diff options
Diffstat (limited to 'fs/ext4/balloc.c')
| -rw-r--r-- | fs/ext4/balloc.c | 340 |
1 files changed, 240 insertions, 100 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index f9e2cd8cf71..fca382037dd 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -30,6 +30,23 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb, */ /* + * Calculate block group number for a given block number + */ +ext4_group_t ext4_get_group_number(struct super_block *sb, + ext4_fsblk_t block) +{ + ext4_group_t group; + + if (test_opt2(sb, STD_GROUP_SIZE)) + group = (block - + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >> + (EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3); + else + ext4_get_group_no_and_offset(sb, block, &group, NULL); + return group; +} + +/* * Calculate the block group number and offset into the block/cluster * allocation bitmap, given a block number */ @@ -49,22 +66,26 @@ 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) +/* + * Check whether the 'block' lives within the 'block_group'. Returns 1 if so + * and 0 otherwise. + */ +static inline 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, NULL); - if (actual_group == block_group) - return 1; - return 0; + + actual_group = ext4_get_group_number(sb, block); + return (actual_group == block_group) ? 1 : 0; } /* Return the number of clusters used for file system metadata; this * represents the overhead needed by the file system. */ -unsigned ext4_num_overhead_clusters(struct super_block *sb, - ext4_group_t block_group, - struct ext4_group_desc *gdp) +static unsigned ext4_num_overhead_clusters(struct super_block *sb, + ext4_group_t block_group, + struct ext4_group_desc *gdp) { unsigned num_clusters; int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c; @@ -90,8 +111,8 @@ unsigned ext4_num_overhead_clusters(struct super_block *sb, * unusual file system layouts. */ if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) { - block_cluster = EXT4_B2C(sbi, (start - - ext4_block_bitmap(sb, gdp))); + block_cluster = EXT4_B2C(sbi, + ext4_block_bitmap(sb, gdp) - start); if (block_cluster < num_clusters) block_cluster = -1; else if (block_cluster == num_clusters) { @@ -102,7 +123,7 @@ unsigned ext4_num_overhead_clusters(struct super_block *sb, if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) { inode_cluster = EXT4_B2C(sbi, - start - ext4_inode_bitmap(sb, gdp)); + ext4_inode_bitmap(sb, gdp) - start); if (inode_cluster < num_clusters) inode_cluster = -1; else if (inode_cluster == num_clusters) { @@ -114,7 +135,7 @@ unsigned ext4_num_overhead_clusters(struct super_block *sb, itbl_blk = ext4_inode_table(sb, gdp); for (i = 0; i < sbi->s_itb_per_group; i++) { if (ext4_block_in_group(sb, itbl_blk + i, block_group)) { - c = EXT4_B2C(sbi, start - itbl_blk + i); + c = EXT4_B2C(sbi, itbl_blk + i - start); if ((c < num_clusters) || (c == inode_cluster) || (c == block_cluster) || (c == itbl_cluster)) continue; @@ -155,25 +176,35 @@ static unsigned int num_clusters_in_group(struct super_block *sb, } /* Initializes an uninitialized block bitmap */ -void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, - ext4_group_t block_group, - struct ext4_group_desc *gdp) +static void ext4_init_block_bitmap(struct super_block *sb, + struct buffer_head *bh, + ext4_group_t block_group, + struct ext4_group_desc *gdp) { unsigned int bit, bit_max; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start, tmp; int flex_bg = 0; + struct ext4_group_info *grp; J_ASSERT_BH(bh, buffer_locked(bh)); /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ - if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { + if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); - ext4_free_group_clusters_set(sb, gdp, 0); - ext4_free_inodes_set(sb, gdp, 0); - ext4_itable_unused_set(sb, gdp, 0); - memset(bh->b_data, 0xff, sb->s_blocksize); + grp = ext4_get_group_info(sb, block_group); + if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + percpu_counter_sub(&sbi->s_freeclusters_counter, + grp->bb_free); + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { + int count; + count = ext4_free_inodes_count(sb, gdp); + percpu_counter_sub(&sbi->s_freeinodes_counter, + count); + } + set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); return; } memset(bh->b_data, 0, sb->s_blocksize); @@ -210,6 +241,8 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, */ ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group), sb->s_blocksize * 8, bh->b_data); + ext4_block_bitmap_csum_set(sb, block_group, gdp, bh); + ext4_group_desc_csum_set(sb, block_group, gdp); } /* Return the number of free blocks in a block group. It is used when @@ -275,14 +308,19 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, return desc; } -static int ext4_valid_block_bitmap(struct super_block *sb, - struct ext4_group_desc *desc, - unsigned int block_group, - struct buffer_head *bh) +/* + * Return the block number which was discovered to be invalid, or 0 if + * the block bitmap is valid. + */ +static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + ext4_group_t block_group, + struct buffer_head *bh) { + struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t offset; ext4_grpblk_t next_zero_bit; - ext4_fsblk_t bitmap_blk; + ext4_fsblk_t blk; ext4_fsblk_t group_first_block; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { @@ -292,41 +330,77 @@ static int ext4_valid_block_bitmap(struct super_block *sb, * or it has to also read the block group where the bitmaps * are located to verify they are set. */ - return 1; + return 0; } group_first_block = ext4_group_first_block_no(sb, block_group); /* check whether block bitmap block number is set */ - bitmap_blk = ext4_block_bitmap(sb, desc); - offset = bitmap_blk - group_first_block; - if (!ext4_test_bit(offset, bh->b_data)) + blk = ext4_block_bitmap(sb, desc); + offset = blk - group_first_block; + if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data)) /* bad block bitmap */ - goto err_out; + return blk; /* check whether the inode bitmap block number is set */ - bitmap_blk = ext4_inode_bitmap(sb, desc); - offset = bitmap_blk - group_first_block; - if (!ext4_test_bit(offset, bh->b_data)) + blk = ext4_inode_bitmap(sb, desc); + offset = blk - group_first_block; + if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data)) /* bad block bitmap */ - goto err_out; + return blk; /* check whether the inode table block number is set */ - bitmap_blk = ext4_inode_table(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_inode_table(sb, desc); + offset = blk - group_first_block; next_zero_bit = ext4_find_next_zero_bit(bh->b_data, - offset + EXT4_SB(sb)->s_itb_per_group, - offset); - if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group) - /* good bitmap for inode tables */ - return 1; - -err_out: - ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu", - block_group, bitmap_blk); + EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group), + EXT4_B2C(sbi, offset)); + if (next_zero_bit < + EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group)) + /* bad bitmap for inode tables */ + return blk; return 0; } + +static void ext4_validate_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + ext4_group_t block_group, + struct buffer_head *bh) +{ + ext4_fsblk_t blk; + struct ext4_group_info *grp = ext4_get_group_info(sb, block_group); + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (buffer_verified(bh)) + return; + + ext4_lock_group(sb, block_group); + blk = ext4_valid_block_bitmap(sb, desc, block_group, bh); + if (unlikely(blk != 0)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: block %llu: invalid block bitmap", + block_group, blk); + if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + percpu_counter_sub(&sbi->s_freeclusters_counter, + grp->bb_free); + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + return; + } + if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, + desc, bh))) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); + if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + percpu_counter_sub(&sbi->s_freeclusters_counter, + grp->bb_free); + set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + return; + } + set_buffer_verified(bh); + ext4_unlock_group(sb, block_group); +} + /** - * ext4_read_block_bitmap() + * ext4_read_block_bitmap_nowait() * @sb: super block * @block_group: given block group * @@ -336,10 +410,10 @@ err_out: * Return buffer_head on success or NULL in case of failure. */ struct buffer_head * -ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) +ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) { struct ext4_group_desc *desc; - struct buffer_head *bh = NULL; + struct buffer_head *bh; ext4_fsblk_t bitmap_blk; desc = ext4_get_group_desc(sb, block_group, NULL); @@ -348,19 +422,19 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) bitmap_blk = ext4_block_bitmap(sb, desc); bh = sb_getblk(sb, bitmap_blk); if (unlikely(!bh)) { - ext4_error(sb, "Cannot read block bitmap - " - "block_group = %u, block_bitmap = %llu", - block_group, bitmap_blk); + ext4_error(sb, "Cannot get buffer for block bitmap - " + "block_group = %u, block_bitmap = %llu", + block_group, bitmap_blk); return NULL; } if (bitmap_uptodate(bh)) - return bh; + goto verify; lock_buffer(bh); if (bitmap_uptodate(bh)) { unlock_buffer(bh); - return bh; + goto verify; } ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { @@ -379,28 +453,62 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) */ set_bitmap_uptodate(bh); unlock_buffer(bh); - return bh; + goto verify; } /* - * submit the buffer_head for read. We can - * safely mark the bitmap as uptodate now. - * We do it here so the bitmap uptodate bit - * get set with buffer lock held. + * submit the buffer_head for reading */ + set_buffer_new(bh); trace_ext4_read_block_bitmap_load(sb, block_group); - set_bitmap_uptodate(bh); - if (bh_submit_read(bh) < 0) { - put_bh(bh); + bh->b_end_io = ext4_end_bitmap_read; + get_bh(bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); + return bh; +verify: + ext4_validate_block_bitmap(sb, desc, block_group, bh); + if (buffer_verified(bh)) + return bh; + put_bh(bh); + return NULL; +} + +/* Returns 0 on success, 1 on error */ +int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, + struct buffer_head *bh) +{ + struct ext4_group_desc *desc; + + if (!buffer_new(bh)) + return 0; + desc = ext4_get_group_desc(sb, block_group, NULL); + if (!desc) + return 1; + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) { ext4_error(sb, "Cannot read block bitmap - " - "block_group = %u, block_bitmap = %llu", - block_group, bitmap_blk); + "block_group = %u, block_bitmap = %llu", + block_group, (unsigned long long) bh->b_blocknr); + return 1; + } + clear_buffer_new(bh); + /* Panic or remount fs read-only if block bitmap is invalid */ + ext4_validate_block_bitmap(sb, desc, block_group, bh); + /* ...but check for error just in case errors=continue. */ + return !buffer_verified(bh); +} + +struct buffer_head * +ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) +{ + struct buffer_head *bh; + + bh = ext4_read_block_bitmap_nowait(sb, block_group); + if (!bh) + return NULL; + if (ext4_wait_block_bitmap(sb, 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; } @@ -416,31 +524,44 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) static int ext4_has_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags) { - s64 free_clusters, dirty_clusters, root_clusters; + s64 free_clusters, dirty_clusters, rsv, resv_clusters; struct percpu_counter *fcc = &sbi->s_freeclusters_counter; struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter; free_clusters = percpu_counter_read_positive(fcc); dirty_clusters = percpu_counter_read_positive(dcc); - root_clusters = EXT4_B2C(sbi, ext4_r_blocks_count(sbi->s_es)); + resv_clusters = atomic64_read(&sbi->s_resv_clusters); + + /* + * r_blocks_count should always be multiple of the cluster ratio so + * we are safe to do a plane bit shift only. + */ + rsv = (ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits) + + resv_clusters; - if (free_clusters - (nclusters + root_clusters + dirty_clusters) < + if (free_clusters - (nclusters + rsv + dirty_clusters) < EXT4_FREECLUSTERS_WATERMARK) { - free_clusters = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc)); + free_clusters = percpu_counter_sum_positive(fcc); dirty_clusters = percpu_counter_sum_positive(dcc); } /* Check whether we have space after accounting for current * dirty clusters & root reserved clusters. */ - if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters)) + if (free_clusters >= (rsv + nclusters + dirty_clusters)) return 1; /* Hm, nope. Are (enough) root reserved clusters available? */ - if (sbi->s_resuid == current_fsuid() || - ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) || + if (uid_eq(sbi->s_resuid, current_fsuid()) || + (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) || capable(CAP_SYS_RESOURCE) || - (flags & EXT4_MB_USE_ROOT_BLOCKS)) { + (flags & EXT4_MB_USE_ROOT_BLOCKS)) { + if (free_clusters >= (nclusters + dirty_clusters + + resv_clusters)) + return 1; + } + /* No free blocks. Let's see if we can dip into reserved pool */ + if (flags & EXT4_MB_USE_RESERVED) { if (free_clusters >= (nclusters + dirty_clusters)) return 1; } @@ -538,6 +659,7 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) struct ext4_group_desc *gdp; ext4_group_t i; ext4_group_t ngroups = ext4_get_groups_count(sb); + struct ext4_group_info *grp; #ifdef EXT4FS_DEBUG struct ext4_super_block *es; ext4_fsblk_t bitmap_count; @@ -553,13 +675,18 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; - desc_count += ext4_free_group_clusters(sb, gdp); + grp = NULL; + if (EXT4_SB(sb)->s_group_info) + grp = ext4_get_group_info(sb, i); + if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + desc_count += ext4_free_group_clusters(sb, gdp); brelse(bitmap_bh); bitmap_bh = ext4_read_block_bitmap(sb, i); if (bitmap_bh == NULL) continue; - x = ext4_count_free(bitmap_bh, sb->s_blocksize); + x = ext4_count_free(bitmap_bh->b_data, + EXT4_CLUSTERS_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n", i, ext4_free_group_clusters(sb, gdp), x); bitmap_count += x; @@ -567,7 +694,7 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) brelse(bitmap_bh); printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu" ", computed = %llu, %llu\n", - EXT4_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)), + EXT4_NUM_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)), desc_count, bitmap_count); return bitmap_count; #else @@ -576,7 +703,11 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; - desc_count += ext4_free_group_clusters(sb, gdp); + grp = NULL; + if (EXT4_SB(sb)->s_group_info) + grp = ext4_get_group_info(sb, i); + if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + desc_count += ext4_free_group_clusters(sb, gdp); } return desc_count; @@ -585,21 +716,15 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) static inline int test_root(ext4_group_t a, int b) { - int num = b; - - while (a > num) - num *= b; - return num == a; -} - -static int ext4_group_sparse(ext4_group_t group) -{ - if (group <= 1) - return 1; - if (!(group & 1)) - return 0; - return (test_root(group, 7) || test_root(group, 5) || - test_root(group, 3)); + while (1) { + if (a < b) + return 0; + if (a == b) + return 1; + if ((a % b) != 0) + return 0; + a = a / b; + } } /** @@ -612,11 +737,26 @@ static int ext4_group_sparse(ext4_group_t group) */ int ext4_bg_has_super(struct super_block *sb, ext4_group_t group) { - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) && - !ext4_group_sparse(group)) + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + + if (group == 0) + return 1; + if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_SPARSE_SUPER2)) { + if (group == le32_to_cpu(es->s_backup_bgs[0]) || + group == le32_to_cpu(es->s_backup_bgs[1])) + return 1; return 0; - return 1; + } + if ((group <= 1) || !EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) + return 1; + if (!(group & 1)) + return 0; + if (test_root(group, 3) || (test_root(group, 5)) || + test_root(group, 7)) + return 1; + + return 0; } static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, |