diff options
52 files changed, 7770 insertions, 861 deletions
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 6a4adcae9f9a..560f88dc7090 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -86,9 +86,21 @@ Alex is working on a new set of patches right now. When mounting an ext4 filesystem, the following option are accepted: (*) == default -extents ext4 will use extents to address file data. The +extents (*) ext4 will use extents to address file data. The file system will no longer be mountable by ext3. +noextents ext4 will not use extents for newly created files + +journal_checksum Enable checksumming of the journal transactions. + This will allow the recovery code in e2fsck and the + kernel to detect corruption in the kernel. It is a + compatible change and will be ignored by older kernels. + +journal_async_commit Commit block can be written to disk without waiting + for descriptor blocks. If enabled older kernels cannot + mount the device. This will enable 'journal_checksum' + internally. + journal=update Update the ext4 file system's journal to the current format. @@ -196,6 +208,12 @@ nobh (a) cache disk block mapping information "nobh" option tries to avoid associating buffer heads (supported only for "writeback" mode). +mballoc (*) Use the multiple block allocator for block allocation +nomballoc disabled multiple block allocator for block allocation. +stripe=n Number of filesystem blocks that mballoc will try + to use for allocation size and alignment. For RAID5/6 + systems this should be the number of data + disks * RAID chunk size in file system blocks. Data Mode --------- diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index dec99455321f..4413a2d4646f 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -857,6 +857,45 @@ CPUs. The "procs_blocked" line gives the number of processes currently blocked, waiting for I/O to complete. +1.9 Ext4 file system parameters +------------------------------ +Ext4 file system have one directory per partition under /proc/fs/ext4/ +# ls /proc/fs/ext4/hdc/ +group_prealloc max_to_scan mb_groups mb_history min_to_scan order2_req +stats stream_req + +mb_groups: +This file gives the details of mutiblock allocator buddy cache of free blocks + +mb_history: +Multiblock allocation history. + +stats: +This file indicate whether the multiblock allocator should start collecting +statistics. The statistics are shown during unmount + +group_prealloc: +The multiblock allocator normalize the block allocation request to +group_prealloc filesystem blocks if we don't have strip value set. +The stripe value can be specified at mount time or during mke2fs. + +max_to_scan: +How long multiblock allocator can look for a best extent (in found extents) + +min_to_scan: +How long multiblock allocator must look for a best extent + +order2_req: +Multiblock allocator use 2^N search using buddies only for requests greater +than or equal to order2_req. The request size is specfied in file system +blocks. A value of 2 indicate only if the requests are greater than or equal +to 4 blocks. + +stream_req: +Files smaller than stream_req are served by the stream allocator, whose +purpose is to pack requests as close each to other as possible to +produce smooth I/O traffic. Avalue of 16 indicate that file smaller than 16 +filesystem block size will use group based preallocation. ------------------------------------------------------------------------------ Summary diff --git a/fs/Kconfig b/fs/Kconfig index 9656139d2e99..219ec06a8c7e 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -236,6 +236,7 @@ config JBD_DEBUG config JBD2 tristate + select CRC32 help This is a generic journaling layer for block devices that support both 32-bit and 64-bit block numbers. It is currently used by diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 33fe39ad4e03..0cc3597c1197 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -546,11 +546,11 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, dentry->d_op = &afs_fs_dentry_operations; d_add(dentry, inode); - _leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%lu }", + _leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%llu }", fid.vnode, fid.unique, dentry->d_inode->i_ino, - dentry->d_inode->i_version); + (unsigned long long)dentry->d_inode->i_version); return NULL; } @@ -630,9 +630,10 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd) * been deleted and replaced, and the original vnode ID has * been reused */ if (fid.unique != vnode->fid.unique) { - _debug("%s: file deleted (uq %u -> %u I:%lu)", + _debug("%s: file deleted (uq %u -> %u I:%llu)", dentry->d_name.name, fid.unique, - vnode->fid.unique, dentry->d_inode->i_version); + vnode->fid.unique, + (unsigned long long)dentry->d_inode->i_version); spin_lock(&vnode->lock); set_bit(AFS_VNODE_DELETED, &vnode->flags); spin_unlock(&vnode->lock); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index d196840127c6..84750c8e9f95 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -301,7 +301,8 @@ int afs_getattr(struct vfsmount *mnt, struct dentry *dentry, inode = dentry->d_inode; - _enter("{ ino=%lu v=%lu }", inode->i_ino, inode->i_version); + _enter("{ ino=%lu v=%llu }", inode->i_ino, + (unsigned long long)inode->i_version); generic_fillattr(inode, stat); return 0; diff --git a/fs/buffer.c b/fs/buffer.c index 7249e014819e..456c9ab7705b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3213,6 +3213,50 @@ static int buffer_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } +/** + * bh_uptodate_or_lock: Test whether the buffer is uptodate + * @bh: struct buffer_head + * + * Return true if the buffer is up-to-date and false, + * with the buffer locked, if not. + */ +int bh_uptodate_or_lock(struct buffer_head *bh) +{ + if (!buffer_uptodate(bh)) { + lock_buffer(bh); + if (!buffer_uptodate(bh)) + return 0; + unlock_buffer(bh); + } + return 1; +} +EXPORT_SYMBOL(bh_uptodate_or_lock); + +/** + * bh_submit_read: Submit a locked buffer for reading + * @bh: struct buffer_head + * + * Returns zero on success and -EIO on error. + */ +int bh_submit_read(struct buffer_head *bh) +{ + BUG_ON(!buffer_locked(bh)); + + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + return 0; + } + + get_bh(bh); + bh->b_end_io = end_buffer_read_sync; + submit_bh(READ, bh); + wait_on_buffer(bh); + if (buffer_uptodate(bh)) + return 0; + return -EIO; +} +EXPORT_SYMBOL(bh_submit_read); + void __init buffer_init(void) { int nrpages; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 154e25f13d77..6abaf75163f0 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -680,11 +680,31 @@ static int ext2_check_descriptors (struct super_block * sb) static loff_t ext2_max_size(int bits) { loff_t res = EXT2_NDIR_BLOCKS; - /* This constant is calculated to be the largest file size for a - * dense, 4k-blocksize file such that the total number of + int meta_blocks; + loff_t upper_limit; + + /* This is calculated to be the largest file size for a + * dense, file such that the total number of * sectors in the file, including data and all indirect blocks, - * does not exceed 2^32. */ - const loff_t upper_limit = 0x1ff7fffd000LL; + * does not exceed 2^32 -1 + * __u32 i_blocks representing the total number of + * 512 bytes blocks of the file + */ + upper_limit = (1LL << 32) - 1; + + /* total blocks in file system block size */ + upper_limit >>= (bits - 9); + + + /* indirect blocks */ + meta_blocks = 1; + /* double indirect blocks */ + meta_blocks += 1 + (1LL << (bits-2)); + /* tripple indirect blocks */ + meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2))); + + upper_limit -= meta_blocks; + upper_limit <<= bits; res += 1LL << (bits-2); res += 1LL << (2*(bits-2)); @@ -692,6 +712,10 @@ static loff_t ext2_max_size(int bits) res <<= bits; if (res > upper_limit) res = upper_limit; + + if (res > MAX_LFS_FILESIZE) + res = MAX_LFS_FILESIZE; + return res; } diff --git a/fs/ext3/super.c b/fs/ext3/super.c index cb14de1502c3..f3675cc630e9 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1436,11 +1436,31 @@ static void ext3_orphan_cleanup (struct super_block * sb, static loff_t ext3_max_size(int bits) { loff_t res = EXT3_NDIR_BLOCKS; - /* This constant is calculated to be the largest file size for a - * dense, 4k-blocksize file such that the total number of + int meta_blocks; + loff_t upper_limit; + + /* This is calculated to be the largest file size for a + * dense, file such that the total number of * sectors in the file, including data and all indirect blocks, - * does not exceed 2^32. */ - const loff_t upper_limit = 0x1ff7fffd000LL; + * does not exceed 2^32 -1 + * __u32 i_blocks representing the total number of + * 512 bytes blocks of the file + */ + upper_limit = (1LL << 32) - 1; + + /* total blocks in file system block size */ + upper_limit >>= (bits - 9); + + + /* indirect blocks */ + meta_blocks = 1; + /* double indirect blocks */ + meta_blocks += 1 + (1LL << (bits-2)); + /* tripple indirect blocks */ + meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2))); + + upper_limit -= meta_blocks; + upper_limit <<= bits; res += 1LL << (bits-2); res += 1LL << (2*(bits-2)); @@ -1448,6 +1468,10 @@ static loff_t ext3_max_size(int bits) res <<= bits; if (res > upper_limit) res = upper_limit; + + if (res > MAX_LFS_FILESIZE) + res = MAX_LFS_FILESIZE; + return res; } diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index ae6e7e502ac9..ac6fa8ca0a2f 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_EXT4DEV_FS) += ext4dev.o ext4dev-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ - ext4_jbd2.o + ext4_jbd2.o migrate.o mballoc.o ext4dev-$(CONFIG_EXT4DEV_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext4dev-$(CONFIG_EXT4DEV_FS_POSIX_ACL) += acl.o diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 71ee95e534fd..ac75ea953d83 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -29,7 +29,7 @@ * Calculate the block group number and offset, given a block number */ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, - unsigned long *blockgrpp, ext4_grpblk_t *offsetp) + ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; ext4_grpblk_t offset; @@ -46,7 +46,7 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, /* 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, - int block_group, struct ext4_group_desc *gdp) + ext4_group_t block_group, struct ext4_group_desc *gdp) { unsigned long start; int bit, bit_max; @@ -60,7 +60,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { ext4_error(sb, __FUNCTION__, - "Checksum bad for group %u\n", block_group); + "Checksum bad for group %lu\n", block_group); gdp->bg_free_blocks_count = 0; gdp->bg_free_inodes_count = 0; gdp->bg_itable_unused = 0; @@ -153,7 +153,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, * group descriptor */ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, - unsigned int block_group, + ext4_group_t block_group, struct buffer_head ** bh) { unsigned long group_desc; @@ -164,7 +164,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, if (block_group >= sbi->s_groups_count) { ext4_error (sb, "ext4_get_group_desc", "block_group >= groups_count - " - "block_group = %d, groups_count = %lu", + "block_group = %lu, groups_count = %lu", block_group, sbi->s_groups_count); return NULL; @@ -176,7 +176,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, if (!sbi->s_group_desc[group_desc]) { ext4_error (sb, "ext4_get_group_desc", "Group descriptor not loaded - " - "block_group = %d, group_desc = %lu, desc = %lu", + "block_group = %lu, group_desc = %lu, desc = %lu", block_group, group_desc, offset); return NULL; } @@ -189,18 +189,70 @@ 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) +{ + ext4_grpblk_t offset; + ext4_grpblk_t next_zero_bit; + ext4_fsblk_t bitmap_blk; + ext4_fsblk_t group_first_block; + + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { + /* with FLEX_BG, the inode/block bitmaps and itable + * blocks may not be in the group at all + * so the bitmap validation will be skipped for those groups + * or it has to also read the block group where the bitmaps + * are located to verify they are set. + */ + return 1; + } + 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)) + /* bad block bitmap */ + goto err_out; + + /* 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)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode table block number is set */ + bitmap_blk = ext4_inode_table(sb, desc); + offset = bitmap_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, __FUNCTION__, + "Invalid block bitmap - " + "block_group = %d, block = %llu", + block_group, bitmap_blk); + return 0; +} /** * read_block_bitmap() * @sb: super block * @block_group: given block group * - * Read the bitmap for a given block_group, reading into the specified - * slot in the superblock's bitmap cache. + * Read the bitmap for a given block_group,and validate the + * bits for block/inode/inode tables are set in the bitmaps * * Return buffer_head on success or NULL in case of failure. */ struct buffer_head * -read_block_bitmap(struct super_block *sb, unsigned int block_group) +read_block_bitmap(struct super_block *sb, ext4_group_t block_group) { struct ext4_group_desc * desc; struct buffer_head * bh = NULL; @@ -210,25 +262,36 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group) if (!desc) return NULL; bitmap_blk = ext4_block_bitmap(sb, desc); + bh = sb_getblk(sb, bitmap_blk); + if (unlikely(!bh)) { + ext4_error(sb, __FUNCTION__, + "Cannot read block bitmap - " + "block_group = %d, block_bitmap = %llu", + (int)block_group, (unsigned long long)bitmap_blk); + return NULL; + } + if (bh_uptodate_or_lock(bh)) + return bh; + if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { - bh = sb_getblk(sb, bitmap_blk); - if (!buffer_uptodate(bh)) { - lock_buffer(bh); - if (!buffer_uptodate(bh)) { - ext4_init_block_bitmap(sb, bh, block_group, - desc); - set_buffer_uptodate(bh); - } - unlock_buffer(bh); - } - } else { - bh = sb_bread(sb, bitmap_blk); + ext4_init_block_bitmap(sb, bh, block_group, desc); + set_buffer_uptodate(bh); + unlock_buffer(bh); + return bh; } - if (!bh) - ext4_error (sb, __FUNCTION__, + if (bh_submit_read(bh) < 0) { + put_bh(bh); + ext4_error(sb, __FUNCTION__, "Cannot read block bitmap - " "block_group = %d, block_bitmap = %llu", - block_group, bitmap_blk); + (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; + } + return bh; } /* @@ -320,7 +383,7 @@ restart: */ static int goal_in_my_reservation(struct ext4_reserve_window *rsv, ext4_grpblk_t grp_goal, - unsigned int group, struct super_block * sb) + ext4_group_t group, struct super_block *sb) { ext4_fsblk_t group_first_block, group_last_block; @@ -463,7 +526,7 @@ static inline int rsv_is_empty(struct ext4_reserve_window *rsv) * when setting the reservation window size through ioctl before the file * is open for write (needs block allocation). * - * Needs truncate_mutex protection prior to call this function. + * Needs down_write(i_data_sem) protection prior to call this function. */ void ext4_init_block_alloc_info(struct inode *inode) { @@ -514,6 +577,8 @@ void ext4_discard_reservation(struct inode *inode) struct ext4_reserve_window_node *rsv; spinlock_t *rsv_lock = &EXT4_SB(inode->i_sb)->s_rsv_window_lock; + ext4_mb_discard_inode_preallocations(inode); + if (!block_i) return; @@ -540,7 +605,7 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb, { struct buffer_head *bitmap_bh = NULL; struct buffer_head *gd_bh; - unsigned long block_group; + ext4_group_t block_group; ext4_grpblk_t bit; unsigned long i; unsigned long overflow; @@ -587,11 +652,13 @@ do_more: in_range(ext4_inode_bitmap(sb, desc), block, count) || in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) || in_range(block + count - 1, ext4_inode_table(sb, desc), - sbi->s_itb_per_group)) + sbi->s_itb_per_group)) { ext4_error (sb, "ext4_free_blocks", "Freeing blocks in system zones - " "Block = %llu, count = %lu", block, count); + goto error_return; + } /* * We are about to start releasing blocks in the bitmap, @@ -720,19 +787,29 @@ error_return: * @inode: inode * @block: start physical block to free * @count: number of blocks to count + * @metadata: Are these metadata blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, - ext4_fsblk_t block, unsigned long count) + ext4_fsblk_t block, unsigned long count, + int metadata) { struct super_block * sb; unsigned long dquot_freed_blocks; + /* this isn't the right place to decide whether block is metadata + * inode.c/extents.c knows better, but for safety ... */ + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || + ext4_should_journal_data(inode)) + metadata = 1; + sb = inode->i_sb; - if (!sb) { - printk ("ext4_free_blocks: nonexistent device"); - return; - } - ext4_free_blocks_sb(handle, sb, block, count, &dquot_freed_blocks); + + if (!test_opt(sb, MBALLOC) || !EXT4_SB(sb)->s_group_info) + ext4_free_blocks_sb(handle, sb, block, count, + &dquot_freed_blocks); + else + ext4_mb_free_blocks(handle, inode, block, count, + metadata, &dquot_freed_blocks); if (dquot_freed_blocks) DQUOT_FREE_BLOCK(inode, dquot_freed_blocks); return; @@ -920,9 +997,10 @@ claim_block(spinlock_t *lock, ext4_grpblk_t block, struct buffer_head *bh) * ext4_journal_release_buffer(), else we'll run out of credits. */ static ext4_grpblk_t -ext4_try_to_allocate(struct super_block *sb, handle_t *handle, int group, - struct buffer_head *bitmap_bh, ext4_grpblk_t grp_goal, - unsigned long *count, struct ext4_reserve_window *my_rsv) +ext4_try_to_allocate(struct super_block *sb, handle_t *handle, + ext4_group_t group, struct buffer_head *bitmap_bh, + ext4_grpblk_t grp_goal, unsigned long *count, + struct ext4_reserve_window *my_rsv) { ext4_fsblk_t group_first_block; ext4_grpblk_t start, end; @@ -1156,7 +1234,7 @@ static int find_next_reservable_window( */ static int alloc_new_reservation(struct ext4_reserve_window_node *my_rsv, ext4_grpblk_t grp_goal, struct super_block *sb, - unsigned int group, struct buffer_head *bitmap_bh) + ext4_group_t group, struct buffer_head *bitmap_bh) { struct ext4_reserve_window_node *search_head; ext4_fsblk_t group_first_block, group_end_block, start_block; @@ -1354,7 +1432,7 @@ static void try_to_extend_reservation(struct ext4_reserve_window_node *my_rsv, */ static ext4_grpblk_t ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, - unsigned int group, struct buffer_head *bitmap_bh, + ext4_group_t group, struct buffer_head *bitmap_bh, ext4_grpblk_t grp_goal, struct ext4_reserve_window_node * my_rsv, unsigned long *count, int *errp) @@ -1510,7 +1588,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries) } /** - * ext4_new_blocks() -- core block(s) allocation function + * ext4_new_blocks_old() -- core block(s) allocation function * @handle: handle to this transaction * @inode: file inode * @goal: given target block(filesystem wide) @@ -1523,17 +1601,17 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries) * any specific goal block. * */ -ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode, +ext4_fsblk_t ext4_new_blocks_old(handle_t *handle, struct inode *inode, ext4_fsblk_t goal, unsigned long *count, int *errp) { struct buffer_head *bitmap_bh = NULL; struct buffer_head *gdp_bh; - unsigned long group_no; - int goal_group; + ext4_group_t group_no; + ext4_group_t goal_group; ext4_grpblk_t grp_target_blk; /* blockgroup relative goal block */ ext4_grpblk_t grp_alloc_blk; /* blockgroup-relative allocated block*/ |