From 79ffab34391933ee3b95dac7f25c0478fa2f8f1e Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 13 May 2009 15:13:42 -0400 Subject: [PATCH 01/49] ext4: Properly initialize the buffer_head state These struct buffer_heads are allocated on the stack (and hence are initialized with stack garbage). They are only used to call a get_blocks() function, so that's mostly OK, but b_state must be initialized to be 0 so we don't have any unexpected BH_* flags set by accident, such as BH_Unwritten or BH_Delay. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 1 + fs/ext4/inode.c | 15 ++++++++++++++- fs/mpage.c | 6 ++++-- 3 files changed, 19 insertions(+), 3 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index e3a55eb8b26a..a953214f2829 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3150,6 +3150,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len) ret = PTR_ERR(handle); break; } + map_bh.b_state = 0; ret = ext4_get_blocks_wrap(handle, inode, block, max_blocks, &map_bh, EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2a9ffd528dd1..d7ad0bb73cd5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2055,7 +2055,20 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) if ((mpd->b_state & (1 << BH_Mapped)) && !(mpd->b_state & (1 << BH_Delay))) return 0; - new.b_state = mpd->b_state; + /* + * We need to make sure the BH_Delay flag is passed down to + * ext4_da_get_block_write(), since it calls + * ext4_get_blocks_wrap() with the EXT4_DELALLOC_RSVED flag. + * This flag causes ext4_get_blocks_wrap() to call + * ext4_da_update_reserve_space() if the passed buffer head + * has the BH_Delay flag set. In the future, once we clean up + * the interfaces to ext4_get_blocks_wrap(), we should pass in + * a separate flag which requests that the delayed allocation + * statistics should be updated, instead of depending on the + * state information getting passed down via the map_bh's + * state bitmasks plus the magic EXT4_DELALLOC_RSVED flag. + */ + new.b_state = mpd->b_state & (1 << BH_Delay); new.b_blocknr = 0; new.b_size = mpd->b_size; next = mpd->b_blocknr; diff --git a/fs/mpage.c b/fs/mpage.c index 680ba60863ff..42381bd6543b 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -379,7 +379,8 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, struct buffer_head map_bh; unsigned long first_logical_block = 0; - clear_buffer_mapped(&map_bh); + map_bh.b_state = 0; + map_bh.b_size = 0; for (page_idx = 0; page_idx < nr_pages; page_idx++) { struct page *page = list_entry(pages->prev, struct page, lru); @@ -412,7 +413,8 @@ int mpage_readpage(struct page *page, get_block_t get_block) struct buffer_head map_bh; unsigned long first_logical_block = 0; - clear_buffer_mapped(&map_bh); + map_bh.b_state = 0; + map_bh.b_size = 0; bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio, &map_bh, &first_logical_block, get_block); if (bio) From 8fb0e342481c4d80040670fec915f0b9c7c6499a Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 12 May 2009 16:22:37 -0400 Subject: [PATCH 02/49] vfs: Add BUG_ON for delayed and unwritten flags in submit_bh() The BH_Delay and BH_Unwritten flags should never leak out to submit_bh(). So add some BUG_ON() checks to submit_bh so we can get a stack trace and determine how and why this might have happened. (Note that only XFS and ext4 use these buffer head flags, and XFS does not use submit_bh(). So this patch should only modify behavior for ext4.) Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" Cc: linux-fsdevel@vger.kernel.org --- fs/buffer.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/buffer.c b/fs/buffer.c index aed297739eb0..ad0112900222 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2933,6 +2933,8 @@ int submit_bh(int rw, struct buffer_head * bh) BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); + BUG_ON(buffer_delay(bh)); + BUG_ON(buffer_unwritten(bh)); /* * Mask in barrier bit for a write (could be either a WRITE or a From 29fa89d088941d79765d60f22d5ccdd6b8696e11 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 12 May 2009 16:30:27 -0400 Subject: [PATCH 03/49] ext4: Mark the unwritten buffer_head as mapped during write_begin Setting BH_Unwritten buffer_heads as BH_Mapped avoids multiple (unnecessary) calls to get_block() during the call to the write(2) system call. Setting BH_Unwritten buffer heads as BH_Mapped requires that the writepages() functions can handle BH_Unwritten buffer_heads. After this commit, things work as follows: ext4_ext_get_block() returns unmapped, unwritten, buffer head when called with create = 0 for prealloc space. This makes sure we handle the read path and non-delayed allocation case correctly. Even though the buffer head is marked unmapped we have valid b_blocknr and b_bdev values in the buffer_head. ext4_da_get_block_prep() called for block resrevation will now return mapped, unwritten, new buffer_head for prealloc space. This avoids multiple calls to get_block() for write to same offset. By making such buffers as BH_New, we also assure that sub-block zeroing of buffered writes happens correctly. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 4 +-- fs/ext4/inode.c | 82 ++++++++++++++++++++++++++++++----------------- 2 files changed, 54 insertions(+), 32 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index a953214f2829..ea5c47608cea 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2872,6 +2872,8 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, if (create == EXT4_CREATE_UNINITIALIZED_EXT) goto out; if (!create) { + if (allocated > max_blocks) + allocated = max_blocks; /* * We have blocks reserved already. We * return allocated blocks so that delalloc @@ -2879,8 +2881,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * the buffer head will be unmapped so that * a read from the block returns 0s. */ - if (allocated > max_blocks) - allocated = max_blocks; set_buffer_unwritten(bh_result); bh_result->b_bdev = inode->i_sb->s_bdev; bh_result->b_blocknr = newblock; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d7ad0bb73cd5..96f3366f59f6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1852,7 +1852,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd) * @logical - first logical block to start assignment with * * the function goes through all passed space and put actual disk - * block numbers into buffer heads, dropping BH_Delay + * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten */ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical, struct buffer_head *exbh) @@ -1902,16 +1902,24 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical, do { if (cur_logical >= logical + blocks) break; - if (buffer_delay(bh)) { - bh->b_blocknr = pblock; - clear_buffer_delay(bh); - bh->b_bdev = inode->i_sb->s_bdev; - } else if (buffer_unwritten(bh)) { - bh->b_blocknr = pblock; - clear_buffer_unwritten(bh); - set_buffer_mapped(bh); - set_buffer_new(bh); - bh->b_bdev = inode->i_sb->s_bdev; + + if (buffer_delay(bh) || + buffer_unwritten(bh)) { + + BUG_ON(bh->b_bdev != inode->i_sb->s_bdev); + + if (buffer_delay(bh)) { + clear_buffer_delay(bh); + bh->b_blocknr = pblock; + } else { + /* + * unwritten already should have + * blocknr assigned. Verify that + */ + clear_buffer_unwritten(bh); + BUG_ON(bh->b_blocknr != pblock); + } + } else if (buffer_mapped(bh)) BUG_ON(bh->b_blocknr != pblock); @@ -2053,7 +2061,8 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) * We consider only non-mapped and non-allocated blocks */ if ((mpd->b_state & (1 << BH_Mapped)) && - !(mpd->b_state & (1 << BH_Delay))) + !(mpd->b_state & (1 << BH_Delay)) && + !(mpd->b_state & (1 << BH_Unwritten))) return 0; /* * We need to make sure the BH_Delay flag is passed down to @@ -2205,6 +2214,17 @@ static void mpage_add_bh_to_extent(struct mpage_da_data *mpd, return; } +static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) +{ + /* + * unmapped buffer is possible for holes. + * delay buffer is possible with delayed allocation. + * We also need to consider unwritten buffer as unmapped. + */ + return (!buffer_mapped(bh) || buffer_delay(bh) || + buffer_unwritten(bh)) && buffer_dirty(bh); +} + /* * __mpage_da_writepage - finds extent of pages and blocks * @@ -2289,8 +2309,7 @@ static int __mpage_da_writepage(struct page *page, * Otherwise we won't make progress * with the page in ext4_da_writepage */ - if (buffer_dirty(bh) && - (!buffer_mapped(bh) || buffer_delay(bh))) { + if (ext4_bh_unmapped_or_delay(NULL, bh)) { mpage_add_bh_to_extent(mpd, logical, bh->b_size, bh->b_state); @@ -2318,6 +2337,14 @@ static int __mpage_da_writepage(struct page *page, /* * this is a special callback for ->write_begin() only * it's intention is to return mapped block or reserve space + * + * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set. + * We also have b_blocknr = -1 and b_bdev initialized properly + * + * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set. + * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev + * initialized properly. + * */ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) @@ -2353,28 +2380,23 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, set_buffer_delay(bh_result); } else if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); - /* - * With sub-block writes into unwritten extents - * we also need to mark the buffer as new so that - * the unwritten parts of the buffer gets correctly zeroed. - */ - if (buffer_unwritten(bh_result)) + if (buffer_unwritten(bh_result)) { + /* A delayed write to unwritten bh should + * be marked new and mapped. Mapped ensures + * that we don't do get_block multiple times + * when we write to the same offset and new + * ensures that we do proper zero out for + * partial write. + */ set_buffer_new(bh_result); + set_buffer_mapped(bh_result); + } ret = 0; } return ret; } -static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) -{ - /* - * unmapped buffer is possible for holes. - * delay buffer is possible with delayed allocation - */ - return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)); -} - static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -2828,7 +2850,7 @@ static int ext4_da_should_update_i_disksize(struct page *page, for (i = 0; i < idx; i++) bh = bh->b_this_page; - if (!buffer_mapped(bh) || (buffer_delay(bh))) + if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh)) return 0; return 1; } From c5ca7c7636fa689a9746b6032f83aa7fffec31c6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 27 Apr 2009 22:48:48 -0400 Subject: [PATCH 04/49] ext4: Fallback to vmalloc if kmalloc can't allocate s_flex_groups array For very large filesystems, the s_flex_groups array can get quite big. For example, a filesystem that can be resized up to 16TB will have 8192 flex groups (assuming the default flex_bg size of 16), so the array is 96k, which is *very* marginal for kmalloc(). On the other hand, a 160GB filesystem without the resize_inode feature will only require 960 bytes. So we try to allocate the array first using kmalloc(), and if that fails, we'll try to use vmalloc() instead. Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2958f4e6f222..3f4475daa66d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -586,7 +587,10 @@ static void ext4_put_super(struct super_block *sb) for (i = 0; i < sbi->s_gdb_count; i++) brelse(sbi->s_group_desc[i]); kfree(sbi->s_group_desc); - kfree(sbi->s_flex_groups); + if (is_vmalloc_addr(sbi->s_flex_groups)) + vfree(sbi->s_flex_groups); + else + kfree(sbi->s_flex_groups); percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -1620,6 +1624,7 @@ static int ext4_fill_flex_info(struct super_block *sb) ext4_group_t flex_group_count; ext4_group_t flex_group; int groups_per_flex = 0; + size_t size; int i; if (!sbi->s_es->s_log_groups_per_flex) { @@ -1634,8 +1639,13 @@ static int ext4_fill_flex_info(struct super_block *sb) flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) + ((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) << EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex; - sbi->s_flex_groups = kzalloc(flex_group_count * - sizeof(struct flex_groups), GFP_KERNEL); + size = flex_group_count * sizeof(struct flex_groups); + sbi->s_flex_groups = kzalloc(size, GFP_KERNEL); + if (sbi->s_flex_groups == NULL) { + sbi->s_flex_groups = vmalloc(size); + if (sbi->s_flex_groups) + memset(sbi->s_flex_groups, 0, size); + } if (sbi->s_flex_groups == NULL) { printk(KERN_ERR "EXT4-fs: not enough memory for " "%u flex groups\n", flex_group_count); @@ -2842,6 +2852,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_journal = NULL; } failed_mount3: + if (sbi->s_flex_groups) { + if (is_vmalloc_addr(sbi->s_flex_groups)) + vfree(sbi->s_flex_groups); + else + kfree(sbi->s_flex_groups); + } percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); From f7c439504ccba0cca43271e651013ab97a221c62 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 24 Apr 2009 23:31:59 -0400 Subject: [PATCH 05/49] ext4: Use is_power_of_2() for clarity Signed-off-by: Robert P. J. Day Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 3f4475daa66d..3e509bc647e3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1483,7 +1483,7 @@ static int parse_options(char *options, struct super_block *sb, return 0; if (option < 0 || option > (1 << 30)) return 0; - if (option & (option - 1)) { + if (!is_power_of_2(option)) { printk(KERN_ERR "EXT4-fs: inode_readahead_blks" " must be a power of 2\n"); return 0; @@ -2101,8 +2101,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a, if (parse_strtoul(buf, 0x40000000, &t)) return -EINVAL; - /* inode_readahead_blks must be a power of 2 */ - if (t & (t-1)) + if (!is_power_of_2(t)) return -EINVAL; sbi->s_inode_readahead_blks = t; From e2d670523c6c4ccb0fca9f3ab1b8f066d9aa57d6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 1 May 2009 00:33:44 -0400 Subject: [PATCH 06/49] ext4: Simplify ext4_commit_super()'s function signature The ext4_commit_super() function took both a struct super_block * and a struct ext4_super_block *, but the struct ext4_super_block can be derived from the struct super_block. Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 3e509bc647e3..ad4c9be4abdc 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -54,8 +54,7 @@ static struct kset *ext4_kset; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); -static int ext4_commit_super(struct super_block *sb, - struct ext4_super_block *es, int sync); +static int ext4_commit_super(struct super_block *sb, int sync); static void ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static void ext4_clear_journal_err(struct super_block *sb, @@ -306,7 +305,7 @@ static void ext4_handle_error(struct super_block *sb) printk(KERN_CRIT "Remounting filesystem read-only\n"); sb->s_flags |= MS_RDONLY; } - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); if (test_opt(sb, ERRORS_PANIC)) panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); @@ -448,7 +447,7 @@ __acquires(bitlock) if (test_opt(sb, ERRORS_CONT)) { EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb, es, 0); + ext4_commit_super(sb, 0); return; } ext4_unlock_group(sb, grp); @@ -577,7 +576,7 @@ static void ext4_put_super(struct super_block *sb) if (!(sb->s_flags & MS_RDONLY)) { EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); } if (sbi->s_proc) { remove_proc_entry(sb->s_id, ext4_proc_root); @@ -1596,7 +1595,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, if (sbi->s_journal) EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " "bpg=%lu, ipg=%lu, mo=%04lx]\n", @@ -2655,7 +2654,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (test_opt(sb, ERRORS_PANIC)) { EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); goto failed_mount4; } } @@ -3132,15 +3131,15 @@ static int ext4_load_journal(struct super_block *sb, sb->s_dirt = 1; /* Make sure we flush the recovery flag to disk. */ - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); } return 0; } -static int ext4_commit_super(struct super_block *sb, - struct ext4_super_block *es, int sync) +static int ext4_commit_super(struct super_block *sb, int sync) { + struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; int error = 0; @@ -3212,7 +3211,7 @@ static void ext4_mark_recovery_complete(struct super_block *sb, sb->s_flags & MS_RDONLY) { EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); sb->s_dirt = 0; - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); } unlock_super(sb); @@ -3253,7 +3252,7 @@ static void ext4_clear_journal_err(struct super_block *sb, EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); jbd2_journal_clear_err(journal); } @@ -3293,7 +3292,7 @@ static void ext4_write_super(struct super_block *sb) BUG(); sb->s_dirt = 0; } else { - ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); + ext4_commit_super(sb, 1); } } @@ -3312,7 +3311,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait) target); } } else { - ext4_commit_super(sb, EXT4_SB(sb)->s_es, wait); + ext4_commit_super(sb, wait); } return ret; } @@ -3345,7 +3344,7 @@ static int ext4_freeze(struct super_block *sb) /* Journal blocked and flushed, clear needs_recovery flag. */ EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - error = ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); + error = ext4_commit_super(sb, 1); if (error) goto out; } @@ -3365,7 +3364,7 @@ static int ext4_unfreeze(struct super_block *sb) lock_super(sb); /* Reser the needs_recovery flag before the fs is unlocked. */ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); + ext4_commit_super(sb, 1); unlock_super(sb); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } @@ -3520,7 +3519,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } } if (sbi->s_journal == NULL) - ext4_commit_super(sb, es, 1); + ext4_commit_super(sb, 1); #ifdef CONFIG_QUOTA /* Release old quota file names */ From 7234ab2a55e77784b44cf2d862136d9e41b8d98a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 30 Apr 2009 21:24:04 -0400 Subject: [PATCH 07/49] ext4: Fix and simplify s_dirt handling The s_dirt flag wasn't completely handled correctly, but it didn't really matter when journalling was enabled. It turns out that when ext4 runs without a journal, we don't clear s_dirt in places where we should have, with the result that the high-level write_super() function was writing the superblock when it wasn't necessary. So we fix this by making ext4_commit_super() clear the s_dirt flag, and removing many of the other places where s_dirt is manipulated. When journalling is enabled, the s_dirt flag might be left set more often, but s_dirt really doesn't matter when journalling is enabled. Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ad4c9be4abdc..7c7a08af1200 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3128,7 +3128,6 @@ static int ext4_load_journal(struct super_block *sb, if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); - sb->s_dirt = 1; /* Make sure we flush the recovery flag to disk. */ ext4_commit_super(sb, 1); @@ -3168,7 +3167,7 @@ static int ext4_commit_super(struct super_block *sb, int sync) &EXT4_SB(sb)->s_freeblocks_counter)); es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &EXT4_SB(sb)->s_freeinodes_counter)); - + sb->s_dirt = 0; BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); if (sync) { @@ -3210,7 +3209,6 @@ static void ext4_mark_recovery_complete(struct super_block *sb, if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) && sb->s_flags & MS_RDONLY) { EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - sb->s_dirt = 0; ext4_commit_super(sb, 1); } unlock_super(sb); @@ -3271,10 +3269,8 @@ int ext4_force_commit(struct super_block *sb) return 0; journal = EXT4_SB(sb)->s_journal; - if (journal) { - sb->s_dirt = 0; + if (journal) ret = ext4_journal_force_commit(journal); - } return ret; } @@ -3282,15 +3278,13 @@ int ext4_force_commit(struct super_block *sb) /* * Ext4 always journals updates to the superblock itself, so we don't * have to propagate any other updates to the superblock on disk at this - * point. (We can probably nuke this function altogether, and remove - * any mention to sb->s_dirt in all of fs/ext4; eventual cleanup...) + * point if the journalling is enabled. */ static void ext4_write_super(struct super_block *sb) { if (EXT4_SB(sb)->s_journal) { if (mutex_trylock(&sb->s_lock) != 0) BUG(); - sb->s_dirt = 0; } else { ext4_commit_super(sb, 1); } @@ -3302,7 +3296,6 @@ static int ext4_sync_fs(struct super_block *sb, int wait) tid_t target; trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait); - sb->s_dirt = 0; if (EXT4_SB(sb)->s_journal) { if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) { @@ -3324,7 +3317,6 @@ static int ext4_freeze(struct super_block *sb) { int error = 0; journal_t *journal; - sb->s_dirt = 0; if (!(sb->s_flags & MS_RDONLY)) { journal = EXT4_SB(sb)->s_journal; From 9ca92389c5312a51e819c15c762f0abdc7f3129b Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 1 May 2009 12:52:25 -0400 Subject: [PATCH 08/49] ext4: Use separate super_operations structure for no_journal filesystems By using a separate super_operations structure for filesystems that have and don't have journals, we can simply ext4_write_super() --- which is only needed when no journal is present --- and ext4_freeze(), ext4_unfreeze(), and ext4_sync_fs(), which are only needed when the journal is present. Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 108 +++++++++++++++++++++++++----------------------- 1 file changed, 57 insertions(+), 51 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 7c7a08af1200..68c3a44c4a97 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -995,7 +995,6 @@ static const struct super_operations ext4_sops = { .dirty_inode = ext4_dirty_inode, .delete_inode = ext4_delete_inode, .put_super = ext4_put_super, - .write_super = ext4_write_super, .sync_fs = ext4_sync_fs, .freeze_fs = ext4_freeze, .unfreeze_fs = ext4_unfreeze, @@ -1010,6 +1009,25 @@ static const struct super_operations ext4_sops = { .bdev_try_to_free_page = bdev_try_to_free_page, }; +static const struct super_operations ext4_nojournal_sops = { + .alloc_inode = ext4_alloc_inode, + .destroy_inode = ext4_destroy_inode, + .write_inode = ext4_write_inode, + .dirty_inode = ext4_dirty_inode, + .delete_inode = ext4_delete_inode, + .write_super = ext4_write_super, + .put_super = ext4_put_super, + .statfs = ext4_statfs, + .remount_fs = ext4_remount, + .clear_inode = ext4_clear_inode, + .show_options = ext4_show_options, +#ifdef CONFIG_QUOTA + .quota_read = ext4_quota_read, + .quota_write = ext4_quota_write, +#endif + .bdev_try_to_free_page = bdev_try_to_free_page, +}; + static const struct export_operations ext4_export_ops = { .fh_to_dentry = ext4_fh_to_dentry, .fh_to_parent = ext4_fh_to_parent, @@ -2615,7 +2633,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* * set up enough so that it can read an inode */ - sb->s_op = &ext4_sops; + if (!test_opt(sb, NOLOAD) && + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) + sb->s_op = &ext4_sops; + else + sb->s_op = &ext4_nojournal_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; #ifdef CONFIG_QUOTA @@ -3275,19 +3297,9 @@ int ext4_force_commit(struct super_block *sb) return ret; } -/* - * Ext4 always journals updates to the superblock itself, so we don't - * have to propagate any other updates to the superblock on disk at this - * point if the journalling is enabled. - */ static void ext4_write_super(struct super_block *sb) { - if (EXT4_SB(sb)->s_journal) { - if (mutex_trylock(&sb->s_lock) != 0) - BUG(); - } else { - ext4_commit_super(sb, 1); - } + ext4_commit_super(sb, 1); } static int ext4_sync_fs(struct super_block *sb, int wait) @@ -3296,15 +3308,9 @@ static int ext4_sync_fs(struct super_block *sb, int wait) tid_t target; trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait); - if (EXT4_SB(sb)->s_journal) { - if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, - &target)) { - if (wait) - jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, - target); - } - } else { - ext4_commit_super(sb, wait); + if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) { + if (wait) + jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target); } return ret; } @@ -3318,32 +3324,31 @@ static int ext4_freeze(struct super_block *sb) int error = 0; journal_t *journal; - if (!(sb->s_flags & MS_RDONLY)) { - journal = EXT4_SB(sb)->s_journal; + if (sb->s_flags & MS_RDONLY) + return 0; - if (journal) { - /* Now we set up the journal barrier. */ - jbd2_journal_lock_updates(journal); + journal = EXT4_SB(sb)->s_journal; - /* - * We don't want to clear needs_recovery flag when we - * failed to flush the journal. - */ - error = jbd2_journal_flush(journal); - if (error < 0) - goto out; - } + /* Now we set up the journal barrier. */ + jbd2_journal_lock_updates(journal); - /* Journal blocked and flushed, clear needs_recovery flag. */ - EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - error = ext4_commit_super(sb, 1); - if (error) - goto out; + /* + * Don't clear the needs_recovery flag if we failed to flush + * the journal. + */ + error = jbd2_journal_flush(journal); + if (error < 0) { + out: + jbd2_journal_unlock_updates(journal); + return error; } + + /* Journal blocked and flushed, clear needs_recovery flag. */ + EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + error = ext4_commit_super(sb, 1); + if (error) + goto out; return 0; -out: - jbd2_journal_unlock_updates(journal); - return error; } /* @@ -3352,14 +3357,15 @@ static int ext4_freeze(struct super_block *sb) */ static int ext4_unfreeze(struct super_block *sb) { - if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) { - lock_super(sb); - /* Reser the needs_recovery flag before the fs is unlocked. */ - EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); - ext4_commit_super(sb, 1); - unlock_super(sb); - jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); - } + if (sb->s_flags & MS_RDONLY) + return 0; + + lock_super(sb); + /* Reset the needs_recovery flag before the fs is unlocked. */ + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + ext4_commit_super(sb, 1); + unlock_super(sb); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); return 0; } From 8df9675f8b498d0bfa1f0b5b06f56bf1ff366dd5 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 1 May 2009 08:50:38 -0400 Subject: [PATCH 09/49] ext4: Avoid races caused by on-line resizing and SMP memory reordering Ext4's on-line resizing adds a new block group and then, only at the last step adjusts s_groups_count. However, it's possible on SMP systems that another CPU could see the updated the s_group_count and not see the newly initialized data structures for the just-added block group. For this reason, it's important to insert a SMP read barrier after reading s_groups_count and before reading any (for example) the new block group descriptors allowed by the increased value of s_groups_count. Unfortunately, we rather blatently violate this locking protocol documented in fs/ext4/resize.c. Fortunately, (1) on-line resizes happen relatively rarely, and (2) it seems rare that the filesystem code will immediately try to use just-added block group before any memory ordering issues resolve themselves. So apparently problems here are relatively hard to hit, since ext3 has been vulnerable to the same issue for years with no one apparently complaining. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 15 +++++++-------- fs/ext4/ext4.h | 12 ++++++++++++ fs/ext4/ialloc.c | 40 +++++++++++++++++++--------------------- fs/ext4/inode.c | 7 ++++--- fs/ext4/mballoc.c | 45 ++++++++++++++++++++++++--------------------- fs/ext4/super.c | 3 +-- 6 files changed, 67 insertions(+), 55 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 53c72ad85877..a5ba039850c5 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -88,6 +88,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, ext4_group_t block_group, struct ext4_group_desc *gdp) { int bit, bit_max; + ext4_group_t ngroups = ext4_get_groups_count(sb); unsigned free_blocks, group_blocks; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -123,7 +124,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, bit_max += ext4_bg_num_gdb(sb, block_group); } - if (block_group == sbi->s_groups_count - 1) { + if (block_group == ngroups - 1) { /* * Even though mke2fs always initialize first and last group * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need @@ -131,7 +132,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, */ group_blocks = ext4_blocks_count(sbi->s_es) - le32_to_cpu(sbi->s_es->s_first_data_block) - - (EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count - 1)); + (EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1)); } else { group_blocks = EXT4_BLOCKS_PER_GROUP(sb); } @@ -205,18 +206,18 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, { unsigned int group_desc; unsigned int offset; + ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); - if (block_group >= sbi->s_groups_count) { + if (block_group >= ngroups) { ext4_error(sb, "ext4_get_group_desc", "block_group >= groups_count - " "block_group = %u, groups_count = %u", - block_group, sbi->s_groups_count); + block_group, ngroups); return NULL; } - smp_rmb(); group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb); offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1); @@ -665,7 +666,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) ext4_fsblk_t desc_count; struct ext4_group_desc *gdp; ext4_group_t i; - ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t ngroups = ext4_get_groups_count(sb); #ifdef EXT4FS_DEBUG struct ext4_super_block *es; ext4_fsblk_t bitmap_count; @@ -677,7 +678,6 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) bitmap_count = 0; gdp = NULL; - smp_rmb(); for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) @@ -700,7 +700,6 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) return bitmap_count; #else desc_count = 0; - smp_rmb(); for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d0f15ef56de1..02ec44bf38e6 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1228,6 +1228,18 @@ struct ext4_group_info *ext4_get_group_info(struct super_block *sb, return grp_info[indexv][indexh]; } +/* + * Reading s_groups_count requires using smp_rmb() afterwards. See + * the locking protocol documented in the comments of ext4_group_add() + * in resize.c + */ +static inline ext4_group_t ext4_get_groups_count(struct super_block *sb) +{ + ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + + smp_rmb(); + return ngroups; +} static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi, ext4_group_t block_group) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f18e0a08a6b5..55ba419ca00b 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -316,7 +316,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) static int find_group_dir(struct super_block *sb, struct inode *parent, ext4_group_t *best_group) { - ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t ngroups = ext4_get_groups_count(sb); unsigned int freei, avefreei; struct ext4_group_desc *desc, *best_desc = NULL; ext4_group_t group; @@ -353,7 +353,7 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, struct flex_groups *flex_group = sbi->s_flex_groups; ext4_group_t parent_group = EXT4_I(parent)->i_block_group; ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group); - ext4_group_t ngroups = sbi->s_groups_count; + ext4_group_t ngroups = ext4_get_groups_count(sb); int flex_size = ext4_flex_bg_size(sbi); ext4_group_t best_flex = parent_fbg_group; int blocks_per_flex = sbi->s_blocks_per_group * flex_size; @@ -362,7 +362,7 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, ext4_group_t n_fbg_groups; ext4_group_t i; - n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >> + n_fbg_groups = (ngroups + flex_size - 1) >> sbi->s_log_groups_per_flex; find_close_to_parent: @@ -478,20 +478,21 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, { ext4_group_t parent_group = EXT4_I(parent)->i_block_group; struct ext4_sb_info *sbi = EXT4_SB(sb); - ext4_group_t ngroups = sbi->s_groups_count; + ext4_group_t real_ngroups = ext4_get_groups_count(sb); int inodes_per_group = EXT4_INODES_PER_GROUP(sb); unsigned int freei, avefreei; ext4_fsblk_t freeb, avefreeb; unsigned int ndirs; int max_dirs, min_inodes; ext4_grpblk_t min_blocks; - ext4_group_t i, grp, g; + ext4_group_t i, grp, g, ngroups; struct ext4_group_desc *desc; struct orlov_stats stats; int flex_size = ext4_flex_bg_size(sbi); + ngroups = real_ngroups; if (flex_size > 1) { - ngroups = (ngroups + flex_size - 1) >> + ngroups = (real_ngroups + flex_size - 1) >> sbi->s_log_groups_per_flex; parent_group >>= sbi->s_log_groups_per_flex; } @@ -543,7 +544,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, */ grp *= flex_size; for (i = 0; i < flex_size; i++) { - if (grp+i >= sbi->s_groups_count) + if (grp+i >= real_ngroups) break; desc = ext4_get_group_desc(sb, grp+i, NULL); if (desc && ext4_free_inodes_count(sb, desc)) { @@ -583,7 +584,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, } fallback: - ngroups = sbi->s_groups_count; + ngroups = real_ngroups; avefreei = freei / ngroups; fallback_retry: parent_group = EXT4_I(parent)->i_block_group; @@ -613,9 +614,8 @@ static int find_group_other(struct super_block *sb, struct inode *parent, ext4_group_t *group, int mode) { ext4_group_t parent_group = EXT4_I(parent)->i_block_group; - ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t i, last, ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; - ext4_group_t i, last; int flex_size = ext4_flex_bg_size(EXT4_SB(sb)); /* @@ -799,11 +799,10 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; struct buffer_head *group_desc_bh; - ext4_group_t group = 0; + ext4_group_t ngroups, group = 0; unsigned long ino = 0; struct inode *inode; struct ext4_group_desc *gdp = NULL; - struct ext4_super_block *es; struct ext4_inode_info *ei; struct ext4_sb_info *sbi; int ret2, err = 0; @@ -818,15 +817,14 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) return ERR_PTR(-EPERM); sb = dir->i_sb; + ngroups = ext4_get_groups_count(sb); trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id, dir->i_ino, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT4_I(inode); - sbi = EXT4_SB(sb); - es = sbi->s_es; if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) { ret2 = find_group_flex(sb, dir, &group); @@ -856,7 +854,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) if (ret2 == -1) goto out; - for (i = 0; i < sbi->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { err = -EIO; gdp = ext4_get_group_desc(sb, group, &group_desc_bh); @@ -917,7 +915,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) * group descriptor metadata has not yet been updated. * So we just go onto the next blockgroup. */ - if (++group == sbi->s_groups_count) + if (++group == ngroups) group = 0; } err = -ENOSPC; @@ -1158,7 +1156,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) { unsigned long desc_count; struct ext4_group_desc *gdp; - ext4_group_t i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); #ifdef EXT4FS_DEBUG struct ext4_super_block *es; unsigned long bitmap_count, x; @@ -1168,7 +1166,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) desc_count = 0; bitmap_count = 0; gdp = NULL; - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; @@ -1190,7 +1188,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) return desc_count; #else desc_count = 0; - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; @@ -1205,9 +1203,9 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) unsigned long ext4_count_dirs(struct super_block * sb) { unsigned long count = 0; - ext4_group_t i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 96f3366f59f6..4e7f363e3030 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4965,7 +4965,8 @@ static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) */ int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk) { - int groups, gdpblocks; + ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb); + int gdpblocks; int idxblocks; int ret = 0; @@ -4992,8 +4993,8 @@ int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk) groups += nrblocks; gdpblocks = groups; - if (groups > EXT4_SB(inode->i_sb)->s_groups_count) - groups = EXT4_SB(inode->i_sb)->s_groups_count; + if (groups > ngroups) + groups = ngroups; if (groups > EXT4_SB(inode->i_sb)->s_gdb_count) gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f871677a7984..c3af9e6b6668 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -739,6 +739,7 @@ static void ext4_mb_generate_buddy(struct super_block *sb, static int ext4_mb_init_cache(struct page *page, char *incore) { + ext4_group_t ngroups; int blocksize; int blocks_per_page; int groups_per_page; @@ -757,6 +758,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) inode = page->mapping->host; sb = inode->i_sb; + ngroups = ext4_get_groups_count(sb); blocksize = 1 << inode->i_blkbits; blocks_per_page = PAGE_CACHE_SIZE / blocksize; @@ -780,7 +782,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) for (i = 0; i < groups_per_page; i++) { struct ext4_group_desc *desc; - if (first_group + i >= EXT4_SB(sb)->s_groups_count) + if (first_group + i >= ngroups) break; err = -EIO; @@ -852,7 +854,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) struct ext4_group_info *grinfo; group = (first_block + i) >> 1; - if (group >= EXT4_SB(sb)->s_groups_count) + if (group >= ngroups) break; /* @@ -1788,6 +1790,7 @@ int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group) int block, pnum; int blocks_per_page; int groups_per_page; + ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t first_group; struct ext4_group_info *grp; @@ -1807,7 +1810,7 @@ int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group) /* read all groups the page covers into the cache */ for (i = 0; i < groups_per_page; i++) { - if ((first_group + i) >= EXT4_SB(sb)->s_groups_count) + if ((first_group + i) >= ngroups) break; grp = ext4_get_group_info(sb, first_group + i); /* take all groups write allocation @@ -1945,8 +1948,7 @@ static int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { - ext4_group_t group; - ext4_group_t i; + ext4_group_t ngroups, group, i; int cr; int err = 0; int bsbits; @@ -1957,6 +1959,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) sb = ac->ac_sb; sbi = EXT4_SB(sb); + ngroups = ext4_get_groups_count(sb); BUG_ON(ac->ac_status == AC_STATUS_FOUND); /* first, try the goal */ @@ -2017,11 +2020,11 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) */ group = ac->ac_g_ex.fe_group; - for (i = 0; i < EXT4_SB(sb)->s_groups_count; group++, i++) { + for (i = 0; i < ngroups; group++, i++) { struct ext4_group_info *grp; struct ext4_group_desc *desc; - if (group == EXT4_SB(sb)->s_groups_count) + if (group == ngroups) group = 0; /* quick check to skip empty groups */ @@ -2315,12 +2318,10 @@ static struct file_operations ext4_mb_seq_history_fops = { static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = seq->private; - struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; - if (*pos < 0 || *pos >= sbi->s_groups_count) + if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; - group = *pos + 1; return (void *) ((unsigned long) group); } @@ -2328,11 +2329,10 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = seq->private; - struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ++*pos; - if (*pos < 0 || *pos >= sbi->s_groups_count) + if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); @@ -2587,6 +2587,7 @@ void ext4_mb_update_group_info(struct ext4_group_info *grp, ext4_grpblk_t add) 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); @@ -2598,7 +2599,7 @@ static int ext4_mb_init_backend(struct super_block *sb) struct ext4_group_desc *desc; /* This is the number of blocks used by GDT */ - num_meta_group_infos = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - + num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); /* @@ -2644,7 +2645,7 @@ static int ext4_mb_init_backend(struct super_block *sb) for (i = 0; i < num_meta_group_infos; i++) { if ((i + 1) == num_meta_group_infos) metalen = sizeof(*meta_group_info) * - (sbi->s_groups_count - + (ngroups - (i << EXT4_DESC_PER_BLOCK_BITS(sb))); meta_group_info = kmalloc(metalen, GFP_KERNEL); if (meta_group_info == NULL) { @@ -2655,7 +2656,7 @@ static int ext4_mb_init_backend(struct super_block *sb) sbi->s_group_info[i] = meta_group_info; } - for (i = 0; i < sbi->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { printk(KERN_ERR @@ -2781,13 +2782,14 @@ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp) int ext4_mb_release(struct super_block *sb) { + ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; struct ext4_group_info *grinfo; struct ext4_sb_info *sbi = EXT4_SB(sb); if (sbi->s_group_info) { - for (i = 0; i < sbi->s_groups_count; i++) { + for (i = 0; i < ngroups; i++) { grinfo = ext4_get_group_info(sb, i); #ifdef DOUBLE_CHECK kfree(grinfo->bb_bitmap); @@ -2797,7 +2799,7 @@ int ext4_mb_release(struct super_block *sb) ext4_unlock_group(sb, i); kfree(grinfo); } - num_meta_group_infos = (sbi->s_groups_count + + num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); for (i = 0; i < num_meta_group_infos; i++) @@ -4121,7 +4123,7 @@ static void ext4_mb_return_to_preallocation(struct inode *inode, static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; - ext4_group_t i; + ext4_group_t ngroups, i; printk(KERN_ERR "EXT4-fs: Can't allocate:" " Allocation context details:\n"); @@ -4145,7 +4147,8 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) printk(KERN_ERR "EXT4-fs: %lu scanned, %d found\n", ac->ac_ex_scanned, ac->ac_found); printk(KERN_ERR "EXT4-fs: groups: \n"); - for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + ngroups = ext4_get_groups_count(sb); + for (i = 0; i < ngroups; i++) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); struct ext4_prealloc_space *pa; ext4_grpblk_t start; @@ -4469,13 +4472,13 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) { - ext4_group_t i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); int ret; int freed = 0; trace_mark(ext4_mb_discard_preallocations, "dev %s needed %d", sb->s_id, needed); - for (i = 0; i < EXT4_SB(sb)->s_groups_count && needed > 0; i++) { + for (i = 0; i < ngroups && needed > 0; i++) { ret = ext4_mb_discard_group_preallocations(sb, i, needed); freed += ret; needed -= ret; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 68c3a44c4a97..fcd7b24c6df3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3557,9 +3557,8 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) if (test_opt(sb, MINIX_DF)) { sbi->s_overhead_last = 0; } else if (sbi->s_blocks_last != ext4_blocks_count(es)) { - ext4_group_t ngroups = sbi->s_groups_count, i; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); ext4_fsblk_t overhead = 0; - smp_rmb(); /* * Compute the overhead (FS structures). This is constant From 114e9fc90703bd6aac0229fb559e97caa6c49770 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 25 Apr 2009 15:48:07 -0400 Subject: [PATCH 10/49] ext4: Remove outdated comment about lock_super() ext4_fill_super() is no longer called by read_super(), and it is no longer called with the superblock locked. The unlock_super()/lock_super() is no longer present, so this comment is entirely superfluous. Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index fcd7b24c6df3..e3b35f26d5fe 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2828,14 +2828,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount4; }; - /* - * akpm: core read_super() calls in here with the superblock locked. - * That deadlocks, because orphan cleanup needs to lock the superblock - * in numerous places. Here we just pop the lock - it's relatively - * harmless, because we are now ready to accept write_super() requests, - * and aviro says that's the only reason for hanging onto the - * superblock lock. - */ EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; From a63c9eb2ce6f5028da90f282798232c4f398ceb8 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 1 May 2009 01:59:42 -0400 Subject: [PATCH 11/49] ext4: ext4_mark_recovery_complete() doesn't need to use lock_super The function ext4_mark_recovery_complete() is called from two call paths: either (a) while mounting the filesystem, in which case there's no danger of any other CPU calling write_super() until the mount is completed, and (b) while remounting the filesystem read-write, in which case the fs core has already locked the superblock. This also allows us to take out a very vile unlock_super()/lock_super() pair in ext4_remount(). Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e3b35f26d5fe..45d0ada9bfce 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3219,13 +3219,11 @@ static void ext4_mark_recovery_complete(struct super_block *sb, if (jbd2_journal_flush(journal) < 0) goto out; - lock_super(sb); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) && sb->s_flags & MS_RDONLY) { EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); ext4_commit_super(sb, 1); } - unlock_super(sb); out: jbd2_journal_unlock_updates(journal); @@ -3436,15 +3434,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); - /* - * We have to unlock super so that we can wait for - * transactions. - */ - if (sbi->s_journal) { - unlock_super(sb); + if (sbi->s_journal) ext4_mark_recovery_complete(sb, es); - lock_super(sb); - } } else { int ret; if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb, From 3b9d4ed26680771295d904a6b83e88e620780893 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 25 Apr 2009 22:54:04 -0400 Subject: [PATCH 12/49] ext4: Replace lock/unlock_super() with an explicit lock for the orphan list Use a separate lock to protect the orphan list, so we can stop overloading the use of lock_super(). Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4_sb.h | 1 + fs/ext4/namei.c | 20 +++++++++++--------- fs/ext4/super.c | 1 + 3 files changed, 13 insertions(+), 9 deletions(-) diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h index 57b71fefbccf..4bda2f75d426 100644 --- a/fs/ext4/ext4_sb.h +++ b/fs/ext4/ext4_sb.h @@ -71,6 +71,7 @@ struct ext4_sb_info { struct inode *s_journal_inode; struct journal_s *s_journal; struct list_head s_orphan; + struct mutex s_orphan_lock; unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 22098e1cd085..8018e49a7287 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1997,7 +1997,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) if (!ext4_handle_valid(handle)) return 0; - lock_super(sb); + mutex_lock(&EXT4_SB(sb)->s_orphan_lock); if (!list_empty(&EXT4_I(inode)->i_orphan)) goto out_unlock; @@ -2006,9 +2006,13 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) /* @@@ FIXME: Observation from aviro: * I think I can trigger J_ASSERT in ext4_orphan_add(). We block - * here (on lock_super()), so race with ext4_link() which might bump + * here (on s_orphan_lock), so race with ext4_link() which might bump * ->i_nlink. For, say it, character device. Not a regular file, * not a directory, not a symlink and ->i_nlink > 0. + * + * tytso, 4/25/2009: I'm not sure how that could happen; + * shouldn't the fs core protect us from these sort of + * unlink()/link() races? */ J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) || inode->i_nlink == 0); @@ -2045,7 +2049,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) jbd_debug(4, "orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); out_unlock: - unlock_super(sb); + mutex_unlock(&EXT4_SB(sb)->s_orphan_lock); ext4_std_error(inode->i_sb, err); return err; } @@ -2066,11 +2070,9 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) if (!ext4_handle_valid(handle)) return 0; - lock_super(inode->i_sb); - if (list_empty(&ei->i_orphan)) { - unlock_super(inode->i_sb); - return 0; - } + mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock); + if (list_empty(&ei->i_orphan)) + goto out; ino_next = NEXT_ORPHAN(inode); prev = ei->i_orphan.prev; @@ -2120,7 +2122,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) out_err: ext4_std_error(inode->i_sb, err); out: - unlock_super(inode->i_sb); + mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock); return err; out_brelse: diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 45d0ada9bfce..7f43fde9554b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2645,6 +2645,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->dq_op = &ext4_quota_operations; #endif INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ + mutex_init(&sbi->s_orphan_lock); sb->s_root = NULL; From 32ed5058ce90024efcd811254b4b1de0468099df Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 25 Apr 2009 22:53:39 -0400 Subject: [PATCH 13/49] ext4: Replace lock/unlock_super() with an explicit lock for resizing Use a separate lock to protect s_groups_count and the other block group descriptors which get changed via an on-line resize operation, so we can stop overloading the use of lock_super(). Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4_sb.h | 1 + fs/ext4/resize.c | 35 ++++++++++++++++++----------------- fs/ext4/super.c | 1 + 3 files changed, 20 insertions(+), 17 deletions(-) diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h index 4bda2f75d426..2d36223d5f57 100644 --- a/fs/ext4/ext4_sb.h +++ b/fs/ext4/ext4_sb.h @@ -72,6 +72,7 @@ struct ext4_sb_info { struct journal_s *s_journal; struct list_head s_orphan; struct mutex s_orphan_lock; + struct mutex s_resize_lock; unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 546c7dd869e1..e8ded13b5cb1 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -193,7 +193,7 @@ static int setup_new_group_blocks(struct super_block *sb, if (IS_ERR(handle)) return PTR_ERR(handle); - lock_super(sb); + mutex_lock(&sbi->s_resize_lock); if (input->group != sbi->s_groups_count) { err = -EBUSY; goto exit_journal; @@ -302,7 +302,7 @@ static int setup_new_group_blocks(struct super_block *sb, brelse(bh); exit_journal: - unlock_super(sb); + mutex_unlock(&sbi->s_resize_lock); if ((err2 = ext4_journal_stop(handle)) && !err) err = err2; @@ -643,11 +643,12 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, * important part is that the new block and inode counts are in the backup * superblocks, and the location of the new group metadata in the GDT backups. * - * We do not need lock_super() for this, because these blocks are not - * otherwise touched by the filesystem code when it is mounted. We don't - * need to worry about last changing from sbi->s_groups_count, because the - * worst that can happen is that we do not copy the full number of backups - * at this time. The resize which changed s_groups_count will backup again. + * We do not need take the s_resize_lock for this, because these + * blocks are not otherwise touched by the filesystem code when it is + * mounted. We don't need to worry about last changing from + * sbi->s_groups_count, because the worst that can happen is that we + * do not copy the full number of backups at this time. The resize + * which changed s_groups_count will backup again. */ static void update_backups(struct super_block *sb, int blk_off, char *data, int size) @@ -809,7 +810,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) goto exit_put; } - lock_super(sb); + mutex_lock(&sbi->s_resize_lock); if (input->group != sbi->s_groups_count) { ext4_warning(sb, __func__, "multiple resizers run on filesystem!"); @@ -840,7 +841,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) /* * OK, now we've set up the new group. Time to make it active. * - * Current kernels don't lock all allocations via lock_super(), + * We do not lock all allocations via s_resize_lock * so we have to be safe wrt. concurrent accesses the group * data. So we need to be careful to set all of the relevant * group descriptor data etc. *before* we enable the group. @@ -900,12 +901,12 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) * * The precise rules we use are: * - * * Writers of s_groups_count *must* hold lock_super + * * Writers of s_groups_count *must* hold s_resize_lock * AND * * Writers must perform a smp_wmb() after updating all dependent * data and before modifying the groups count * - * * Readers must hold lock_super() over the access + * * Readers must hold s_resize_lock over the access * OR * * Readers must perform an smp_rmb() after reading the groups count * and before reading any dependent data. @@ -948,7 +949,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) sb->s_dirt = 1; exit_journal: - unlock_super(sb); + mutex_unlock(&sbi->s_resize_lock); if ((err2 = ext4_journal_stop(handle)) && !err) err = err2; if (!err) { @@ -986,7 +987,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, /* We don't need to worry about locking wrt other resizers just * yet: we're going to revalidate es->s_blocks_count after - * taking lock_super() below. */ + * taking the s_resize_lock below. */ o_blocks_count = ext4_blocks_count(es); o_groups_count = EXT4_SB(sb)->s_groups_count; @@ -1056,11 +1057,11 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, goto exit_put; } - lock_super(sb); + mutex_lock(&EXT4_SB(sb)->s_resize_lock); if (o_blocks_count != ext4_blocks_count(es)) { ext4_warning(sb, __func__, "multiple resizers run on filesystem!"); - unlock_super(sb); + mutex_unlock(&EXT4_SB(sb)->s_resize_lock); ext4_journal_stop(handle); err = -EBUSY; goto exit_put; @@ -1070,14 +1071,14 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, EXT4_SB(sb)->s_sbh))) { ext4_warning(sb, __func__, "error %d on journal write access", err); - unlock_super(sb); + mutex_unlock(&EXT4_SB(sb)->s_resize_lock); ext4_journal_stop(handle); goto exit_put; } ext4_blocks_count_set(es, o_blocks_count + add); ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); sb->s_dirt = 1; - unlock_super(sb); + mutex_unlock(&EXT4_SB(sb)->s_resize_lock); ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); /* We add the blocks to the bitmap and set the group need init bit */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 7f43fde9554b..1fbf0906ae2e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2646,6 +2646,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #endif INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); + mutex_init(&sbi->s_resize_lock); sb->s_root = NULL; From 75507efb1372b6acf1aa6bf00ebd49ce196fd994 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 1 May 2009 12:58:36 -0400 Subject: [PATCH 14/49] ext4: Don't avoid using BLOCK_UNINIT block groups in mballoc By avoiding the use of not-yet-used block groups (i.e., block groups with the BLOCK_UNINIT flag), mballoc had a tendency to create large files with large non-contiguous gaps. In addition avoiding the use of new block groups had a tendency to push regular file data into the first block group in a flex_bg group, which slows down the speed of e2fsck pass 2, since it has a tendency to seek much more. For example: Before Patch After Patch Time in seconds Time in seconds Real / User/ Sys MB/s Real / User/ Sys MB/s Pass 1 8.52 / 2.21 / 0.46 20.43 8.84 / 4.97 / 1.11 19.68 Pass 2 21.16 / 1.02 / 1.86 11.30 6.54 / 1.77 / 1.78 36.39 Pass 3 0.01 / 0.00 / 0.00 139.00 0.01 / 0.01 / 0.00 128.90 Pass 4 0.16 / 0.15 / 0.00 0.00 0.17 / 0.17 / 0.00 0.00 Pass 5 2.52 / 1.99 / 0.09 0.79 2.31 / 1.78 / 0.06 0.86 Total 32.40 / 5.11 / 2.49 12.81 17.99 / 8.75 / 2.98 23.01 This was on a sample 80 gig root filesystem which was approximately 50% full. Note the improved e2fsck pass 2 performance, by over a factor of 3, due to a decreased number of seeks. (The total amount of I/O in pass 2 was unchanged; the layout of the directory blocks was simply much better from e2fsck's's perspective.) Other changes as a result of this patch on this sample filesystem: Before Patch After Patch # of non-contig files 762 779 # of non-contig directories 571 570 # of BLOCK_UNINIT bg's 307 293 # of INODE_UNINIT bg's 503 503 Out of 640 block groups, of which 333 were in use, this patch caused an extra 14 block groups to be utilized. The number of non-contiguous files did go up slightly, but when measured against the 99.9% of the files (603,154) which were contiguously allocated, this is pretty insignificant. Signed-off-by: "Theodore Ts'o" Signed-off-by: Andreas Dilger --- fs/ext4/mballoc.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c3af9e6b6668..dbd47eac13ec 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1728,7 +1728,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, unsigned free, fragments; unsigned i, bits; int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb)); - struct ext4_group_desc *desc; struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); BUG_ON(cr < 0 || cr >= 4); @@ -1744,10 +1743,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, switch (cr) { case 0: BUG_ON(ac->ac_2order == 0); - /* If this group is uninitialized, skip it initially */ - desc = ext4_get_group_desc(ac->ac_sb, group, NULL); - if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) - return 0; /* Avoid using the first bg of a flexgroup for data files */ if ((ac->ac_flags & EXT4_MB_HINT_DATA) && @@ -2067,9 +2062,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) ac->ac_groups_scanned++; desc = ext4_get_group_desc(sb, group, NULL); - if (cr == 0 || (desc->bg_flags & - cpu_to_le16(EXT4_BG_BLOCK_UNINIT) && - ac->ac_2order != 0)) + if (cr == 0) ext4_mb_simple_scan_group(ac, &e4b); else if (cr == 1 && ac->ac_g_ex.fe_len == sbi->s_stripe) From d444c3c38189b3f18337a213855ac1c07af4e2d9 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 1 May 2009 13:44:33 -0400 Subject: [PATCH 15/49] ext4: Move the ext4_i.h header file into ext4.h There is no longer a reason for a separate ext4_i.h header file, so move it into ext4.h just to make life easier for developers to find the relevant data structures and typedefs. Should also speed up compiles slightly, too. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 122 ++++++++++++++++++++++++++++++++++++++++- fs/ext4/ext4_i.h | 140 ----------------------------------------------- 2 files changed, 121 insertions(+), 141 deletions(-) delete mode 100644 fs/ext4/ext4_i.h diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 02ec44bf38e6..ba57d669cb65 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -21,7 +21,10 @@ #include #include #include -#include "ext4_i.h" +#include +#include +#include +#include /* * The fourth extended filesystem constants/structures @@ -46,6 +49,19 @@ #define ext4_debug(f, a...) do {} while (0) #endif +/* data type for block offset of block group */ +typedef int ext4_grpblk_t; + +/* data type for filesystem-wide blocks number */ +typedef unsigned long long ext4_fsblk_t; + +/* data type for file logical block number */ +typedef __u32 ext4_lblk_t; + +/* data type for block group number */ +typedef unsigned int ext4_group_t; + + /* prefer goal again. length */ #define EXT4_MB_HINT_MERGE 1 /* blocks already reserved */ @@ -515,6 +531,110 @@ do { \ #endif /* defined(__KERNEL__) || defined(__linux__) */ +/* + * storage for cached extent + */ +struct ext4_ext_cache { + ext4_fsblk_t ec_start; + ext4_lblk_t ec_block; + __u32 ec_len; /* must be 32bit to return holes */ + __u32 ec_type; +}; + +/* + * fourth extended file system inode data in memory + */ +struct ext4_inode_info { + __le32 i_data[15]; /* unconverted */ + __u32 i_flags; + ext4_fsblk_t i_file_acl; + __u32 i_dtime; + + /* + * i_block_group is the number of the block group which contains + * this file's inode. Constant across the lifetime of the inode, + * it is ued for making block allocation decisions - we try to + * place a file's data blocks near its inode block, and new inodes + * near to their parent directory's inode. + */ + ext4_group_t i_block_group; + __u32 i_state; /* Dynamic state flags for ext4 */ + + ext4_lblk_t i_dir_start_lookup; +#ifdef CONFIG_EXT4_FS_XATTR + /* + * Extended attributes can be read independently of the main file + * data. Taking i_mutex even when reading would cause contention + * between readers of EAs and writers of regular file data, so + * instead we synchronize on xattr_sem when reading or changing + * EAs. + */ + struct rw_semaphore xattr_sem; +#endif +#ifdef CONFIG_EXT4_FS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif + + struct list_head i_orphan; /* unlinked but open inodes */ + + /* + * i_disksize keeps track of what the inode size is ON DISK, not + * in memory. During truncate, i_size is set to the new size by + * the VFS prior to calling ext4_truncate(), but the filesystem won't + * set i_disksize to 0 until the truncate is actually under way. + * + * The intent is that i_disksize always represents the blocks which + * are used by this file. This allows recovery to restart truncate + * on orphans if we crash during truncate. We actually write i_disksize + * into the on-disk inode when writing inodes out, instead of i_size. + * + * The only time when i_disksize and i_size may be different is when + * a truncate is in progress. The only things which change i_disksize + * are ext4_get_block (growth) and ext4_truncate (shrinkth). + */ + loff_t i_disksize; + + /* + * i_data_sem is for serialising ext4_truncate() against + * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's + * data tree are chopped off during truncate. We can't do that in + * ext4 because whenever we perform intermediate commits during + * truncate, the inode and all the metadata blocks *must* be in a + * consistent state which allows truncation of the orphans to restart + * during recovery. Hence we must fix the get_block-vs-truncate race + * by other means, so we have i_data_sem. + */ + struct rw_semaphore i_data_sem; + struct inode vfs_inode; + struct jbd2_inode jinode; + + struct ext4_ext_cache i_cached_extent; + /* + * File creation time. Its function is same as that of + * struct timespec i_{a,c,m}time in the generic inode. + */ + struct timespec i_crtime; + + /* mballoc */ + struct list_head i_prealloc_list; + spinlock_t i_prealloc_lock; + + /* ialloc */ + ext4_group_t i_last_alloc_group; + + /* allocation reservation info for delalloc */ + unsigned int i_reserved_data_blocks; + unsigned int i_reserved_meta_blocks; + unsigned int i_allocated_meta_blocks; + unsigned short i_delalloc_reserved_flag; + + /* on-disk additional length */ + __u16 i_extra_isize; + + spinlock_t i_block_reservation_lock; +}; + /* * File system states */ diff --git a/fs/ext4/ext4_i.h b/fs/ext4/ext4_i.h deleted file mode 100644 index 4ce2187123aa..000000000000 --- a/fs/ext4/ext4_i.h +++ /dev/null @@ -1,140 +0,0 @@ -/* - * ext4_i.h - * - * Copyright (C) 1992, 1993, 1994, 1995 - * Remy Card (card@masi.ibp.fr) - * Laboratoire MASI - Institut Blaise Pascal - * Universite Pierre et Marie Curie (Paris VI) - * - * from - * - * linux/include/linux/minix_fs_i.h - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -#ifndef _EXT4_I -#define _EXT4_I - -#include -#include -#include -#include - -/* data type for block offset of block group */ -typedef int ext4_grpblk_t; - -/* data type for filesystem-wide blocks number */ -typedef unsigned long long ext4_fsblk_t; - -/* data type for file logical block number */ -typedef __u32 ext4_lblk_t; - -/* data type for block group number */ -typedef unsigned int ext4_group_t; - -/* - * storage for cached extent - */ -struct ext4_ext_cache { - ext4_fsblk_t ec_start; - ext4_lblk_t ec_block; - __u32 ec_len; /* must be 32bit to return holes */ - __u32 ec_type; -}; - -/* - * fourth extended file system inode data in memory - */ -struct ext4_inode_info { - __le32 i_data[15]; /* unconverted */ - __u32 i_flags; - ext4_fsblk_t i_file_acl; - __u32 i_dtime; - - /* - * i_block_group is the number of the block group which contains - * this file's inode. Constant across the lifetime of the inode, - * it is ued for making block allocation decisions - we try to - * place a file's data blocks near its inode block, and new inodes - * near to their parent directory's inode. - */ - ext4_group_t i_block_group; - __u32 i_state; /* Dynamic state flags for ext4 */ - - ext4_lblk_t i_dir_start_lookup; -#ifdef CONFIG_EXT4_FS_XATTR - /* - * Extended attributes can be read independently of the main file - * data. Taking i_mutex even when reading would cause contention - * between readers of EAs and writers of regular file data, so - * instead we synchronize on xattr_sem when reading or changing - * EAs. - */ - struct rw_semaphore xattr_sem; -#endif -#ifdef CONFIG_EXT4_FS_POSIX_ACL - struct posix_acl *i_acl; - struct posix_acl *i_default_acl; -#endif - - struct list_head i_orphan; /* unlinked but open inodes */ - - /* - * i_disksize keeps track of what the inode size is ON DISK, not - * in memory. During truncate, i_size is set to the new size by - * the VFS prior to calling ext4_truncate(), but the filesystem won't - * set i_disksize to 0 until the truncate is actually under way. - * - * The intent is that i_disksize always represents the blocks which - * are used by this file. This allows recovery to restart truncate - * on orphans if we crash during truncate. We actually write i_disksize - * into the on-disk inode when writing inodes out, instead of i_size. - * - * The only time when i_disksize and i_size may be different is when - * a truncate is in progress. The only things which change i_disksize - * are ext4_get_block (growth) and ext4_truncate (shrinkth). - */ - loff_t i_disksize; - - /* - * i_data_sem is for serialising ext4_truncate() against - * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's - * data tree are chopped off during truncate. We can't do that in - * ext4 because whenever we perform intermediate commits during - * truncate, the inode and all the metadata blocks *must* be in a - * consistent state which allows truncation of the orphans to restart - * during recovery. Hence we must fix the get_block-vs-truncate race - * by other means, so we have i_data_sem. - */ - struct rw_semaphore i_data_sem; - struct inode vfs_inode; - struct jbd2_inode jinode; - - struct ext4_ext_cache i_cached_extent; - /* - * File creation time. Its function is same as that of - * struct timespec i_{a,c,m}time in the generic inode. - */ - struct timespec i_crtime; - - /* mballoc */ - struct list_head i_prealloc_list; - spinlock_t i_prealloc_lock; - - /* ialloc */ - ext4_group_t i_last_alloc_group; - - /* allocation reservation info for delalloc */ - unsigned int i_reserved_data_blocks; - unsigned int i_reserved_meta_blocks; - unsigned int i_allocated_meta_blocks; - unsigned short i_delalloc_reserved_flag; - - /* on-disk additional length */ - __u16 i_extra_isize; - - spinlock_t i_block_reservation_lock; -}; - -#endif /* _EXT4_I */ From ca0faba0e8ac844dc0279825eb8db876b5962ea5 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 3 May 2009 16:33:44 -0400 Subject: [PATCH 16/49] ext4: Move the ext4_sb.h header file into ext4.h There is no longer a reason for a separate ext4_sb.h header file, so move it into ext4.h just to make life easier for developers to find the relevant data structures and typedefs. Should also speed up compiles slightly, too. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 144 ++++++++++++++++++++++++++++++++++++++-- fs/ext4/ext4_sb.h | 163 ---------------------------------------------- 2 files changed, 140 insertions(+), 167 deletions(-) delete mode 100644 fs/ext4/ext4_sb.h diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ba57d669cb65..af3c906e705b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -25,6 +25,10 @@ #include #include #include +#include +#include +#include +#include /* * The fourth extended filesystem constants/structures @@ -195,9 +199,6 @@ struct flex_groups { #define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */ #define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */ -#ifdef __KERNEL__ -#include "ext4_sb.h" -#endif /* * Macro-instructions used to manage group descriptors */ @@ -809,6 +810,136 @@ struct ext4_super_block { }; #ifdef __KERNEL__ +/* + * fourth extended-fs super-block data in memory + */ +struct ext4_sb_info { + unsigned long s_desc_size; /* Size of a group descriptor in bytes */ + unsigned long s_inodes_per_block;/* Number of inodes per block */ + unsigned long s_blocks_per_group;/* Number of blocks in a group */ + unsigned long s_inodes_per_group;/* Number of inodes in a group */ + unsigned long s_itb_per_group; /* Number of inode table blocks per group */ + 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 */ + 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 */ + struct buffer_head * s_sbh; /* Buffer containing the super block */ + struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ + struct buffer_head **s_group_desc; + unsigned long s_mount_opt; + ext4_fsblk_t s_sb_block; + uid_t s_resuid; + gid_t s_resgid; + unsigned short s_mount_state; + unsigned short s_pad; + int s_addr_per_block_bits; + int s_desc_per_block_bits; + int s_inode_size; + int s_first_ino; + unsigned int s_inode_readahead_blks; + spinlock_t s_next_gen_lock; + u32 s_next_generation; + u32 s_hash_seed[4]; + int s_def_hash_version; + int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */ + struct percpu_counter s_freeblocks_counter; + struct percpu_counter s_freeinodes_counter; + struct percpu_counter s_dirs_counter; + struct percpu_counter s_dirtyblocks_counter; + struct blockgroup_lock *s_blockgroup_lock; + struct proc_dir_entry *s_proc; + struct kobject s_kobj; + struct completion s_kobj_unregister; + + /* Journaling */ + struct inode *s_journal_inode; + struct journal_s *s_journal; + struct list_head s_orphan; + struct mutex s_orphan_lock; + struct mutex s_resize_lock; + unsigned long s_commit_interval; + u32 s_max_batch_time; + u32 s_min_batch_time; + struct block_device *journal_bdev; +#ifdef CONFIG_JBD2_DEBUG + struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ + wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */ +#endif +#ifdef CONFIG_QUOTA + char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ + int s_jquota_fmt; /* Format of quota to use */ +#endif + unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ + +#ifdef EXTENTS_STATS + /* ext4 extents stats */ + unsigned long s_ext_min; + unsigned long s_ext_max; + unsigned long s_depth_max; + spinlock_t s_ext_stats_lock; + unsigned long s_ext_blocks; + unsigned long s_ext_extents; +#endif + + /* for buddy allocator */ + struct ext4_group_info ***s_group_info; + struct inode *s_buddy_cache; + long s_blocks_reserved; + spinlock_t s_reserve_lock; + spinlock_t s_md_lock; + tid_t s_last_transaction; + unsigned short *s_mb_offsets; + unsigned int *s_mb_maxs; + + /* tunables */ + unsigned long s_stripe; + unsigned int s_mb_stream_request; + unsigned int s_mb_max_to_scan; + unsigned int s_mb_min_to_scan; + unsigned int s_mb_stats; + unsigned int s_mb_order2_reqs; + unsigned int s_mb_group_prealloc; + /* where last allocation was done - for stream allocation */ + unsigned long s_mb_last_group; + unsigned long s_mb_last_start; + + /* history to debug policy */ + struct ext4_mb_history *s_mb_history; + int s_mb_history_cur; + int s_mb_history_max; + int s_mb_history_num; + spinlock_t s_mb_history_lock; + int s_mb_history_filter; + + /* stats for buddy allocator */ + spinlock_t s_mb_pa_lock; + atomic_t s_bal_reqs; /* number of reqs with len > 1 */ + atomic_t s_bal_success; /* we found long enough chunks */ + atomic_t s_bal_allocated; /* in blocks */ + atomic_t s_bal_ex_scanned; /* total extents scanned */ + atomic_t s_bal_goals; /* goal hits */ + atomic_t s_bal_breaks; /* too long searches */ + atomic_t s_bal_2orders; /* 2^order hits */ + spinlock_t s_bal_lock; + unsigned long s_mb_buddies_generated; + unsigned long long s_mb_generation_time; + atomic_t s_mb_lost_chunks; + atomic_t s_mb_preallocated; + atomic_t s_mb_discarded; + + /* locality groups */ + struct ext4_locality_group *s_locality_groups; + + /* for write statistics */ + unsigned long s_sectors_written_start; + u64 s_kbytes_written; + + unsigned int s_log_groups_per_flex; + struct flex_groups *s_flex_groups; +}; + static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) { return sb->s_fs_info; @@ -824,7 +955,6 @@ static inline struct timespec ext4_current_time(struct inode *inode) current_fs_time(inode->i_sb) : CURRENT_TIME_SEC; } - static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || @@ -833,6 +963,12 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) (ino >= EXT4_FIRST_INO(sb) && ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } + +static inline spinlock_t * +sb_bgl_lock(struct ext4_sb_info *sbi, unsigned int block_group) +{ + return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group); +} #else /* Assume that user mode programs are passing in an ext4fs superblock, not * a kernel struct super_block. This will allow us to call the feature-test diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h deleted file mode 100644 index 2d36223d5f57..000000000000 --- a/fs/ext4/ext4_sb.h +++ /dev/null @@ -1,163 +0,0 @@ -/* - * ext4_sb.h - * - * Copyright (C) 1992, 1993, 1994, 1995 - * Remy Card (card@masi.ibp.fr) - * Laboratoire MASI - Institut Blaise Pascal - * Universite Pierre et Marie Curie (Paris VI) - * - * from - * - * linux/include/linux/minix_fs_sb.h - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -#ifndef _EXT4_SB -#define _EXT4_SB - -#ifdef __KERNEL__ -#include -#include -#include -#include -#endif -#include - -/* - * fourth extended-fs super-block data in memory - */ -struct ext4_sb_info { - unsigned long s_desc_size; /* Size of a group descriptor in bytes */ - unsigned long s_inodes_per_block;/* Number of inodes per block */ - unsigned long s_blocks_per_group;/* Number of blocks in a group */ - unsigned long s_inodes_per_group;/* Number of inodes in a group */ - unsigned long s_itb_per_group; /* Number of inode table blocks per group */ - 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 */ - 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 */ - struct buffer_head * s_sbh; /* Buffer containing the super block */ - struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ - struct buffer_head **s_group_desc; - unsigned long s_mount_opt; - ext4_fsblk_t s_sb_block; - uid_t s_resuid; - gid_t s_resgid; - unsigned short s_mount_state; - unsigned short s_pad; - int s_addr_per_block_bits; - int s_desc_per_block_bits; - int s_inode_size; - int s_first_ino; - unsigned int s_inode_readahead_blks; - spinlock_t s_next_gen_lock; - u32 s_next_generation; - u32 s_hash_seed[4]; - int s_def_hash_version; - int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */ - struct percpu_counter s_freeblocks_counter; - struct percpu_counter s_freeinodes_counter; - struct percpu_counter s_dirs_counter; - struct percpu_counter s_dirtyblocks_counter; - struct blockgroup_lock *s_blockgroup_lock; - struct proc_dir_entry *s_proc; - struct kobject s_kobj; - struct completion s_kobj_unregister; - - /* Journaling */ - struct inode *s_journal_inode; - struct journal_s *s_journal; - struct list_head s_orphan; - struct mutex s_orphan_lock; - struct mutex s_resize_lock; - unsigned long s_commit_interval; - u32 s_max_batch_time; - u32 s_min_batch_time; - struct block_device *journal_bdev; -#ifdef CONFIG_JBD2_DEBUG - struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ - wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */ -#endif -#ifdef CONFIG_QUOTA - char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ - int s_jquota_fmt; /* Format of quota to use */ -#endif - unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ - -#ifdef EXTENTS_STATS - /* ext4 extents stats */ - unsigned long s_ext_min; - unsigned long s_ext_max; - unsigned long s_depth_max; - spinlock_t s_ext_stats_lock; - unsigned long s_ext_blocks; - unsigned long s_ext_extents; -#endif - - /* for buddy allocator */ - struct ext4_group_info ***s_group_info; - struct inode *s_buddy_cache; - long s_blocks_reserved; - spinlock_t s_reserve_lock; - spinlock_t s_md_lock; - tid_t s_last_transaction; - unsigned short *s_mb_offsets; - unsigned int *s_mb_maxs; - - /* tunables */ - unsigned long s_stripe; - unsigned int s_mb_stream_request; - unsigned int s_mb_max_to_scan; - unsigned int s_mb_min_to_scan; - unsigned int s_mb_stats; - unsigned int s_mb_order2_reqs; - unsigned int s_mb_group_prealloc; - /* where last allocation was done - for stream allocation */ - unsigned long s_mb_last_group; - unsigned long s_mb_last_start; - - /* history to debug policy */ - struct ext4_mb_history *s_mb_history; - int s_mb_history_cur; - int s_mb_history_max; - int s_mb_history_num; - spinlock_t s_mb_history_lock; - int s_mb_history_filter; - - /* stats for buddy allocator */ - spinlock_t s_mb_pa_lock; - atomic_t s_bal_reqs; /* number of reqs with len > 1 */ - atomic_t s_bal_success; /* we found long enough chunks */ - atomic_t s_bal_allocated; /* in blocks */ - atomic_t s_bal_ex_scanned; /* total extents scanned */ - atomic_t s_bal_goals; /* goal hits */ - atomic_t s_bal_breaks; /* too long searches */ - atomic_t s_bal_2orders; /* 2^order hits */ - spinlock_t s_bal_lock; - unsigned long s_mb_buddies_generated; - unsigned long long s_mb_generation_time; - atomic_t s_mb_lost_chunks; - atomic_t s_mb_preallocated; - atomic_t s_mb_discarded; - - /* locality groups */ - struct ext4_locality_group *s_locality_groups; - - /* for write statistics */ - unsigned long s_sectors_written_start; - u64 s_kbytes_written; - - unsigned int s_log_groups_per_flex; - struct flex_groups *s_flex_groups; -}; - -static inline spinlock_t * -sb_bgl_lock(struct ext4_sb_info *sbi, unsigned int block_group) -{ - return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group); -} - -#endif /* _EXT4_SB */ From 596397b77c895d0fa3674f579c94ad5ea88ef01d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 1 May 2009 13:49:15 -0400 Subject: [PATCH 17/49] ext4: Move fs/ext4/namei.h into ext4.h The fs/ext4/namei.h header file had only a single function declaration, and should have never been a standalone file. Move it into ext4.h, where should have been from the beginning. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + fs/ext4/namei.c | 1 - fs/ext4/namei.h | 8 -------- fs/ext4/super.c | 1 - 4 files changed, 1 insertion(+), 10 deletions(-) delete mode 100644 fs/ext4/namei.h diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index af3c906e705b..d9c5251d082c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1594,6 +1594,7 @@ extern const struct file_operations ext4_file_operations; /* namei.c */ extern const struct inode_operations ext4_dir_inode_operations; extern const struct inode_operations ext4_special_inode_operations; +extern struct dentry *ext4_get_parent(struct dentry *child); /* symlink.c */ extern const struct inode_operations ext4_symlink_inode_operations; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 8018e49a7287..c9690b250e5e 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -37,7 +37,6 @@ #include "ext4.h" #include "ext4_jbd2.h" -#include "namei.h" #include "xattr.h" #include "acl.h" diff --git a/fs/ext4/namei.h b/fs/ext4/namei.h deleted file mode 100644 index 5e4dfff36a00..000000000000 --- a/fs/ext4/namei.h +++ /dev/null @@ -1,8 +0,0 @@ -/* linux/fs/ext4/namei.h - * - * Copyright (C) 2005 Simtec Electronics - * Ben Dooks - * -*/ - -extern struct dentry *ext4_get_parent(struct dentry *child); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1fbf0906ae2e..d79e1c428b4a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -46,7 +46,6 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" -#include "namei.h" #include "group.h" struct proc_dir_entry *ext4_proc_root; From bb23c20a851a5038b255a3c0d0aa56093c1da3f8 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 1 May 2009 19:44:44 -0400 Subject: [PATCH 18/49] ext4: Move fs/ext4/group.h into ext4.h Move the function prototypes in group.h into ext4.h so they are all defined in one place. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 1 - fs/ext4/ext4.h | 17 +++++++++++++++++ fs/ext4/group.h | 29 ----------------------------- fs/ext4/ialloc.c | 1 - fs/ext4/mballoc.h | 1 - fs/ext4/resize.c | 1 - fs/ext4/super.c | 1 - 7 files changed, 17 insertions(+), 34 deletions(-) delete mode 100644 fs/ext4/group.h diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index a5ba039850c5..92f557d957d9 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -19,7 +19,6 @@ #include #include "ext4.h" #include "ext4_jbd2.h" -#include "group.h" #include "mballoc.h" /* diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d9c5251d082c..5973f3261b0c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1270,6 +1270,14 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, struct buffer_head ** bh); extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); +struct buffer_head *ext4_read_block_bitmap(struct super_block *sb, + ext4_group_t block_group); +extern unsigned ext4_init_block_bitmap(struct super_block *sb, + struct buffer_head *bh, + ext4_group_t group, + struct ext4_group_desc *desc); +#define ext4_free_blocks_after_init(sb, group, desc) \ + ext4_init_block_bitmap(sb, NULL, group, desc) /* dir.c */ extern int ext4_check_dir_entry(const char *, struct inode *, @@ -1294,6 +1302,11 @@ extern struct inode * ext4_orphan_get(struct super_block *, unsigned long); extern unsigned long ext4_count_free_inodes(struct super_block *); extern unsigned long ext4_count_dirs(struct super_block *); extern void ext4_check_inodes_bitmap(struct super_block *); +extern unsigned ext4_init_inode_bitmap(struct super_block *sb, + struct buffer_head *bh, + ext4_group_t group, + struct ext4_group_desc *desc); +extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap); /* mballoc.c */ extern long ext4_mb_stats; @@ -1417,6 +1430,10 @@ extern void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); +extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group, + struct ext4_group_desc *gdp); +extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group, + struct ext4_group_desc *gdp); static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { diff --git a/fs/ext4/group.h b/fs/ext4/group.h deleted file mode 100644 index c2c0a8d06d0e..000000000000 --- a/fs/ext4/group.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * linux/fs/ext4/group.h - * - * Copyright (C) 2007 Cluster File Systems, Inc - * - * Author: Andreas Dilger - */ - -#ifndef _LINUX_EXT4_GROUP_H -#define _LINUX_EXT4_GROUP_H - -extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group, - struct ext4_group_desc *gdp); -extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group, - struct ext4_group_desc *gdp); -struct buffer_head *ext4_read_block_bitmap(struct super_block *sb, - ext4_group_t block_group); -extern unsigned ext4_init_block_bitmap(struct super_block *sb, - struct buffer_head *bh, - ext4_group_t group, - struct ext4_group_desc *desc); -#define ext4_free_blocks_after_init(sb, group, desc) \ - ext4_init_block_bitmap(sb, NULL, group, desc) -extern unsigned ext4_init_inode_bitmap(struct super_block *sb, - struct buffer_head *bh, - ext4_group_t group, - struct ext4_group_desc *desc); -extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap); -#endif /* _LINUX_EXT4_GROUP_H */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 55ba419ca00b..916d05c881ca 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -27,7 +27,6 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" -#include "group.h" /* * ialloc.c contains the inodes allocation and deallocation routines diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index dd9e6cd5f6cf..75e34f69215b 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -23,7 +23,6 @@ #include #include "ext4_jbd2.h" #include "ext4.h" -#include "group.h" /* * with AGGRESSIVE_CHECK allocator runs consistency checks over diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index e8ded13b5cb1..27eb289eea37 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -15,7 +15,6 @@ #include #include "ext4_jbd2.h" -#include "group.h" #define outside(b, first, last) ((b) < (first) || (b) >= (last)) #define inside(b, first, last) ((b) >= (first) && (b) < (last)) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d79e1c428b4a..7903f20c8075 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -46,7 +46,6 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" -#include "group.h" struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; From f40339031b04279c3fdde7ac5fe97db33b2a7694 Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Fri, 1 May 2009 20:27:20 -0400 Subject: [PATCH 19/49] ext4: Make the length of the mb_history file tunable In memory-constrained systems with many partitions, the ~68K for each partition for the mb_history buffer can be excessive. This patch adds a new mount option, mb_history_length, as well as a way of setting the default via a module parameter (or via a sysfs parameter in /sys/module/ext4/parameter/default_mb_history_length). If the mb_history_length is set to zero, the mb_history facility is disabled entirely. Signed-off-by: Curt Wohlgemuth Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 13 +++++++------ fs/ext4/super.c | 18 +++++++++++++++++- 2 files changed, 24 insertions(+), 7 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index dbd47eac13ec..df75855ae6f7 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2413,7 +2413,8 @@ static void ext4_mb_history_release(struct super_block *sb) if (sbi->s_proc != NULL) { remove_proc_entry("mb_groups", sbi->s_proc); - remove_proc_entry("mb_history", sbi->s_proc); + if (sbi->s_mb_history_max) + remove_proc_entry("mb_history", sbi->s_proc); } kfree(sbi->s_mb_history); } @@ -2424,17 +2425,17 @@ static void ext4_mb_history_init(struct super_block *sb) int i; if (sbi->s_proc != NULL) { - proc_create_data("mb_history", S_IRUGO, sbi->s_proc, - &ext4_mb_seq_history_fops, sb); + if (sbi->s_mb_history_max) + proc_create_data("mb_history", S_IRUGO, sbi->s_proc, + &ext4_mb_seq_history_fops, sb); proc_create_data("mb_groups", S_IRUGO, sbi->s_proc, &ext4_mb_seq_groups_fops, sb); } - sbi->s_mb_history_max = 1000; sbi->s_mb_history_cur = 0; spin_lock_init(&sbi->s_mb_history_lock); i = sbi->s_mb_history_max * sizeof(struct ext4_mb_history); - sbi->s_mb_history = kzalloc(i, GFP_KERNEL); + sbi->s_mb_history = i ? kzalloc(i, GFP_KERNEL) : NULL; /* if we can't allocate history, then we simple won't use it */ } @@ -2444,7 +2445,7 @@ ext4_mb_store_history(struct ext4_allocation_context *ac) struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_mb_history h; - if (unlikely(sbi->s_mb_history == NULL)) + if (sbi->s_mb_history == NULL) return; if (!(ac->ac_op & sbi->s_mb_history_filter)) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 7903f20c8075..39223a52bc71 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -47,6 +47,13 @@ #include "xattr.h" #include "acl.h" +static int default_mb_history_length = 1000; + +module_param_named(default_mb_history_length, default_mb_history_length, + int, 0644); +MODULE_PARM_DESC(default_mb_history_length, + "Default number of entries saved for mb_history"); + struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; @@ -1042,7 +1049,7 @@ enum { Opt_journal_update, Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, - Opt_data_err_abort, Opt_data_err_ignore, + Opt_data_err_abort, Opt_data_err_ignore, Opt_mb_history_length, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize, @@ -1088,6 +1095,7 @@ static const match_table_t tokens = { {Opt_data_writeback, "data=writeback"}, {Opt_data_err_abort, "data_err=abort"}, {Opt_data_err_ignore, "data_err=ignore"}, + {Opt_mb_history_length, "mb_history_length=%u"}, {Opt_offusrjquota, "usrjquota="}, {Opt_usrjquota, "usrjquota=%s"}, {Opt_offgrpjquota, "grpjquota="}, @@ -1329,6 +1337,13 @@ static int parse_options(char *options, struct super_block *sb, case Opt_data_err_ignore: clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT); break; + case Opt_mb_history_length: + if (match_int(&args[0], &option)) + return 0; + if (option < 0) + return 0; + sbi->s_mb_history_max = option; + break; #ifdef CONFIG_QUOTA case Opt_usrjquota: qtype = USRQUOTA; @@ -2345,6 +2360,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; + sbi->s_mb_history_max = default_mb_history_length; set_opt(sbi->s_mount_opt, BARRIER); From abc8746eb91fb01e8d411896f80f7687c0d8372e Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sat, 2 May 2009 22:54:32 -0400 Subject: [PATCH 20/49] ext4: hook fiemap operation for directories Add fiemap callback for directories Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/namei.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index c9690b250e5e..f2bc160463b7 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2534,6 +2534,7 @@ const struct inode_operations ext4_dir_inode_operations = { .removexattr = generic_removexattr, #endif .permission = ext4_permission, + .fiemap = ext4_fiemap, }; const struct inode_operations ext4_special_inode_operations = { From 19ba0559f9ce104171ab16706893ce01f03ef116 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 13 May 2009 18:12:05 -0400 Subject: [PATCH 21/49] vfs: Enable FS_IOC_FIEMAP and FIGETBSZ for all filetypes The fiemap and get_blk_size ioctls should be enabled even for directories. So move it outisde file_ioctl. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ioctl.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/fs/ioctl.c b/fs/ioctl.c index 82d9c42b8bac..286f38dfc6c0 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -414,10 +414,6 @@ static int file_ioctl(struct file *filp, unsigned int cmd, switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); - case FS_IOC_FIEMAP: - return ioctl_fiemap(filp, arg); - case FIGETBSZ: - return put_user(inode->i_sb->s_blocksize, p); case FIONREAD: return put_user(i_size_read(inode) - filp->f_pos, p); } @@ -557,6 +553,16 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, error = ioctl_fsthaw(filp); break; + case FS_IOC_FIEMAP: + return ioctl_fiemap(filp, arg); + + case FIGETBSZ: + { + struct inode *inode = filp->f_path.dentry->d_inode; + int __user *p = (int __user *)arg; + return put_user(inode->i_sb->s_blocksize, p); + } + default: if (S_ISREG(filp->f_path.dentry->d_inode->i_mode)) error = file_ioctl(filp, cmd, arg); From c9877b205f6ce7943bb95281342f4001cc1c00ec Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 1 May 2009 23:32:06 -0400 Subject: [PATCH 22/49] ext4: fix for fiemap last-block test Carl Henrik Lunde reported and debugged this; the test for the last allocated block was comparing bytes to blocks in this test: if (logical + length - 1 == EXT_MAX_BLOCK || ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK) flags |= FIEMAP_EXTENT_LAST; so any extent which ended right at 4G was stopping the extent walk. Just replacing these values with the extent block & length should fix it. Also give blksize_bits a saner type, and reverse the order of the tests to make the more likely case tested first. Signed-off-by: Eric Sandeen Reported-by: Carl Henrik Lunde Tested-by: Carl Henrik Lunde Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index ea5c47608cea..5f7295287de1 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3196,7 +3196,7 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, void *data) { struct fiemap_extent_info *fieinfo = data; - unsigned long blksize_bits = inode->i_sb->s_blocksize_bits; + unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; __u64 logical; __u64 physical; __u64 length; @@ -3243,8 +3243,8 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, * * XXX this might miss a single-block extent at EXT_MAX_BLOCK */ - if (logical + length - 1 == EXT_MAX_BLOCK || - ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK) + if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK || + newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) flags |= FIEMAP_EXTENT_LAST; error = fiemap_fill_next_extent(fieinfo, logical, physical, From eefd7f03b86b8a319890e7fac5a6fcc7f8694b76 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 2 May 2009 19:05:37 -0400 Subject: [PATCH 23/49] ext4: fix the length returned by fiemap for an unallocated extent If the file's blocks have not yet been allocated because of delayed allocation, the length of the extent returned by fiemap is incorrect. This commit fixes this bug. Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5f7295287de1..4fec6b746382 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3244,8 +3244,15 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, * XXX this might miss a single-block extent at EXT_MAX_BLOCK */ if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK || - newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) + newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) { + loff_t size = i_size_read(inode); + loff_t bs = EXT4_BLOCK_SIZE(inode->i_sb); + flags |= FIEMAP_EXTENT_LAST; + if ((flags & FIEMAP_EXTENT_DELALLOC) && + logical+length > size) + length = (size - logical + bs - 1) & ~(bs-1); + } error = fiemap_fill_next_extent(fieinfo, logical, physical, length, flags); From 955ce5f5be67dfe0d1d096b543af33fe8a1ce3dd Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sat, 2 May 2009 20:35:09 -0400 Subject: [PATCH 24/49] ext4: Convert ext4_lock_group to use sb_bgl_lock We have sb_bgl_lock() and ext4_group_info.bb_state bit spinlock to protech group information. The later is only used within mballoc code. Consolidate them to use sb_bgl_lock(). This makes the mballoc.c code much simpler and also avoid confusion with two locks protecting same info. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 12 ++++---- fs/ext4/ext4.h | 26 ++++++---------- fs/ext4/ialloc.c | 29 +++++++++--------- fs/ext4/mballoc.c | 78 ++++++++++++++++------------------------------- fs/ext4/super.c | 6 ++-- 5 files changed, 59 insertions(+), 92 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 92f557d957d9..e2126d70dff5 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -326,16 +326,16 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) unlock_buffer(bh); return bh; } - spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { ext4_init_block_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_unlock_group(sb, block_group); unlock_buffer(bh); return bh; } - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_unlock_group(sb, block_group); if (buffer_uptodate(bh)) { /* * if not uninit if bh is uptodate, @@ -451,7 +451,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, down_write(&grp->alloc_sem); for (i = 0, blocks_freed = 0; i < count; i++) { BUFFER_TRACE(bitmap_bh, "clear bit"); - if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group), + if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group), bit + i, bitmap_bh->b_data)) { ext4_error(sb, __func__, "bit already cleared for block %llu", @@ -461,11 +461,11 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, blocks_freed++; } } - spin_lock(sb_bgl_lock(sbi, block_group)); + ext4_lock_group(sb, block_group); blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc); ext4_free_blks_set(sb, desc, blk_free_count); desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc); - spin_unlock(sb_bgl_lock(sbi, block_group)); + ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed); if (sbi->s_log_groups_per_flex) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5973f3261b0c..149e02dc3606 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -963,12 +963,6 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) (ino >= EXT4_FIRST_INO(sb) && ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } - -static inline spinlock_t * -sb_bgl_lock(struct ext4_sb_info *sbi, unsigned int block_group) -{ - return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group); -} #else /* Assume that user mode programs are passing in an ext4fs superblock, not * a kernel struct super_block. This will allow us to call the feature-test @@ -1568,33 +1562,31 @@ struct ext4_group_info { }; #define EXT4_GROUP_INFO_NEED_INIT_BIT 0 -#define EXT4_GROUP_INFO_LOCKED_BIT 1 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) +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); +} + static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info *grinfo = ext4_get_group_info(sb, group); - - bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state)); + spin_lock(ext4_group_lock_ptr(sb, group)); } static inline void ext4_unlock_group(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info *grinfo = ext4_get_group_info(sb, group); - - bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state)); + spin_unlock(ext4_group_lock_ptr(sb, group)); } static inline int ext4_is_group_locked(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info *grinfo = ext4_get_group_info(sb, group); - - return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT, - &(grinfo->bb_state)); + return spin_is_locked(ext4_group_lock_ptr(sb, group)); } /* diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 916d05c881ca..82f7d1d7eae0 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -122,16 +122,16 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) unlock_buffer(bh); return bh; } - spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { ext4_init_inode_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_unlock_group(sb, block_group); unlock_buffer(bh); return bh; } - spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group)); + ext4_unlock_group(sb, block_group); if (buffer_uptodate(bh)) { /* * if not uninit if bh is uptodate, @@ -246,9 +246,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) goto error_return; /* Ok, now we can actually update the inode bitmaps.. */ - spin_lock(sb_bgl_lock(sbi, block_group)); - cleared = ext4_clear_bit(bit, bitmap_bh->b_data); - spin_unlock(sb_bgl_lock(sbi, block_group)); + cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group), + bit, bitmap_bh->b_data); if (!cleared) ext4_error(sb, "ext4_free_inode", "bit already cleared for inode %lu", ino); @@ -260,7 +259,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) if (fatal) goto error_return; if (gdp) { - spin_lock(sb_bgl_lock(sbi, block_group)); + ext4_lock_group(sb, block_group); count = ext4_free_inodes_count(sb, gdp) + 1; ext4_free_inodes_set(sb, gdp, count); if (is_directory) { @@ -276,7 +275,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) } gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); - spin_unlock(sb_bgl_lock(sbi, block_group)); + ext4_unlock_group(sb, block_group); percpu_counter_inc(&sbi->s_freeinodes_counter); if (is_directory) percpu_counter_dec(&sbi->s_dirs_counter); @@ -707,10 +706,10 @@ static int find_group_other(struct super_block *sb, struct inode *parent, /* * claim the inode from the inode bitmap. If the group - * is uninit we need to take the groups's sb_bgl_lock + * is uninit we need to take the groups's ext4_group_lock * and clear the uninit flag. The inode bitmap update * and group desc uninit flag clear should be done - * after holding sb_bgl_lock so that ext4_read_inode_bitmap + * after holding ext4_group_lock so that ext4_read_inode_bitmap * doesn't race with the ext4_claim_inode */ static int ext4_claim_inode(struct super_block *sb, @@ -721,7 +720,7 @@ static int ext4_claim_inode(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); - spin_lock(sb_bgl_lock(sbi, group)); + ext4_lock_group(sb, group); if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) { /* not a free inode */ retval = 1; @@ -730,7 +729,7 @@ static int ext4_claim_inode(struct super_block *sb, ino++; if ((group == 0 && ino < EXT4_FIRST_INO(sb)) || ino > EXT4_INODES_PER_GROUP(sb)) { - spin_unlock(sb_bgl_lock(sbi, group)); + ext4_unlock_group(sb, group); ext4_error(sb, __func__, "reserved inode or inode > inodes count - " "block_group = %u, inode=%lu", group, @@ -779,7 +778,7 @@ static int ext4_claim_inode(struct super_block *sb, } gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); err_ret: - spin_unlock(sb_bgl_lock(sbi, group)); + ext4_unlock_group(sb, group); return retval; } @@ -935,7 +934,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) } free = 0; - spin_lock(sb_bgl_lock(sbi, group)); + ext4_lock_group(sb, group); /* recheck and clear flag under lock if we still need to */ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { free = ext4_free_blocks_after_init(sb, group, gdp); @@ -944,7 +943,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); } - spin_unlock(sb_bgl_lock(sbi, group)); + ext4_unlock_group(sb, group); /* Don't need to dirty bitmap block if we didn't change it */ if (free) { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index df75855ae6f7..e76459cedcdb 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -372,24 +372,12 @@ static inline void mb_set_bit(int bit, void *addr) ext4_set_bit(bit, addr); } -static inline void mb_set_bit_atomic(spinlock_t *lock, int bit, void *addr) -{ - addr = mb_correct_addr_and_bit(&bit, addr); - ext4_set_bit_atomic(lock, bit, addr); -} - static inline void mb_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_clear_bit(bit, addr); } -static inline void mb_clear_bit_atomic(spinlock_t *lock, int bit, void *addr) -{ - addr = mb_correct_addr_and_bit(&bit, addr); - ext4_clear_bit_atomic(lock, bit, addr); -} - static inline int mb_find_next_zero_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; @@ -803,17 +791,17 @@ static int ext4_mb_init_cache(struct page *page, char *incore) unlock_buffer(bh[i]); continue; } - spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i)); + ext4_lock_group(sb, first_group + i); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { ext4_init_block_bitmap(sb, bh[i], first_group + i, desc); set_bitmap_uptodate(bh[i]); set_buffer_uptodate(bh[i]); - spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i)); + ext4_unlock_group(sb, first_group + i); unlock_buffer(bh[i]); continue; } - spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i)); + ext4_unlock_group(sb, first_group + i); if (buffer_uptodate(bh[i])) { /* * if not uninit if bh is uptodate, @@ -1080,7 +1068,7 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) return 0; } -static void mb_clear_bits(spinlock_t *lock, void *bm, int cur, int len) +static void mb_clear_bits(void *bm, int cur, int len) { __u32 *addr; @@ -1093,15 +1081,12 @@ static void mb_clear_bits(spinlock_t *lock, void *bm, int cur, int len) cur += 32; continue; } - if (lock) - mb_clear_bit_atomic(lock, cur, bm); - else - mb_clear_bit(cur, bm); + mb_clear_bit(cur, bm); cur++; } } -static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len) +static void mb_set_bits(void *bm, int cur, int len) { __u32 *addr; @@ -1114,10 +1099,7 @@ static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len) cur += 32; continue; } - if (lock) - mb_set_bit_atomic(lock, cur, bm); - else - mb_set_bit(cur, bm); + mb_set_bit(cur, bm); cur++; } } @@ -1332,8 +1314,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) e4b->bd_info->bb_counters[ord]++; } - mb_set_bits(sb_bgl_lock(EXT4_SB(e4b->bd_sb), ex->fe_group), - EXT4_MB_BITMAP(e4b), ex->fe_start, len0); + mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0); mb_check_buddy(e4b); return ret; @@ -2756,7 +2737,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) return 0; } -/* need to called with ext4 group lock (ext4_lock_group) */ +/* need to called with the ext4 group lock held */ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp) { struct ext4_prealloc_space *pa; @@ -2993,14 +2974,17 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, * Fix the bitmap and repeat the block allocation * We leak some of the blocks here. */ - mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group), - bitmap_bh->b_data, ac->ac_b_ex.fe_start, - ac->ac_b_ex.fe_len); + ext4_lock_group(sb, ac->ac_b_ex.fe_group); + mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, + ac->ac_b_ex.fe_len); + ext4_unlock_group(sb, ac->ac_b_ex.fe_group); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!err) err = -EAGAIN; goto out_err; } + + ext4_lock_group(sb, ac->ac_b_ex.fe_group); #ifdef AGGRESSIVE_CHECK { int i; @@ -3010,9 +2994,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, } } #endif - spin_lock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group)); - mb_set_bits(NULL, bitmap_bh->b_data, - ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len); + mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,ac->ac_b_ex.fe_len); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_blks_set(sb, gdp, @@ -3022,7 +3004,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len; ext4_free_blks_set(sb, gdp, len); gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp); - spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group)); + + ext4_unlock_group(sb, ac->ac_b_ex.fe_group); percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative @@ -3455,7 +3438,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) * the function goes through all block freed in the group * but not yet committed and marks them used in in-core bitmap. * buddy must be generated from this bitmap - * Need to be called with ext4 group lock (ext4_lock_group) + * Need to be called with the ext4 group lock held */ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group) @@ -3469,9 +3452,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, while (n) { entry = rb_entry(n, struct ext4_free_data, node); - mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group), - bitmap, entry->start_blk, - entry->count); + mb_set_bits(bitmap, entry->start_blk, entry->count); n = rb_next(n); } return; @@ -3480,7 +3461,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, /* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap - * Need to be called with ext4 group lock (ext4_lock_group) + * Need to be called with ext4 group lock held */ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group) @@ -3512,8 +3493,7 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); - mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group), - bitmap, start, len); + mb_set_bits(bitmap, start, len); preallocated += len; count++; } @@ -4856,29 +4836,25 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode, new_entry->group = block_group; new_entry->count = count; new_entry->t_tid = handle->h_transaction->t_tid; + ext4_lock_group(sb, block_group); - mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data, - bit, count); + mb_clear_bits(bitmap_bh->b_data, bit, count); ext4_mb_free_metadata(handle, &e4b, new_entry); - ext4_unlock_group(sb, block_group); } else { - ext4_lock_group(sb, block_group); /* need to update group_info->bb_free and bitmap * with group lock held. generate_buddy look at * them with group lock_held */ - mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data, - bit, count); + ext4_lock_group(sb, block_group); + mb_clear_bits(bitmap_bh->b_data, bit, count); mb_free_blocks(inode, &e4b, bit, count); ext4_mb_return_to_preallocation(inode, &e4b, block, count); - ext4_unlock_group(sb, block_group); } - spin_lock(sb_bgl_lock(sbi, block_group)); ret = ext4_free_blks_count(sb, gdp) + count; ext4_free_blks_set(sb, gdp, ret); gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); - spin_unlock(sb_bgl_lock(sbi, block_group)); + ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeblocks_counter, count); if (sbi->s_log_groups_per_flex) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 39223a52bc71..dc34ed3d1327 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1784,18 +1784,18 @@ static int ext4_check_descriptors(struct super_block *sb) "(block %llu)!\n", i, inode_table); return 0; } - spin_lock(sb_bgl_lock(sbi, i)); + ext4_lock_group(sb, i); if (!ext4_group_desc_csum_verify(sbi, i, gdp)) { printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " "Checksum for group %u failed (%u!=%u)\n", i, le16_to_cpu(ext4_group_desc_csum(sbi, i, gdp)), le16_to_cpu(gdp->bg_checksum)); if (!(sb->s_flags & MS_RDONLY)) { - spin_unlock(sb_bgl_lock(sbi, i)); + ext4_unlock_group(sb, i); return 0; } } - spin_unlock(sb_bgl_lock(sbi, i)); + ext4_unlock_group(sb, i); if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); } From bc8e67409ccdcff72c3f1656b1fb1aad7ff396db Mon Sep 17 00:00:00 2001 From: Vincent Minet Date: Fri, 15 May 2009 08:33:18 -0400 Subject: [PATCH 25/49] ext4: Fix spinlock assertions on UP systems On UP systems without DEBUG_SPINLOCK, ext4_is_group_locked always fails which triggers a BUG_ON() call. This patch fixes it by using assert_spin_locked instead. Signed-off-by: Vincent Minet Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 6 ------ fs/ext4/mballoc.c | 10 +++++----- 2 files changed, 5 insertions(+), 11 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 149e02dc3606..89190ae671f6 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1583,12 +1583,6 @@ static inline void ext4_unlock_group(struct super_block *sb, spin_unlock(ext4_group_lock_ptr(sb, group)); } -static inline int ext4_is_group_locked(struct super_block *sb, - ext4_group_t group) -{ - return spin_is_locked(ext4_group_lock_ptr(sb, group)); -} - /* * Inodes and files operations */ diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index e76459cedcdb..541bd9adffa2 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -436,7 +436,7 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; - BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); for (i = 0; i < count; i++) { if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) { ext4_fsblk_t blocknr; @@ -460,7 +460,7 @@ static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; - BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); for (i = 0; i < count; i++) { BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap)); mb_set_bit(first + i, e4b->bd_info->bb_bitmap); @@ -1115,7 +1115,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct super_block *sb = e4b->bd_sb; BUG_ON(first + count > (sb->s_blocksize << 3)); - BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); @@ -1196,7 +1196,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block, int ord; void *buddy; - BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); BUG_ON(ex == NULL); buddy = mb_find_buddy(e4b, order, &max); @@ -1260,7 +1260,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); - BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group)); + assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); mb_check_buddy(e4b); mb_mark_used_double(e4b, start, len); From f888e652d758bfe0c04c209b72a05972daeba386 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 12 May 2009 00:21:29 -0400 Subject: [PATCH 26/49] ext4: Simplify function signature for ext4_da_get_block_write() The function ext4_da_get_block_write() is called in exactly one write, and the last argument, create, is always 1. Remove it to simplify the code slightly. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4e7f363e3030..476d843610ac 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2000,7 +2000,7 @@ static void ext4_print_free_blocks(struct inode *inode) #define EXT4_DELALLOC_RSVED 1 static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) + struct buffer_head *bh_result) { int ret; unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; @@ -2010,7 +2010,7 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, handle = ext4_journal_current_handle(); BUG_ON(!handle); ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks, - bh_result, create, 0, EXT4_DELALLOC_RSVED); + bh_result, 1, 0, EXT4_DELALLOC_RSVED); if (ret <= 0) return ret; @@ -2088,7 +2088,7 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) if (!new.b_size) return 0; - err = ext4_da_get_block_write(mpd->inode, next, &new, 1); + err = ext4_da_get_block_write(mpd->inode, next, &new); if (err) { /* * If get block returns with error we simply From e4d996ca806e93dddb5d76c0d3d859b494c559f6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 12 May 2009 00:25:28 -0400 Subject: [PATCH 27/49] ext4: Rename ext4_get_blocks_handle() to be ext4_ind_get_blocks() The static function ext4_get_blocks_handle() is badly named. Of *course* it takes a handle. Since its counterpart for extent-based file is ext4_ext_get_blocks(), rename it to be ext4_ind_get_blocks(). Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 476d843610ac..f758e8021d1a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -914,7 +914,7 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode, * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) */ -static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, +static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int maxblocks, struct buffer_head *bh_result, int create, int extend_disksize) @@ -1129,7 +1129,7 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) * mapped. * * If file type is extents based, it will call ext4_ext_get_blocks(), - * Otherwise, call with ext4_get_blocks_handle() to handle indirect mapping + * Otherwise, call with ext4_ind_get_blocks() to handle indirect mapping * based files * * On success, it returns the number of blocks being mapped or allocate. @@ -1160,8 +1160,8 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, retval = ext4_ext_get_blocks(handle, inode, block, max_blocks, bh, 0, 0); } else { - retval = ext4_get_blocks_handle(handle, - inode, block, max_blocks, bh, 0, 0); + retval = ext4_ind_get_blocks(handle, inode, block, max_blocks, + bh, 0, 0); } up_read((&EXT4_I(inode)->i_data_sem)); @@ -1215,7 +1215,7 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, retval = ext4_ext_get_blocks(handle, inode, block, max_blocks, bh, create, extend_disksize); } else { - retval = ext4_get_blocks_handle(handle, inode, block, + retval = ext4_ind_get_blocks(handle, inode, block, max_blocks, bh, create, extend_disksize); if (retval > 0 && buffer_new(bh)) { @@ -1297,7 +1297,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, err = ext4_get_blocks_wrap(handle, inode, block, 1, &dummy, create, 1, 0); /* - * ext4_get_blocks_handle() returns number of blocks + * ext4_get_blocks_wrap() returns number of blocks * mapped. 0 in case of a HOLE. */ if (err > 0) { From 12b7ac176831df1aa58a787e67c3e5d698b30163 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 14 May 2009 00:57:44 -0400 Subject: [PATCH 28/49] ext4: Rename ext4_get_blocks_wrap() to be ext4_get_blocks() Another function rename for clarity's sake. The _wrap prefix simply confuses people, and didn't add much people trying to follow the code paths. Signed-off-by: "Theodore Ts'o" --- fs/ext4/dir.c | 3 +-- fs/ext4/ext4.h | 8 ++++---- fs/ext4/extents.c | 6 +++--- fs/ext4/inode.c | 35 +++++++++++++++++------------------ 4 files changed, 25 insertions(+), 27 deletions(-) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index b64789929a65..052d6378f997 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -131,8 +131,7 @@ static int ext4_readdir(struct file *filp, struct buffer_head *bh = NULL; map_bh.b_state = 0; - err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh, - 0, 0, 0); + err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0, 0, 0); if (err > 0) { pgoff_t index = map_bh.b_blocknr >> (PAGE_CACHE_SHIFT - inode->i_blkbits); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 89190ae671f6..5dc8368e46bc 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1617,10 +1617,10 @@ extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len); -extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, - sector_t block, unsigned int max_blocks, - struct buffer_head *bh, int create, - int extend_disksize, int flag); +extern int ext4_get_blocks(handle_t *handle, struct inode *inode, + sector_t block, unsigned int max_blocks, + struct buffer_head *bh, int create, + int extend_disksize, int flag); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 4fec6b746382..7e7d02dd2739 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3151,9 +3151,9 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len) break; } map_bh.b_state = 0; - ret = ext4_get_blocks_wrap(handle, inode, block, - max_blocks, &map_bh, - EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); + ret = ext4_get_blocks(handle, inode, block, + max_blocks, &map_bh, + EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); if (ret <= 0) { #ifdef EXT4FS_DEBUG WARN_ON(ret <= 0); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f758e8021d1a..a9a9b9b77e8e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1121,7 +1121,7 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) } /* - * The ext4_get_blocks_wrap() function try to look up the requested blocks, + * The ext4_get_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. * * Otherwise it takes the write lock of the i_data_sem and allocate blocks @@ -1142,9 +1142,9 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) * * It returns the error in case of allocation failure. */ -int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, - unsigned int max_blocks, struct buffer_head *bh, - int create, int extend_disksize, int flag) +int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, + unsigned int max_blocks, struct buffer_head *bh, + int create, int extend_disksize, int flag) { int retval; @@ -1268,8 +1268,8 @@ int ext4_get_block(struct inode *inode, sector_t iblock, started = 1; } - ret = ext4_get_blocks_wrap(handle, inode, iblock, - max_blocks, bh_result, create, 0, 0); + ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result, + create, 0, 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -1294,10 +1294,9 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, dummy.b_state = 0; dummy.b_blocknr = -1000; buffer_trace_init(&dummy.b_history); - err = ext4_get_blocks_wrap(handle, inode, block, 1, - &dummy, create, 1, 0); + err = ext4_get_blocks(handle, inode, block, 1, &dummy, create, 1, 0); /* - * ext4_get_blocks_wrap() returns number of blocks + * ext4_get_blocks() returns number of blocks * mapped. 0 in case of a HOLE. */ if (err > 0) { @@ -2009,8 +2008,8 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, handle = ext4_journal_current_handle(); BUG_ON(!handle); - ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks, - bh_result, 1, 0, EXT4_DELALLOC_RSVED); + ret = ext4_get_blocks(handle, inode, iblock, max_blocks, + bh_result, 1, 0, EXT4_DELALLOC_RSVED); if (ret <= 0) return ret; @@ -2067,11 +2066,11 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) /* * We need to make sure the BH_Delay flag is passed down to * ext4_da_get_block_write(), since it calls - * ext4_get_blocks_wrap() with the EXT4_DELALLOC_RSVED flag. - * This flag causes ext4_get_blocks_wrap() to call + * ext4_get_blocks() with the EXT4_DELALLOC_RSVED flag. + * This flag causes ext4_get_blocks() to call * ext4_da_update_reserve_space() if the passed buffer head * has the BH_Delay flag set. In the future, once we clean up - * the interfaces to ext4_get_blocks_wrap(), we should pass in + * the interfaces to ext4_get_blocks(), we should pass in * a separate flag which requests that the delayed allocation * statistics should be updated, instead of depending on the * state information getting passed down via the map_bh's @@ -2363,7 +2362,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, 1, bh_result, 0, 0, 0); if ((ret == 0) && !buffer_delay(bh_result)) { /* the block isn't (pre)allocated yet, let's reserve space */ /* @@ -2407,8 +2406,8 @@ static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, * we don't want to do block allocation in writepage * so call get_block_wrap with create = 0 */ - ret = ext4_get_blocks_wrap(NULL, inode, iblock, max_blocks, - bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, + bh_result, 0, 0, 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -5034,7 +5033,7 @@ int ext4_writepage_trans_blocks(struct inode *inode) * Calculate the journal credits for a chunk of data modification. * * This is called from DIO, fallocate or whoever calling - * ext4_get_blocks_wrap() to map/allocate a chunk of contigous disk blocks. + * ext4_get_blocks() to map/allocate a chunk of contigous disk blocks. * * journal buffers for data blocks are not included here, as DIO * and fallocate do no need to journal data buffers. From c21770573319922e3f3fcb331cfaa290c49f1c81 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 14 May 2009 00:58:52 -0400 Subject: [PATCH 29/49] ext4: Define a new set of flags for ext4_get_blocks() The functions ext4_get_blocks(), ext4_ext_get_blocks(), and ext4_ind_get_blocks() used an ad-hoc set of integer variables used as boolean flags passed in as arguments. Use a single flags parameter and a setandard set of bitfield flags instead. This saves space on the call stack, and it also makes the code a bit more understandable. Signed-off-by: "Theodore Ts'o" --- fs/ext4/dir.c | 2 +- fs/ext4/ext4.h | 22 ++++++++++++------ fs/ext4/extents.c | 22 +++++++++--------- fs/ext4/inode.c | 57 +++++++++++++++++++++++++---------------------- 4 files changed, 57 insertions(+), 46 deletions(-) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 052d6378f997..9dc93168e262 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -131,7 +131,7 @@ static int ext4_readdir(struct file *filp, struct buffer_head *bh = NULL; map_bh.b_state = 0; - err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0, 0, 0); + err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0); if (err > 0) { pgoff_t index = map_bh.b_blocknr >> (PAGE_CACHE_SHIFT - inode->i_blkbits); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5dc8368e46bc..17feb4ac633a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -314,10 +314,20 @@ struct ext4_new_group_data { }; /* - * Following is used by preallocation code to tell get_blocks() that we - * want uninitialzed extents. + * Flags used by ext4_get_blocks() */ -#define EXT4_CREATE_UNINITIALIZED_EXT 2 + /* Allocate any needed blocks and/or convert an unitialized + extent to be an initialized ext4 */ +#define EXT4_GET_BLOCKS_CREATE 1 + /* Request the creation of an unitialized extent */ +#define EXT4_GET_BLOCKS_UNINIT_EXT 2 +#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\ + EXT4_GET_BLOCKS_CREATE) + /* Update the ext4_inode_info i_disksize field */ +#define EXT4_GET_BLOCKS_EXTEND_DISKSIZE 4 + /* Caller is from the delayed allocation writeout path, + so the filesystem blocks have already been accounted for */ +#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 8 /* * ioctl commands @@ -1610,8 +1620,7 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk); extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int max_blocks, - struct buffer_head *bh_result, - int create, int extend_disksize); + struct buffer_head *bh_result, int flags); extern void ext4_ext_truncate(struct inode *); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); @@ -1619,8 +1628,7 @@ extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len); extern int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, unsigned int max_blocks, - struct buffer_head *bh, int create, - int extend_disksize, int flag); + struct buffer_head *bh, int flags); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7e7d02dd2739..27c383c7b43c 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2784,7 +2784,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int max_blocks, struct buffer_head *bh_result, - int create, int extend_disksize) + int flags) { struct ext4_ext_path *path = NULL; struct ext4_extent_header *eh; @@ -2803,7 +2803,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, cache_type = ext4_ext_in_cache(inode, iblock, &newex); if (cache_type) { if (cache_type == EXT4_EXT_CACHE_GAP) { - if (!create) { + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * block isn't allocated yet and * user doesn't want to allocate it @@ -2869,9 +2869,9 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, EXT4_EXT_CACHE_EXTENT); goto out; } - if (create == EXT4_CREATE_UNINITIALIZED_EXT) + if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) goto out; - if (!create) { + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { if (allocated > max_blocks) allocated = max_blocks; /* @@ -2903,7 +2903,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * requested block isn't allocated yet; * we couldn't try to create block if create flag is zero */ - if (!create) { + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * put just found gap into cache to speed up * subsequent requests @@ -2932,10 +2932,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * EXT_UNINIT_MAX_LEN. */ if (max_blocks > EXT_INIT_MAX_LEN && - create != EXT4_CREATE_UNINITIALIZED_EXT) + !(flags & EXT4_GET_BLOCKS_UNINIT_EXT)) max_blocks = EXT_INIT_MAX_LEN; else if (max_blocks > EXT_UNINIT_MAX_LEN && - create == EXT4_CREATE_UNINITIALIZED_EXT) + (flags & EXT4_GET_BLOCKS_UNINIT_EXT)) max_blocks = EXT_UNINIT_MAX_LEN; /* Check if we can really insert (iblock)::(iblock+max_blocks) extent */ @@ -2966,7 +2966,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, /* try to insert new extent into found leaf and return */ ext4_ext_store_pblock(&newex, newblock); newex.ee_len = cpu_to_le16(ar.len); - if (create == EXT4_CREATE_UNINITIALIZED_EXT) /* Mark uninitialized */ + if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) /* Mark uninitialized */ ext4_ext_mark_uninitialized(&newex); err = ext4_ext_insert_extent(handle, inode, path, &newex); if (err) { @@ -2983,7 +2983,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, newblock = ext_pblock(&newex); allocated = ext4_ext_get_actual_len(&newex); outnew: - if (extend_disksize) { + if (flags & EXT4_GET_BLOCKS_EXTEND_DISKSIZE) { disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits; if (disksize > i_size_read(inode)) disksize = i_size_read(inode); @@ -2994,7 +2994,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, set_buffer_new(bh_result); /* Cache only when it is _not_ an uninitialized extent */ - if (create != EXT4_CREATE_UNINITIALIZED_EXT) + if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) ext4_ext_put_in_cache(inode, iblock, allocated, newblock, EXT4_EXT_CACHE_EXTENT); out: @@ -3153,7 +3153,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len) map_bh.b_state = 0; ret = ext4_get_blocks(handle, inode, block, max_blocks, &map_bh, - EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); + EXT4_GET_BLOCKS_CREATE_UNINIT_EXT); if (ret <= 0) { #ifdef EXT4FS_DEBUG WARN_ON(ret <= 0); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a9a9b9b77e8e..8b7564dfacdf 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -917,7 +917,7 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode, static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int maxblocks, struct buffer_head *bh_result, - int create, int extend_disksize) + int flags) { int err = -EIO; ext4_lblk_t offsets[4]; @@ -934,7 +934,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)); - J_ASSERT(handle != NULL || create == 0); + J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); depth = ext4_block_to_path(inode, iblock, offsets, &blocks_to_boundary); @@ -963,7 +963,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, } /* Next simple case - plain lookup or failed read of indirect block */ - if (!create || err == -EIO) + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO) goto cleanup; /* @@ -1002,7 +1002,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, * protect it if you're about to implement concurrent * ext4_get_block() -bzzz */ - if (!err && extend_disksize) { + if (!err && (flags & EXT4_GET_BLOCKS_EXTEND_DISKSIZE)) { disksize = ((loff_t) iblock + count) << inode->i_blkbits; if (disksize > i_size_read(inode)) disksize = i_size_read(inode); @@ -1144,7 +1144,7 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) */ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, unsigned int max_blocks, struct buffer_head *bh, - int create, int extend_disksize, int flag) + int flags) { int retval; @@ -1158,15 +1158,15 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, down_read((&EXT4_I(inode)->i_data_sem)); if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { retval = ext4_ext_get_blocks(handle, inode, block, max_blocks, - bh, 0, 0); + bh, 0); } else { retval = ext4_ind_get_blocks(handle, inode, block, max_blocks, - bh, 0, 0); + bh, 0); } up_read((&EXT4_I(inode)->i_data_sem)); /* If it is only a block(s) look up */ - if (!create) + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) return retval; /* @@ -1205,7 +1205,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, * let the underlying get_block() function know to * avoid double accounting */ - if (flag) + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) EXT4_I(inode)->i_delalloc_reserved_flag = 1; /* * We need to check for EXT4 here because migrate @@ -1213,10 +1213,10 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, */ if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { retval = ext4_ext_get_blocks(handle, inode, block, max_blocks, - bh, create, extend_disksize); + bh, flags); } else { retval = ext4_ind_get_blocks(handle, inode, block, - max_blocks, bh, create, extend_disksize); + max_blocks, bh, flags); if (retval > 0 && buffer_new(bh)) { /* @@ -1229,7 +1229,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, } } - if (flag) { + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { EXT4_I(inode)->i_delalloc_reserved_flag = 0; /* * Update reserved blocks/metadata blocks @@ -1269,7 +1269,7 @@ int ext4_get_block(struct inode *inode, sector_t iblock, } ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result, - create, 0, 0); + create ? EXT4_GET_BLOCKS_CREATE : 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -1288,16 +1288,19 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, { struct buffer_head dummy; int fatal = 0, err; + int flags = EXT4_GET_BLOCKS_EXTEND_DISKSIZE; J_ASSERT(handle != NULL || create == 0); dummy.b_state = 0; dummy.b_blocknr = -1000; buffer_trace_init(&dummy.b_history); - err = ext4_get_blocks(handle, inode, block, 1, &dummy, create, 1, 0); + if (create) + flags |= EXT4_GET_BLOCKS_CREATE; + err = ext4_get_blocks(handle, inode, block, 1, &dummy, flags); /* - * ext4_get_blocks() returns number of blocks - * mapped. 0 in case of a HOLE. + * ext4_get_blocks() returns number of blocks mapped. 0 in + * case of a HOLE. */ if (err > 0) { if (err > 1) @@ -1997,7 +2000,6 @@ static void ext4_print_free_blocks(struct inode *inode) return; } -#define EXT4_DELALLOC_RSVED 1 static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result) { @@ -2009,7 +2011,8 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, handle = ext4_journal_current_handle(); BUG_ON(!handle); ret = ext4_get_blocks(handle, inode, iblock, max_blocks, - bh_result, 1, 0, EXT4_DELALLOC_RSVED); + bh_result, EXT4_GET_BLOCKS_CREATE| + EXT4_GET_BLOCKS_DELALLOC_RESERVE); if (ret <= 0) return ret; @@ -2065,16 +2068,17 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) return 0; /* * We need to make sure the BH_Delay flag is passed down to - * ext4_da_get_block_write(), since it calls - * ext4_get_blocks() with the EXT4_DELALLOC_RSVED flag. - * This flag causes ext4_get_blocks() to call + * ext4_da_get_block_write(), since it calls ext4_get_blocks() + * with the EXT4_GET_BLOCKS_DELALLOC_RESERVE flag. This flag + * causes ext4_get_blocks() to call * ext4_da_update_reserve_space() if the passed buffer head * has the BH_Delay flag set. In the future, once we clean up - * the interfaces to ext4_get_blocks(), we should pass in - * a separate flag which requests that the delayed allocation + * the interfaces to ext4_get_blocks(), we should pass in a + * separate flag which requests that the delayed allocation * statistics should be updated, instead of depending on the * state information getting passed down via the map_bh's - * state bitmasks plus the magic EXT4_DELALLOC_RSVED flag. + * state bitmasks plus the magic + * EXT4_GET_BLOCKS_DELALLOC_RESERVE flag. */ new.b_state = mpd->b_state & (1 << BH_Delay); new.b_blocknr = 0; @@ -2362,7 +2366,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_get_blocks(NULL, inode, iblock, 1, bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, 1, bh_result, 0); if ((ret == 0) && !buffer_delay(bh_result)) { /* the block isn't (pre)allocated yet, let's reserve space */ /* @@ -2406,8 +2410,7 @@ static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, * we don't want to do block allocation in writepage * so call get_block_wrap with create = 0 */ - ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, - bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; From b920c75502cb2c48654ef196d647c8eb81ab608a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 14 May 2009 00:54:29 -0400 Subject: [PATCH 30/49] ext4: Add documentation to the ext4_*get_block* functions This adds more documentation to various internal functions in fs/ext4/inode.c, most notably ext4_ind_get_blocks(), ext4_da_get_block_write(), ext4_da_get_block_prep(), ext4_normal_get_block_write(). In addition, the static function ext4_normal_get_block_write() has been renamed noalloc_get_block_write(), since it is used in many places far beyond ext4_normal_writepage(). Plenty of warnings have been added to the noalloc_get_block_write() function, since the way it is used is amazingly fragile. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 86 +++++++++++++++++++++++++++++++------------------ 1 file changed, 55 insertions(+), 31 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8b7564dfacdf..fd5f27a9b81b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -892,6 +892,10 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode, } /* + * The ext4_ind_get_blocks() function handles non-extents inodes + * (i.e., using the traditional indirect/double-indirect i_blocks + * scheme) for ext4_get_blocks(). + * * Allocation strategy is simple: if we have to allocate something, we will * have to go the whole way to leaf. So let's do it before attaching anything * to tree, set linkage between the newborn blocks, write them if sync is @@ -909,10 +913,11 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode, * return = 0, if plain lookup failed. * return < 0, error case. * - * - * Need to be called with - * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block - * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) + * The ext4_ind_get_blocks() function should be called with + * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem + * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or + * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system + * blocks. */ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int maxblocks, @@ -1152,8 +1157,8 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, clear_buffer_unwritten(bh); /* - * Try to see if we can get the block without requesting - * for new file system block. + * Try to see if we can get the block without requesting a new + * file system block. */ down_read((&EXT4_I(inode)->i_data_sem)); if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { @@ -2000,6 +2005,12 @@ static void ext4_print_free_blocks(struct inode *inode) return; } +/* + * This function is used by mpage_da_map_blocks(). We separate it out + * as a separate function just to make life easier, and because + * mpage_da_map_blocks() used to be a generic function that took a + * get_block_t. + */ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result) { @@ -2031,8 +2042,8 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, /* * Update on-disk size along with block allocation we don't - * use 'extend_disksize' as size may change within already - * allocated block -bzzz + * use EXT4_GET_BLOCKS_EXTEND_DISKSIZE as size may change + * within already allocated block -bzzz */ disksize = ((loff_t) iblock + ret) << inode->i_blkbits; if (disksize > i_size_read(inode)) @@ -2338,8 +2349,9 @@ static int __mpage_da_writepage(struct page *page, } /* - * this is a special callback for ->write_begin() only - * it's intention is to return mapped block or reserve space + * This is a special get_blocks_t callback which is used by + * ext4_da_write_begin(). It will either return mapped block or + * reserve space for a single block. * * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set. * We also have b_blocknr = -1 and b_bdev initialized properly @@ -2347,7 +2359,6 @@ static int __mpage_da_writepage(struct page *page, * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set. * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev * initialized properly. - * */ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) @@ -2400,7 +2411,23 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return ret; } -static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, +/* + * This function is used as a standard get_block_t calback function + * when there is no desire to allocate any blocks. It is used as a + * callback function for block_prepare_write(), nobh_writepage(), and + * block_write_full_page(). These functions should only try to map a + * single block at a time. + * + * Since this function doesn't do block allocations even if the caller + * requests it by passing in create=1, it is critically important that + * any caller checks to make sure that any buffer heads are returned + * by this function are either all already mapped or marked for + * delayed allocation before calling nobh_writepage() or + * block_write_full_page(). Otherwise, b_blocknr could be left + * unitialized, and the page write functions will be taken by + * surprise. + */ +static int noalloc_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret = 0; @@ -2419,10 +2446,11 @@ static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, } /* - * get called vi ext4_da_writepages after taking page lock (have journal handle) - * get called via journal_submit_inode_data_buffers (no journal handle) - * get called via shrink_page_list via pdflush (no journal handle) - * or grab_page_cache when doing write_begin (have journal handle) + * This function can get called via... + * - ext4_da_writepages after taking page lock (have journal handle) + * - journal_submit_inode_data_buffers (no journal handle) + * - shrink_page_list via pdflush (no journal handle) + * - grab_page_cache when doing write_begin (have journal handle) */ static int ext4_da_writepage(struct page *page, struct writeback_control *wbc) @@ -2473,7 +2501,7 @@ static int ext4_da_writepage(struct page *page, * do block allocation here. */ ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, - ext4_normal_get_block_write); + noalloc_get_block_write); if (!ret) { page_bufs = page_buffers(page); /* check whether all are mapped and non delay */ @@ -2498,11 +2526,10 @@ static int ext4_da_writepage(struct page *page, } if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) - ret = nobh_writepage(page, ext4_normal_get_block_write, wbc); + ret = nobh_writepage(page, noalloc_get_block_write, wbc); else - ret = block_write_full_page(page, - ext4_normal_get_block_write, - wbc); + ret = block_write_full_page(page, noalloc_get_block_write, + wbc); return ret; } @@ -2814,7 +2841,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, *pagep = page; ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - ext4_da_get_block_prep); + ext4_da_get_block_prep); if (ret < 0) { unlock_page(page); ext4_journal_stop(handle); @@ -3122,12 +3149,10 @@ static int __ext4_normal_writepage(struct page *page, struct inode *inode = page->mapping->host; if (test_opt(inode->i_sb, NOBH)) - return nobh_writepage(page, - ext4_normal_get_block_write, wbc); + return nobh_writepage(page, noalloc_get_block_write, wbc); else - return block_write_full_page(page, - ext4_normal_get_block_write, - wbc); + return block_write_full_page(page, noalloc_get_block_write, + wbc); } static int ext4_normal_writepage(struct page *page, @@ -3179,7 +3204,7 @@ static int __ext4_journalled_writepage(struct page *page, int err; ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, - ext4_normal_get_block_write); + noalloc_get_block_write); if (ret != 0) goto out_unlock; @@ -3264,9 +3289,8 @@ static int ext4_journalled_writepage(struct page *page, * really know unless we go poke around in the buffer_heads. * But block_write_full_page will do the right thing. */ - return block_write_full_page(page, - ext4_normal_get_block_write, - wbc); + return block_write_full_page(page, noalloc_get_block_write, + wbc); } no_write: redirty_page_for_writepage(wbc, page); From a2dc52b5d1d8cc280b3e795abf1c80ac8c49f30c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 12 May 2009 13:51:29 -0400 Subject: [PATCH 31/49] ext4: Add BUG_ON debugging checks to noalloc_get_block_write() Enforce that noalloc_get_block_write() is only called to map one block at a time, and that it always is successful in finding a mapping for given an inode's logical block block number if it is called with create == 1. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fd5f27a9b81b..e6113c3a126f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2433,11 +2433,14 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock, int ret = 0; unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; + BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize); + /* * we don't want to do block allocation in writepage * so call get_block_wrap with create = 0 */ ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0); + BUG_ON(create && ret == 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; From 2fa3cdfb319055fd8b25abdafa413e16f00ad493 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 14 May 2009 09:29:45 -0400 Subject: [PATCH 32/49] ext4: Merge ext4_da_get_block_write() into mpage_da_map_blocks() The static function ext4_da_get_block_write() was only used by mpage_da_map_blocks(). So to simplify the code, merge that function into mpage_da_map_blocks(). Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 110 +++++++++++++++++++----------------------------- 1 file changed, 43 insertions(+), 67 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e6113c3a126f..bfe50a22363b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2005,57 +2005,6 @@ static void ext4_print_free_blocks(struct inode *inode) return; } -/* - * This function is used by mpage_da_map_blocks(). We separate it out - * as a separate function just to make life easier, and because - * mpage_da_map_blocks() used to be a generic function that took a - * get_block_t. - */ -static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result) -{ - int ret; - unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; - loff_t disksize = EXT4_I(inode)->i_disksize; - handle_t *handle = NULL; - - handle = ext4_journal_current_handle(); - BUG_ON(!handle); - ret = ext4_get_blocks(handle, inode, iblock, max_blocks, - bh_result, EXT4_GET_BLOCKS_CREATE| - EXT4_GET_BLOCKS_DELALLOC_RESERVE); - if (ret <= 0) - return ret; - - bh_result->b_size = (ret << inode->i_blkbits); - - if (ext4_should_order_data(inode)) { - int retval; - retval = ext4_jbd2_file_inode(handle, inode); - if (retval) - /* - * Failed to add inode for ordered mode. Don't - * update file size - */ - return retval; - } - - /* - * Update on-disk size along with block allocation we don't - * use EXT4_GET_BLOCKS_EXTEND_DISKSIZE as size may change - * within already allocated block -bzzz - */ - disksize = ((loff_t) iblock + ret) << inode->i_blkbits; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); - if (disksize > EXT4_I(inode)->i_disksize) { - ext4_update_i_disksize(inode, disksize); - ret = ext4_mark_inode_dirty(handle, inode); - return ret; - } - return 0; -} - /* * mpage_da_map_blocks - go through given space * @@ -2066,9 +2015,12 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, */ static int mpage_da_map_blocks(struct mpage_da_data *mpd) { - int err = 0; + int err, blks; struct buffer_head new; - sector_t next; + sector_t next = mpd->b_blocknr; + unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits; + loff_t disksize = EXT4_I(mpd->inode)->i_disksize; + handle_t *handle = NULL; /* * We consider only non-mapped and non-allocated blocks @@ -2077,6 +2029,16 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) !(mpd->b_state & (1 << BH_Delay)) && !(mpd->b_state & (1 << BH_Unwritten))) return 0; + + /* + * If we didn't accumulate anything to write simply return + */ + if (!mpd->b_size) + return 0; + + handle = ext4_journal_current_handle(); + BUG_ON(!handle); + /* * We need to make sure the BH_Delay flag is passed down to * ext4_da_get_block_write(), since it calls ext4_get_blocks() @@ -2092,18 +2054,11 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) * EXT4_GET_BLOCKS_DELALLOC_RESERVE flag. */ new.b_state = mpd->b_state & (1 << BH_Delay); - new.b_blocknr = 0; - new.b_size = mpd->b_size; - next = mpd->b_blocknr; - /* - * If we didn't accumulate anything - * to write simply return - */ - if (!new.b_size) - return 0; - - err = ext4_da_get_block_write(mpd->inode, next, &new); - if (err) { + blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks, + &new, EXT4_GET_BLOCKS_CREATE| + EXT4_GET_BLOCKS_DELALLOC_RESERVE); + if (blks < 0) { + err = blks; /* * If get block returns with error we simply * return. Later writepage will redirty the page and @@ -2136,12 +2091,14 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) if (err == -ENOSPC) { ext4_print_free_blocks(mpd->inode); } - /* invlaidate all the pages */ + /* invalidate all the pages */ ext4_da_block_invalidatepages(mpd, next, mpd->b_size >> mpd->inode->i_blkbits); return err; } - BUG_ON(new.b_size == 0); + BUG_ON(blks == 0); + + new.b_size = (blks << mpd->inode->i_blkbits); if (buffer_new(&new)) __unmap_underlying_blocks(mpd->inode, &new); @@ -2154,6 +2111,25 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) (mpd->b_state & (1 << BH_Unwritten))) mpage_put_bnr_to_bhs(mpd, next, &new); + if (ext4_should_order_data(mpd->inode)) { + err = ext4_jbd2_file_inode(handle, mpd->inode); + if (err) + return err; + } + + /* + * Update on-disk size along with block allocation we don't + * use EXT4_GET_BLOCKS_EXTEND_DISKSIZE as size may change + * within already allocated block -bzzz + */ + disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits; + if (disksize > i_size_read(mpd->inode)) + disksize = i_size_read(mpd->inode); + if (disksize > EXT4_I(mpd->inode)->i_disksize) { + ext4_update_i_disksize(mpd->inode, disksize); + return ext4_mark_inode_dirty(handle, mpd->inode); + } + return 0; } From 2ac3b6e00acb46406c993d57921f86a594aafe08 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 14 May 2009 13:57:08 -0400 Subject: [PATCH 33/49] ext4: Clean up ext4_get_blocks() so it does not depend on bh_result->b_state The ext4_get_blocks() function was depending on the value of bh_result->b_state as an input parameter to decide whether or not update the delalloc accounting statistics by calling ext4_da_update_reserve_space(). We now use a separate flag, EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE, to requests this update, so that all callers of ext4_get_blocks() can clear map_bh.b_state before calling ext4_get_blocks() without worrying about any consistency issues. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 15 ++++++++----- fs/ext4/inode.c | 56 +++++++++++++++++++++++++++---------------------- 2 files changed, 41 insertions(+), 30 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 17feb4ac633a..d164f1294e5f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -318,16 +318,21 @@ struct ext4_new_group_data { */ /* Allocate any needed blocks and/or convert an unitialized extent to be an initialized ext4 */ -#define EXT4_GET_BLOCKS_CREATE 1 +#define EXT4_GET_BLOCKS_CREATE 0x0001 /* Request the creation of an unitialized extent */ -#define EXT4_GET_BLOCKS_UNINIT_EXT 2 +#define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002 #define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\ EXT4_GET_BLOCKS_CREATE) /* Update the ext4_inode_info i_disksize field */ -#define EXT4_GET_BLOCKS_EXTEND_DISKSIZE 4 +#define EXT4_GET_BLOCKS_EXTEND_DISKSIZE 0x0004 /* Caller is from the delayed allocation writeout path, - so the filesystem blocks have already been accounted for */ -#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 8 + so set the magic i_delalloc_reserve_flag after taking the + inode allocation semaphore for */ +#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0008 + /* Call ext4_da_update_reserve_space() after successfully + allocating the blocks */ +#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0010 + /* * ioctl commands diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bfe50a22363b..d7b7480682b9 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1234,16 +1234,15 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, } } - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) EXT4_I(inode)->i_delalloc_reserved_flag = 0; - /* - * Update reserved blocks/metadata blocks - * after successful block allocation - * which were deferred till now - */ - if ((retval > 0) && buffer_delay(bh)) - ext4_da_update_reserve_space(inode, retval); - } + + /* + * Update reserved blocks/metadata blocks after successful + * block allocation which had been deferred till now. + */ + if ((retval > 0) && (flags & EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE)) + ext4_da_update_reserve_space(inode, retval); up_write((&EXT4_I(inode)->i_data_sem)); return retval; @@ -2015,7 +2014,7 @@ static void ext4_print_free_blocks(struct inode *inode) */ static int mpage_da_map_blocks(struct mpage_da_data *mpd) { - int err, blks; + int err, blks, get_blocks_flags; struct buffer_head new; sector_t next = mpd->b_blocknr; unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits; @@ -2040,23 +2039,30 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) BUG_ON(!handle); /* - * We need to make sure the BH_Delay flag is passed down to - * ext4_da_get_block_write(), since it calls ext4_get_blocks() - * with the EXT4_GET_BLOCKS_DELALLOC_RESERVE flag. This flag - * causes ext4_get_blocks() to call - * ext4_da_update_reserve_space() if the passed buffer head - * has the BH_Delay flag set. In the future, once we clean up - * the interfaces to ext4_get_blocks(), we should pass in a - * separate flag which requests that the delayed allocation - * statistics should be updated, instead of depending on the - * state information getting passed down via the map_bh's - * state bitmasks plus the magic - * EXT4_GET_BLOCKS_DELALLOC_RESERVE flag. + * Call ext4_get_blocks() to allocate any delayed allocation + * blocks, or to convert an uninitialized extent to be + * initialized (in the case where we have written into + * one or more preallocated blocks). + * + * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to + * indicate that we are on the delayed allocation path. This + * affects functions in many different parts of the allocation + * call path. This flag exists primarily because we don't + * want to change *many* call functions, so ext4_get_blocks() + * will set the magic i_delalloc_reserved_flag once the + * inode's allocation semaphore is taken. + * + * If the blocks in questions were delalloc blocks, set + * EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting + * variables are updated after the blocks have been allocated. */ - new.b_state = mpd->b_state & (1 << BH_Delay); + new.b_state = 0; + get_blocks_flags = (EXT4_GET_BLOCKS_CREATE | + EXT4_GET_BLOCKS_DELALLOC_RESERVE); + if (mpd->b_state & (1 << BH_Delay)) + get_blocks_flags |= EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE; blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks, - &new, EXT4_GET_BLOCKS_CREATE| - EXT4_GET_BLOCKS_DELALLOC_RESERVE); + &new, get_blocks_flags); if (blks < 0) { err = blks; /* From 6fd058f7791087648c683eb8572edf3be3c4c23c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 17 May 2009 15:38:01 -0400 Subject: [PATCH 34/49] ext4: Add a comprehensive block validity check to ext4_get_blocks() To catch filesystem bugs or corruption which could lead to the filesystem getting severly damaged, this patch adds a facility for tracking all of the filesystem metadata blocks by contiguous regions in a red-black tree. This allows quick searching of the tree to locate extents which might overlap with filesystem metadata blocks. This facility is also used by the multi-block allocator to assure that it is not allocating blocks out of the system zone, as well as by the routines used when reading indirect blocks and extents information from disk to make sure their contents are valid. Signed-off-by: "Theodore Ts'o" --- fs/ext4/Makefile | 4 +- fs/ext4/block_validity.c | 244 +++++++++++++++++++++++++++++++++++++++ fs/ext4/ext4.h | 11 ++ fs/ext4/extents.c | 22 +--- fs/ext4/inode.c | 47 ++++++-- fs/ext4/mballoc.c | 11 +- fs/ext4/super.c | 32 ++++- 7 files changed, 332 insertions(+), 39 deletions(-) create mode 100644 fs/ext4/block_validity.c diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index a8ff003a00f7..8a34710ecf40 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -5,8 +5,8 @@ obj-$(CONFIG_EXT4_FS) += ext4.o ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \ - ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ - ext4_jbd2.o migrate.o mballoc.o + ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ + ext4_jbd2.o migrate.o mballoc.o block_validity.o ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c new file mode 100644 index 000000000000..50784ef07563 --- /dev/null +++ b/fs/ext4/block_validity.c @@ -0,0 +1,244 @@ +/* + * linux/fs/ext4/block_validity.c + * + * Copyright (C) 2009 + * Theodore Ts'o (tytso@mit.edu) + * + * Track which blocks in the filesystem are metadata blocks that + * should never be used as data blocks by files or directories. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "ext4.h" + +struct ext4_system_zone { + struct rb_node node; + ext4_fsblk_t start_blk; + unsigned int count; +}; + +static struct kmem_cache *ext4_system_zone_cachep; + +int __init init_ext4_system_zone(void) +{ + ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, + SLAB_RECLAIM_ACCOUNT); + if (ext4_system_zone_cachep == NULL) + return -ENOMEM; + return 0; +} + +void exit_ext4_system_zone(void) +{ + kmem_cache_destroy(ext4_system_zone_cachep); +} + +static inline int can_merge(struct ext4_system_zone *entry1, + struct ext4_system_zone *entry2) +{ + if ((entry1->start_blk + entry1->count) == entry2->start_blk) + return 1; + return 0; +} + +/* + * Mark a range of blocks as belonging to the "system zone" --- that + * is, filesystem metadata blocks which should never be used by + * inodes. + */ +static int add_system_zone(struct ext4_sb_info *sbi, + ext4_fsblk_t start_blk, + unsigned int count) +{ + struct ext4_system_zone *new_entry = NULL, *entry; + struct rb_node **n = &sbi->system_blks.rb_node, *node; + struct rb_node *parent = NULL, *new_node = NULL; + + while (*n) { + parent = *n; + entry = rb_entry(parent, struct ext4_system_zone, node); + if (start_blk < entry->start_blk) + n = &(*n)->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = &(*n)->rb_right; + else { + if (start_blk + count > (entry->start_blk + + entry->count)) + entry->count = (start_blk + count - + entry->start_blk); + new_node = *n; + new_entry = rb_entry(new_node, struct ext4_system_zone, + node); + break; + } + } + + if (!new_entry) { + new_entry = kmem_cache_alloc(ext4_system_zone_cachep, + GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + new_entry->start_blk = start_blk; + new_entry->count = count; + new_node = &new_entry->node; + + rb_link_node(new_node, parent, n); + rb_insert_color(new_node, &sbi->system_blks); + } + + /* Can we merge to the left? */ + node = rb_prev(new_node); + if (node) { + entry = rb_entry(node, struct ext4_system_zone, node); + if (can_merge(entry, new_entry)) { + new_entry->start_blk = entry->start_blk; + new_entry->count += entry->count; + rb_erase(node, &sbi->system_blks); + kmem_cache_free(ext4_system_zone_cachep, entry); + } + } + + /* Can we merge to the right? */ + node = rb_next(new_node); + if (node) { + entry = rb_entry(node, struct ext4_system_zone, node); + if (can_merge(new_entry, entry)) { + new_entry->count += entry->count; + rb_erase(node, &sbi->system_blks); + kmem_cache_free(ext4_system_zone_cachep, entry); + } + } + return 0; +} + +static void debug_print_tree(struct ext4_sb_info *sbi) +{ + struct rb_node *node; + struct ext4_system_zone *entry; + int first = 1; + + printk(KERN_INFO "System zones: "); + node = rb_first(&sbi->system_blks); + while (node) { + entry = rb_entry(node, struct ext4_system_zone, node); + printk("%s%llu-%llu", first ? "" : ", ", + entry->start_blk, entry->start_blk + entry->count - 1); + first = 0; + node = rb_next(node); + } + printk("\n"); +} + +int ext4_setup_system_zone(struct super_block *sb) +{ + ext4_group_t ngroups = ext4_get_groups_count(sb); + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp; + ext4_group_t i; + int flex_size = ext4_flex_bg_size(sbi); + int ret; + + if (!test_opt(sb, BLOCK_VALIDITY)) { + if (EXT4_SB(sb)->system_blks.rb_node) + ext4_release_system_zone(sb); + return 0; + } + if (EXT4_SB(sb)->system_blks.rb_node) + return 0; + + for (i=0; i < ngroups; i++) { + if (ext4_bg_has_super(sb, i) && + ((i < 5) || ((i % flex_size) == 0))) + add_system_zone(sbi, ext4_group_first_block_no(sb, i), + sbi->s_gdb_count + 1); + gdp = ext4_get_group_desc(sb, i, NULL); + ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1); + if (ret) + return ret; + ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1); + if (ret) + return ret; + ret = add_system_zone(sbi, ext4_inode_table(sb, gdp), + sbi->s_itb_per_group); + if (ret) + return ret; + } + + if (test_opt(sb, DEBUG)) + debug_print_tree(EXT4_SB(sb)); + return 0; +} + +/* Called when the filesystem is unmounted */ +void ext4_release_system_zone(struct super_block *sb) +{ + struct rb_node *n = EXT4_SB(sb)->system_blks.rb_node; + struct rb_node *parent; + struct ext4_system_zone *entry; + + while (n) { + /* Do the node's children first */ + if (n->rb_left) { + n = n->rb_left; + continue; + } + if (n->rb_right) { + n = n->rb_right; + continue; + } + /* + * The node has no children; free it, and then zero + * out parent's link to it. Finally go to the + * beginning of the loop and try to free the parent + * node. + */ + parent = rb_parent(n); + entry = rb_entry(n, struct ext4_system_zone, node); + kmem_cache_free(ext4_system_zone_cachep, entry); + if (!parent) + EXT4_SB(sb)->system_blks.rb_node = NULL; + else if (parent->rb_left == n) + parent->rb_left = NULL; + else if (parent->rb_right == n) + parent->rb_right = NULL; + n = parent; + } + EXT4_SB(sb)->system_blks.rb_node = NULL; +} + +/* + * Returns 1 if the passed-in block region (start_blk, + * start_blk+count) is valid; 0 if some part of the block region + * overlaps with filesystem metadata blocks. + */ +int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, + unsigned int count) +{ + struct ext4_system_zone *entry; + struct rb_node *n = sbi->system_blks.rb_node; + + if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || + (start_blk + count > ext4_blocks_count(sbi->s_es))) + return 0; + while (n) { + entry = rb_entry(n, struct ext4_system_zone, node); + if (start_blk + count - 1 < entry->start_blk) + n = n->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = n->rb_right; + else + return 0; + } + return 1; +} + diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d164f1294e5f..4311cc85b534 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -696,6 +696,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */ #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ +#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H @@ -887,6 +888,7 @@ struct ext4_sb_info { int s_jquota_fmt; /* Format of quota to use */ #endif unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ + struct rb_root system_blks; #ifdef EXTENTS_STATS /* ext4 extents stats */ @@ -1618,6 +1620,15 @@ extern struct dentry *ext4_get_parent(struct dentry *child); extern const struct inode_operations ext4_symlink_inode_operations; extern const struct inode_operations ext4_fast_symlink_inode_operations; +/* block_validity */ +extern void ext4_release_system_zone(struct super_block *sb); +extern int ext4_setup_system_zone(struct super_block *sb); +extern int __init init_ext4_system_zone(void); +extern void exit_ext4_system_zone(void); +extern int ext4_data_block_valid(struct ext4_sb_info *sbi, + ext4_fsblk_t start_blk, + unsigned int count); + /* extents.c */ extern int ext4_ext_tree_init(handle_t *handle, struct inode *); extern int ext4_ext_writepage_trans_blocks(struct inode *, int); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 27c383c7b43c..d04b779b780e 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -326,32 +326,18 @@ ext4_ext_max_entries(struct inode *inode, int depth) static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { - ext4_fsblk_t block = ext_pblock(ext), valid_block; + ext4_fsblk_t block = ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; - valid_block = le32_to_cpu(es->s_first_data_block) + - EXT4_SB(inode->i_sb)->s_gdb_count; - if (unlikely(block <= valid_block || - ((block + len) > ext4_blocks_count(es)))) - return 0; - else - return 1; + return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); } static int ext4_valid_extent_idx(struct inode *inode, struct ext4_extent_idx *ext_idx) { - ext4_fsblk_t block = idx_pblock(ext_idx), valid_block; - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + ext4_fsblk_t block = idx_pblock(ext_idx); - valid_block = le32_to_cpu(es->s_first_data_block) + - EXT4_SB(inode->i_sb)->s_gdb_count; - if (unlikely(block <= valid_block || - (block >= ext4_blocks_count(es)))) - return 0; - else - return 1; + return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); } static int ext4_valid_extent_entries(struct inode *inode, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d7b7480682b9..dadd3f995db5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -372,20 +372,21 @@ static int ext4_block_to_path(struct inode *inode, } static int __ext4_check_blockref(const char *function, struct inode *inode, - __le32 *p, unsigned int max) { - - unsigned int maxblocks = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es); + __le32 *p, unsigned int max) +{ __le32 *bref = p; + unsigned int blk; + while (bref < p+max) { - if (unlikely(le32_to_cpu(*bref) >= maxblocks)) { + blk = le32_to_cpu(*bref++); + if (blk && + unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), + blk, 1))) { ext4_error(inode->i_sb, function, - "block reference %u >= max (%u) " - "in inode #%lu, offset=%d", - le32_to_cpu(*bref), maxblocks, - inode->i_ino, (int)(bref-p)); + "invalid block reference %u " + "in inode #%lu", blk, inode->i_ino); return -EIO; } - bref++; } return 0; } @@ -1125,6 +1126,21 @@ 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) +{ + if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) { + ext4_error(inode->i_sb, "check_block_validity", + "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; +} + /* * The ext4_get_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. @@ -1170,6 +1186,13 @@ 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); + if (ret != 0) + return ret; + } + /* If it is only a block(s) look up */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) return retval; @@ -1245,6 +1268,12 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, ext4_da_update_reserve_space(inode, retval); 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); + if (ret != 0) + return ret; + } return retval; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 541bd9adffa2..ed8482e22c0e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2961,15 +2961,10 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, + le32_to_cpu(es->s_first_data_block); len = ac->ac_b_ex.fe_len; - if (in_range(ext4_block_bitmap(sb, gdp), block, len) || - in_range(ext4_inode_bitmap(sb, gdp), block, len) || - in_range(block, ext4_inode_table(sb, gdp), - EXT4_SB(sb)->s_itb_per_group) || - in_range(block + len - 1, ext4_inode_table(sb, gdp), - EXT4_SB(sb)->s_itb_per_group)) { + if (!ext4_data_block_valid(sbi, block, len)) { ext4_error(sb, __func__, - "Allocating block %llu in system zone of %d group\n", - block, ac->ac_b_ex.fe_group); + "Allocating blocks %llu-%llu which overlap " + "fs metadata\n", block, block+len); /* File system mounted not to panic on error * Fix the bitmap and repeat the block allocation * We leak some of the blocks here. diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dc34ed3d1327..600b7ad699b5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -568,6 +568,7 @@ static void ext4_put_super(struct super_block *sb) struct ext4_super_block *es = sbi->s_es; int i, err; + ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); ext4_xattr_put_super(sb); @@ -1055,6 +1056,7 @@ enum { Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_stripe, Opt_delalloc, Opt_nodelalloc, + Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio }; @@ -1114,6 +1116,8 @@ static const match_table_t tokens = { {Opt_resize, "resize"}, {Opt_delalloc, "delalloc"}, {Opt_nodelalloc, "nodelalloc"}, + {Opt_block_validity, "block_validity"}, + {Opt_noblock_validity, "noblock_validity"}, {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, {Opt_journal_ioprio, "journal_ioprio=%u"}, {Opt_auto_da_alloc, "auto_da_alloc=%u"}, @@ -1508,6 +1512,12 @@ static int parse_options(char *options, struct super_block *sb, case Opt_delalloc: set_opt(sbi->s_mount_opt, DELALLOC); break; + case Opt_block_validity: + set_opt(sbi->s_mount_opt, BLOCK_VALIDITY); + break; + case Opt_noblock_validity: + clear_opt(sbi->s_mount_opt, BLOCK_VALIDITY); + break; case Opt_inode_readahead_blks: if (match_int(&args[0], &option)) return 0; @@ -2826,6 +2836,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } else if (test_opt(sb, DELALLOC)) printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n"); + err = ext4_setup_system_zone(sb); + if (err) { + printk(KERN_ERR "EXT4-fs: failed to initialize system " + "zone (%d)\n", err); + goto failed_mount4; + } + ext4_ext_init(sb); err = ext4_mb_init(sb, needs_recovery); if (err) { @@ -2875,6 +2892,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) failed_mount4: printk(KERN_ERR "EXT4-fs (device %s): mount failed\n", sb->s_id); + ext4_release_system_zone(sb); if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; @@ -3515,6 +3533,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sb->s_flags &= ~MS_RDONLY; } } + ext4_setup_system_zone(sb); if (sbi->s_journal == NULL) ext4_commit_super(sb, 1); @@ -3927,13 +3946,16 @@ static int __init init_ext4_fs(void) { int err; + err = init_ext4_system_zone(); + if (err) + return err; ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj); if (!ext4_kset) - return -ENOMEM; + goto out4; ext4_proc_root = proc_mkdir("fs/ext4", NULL); err = init_ext4_mballoc(); if (err) - return err; + goto out3; err = init_ext4_xattr(); if (err) @@ -3958,6 +3980,11 @@ static int __init init_ext4_fs(void) exit_ext4_xattr(); out2: exit_ext4_mballoc(); +out3: + remove_proc_entry("fs/ext4", NULL); + kset_unregister(ext4_kset); +out4: + exit_ext4_system_zone(); return err; } @@ -3972,6 +3999,7 @@ static void __exit exit_ext4_fs(void) exit_ext4_mballoc(); remove_proc_entry("fs/ext4", NULL); kset_unregister(ext4_kset); + exit_ext4_system_zone(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); From 0568c518937ee3a9b6a94d18bae9c150fe5d6832 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 17 May 2009 23:31:23 -0400 Subject: [PATCH 35/49] ext4: down i_data_sem only for read when walking tree for fiemap Not sure why I put this in as down_write originally; all we are doing is walking the tree, nothing will change under us and concurrent reads should be no problem. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index d04b779b780e..d4e99e96fddb 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3312,10 +3312,10 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, * Walk the extent tree gathering extent information. * ext4_ext_fiemap_cb will push extents back to user. */ - down_write(&EXT4_I(inode)->i_data_sem); + down_read(&EXT4_I(inode)->i_data_sem); error = ext4_ext_walk_space(inode, start_blk, len_blks, ext4_ext_fiemap_cb, fieinfo); - up_write(&EXT4_I(inode)->i_data_sem); + up_read(&EXT4_I(inode)->i_data_sem); } return error; From f68301656b5f5d2de104f2687add6beeb8f3c3b9 Mon Sep 17 00:00:00 2001 From: Manish Katiyar Date: Sun, 17 May 2009 23:52:44 -0400 Subject: [PATCH 36/49] ext4: Fix memory leak in ext4_fill_super() in case of a failed mount Signed-off-by: Manish Katiyar Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 600b7ad699b5..eca6c057b119 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2924,6 +2924,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) brelse(bh); out_fail: sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); kfree(sbi); lock_kernel(); return ret; From de5ce037304f2c88a319b1c3b808ab0c4c618c1c Mon Sep 17 00:00:00 2001 From: Manish Katiyar Date: Sun, 17 May 2009 23:52:47 -0400 Subject: [PATCH 37/49] ext3: Fix memory leak in ext3_fill_super() in case of a failed mount Signed-off-by: Manish Katiyar Signed-off-by: "Theodore Ts'o" --- fs/ext3/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 599dbfe504c3..d8b73d4abe3e 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2021,6 +2021,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) brelse(bh); out_fail: sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); kfree(sbi); lock_kernel(); return ret; From 0f7ee7c17241915fdaff49d1a36f5aafd80a7dce Mon Sep 17 00:00:00 2001 From: Manish Katiyar Date: Sun, 17 May 2009 23:52:51 -0400 Subject: [PATCH 38/49] ext2: Fix memory leak in ext2_fill_super() in case of a failed mount Signed-off-by: Manish Katiyar Signed-off-by: "Theodore Ts'o" --- fs/ext2/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 5c4afe652245..e3c748faf2db 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1093,6 +1093,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) brelse(bh); failed_sbi: sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); kfree(sbi); return ret; } From 759d427aa5a9d88a81afd11817cdeb40aea85234 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 25 May 2009 11:51:00 -0400 Subject: [PATCH 39/49] ext4: remove unused function __ext4_write_dirty_metadata The __ext4_write_dirty_metadata() function was introduced by commit 0390131b, "ext4: Allow ext4 to run without a journal", but nothing ever used the function, either then or since. So let's remove it and save a bit of space. Cc: Frank Mayhar Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index dadd3f995db5..14c00fff3713 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4790,25 +4790,6 @@ int ext4_write_inode(struct inode *inode, int wait) return ext4_force_commit(inode->i_sb); } -int __ext4_write_dirty_metadata(struct inode *inode, struct buffer_head *bh) -{ - int err = 0; - - mark_buffer_dirty(bh); - if (inode && inode_needs_sync(inode)) { - sync_dirty_buffer(bh); - if (buffer_req(bh) && !buffer_uptodate(bh)) { - ext4_error(inode->i_sb, __func__, - "IO error syncing inode, " - "inode=%lu, block=%llu", - inode->i_ino, - (unsigned long long)bh->b_blocknr); - err = -EIO; - } - } - return err; -} - /* * ext4_setattr() * From 88b6edd17c62b7d346d21f4087893ce7d4ef828a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 25 May 2009 11:50:39 -0400 Subject: [PATCH 40/49] ext4: Clean up calls to ext4_get_group_desc() If the caller isn't planning on modifying the block group descriptors, there's no need to pass in a pointer to a struct buffer_head. Nuking this saves a tiny amount of CPU time and stack space usage. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ialloc.c | 3 +-- fs/ext4/super.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 82f7d1d7eae0..3743bd849bce 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -347,7 +347,6 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *desc; - struct buffer_head *bh; struct flex_groups *flex_group = sbi->s_flex_groups; ext4_group_t parent_group = EXT4_I(parent)->i_block_group; ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group); @@ -402,7 +401,7 @@ static int find_group_flex(struct super_block *sb, struct inode *parent, found_flexbg: for (i = best_flex * flex_size; i < ngroups && i < (best_flex + 1) * flex_size; i++) { - desc = ext4_get_group_desc(sb, i, &bh); + desc = ext4_get_group_desc(sb, i, NULL); if (ext4_free_inodes_count(sb, desc)) { *best_group = i; goto out; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eca6c057b119..91b98b58ccb9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1660,7 +1660,6 @@ static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; - struct buffer_head *bh; ext4_group_t flex_group_count; ext4_group_t flex_group; int groups_per_flex = 0; @@ -1693,7 +1692,7 @@ static int ext4_fill_flex_info(struct super_block *sb) } for (i = 0; i < sbi->s_groups_count; i++) { - gdp = ext4_get_group_desc(sb, i, &bh); + 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, From bfcd3555af478dbf04c87adc9bb1a739d0a6ccff Mon Sep 17 00:00:00 2001 From: Alberto Bertogli Date: Tue, 9 Jun 2009 00:06:20 -0400 Subject: [PATCH 41/49] jbd2: Fix minor typos in comments in fs/jbd2/journal.c Signed-off-by: Alberto Bertogli Signed-off-by: Theodore Ts'o --- fs/jbd2/journal.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 58144102bf25..62be7d294ec2 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1781,7 +1781,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) * Journal abort has very specific semantics, which we describe * for journal abort. * - * Two internal function, which provide abort to te jbd layer + * Two internal functions, which provide abort to the jbd layer * itself are here. */ @@ -1879,7 +1879,7 @@ void jbd2_journal_abort(journal_t *journal, int errno) * int jbd2_journal_errno () - returns the journal's error state. * @journal: journal to examine. * - * This is the errno numbet set with jbd2_journal_abort(), the last + * This is the errno number set with jbd2_journal_abort(), the last * time the journal was mounted - if the journal was stopped * without calling abort this will be 0. * @@ -1903,7 +1903,7 @@ int jbd2_journal_errno(journal_t *journal) * int jbd2_journal_clear_err () - clears the journal's error state * @journal: journal to act on. * - * An error must be cleared or Acked to take a FS out of readonly + * An error must be cleared or acked to take a FS out of readonly * mode. */ int jbd2_journal_clear_err(journal_t *journal) @@ -1923,7 +1923,7 @@ int jbd2_journal_clear_err(journal_t *journal) * void jbd2_journal_ack_err() - Ack journal err. * @journal: journal to act on. * - * An error must be cleared or Acked to take a FS out of readonly + * An error must be cleared or acked to take a FS out of readonly * mode. */ void jbd2_journal_ack_err(journal_t *journal) From 0b8e58a140cae2ba1c4a21ccae7c6c3c939c51f9 Mon Sep 17 00:00:00 2001 From: Andreas Dilger Date: Wed, 3 Jun 2009 17:59:28 -0400 Subject: [PATCH 42/49] ext4: super.c whitespace cleanup Cleanup of whitespace and formatting. Initially driven by confusing indents for the ext4_{block,inode}_bitmap() et. al. helper routines, but figured I'd cleanup some other 80-column wrapping and other indenting problems at the same time. Signed-off-by: Andreas Dilger Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 117 +++++++++++++++++++++++++----------------------- 1 file changed, 61 insertions(+), 56 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 91b98b58ccb9..0a97b1ad3e19 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -79,7 +79,7 @@ ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, { return le32_to_cpu(bg->bg_block_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, @@ -87,7 +87,7 @@ ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, { return le32_to_cpu(bg->bg_inode_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_table(struct super_block *sb, @@ -95,7 +95,7 @@ ext4_fsblk_t ext4_inode_table(struct super_block *sb, { return le32_to_cpu(bg->bg_inode_table_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } __u32 ext4_free_blks_count(struct super_block *sb, @@ -103,7 +103,7 @@ __u32 ext4_free_blks_count(struct super_block *sb, { return le16_to_cpu(bg->bg_free_blocks_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0); + (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0); } __u32 ext4_free_inodes_count(struct super_block *sb, @@ -111,7 +111,7 @@ __u32 ext4_free_inodes_count(struct super_block *sb, { return le16_to_cpu(bg->bg_free_inodes_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0); + (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0); } __u32 ext4_used_dirs_count(struct super_block *sb, @@ -119,7 +119,7 @@ __u32 ext4_used_dirs_count(struct super_block *sb, { return le16_to_cpu(bg->bg_used_dirs_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0); + (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0); } __u32 ext4_itable_unused_count(struct super_block *sb, @@ -127,7 +127,7 @@ __u32 ext4_itable_unused_count(struct super_block *sb, { return le16_to_cpu(bg->bg_itable_unused_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0); + (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0); } void ext4_block_bitmap_set(struct super_block *sb, @@ -207,8 +207,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) journal = EXT4_SB(sb)->s_journal; if (journal) { if (is_journal_aborted(journal)) { - ext4_abort(sb, __func__, - "Detected aborted journal"); + ext4_abort(sb, __func__, "Detected aborted journal"); return ERR_PTR(-EROFS); } return jbd2_journal_start(journal, nblocks); @@ -436,7 +435,7 @@ void ext4_warning(struct super_block *sb, const char *function, } void ext4_grp_locked_error(struct super_block *sb, ext4_group_t grp, - const char *function, const char *fmt, ...) + const char *function, const char *fmt, ...) __releases(bitlock) __acquires(bitlock) { @@ -472,7 +471,6 @@ __acquires(bitlock) return; } - void ext4_update_dynamic_rev(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; @@ -638,7 +636,6 @@ static void ext4_put_super(struct super_block *sb) lock_kernel(); kfree(sbi->s_blockgroup_lock); kfree(sbi); - return; } static struct kmem_cache *ext4_inode_cachep; @@ -653,6 +650,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS); if (!ei) return NULL; + #ifdef CONFIG_EXT4_FS_POSIX_ACL ei->i_acl = EXT4_ACL_NOT_CACHED; ei->i_default_acl = EXT4_ACL_NOT_CACHED; @@ -673,6 +671,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_allocated_meta_blocks = 0; ei->i_delalloc_reserved_flag = 0; spin_lock_init(&(ei->i_block_reservation_lock)); + return &ei->vfs_inode; } @@ -879,12 +878,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",noauto_da_alloc"); ext4_show_quota_options(seq, sb); + return 0; } - static struct inode *ext4_nfs_get_inode(struct super_block *sb, - u64 ino, u32 generation) + u64 ino, u32 generation) { struct inode *inode; @@ -913,14 +912,14 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb, } static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid, - int fh_len, int fh_type) + int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, - int fh_len, int fh_type) + int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); @@ -932,7 +931,8 @@ static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, * which would prevent try_to_free_buffers() from freeing them, we must use * jbd2 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) +static int bdev_try_to_free_page(struct super_block *sb, struct page *page, + gfp_t wait) { journal_t *journal = EXT4_SB(sb)->s_journal; @@ -1133,8 +1133,9 @@ static ext4_fsblk_t get_sb_block(void **data) if (!options || strncmp(options, "sb=", 3) != 0) return 1; /* Default location */ + options += 3; - /*todo: use simple_strtoll with >32bit ext4 */ + /* TODO: use simple_strtoll with >32bit ext4 */ sb_block = simple_strtoul(options, &options, 0); if (*options && *options != ',') { printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n", @@ -1144,6 +1145,7 @@ static ext4_fsblk_t get_sb_block(void **data) if (*options == ',') options++; *data = (void *) options; + return sb_block; } @@ -1626,7 +1628,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, printk(KERN_WARNING "EXT4-fs warning: checktime reached, " "running e2fsck is recommended\n"); - if (!sbi->s_journal) + if (!sbi->s_journal) es->s_state &= cpu_to_le16(~EXT4_VALID_FS); if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT); @@ -1810,7 +1812,7 @@ static int ext4_check_descriptors(struct super_block *sb) } ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); - sbi->s_es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb)); + sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb)); return 1; } @@ -1926,6 +1928,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, #endif sb->s_flags = s_flags; /* Restore MS_RDONLY status */ } + /* * Maximal extent format file size. * Resulting logical blkno at s_maxbytes must fit in our on-disk @@ -1976,19 +1979,19 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) loff_t res = EXT4_NDIR_BLOCKS; int meta_blocks; loff_t upper_limit; - /* This is calculated to be the largest file size for a - * dense, bitmapped file such that the total number of - * sectors in the file, including data and all indirect blocks, - * does not exceed 2^48 -1 - * __u32 i_blocks_lo and _u16 i_blocks_high representing the - * total number of 512 bytes blocks of the file + /* This is calculated to be the largest file size for a dense, block + * mapped file such that the file's total number of 512-byte sectors, + * including data and all indirect blocks, does not exceed (2^48 - 1). + * + * __u32 i_blocks_lo and _u16 i_blocks_high represent the total + * number of 512-byte sectors of the file. */ if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) { /* - * !has_huge_files or CONFIG_LBD is not enabled - * implies the inode i_block represent total blocks in - * 512 bytes 32 == size of vfs inode i_blocks * 8 + * !has_huge_files or CONFIG_LBD not enabled implies that + * the inode i_block field represents total file blocks in + * 2^32 512-byte sectors == size of vfs inode i_blocks * 8 */ upper_limit = (1LL << 32) - 1; @@ -2030,7 +2033,7 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) } static ext4_fsblk_t descriptor_loc(struct super_block *sb, - ext4_fsblk_t logical_sb_block, int nr) + ext4_fsblk_t logical_sb_block, int nr) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t bg, first_meta_bg; @@ -2044,6 +2047,7 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb, bg = sbi->s_desc_per_block * nr; if (ext4_bg_has_super(sb, bg)) has_super = 1; + return (has_super + ext4_group_first_block_no(sb, bg)); } @@ -2148,7 +2152,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a, } static ssize_t sbi_ui_show(struct ext4_attr *a, - struct ext4_sb_info *sbi, char *buf) + struct ext4_sb_info *sbi, char *buf) { unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset); @@ -2253,7 +2257,6 @@ static struct kobj_type ext4_ktype = { static int ext4_fill_super(struct super_block *sb, void *data, int silent) __releases(kernel_lock) __acquires(kernel_lock) - { struct buffer_head *bh; struct ext4_super_block *es = NULL; @@ -2379,7 +2382,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ set_opt(sbi->s_mount_opt, DELALLOC); - if (!parse_options((char *) data, sb, &journal_devnum, &journal_ioprio, NULL, 0)) goto failed_mount; @@ -2442,7 +2444,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (sb->s_blocksize != blocksize) { - /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { printk(KERN_ERR "EXT4-fs: bad block size %d.\n", @@ -2489,6 +2490,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2); } + sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || @@ -2501,10 +2503,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } else sbi->s_desc_size = EXT4_MIN_DESC_SIZE; + sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0) goto cantfind_ext4; + sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0) goto cantfind_ext4; @@ -2515,6 +2519,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_mount_state = le16_to_cpu(es->s_state); sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); + 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; @@ -2566,12 +2571,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - /* - * It makes no sense for the first data block to be beyond the end - * of the filesystem. - */ - if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { - printk(KERN_WARNING "EXT4-fs: bad geometry: first data" + /* + * It makes no sense for the first data block to be beyond the end + * of the filesystem. + */ + if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { + printk(KERN_WARNING "EXT4-fs: bad geometry: first data" "block %u is beyond end of filesystem (%llu)\n", le32_to_cpu(es->s_first_data_block), ext4_blocks_count(es)); @@ -3082,6 +3087,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, EXT4_SB(sb)->journal_bdev = bdev; ext4_init_journal_params(sb, journal); return journal; + out_journal: jbd2_journal_destroy(journal); out_bdev: @@ -3116,7 +3122,6 @@ static int ext4_load_journal(struct super_block *sb, * crash? For recovery, we need to check in advance whether we * can get read-write access to the device. */ - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) { if (sb->s_flags & MS_RDONLY) { printk(KERN_INFO "EXT4-fs: INFO: recovery " @@ -3234,7 +3239,6 @@ static int ext4_commit_super(struct super_block *sb, int sync) return error; } - /* * Have we just finished recovery? If so, and if we are mounting (or * remounting) the filesystem readonly, then we will end up with a @@ -3485,8 +3489,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) /* * Make sure the group descriptor checksums - * are sane. If they aren't, refuse to - * remount r/w. + * are sane. If they aren't, refuse to remount r/w. */ for (g = 0; g < sbi->s_groups_count; g++) { struct ext4_group_desc *gdp = @@ -3545,6 +3548,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) kfree(old_opts.s_qf_names[i]); #endif return 0; + restore_opts: sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; @@ -3628,11 +3632,12 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) le64_to_cpup((void *)es->s_uuid + sizeof(u64)); buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL; buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL; + return 0; } -/* Helper function for writing quotas on sync - we need to start transaction before quota file - * is locked for write. Otherwise the are possible deadlocks: +/* Helper function for writing quotas on sync - we need to start transaction + * before quota file is locked for write. Otherwise the are possible deadlocks: * Process 1 Process 2 * ext4_create() quota_sync() * jbd2_journal_start() write_dquot() @@ -3656,7 +3661,7 @@ static int ext4_write_dquot(struct dquot *dquot) inode = dquot_to_inode(dquot); handle = ext4_journal_start(inode, - EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); + EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); @@ -3672,7 +3677,7 @@ static int ext4_acquire_dquot(struct dquot *dquot) handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), - EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb)); + EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); @@ -3688,7 +3693,7 @@ static int ext4_release_dquot(struct dquot *dquot) handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), - EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); + EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); @@ -3736,7 +3741,7 @@ static int ext4_write_info(struct super_block *sb, int type) static int ext4_quota_on_mount(struct super_block *sb, int type) { return vfs_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type], - EXT4_SB(sb)->s_jquota_fmt, type); + EXT4_SB(sb)->s_jquota_fmt, type); } /* @@ -3907,10 +3912,10 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, #endif -static int ext4_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static int ext4_get_sb(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data, struct vfsmount *mnt) { - return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt); + return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt); } static struct file_system_type ext4_fs_type = { @@ -3922,14 +3927,14 @@ static struct file_system_type ext4_fs_type = { }; #ifdef CONFIG_EXT4DEV_COMPAT -static int ext4dev_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static int ext4dev_get_sb(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data,struct vfsmount *mnt) { printk(KERN_WARNING "EXT4-fs: Update your userspace programs " "to mount using ext4\n"); printk(KERN_WARNING "EXT4-fs: ext4dev backwards compatibility " "will go away by 2.6.31\n"); - return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt); + return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt); } static struct file_system_type ext4dev_fs_type = { From 03f5d8bcf094a5e3b501bd2ae1553656efa8d1be Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 9 Jun 2009 00:17:05 -0400 Subject: [PATCH 43/49] ext4: Get rid of EXTEND_DISKSIZE flag of ext4_get_blocks_handle() Get rid of EXTEND_DISKSIZE flag of ext4_get_blocks_handle(). This seems to be a relict from some old days and setting disksize in this function does not make much sense. Currently it was set only by ext4_getblk(). Since the parameter has some effect only if create == 1, it is easy to check by grepping through the sources that the three callers which end up calling ext4_getblk() with create == 1 (ext4_append, ext4_quota_write, ext4_mkdir) do the right thing and set disksize themselves. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 6 ++---- fs/ext4/extents.c | 9 --------- fs/ext4/inode.c | 23 +++-------------------- 3 files changed, 5 insertions(+), 33 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4311cc85b534..59657ff7b8f4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -323,15 +323,13 @@ struct ext4_new_group_data { #define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002 #define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\ EXT4_GET_BLOCKS_CREATE) - /* Update the ext4_inode_info i_disksize field */ -#define EXT4_GET_BLOCKS_EXTEND_DISKSIZE 0x0004 /* Caller is from the delayed allocation writeout path, so set the magic i_delalloc_reserve_flag after taking the inode allocation semaphore for */ -#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0008 +#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004 /* Call ext4_da_update_reserve_space() after successfully allocating the blocks */ -#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0010 +#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0008 /* diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index d4e99e96fddb..9c35a7b1f0ae 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2779,7 +2779,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, int err = 0, depth, ret, cache_type; unsigned int allocated = 0; struct ext4_allocation_request ar; - loff_t disksize; __clear_bit(BH_New, &bh_result->b_state); ext_debug("blocks %u/%u requested for inode %u\n", @@ -2969,14 +2968,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, newblock = ext_pblock(&newex); allocated = ext4_ext_get_actual_len(&newex); outnew: - if (flags & EXT4_GET_BLOCKS_EXTEND_DISKSIZE) { - disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); - if (disksize > EXT4_I(inode)->i_disksize) - EXT4_I(inode)->i_disksize = disksize; - } - set_buffer_new(bh_result); /* Cache only when it is _not_ an uninitialized extent */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 14c00fff3713..17ed0d244dbb 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -933,11 +933,8 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, int indirect_blks; int blocks_to_boundary = 0; int depth; - struct ext4_inode_info *ei = EXT4_I(inode); int count = 0; ext4_fsblk_t first_block = 0; - loff_t disksize; - J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)); J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); @@ -1003,19 +1000,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, if (!err) err = ext4_splice_branch(handle, inode, iblock, partial, indirect_blks, count); - /* - * i_disksize growing is protected by i_data_sem. Don't forget to - * protect it if you're about to implement concurrent - * ext4_get_block() -bzzz - */ - if (!err && (flags & EXT4_GET_BLOCKS_EXTEND_DISKSIZE)) { - disksize = ((loff_t) iblock + count) << inode->i_blkbits; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); - if (disksize > ei->i_disksize) - ei->i_disksize = disksize; - } - if (err) + else goto cleanup; set_buffer_new(bh_result); @@ -1321,7 +1306,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, { struct buffer_head dummy; int fatal = 0, err; - int flags = EXT4_GET_BLOCKS_EXTEND_DISKSIZE; + int flags = 0; J_ASSERT(handle != NULL || create == 0); @@ -2153,9 +2138,7 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) } /* - * Update on-disk size along with block allocation we don't - * use EXT4_GET_BLOCKS_EXTEND_DISKSIZE as size may change - * within already allocated block -bzzz + * Update on-disk size along with block allocation. */ disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits; if (disksize > i_size_read(mpd->inode)) From b31e15527a9bb71b6a11a425d17ce139a62f5af5 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Thu, 4 Jun 2009 17:36:36 -0400 Subject: [PATCH 44/49] ext4: Change all super.c messages to print the device This patch changes ext4 super.c to include the device name with all warning/error messages, by using a new utility function ext4_msg. It's a rather large patch, but very mechanic. I left debug printks alone. This is a straightforward port of a patch which Andi Kleen did for ext3. Cc: Andi Kleen Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 + fs/ext4/super.c | 462 ++++++++++++++++++++++++------------------------ 2 files changed, 235 insertions(+), 229 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 59657ff7b8f4..cc7d5edc38c9 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1401,6 +1401,8 @@ extern void ext4_abort(struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); extern void ext4_warning(struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); +extern void ext4_msg(struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); extern void ext4_grp_locked_error(struct super_block *, ext4_group_t, const char *, const char *, ...) __attribute__ ((format (printf, 4, 5))); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0a97b1ad3e19..c191d0f65fed 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -306,7 +306,7 @@ static void ext4_handle_error(struct super_block *sb) jbd2_journal_abort(journal, -EIO); } if (test_opt(sb, ERRORS_RO)) { - printk(KERN_CRIT "Remounting filesystem read-only\n"); + ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); sb->s_flags |= MS_RDONLY; } ext4_commit_super(sb, 1); @@ -399,8 +399,6 @@ void ext4_abort(struct super_block *sb, const char *function, { va_list args; - printk(KERN_CRIT "ext4_abort called.\n"); - va_start(args, fmt); printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function); vprintk(fmt, args); @@ -413,7 +411,7 @@ void ext4_abort(struct super_block *sb, const char *function, if (sb->s_flags & MS_RDONLY) return; - printk(KERN_CRIT "Remounting filesystem read-only\n"); + ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; sb->s_flags |= MS_RDONLY; EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT; @@ -421,6 +419,18 @@ void ext4_abort(struct super_block *sb, const char *function, jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); } +void ext4_msg (struct super_block * sb, const char *prefix, + const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + printk("%sEXT4-fs (%s): ", prefix, sb->s_id); + vprintk(fmt, args); + printk("\n"); + va_end(args); +} + void ext4_warning(struct super_block *sb, const char *function, const char *fmt, ...) { @@ -499,7 +509,7 @@ void ext4_update_dynamic_rev(struct super_block *sb) /* * Open the external journal device */ -static struct block_device *ext4_blkdev_get(dev_t dev) +static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb) { struct block_device *bdev; char b[BDEVNAME_SIZE]; @@ -510,7 +520,7 @@ static struct block_device *ext4_blkdev_get(dev_t dev) return bdev; fail: - printk(KERN_ERR "EXT4-fs: failed to open journal device %s: %ld\n", + ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld", __bdevname(dev, b), PTR_ERR(bdev)); return NULL; } @@ -546,8 +556,8 @@ static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi) { struct list_head *l; - printk(KERN_ERR "sb orphan head is %d\n", - le32_to_cpu(sbi->s_es->s_last_orphan)); + ext4_msg(sb, KERN_ERR, "sb orphan head is %d", + le32_to_cpu(sbi->s_es->s_last_orphan)); printk(KERN_ERR "sb_info orphan list:\n"); list_for_each(l, &sbi->s_orphan) { @@ -678,8 +688,9 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) static void ext4_destroy_inode(struct inode *inode) { if (!list_empty(&(EXT4_I(inode)->i_orphan))) { - printk("EXT4 Inode %p: orphan list check failed!\n", - EXT4_I(inode)); + ext4_msg(inode->i_sb, KERN_ERR, + "Inode %lu (%p): orphan list check failed!", + inode->i_ino, EXT4_I(inode)); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4, EXT4_I(inode), sizeof(struct ext4_inode_info), true); @@ -1239,8 +1250,7 @@ static int parse_options(char *options, struct super_block *sb, #else case Opt_user_xattr: case Opt_nouser_xattr: - printk(KERN_ERR "EXT4 (no)user_xattr options " - "not supported\n"); + ext4_msg(sb, KERN_ERR, "(no)user_xattr options not supported"); break; #endif #ifdef CONFIG_EXT4_FS_POSIX_ACL @@ -1253,8 +1263,7 @@ static int parse_options(char *options, struct super_block *sb, #else case Opt_acl: case Opt_noacl: - printk(KERN_ERR "EXT4 (no)acl options " - "not supported\n"); + ext4_msg(sb, KERN_ERR, "(no)acl options not supported"); break; #endif case Opt_journal_update: @@ -1264,16 +1273,16 @@ static int parse_options(char *options, struct super_block *sb, user to specify an existing inode to be the journal file. */ if (is_remount) { - printk(KERN_ERR "EXT4-fs: cannot specify " - "journal on remount\n"); + ext4_msg(sb, KERN_ERR, + "Cannot specify journal on remount"); return 0; } set_opt(sbi->s_mount_opt, UPDATE_JOURNAL); break; case Opt_journal_dev: if (is_remount) { - printk(KERN_ERR "EXT4-fs: cannot specify " - "journal on remount\n"); + ext4_msg(sb, KERN_ERR, + "Cannot specify journal on remount"); return 0; } if (match_int(&args[0], &option)) @@ -1327,9 +1336,8 @@ static int parse_options(char *options, struct super_block *sb, if (is_remount) { if ((sbi->s_mount_opt & EXT4_MOUNT_DATA_FLAGS) != data_opt) { - printk(KERN_ERR - "EXT4-fs: cannot change data " - "mode on remount\n"); + ext4_msg(sb, KERN_ERR, + "Cannot change data mode on remount"); return 0; } } else { @@ -1359,31 +1367,31 @@ static int parse_options(char *options, struct super_block *sb, set_qf_name: if (sb_any_quota_loaded(sb) && !sbi->s_qf_names[qtype]) { - printk(KERN_ERR - "EXT4-fs: Cannot change journaled " - "quota options when quota turned on.\n"); + ext4_msg(sb, KERN_ERR, + "Cannot change journaled " + "quota options when quota turned on"); return 0; } qname = match_strdup(&args[0]); if (!qname) { - printk(KERN_ERR - "EXT4-fs: not enough memory for " - "storing quotafile name.\n"); + ext4_msg(sb, KERN_ERR, + "Not enough memory for " + "storing quotafile name"); return 0; } if (sbi->s_qf_names[qtype] && strcmp(sbi->s_qf_names[qtype], qname)) { - printk(KERN_ERR - "EXT4-fs: %s quota file already " - "specified.\n", QTYPE2NAME(qtype)); + ext4_msg(sb, KERN_ERR, + "%s quota file already " + "specified", QTYPE2NAME(qtype)); kfree(qname); return 0; } sbi->s_qf_names[qtype] = qname; if (strchr(sbi->s_qf_names[qtype], '/')) { - printk(KERN_ERR - "EXT4-fs: quotafile must be on " - "filesystem root.\n"); + ext4_msg(sb, KERN_ERR, + "quotafile must be on " + "filesystem root"); kfree(sbi->s_qf_names[qtype]); sbi->s_qf_names[qtype] = NULL; return 0; @@ -1398,9 +1406,9 @@ static int parse_options(char *options, struct super_block *sb, clear_qf_name: if (sb_any_quota_loaded(sb) && sbi->s_qf_names[qtype]) { - printk(KERN_ERR "EXT4-fs: Cannot change " + ext4_msg(sb, KERN_ERR, "Cannot change " "journaled quota options when " - "quota turned on.\n"); + "quota turned on"); return 0; } /* @@ -1417,9 +1425,9 @@ static int parse_options(char *options, struct super_block *sb, set_qf_format: if (sb_any_quota_loaded(sb) && sbi->s_jquota_fmt != qfmt) { - printk(KERN_ERR "EXT4-fs: Cannot change " + ext4_msg(sb, KERN_ERR, "Cannot change " "journaled quota options when " - "quota turned on.\n"); + "quota turned on"); return 0; } sbi->s_jquota_fmt = qfmt; @@ -1435,8 +1443,8 @@ static int parse_options(char *options, struct super_block *sb, break; case Opt_noquota: if (sb_any_quota_loaded(sb)) { - printk(KERN_ERR "EXT4-fs: Cannot change quota " - "options when quota turned on.\n"); + ext4_msg(sb, KERN_ERR, "Cannot change quota " + "options when quota turned on"); return 0; } clear_opt(sbi->s_mount_opt, QUOTA); @@ -1447,8 +1455,8 @@ static int parse_options(char *options, struct super_block *sb, case Opt_quota: case Opt_usrquota: case Opt_grpquota: - printk(KERN_ERR - "EXT4-fs: quota options not supported.\n"); + ext4_msg(sb, KERN_ERR, + "quota options not supported"); break; case Opt_usrjquota: case Opt_grpjquota: @@ -1456,9 +1464,8 @@ static int parse_options(char *options, struct super_block *sb, case Opt_offgrpjquota: case Opt_jqfmt_vfsold: case Opt_jqfmt_vfsv0: - printk(KERN_ERR - "EXT4-fs: journaled quota options not " - "supported.\n"); + ext4_msg(sb, KERN_ERR, + "journaled quota options not supported"); break; case Opt_noquota: break; @@ -1483,8 +1490,9 @@ static int parse_options(char *options, struct super_block *sb, break; case Opt_resize: if (!is_remount) { - printk("EXT4-fs: resize option only available " - "for remount\n"); + ext4_msg(sb, KERN_ERR, + "resize option only available " + "for remount"); return 0; } if (match_int(&args[0], &option) != 0) @@ -1526,8 +1534,9 @@ static int parse_options(char *options, struct super_block *sb, if (option < 0 || option > (1 << 30)) return 0; if (!is_power_of_2(option)) { - printk(KERN_ERR "EXT4-fs: inode_readahead_blks" - " must be a power of 2\n"); + ext4_msg(sb, KERN_ERR, + "EXT4-fs: inode_readahead_blks" + " must be a power of 2"); return 0; } sbi->s_inode_readahead_blks = option; @@ -1554,9 +1563,9 @@ static int parse_options(char *options, struct super_block *sb, set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC); break; default: - printk(KERN_ERR - "EXT4-fs: Unrecognized mount option \"%s\" " - "or missing value\n", p); + ext4_msg(sb, KERN_ERR, + "Unrecognized mount option \"%s\" " + "or missing value", p); return 0; } } @@ -1574,21 +1583,21 @@ static int parse_options(char *options, struct super_block *sb, (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)) || (sbi->s_qf_names[GRPQUOTA] && (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA))) { - printk(KERN_ERR "EXT4-fs: old and new quota " - "format mixing.\n"); + ext4_msg(sb, KERN_ERR, "old and new quota " + "format mixing"); return 0; } if (!sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT4-fs: journaled quota format " - "not specified.\n"); + ext4_msg(sb, KERN_ERR, "journaled quota format " + "not specified"); return 0; } } else { if (sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT4-fs: journaled quota format " + ext4_msg(sb, KERN_ERR, "journaled quota format " "specified with no journaling " - "enabled.\n"); + "enabled"); return 0; } } @@ -1603,31 +1612,31 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int res = 0; if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { - printk(KERN_ERR "EXT4-fs warning: revision level too high, " - "forcing read-only mode\n"); + ext4_msg(sb, KERN_ERR, "revision level too high, " + "forcing read-only mode"); res = MS_RDONLY; } if (read_only) return res; if (!(sbi->s_mount_state & EXT4_VALID_FS)) - printk(KERN_WARNING "EXT4-fs warning: mounting unchecked fs, " - "running e2fsck is recommended\n"); + ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, " + "running e2fsck is recommended"); else if ((sbi->s_mount_state & EXT4_ERROR_FS)) - printk(KERN_WARNING - "EXT4-fs warning: mounting fs with errors, " - "running e2fsck is recommended\n"); + ext4_msg(sb, KERN_WARNING, + "warning: mounting fs with errors, " + "running e2fsck is recommended"); else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 && le16_to_cpu(es->s_mnt_count) >= (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) - printk(KERN_WARNING - "EXT4-fs warning: maximal mount count reached, " - "running e2fsck is recommended\n"); + ext4_msg(sb, KERN_WARNING, + "warning: maximal mount count reached, " + "running e2fsck is recommended"); else if (le32_to_cpu(es->s_checkinterval) && (le32_to_cpu(es->s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= get_seconds())) - printk(KERN_WARNING - "EXT4-fs warning: checktime reached, " - "running e2fsck is recommended\n"); + ext4_msg(sb, KERN_WARNING, + "warning: checktime reached, " + "running e2fsck is recommended"); if (!sbi->s_journal) es->s_state &= cpu_to_le16(~EXT4_VALID_FS); if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) @@ -1649,11 +1658,11 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, sbi->s_mount_opt); if (EXT4_SB(sb)->s_journal) { - printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n", - sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" : + ext4_msg(sb, KERN_INFO, "%s journal on %s", + EXT4_SB(sb)->s_journal->j_inode ? "internal" : "external", EXT4_SB(sb)->s_journal->j_devname); } else { - printk(KERN_INFO "EXT4 FS on %s, no journal\n", sb->s_id); + ext4_msg(sb, KERN_INFO, "no journal"); } return res; } @@ -1688,8 +1697,8 @@ static int ext4_fill_flex_info(struct super_block *sb) memset(sbi->s_flex_groups, 0, size); } if (sbi->s_flex_groups == NULL) { - printk(KERN_ERR "EXT4-fs: not enough memory for " - "%u flex groups\n", flex_group_count); + ext4_msg(sb, KERN_ERR, "not enough memory for " + "%u flex groups", flex_group_count); goto failed; } @@ -1775,32 +1784,32 @@ static int ext4_check_descriptors(struct super_block *sb) block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap < first_block || block_bitmap > last_block) { - printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " - "(block %llu)!\n", i, block_bitmap); + "(block %llu)!", i, block_bitmap); return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); if (inode_bitmap < first_block || inode_bitmap > last_block) { - printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " - "(block %llu)!\n", i, inode_bitmap); + "(block %llu)!", i, inode_bitmap); return 0; } inode_table = ext4_inode_table(sb, gdp); if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { - printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u not in group " - "(block %llu)!\n", i, inode_table); + "(block %llu)!", i, inode_table); return 0; } ext4_lock_group(sb, i); if (!ext4_group_desc_csum_verify(sbi, i, gdp)) { - printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " - "Checksum for group %u failed (%u!=%u)\n", - i, le16_to_cpu(ext4_group_desc_csum(sbi, i, - gdp)), le16_to_cpu(gdp->bg_checksum)); + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Checksum for group %u failed (%u!=%u)", + i, le16_to_cpu(ext4_group_desc_csum(sbi, i, + gdp)), le16_to_cpu(gdp->bg_checksum)); if (!(sb->s_flags & MS_RDONLY)) { ext4_unlock_group(sb, i); return 0; @@ -1847,8 +1856,8 @@ static void ext4_orphan_cleanup(struct super_block *sb, } if (bdev_read_only(sb->s_bdev)) { - printk(KERN_ERR "EXT4-fs: write access " - "unavailable, skipping orphan cleanup.\n"); + ext4_msg(sb, KERN_ERR, "write access " + "unavailable, skipping orphan cleanup"); return; } @@ -1862,8 +1871,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, } if (s_flags & MS_RDONLY) { - printk(KERN_INFO "EXT4-fs: %s: orphan cleanup on readonly fs\n", - sb->s_id); + ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs"); sb->s_flags &= ~MS_RDONLY; } #ifdef CONFIG_QUOTA @@ -1874,9 +1882,9 @@ static void ext4_orphan_cleanup(struct super_block *sb, if (EXT4_SB(sb)->s_qf_names[i]) { int ret = ext4_quota_on_mount(sb, i); if (ret < 0) - printk(KERN_ERR - "EXT4-fs: Cannot turn on journaled " - "quota: error %d\n", ret); + ext4_msg(sb, KERN_ERR, + "Cannot turn on journaled " + "quota: error %d", ret); } } #endif @@ -1893,16 +1901,16 @@ static void ext4_orphan_cleanup(struct super_block *sb, list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan); vfs_dq_init(inode); if (inode->i_nlink) { - printk(KERN_DEBUG - "%s: truncating inode %lu to %lld bytes\n", + ext4_msg(sb, KERN_DEBUG, + "%s: truncating inode %lu to %lld bytes", __func__, inode->i_ino, inode->i_size); jbd_debug(2, "truncating inode %lu to %lld bytes\n", inode->i_ino, inode->i_size); ext4_truncate(inode); nr_truncates++; } else { - printk(KERN_DEBUG - "%s: deleting unreferenced inode %lu\n", + ext4_msg(sb, KERN_DEBUG, + "%s: deleting unreferenced inode %lu", __func__, inode->i_ino); jbd_debug(2, "deleting unreferenced inode %lu\n", inode->i_ino); @@ -1914,11 +1922,11 @@ static void ext4_orphan_cleanup(struct super_block *sb, #define PLURAL(x) (x), ((x) == 1) ? "" : "s" if (nr_orphans) - printk(KERN_INFO "EXT4-fs: %s: %d orphan inode%s deleted\n", - sb->s_id, PLURAL(nr_orphans)); + ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted", + PLURAL(nr_orphans)); if (nr_truncates) - printk(KERN_INFO "EXT4-fs: %s: %d truncate%s cleaned up\n", - sb->s_id, PLURAL(nr_truncates)); + ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up", + PLURAL(nr_truncates)); #ifdef CONFIG_QUOTA /* Turn quotas off */ for (i = 0; i < MAXQUOTAS; i++) { @@ -2307,7 +2315,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); if (!blocksize) { - printk(KERN_ERR "EXT4-fs: unable to set blocksize\n"); + ext4_msg(sb, KERN_ERR, "unable to set blocksize"); goto out_fail; } @@ -2323,7 +2331,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (!(bh = sb_bread(sb, logical_sb_block))) { - printk(KERN_ERR "EXT4-fs: unable to read superblock\n"); + ext4_msg(sb, KERN_ERR, "unable to read superblock"); goto out_fail; } /* @@ -2393,9 +2401,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) (EXT4_HAS_COMPAT_FEATURE(sb, ~0U) || EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) || EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U))) - printk(KERN_WARNING - "EXT4-fs warning: feature flags set on rev 0 fs, " - "running e2fsck is recommended\n"); + ext4_msg(sb, KERN_WARNING, + "feature flags set on rev 0 fs, " + "running e2fsck is recommended"); /* * Check feature flags regardless of the revision level, since we @@ -2404,16 +2412,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP); if (features) { - printk(KERN_ERR "EXT4-fs: %s: couldn't mount because of " - "unsupported optional features (%x).\n", sb->s_id, + 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) { - printk(KERN_ERR "EXT4-fs: %s: couldn't mount RDWR because of " - "unsupported optional features (%x).\n", sb->s_id, + 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)); goto failed_mount; @@ -2427,9 +2437,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ if (sizeof(root->i_blocks) < sizeof(u64) && !(sb->s_flags & MS_RDONLY)) { - printk(KERN_ERR "EXT4-fs: %s: Filesystem with huge " + ext4_msg(sb, KERN_ERR, "Filesystem with huge " "files cannot be mounted read-write " - "without CONFIG_LBD.\n", sb->s_id); + "without CONFIG_LBD"); goto failed_mount; } } @@ -2437,16 +2447,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (blocksize < EXT4_MIN_BLOCK_SIZE || blocksize > EXT4_MAX_BLOCK_SIZE) { - printk(KERN_ERR - "EXT4-fs: Unsupported filesystem blocksize %d on %s.\n", - blocksize, sb->s_id); + ext4_msg(sb, KERN_ERR, + "Unsupported filesystem blocksize %d", blocksize); goto failed_mount; } if (sb->s_blocksize != blocksize) { /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { - printk(KERN_ERR "EXT4-fs: bad block size %d.\n", + ext4_msg(sb, KERN_ERR, "bad block size %d", blocksize); goto failed_mount; } @@ -2456,15 +2465,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) offset = do_div(logical_sb_block, blocksize); bh = sb_bread(sb, logical_sb_block); if (!bh) { - printk(KERN_ERR - "EXT4-fs: Can't read superblock on 2nd try.\n"); + ext4_msg(sb, KERN_ERR, + "Can't read superblock on 2nd try"); goto failed_mount; } es = (struct ext4_super_block *)(((char *)bh->b_data) + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { - printk(KERN_ERR - "EXT4-fs: Magic mismatch, very weird !\n"); + ext4_msg(sb, KERN_ERR, + "Magic mismatch, very weird!"); goto failed_mount; } } @@ -2482,8 +2491,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || (!is_power_of_2(sbi->s_inode_size)) || (sbi->s_inode_size > blocksize)) { - printk(KERN_ERR - "EXT4-fs: unsupported inode size: %d\n", + ext4_msg(sb, KERN_ERR, + "unsupported inode size: %d", sbi->s_inode_size); goto failed_mount; } @@ -2496,8 +2505,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || sbi->s_desc_size > EXT4_MAX_DESC_SIZE || !is_power_of_2(sbi->s_desc_size)) { - printk(KERN_ERR - "EXT4-fs: unsupported descriptor size %lu\n", + ext4_msg(sb, KERN_ERR, + "unsupported descriptor size %lu", sbi->s_desc_size); goto failed_mount; } @@ -2537,25 +2546,24 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (sbi->s_blocks_per_group > blocksize * 8) { - printk(KERN_ERR - "EXT4-fs: #blocks per group too big: %lu\n", + ext4_msg(sb, KERN_ERR, + "#blocks per group too big: %lu", sbi->s_blocks_per_group); goto failed_mount; } if (sbi->s_inodes_per_group > blocksize * 8) { - printk(KERN_ERR - "EXT4-fs: #inodes per group too big: %lu\n", + ext4_msg(sb, KERN_ERR, + "#inodes per group too big: %lu", sbi->s_inodes_per_group); goto failed_mount; } if (ext4_blocks_count(es) > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { - printk(KERN_ERR "EXT4-fs: filesystem on %s:" - " too large to mount safely\n", sb->s_id); + ext4_msg(sb, KERN_ERR, "filesystem" + " too large to mount safely"); if (sizeof(sector_t) < 8) - printk(KERN_WARNING "EXT4-fs: CONFIG_LBD not " - "enabled\n"); + ext4_msg(sb, KERN_WARNING, "CONFIG_LBD not enabled"); goto failed_mount; } @@ -2565,8 +2573,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* check blocks count against device size */ blocks_count = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits; if (blocks_count && ext4_blocks_count(es) > blocks_count) { - printk(KERN_WARNING "EXT4-fs: bad geometry: block count %llu " - "exceeds size of device (%llu blocks)\n", + ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu " + "exceeds size of device (%llu blocks)", ext4_blocks_count(es), blocks_count); goto failed_mount; } @@ -2576,10 +2584,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * of the filesystem. */ if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { - printk(KERN_WARNING "EXT4-fs: bad geometry: first data" - "block %u is beyond end of filesystem (%llu)\n", - le32_to_cpu(es->s_first_data_block), - ext4_blocks_count(es)); + ext4_msg(sb, KERN_WARNING, "bad geometry: first data" + "block %u is beyond end of filesystem (%llu)", + le32_to_cpu(es->s_first_data_block), + ext4_blocks_count(es)); goto failed_mount; } blocks_count = (ext4_blocks_count(es) - @@ -2587,9 +2595,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) EXT4_BLOCKS_PER_GROUP(sb) - 1); do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { - printk(KERN_WARNING "EXT4-fs: groups count too large: %u " + ext4_msg(sb, KERN_WARNING, "groups count too large: %u " "(block count %llu, first data block %u, " - "blocks per group %lu)\n", sbi->s_groups_count, + "blocks per group %lu)", sbi->s_groups_count, ext4_blocks_count(es), le32_to_cpu(es->s_first_data_block), EXT4_BLOCKS_PER_GROUP(sb)); @@ -2601,7 +2609,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *), GFP_KERNEL); if (sbi->s_group_desc == NULL) { - printk(KERN_ERR "EXT4-fs: not enough memory\n"); + ext4_msg(sb, KERN_ERR, "not enough memory"); goto failed_mount; } @@ -2616,21 +2624,21 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) block = descriptor_loc(sb, logical_sb_block, i); sbi->s_group_desc[i] = sb_bread(sb, block); if (!sbi->s_group_desc[i]) { - printk(KERN_ERR "EXT4-fs: " - "can't read group descriptor %d\n", i); + ext4_msg(sb, KERN_ERR, + "can't read group descriptor %d", i); db_count = i; goto failed_mount2; } } if (!ext4_check_descriptors(sb)) { - printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n"); + ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); goto failed_mount2; } if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) if (!ext4_fill_flex_info(sb)) { - printk(KERN_ERR - "EXT4-fs: unable to initialize " - "flex_bg meta info!\n"); + ext4_msg(sb, KERN_ERR, + "unable to initialize " + "flex_bg meta info!"); goto failed_mount2; } @@ -2652,7 +2660,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0); } if (err) { - printk(KERN_ERR "EXT4-fs: insufficient memory\n"); + ext4_msg(sb, KERN_ERR, "insufficient memory"); goto failed_mount3; } @@ -2692,13 +2700,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount3; if (!(sb->s_flags & MS_RDONLY) && EXT4_SB(sb)->s_journal->j_failed_commit) { - printk(KERN_CRIT "EXT4-fs error (device %s): " + ext4_msg(sb, KERN_CRIT, "error: " "ext4_fill_super: Journal transaction " - "%u is corrupt\n", sb->s_id, + "%u is corrupt", EXT4_SB(sb)->s_journal->j_failed_commit); if (test_opt(sb, ERRORS_RO)) { - printk(KERN_CRIT - "Mounting filesystem read-only\n"); + ext4_msg(sb, KERN_CRIT, + "Mounting filesystem read-only"); sb->s_flags |= MS_RDONLY; EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); @@ -2712,8 +2720,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) && EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) { - printk(KERN_ERR "EXT4-fs: required journal recovery " - "suppressed and not mounted read-only\n"); + ext4_msg(sb, KERN_ERR, "required journal recovery " + "suppressed and not mounted read-only"); goto failed_mount4; } else { clear_opt(sbi->s_mount_opt, DATA_FLAGS); @@ -2726,7 +2734,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (ext4_blocks_count(es) > 0xffffffffULL && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_64BIT)) { - printk(KERN_ERR "EXT4-fs: Failed to set 64-bit journal feature\n"); + ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); goto failed_mount4; } @@ -2764,8 +2772,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) case EXT4_MOUNT_WRITEBACK_DATA: if (!jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { - printk(KERN_ERR "EXT4-fs: Journal does not support " - "requested data journaling mode\n"); + ext4_msg(sb, KERN_ERR, "Journal does not support " + "requested data journaling mode"); goto failed_mount4; } default: @@ -2777,8 +2785,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (test_opt(sb, NOBH)) { if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) { - printk(KERN_WARNING "EXT4-fs: Ignoring nobh option - " - "its supported only with writeback mode\n"); + ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - " + "its supported only with writeback mode"); clear_opt(sbi->s_mount_opt, NOBH); } } @@ -2789,18 +2797,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) root = ext4_iget(sb, EXT4_ROOT_INO); if (IS_ERR(root)) { - printk(KERN_ERR "EXT4-fs: get root inode failed\n"); + ext4_msg(sb, KERN_ERR, "get root inode failed"); ret = PTR_ERR(root); goto failed_mount4; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { iput(root); - printk(KERN_ERR "EXT4-fs: corrupt root inode, run e2fsck\n"); + ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck"); goto failed_mount4; } sb->s_root = d_alloc_root(root); if (!sb->s_root) { - printk(KERN_ERR "EXT4-fs: get root dentry failed\n"); + ext4_msg(sb, KERN_ERR, "get root dentry failed"); iput(root); ret = -ENOMEM; goto failed_mount4; @@ -2829,29 +2837,29 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_inode_size) { sbi->s_want_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; - printk(KERN_INFO "EXT4-fs: required extra inode space not" - "available.\n"); + ext4_msg(sb, KERN_INFO, "required extra inode space not" + "available"); } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { - printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - " - "requested data journaling mode\n"); + ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - " + "requested data journaling mode"); clear_opt(sbi->s_mount_opt, DELALLOC); } else if (test_opt(sb, DELALLOC)) - printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n"); + ext4_msg(sb, KERN_INFO, "delayed allocation enabled"); err = ext4_setup_system_zone(sb); if (err) { - printk(KERN_ERR "EXT4-fs: failed to initialize system " - "zone (%d)\n", err); + ext4_msg(sb, KERN_ERR, "failed to initialize system " + "zone (%d)\n", err); goto failed_mount4; } ext4_ext_init(sb); err = ext4_mb_init(sb, needs_recovery); if (err) { - printk(KERN_ERR "EXT4-fs: failed to initalize mballoc (%d)\n", - err); + ext4_msg(sb, KERN_ERR, "failed to initalize mballoc (%d)", + err); goto failed_mount4; } @@ -2869,7 +2877,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; if (needs_recovery) { - printk(KERN_INFO "EXT4-fs: recovery complete.\n"); + ext4_msg(sb, KERN_INFO, "recovery complete"); ext4_mark_recovery_complete(sb, es); } if (EXT4_SB(sb)->s_journal) { @@ -2882,20 +2890,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } else descr = "out journal"; - printk(KERN_INFO "EXT4-fs: mounted filesystem %s with%s\n", - sb->s_id, descr); + ext4_msg(sb, KERN_INFO, "mounted filesystem with%s", descr); lock_kernel(); return 0; cantfind_ext4: if (!silent) - printk(KERN_ERR "VFS: Can't find ext4 filesystem on dev %s.\n", - sb->s_id); + ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto failed_mount; failed_mount4: - printk(KERN_ERR "EXT4-fs (device %s): mount failed\n", sb->s_id); + ext4_msg(sb, KERN_ERR, "mount failed"); ext4_release_system_zone(sb); if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); @@ -2973,27 +2979,27 @@ static journal_t *ext4_get_journal(struct super_block *sb, journal_inode = ext4_iget(sb, journal_inum); if (IS_ERR(journal_inode)) { - printk(KERN_ERR "EXT4-fs: no journal found.\n"); + ext4_msg(sb, KERN_ERR, "no journal found"); return NULL; } if (!journal_inode->i_nlink) { make_bad_inode(journal_inode); iput(journal_inode); - printk(KERN_ERR "EXT4-fs: journal inode is deleted.\n"); + ext4_msg(sb, KERN_ERR, "journal inode is deleted"); return NULL; } jbd_debug(2, "Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); if (!S_ISREG(journal_inode->i_mode)) { - printk(KERN_ERR "EXT4-fs: invalid journal inode.\n"); + ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); return NULL; } journal = jbd2_journal_init_inode(journal_inode); if (!journal) { - printk(KERN_ERR "EXT4-fs: Could not load journal inode\n"); + ext4_msg(sb, KERN_ERR, "Could not load journal inode"); iput(journal_inode); return NULL; } @@ -3017,13 +3023,13 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)); - bdev = ext4_blkdev_get(j_dev); + bdev = ext4_blkdev_get(j_dev, sb); if (bdev == NULL) return NULL; if (bd_claim(bdev, sb)) { - printk(KERN_ERR - "EXT4-fs: failed to claim external journal device.\n"); + ext4_msg(sb, KERN_ERR, + "failed to claim external journal device"); blkdev_put(bdev, FMODE_READ|FMODE_WRITE); return NULL; } @@ -3031,8 +3037,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, blocksize = sb->s_blocksize; hblock = bdev_hardsect_size(bdev); if (blocksize < hblock) { - printk(KERN_ERR - "EXT4-fs: blocksize too small for journal device.\n"); + ext4_msg(sb, KERN_ERR, + "blocksize too small for journal device"); goto out_bdev; } @@ -3040,8 +3046,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, offset = EXT4_MIN_BLOCK_SIZE % blocksize; set_blocksize(bdev, blocksize); if (!(bh = __bread(bdev, sb_block, blocksize))) { - printk(KERN_ERR "EXT4-fs: couldn't read superblock of " - "external journal\n"); + ext4_msg(sb, KERN_ERR, "couldn't read superblock of " + "external journal"); goto out_bdev; } @@ -3049,14 +3055,14 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { - printk(KERN_ERR "EXT4-fs: external journal has " - "bad superblock\n"); + ext4_msg(sb, KERN_ERR, "external journal has " + "bad superblock"); brelse(bh); goto out_bdev; } if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { - printk(KERN_ERR "EXT4-fs: journal UUID does not match\n"); + ext4_msg(sb, KERN_ERR, "journal UUID does not match"); brelse(bh); goto out_bdev; } @@ -3068,19 +3074,19 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, journal = jbd2_journal_init_dev(bdev, sb->s_bdev, start, len, blocksize); if (!journal) { - printk(KERN_ERR "EXT4-fs: failed to create device journal\n"); + ext4_msg(sb, KERN_ERR, "failed to create device journal"); goto out_bdev; } journal->j_private = sb; ll_rw_block(READ, 1, &journal->j_sb_buffer); wait_on_buffer(journal->j_sb_buffer); if (!buffer_uptodate(journal->j_sb_buffer)) { - printk(KERN_ERR "EXT4-fs: I/O error on journal device\n"); + ext4_msg(sb, KERN_ERR, "I/O error on journal device"); goto out_journal; } if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { - printk(KERN_ERR "EXT4-fs: External journal has more than one " - "user (unsupported) - %d\n", + ext4_msg(sb, KERN_ERR, "External journal has more than one " + "user (unsupported) - %d", be32_to_cpu(journal->j_superblock->s_nr_users)); goto out_journal; } @@ -3109,8 +3115,8 @@ static int ext4_load_journal(struct super_block *sb, if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { - printk(KERN_INFO "EXT4-fs: external journal device major/minor " - "numbers have changed\n"); + ext4_msg(sb, KERN_INFO, "external journal device major/minor " + "numbers have changed"); journal_dev = new_decode_dev(journal_devnum); } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); @@ -3124,21 +3130,21 @@ static int ext4_load_journal(struct super_block *sb, */ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) { if (sb->s_flags & MS_RDONLY) { - printk(KERN_INFO "EXT4-fs: INFO: recovery " - "required on readonly filesystem.\n"); + ext4_msg(sb, KERN_INFO, "INFO: recovery " + "required on readonly filesystem"); if (really_read_only) { - printk(KERN_ERR "EXT4-fs: write access " - "unavailable, cannot proceed.\n"); + ext4_msg(sb, KERN_ERR, "write access " + "unavailable, cannot proceed"); return -EROFS; } - printk(KERN_INFO "EXT4-fs: write access will " - "be enabled during recovery.\n"); + ext4_msg(sb, KERN_INFO, "write access will " + "be enabled during recovery"); } } if (journal_inum && journal_dev) { - printk(KERN_ERR "EXT4-fs: filesystem has both journal " - "and inode journals!\n"); + ext4_msg(sb, KERN_ERR, "filesystem has both journal " + "and inode journals!"); return -EINVAL; } @@ -3151,14 +3157,14 @@ static int ext4_load_journal(struct super_block *sb, } if (journal->j_flags & JBD2_BARRIER) - printk(KERN_INFO "EXT4-fs: barriers enabled\n"); + ext4_msg(sb, KERN_INFO, "barriers enabled"); else - printk(KERN_INFO "EXT4-fs: barriers disabled\n"); + ext4_msg(sb, KERN_INFO, "barriers disabled"); if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) { err = jbd2_journal_update_format(journal); if (err) { - printk(KERN_ERR "EXT4-fs: error updating journal.\n"); + ext4_msg(sb, KERN_ERR, "error updating journal"); jbd2_journal_destroy(journal); return err; } @@ -3170,7 +3176,7 @@ static int ext4_load_journal(struct super_block *sb, err = jbd2_journal_load(journal); if (err) { - printk(KERN_ERR "EXT4-fs: error loading journal.\n"); + ext4_msg(sb, KERN_ERR, "error loading journal"); jbd2_journal_destroy(journal); return err; } @@ -3206,8 +3212,8 @@ static int ext4_commit_super(struct super_block *sb, int sync) * be remapped. Nothing we can do but to retry the * write and hope for the best. */ - printk(KERN_ERR "EXT4-fs: previous I/O error to " - "superblock detected for %s.\n", sb->s_id); + ext4_msg(sb, KERN_ERR, "previous I/O error to " + "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } @@ -3230,8 +3236,8 @@ static int ext4_commit_super(struct super_block *sb, int sync) error = buffer_write_io_error(sbh); if (error) { - printk(KERN_ERR "EXT4-fs: I/O error while writing " - "superblock for %s.\n", sb->s_id); + ext4_msg(sb, KERN_ERR, "I/O error while writing " + "superblock"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } @@ -3478,9 +3484,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) int ret; if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP))) { - printk(KERN_WARNING "EXT4-fs: %s: couldn't " + ext4_msg(sb, KERN_WARNING, "couldn't " "remount RDWR because of unsupported " - "optional features (%x).\n", sb->s_id, + "optional features (%x)", (le32_to_cpu(sbi->s_es->s_feature_ro_compat) & ~EXT4_FEATURE_RO_COMPAT_SUPP)); err = -EROFS; @@ -3496,9 +3502,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_get_group_desc(sb, g, NULL); if (!ext4_group_desc_csum_verify(sbi, g, gdp)) { - printk(KERN_ERR - "EXT4-fs: ext4_remount: " - "Checksum for group %u failed (%u!=%u)\n", + ext4_msg(sb, KERN_ERR, + "ext4_remount: Checksum for group %u failed (%u!=%u)", g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)), le16_to_cpu(gdp->bg_checksum)); err = -EINVAL; @@ -3512,11 +3517,10 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) * require a full umount/remount for now. */ if (es->s_last_orphan) { - printk(KERN_WARNING "EXT4-fs: %s: couldn't " + ext4_msg(sb, KERN_WARNING, "Couldn't " "remount RDWR because of unprocessed " "orphan inode list. Please " - "umount/remount instead.\n", - sb->s_id); + "umount/remount instead"); err = -EINVAL; goto restore_opts; } @@ -3772,9 +3776,9 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, if (EXT4_SB(sb)->s_qf_names[type]) { /* Quotafile not in fs root? */ if (path.dentry->d_parent != sb->s_root) - printk(KERN_WARNING - "EXT4-fs: Quota file not on filesystem root. " - "Journaled quota will not work.\n"); + ext4_msg(sb, KERN_WARNING, + "Quota file not on filesystem root. " + "Journaled quota will not work"); } /* @@ -3857,8 +3861,8 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, handle_t *handle = journal_current_handle(); if (EXT4_SB(sb)->s_journal && !handle) { - printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)" - " cancelled because transaction is not started.\n", + ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" + " cancelled because transaction is not started", (unsigned long long)off, (unsigned long long)len); return -EIO; } @@ -3930,10 +3934,10 @@ static struct file_system_type ext4_fs_type = { static int ext4dev_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data,struct vfsmount *mnt) { - printk(KERN_WARNING "EXT4-fs: Update your userspace programs " - "to mount using ext4\n"); - printk(KERN_WARNING "EXT4-fs: ext4dev backwards compatibility " - "will go away by 2.6.31\n"); + printk(KERN_WARNING "EXT4-fs (%s): Update your userspace programs " + "to mount using ext4\n", dev_name); + printk(KERN_WARNING "EXT4-fs (%s): ext4dev backwards compatibility " + "will go away by 2.6.31\n", dev_name); return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt); } From 1938a150c25bf7c2c47182e753a1038945b70b0e Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 5 Jun 2009 01:00:26 -0400 Subject: [PATCH 45/49] ext4: Avoid leaking blocks after a block allocation failure We should add inode to the orphan list in the same transaction as block allocation. This ensures that if we crash after a failed block allocation and before we do a vmtruncate we don't leak block (ie block marked as used in bitmap but not claimed by the inode). Signed-off-by: Aneesh Kumar K.V CC: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 17ed0d244dbb..8d215881172f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1459,7 +1459,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; - int ret, needed_blocks = ext4_writepage_trans_blocks(inode); + int ret, needed_blocks; handle_t *handle; int retries = 0; struct page *page; @@ -1470,6 +1470,11 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, "dev %s ino %lu pos %llu len %u flags %u", inode->i_sb->s_id, inode->i_ino, (unsigned long long) pos, len, flags); + /* + * Reserve one block more for addition to orphan list in case + * we allocate blocks but write fails for some reason + */ + needed_blocks = ext4_writepage_trans_blocks(inode) + 1; index = pos >> PAGE_CACHE_SHIFT; from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; @@ -1503,15 +1508,30 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, if (ret) { unlock_page(page); - ext4_journal_stop(handle); page_cache_release(page); /* * block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold i_mutex. + * + * Add inode to orphan list in case we crash before + * truncate finishes */ if (pos + len > inode->i_size) + ext4_orphan_add(handle, inode); + + ext4_journal_stop(handle); + if (pos + len > inode->i_size) { vmtruncate(inode, inode->i_size); + /* + * If vmtruncate failed early the inode might + * still be on the orphan list; we need to + * make sure the inode is removed from the + * orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) From f8514083cd61daef12fba5ef883ad9352c450428 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 5 Jun 2009 00:56:49 -0400 Subject: [PATCH 46/49] ext4: truncate the file properly if we fail to copy data from userspace In generic_perform_write if we fail to copy the user data we don't update the inode->i_size. We should truncate the file in the above case so that we don't have blocks allocated outside inode->i_size. Add the inode to orphan list in the same transaction as block allocation This ensures that if we crash in between the recovery would do the truncate. Signed-off-by: Aneesh Kumar K.V CC: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 128 ++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 102 insertions(+), 26 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8d215881172f..2c10d346f7a3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1549,6 +1549,52 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh) return ext4_handle_dirty_metadata(handle, NULL, bh); } +static int ext4_generic_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + int i_size_changed = 0; + struct inode *inode = mapping->host; + handle_t *handle = ext4_journal_current_handle(); + + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + + /* + * No need to use i_size_read() here, the i_size + * cannot change under us because we hold i_mutex. + * + * But it's important to update i_size while still holding page lock: + * page writeout could otherwise come in and zero beyond i_size. + */ + if (pos + copied > inode->i_size) { + i_size_write(inode, pos + copied); + i_size_changed = 1; + } + + if (pos + copied > EXT4_I(inode)->i_disksize) { + /* We need to mark inode dirty even if + * new_i_size is less that inode->i_size + * bu greater than i_disksize.(hint delalloc) + */ + ext4_update_i_disksize(inode, (pos + copied)); + i_size_changed = 1; + } + unlock_page(page); + page_cache_release(page); + + /* + * Don't mark the inode dirty under page lock. First, it unnecessarily + * makes the holding time of page lock longer. Second, it forces lock + * ordering of page lock and transaction start for journaling + * filesystems. + */ + if (i_size_changed) + ext4_mark_inode_dirty(handle, inode); + + return copied; +} + /* * We need to pick up the new inode size which generic_commit_write gave us * `file' can be NULL - eg, when called from page_symlink(). @@ -1572,21 +1618,15 @@ static int ext4_ordered_write_end(struct file *file, ret = ext4_jbd2_file_inode(handle, inode); if (ret == 0) { - loff_t new_i_size; - - new_i_size = pos + copied; - if (new_i_size > EXT4_I(inode)->i_disksize) { - ext4_update_i_disksize(inode, new_i_size); - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) - */ - ext4_mark_inode_dirty(handle, inode); - } - - ret2 = generic_write_end(file, mapping, pos, len, copied, + ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; + if (pos + len > inode->i_size) + /* if we have allocated more blocks and copied + * less. We will have blocks allocated outside + * inode->i_size. So truncate them + */ + ext4_orphan_add(handle, inode); if (ret2 < 0) ret = ret2; } @@ -1594,6 +1634,18 @@ static int ext4_ordered_write_end(struct file *file, if (!ret) ret = ret2; + if (pos + len > inode->i_size) { + vmtruncate(inode, inode->i_size); + /* + * If vmtruncate failed early the inode might still be + * on the orphan list; we need to make sure the inode + * is removed from the orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } + + return ret ? ret : copied; } @@ -1605,25 +1657,21 @@ static int ext4_writeback_write_end(struct file *file, handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; int ret = 0, ret2; - loff_t new_i_size; trace_mark(ext4_writeback_write_end, "dev %s ino %lu pos %llu len %u copied %u", inode->i_sb->s_id, inode->i_ino, (unsigned long long) pos, len, copied); - new_i_size = pos + copied; - if (new_i_size > EXT4_I(inode)->i_disksize) { - ext4_update_i_disksize(inode, new_i_size); - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) - */ - ext4_mark_inode_dirty(handle, inode); - } - - ret2 = generic_write_end(file, mapping, pos, len, copied, + ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; + if (pos + len > inode->i_size) + /* if we have allocated more blocks and copied + * less. We will have blocks allocated outside + * inode->i_size. So truncate them + */ + ext4_orphan_add(handle, inode); + if (ret2 < 0) ret = ret2; @@ -1631,6 +1679,17 @@ static int ext4_writeback_write_end(struct file *file, if (!ret) ret = ret2; + if (pos + len > inode->i_size) { + vmtruncate(inode, inode->i_size); + /* + * If vmtruncate failed early the inode might still be + * on the orphan list; we need to make sure the inode + * is removed from the orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } + return ret ? ret : copied; } @@ -1675,10 +1734,27 @@ static int ext4_journalled_write_end(struct file *file, } unlock_page(page); + page_cache_release(page); + if (pos + len > inode->i_size) + /* if we have allocated more blocks and copied + * less. We will have blocks allocated outside + * inode->i_size. So truncate them + */ + ext4_orphan_add(handle, inode); + ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; - page_cache_release(page); + if (pos + len > inode->i_size) { + vmtruncate(inode, inode->i_size); + /* + * If vmtruncate failed early the inode might still be + * on the orphan list; we need to make sure the inode + * is removed from the orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } return ret ? ret : copied; } From 9aee2286071c23c535fe9928eec1a26e0bcf256d Mon Sep 17 00:00:00 2001 From: Toshiyuki Okajima Date: Mon, 8 Jun 2009 12:41:35 -0400 Subject: [PATCH 47/49] ext4: fix dx_map_entry to support 256k directory blocks The dx_map_entry structure doesn't support over 64KB block size by current usage of its member("offs"). Because "offs" treats an offset of copies of the ext4_dir_entry_2 structure as is. This member size is 16 bits. But real offset for over 64KB(256KB) block size needs 18 bits. However, real offset keeps 4 byte boundary, so lower 2 bits is not used. Therefore, we do the following to fix this limitation: For "store": we divide the real offset by 4 and then store this result to "offs" member. For "use": we multiply "offs" member by 4 and then use this result as real offset. Signed-off-by: Toshiyuki Okajima Signed-off-by: "Theodore Ts'o" --- fs/ext4/namei.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index f2bc160463b7..07eb6649e4fa 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -749,7 +749,7 @@ static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize, ext4fs_dirhash(de->name, de->name_len, &h); map_tail--; map_tail->hash = h.hash; - map_tail->offs = (u16) ((char *) de - base); + map_tail->offs = ((char *) de - base)>>2; map_tail->size = le16_to_cpu(de->rec_len); count++; cond_resched(); @@ -1147,7 +1147,8 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count, unsigned rec_len = 0; while (count--) { - struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + map->offs); + struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) + (from + (map->offs<<2)); rec_len = EXT4_DIR_REC_LEN(de->name_len); memcpy (to, de, rec_len); ((struct ext4_dir_entry_2 *) to)->rec_len = From 0eab928221bac8895a0b494a16a8810002bd8645 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 9 Jun 2009 09:54:40 -0400 Subject: [PATCH 48/49] ext4: Don't treat a truncation of a zero-length file as replace-via-truncate If a non-existent file is opened via O_WRONLY|O_CREAT|O_TRUNC, there's no need to treat this as a true file truncation, so we shouldn't activate the replace-via-truncate hueristic. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2c10d346f7a3..875db944b22f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4127,7 +4127,8 @@ void ext4_truncate(struct inode *inode) if (!ext4_can_truncate(inode)) return; - if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) + if (ei->i_disksize && 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) { From a41f20716975910d9beb90b7efc61107901492b8 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 10 Jun 2009 14:22:55 -0400 Subject: [PATCH 49/49] ext4: Avoid corrupting the uninitialized bit in the extent during truncate The unitialized bit was not properly getting preserved in in an extent which is partially truncated because the it was geting set to the value of the first extent to be removed or truncated as part of the truncate operation, and if there are multiple extents are getting removed or modified as part of the truncate operation, it is only the last extent which will might be partially truncated, and its uninitalized bit is not necessarily the same as the first extent to be truncated. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9c35a7b1f0ae..2593f748c3a4 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2083,12 +2083,16 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ex = EXT_LAST_EXTENT(eh); ex_ee_block = le32_to_cpu(ex->ee_block); - if (ext4_ext_is_uninitialized(ex)) - uninitialized = 1; ex_ee_len = ext4_ext_get_actual_len(ex); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { + + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + else + uninitialized = 0; + ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len); path[depth].p_ext = ex;