diff options
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/balloc.c | 88 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 80 | ||||
-rw-r--r-- | fs/ext4/resize.c | 3 | ||||
-rw-r--r-- | fs/ext4/super.c | 116 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 5 |
5 files changed, 223 insertions, 69 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index da994374ec3b..9cc80b9cc8d8 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -43,6 +43,46 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, } +static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block, + ext4_group_t block_group) +{ + ext4_group_t actual_group; + ext4_get_group_no_and_offset(sb, block, &actual_group, 0); + if (actual_group == block_group) + return 1; + return 0; +} + +static int ext4_group_used_meta_blocks(struct super_block *sb, + ext4_group_t block_group) +{ + ext4_fsblk_t tmp; + struct ext4_sb_info *sbi = EXT4_SB(sb); + /* block bitmap, inode bitmap, and inode table blocks */ + int used_blocks = sbi->s_itb_per_group + 2; + + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { + struct ext4_group_desc *gdp; + struct buffer_head *bh; + + gdp = ext4_get_group_desc(sb, block_group, &bh); + if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), + block_group)) + used_blocks--; + + if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), + block_group)) + used_blocks--; + + tmp = ext4_inode_table(sb, gdp); + for (; tmp < ext4_inode_table(sb, gdp) + + sbi->s_itb_per_group; tmp++) { + if (!ext4_block_in_group(sb, tmp, block_group)) + used_blocks -= 1; + } + } + return used_blocks; +} /* Initializes an uninitialized block bitmap if given, and returns the * number of blocks free in the group. */ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, @@ -105,20 +145,34 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, free_blocks = group_blocks - bit_max; if (bh) { - ext4_fsblk_t start; + ext4_fsblk_t start, tmp; + int flex_bg = 0; for (bit = 0; bit < bit_max; bit++) ext4_set_bit(bit, bh->b_data); start = ext4_group_first_block_no(sb, block_group); - /* Set bits for block and inode bitmaps, and inode table */ - ext4_set_bit(ext4_block_bitmap(sb, gdp) - start, bh->b_data); - ext4_set_bit(ext4_inode_bitmap(sb, gdp) - start, bh->b_data); - for (bit = (ext4_inode_table(sb, gdp) - start), - bit_max = bit + sbi->s_itb_per_group; bit < bit_max; bit++) - ext4_set_bit(bit, bh->b_data); + if (EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_FLEX_BG)) + flex_bg = 1; + /* Set bits for block and inode bitmaps, and inode table */ + tmp = ext4_block_bitmap(sb, gdp); + if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) + ext4_set_bit(tmp - start, bh->b_data); + + tmp = ext4_inode_bitmap(sb, gdp); + if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) + ext4_set_bit(tmp - start, bh->b_data); + + tmp = ext4_inode_table(sb, gdp); + for (; tmp < ext4_inode_table(sb, gdp) + + sbi->s_itb_per_group; tmp++) { + if (!flex_bg || + ext4_block_in_group(sb, tmp, block_group)) + ext4_set_bit(tmp - start, bh->b_data); + } /* * Also if the number of blocks within the group is * less than the blocksize * 8 ( which is the size @@ -126,8 +180,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, */ mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data); } - - return free_blocks - sbi->s_itb_per_group - 2; + return free_blocks - ext4_group_used_meta_blocks(sb, block_group); } @@ -287,11 +340,11 @@ read_block_bitmap(struct super_block *sb, ext4_group_t block_group) (int)block_group, (unsigned long long)bitmap_blk); return NULL; } - if (!ext4_valid_block_bitmap(sb, desc, block_group, bh)) { - put_bh(bh); - return NULL; - } - + ext4_valid_block_bitmap(sb, desc, block_group, bh); + /* + * file system mounted not to panic on error, + * continue with corrupt bitmap + */ return bh; } /* @@ -1770,7 +1823,12 @@ allocated: "Allocating block in system zone - " "blocks from %llu, length %lu", ret_block, num); - goto out; + /* + * claim_block marked the blocks we allocated + * as in use. So we may want to selectively + * mark some of the blocks as free + */ + goto retry_alloc; } performed_allocation = 1; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index fbec2ef93797..c9900aade150 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2639,8 +2639,7 @@ static int ext4_mb_init_per_dev_proc(struct super_block *sb) struct proc_dir_entry *proc; char devname[64]; - snprintf(devname, sizeof(devname) - 1, "%s", - bdevname(sb->s_bdev, devname)); + bdevname(sb->s_bdev, devname); sbi->s_mb_proc = proc_mkdir(devname, proc_root_ext4); MB_PROC_HANDLER(EXT4_MB_STATS_NAME, stats); @@ -2674,8 +2673,7 @@ static int ext4_mb_destroy_per_dev_proc(struct super_block *sb) if (sbi->s_mb_proc == NULL) return -EINVAL; - snprintf(devname, sizeof(devname) - 1, "%s", - bdevname(sb->s_bdev, devname)); + bdevname(sb->s_bdev, devname); remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_mb_proc); remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_mb_proc); remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_mb_proc); @@ -2738,7 +2736,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block; - int err; + int err, len; BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(ac->ac_b_ex.fe_len <= 0); @@ -2747,8 +2745,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, sbi = EXT4_SB(sb); es = sbi->s_es; - ext4_debug("using block group %lu(%d)\n", ac->ac_b_ex.fe_group, - gdp->bg_free_blocks_count); err = -EIO; bitmap_bh = read_block_bitmap(sb, ac->ac_b_ex.fe_group); @@ -2764,6 +2760,9 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, if (!gdp) goto out_err; + ext4_debug("using block group %lu(%d)\n", ac->ac_b_ex.fe_group, + gdp->bg_free_blocks_count); + err = ext4_journal_get_write_access(handle, gdp_bh); if (err) goto out_err; @@ -2772,14 +2771,27 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, + ac->ac_b_ex.fe_start + le32_to_cpu(es->s_first_data_block); - if (block == ext4_block_bitmap(sb, gdp) || - block == ext4_inode_bitmap(sb, gdp) || - in_range(block, ext4_inode_table(sb, gdp), - EXT4_SB(sb)->s_itb_per_group)) { - + 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)) { ext4_error(sb, __func__, "Allocating block in system zone - block = %llu", block); + /* File system mounted not to panic on error + * 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); + err = ext4_journal_dirty_metadata(handle, bitmap_bh); + if (!err) + err = -EAGAIN; + goto out_err; } #ifdef AGGRESSIVE_CHECK { @@ -2882,12 +2894,11 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, if (size < i_size_read(ac->ac_inode)) size = i_size_read(ac->ac_inode); - /* max available blocks in a free group */ - max = EXT4_BLOCKS_PER_GROUP(ac->ac_sb) - 1 - 1 - - EXT4_SB(ac->ac_sb)->s_itb_per_group; + /* max size of free chunks */ + max = 2 << bsbits; -#define NRL_CHECK_SIZE(req, size, max,bits) \ - (req <= (size) || max <= ((size) >> bits)) +#define NRL_CHECK_SIZE(req, size, max, chunk_size) \ + (req <= (size) || max <= (chunk_size)) /* first, try to predict filesize */ /* XXX: should this table be tunable? */ @@ -2906,16 +2917,16 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, size = 512 * 1024; } else if (size <= 1024 * 1024) { size = 1024 * 1024; - } else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, bsbits)) { + } else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, 2 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> - (20 - bsbits)) << 20; - size = 1024 * 1024; - } else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, bsbits)) { + (21 - bsbits)) << 21; + size = 2 * 1024 * 1024; + } else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, 4 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (22 - bsbits)) << 22; size = 4 * 1024 * 1024; } else if (NRL_CHECK_SIZE(ac->ac_o_ex.fe_len, - (8<<20)>>bsbits, max, bsbits)) { + (8<<20)>>bsbits, max, 8 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (23 - bsbits)) << 23; size = 8 * 1024 * 1024; @@ -3084,8 +3095,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { - unsigned len = ac->ac_o_ex.fe_len; - + unsigned int len = ac->ac_o_ex.fe_len; ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); @@ -4035,7 +4045,6 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, ac->ac_op = EXT4_MB_HISTORY_ALLOC; ext4_mb_normalize_request(ac, ar); - repeat: /* allocate space in core */ ext4_mb_regular_allocator(ac); @@ -4049,10 +4058,21 @@ repeat: } if (likely(ac->ac_status == AC_STATUS_FOUND)) { - ext4_mb_mark_diskspace_used(ac, handle); - *errp = 0; - block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); - ar->len = ac->ac_b_ex.fe_len; + *errp = ext4_mb_mark_diskspace_used(ac, handle); + if (*errp == -EAGAIN) { + ac->ac_b_ex.fe_group = 0; + ac->ac_b_ex.fe_start = 0; + ac->ac_b_ex.fe_len = 0; + ac->ac_status = AC_STATUS_CONTINUE; + goto repeat; + } else if (*errp) { + ac->ac_b_ex.fe_len = 0; + ar->len = 0; + ext4_mb_show_ac(ac); + } else { + block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); + ar->len = ac->ac_b_ex.fe_len; + } } else { freed = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len); if (freed) @@ -4239,6 +4259,8 @@ do_more: ext4_error(sb, __func__, "Freeing blocks in system zone - " "Block = %lu, count = %lu", block, count); + /* err = 0. ext4_std_error should be a no op */ + goto error_return; } BUFFER_TRACE(bitmap_bh, "getting write access"); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9f086a6a472b..9ecb92f68543 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -563,7 +563,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, } blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count; - data = (__le32 *)dind->b_data + EXT4_SB(sb)->s_gdb_count; + data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count % + EXT4_ADDR_PER_BLOCK(sb)); end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb); /* Get each reserved primary GDT block and verify it holds backups */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 52dd0679a4e2..cb96f127c366 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -671,6 +671,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) unsigned long def_mount_opts; struct super_block *sb = vfs->mnt_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); + journal_t *journal = sbi->s_journal; struct ext4_super_block *es = sbi->s_es; def_mount_opts = le32_to_cpu(es->s_default_mount_opts); @@ -729,8 +730,15 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_printf(seq, ",commit=%u", (unsigned) (sbi->s_commit_interval / HZ)); } - if (test_opt(sb, BARRIER)) - seq_puts(seq, ",barrier=1"); + /* + * We're changing the default of barrier mount option, so + * let's always display its mount state so it's clear what its + * status is. + */ + seq_puts(seq, ",barrier="); + seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0"); + if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) + seq_puts(seq, ",journal_async_commit"); if (test_opt(sb, NOBH)) seq_puts(seq, ",nobh"); if (!test_opt(sb, EXTENTS)) @@ -979,7 +987,7 @@ static int parse_options (char *options, struct super_block *sb, int data_opt = 0; int option; #ifdef CONFIG_QUOTA - int qtype; + int qtype, qfmt; char *qname; #endif @@ -1162,9 +1170,11 @@ static int parse_options (char *options, struct super_block *sb, case Opt_grpjquota: qtype = GRPQUOTA; set_qf_name: - if (sb_any_quota_enabled(sb)) { + if ((sb_any_quota_enabled(sb) || + sb_any_quota_suspended(sb)) && + !sbi->s_qf_names[qtype]) { printk(KERN_ERR - "EXT4-fs: Cannot change journalled " + "EXT4-fs: Cannot change journaled " "quota options when quota turned on.\n"); return 0; } @@ -1200,9 +1210,11 @@ set_qf_name: case Opt_offgrpjquota: qtype = GRPQUOTA; clear_qf_name: - if (sb_any_quota_enabled(sb)) { + if ((sb_any_quota_enabled(sb) || + sb_any_quota_suspended(sb)) && + sbi->s_qf_names[qtype]) { printk(KERN_ERR "EXT4-fs: Cannot change " - "journalled quota options when " + "journaled quota options when " "quota turned on.\n"); return 0; } @@ -1213,10 +1225,20 @@ clear_qf_name: sbi->s_qf_names[qtype] = NULL; break; case Opt_jqfmt_vfsold: - sbi->s_jquota_fmt = QFMT_VFS_OLD; - break; + qfmt = QFMT_VFS_OLD; + goto set_qf_format; case Opt_jqfmt_vfsv0: - sbi->s_jquota_fmt = QFMT_VFS_V0; + qfmt = QFMT_VFS_V0; +set_qf_format: + if ((sb_any_quota_enabled(sb) || + sb_any_quota_suspended(sb)) && + sbi->s_jquota_fmt != qfmt) { + printk(KERN_ERR "EXT4-fs: Cannot change " + "journaled quota options when " + "quota turned on.\n"); + return 0; + } + sbi->s_jquota_fmt = qfmt; break; case Opt_quota: case Opt_usrquota: @@ -1241,6 +1263,9 @@ clear_qf_name: case Opt_quota: case Opt_usrquota: case Opt_grpquota: + printk(KERN_ERR + "EXT4-fs: quota options not supported.\n"); + break; case Opt_usrjquota: case Opt_grpjquota: case Opt_offusrjquota: @@ -1248,7 +1273,7 @@ clear_qf_name: case Opt_jqfmt_vfsold: case Opt_jqfmt_vfsv0: printk(KERN_ERR - "EXT4-fs: journalled quota options not " + "EXT4-fs: journaled quota options not " "supported.\n"); break; case Opt_noquota: @@ -1333,14 +1358,14 @@ clear_qf_name: } if (!sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT4-fs: journalled quota format " + printk(KERN_ERR "EXT4-fs: journaled quota format " "not specified.\n"); return 0; } } else { if (sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT4-fs: journalled quota format " - "specified with no journalling " + printk(KERN_ERR "EXT4-fs: journaled quota format " + "specified with no journaling " "enabled.\n"); return 0; } @@ -1581,7 +1606,7 @@ static void ext4_orphan_cleanup (struct super_block * sb, int ret = ext4_quota_on_mount(sb, i); if (ret < 0) printk(KERN_ERR - "EXT4-fs: Cannot turn on journalled " + "EXT4-fs: Cannot turn on journaled " "quota: error %d\n", ret); } } @@ -1890,6 +1915,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) sbi->s_resgid = le16_to_cpu(es->s_def_resgid); set_opt(sbi->s_mount_opt, RESERVATION); + set_opt(sbi->s_mount_opt, BARRIER); /* * turn on extents feature by default in ext4 filesystem @@ -2172,6 +2198,29 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) { if (ext4_load_journal(sb, es, journal_devnum)) 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_fill_super: Journal transaction " + "%u is corrupt\n", sb->s_id, + EXT4_SB(sb)->s_journal->j_failed_commit); + if (test_opt (sb, ERRORS_RO)) { + printk (KERN_CRIT + "Mounting filesystem read-only\n"); + sb->s_flags |= MS_RDONLY; + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + } + 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); + printk(KERN_CRIT + "EXT4-fs (device %s): mount failed\n", + sb->s_id); + goto failed_mount4; + } + } } else if (journal_inum) { if (ext4_create_journal(sb, es, journal_inum)) goto failed_mount3; @@ -3106,7 +3155,7 @@ static int ext4_release_dquot(struct dquot *dquot) static int ext4_mark_dquot_dirty(struct dquot *dquot) { - /* Are we journalling quotas? */ + /* Are we journaling quotas? */ if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] || EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) { dquot_mark_dquot_dirty(dquot); @@ -3153,23 +3202,42 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, if (!test_opt(sb, QUOTA)) return -EINVAL; - /* Not journalling quota? */ - if ((!EXT4_SB(sb)->s_qf_names[USRQUOTA] && - !EXT4_SB(sb)->s_qf_names[GRPQUOTA]) || remount) + /* When remounting, no checks are needed and in fact, path is NULL */ + if (remount) return vfs_quota_on(sb, type, format_id, path, remount); + err = path_lookup(path, LOOKUP_FOLLOW, &nd); if (err) return err; + /* Quotafile not on the same filesystem? */ if (nd.path.mnt->mnt_sb != sb) { path_put(&nd.path); return -EXDEV; } - /* Quotafile not of fs root? */ - if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode) - printk(KERN_WARNING - "EXT4-fs: Quota file not on filesystem root. " - "Journalled quota will not work.\n"); + /* Journaling quota? */ + if (EXT4_SB(sb)->s_qf_names[type]) { + /* Quotafile not of fs root? */ + if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode) + printk(KERN_WARNING + "EXT4-fs: Quota file not on filesystem root. " + "Journaled quota will not work.\n"); + } + + /* + * When we journal data on quota file, we have to flush journal to see + * all updates to the file when we bypass pagecache... + */ + if (ext4_should_journal_data(nd.path.dentry->d_inode)) { + /* + * We don't need to lock updates but journal_flush() could + * otherwise be livelocked... + */ + jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); + jbd2_journal_flush(EXT4_SB(sb)->s_journal); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + } + path_put(&nd.path); return vfs_quota_on(sb, type, format_id, path, remount); } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 3fbc2c6c3d0e..ff08633f398e 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1009,6 +1009,11 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, i.value = NULL; error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { + if (EXT4_I(inode)->i_file_acl && !bs.s.base) { + error = ext4_xattr_block_find(inode, &i, &bs); + if (error) + goto cleanup; + } error = ext4_xattr_block_set(handle, inode, &i, &bs); if (error) goto cleanup; |