From 5e1f8c9e20a92743eefc9a82c2db835213905e26 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 28 Oct 2008 13:21:55 -0400 Subject: ext3: Add support for non-native signed/unsigned htree hash algorithms The original ext3 hash algorithms assumed that variables of type char were signed, as God and K&R intended. Unfortunately, this assumption is not true on some architectures. Userspace support for marking filesystems with non-native signed/unsigned chars was added two years ago, but the kernel-side support was never added (until now). Signed-off-by: "Theodore Ts'o" Cc: akpm@linux-foundation.org Cc: linux-kernel@vger.kernel.org --- fs/ext3/super.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'fs/ext3/super.c') diff --git a/fs/ext3/super.c b/fs/ext3/super.c index f6c94f232ec..541d5e4f7f6 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1744,6 +1744,18 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) for (i=0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; + i = le32_to_cpu(es->s_flags); + if (i & EXT2_FLAGS_UNSIGNED_HASH) + sbi->s_hash_unsigned = 3; + else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { +#ifdef __CHAR_UNSIGNED__ + es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); + sbi->s_hash_unsigned = 3; +#else + es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); +#endif + sb->s_dirt = 1; + } if (sbi->s_blocks_per_group > blocksize * 8) { printk (KERN_ERR -- cgit v1.2.3 From 6b082b531228c43d454c082fc0f969da1695b060 Mon Sep 17 00:00:00 2001 From: Toshiyuki Okajima Date: Mon, 5 Jan 2009 22:38:14 -0500 Subject: ext3: provide function to release metadata pages under memory pressure Pages in the page cache belonging to ext3 data files are released via the ext3_releasepage() function specified in the ext3 inode's address_space_ops. However, metadata blocks (such as indirect blocks, directory blocks, etc) are managed via the block device address_space_ops, and they can not be released by try_to_free_buffers() if they have a journal head attached to them. To address this, we supply a try_to_free_pages() function which calls journal_try_to_free_buffers() function to free the metadata, and which is called by the block device's blkdev_releasepage() function. Signed-off-by: Toshiyuki Okajima Signed-off-by: "Theodore Ts'o" Cc: linux-fsdevel@vger.kernel.org --- fs/ext3/super.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'fs/ext3/super.c') diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 541d5e4f7f6..6900ff05e3a 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -682,6 +682,26 @@ static struct dentry *ext3_fh_to_parent(struct super_block *sb, struct fid *fid, ext3_nfs_get_inode); } +/* + * Try to release metadata pages (indirect blocks, directories) which are + * mapped via the block device. Since these pages could have journal heads + * which would prevent try_to_free_buffers() from freeing them, we must use + * jbd layer's try_to_free_buffers() function to release them. + */ +static int bdev_try_to_free_page(struct super_block *sb, struct page *page, + gfp_t wait) +{ + journal_t *journal = EXT3_SB(sb)->s_journal; + + WARN_ON(PageChecked(page)); + if (!page_has_buffers(page)) + return 0; + if (journal) + return journal_try_to_free_buffers(journal, page, + wait & ~__GFP_WAIT); + return try_to_free_buffers(page); +} + #ifdef CONFIG_QUOTA #define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group") #define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA)) @@ -746,6 +766,7 @@ static const struct super_operations ext3_sops = { .quota_read = ext3_quota_read, .quota_write = ext3_quota_write, #endif + .bdev_try_to_free_page = bdev_try_to_free_page, }; static const struct export_operations ext3_export_ops = { -- cgit v1.2.3 From 5df096d67ec2b6578518caed7d57317a4b807aa1 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Wed, 7 Jan 2009 18:07:25 -0800 Subject: ext3: allocate ->s_blockgroup_lock separately As spotted by kmemtrace, struct ext3_sb_info is 17152 bytes on 64-bit which makes it a very bad fit for SLAB allocators. The culprit of the wasted memory is ->s_blockgroup_lock which can be as big as 16 KB when NR_CPUS >= 32. To fix that, allocate ->s_blockgroup_lock, which fits nicely in a order 2 page in the worst case, separately. This shinks down struct ext3_sb_info enough to fit a 1 KB slab cache so now we allocate 16 KB + 1 KB instead of 32 KB saving 15 KB of memory. Acked-by: Andreas Dilger Signed-off-by: Pekka Enberg Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/super.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'fs/ext3/super.c') diff --git a/fs/ext3/super.c b/fs/ext3/super.c index c22d01467bd..01c235bc205 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -439,6 +439,7 @@ static void ext3_put_super (struct super_block * sb) ext3_blkdev_remove(sbi); } sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); kfree(sbi); return; } @@ -1546,6 +1547,13 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; + + sbi->s_blockgroup_lock = + kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); + if (!sbi->s_blockgroup_lock) { + kfree(sbi); + return -ENOMEM; + } sb->s_fs_info = sbi; sbi->s_mount_opt = 0; sbi->s_resuid = EXT3_DEF_RESUID; @@ -1786,7 +1794,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) goto failed_mount; } - bgl_lock_init(&sbi->s_blockgroup_lock); + bgl_lock_init(sbi->s_blockgroup_lock); for (i = 0; i < db_count; i++) { block = descriptor_loc(sb, logic_sb_block, i); -- cgit v1.2.3 From c4be0c1dc4cdc37b175579be1460f15ac6495e9a Mon Sep 17 00:00:00 2001 From: Takashi Sato Date: Fri, 9 Jan 2009 16:40:58 -0800 Subject: filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato Signed-off-by: Masayuki Hamaguchi Cc: Cc: Cc: Christoph Hellwig Cc: Dave Kleikamp Cc: Dave Chinner Cc: Alasdair G Kergon Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/super.c | 45 +++++++++++++++++++++++++++++---------------- 1 file changed, 29 insertions(+), 16 deletions(-) (limited to 'fs/ext3/super.c') diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 5d047a030a7..b70d90e08a3 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -48,8 +48,8 @@ static int ext3_load_journal(struct super_block *, struct ext3_super_block *, unsigned long journal_devnum); static int ext3_create_journal(struct super_block *, struct ext3_super_block *, unsigned int); -static void ext3_commit_super (struct super_block * sb, - struct ext3_super_block * es, +static int ext3_commit_super(struct super_block *sb, + struct ext3_super_block *es, int sync); static void ext3_mark_recovery_complete(struct super_block * sb, struct ext3_super_block * es); @@ -60,9 +60,9 @@ static const char *ext3_decode_error(struct super_block * sb, int errno, char nbuf[16]); static int ext3_remount (struct super_block * sb, int * flags, char * data); static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf); -static void ext3_unlockfs(struct super_block *sb); +static int ext3_unfreeze(struct super_block *sb); static void ext3_write_super (struct super_block * sb); -static void ext3_write_super_lockfs(struct super_block *sb); +static int ext3_freeze(struct super_block *sb); /* * Wrappers for journal_start/end. @@ -759,8 +759,8 @@ static const struct super_operations ext3_sops = { .put_super = ext3_put_super, .write_super = ext3_write_super, .sync_fs = ext3_sync_fs, - .write_super_lockfs = ext3_write_super_lockfs, - .unlockfs = ext3_unlockfs, + .freeze_fs = ext3_freeze, + .unfreeze_fs = ext3_unfreeze, .statfs = ext3_statfs, .remount_fs = ext3_remount, .clear_inode = ext3_clear_inode, @@ -2311,21 +2311,23 @@ static int ext3_create_journal(struct super_block * sb, return 0; } -static void ext3_commit_super (struct super_block * sb, - struct ext3_super_block * es, +static int ext3_commit_super(struct super_block *sb, + struct ext3_super_block *es, int sync) { struct buffer_head *sbh = EXT3_SB(sb)->s_sbh; + int error = 0; if (!sbh) - return; + return error; es->s_wtime = cpu_to_le32(get_seconds()); es->s_free_blocks_count = cpu_to_le32(ext3_count_free_blocks(sb)); es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb)); BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); if (sync) - sync_dirty_buffer(sbh); + error = sync_dirty_buffer(sbh); + return error; } @@ -2439,12 +2441,14 @@ static int ext3_sync_fs(struct super_block *sb, int wait) * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. */ -static void ext3_write_super_lockfs(struct super_block *sb) +static int ext3_freeze(struct super_block *sb) { + int error = 0; + journal_t *journal; sb->s_dirt = 0; if (!(sb->s_flags & MS_RDONLY)) { - journal_t *journal = EXT3_SB(sb)->s_journal; + journal = EXT3_SB(sb)->s_journal; /* Now we set up the journal barrier. */ journal_lock_updates(journal); @@ -2453,20 +2457,28 @@ static void ext3_write_super_lockfs(struct super_block *sb) * We don't want to clear needs_recovery flag when we failed * to flush the journal. */ - if (journal_flush(journal) < 0) - return; + error = journal_flush(journal); + if (error < 0) + goto out; /* Journal blocked and flushed, clear needs_recovery flag. */ EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER); - ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1); + error = ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1); + if (error) + goto out; } + return 0; + +out: + journal_unlock_updates(journal); + return error; } /* * Called by LVM after the snapshot is done. We need to reset the RECOVER * flag here, even though the filesystem is not technically dirty yet. */ -static void ext3_unlockfs(struct super_block *sb) +static int ext3_unfreeze(struct super_block *sb) { if (!(sb->s_flags & MS_RDONLY)) { lock_super(sb); @@ -2476,6 +2488,7 @@ static void ext3_unlockfs(struct super_block *sb) unlock_super(sb); journal_unlock_updates(EXT3_SB(sb)->s_journal); } + return 0; } static int ext3_remount (struct super_block * sb, int * flags, char * data) -- cgit v1.2.3