53f7da Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 12 Sep 2009 13:41:55 -0400 Subject: ext4: Assure that metadata blocks are written during fsync in no journal mode When there is no journal present, we must attach buffer heads associated with extent tree and indirect blocks to the inode's mapping->private_list via mark_buffer_dirty_inode() so that ext4_sync_file() --- which is called to service fsync() and fdatasync() system calls --- can write out the inode's metadata blocks by calling sync_mapping_buffers(). Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4_jbd2.c | 5 ++++- fs/ext4/fsync.c | 9 +++++++-- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index ecb9ca455fd5..6a9409920dee 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -89,7 +89,10 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle, ext4_journal_abort_handle(where, __func__, bh, handle, err); } else { - mark_buffer_dirty(bh); + if (inode && bh) + mark_buffer_dirty_inode(bh, inode); + else + mark_buffer_dirty(bh); if (inode && inode_needs_sync(inode)) { sync_dirty_buffer(bh); if (buffer_req(bh) && !buffer_uptodate(bh)) { diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index ab418c0f502d..07475740b512 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -50,7 +50,7 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) { struct inode *inode = dentry->d_inode; journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; - int ret = 0; + int err, ret = 0; J_ASSERT(ext4_journal_current_handle() == NULL); @@ -79,6 +79,9 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) goto out; } + if (!journal) + ret = sync_mapping_buffers(inode->i_mapping); + if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) goto out; @@ -91,7 +94,9 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) .sync_mode = WB_SYNC_ALL, .nr_to_write = 0, /* sys_fsync did this */ }; - ret = sync_inode(inode, &wbc); + err = sync_inode(inode, &wbc); + if (ret == 0) + ret = err; } out: if (journal && (journal->j_flags & JBD2_BARRIER)) -- cgit v1.2.3 From 91ac6f43317c0bf99969665f98016548011dfa38 Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Wed, 9 Sep 2009 22:33:47 -0400 Subject: ext4: Make non-journal fsync work properly Teach ext4_write_inode() and ext4_do_update_inode() about non-journal mode: If we're not using a journal, ext4_write_inode() now calls ext4_do_update_inode() (after getting the iloc via ext4_get_inode_loc()) with a new "do_sync" parameter. If that parameter is nonzero _and_ we're not using a journal, ext4_do_update_inode() calls sync_dirty_buffer() instead of ext4_handle_dirty_metadata(). This problem was found in power-fail testing, checking the amount of loss of files and blocks after a power failure when using fsync() and when not using fsync(). It turned out that using fsync() was actually worse than not doing so, possibly because it increased the likelihood that the inodes would remain unflushed and would therefore be lost at the power failure. Signed-off-by: Frank Mayhar Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 54 ++++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 40 insertions(+), 14 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6253ecdac67f..d04c8428bde2 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4538,7 +4538,8 @@ static int ext4_inode_blocks_set(handle_t *handle, */ static int ext4_do_update_inode(handle_t *handle, struct inode *inode, - struct ext4_iloc *iloc) + struct ext4_iloc *iloc, + int do_sync) { struct ext4_inode *raw_inode = ext4_raw_inode(iloc); struct ext4_inode_info *ei = EXT4_I(inode); @@ -4640,10 +4641,22 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize); } - BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - rc = ext4_handle_dirty_metadata(handle, inode, bh); - if (!err) - err = rc; + /* + * If we're not using a journal and we were called from + * ext4_write_inode() to sync the inode (making do_sync true), + * we can just use sync_dirty_buffer() directly to do our dirty + * work. Testing s_journal here is a bit redundant but it's + * worth it to avoid potential future trouble. + */ + if (EXT4_SB(inode->i_sb)->s_journal == NULL && do_sync) { + BUFFER_TRACE(bh, "call sync_dirty_buffer"); + sync_dirty_buffer(bh); + } else { + BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); + rc = ext4_handle_dirty_metadata(handle, inode, bh); + if (!err) + err = rc; + } ei->i_state &= ~EXT4_STATE_NEW; out_brelse: @@ -4689,19 +4702,32 @@ out_brelse: */ int ext4_write_inode(struct inode *inode, int wait) { + int err; + if (current->flags & PF_MEMALLOC) return 0; - if (ext4_journal_current_handle()) { - jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); - dump_stack(); - return -EIO; - } + if (EXT4_SB(inode->i_sb)->s_journal) { + if (ext4_journal_current_handle()) { + jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); + dump_stack(); + return -EIO; + } - if (!wait) - return 0; + if (!wait) + return 0; + + err = ext4_force_commit(inode->i_sb); + } else { + struct ext4_iloc iloc; - return ext4_force_commit(inode->i_sb); + err = ext4_get_inode_loc(inode, &iloc); + if (err) + return err; + err = ext4_do_update_inode(EXT4_NOJOURNAL_HANDLE, + inode, &iloc, wait); + } + return err; } /* @@ -4995,7 +5021,7 @@ int ext4_mark_iloc_dirty(handle_t *handle, get_bh(iloc->bh); /* ext4_do_update_inode() does jbd2_journal_dirty_metadata */ - err = ext4_do_update_inode(handle, inode, iloc); + err = ext4_do_update_inode(handle, inode, iloc, 0); put_bh(iloc->bh); return err; } -- cgit v1.2.3 From b6a758ec3af3ec236dbfdcf6a06b84ac8f94957e Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Wed, 9 Sep 2009 23:47:46 -0400 Subject: ext4: move ext4_mb_init_group() function earlier in the mballoc.c This moves the function around so that it can be called from ext4_mb_load_buddy(). Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 182 +++++++++++++++++++++++++++--------------------------- 1 file changed, 91 insertions(+), 91 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 5ef6daf0cdc6..fed5ac699141 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -910,6 +910,97 @@ out: return err; } +static noinline_for_stack +int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) +{ + + int ret = 0; + void *bitmap; + int blocks_per_page; + int block, pnum, poff; + int num_grp_locked = 0; + struct ext4_group_info *this_grp; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct inode *inode = sbi->s_buddy_cache; + struct page *page = NULL, *bitmap_page = NULL; + + mb_debug(1, "init group %u\n", group); + blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; + this_grp = ext4_get_group_info(sb, group); + /* + * This ensures we don't add group + * to this buddy cache via resize + */ + num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, group); + if (!EXT4_MB_GRP_NEED_INIT(this_grp)) { + /* + * somebody initialized the group + * return without doing anything + */ + ret = 0; + goto err; + } + /* + * the buddy cache inode stores the block bitmap + * and buddy information in consecutive blocks. + * So for each group we need two blocks. + */ + block = group * 2; + pnum = block / blocks_per_page; + poff = block % blocks_per_page; + page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); + if (page) { + BUG_ON(page->mapping != inode->i_mapping); + ret = ext4_mb_init_cache(page, NULL); + if (ret) { + unlock_page(page); + goto err; + } + unlock_page(page); + } + if (page == NULL || !PageUptodate(page)) { + ret = -EIO; + goto err; + } + mark_page_accessed(page); + bitmap_page = page; + bitmap = page_address(page) + (poff * sb->s_blocksize); + + /* init buddy cache */ + block++; + pnum = block / blocks_per_page; + poff = block % blocks_per_page; + page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); + if (page == bitmap_page) { + /* + * If both the bitmap and buddy are in + * the same page we don't need to force + * init the buddy + */ + unlock_page(page); + } else if (page) { + BUG_ON(page->mapping != inode->i_mapping); + ret = ext4_mb_init_cache(page, bitmap); + if (ret) { + unlock_page(page); + goto err; + } + unlock_page(page); + } + if (page == NULL || !PageUptodate(page)) { + ret = -EIO; + goto err; + } + mark_page_accessed(page); +err: + ext4_mb_put_buddy_cache_lock(sb, group, num_grp_locked); + if (bitmap_page) + page_cache_release(bitmap_page); + if (page) + page_cache_release(page); + return ret; +} + static noinline_for_stack int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b) @@ -1839,97 +1930,6 @@ void ext4_mb_put_buddy_cache_lock(struct super_block *sb, } -static noinline_for_stack -int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) -{ - - int ret; - void *bitmap; - int blocks_per_page; - int block, pnum, poff; - int num_grp_locked = 0; - struct ext4_group_info *this_grp; - struct ext4_sb_info *sbi = EXT4_SB(sb); - struct inode *inode = sbi->s_buddy_cache; - struct page *page = NULL, *bitmap_page = NULL; - - mb_debug(1, "init group %u\n", group); - blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; - this_grp = ext4_get_group_info(sb, group); - /* - * This ensures we don't add group - * to this buddy cache via resize - */ - num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, group); - if (!EXT4_MB_GRP_NEED_INIT(this_grp)) { - /* - * somebody initialized the group - * return without doing anything - */ - ret = 0; - goto err; - } - /* - * the buddy cache inode stores the block bitmap - * and buddy information in consecutive blocks. - * So for each group we need two blocks. - */ - block = group * 2; - pnum = block / blocks_per_page; - poff = block % blocks_per_page; - page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); - if (page) { - BUG_ON(page->mapping != inode->i_mapping); - ret = ext4_mb_init_cache(page, NULL); - if (ret) { - unlock_page(page); - goto err; - } - unlock_page(page); - } - if (page == NULL || !PageUptodate(page)) { - ret = -EIO; - goto err; - } - mark_page_accessed(page); - bitmap_page = page; - bitmap = page_address(page) + (poff * sb->s_blocksize); - - /* init buddy cache */ - block++; - pnum = block / blocks_per_page; - poff = block % blocks_per_page; - page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); - if (page == bitmap_page) { - /* - * If both the bitmap and buddy are in - * the same page we don't need to force - * init the buddy - */ - unlock_page(page); - } else if (page) { - BUG_ON(page->mapping != inode->i_mapping); - ret = ext4_mb_init_cache(page, bitmap); - if (ret) { - unlock_page(page); - goto err; - } - unlock_page(page); - } - if (page == NULL || !PageUptodate(page)) { - ret = -EIO; - goto err; - } - mark_page_accessed(page); -err: - ext4_mb_put_buddy_cache_lock(sb, group, num_grp_locked); - if (bitmap_page) - page_cache_release(bitmap_page); - if (page) - page_cache_release(page); - return ret; -} - static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { -- cgit v1.2.3 From f41c0750538667b87a19c93952e5d42fcc069bd7 Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Wed, 9 Sep 2009 23:34:50 -0400 Subject: ext4: check for need init flag in ext4_mb_load_buddy We should check for need init flag with the group's alloc_sem held, to make sure while we are loading the buddy cache and holding a reference to it, a file system resize can't add new blocks to same group. The patch also drops the need init flag check in ext4_mb_regular_allocator() because doing the check without holding alloc_sem is racy. Signed-off-by: "Theodore Ts'o" Signed-off-by: Aneesh Kumar K.V --- fs/ext4/mballoc.c | 39 ++++++++++++++++++--------------------- 1 file changed, 18 insertions(+), 21 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index fed5ac699141..484c9d10c7fa 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1034,8 +1034,26 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, * groups mapped by the page is blocked * till we are done with allocation */ +repeat_load_buddy: down_read(e4b->alloc_semp); + if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { + /* we need to check for group need init flag + * with alloc_semp held so that we can be sure + * that new blocks didn't get added to the group + * when we are loading the buddy cache + */ + up_read(e4b->alloc_semp); + /* + * we need full data about the group + * to make a good selection + */ + ret = ext4_mb_init_group(sb, group); + if (ret) + return ret; + goto repeat_load_buddy; + } + /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. @@ -2012,27 +2030,6 @@ repeat: if (grp->bb_free == 0) continue; - /* - * if the group is already init we check whether it is - * a good group and if not we don't load the buddy - */ - if (EXT4_MB_GRP_NEED_INIT(grp)) { - /* - * we need full data about the group - * to make a good selection - */ - err = ext4_mb_init_group(sb, group); - if (err) - goto out; - } - - /* - * If the particular group doesn't satisfy our - * criteria we continue with the next group - */ - if (!ext4_mb_good_group(ac, group, cr)) - continue; - err = ext4_mb_load_buddy(sb, group, &e4b); if (err) goto out; -- cgit v1.2.3 From 08c3a8133810d955d97f7146c50c43e4073f2148 Mon Sep 17 00:00:00 2001 From: Aneesh Kumar K.V Date: Wed, 9 Sep 2009 23:50:17 -0400 Subject: ext4: Clarify the locking details in mballoc We don't need to take the alloc_sem lock when we are adding new groups, since mballoc won't see the new group added until we bump sbi->s_groups_count. Signed-off-by: "Theodore Ts'o" Signed-off-by: Aneesh Kumar K.V --- fs/ext4/mballoc.c | 7 +++++-- fs/ext4/resize.c | 7 +------ 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 484c9d10c7fa..d23056d375b3 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -928,8 +928,11 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; this_grp = ext4_get_group_info(sb, group); /* - * This ensures we don't add group - * to this buddy cache via resize + * This ensures that we don't reinit the buddy cache + * page which map to the group from which we are already + * allocating. If we are looking at the buddy cache we would + * have taken a reference using ext4_mb_load_buddy and that + * would have taken the alloc_sem lock. */ num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, group); if (!EXT4_MB_GRP_NEED_INIT(this_grp)) { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 68b0351fc647..3cfc343c41b5 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -746,7 +746,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) struct inode *inode = NULL; handle_t *handle; int gdb_off, gdb_num; - int num_grp_locked = 0; int err, err2; gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb); @@ -856,7 +855,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) * using the new disk blocks. */ - num_grp_locked = ext4_mb_get_buddy_cache_lock(sb, input->group); /* Update group descriptor block for new group */ gdp = (struct ext4_group_desc *)((char *)primary->b_data + gdb_off * EXT4_DESC_SIZE(sb)); @@ -875,10 +873,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) * descriptor */ err = ext4_mb_add_groupinfo(sb, input->group, gdp); - if (err) { - ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked); + if (err) goto exit_journal; - } /* * Make the new blocks and inodes valid next. We do this before @@ -920,7 +916,6 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) /* Update the global fs size fields */ sbi->s_groups_count++; - ext4_mb_put_buddy_cache_lock(sb, input->group, num_grp_locked); ext4_handle_dirty_metadata(handle, NULL, primary); -- cgit v1.2.3 From 71290b368ad5e1e0b0b300c9d5638490a9fd1a2d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 10 Sep 2009 17:31:04 -0400 Subject: ext4: Don't update superblock write time when filesystem is read-only This avoids updating the superblock write time when we are mounting the root file system read/only but we need to replay the journal; at that point, for people who are east of GMT and who make their clock tick in localtime for Windows bug-for-bug compatibility, and this will cause e2fsck to complain and force a full file system check. Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f1815d3bcfd5..9f6fa3f74629 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3222,7 +3222,18 @@ static int ext4_commit_super(struct super_block *sb, int sync) clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } - es->s_wtime = cpu_to_le32(get_seconds()); + /* + * If the file system is mounted read-only, don't update the + * superblock write time. This avoids updating the superblock + * write time when we are mounting the root file system + * read/only but we need to replay the journal; at that point, + * for people who are east of GMT and who make their clock + * tick in localtime for Windows bug-for-bug compatibility, + * the clock is set in the future, and this will cause e2fsck + * to complain and force a full file system check. + */ + if (!(sb->s_flags & MS_RDONLY)) + es->s_wtime = cpu_to_le32(get_seconds()); es->s_kbytes_written = cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) - -- cgit v1.2.3 From 0e3d2a6313d03413d93327202a60256d1d726fdc Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 11 Sep 2009 09:30:12 -0400 Subject: ext4: Fix async commit mode to be safe by using a barrier Previously the journal_async_commit mount option was equivalent to using barrier=0 (and just as unsafe). This patch fixes it so that we eliminate the barrier before the commit block (by not using ordered mode), and explicitly issuing an empty barrier bio after writing the commit block. Because of the journal checksum, it is safe to do this; if the journal blocks are not all written before a power failure, the checksum in the commit block will prevent the last transaction from being replayed. Using the fs_mark benchmark, using journal_async_commit shows a 50% improvement: FSUse% Count Size Files/sec App Overhead 8 1000 10240 30.5 28242 vs. FSUse% Count Size Files/sec App Overhead 8 1000 10240 45.8 28620 Signed-off-by: "Theodore Ts'o" --- fs/jbd2/commit.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 0df600e9162d..26d991ddc1e6 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -25,6 +25,7 @@ #include #include #include +#include #include /* @@ -133,8 +134,8 @@ static int journal_submit_commit_record(journal_t *journal, bh->b_end_io = journal_end_buffer_io_sync; if (journal->j_flags & JBD2_BARRIER && - !JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { + !JBD2_HAS_INCOMPAT_FEATURE(journal, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { set_buffer_ordered(bh); barrier_done = 1; } @@ -706,11 +707,13 @@ start_journal_io: /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) __jbd2_journal_abort_hard(journal); + if (journal->j_flags & JBD2_BARRIER) + blkdev_issue_flush(journal->j_dev, NULL); } /* @@ -833,7 +836,7 @@ wait_for_iobuf: jbd_debug(3, "JBD: commit phase 5\n"); if (!JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) -- cgit v1.2.3 From 1f7bebb9e911d870fa8f997ddff838e82b5715ea Mon Sep 17 00:00:00 2001 From: Andreas Schlick Date: Thu, 10 Sep 2009 23:16:07 -0400 Subject: ext4: Always set dx_node's fake_dirent explicitly. When ext4_dx_add_entry() has to split an index node, it has to ensure that name_len of dx_node's fake_dirent is also zero, because otherwise e2fsck won't recognise it as an intermediate htree node and consider the htree to be corrupted. Signed-off-by: Andreas Schlick Signed-off-by: "Theodore Ts'o" --- fs/ext4/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index f27c8164c1fe..42f81d285cd5 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1597,9 +1597,9 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, goto cleanup; node2 = (struct dx_node *)(bh2->b_data); entries2 = node2->entries; + memset(&node2->fake, 0, sizeof(struct fake_dirent)); node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize, sb->s_blocksize); - node2->fake.inode = 0; BUFFER_TRACE(frame->bh, "get_write_access"); err = ext4_journal_get_write_access(handle, frame->bh); if (err) -- cgit v1.2.3 From 7ad9bb651fc2036ea94bed94da76a4b08959a911 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 11 Sep 2009 16:51:28 -0400 Subject: ext4: Fix initalization of s_flex_groups The s_flex_groups array should have been initialized using atomic_add to sum up the free counts from the block groups that make up a flex_bg. By using atomic_set, the value of the s_flex_groups array was set to the values of the last block group in the flex_bg. The impact of this bug is that the block and inode allocation algorithms might not pick the best flex_bg for new allocation. Thanks to Damien Guibouret for pointing out this problem! Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9f6fa3f74629..04c693357336 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1694,12 +1694,12 @@ static int ext4_fill_flex_info(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); - atomic_set(&sbi->s_flex_groups[flex_group].free_inodes, - ext4_free_inodes_count(sb, gdp)); - atomic_set(&sbi->s_flex_groups[flex_group].free_blocks, - ext4_free_blks_count(sb, gdp)); - atomic_set(&sbi->s_flex_groups[flex_group].used_dirs, - ext4_used_dirs_count(sb, gdp)); + atomic_add(ext4_free_inodes_count(sb, gdp), + &sbi->s_flex_groups[flex_group].free_inodes); + atomic_add(ext4_free_blks_count(sb, gdp), + &sbi->s_flex_groups[flex_group].free_blocks); + atomic_add(ext4_used_dirs_count(sb, gdp), + &sbi->s_flex_groups[flex_group].used_dirs); } return 1; -- cgit v1.2.3 From 3661d28615ea580c1db02a972fd4d3898df1cb01 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 14 Sep 2009 22:59:50 -0400 Subject: ext4: Fix include/trace/events/ext4.h to work with Systemtap Using relative pathnames in #include statements interacts badly with SystemTap, since the fs/ext4/*.h header files are not packaged up as part of a distribution kernel's header files. Since systemtap doesn't use TP_fast_assign(), we can use a blind structure definition and then make sure the needed header files are defined before the ext4 source files #include the trace/events/ext4.h header file. https://bugzilla.redhat.com/show_bug.cgi?id=512478 Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 1 + include/trace/events/ext4.h | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 04c693357336..af95dd8ba54b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -45,6 +45,7 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" +#include "mballoc.h" #define CREATE_TRACE_POINTS #include diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 68b53c7ef8a7..6fe6ce9ee071 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -5,10 +5,12 @@ #define _TRACE_EXT4_H #include -#include "../../../fs/ext4/ext4.h" -#include "../../../fs/ext4/mballoc.h" #include +struct ext4_allocation_context; +struct ext4_allocation_request; +struct ext4_prealloc_space; + TRACE_EVENT(ext4_free_inode, TP_PROTO(struct inode *inode), -- cgit v1.2.3 From e8505970af46658ece2545e9bc1fe594998fdcdf Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Wed, 16 Sep 2009 13:46:38 -0400 Subject: ext4: Replace get_ext_path macro with an inline funciton Replace get_ext_path macro with an inline function, since this macro looks like a function call but its arguments get modified. Ted pointed this out, thanks. Signed-off-by: Akira Fujita Signed-off-by: "Theodore Ts'o" --- fs/ext4/move_extent.c | 55 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 34 insertions(+), 21 deletions(-) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 4c4491cef357..e4bd8761498a 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -19,14 +19,29 @@ #include "ext4_extents.h" #include "ext4.h" -#define get_ext_path(path, inode, block, ret) \ - do { \ - path = ext4_ext_find_extent(inode, block, path); \ - if (IS_ERR(path)) { \ - ret = PTR_ERR(path); \ - path = NULL; \ - } \ - } while (0) +/** + * get_ext_path - Find an extent path for designated logical block number. + * + * @inode: an inode which is searched + * @lblock: logical block number to find an extent path + * @path: pointer to an extent path pointer (for output) + * + * ext4_ext_find_extent wrapper. Return 0 on success, or a negative error value + * on failure. + */ +static inline int +get_ext_path(struct inode *inode, ext4_lblk_t lblock, + struct ext4_ext_path **path) +{ + int ret = 0; + + *path = ext4_ext_find_extent(inode, lblock, *path); + if (IS_ERR(*path)) { + ret = PTR_ERR(*path); + *path = NULL; + } + return ret; +} /** * copy_extent_status - Copy the extent's initialization status @@ -283,7 +298,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode, } if (new_flag) { - get_ext_path(orig_path, orig_inode, eblock, err); + err = get_ext_path(orig_inode, eblock, &orig_path); if (orig_path == NULL) goto out; @@ -293,8 +308,8 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode, } if (end_flag) { - get_ext_path(orig_path, orig_inode, - le32_to_cpu(end_ext->ee_block) - 1, err); + err = get_ext_path(orig_inode, + le32_to_cpu(end_ext->ee_block) - 1, &orig_path); if (orig_path == NULL) goto out; @@ -631,12 +646,12 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, mext_double_down_write(orig_inode, donor_inode); /* Get the original extent for the block "orig_off" */ - get_ext_path(orig_path, orig_inode, orig_off, err); + err = get_ext_path(orig_inode, orig_off, &orig_path); if (orig_path == NULL) goto out; /* Get the donor extent for the head */ - get_ext_path(donor_path, donor_inode, donor_off, err); + err = get_ext_path(donor_inode, donor_off, &donor_path); if (donor_path == NULL) goto out; depth = ext_depth(orig_inode); @@ -678,7 +693,7 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, if (orig_path) ext4_ext_drop_refs(orig_path); - get_ext_path(orig_path, orig_inode, orig_off, err); + err = get_ext_path(orig_inode, orig_off, &orig_path); if (orig_path == NULL) goto out; depth = ext_depth(orig_inode); @@ -692,8 +707,7 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, if (donor_path) ext4_ext_drop_refs(donor_path); - get_ext_path(donor_path, donor_inode, - donor_off, err); + err = get_ext_path(donor_inode, donor_off, &donor_path); if (donor_path == NULL) goto out; depth = ext_depth(donor_inode); @@ -1154,12 +1168,12 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, if (file_end < block_end) len -= block_end - file_end; - get_ext_path(orig_path, orig_inode, block_start, ret); + ret = get_ext_path(orig_inode, block_start, &orig_path); if (orig_path == NULL) goto out2; /* Get path structure to check the hole */ - get_ext_path(holecheck_path, orig_inode, block_start, ret); + ret = get_ext_path(orig_inode, block_start, &holecheck_path); if (holecheck_path == NULL) goto out; @@ -1289,8 +1303,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, /* Decrease buffer counter */ if (holecheck_path) ext4_ext_drop_refs(holecheck_path); - get_ext_path(holecheck_path, orig_inode, - seq_start, ret); + ret = get_ext_path(orig_inode, seq_start, &holecheck_path); if (holecheck_path == NULL) break; depth = holecheck_path->p_depth; @@ -1298,7 +1311,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, /* Decrease buffer counter */ if (orig_path) ext4_ext_drop_refs(orig_path); - get_ext_path(orig_path, orig_inode, seq_start, ret); + ret = get_ext_path(orig_inode, seq_start, &orig_path); if (orig_path == NULL) break; -- cgit v1.2.3 From 2147b1a6a48e28399120ca51d4a91840a278611f Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Wed, 16 Sep 2009 13:46:35 -0400 Subject: ext4: Replace BUG_ON() with ext4_error() in move_extents.c Replace BUG_ON calls with a call to ext4_error() to print an error message if EXT4_IOC_MOVE_EXT failed with some kind of reasons. This will help to debug. Ted pointed this out, thanks. Signed-off-by: Akira Fujita Signed-off-by: "Theodore Ts'o" --- fs/ext4/move_extent.c | 149 ++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 109 insertions(+), 40 deletions(-) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index e4bd8761498a..2258560e9722 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -127,6 +127,31 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, return 1; } +/** + * mext_check_null_inode - NULL check for two inodes + * + * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. + */ +static int +mext_check_null_inode(struct inode *inode1, struct inode *inode2, + const char *function) +{ + int ret = 0; + + if (inode1 == NULL) { + ext4_error(inode2->i_sb, function, + "Both inodes should not be NULL: " + "inode1 NULL inode2 %lu", inode2->i_ino); + ret = -EIO; + } else if (inode2 == NULL) { + ext4_error(inode1->i_sb, function, + "Both inodes should not be NULL: " + "inode1 %lu inode2 NULL", inode1->i_ino); + ret = -EIO; + } + return ret; +} + /** * mext_double_down_read - Acquire two inodes' read semaphore * @@ -139,8 +164,6 @@ mext_double_down_read(struct inode *orig_inode, struct inode *donor_inode) { struct inode *first = orig_inode, *second = donor_inode; - BUG_ON(orig_inode == NULL || donor_inode == NULL); - /* * Use the inode number to provide the stable locking order instead * of its address, because the C language doesn't guarantee you can @@ -167,8 +190,6 @@ mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode) { struct inode *first = orig_inode, *second = donor_inode; - BUG_ON(orig_inode == NULL || donor_inode == NULL); - /* * Use the inode number to provide the stable locking order instead * of its address, because the C language doesn't guarantee you can @@ -193,8 +214,6 @@ mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode) static void mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode) { - BUG_ON(orig_inode == NULL || donor_inode == NULL); - up_read(&EXT4_I(orig_inode)->i_data_sem); up_read(&EXT4_I(donor_inode)->i_data_sem); } @@ -209,8 +228,6 @@ mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode) static void mext_double_up_write(struct inode *orig_inode, struct inode *donor_inode) { - BUG_ON(orig_inode == NULL || donor_inode == NULL); - up_write(&EXT4_I(orig_inode)->i_data_sem); up_write(&EXT4_I(donor_inode)->i_data_sem); } @@ -534,7 +551,15 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode, * oext |-----------| * new_ext |-------| */ - BUG_ON(le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end); + if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) { + ext4_error(orig_inode->i_sb, __func__, + "new_ext_end(%u) should be less than or equal to " + "oext->ee_block(%u) + oext_alen(%d) - 1", + new_ext_end, le32_to_cpu(oext->ee_block), + oext_alen); + ret = -EIO; + goto out; + } /* * Case: new_ext is smaller than original extent @@ -558,6 +583,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode, ret = mext_insert_extents(handle, orig_inode, orig_path, o_start, o_end, &start_ext, &new_ext, &end_ext); +out: return ret; } @@ -668,7 +694,20 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, /* Loop for the donor extents */ while (1) { /* The extent for donor must be found. */ - BUG_ON(!dext || donor_off != le32_to_cpu(tmp_dext.ee_block)); + if (!dext) { + ext4_error(donor_inode->i_sb, __func__, + "The extent for donor must be found"); + err = -EIO; + goto out; + } else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) { + ext4_error(donor_inode->i_sb, __func__, + "Donor offset(%u) and the first block of donor " + "extent(%u) should be equal", + donor_off, + le32_to_cpu(tmp_dext.ee_block)); + err = -EIO; + goto out; + } /* Set donor extent to orig extent */ err = mext_leaf_block(handle, orig_inode, @@ -1050,18 +1089,23 @@ mext_check_arguments(struct inode *orig_inode, * @inode1: the inode structure * @inode2: the inode structure * - * Lock two inodes' i_mutex by i_ino order. This function is moved from - * fs/inode.c. + * Lock two inodes' i_mutex by i_ino order. + * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. */ -static void +static int mext_inode_double_lock(struct inode *inode1, struct inode *inode2) { - if (inode1 == NULL || inode2 == NULL || inode1 == inode2) { - if (inode1) - mutex_lock(&inode1->i_mutex); - else if (inode2) - mutex_lock(&inode2->i_mutex); - return; + int ret = 0; + + BUG_ON(inode1 == NULL && inode2 == NULL); + + ret = mext_check_null_inode(inode1, inode2, __func__); + if (ret < 0) + goto out; + + if (inode1 == inode2) { + mutex_lock(&inode1->i_mutex); + goto out; } if (inode1->i_ino < inode2->i_ino) { @@ -1071,6 +1115,9 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2) mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT); mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD); } + +out: + return ret; } /** @@ -1079,17 +1126,28 @@ mext_inode_double_lock(struct inode *inode1, struct inode *inode2) * @inode1: the inode that is released first * @inode2: the inode that is released second * - * This function is moved from fs/inode.c. + * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. */ -static void +static int mext_inode_double_unlock(struct inode *inode1, struct inode *inode2) { + int ret = 0; + + BUG_ON(inode1 == NULL && inode2 == NULL); + + ret = mext_check_null_inode(inode1, inode2, __func__); + if (ret < 0) + goto out; + if (inode1) mutex_unlock(&inode1->i_mutex); if (inode2 && inode2 != inode1) mutex_unlock(&inode2->i_mutex); + +out: + return ret; } /** @@ -1146,21 +1204,23 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0; ext4_lblk_t rest_blocks; pgoff_t orig_page_offset = 0, seq_end_page; - int ret, depth, last_extent = 0; + int ret1, ret2, depth, last_extent = 0; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; int data_offset_in_page; int block_len_in_page; int uninit; /* protect orig and donor against a truncate */ - mext_inode_double_lock(orig_inode, donor_inode); + ret1 = mext_inode_double_lock(orig_inode, donor_inode); + if (ret1 < 0) + return ret1; mext_double_down_read(orig_inode, donor_inode); /* Check the filesystem environment whether move_extent can be done */ - ret = mext_check_arguments(orig_inode, donor_inode, orig_start, + ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start, donor_start, &len, *moved_len); mext_double_up_read(orig_inode, donor_inode); - if (ret) + if (ret1) goto out2; file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits; @@ -1168,19 +1228,19 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, if (file_end < block_end) len -= block_end - file_end; - ret = get_ext_path(orig_inode, block_start, &orig_path); + ret1 = get_ext_path(orig_inode, block_start, &orig_path); if (orig_path == NULL) goto out2; /* Get path structure to check the hole */ - ret = get_ext_path(orig_inode, block_start, &holecheck_path); + ret1 = get_ext_path(orig_inode, block_start, &holecheck_path); if (holecheck_path == NULL) goto out; depth = ext_depth(orig_inode); ext_cur = holecheck_path[depth].p_ext; if (ext_cur == NULL) { - ret = -EINVAL; + ret1 = -EINVAL; goto out; } @@ -1193,13 +1253,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, last_extent = mext_next_extent(orig_inode, holecheck_path, &ext_cur); if (last_extent < 0) { - ret = last_extent; + ret1 = last_extent; goto out; } last_extent = mext_next_extent(orig_inode, orig_path, &ext_dummy); if (last_extent < 0) { - ret = last_extent; + ret1 = last_extent; goto out; } } @@ -1209,7 +1269,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, if (le32_to_cpu(ext_cur->ee_block) > block_end) { ext4_debug("ext4 move extent: The specified range of file " "may be the hole\n"); - ret = -EINVAL; + ret1 = -EINVAL; goto out; } @@ -1229,7 +1289,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, last_extent = mext_next_extent(orig_inode, holecheck_path, &ext_cur); if (last_extent < 0) { - ret = last_extent; + ret1 = last_extent; break; } add_blocks = ext4_ext_get_actual_len(ext_cur); @@ -1281,16 +1341,23 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, while (orig_page_offset <= seq_end_page) { /* Swap original branches with new branches */ - ret = move_extent_per_page(o_filp, donor_inode, + ret1 = move_extent_per_page(o_filp, donor_inode, orig_page_offset, data_offset_in_page, block_len_in_page, uninit); - if (ret < 0) + if (ret1 < 0) goto out; orig_page_offset++; /* Count how many blocks we have exchanged */ *moved_len += block_len_in_page; - BUG_ON(*moved_len > len); + 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; + } data_offset_in_page = 0; rest_blocks -= block_len_in_page; @@ -1303,7 +1370,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, /* Decrease buffer counter */ if (holecheck_path) ext4_ext_drop_refs(holecheck_path); - ret = get_ext_path(orig_inode, seq_start, &holecheck_path); + ret1 = get_ext_path(orig_inode, seq_start, &holecheck_path); if (holecheck_path == NULL) break; depth = holecheck_path->p_depth; @@ -1311,7 +1378,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, /* Decrease buffer counter */ if (orig_path) ext4_ext_drop_refs(orig_path); - ret = get_ext_path(orig_inode, seq_start, &orig_path); + ret1 = get_ext_path(orig_inode, seq_start, &orig_path); if (orig_path == NULL) break; @@ -1330,10 +1397,12 @@ out: kfree(holecheck_path); } out2: - mext_inode_double_unlock(orig_inode, donor_inode); + ret2 = mext_inode_double_unlock(orig_inode, donor_inode); - if (ret) - return ret; + if (ret1) + return ret1; + else if (ret2) + return ret2; return 0; } -- cgit v1.2.3 From 347fa6f1c7cb5df2b38d3c9167cfe242ce0cd1da Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Wed, 16 Sep 2009 14:25:07 -0400 Subject: ext4: Add null extent check to ext_get_path There is the possibility that path structure which is taken by ext4_ext_find_extent() indicates null extents. Because during data block exchanging in ext4_move_extents(), constitution of an extent tree may be changed. As a solution, the patch adds null extent check to ext_get_path(). Reported-by: Peng Tao Signed-off-by: Akira Fujita Signed-off-by: "Theodore Ts'o" --- fs/ext4/move_extent.c | 34 ++++++++++++++++------------------ 1 file changed, 16 insertions(+), 18 deletions(-) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 2258560e9722..1c509d549137 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -39,7 +39,9 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock, if (IS_ERR(*path)) { ret = PTR_ERR(*path); *path = NULL; - } + } else if ((*path)[ext_depth(inode)].p_ext == NULL) + ret = -ENODATA; + return ret; } @@ -316,7 +318,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode, if (new_flag) { err = get_ext_path(orig_inode, eblock, &orig_path); - if (orig_path == NULL) + if (err) goto out; if (ext4_ext_insert_extent(handle, orig_inode, @@ -327,7 +329,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode, if (end_flag) { err = get_ext_path(orig_inode, le32_to_cpu(end_ext->ee_block) - 1, &orig_path); - if (orig_path == NULL) + if (err) goto out; if (ext4_ext_insert_extent(handle, orig_inode, @@ -673,12 +675,12 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, /* Get the original extent for the block "orig_off" */ err = get_ext_path(orig_inode, orig_off, &orig_path); - if (orig_path == NULL) + if (err) goto out; /* Get the donor extent for the head */ err = get_ext_path(donor_inode, donor_off, &donor_path); - if (donor_path == NULL) + if (err) goto out; depth = ext_depth(orig_inode); oext = orig_path[depth].p_ext; @@ -733,7 +735,7 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, if (orig_path) ext4_ext_drop_refs(orig_path); err = get_ext_path(orig_inode, orig_off, &orig_path); - if (orig_path == NULL) + if (err) goto out; depth = ext_depth(orig_inode); oext = orig_path[depth].p_ext; @@ -747,7 +749,7 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, if (donor_path) ext4_ext_drop_refs(donor_path); err = get_ext_path(donor_inode, donor_off, &donor_path); - if (donor_path == NULL) + if (err) goto out; depth = ext_depth(donor_inode); dext = donor_path[depth].p_ext; @@ -1221,7 +1223,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, donor_start, &len, *moved_len); mext_double_up_read(orig_inode, donor_inode); if (ret1) - goto out2; + goto out; file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits; block_end = block_start + len - 1; @@ -1229,20 +1231,16 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, len -= block_end - file_end; ret1 = get_ext_path(orig_inode, block_start, &orig_path); - if (orig_path == NULL) - goto out2; + if (ret1) + goto out; /* Get path structure to check the hole */ ret1 = get_ext_path(orig_inode, block_start, &holecheck_path); - if (holecheck_path == NULL) + if (ret1) goto out; depth = ext_depth(orig_inode); ext_cur = holecheck_path[depth].p_ext; - if (ext_cur == NULL) { - ret1 = -EINVAL; - goto out; - } /* * Get proper extent whose ee_block is beyond block_start @@ -1371,7 +1369,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, if (holecheck_path) ext4_ext_drop_refs(holecheck_path); ret1 = get_ext_path(orig_inode, seq_start, &holecheck_path); - if (holecheck_path == NULL) + if (ret1) break; depth = holecheck_path->p_depth; @@ -1379,7 +1377,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, if (orig_path) ext4_ext_drop_refs(orig_path); ret1 = get_ext_path(orig_inode, seq_start, &orig_path); - if (orig_path == NULL) + if (ret1) break; ext_cur = holecheck_path[depth].p_ext; @@ -1396,7 +1394,7 @@ out: ext4_ext_drop_refs(holecheck_path); kfree(holecheck_path); } -out2: + ret2 = mext_inode_double_unlock(orig_inode, donor_inode); if (ret1) -- cgit v1.2.3 From c40ce3c9ea97425a12d7e44031a98fe50add6fc1 Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Wed, 16 Sep 2009 14:25:39 -0400 Subject: ext4: Fix different block exchange issue in EXT4_IOC_MOVE_EXT If logical block offset of original file which is passed to EXT4_IOC_MOVE_EXT is different from donor file's, a calculation error occurs in ext4_calc_swap_extents(), therefore wrong block is exchanged between original file and donor file. As a result, we hit ext4_error() in check_block_validity(). To detect the logical offset difference in EXT4_IOC_MOVE_EXT, add checks to mext_calc_swap_extents() and handle it as error, since data exchange must be done between the same blocks in EXT4_IOC_MOVE_EXT. Reported-by: Peng Tao Signed-off-by: Akira Fujita Signed-off-by: "Theodore Ts'o" --- fs/ext4/move_extent.c | 46 +++++++++++++++++++++++++++++++++++++--------- 1 file changed, 37 insertions(+), 9 deletions(-) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 1c509d549137..1f027b1ec430 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -597,8 +597,10 @@ out: * @orig_off: block offset of original inode * @donor_off: block offset of donor inode * @max_count: the maximun length of extents + * + * Return 0 on success, or a negative error value on failure. */ -static void +static int mext_calc_swap_extents(struct ext4_extent *tmp_dext, struct ext4_extent *tmp_oext, ext4_lblk_t orig_off, ext4_lblk_t donor_off, @@ -607,6 +609,19 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, ext4_lblk_t diff, orig_diff; struct ext4_extent dext_old, oext_old; + BUG_ON(orig_off != donor_off); + + /* original and donor extents have to cover the same block offset */ + if (orig_off < le32_to_cpu(tmp_oext->ee_block) || + le32_to_cpu(tmp_oext->ee_block) + + ext4_ext_get_actual_len(tmp_oext) - 1 < orig_off) + return -ENODATA; + + if (orig_off < le32_to_cpu(tmp_dext->ee_block) || + le32_to_cpu(tmp_dext->ee_block) + + ext4_ext_get_actual_len(tmp_dext) - 1 < orig_off) + return -ENODATA; + dext_old = *tmp_dext; oext_old = *tmp_oext; @@ -634,6 +649,8 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, copy_extent_status(&oext_old, tmp_dext); copy_extent_status(&dext_old, tmp_oext); + + return 0; } /** @@ -690,8 +707,10 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, dext = donor_path[depth].p_ext; tmp_dext = *dext; - 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) + goto out; /* Loop for the donor extents */ while (1) { @@ -760,9 +779,10 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, } tmp_dext = *dext; - mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, - donor_off, - count - replaced_count); + err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, + donor_off, count - replaced_count); + if (err) + goto out; } out: @@ -1243,11 +1263,15 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, ext_cur = holecheck_path[depth].p_ext; /* - * Get proper extent whose ee_block is beyond block_start - * if block_start was within the hole. + * Get proper starting location of block replacement if block_start was + * within the hole. */ if (le32_to_cpu(ext_cur->ee_block) + ext4_ext_get_actual_len(ext_cur) - 1 < block_start) { + /* + * The hole exists between extents or the tail of + * original file. + */ last_extent = mext_next_extent(orig_inode, holecheck_path, &ext_cur); if (last_extent < 0) { @@ -1260,8 +1284,12 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, ret1 = last_extent; goto out; } - } - seq_start = block_start; + seq_start = le32_to_cpu(ext_cur->ee_block); + } else if (le32_to_cpu(ext_cur->ee_block) > block_start) + /* The hole exists at the beginning of original file. */ + seq_start = le32_to_cpu(ext_cur->ee_block); + else + seq_start = block_start; /* No blocks within the specified range. */ if (le32_to_cpu(ext_cur->ee_block) > block_end) { -- cgit v1.2.3 From fb0a387dcdcd21aab1b09ee7fd80b7c979bdbbfd Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 16 Sep 2009 14:45:10 -0400 Subject: ext4: limit block allocations for indirect-block files to < 2^32 Today, the ext4 allocator will happily allocate blocks past 2^32 for indirect-block files, which results in the block numbers getting truncated, and corruption ensues. This patch limits such allocations to < 2^32, and adds BUG_ONs if we do get blocks larger than that. This should address RH Bug 519471, ext4 bitmap allocator must limit blocks to < 2^32 * ext4_find_goal() is modified to choose a goal < UINT_MAX, so that our starting point is in an acceptable range. * ext4_xattr_block_set() is modified such that the goal block is < UINT_MAX, as above. * ext4_mb_regular_allocator() is modified so that the group search does not continue into groups which are too high * ext4_mb_use_preallocated() has a check that we don't use preallocated space which is too far out * ext4_alloc_blocks() and ext4_xattr_block_set() add some BUG_ONs No attempt has been made to limit inode locations to < 2^32, so we may wind up with blocks far from their inodes. Doing this much already will lead to some odd ENOSPC issues when the "lower 32" gets full, and further restricting inodes could make that even weirder. For high inodes, choosing a goal of the original, % UINT_MAX, may be a bit odd, but then we're in an odd situation anyway, and I don't know of a better heuristic. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 4 ++++ fs/ext4/inode.c | 11 ++++++++++- fs/ext4/mballoc.c | 9 +++++++++ fs/ext4/super.c | 2 ++ fs/ext4/xattr.c | 15 +++++++++++++-- 5 files changed, 38 insertions(+), 3 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4dc64ed58d26..2a0f75d55fad 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -403,6 +403,9 @@ struct ext4_mount_options { #endif }; +/* Max physical block we can addres w/o extents */ +#define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF + /* * Structure of an inode on the disk */ @@ -857,6 +860,7 @@ struct ext4_sb_info { unsigned long s_gdb_count; /* Number of group descriptor blocks */ unsigned long s_desc_per_block; /* Number of group descriptors per block */ ext4_group_t s_groups_count; /* Number of groups in the fs */ + ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */ unsigned long s_overhead_last; /* Last calculated overhead */ unsigned long s_blocks_last; /* Last seen block count */ loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d04c8428bde2..5a8979259c9a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -562,15 +562,21 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) * * Normally this function find the preferred place for block allocation, * returns it. + * Because this is only used for non-extent files, we limit the block nr + * to 32 bits. */ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, Indirect *partial) { + ext4_fsblk_t goal; + /* * XXX need to get goal block from mballoc's data structures */ - return ext4_find_near(inode, partial); + goal = ext4_find_near(inode, partial); + goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; + return goal; } /** @@ -651,6 +657,8 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, if (*err) goto failed_out; + BUG_ON(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS); + target -= count; /* allocate blocks for indirect blocks */ while (index < indirect_blks && count) { @@ -685,6 +693,7 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, ar.flags = EXT4_MB_HINT_DATA; current_block = ext4_mb_new_blocks(handle, &ar, err); + BUG_ON(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS); if (*err && (target == blks)) { /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index d23056d375b3..e9c61896d605 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1965,6 +1965,10 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) sb = ac->ac_sb; sbi = EXT4_SB(sb); ngroups = ext4_get_groups_count(sb); + /* non-extent files are limited to low blocks/groups */ + if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL)) + ngroups = sbi->s_blockfile_groups; + BUG_ON(ac->ac_status == AC_STATUS_FOUND); /* first, try the goal */ @@ -3382,6 +3386,11 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) ac->ac_o_ex.fe_logical >= pa->pa_lstart + pa->pa_len) continue; + /* non-extent files can't have physical blocks past 2^32 */ + if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL) && + pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS) + continue; + /* found preallocated blocks, use them */ spin_lock(&pa->pa_lock); if (pa->pa_deleted == 0 && pa->pa_free) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index af95dd8ba54b..a6b1ab734728 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2616,6 +2616,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } sbi->s_groups_count = blocks_count; + sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, + (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *), diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 62b31c246994..fed5b01d7a8d 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -810,12 +810,23 @@ inserted: get_bh(new_bh); } else { /* We need to allocate a new block */ - ext4_fsblk_t goal = ext4_group_first_block_no(sb, + ext4_fsblk_t goal, block; + + goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); - ext4_fsblk_t block = ext4_new_meta_blocks(handle, inode, + + /* non-extent files can't have physical blocks past 2^32 */ + if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) + goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; + + block = ext4_new_meta_blocks(handle, inode, goal, NULL, &error); if (error) goto cleanup; + + if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) + BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS); + ea_idebug(inode, "creating block %d", block); new_bh = sb_getblk(sb, block); -- cgit v1.2.3 From 1b9c12f44c1eb614fd3b8822bfe8f1f5d8e53737 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 17 Sep 2009 08:32:22 -0400 Subject: ext4: store EXT4_EXT_MIGRATE in i_state instead of i_flags EXT4_EXT_MIGRATE is only intended to be used for an in-memory flag, and the hex value assigned to it collides with FS_DIRECTIO_FL (which is also stored in i_flags). There's no reason for the EXT4_EXT_MIGRATE bit to be stored in i_flags, so we switch it to use i_state instead. Cc: "Aneesh Kumar K.V" Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 +- fs/ext4/inode.c | 6 ++---- fs/ext4/migrate.c | 20 ++++++++++---------- 3 files changed, 13 insertions(+), 15 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 2a0f75d55fad..84e7f1d00a83 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -268,7 +268,6 @@ struct flex_groups { #define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ #define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */ #define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ -#define EXT4_EXT_MIGRATE 0x00100000 /* Inode is migrating */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ #define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */ @@ -306,6 +305,7 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) #define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */ #define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */ #define EXT4_STATE_DA_ALLOC_CLOSE 0x00000010 /* Alloc DA blks on close */ +#define EXT4_STATE_EXT_MIGRATE 0x00000020 /* Inode is migrating */ /* Used to pass group descriptor data when online resize is done */ struct ext4_new_group_input { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5a8979259c9a..a5b4ce40cc66 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1255,8 +1255,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, * i_data's format changing. Force the migrate * to fail by clearing migrate flags */ - EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags & - ~EXT4_EXT_MIGRATE; + EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE; } } @@ -4596,8 +4595,7 @@ static int ext4_do_update_inode(handle_t *handle, if (ext4_inode_blocks_set(handle, raw_inode, ei)) goto out_brelse; raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); - /* clear the migrate flag in the raw_inode */ - raw_inode->i_flags = cpu_to_le32(ei->i_flags & ~EXT4_EXT_MIGRATE); + raw_inode->i_flags = cpu_to_le32(ei->i_flags); if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_HURD)) raw_inode->i_file_acl_high = diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 05361ad5b80a..bf519f239ae6 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -353,17 +353,16 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode, down_write(&EXT4_I(inode)->i_data_sem); /* - * if EXT4_EXT_MIGRATE is cleared a block allocation + * if EXT4_STATE_EXT_MIGRATE is cleared a block allocation * happened after we started the migrate. We need to * fail the migrate */ - if (!(EXT4_I(inode)->i_flags & EXT4_EXT_MIGRATE)) { + if (!(EXT4_I(inode)->i_state & EXT4_STATE_EXT_MIGRATE)) { retval = -EAGAIN; up_write(&EXT4_I(inode)->i_data_sem); goto err_out; } else - EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags & - ~EXT4_EXT_MIGRATE; + EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE; /* * We have the extent map build with the tmp inode. * Now copy the i_data across @@ -517,14 +516,15 @@ int ext4_ext_migrate(struct inode *inode) * when we add extents we extent the journal */ /* - * Even though we take i_mutex we can still cause block allocation - * via mmap write to holes. If we have allocated new blocks we fail - * migrate. New block allocation will clear EXT4_EXT_MIGRATE flag. - * The flag is updated with i_data_sem held to prevent racing with - * block allocation. + * Even though we take i_mutex we can still cause block + * allocation via mmap write to holes. If we have allocated + * new blocks we fail migrate. New block allocation will + * clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated + * with i_data_sem held to prevent racing with block + * allocation. */ down_read((&EXT4_I(inode)->i_data_sem)); - EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags | EXT4_EXT_MIGRATE; + EXT4_I(inode)->i_state |= EXT4_STATE_EXT_MIGRATE; up_read((&EXT4_I(inode)->i_data_sem)); handle = ext4_journal_start(inode, 1); -- cgit v1.2.3 From fb40ba0d98968bc3454731360363d725b4f1064c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 16 Sep 2009 19:30:40 -0400 Subject: ext4: Add a tracepoint for ext4_alloc_da_blocks() Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 2 ++ include/trace/events/ext4.h | 27 +++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a5b4ce40cc66..9887a0c562d5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3128,6 +3128,8 @@ out: */ int ext4_alloc_da_blocks(struct inode *inode) { + trace_ext4_alloc_da_blocks(inode); + if (!EXT4_I(inode)->i_reserved_data_blocks && !EXT4_I(inode)->i_reserved_meta_blocks) return 0; diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 6fe6ce9ee071..c1bd8f1e8b94 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -10,6 +10,9 @@ struct ext4_allocation_context; struct ext4_allocation_request; struct ext4_prealloc_space; +struct ext4_inode_info; + +#define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) TRACE_EVENT(ext4_free_inode, TP_PROTO(struct inode *inode), @@ -710,6 +713,30 @@ TRACE_EVENT(ext4_sync_fs, __entry->wait) ); +TRACE_EVENT(ext4_alloc_da_blocks, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( unsigned int, data_blocks ) + __field( unsigned int, meta_blocks ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks; + __entry->meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks; + ), + + TP_printk("dev %s ino %lu data_blocks %u meta_blocks %u", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, + __entry->data_blocks, __entry->meta_blocks) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 5534fb5bb35a62a94e0bd1fa2421f7fb6e894f10 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 17 Sep 2009 09:34:16 -0400 Subject: ext4: Fix the alloc on close after a truncate hueristic In an attempt to avoid doing an unneeded flush after opening a (previously non-existent) file with O_CREAT|O_TRUNC, the code only triggered the hueristic if ei->disksize was non-zero. Turns out that the VFS doesn't call ->truncate() if the file doesn't exist, and ei->disksize is always zero even if the file previously existed. So remove the test, since it isn't necessary and in fact disabled the hueristic. Thanks to Clemens Eisserer that he was seeing problems with files written using kwrite and eclipse after sudden crashes caused by a buggy Intel video driver. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9887a0c562d5..4abd683b963d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3973,8 +3973,7 @@ void ext4_truncate(struct inode *inode) if (!ext4_can_truncate(inode)) return; - if (ei->i_disksize && inode->i_size == 0 && - !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) + if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE; if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { -- cgit v1.2.3 From 0a80e9867db154966b2a771042e10452ac110e1e Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Thu, 17 Sep 2009 11:55:58 -0400 Subject: ext4: replace MAX_DEFRAG_SIZE with EXT_MAX_BLOCK There's no reason to redefine the maximum allowable offset in an extent-based file just for defrag; EXT_MAX_BLOCK already does this. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 - fs/ext4/ext4_extents.h | 1 + fs/ext4/move_extent.c | 12 ++++++------ 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 84e7f1d00a83..e227eea23f05 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -476,7 +476,6 @@ struct move_extent { __u64 len; /* block length to be moved */ __u64 moved_len; /* moved block length */ }; -#define MAX_DEFRAG_SIZE ((1UL<<31) - 1) #define EXT4_EPOCH_BITS 2 #define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1) diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 9538633879d7..61652f1d15e6 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -137,6 +137,7 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, #define EXT_BREAK 1 #define EXT_REPEAT 2 +/* Maximum logical block in a file; ext4_extent's ee_block is __le32 */ #define EXT_MAX_BLOCK 0xffffffff /* diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 1f027b1ec430..c07a2915e40b 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -1040,12 +1040,12 @@ mext_check_arguments(struct inode *orig_inode, return -EINVAL; } - if ((orig_start > MAX_DEFRAG_SIZE) || - (donor_start > MAX_DEFRAG_SIZE) || - (*len > MAX_DEFRAG_SIZE) || - (orig_start + *len > MAX_DEFRAG_SIZE)) { - ext4_debug("ext4 move extent: Can't handle over [%lu] blocks " - "[ino:orig %lu, donor %lu]\n", MAX_DEFRAG_SIZE, + if ((orig_start > EXT_MAX_BLOCK) || + (donor_start > EXT_MAX_BLOCK) || + (*len > EXT_MAX_BLOCK) || + (orig_start + *len > EXT_MAX_BLOCK)) { + ext4_debug("ext4 move extent: Can't handle over [%u] blocks " + "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCK, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } -- cgit v1.2.3 From 1358870deaf11a752a84fbd89201749aa62498e8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 18 Sep 2009 12:22:29 -0400 Subject: ext4: Update documentation about quota mount options Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/ext4.txt | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 3e329dbac785..18b5ec8cea45 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -257,10 +257,18 @@ resuid=n The user ID which may use the reserved blocks. sb=n Use alternate superblock at this location. -quota -noquota -grpquota -usrquota +quota These options are ignored by the filesystem. They +noquota are used only by quota tools to recognize volumes +grpquota where quota should be turned on. See documentation +usrquota in the quota-tools package for more details + (http://sourceforge.net/projects/linuxquota). + +jqfmt= These options tell filesystem details about quota +usrjquota= so that quota information can be properly updated +grpjquota= during journal replay. They replace the above + quota options. See documentation in the quota-tools + package for more details + (http://sourceforge.net/projects/linuxquota). bh (*) ext4 associates buffer heads to data pages to nobh (a) cache disk block mapping information -- cgit v1.2.3