diff options
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/Kconfig | 17 | ||||
-rw-r--r-- | fs/ext4/Makefile | 4 | ||||
-rw-r--r-- | fs/ext4/acl.c | 37 | ||||
-rw-r--r-- | fs/ext4/balloc.c | 71 | ||||
-rw-r--r-- | fs/ext4/bitmap.c | 24 | ||||
-rw-r--r-- | fs/ext4/dir.c | 118 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 249 | ||||
-rw-r--r-- | fs/ext4/ext4_extents.h | 40 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.c | 12 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.h | 32 | ||||
-rw-r--r-- | fs/ext4/extents.c | 864 | ||||
-rw-r--r-- | fs/ext4/extents_status.c | 500 | ||||
-rw-r--r-- | fs/ext4/extents_status.h | 45 | ||||
-rw-r--r-- | fs/ext4/file.c | 462 | ||||
-rw-r--r-- | fs/ext4/fsync.c | 111 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 43 | ||||
-rw-r--r-- | fs/ext4/indirect.c | 23 | ||||
-rw-r--r-- | fs/ext4/inline.c | 1884 | ||||
-rw-r--r-- | fs/ext4/inode.c | 836 | ||||
-rw-r--r-- | fs/ext4/ioctl.c | 41 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 227 | ||||
-rw-r--r-- | fs/ext4/mballoc.h | 5 | ||||
-rw-r--r-- | fs/ext4/migrate.c | 1 | ||||
-rw-r--r-- | fs/ext4/mmp.c | 6 | ||||
-rw-r--r-- | fs/ext4/move_extent.c | 521 | ||||
-rw-r--r-- | fs/ext4/namei.c | 613 | ||||
-rw-r--r-- | fs/ext4/page-io.c | 179 | ||||
-rw-r--r-- | fs/ext4/resize.c | 459 | ||||
-rw-r--r-- | fs/ext4/super.c | 553 | ||||
-rw-r--r-- | fs/ext4/symlink.c | 4 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 121 | ||||
-rw-r--r-- | fs/ext4/xattr.h | 158 |
32 files changed, 6098 insertions, 2162 deletions
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index c22f17021b6..987358740cb 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -39,22 +39,9 @@ config EXT4_USE_FOR_EXT23 compiled kernel size by using one file system driver for ext2, ext3, and ext4 file systems. -config EXT4_FS_XATTR - bool "Ext4 extended attributes" - depends on EXT4_FS - default y - help - Extended attributes are name:value pairs associated with inodes by - the kernel or by users (see the attr(5) manual page, or visit - <http://acl.bestbits.at/> for details). - - If unsure, say N. - - You need this for POSIX ACL support on ext4. - config EXT4_FS_POSIX_ACL bool "Ext4 POSIX Access Control Lists" - depends on EXT4_FS_XATTR + depends on EXT4_FS select FS_POSIX_ACL help POSIX Access Control Lists (ACLs) support permissions for users and @@ -67,7 +54,7 @@ config EXT4_FS_POSIX_ACL config EXT4_FS_SECURITY bool "Ext4 Security Labels" - depends on EXT4_FS_XATTR + depends on EXT4_FS help Security labels support alternative access control models implemented by security modules like SELinux. This option diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 56fd8f86593..0310fec2ee3 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -7,8 +7,8 @@ obj-$(CONFIG_EXT4_FS) += ext4.o ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \ - mmp.o indirect.o + mmp.o indirect.o extents_status.o xattr.o xattr_user.o \ + xattr_trusted.o inline.o -ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index a5c29bb3b83..e6e0d988439 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -55,16 +55,23 @@ ext4_acl_from_disk(const void *value, size_t size) case ACL_OTHER: value = (char *)value + sizeof(ext4_acl_entry_short); - acl->a_entries[n].e_id = ACL_UNDEFINED_ID; break; case ACL_USER: + value = (char *)value + sizeof(ext4_acl_entry); + if ((char *)value > end) + goto fail; + acl->a_entries[n].e_uid = + make_kuid(&init_user_ns, + le32_to_cpu(entry->e_id)); + break; case ACL_GROUP: value = (char *)value + sizeof(ext4_acl_entry); if ((char *)value > end) goto fail; - acl->a_entries[n].e_id = - le32_to_cpu(entry->e_id); + acl->a_entries[n].e_gid = + make_kgid(&init_user_ns, + le32_to_cpu(entry->e_id)); break; default: @@ -98,13 +105,19 @@ ext4_acl_to_disk(const struct posix_acl *acl, size_t *size) ext_acl->a_version = cpu_to_le32(EXT4_ACL_VERSION); e = (char *)ext_acl + sizeof(ext4_acl_header); for (n = 0; n < acl->a_count; n++) { + const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext4_acl_entry *entry = (ext4_acl_entry *)e; - entry->e_tag = cpu_to_le16(acl->a_entries[n].e_tag); - entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm); - switch (acl->a_entries[n].e_tag) { + entry->e_tag = cpu_to_le16(acl_e->e_tag); + entry->e_perm = cpu_to_le16(acl_e->e_perm); + switch (acl_e->e_tag) { case ACL_USER: + entry->e_id = cpu_to_le32( + from_kuid(&init_user_ns, acl_e->e_uid)); + e += sizeof(ext4_acl_entry); + break; case ACL_GROUP: - entry->e_id = cpu_to_le32(acl->a_entries[n].e_id); + entry->e_id = cpu_to_le32( + from_kgid(&init_user_ns, acl_e->e_gid)); e += sizeof(ext4_acl_entry); break; @@ -374,7 +387,7 @@ ext4_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer, return PTR_ERR(acl); if (acl == NULL) return -ENODATA; - error = posix_acl_to_xattr(acl, buffer, size); + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return error; @@ -397,7 +410,7 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value, return -EPERM; if (value) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); else if (acl) { @@ -410,8 +423,10 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value, retry: handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + goto release_and_out; + } error = ext4_set_acl(handle, inode, type, acl); ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index cee7812cc3c..cf1821784a1 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -174,8 +174,7 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, ext4_free_inodes_set(sb, gdp, 0); ext4_itable_unused_set(sb, gdp, 0); memset(bh->b_data, 0xff, sb->s_blocksize); - ext4_block_bitmap_csum_set(sb, block_group, gdp, bh, - EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_block_bitmap_csum_set(sb, block_group, gdp, bh); return; } memset(bh->b_data, 0, sb->s_blocksize); @@ -212,8 +211,7 @@ 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_BLOCKS_PER_GROUP(sb) / 8); + ext4_block_bitmap_csum_set(sb, block_group, gdp, bh); ext4_group_desc_csum_set(sb, block_group, gdp); } @@ -280,14 +278,18 @@ 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, + 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 blk; ext4_fsblk_t group_first_block; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { @@ -297,37 +299,33 @@ 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; + blk = ext4_block_bitmap(sb, desc); + offset = blk - group_first_block; if (!ext4_test_bit(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; + blk = ext4_inode_bitmap(sb, desc); + offset = blk - group_first_block; if (!ext4_test_bit(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); + if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group) + /* bad bitmap for inode tables */ + return blk; return 0; } @@ -336,14 +334,26 @@ void ext4_validate_block_bitmap(struct super_block *sb, unsigned int block_group, struct buffer_head *bh) { + ext4_fsblk_t blk; + if (buffer_verified(bh)) return; ext4_lock_group(sb, block_group); - if (ext4_valid_block_bitmap(sb, desc, block_group, bh) && - ext4_block_bitmap_csum_verify(sb, block_group, desc, bh, - EXT4_BLOCKS_PER_GROUP(sb) / 8)) - set_buffer_verified(bh); + 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); + 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); + return; + } + set_buffer_verified(bh); ext4_unlock_group(sb, block_group); } @@ -609,7 +619,8 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) if (bitmap_bh == NULL) continue; - x = ext4_count_free(bitmap_bh, sb->s_blocksize); + x = ext4_count_free(bitmap_bh->b_data, + EXT4_BLOCKS_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; diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index b319721da26..3285aa5a706 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -11,24 +11,11 @@ #include <linux/jbd2.h> #include "ext4.h" -#ifdef EXT4FS_DEBUG - -static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0}; - -unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars) +unsigned int ext4_count_free(char *bitmap, unsigned int numchars) { - unsigned int i, sum = 0; - - if (!map) - return 0; - for (i = 0; i < numchars; i++) - sum += nibblemap[map->b_data[i] & 0xf] + - nibblemap[(map->b_data[i] >> 4) & 0xf]; - return sum; + return numchars * BITS_PER_BYTE - memweight(bitmap, numchars); } -#endif /* EXT4FS_DEBUG */ - int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz) @@ -71,11 +58,12 @@ void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, - struct buffer_head *bh, int sz) + struct buffer_head *bh) { __u32 hi; __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); + int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) @@ -92,14 +80,14 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, if (provided == calculated) return 1; - ext4_error(sb, "Bad block bitmap checksum: block_group = %u", group); return 0; } void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, - struct buffer_head *bh, int sz) + struct buffer_head *bh) { + int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index aa39e600d15..80a28b29727 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -27,23 +27,11 @@ #include <linux/slab.h> #include <linux/rbtree.h> #include "ext4.h" - -static unsigned char ext4_filetype_table[] = { - DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK -}; +#include "xattr.h" static int ext4_dx_readdir(struct file *filp, void *dirent, filldir_t filldir); -static unsigned char get_dtype(struct super_block *sb, int filetype) -{ - if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) || - (filetype >= EXT4_FT_MAX)) - return DT_UNKNOWN; - - return (ext4_filetype_table[filetype]); -} - /** * Check if the given dir-inode refers to an htree-indexed directory * (or a directory which chould potentially get coverted to use htree @@ -68,11 +56,14 @@ static int is_dx_dir(struct inode *inode) * Return 0 if the directory entry is OK, and 1 if there is a problem * * Note: this is the opposite of what ext2 and ext3 historically returned... + * + * bh passed here can be an inode block or a dir data block, depending + * on the inode inline data flag. */ int __ext4_check_dir_entry(const char *function, unsigned int line, struct inode *dir, struct file *filp, struct ext4_dir_entry_2 *de, - struct buffer_head *bh, + struct buffer_head *bh, char *buf, int size, unsigned int offset) { const char *error_msg = NULL; @@ -85,9 +76,8 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, error_msg = "rec_len % 4 != 0"; else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len))) error_msg = "rec_len is too small for name_len"; - else if (unlikely(((char *) de - bh->b_data) + rlen > - dir->i_sb->s_blocksize)) - error_msg = "directory entry across blocks"; + else if (unlikely(((char *) de - buf) + rlen > size)) + error_msg = "directory entry across range"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; @@ -98,14 +88,14 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, ext4_error_file(filp, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u(%u), " "inode=%u, rec_len=%d, name_len=%d", - error_msg, (unsigned) (offset % bh->b_size), + error_msg, (unsigned) (offset % size), offset, le32_to_cpu(de->inode), rlen, de->name_len); else ext4_error_inode(dir, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u(%u), " "inode=%u, rec_len=%d, name_len=%d", - error_msg, (unsigned) (offset % bh->b_size), + error_msg, (unsigned) (offset % size), offset, le32_to_cpu(de->inode), rlen, de->name_len); @@ -125,6 +115,14 @@ static int ext4_readdir(struct file *filp, int ret = 0; int dir_has_error = 0; + if (ext4_has_inline_data(inode)) { + int has_inline_data = 1; + ret = ext4_read_inline_dir(filp, dirent, filldir, + &has_inline_data); + if (has_inline_data) + return ret; + } + if (is_dx_dir(inode)) { err = ext4_dx_readdir(filp, dirent, filldir); if (err != ERR_BAD_DX_DIR) { @@ -221,8 +219,9 @@ revalidate: while (!error && filp->f_pos < inode->i_size && offset < sb->s_blocksize) { de = (struct ext4_dir_entry_2 *) (bh->b_data + offset); - if (ext4_check_dir_entry(inode, filp, de, - bh, offset)) { + if (ext4_check_dir_entry(inode, filp, de, bh, + bh->b_data, bh->b_size, + offset)) { /* * On error, skip the f_pos to the next block */ @@ -324,74 +323,27 @@ static inline loff_t ext4_get_htree_eof(struct file *filp) /* - * ext4_dir_llseek() based on generic_file_llseek() to handle both - * non-htree and htree directories, where the "offset" is in terms - * of the filename hash value instead of the byte offset. + * ext4_dir_llseek() calls generic_file_llseek_size to handle htree + * directories, where the "offset" is in terms of the filename hash + * value instead of the byte offset. * - * NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX) - * will be invalid once the directory was converted into a dx directory + * Because we may return a 64-bit hash that is well beyond offset limits, + * we need to pass the max hash as the maximum allowable offset in + * the htree directory case. + * + * For non-htree, ext4_llseek already chooses the proper max offset. */ -loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin) +loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; - loff_t ret = -EINVAL; int dx_dir = is_dx_dir(inode); + loff_t htree_max = ext4_get_htree_eof(file); - mutex_lock(&inode->i_mutex); - - /* NOTE: relative offsets with dx directories might not work - * as expected, as it is difficult to figure out the - * correct offset between dx hashes */ - - switch (origin) { - case SEEK_END: - if (unlikely(offset > 0)) - goto out_err; /* not supported for directories */ - - /* so only negative offsets are left, does that have a - * meaning for directories at all? */ - if (dx_dir) - offset += ext4_get_htree_eof(file); - else - offset += inode->i_size; - break; - case SEEK_CUR: - /* - * Here we special-case the lseek(fd, 0, SEEK_CUR) - * position-querying operation. Avoid rewriting the "same" - * f_pos value back to the file because a concurrent read(), - * write() or lseek() might have altered it - */ - if (offset == 0) { - offset = file->f_pos; - goto out_ok; - } - - offset += file->f_pos; - break; - } - - if (unlikely(offset < 0)) - goto out_err; - - if (!dx_dir) { - if (offset > inode->i_sb->s_maxbytes) - goto out_err; - } else if (offset > ext4_get_htree_eof(file)) - goto out_err; - - /* Special lock needed here? */ - if (offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } - -out_ok: - ret = offset; -out_err: - mutex_unlock(&inode->i_mutex); - - return ret; + if (likely(dx_dir)) + return generic_file_llseek_size(file, offset, whence, + htree_max, htree_max); + else + return ext4_llseek(file, offset, whence); } /* diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index cfc4e01b3c8..8462eb3c33a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -57,6 +57,16 @@ #define ext4_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif +/* + * Turn on EXT_DEBUG to get lots of info about extents operations. + */ +#define EXT_DEBUG__ +#ifdef EXT_DEBUG +#define ext_debug(fmt, ...) printk(fmt, ##__VA_ARGS__) +#else +#define ext_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) +#endif + #define EXT4_ERROR_INODE(inode, fmt, a...) \ ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a) @@ -186,7 +196,6 @@ struct mpage_da_data { #define EXT4_IO_END_ERROR 0x0002 #define EXT4_IO_END_QUEUED 0x0004 #define EXT4_IO_END_DIRECT 0x0008 -#define EXT4_IO_END_IN_FSYNC 0x0010 struct ext4_io_page { struct page *p_page; @@ -393,6 +402,7 @@ struct flex_groups { #define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */ #define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ +#define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ #define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */ @@ -449,28 +459,26 @@ enum { EXT4_INODE_EXTENTS = 19, /* Inode uses extents */ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */ EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */ + EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */ }; -#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG)) -#define CHECK_FLAG_VALUE(FLAG) if (!TEST_FLAG_VALUE(FLAG)) { \ - printk(KERN_EMERG "EXT4 flag fail: " #FLAG ": %d %d\n", \ - EXT4_##FLAG##_FL, EXT4_INODE_##FLAG); BUG_ON(1); } - -/* - * Since it's pretty easy to mix up bit numbers and hex values, and we - * can't do a compile-time test for ENUM values, we use a run-time - * test to make sure that EXT4_XXX_FL is consistent with respect to - * EXT4_INODE_XXX. If all is well the printk and BUG_ON will all drop - * out so it won't cost any extra space in the compiled kernel image. - * But it's important that these values are the same, since we are - * using EXT4_INODE_XXX to test for the flag values, but EXT4_XX_FL - * must be consistent with the values of FS_XXX_FL defined in - * include/linux/fs.h and the on-disk values found in ext2, ext3, and - * ext4 filesystems, and of course the values defined in e2fsprogs. +/* + * Since it's pretty easy to mix up bit numbers and hex values, we use a + * build-time check to make sure that EXT4_XXX_FL is consistent with respect to + * EXT4_INODE_XXX. If all is well, the macros will be dropped, so, it won't cost + * any extra space in the compiled kernel image, otherwise, the build will fail. + * It's important that these values are the same, since we are using + * EXT4_INODE_XXX to test for flag values, but EXT4_XXX_FL must be consistent + * with the values of FS_XXX_FL defined in include/linux/fs.h and the on-disk + * values found in ext2, ext3 and ext4 filesystems, and of course the values + * defined in e2fsprogs. * * It's not paranoia if the Murphy's Law really *is* out to get you. :-) */ +#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG)) +#define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG)) + static inline void ext4_check_flag_values(void) { CHECK_FLAG_VALUE(SECRM); @@ -495,6 +503,7 @@ static inline void ext4_check_flag_values(void) CHECK_FLAG_VALUE(EXTENTS); CHECK_FLAG_VALUE(EA_INODE); CHECK_FLAG_VALUE(EOFBLOCKS); + CHECK_FLAG_VALUE(INLINE_DATA); CHECK_FLAG_VALUE(RESERVED); } @@ -571,6 +580,8 @@ enum { #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 /* Request will not result in inode size update (user for fallocate) */ #define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 + /* Do not take i_data_sem locking in ext4_map_blocks */ +#define EXT4_GET_BLOCKS_NO_LOCK 0x0100 /* * Flags used by ext4_free_blocks @@ -810,6 +821,8 @@ struct ext4_ext_cache { __u32 ec_len; /* must be 32bit to return holes */ }; +#include "extents_status.h" + /* * fourth extended file system inode data in memory */ @@ -832,7 +845,6 @@ struct ext4_inode_info { #endif unsigned long i_flags; -#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 @@ -841,7 +853,6 @@ struct ext4_inode_info { * EAs. */ struct rw_semaphore xattr_sem; -#endif struct list_head i_orphan; /* unlinked but open inodes */ @@ -887,6 +898,10 @@ struct ext4_inode_info { struct list_head i_prealloc_list; spinlock_t i_prealloc_lock; + /* extents status tree */ + struct ext4_es_tree i_es_tree; + rwlock_t i_es_lock; + /* ialloc */ ext4_group_t i_last_alloc_group; @@ -901,6 +916,10 @@ struct ext4_inode_info { /* on-disk additional length */ __u16 i_extra_isize; + /* Indicate the inline data space. */ + u16 i_inline_off; + u16 i_inline_size; + #ifdef CONFIG_QUOTA /* quota space reservation, managed internally by quota code */ qsize_t i_reserved_quota; @@ -910,9 +929,7 @@ struct ext4_inode_info { struct list_head i_completed_io_list; spinlock_t i_completed_io_lock; atomic_t i_ioend_count; /* Number of outstanding io_end structs */ - /* current io_end structure for async DIO write*/ - ext4_io_end_t *cur_aio_dio; - atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */ + atomic_t i_unwritten; /* Nr. of inflight conversions pending */ spinlock_t i_block_reservation_lock; @@ -1161,8 +1178,7 @@ struct ext4_sb_info { unsigned long s_desc_per_block; /* Number of group descriptors per block */ ext4_group_t s_groups_count; /* Number of groups in the fs */ ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */ - unsigned long s_overhead_last; /* Last calculated overhead */ - unsigned long s_blocks_last; /* Last seen block count */ + unsigned long s_overhead; /* # of fs overhead clusters */ unsigned int s_cluster_ratio; /* Number of blocks per cluster */ unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */ loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ @@ -1232,6 +1248,7 @@ struct ext4_sb_info { spinlock_t s_md_lock; unsigned short *s_mb_offsets; unsigned int *s_mb_maxs; + unsigned int s_group_info_size; /* tunables */ unsigned long s_stripe; @@ -1242,6 +1259,7 @@ struct ext4_sb_info { unsigned int s_mb_order2_reqs; unsigned int s_mb_group_prealloc; unsigned int s_max_writeback_mb_bump; + unsigned int s_max_dir_size_kb; /* where last allocation was done - for stream allocation */ unsigned long s_mb_last_group; unsigned long s_mb_last_start; @@ -1269,8 +1287,12 @@ struct ext4_sb_info { unsigned long s_sectors_written_start; u64 s_kbytes_written; + /* the size of zero-out chunk */ + unsigned int s_extent_max_zeroout_kb; + unsigned int s_log_groups_per_flex; struct flex_groups *s_flex_groups; + ext4_group_t s_flex_groups_allocated; /* workqueue for dio unwritten */ struct workqueue_struct *dio_unwritten_wq; @@ -1314,6 +1336,8 @@ static inline struct timespec ext4_current_time(struct inode *inode) static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || + ino == EXT4_USR_QUOTA_INO || + ino == EXT4_GRP_QUOTA_INO || ino == EXT4_JOURNAL_INO || ino == EXT4_RESIZE_INO || (ino >= EXT4_FIRST_INO(sb) && @@ -1325,10 +1349,20 @@ static inline void ext4_set_io_unwritten_flag(struct inode *inode, { if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { io_end->flag |= EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + atomic_inc(&EXT4_I(inode)->i_unwritten); } } +static inline ext4_io_end_t *ext4_inode_aio(struct inode *inode) +{ + return inode->i_private; +} + +static inline void ext4_inode_aio_set(struct inode *inode, ext4_io_end_t *io) +{ + inode->i_private = io; +} + /* * Inode dynamic state flags */ @@ -1342,6 +1376,9 @@ enum { EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/ EXT4_STATE_NEWENTRY, /* File just added to dir */ EXT4_STATE_DELALLOC_RESERVED, /* blks already reserved for delalloc */ + EXT4_STATE_DIOREAD_LOCK, /* Disable support for dio read + nolocking */ + EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ @@ -1463,7 +1500,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */ #define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM 0x2000 /* use crc32c for bg */ #define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */ -#define EXT4_FEATURE_INCOMPAT_INLINEDATA 0x8000 /* data in inode */ +#define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */ #define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR #define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ @@ -1487,7 +1524,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_INCOMPAT_EXTENTS| \ EXT4_FEATURE_INCOMPAT_64BIT| \ EXT4_FEATURE_INCOMPAT_FLEX_BG| \ - EXT4_FEATURE_INCOMPAT_MMP) + EXT4_FEATURE_INCOMPAT_MMP | \ + EXT4_FEATURE_INCOMPAT_INLINE_DATA) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ @@ -1496,7 +1534,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ + EXT4_FEATURE_RO_COMPAT_QUOTA) /* * Default values for user and/or group using reserved blocks @@ -1573,6 +1612,11 @@ struct ext4_dir_entry_tail { __le32 det_checksum; /* crc32c(uuid+inum+dirblock) */ }; +#define EXT4_DIRENT_TAIL(block, blocksize) \ + ((struct ext4_dir_entry_tail *)(((void *)(block)) + \ + ((blocksize) - \ + sizeof(struct ext4_dir_entry_tail)))) + /* * Ext4 directory file types. Only the low 3 bits are used. The * other bits are reserved for now. @@ -1663,10 +1707,12 @@ static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, { struct { struct shash_desc shash; - char ctx[crypto_shash_descsize(sbi->s_chksum_driver)]; + char ctx[4]; } desc; int err; + BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx)); + desc.shash.tfm = sbi->s_chksum_driver; desc.shash.flags = 0; *(u32 *)desc.ctx = crc; @@ -1852,7 +1898,7 @@ struct mmpd_data { # define NORET_AND noreturn, /* bitmap.c */ -extern unsigned int ext4_count_free(struct buffer_head *, unsigned); +extern unsigned int ext4_count_free(char *bitmap, unsigned numchars); void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz); @@ -1861,10 +1907,10 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct buffer_head *bh, int sz); void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, - struct buffer_head *bh, int sz); + struct buffer_head *bh); int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, - struct buffer_head *bh, int sz); + struct buffer_head *bh); /* balloc.c */ extern void ext4_validate_block_bitmap(struct super_block *sb, @@ -1915,18 +1961,46 @@ ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, struct file *, struct ext4_dir_entry_2 *, - struct buffer_head *, unsigned int); -#define ext4_check_dir_entry(dir, filp, de, bh, offset) \ + struct buffer_head *, char *, int, + unsigned int); +#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \ unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \ - (de), (bh), (offset))) + (de), (bh), (buf), (size), (offset))) extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, struct ext4_dir_entry_2 *dirent); extern void ext4_htree_free_dir_info(struct dir_private_info *p); +extern int ext4_find_dest_de(struct inode *dir, struct inode *inode, + struct buffer_head *bh, + void *buf, int buf_size, + const char *name, int namelen, + struct ext4_dir_entry_2 **dest_de); +void ext4_insert_dentry(struct inode *inode, + struct ext4_dir_entry_2 *de, + int buf_size, + const char *name, int namelen); +static inline void ext4_update_dx_flag(struct inode *inode) +{ + if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_COMPAT_DIR_INDEX)) + ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); +} +static unsigned char ext4_filetype_table[] = { + DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK +}; + +static inline unsigned char get_dtype(struct super_block *sb, int filetype) +{ + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) || + (filetype >= EXT4_FT_MAX)) + return DT_UNKNOWN; + + return ext4_filetype_table[filetype]; +} /* fsync.c */ extern int ext4_sync_file(struct file *, loff_t, loff_t, int); -extern int ext4_flush_completed_IO(struct inode *); +extern int ext4_flush_unwritten_io(struct inode *); /* hash.c */ extern int ext4fs_dirhash(const char *name, int len, struct @@ -1960,6 +2034,8 @@ extern void ext4_exit_mballoc(void); extern void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags); +extern int ext4_mb_alloc_groupinfo(struct super_block *sb, + ext4_group_t ngroups); extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, @@ -1971,8 +2047,23 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int, int *); struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int, int *); +int ext4_get_block_write(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create); int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); +int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, + struct buffer_head *bh, int create); +int ext4_walk_page_buffers(handle_t *handle, + struct buffer_head *head, + unsigned from, + unsigned to, + int *partial, + int (*fn)(handle_t *handle, + struct buffer_head *bh)); +int do_journal_get_write_access(handle_t *handle, + struct buffer_head *bh); +#define FALL_BACK_TO_NONDELALLOC 1 +#define CONVERT_INLINE_DATA 2 extern struct inode *ext4_iget(struct super_block *, unsigned long); extern int ext4_write_inode(struct inode *, struct writeback_control *); @@ -2027,6 +2118,20 @@ extern int ext4_orphan_add(handle_t *, struct inode *); extern int ext4_orphan_del(handle_t *, struct inode *); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, __u32 start_minor_hash, __u32 *next_hash); +extern int search_dir(struct buffer_head *bh, + char *search_buf, + int buf_size, + struct inode *dir, + const struct qstr *d_name, + unsigned int offset, + struct ext4_dir_entry_2 **res_dir); +extern int ext4_generic_delete_entry(handle_t *handle, + struct inode *dir, + struct ext4_dir_entry_2 *de_del, + struct buffer_head *bh, + void *entry_buf, + int buf_size, + int csum_size); /* resize.c */ extern int ext4_group_add(struct super_block *sb, @@ -2037,13 +2142,15 @@ extern int ext4_group_extend(struct super_block *sb, extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count); /* super.c */ +extern int ext4_calculate_overhead(struct super_block *sb); extern int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es); -extern void ext4_superblock_csum_set(struct super_block *sb, - struct ext4_super_block *es); +extern void ext4_superblock_csum_set(struct super_block *sb); extern void *ext4_kvmalloc(size_t size, gfp_t flags); extern void *ext4_kvzalloc(size_t size, gfp_t flags); extern void ext4_kvfree(void *ptr); +extern int ext4_alloc_flex_bg_array(struct super_block *sb, + ext4_group_t ngroup); extern __printf(4, 5) void __ext4_error(struct super_block *, const char *, unsigned int, const char *, ...); @@ -2321,15 +2428,6 @@ static inline void ext4_unlock_group(struct super_block *sb, spin_unlock(ext4_group_lock_ptr(sb, group)); } -static inline void ext4_mark_super_dirty(struct super_block *sb) -{ - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - - ext4_superblock_csum_set(sb, es); - if (EXT4_SB(sb)->s_journal == NULL) - sb->s_dirt =1; -} - /* * Block validity checking */ @@ -2354,11 +2452,21 @@ extern const struct file_operations ext4_dir_operations; extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); +extern void ext4_unwritten_wait(struct inode *inode); /* 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); +extern struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, + struct ext4_dir_entry_2 *de, + int blocksize, int csum_size, + unsigned int parent_ino, int dotdot_real_len); +extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t, + unsigned int blocksize); +extern int ext4_handle_dirty_dirent_node(handle_t *handle, + struct inode *inode, + struct buffer_head *bh); /* symlink.c */ extern const struct inode_operations ext4_symlink_inode_operations; @@ -2376,6 +2484,9 @@ extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); /* extents.c */ +struct ext4_ext_path; +struct ext4_extent; + extern int ext4_ext_tree_init(handle_t *handle, struct inode *); extern int ext4_ext_writepage_trans_blocks(struct inode *, int); extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, @@ -2393,8 +2504,27 @@ extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset, ssize_t len); extern int ext4_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); +extern int ext4_ext_calc_metadata_amount(struct inode *inode, + ext4_lblk_t lblocks); +extern int ext4_extent_tree_init(handle_t *, struct inode *); +extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, + int num, + struct ext4_ext_path *path); +extern int ext4_can_extents_be_merged(struct inode *inode, + struct ext4_extent *ex1, + struct ext4_extent *ex2); +extern int ext4_ext_insert_extent(handle_t *, struct inode *, + struct ext4_ext_path *, + struct ext4_extent *, int); +extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, + struct ext4_ext_path *); +extern void ext4_ext_drop_refs(struct ext4_ext_path *); +extern int ext4_ext_check_inode(struct inode *inode); +extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); + + /* move_extent.c */ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 start_orig, __u64 start_donor, @@ -2402,11 +2532,11 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, /* page-io.c */ extern int __init ext4_init_pageio(void); +extern void ext4_add_complete_io(ext4_io_end_t *io_end); extern void ext4_exit_pageio(void); extern void ext4_ioend_wait(struct inode *); extern void ext4_free_io_end(ext4_io_end_t *io); extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags); -extern int ext4_end_io_nolock(ext4_io_end_t *io); extern void ext4_io_submit(struct ext4_io_submit *io); extern int ext4_bio_write_page(struct ext4_io_submit *io, struct page *page, @@ -2428,17 +2558,13 @@ enum ext4_state_bits { * never, ever appear in a buffer_head's state * flag. See EXT4_MAP_FROM_CLUSTER to see where * this is used. */ - BH_Da_Mapped, /* Delayed allocated block that now has a mapping. This - * flag is set when ext4_map_blocks is called on a - * delayed allocated block to get its real mapping. */ }; BUFFER_FNS(Uninit, uninit) TAS_BUFFER_FNS(Uninit, uninit) -BUFFER_FNS(Da_Mapped, da_mapped) /* - * Add new method to test wether block and inode bitmaps are properly + * Add new method to test whether block and inode bitmaps are properly * initialized. With uninit_bg reading the block from disk is not enough * to mark the bitmap uptodate. We need to also zero-out the bitmap */ @@ -2454,6 +2580,21 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh) set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state); } +/* + * Disable DIO read nolock optimization, so new dioreaders will be forced + * to grab i_mutex + */ +static inline void ext4_inode_block_unlocked_dio(struct inode *inode) +{ + ext4_set_inode_state(inode, EXT4_STATE_DIOREAD_LOCK); + smp_mb(); +} +static inline void ext4_inode_resume_unlocked_dio(struct inode *inode) +{ + smp_mb(); + ext4_clear_inode_state(inode, EXT4_STATE_DIOREAD_LOCK); +} + #define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1) /* For ioend & aio unwritten conversion wait queues */ @@ -2471,6 +2612,4 @@ extern void ext4_resize_end(struct super_block *sb); #endif /* __KERNEL__ */ -#include "ext4_extents.h" - #endif /* _EXT4_H */ diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index cb1b2c91996..487fda12bc0 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -43,16 +43,6 @@ #define CHECK_BINSEARCH__ /* - * Turn on EXT_DEBUG to get lots of info about extents operations. - */ -#define EXT_DEBUG__ -#ifdef EXT_DEBUG -#define ext_debug(fmt, ...) printk(fmt, ##__VA_ARGS__) -#else -#define ext_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) -#endif - -/* * If EXT_STATS is defined then stats numbers are collected. * These number will be displayed at umount time. */ @@ -144,20 +134,6 @@ struct ext4_ext_path { */ /* - * to be called by ext4_ext_walk_space() - * negative retcode - error - * positive retcode - signal for ext4_ext_walk_space(), see below - * callback must return valid extent (passed or newly created) - */ -typedef int (*ext_prepare_callback)(struct inode *, ext4_lblk_t, - struct ext4_ext_cache *, - struct ext4_extent *, void *); - -#define EXT_CONTINUE 0 -#define EXT_BREAK 1 -#define EXT_REPEAT 2 - -/* * Maximum number of logical blocks in a file; ext4_extent's ee_block is * __le32. */ @@ -300,21 +276,5 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, 0xffff); } -extern int ext4_ext_calc_metadata_amount(struct inode *inode, - ext4_lblk_t lblocks); -extern int ext4_extent_tree_init(handle_t *, struct inode *); -extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, - int num, - struct ext4_ext_path *path); -extern int ext4_can_extents_be_merged(struct inode *inode, - struct ext4_extent *ex1, - struct ext4_extent *ex2); -extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *, int); -extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, - struct ext4_ext_path *); -extern void ext4_ext_drop_refs(struct ext4_ext_path *); -extern int ext4_ext_check_inode(struct inode *inode); -extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk, - int search_hint_reverse); #endif /* _EXT4_EXTENTS */ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 90f7c2e84db..b4323ba846b 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -138,24 +138,18 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, } int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb, - int now) + handle_t *handle, struct super_block *sb) { struct buffer_head *bh = EXT4_SB(sb)->s_sbh; int err = 0; + ext4_superblock_csum_set(sb); if (ext4_handle_valid(handle)) { - ext4_superblock_csum_set(sb, - (struct ext4_super_block *)bh->b_data); err = jbd2_journal_dirty_metadata(handle, bh); if (err) ext4_journal_abort_handle(where, line, __func__, bh, handle, err); - } else if (now) { - ext4_superblock_csum_set(sb, - (struct ext4_super_block *)bh->b_data); - mark_buffer_dirty(bh); } else - sb->s_dirt = 1; + mark_buffer_dirty(bh); return err; } diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index f440e8f1841..7177f9b21cb 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -87,14 +87,20 @@ #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ -#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0) +#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ -#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0) - -#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0) +#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ + +3+DQUOT_INIT_REWRITE) : 0) + +#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ + +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 @@ -213,8 +219,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, struct buffer_head *bh); int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb, - int now); + handle_t *handle, struct super_block *sb); #define ext4_journal_get_write_access(handle, bh) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh)) @@ -226,10 +231,8 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) -#define ext4_handle_dirty_super_now(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 1) #define ext4_handle_dirty_super(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 0) + __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); @@ -251,13 +254,6 @@ static inline void ext4_handle_sync(handle_t *handle) handle->h_sync = 1; } -static inline void ext4_handle_release_buffer(handle_t *handle, - struct buffer_head *bh) -{ - if (ext4_handle_valid(handle)) - jbd2_journal_release_buffer(handle, bh); -} - static inline int ext4_handle_is_aborted(handle_t *handle) { if (ext4_handle_valid(handle)) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 91341ec6e06..5ae1674ec12 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -41,6 +41,8 @@ #include <asm/uaccess.h> #include <linux/fiemap.h> #include "ext4_jbd2.h" +#include "ext4_extents.h" +#include "xattr.h" #include <trace/events/ext4.h> @@ -52,6 +54,9 @@ #define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */ #define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */ +#define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */ +#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */ + static __le32 ext4_extent_block_csum(struct inode *inode, struct ext4_extent_header *eh) { @@ -106,6 +111,9 @@ static int ext4_split_extent_at(handle_t *handle, int split_flag, int flags); +static int ext4_find_delayed_extent(struct inode *inode, + struct ext4_ext_cache *newex); + static int ext4_ext_truncate_extend_restart(handle_t *handle, struct inode *inode, int needed) @@ -1177,7 +1185,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block), ext4_idx_pblock(EXT_FIRST_INDEX(neh))); - neh->eh_depth = cpu_to_le16(le16_to_cpu(neh->eh_depth) + 1); + le16_add_cpu(&neh->eh_depth, 1); ext4_mark_inode_dirty(handle, inode); out: brelse(bh); @@ -1656,16 +1664,60 @@ static int ext4_ext_try_to_merge_right(struct inode *inode, } /* + * This function does a very simple check to see if we can collapse + * an extent tree with a single extent tree leaf block into the inode. + */ +static void ext4_ext_try_to_merge_up(handle_t *handle, + struct inode *inode, + struct ext4_ext_path *path) +{ + size_t s; + unsigned max_root = ext4_ext_space_root(inode, 0); + ext4_fsblk_t blk; + + if ((path[0].p_depth != 1) || + (le16_to_cpu(path[0].p_hdr->eh_entries) != 1) || + (le16_to_cpu(path[1].p_hdr->eh_entries) > max_root)) + return; + + /* + * We need to modify the block allocation bitmap and the block + * group descriptor to release the extent tree block. If we + * can't get the journal credits, give up. + */ + if (ext4_journal_extend(handle, 2)) + return; + + /* + * Copy the extent data up to the inode + */ + blk = ext4_idx_pblock(path[0].p_idx); + s = le16_to_cpu(path[1].p_hdr->eh_entries) * + sizeof(struct ext4_extent_idx); + s += sizeof(struct ext4_extent_header); + + memcpy(path[0].p_hdr, path[1].p_hdr, s); + path[0].p_depth = 0; + path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) + + (path[1].p_ext - EXT_FIRST_EXTENT(path[1].p_hdr)); + path[0].p_hdr->eh_max = cpu_to_le16(max_root); + + brelse(path[1].p_bh); + ext4_free_blocks(handle, inode, NULL, blk, 1, + EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); +} + +/* * This function tries to merge the @ex extent to neighbours in the tree. * return 1 if merge left else 0. */ -static int ext4_ext_try_to_merge(struct inode *inode, +static void ext4_ext_try_to_merge(handle_t *handle, + struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth; int merge_done = 0; - int ret = 0; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); @@ -1675,9 +1727,9 @@ static int ext4_ext_try_to_merge(struct inode *inode, merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1); if (!merge_done) - ret = ext4_ext_try_to_merge_right(inode, path, ex); + (void) ext4_ext_try_to_merge_right(inode, path, ex); - return ret; + ext4_ext_try_to_merge_up(handle, inode, path); } /* @@ -1891,18 +1943,17 @@ has_space: nearex->ee_len = newext->ee_len; merge: - /* try to merge extents to the right */ + /* try to merge extents */ if (!(flag & EXT4_GET_BLOCKS_PRE_IO)) - ext4_ext_try_to_merge(inode, path, nearex); + ext4_ext_try_to_merge(handle, inode, path, nearex); - /* try to merge extents to the left */ /* time to correct all indexes above */ err = ext4_ext_correct_indexes(handle, inode, path); if (err) goto cleanup; - err = ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); cleanup: if (npath) { @@ -1913,27 +1964,33 @@ cleanup: return err; } -static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, - ext4_lblk_t num, ext_prepare_callback func, - void *cbdata) +static int ext4_fill_fiemap_extents(struct inode *inode, + ext4_lblk_t block, ext4_lblk_t num, + struct fiemap_extent_info *fieinfo) { struct ext4_ext_path *path = NULL; - struct ext4_ext_cache cbex; + struct ext4_ext_cache newex; struct ext4_extent *ex; - ext4_lblk_t next, start = 0, end = 0; + ext4_lblk_t next, next_del, start = 0, end = 0; ext4_lblk_t last = block + num; - int depth, exists, err = 0; - - BUG_ON(func == NULL); - BUG_ON(inode == NULL); + int exists, depth = 0, err = 0; + unsigned int flags = 0; + unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; while (block < last && block != EXT_MAX_BLOCKS) { num = last - block; /* find extent for this block */ down_read(&EXT4_I(inode)->i_data_sem); + + if (path && ext_depth(inode) != depth) { + /* depth was changed. we have to realloc path */ + kfree(path); + path = NULL; + } + path = ext4_ext_find_extent(inode, block, path); - up_read(&EXT4_I(inode)->i_data_sem); if (IS_ERR(path)) { + up_read(&EXT4_I(inode)->i_data_sem); err = PTR_ERR(path); path = NULL; break; @@ -1941,13 +1998,16 @@ static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, depth = ext_depth(inode); if (unlikely(path[depth].p_hdr == NULL)) { + up_read(&EXT4_I(inode)->i_data_sem); EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); err = -EIO; break; } ex = path[depth].p_ext; next = ext4_ext_next_allocated_block(path); + ext4_ext_drop_refs(path); + flags = 0; exists = 0; if (!ex) { /* there is no extent yet, so try to allocate @@ -1984,40 +2044,64 @@ static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, BUG_ON(end <= start); if (!exists) { - cbex.ec_block = start; - cbex.ec_len = end - start; - cbex.ec_start = 0; + newex.ec_block = start; + newex.ec_len = end - start; + newex.ec_start = 0; } else { - cbex.ec_block = le32_to_cpu(ex->ee_block); - cbex.ec_len = ext4_ext_get_actual_len(ex); - cbex.ec_start = ext4_ext_pblock(ex); + newex.ec_block = le32_to_cpu(ex->ee_block); + newex.ec_len = ext4_ext_get_actual_len(ex); + newex.ec_start = ext4_ext_pblock(ex); + if (ext4_ext_is_uninitialized(ex)) + flags |= FIEMAP_EXTENT_UNWRITTEN; } - if (unlikely(cbex.ec_len == 0)) { - EXT4_ERROR_INODE(inode, "cbex.ec_len == 0"); - err = -EIO; - break; + /* + * Find delayed extent and update newex accordingly. We call + * it even in !exists case to find out whether newex is the + * last existing extent or not. + */ + next_del = ext4_find_delayed_extent(inode, &newex); + if (!exists && next_del) { + exists = 1; + flags |= FIEMAP_EXTENT_DELALLOC; } - err = func(inode, next, &cbex, ex, cbdata); - ext4_ext_drop_refs(path); + up_read(&EXT4_I(inode)->i_data_sem); - if (err < 0) + if (unlikely(newex.ec_len == 0)) { + EXT4_ERROR_INODE(inode, "newex.ec_len == 0"); + err = -EIO; break; + } - if (err == EXT_REPEAT) - continue; - else if (err == EXT_BREAK) { - err = 0; - break; + /* This is possible iff next == next_del == EXT_MAX_BLOCKS */ + if (next == next_del) { + flags |= FIEMAP_EXTENT_LAST; + if (unlikely(next_del != EXT_MAX_BLOCKS || + next != EXT_MAX_BLOCKS)) { + EXT4_ERROR_INODE(inode, + "next extent == %u, next " + "delalloc extent = %u", + next, next_del); + err = -EIO; + break; + } } - if (ext_depth(inode) != depth) { - /* depth was changed. we have to realloc path */ - kfree(path); - path = NULL; + if (exists) { + err = fiemap_fill_next_extent(fieinfo, + (__u64)newex.ec_block << blksize_bits, + (__u64)newex.ec_start << blksize_bits, + (__u64)newex.ec_len << blksize_bits, + flags); + if (err < 0) + break; + if (err == 1) { + err = 0; + break; + } } - block = cbex.ec_block + cbex.ec_len; + block = newex.ec_block + newex.ec_len; } if (path) { @@ -2093,13 +2177,10 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, } /* - * ext4_ext_check_cache() + * ext4_ext_in_cache() * Checks to see if the given block is in the cache. * If it is, the cached extent is stored in the given - * cache extent pointer. If the cached extent is a hole, - * this routine should be used instead of - * ext4_ext_in_cache if the calling function needs to - * know the size of the hole. + * cache extent pointer. * * @inode: The files inode * @block: The block to look for in the cache @@ -2108,10 +2189,11 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, * * Return 0 if cache is invalid; 1 if the cache is valid */ -static int ext4_ext_check_cache(struct inode *inode, ext4_lblk_t block, - struct ext4_ext_cache *ex){ +static int +ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block, + struct ext4_extent *ex) +{ struct ext4_ext_cache *cex; - struct ext4_sb_info *sbi; int ret = 0; /* @@ -2119,14 +2201,15 @@ static int ext4_ext_check_cache(struct inode *inode, ext4_lblk_t block, */ spin_lock(&EXT4_I(inode)->i_block_reservation_lock); cex = &EXT4_I(inode)->i_cached_extent; - sbi = EXT4_SB(inode->i_sb); /* has cache valid data? */ if (cex->ec_len == 0) goto errout; if (in_range(block, cex->ec_block, cex->ec_len)) { - memcpy(ex, cex, sizeof(struct ext4_ext_cache)); + ex->ee_block = cpu_to_le32(cex->ec_block); + ext4_ext_store_pblock(ex, cex->ec_start); + ex->ee_len = cpu_to_le16(cex->ec_len); ext_debug("%u cached by %u:%u:%llu\n", block, cex->ec_block, cex->ec_len, cex->ec_start); @@ -2139,48 +2222,18 @@ errout: } /* - * ext4_ext_in_cache() - * Checks to see if the given block is in the cache. - * If it is, the cached extent is stored in the given - * extent pointer. - * - * @inode: The files inode - * @block: The block to look for in the cache - * @ex: Pointer where the cached extent will be stored - * if it contains block - * - * Return 0 if cache is invalid; 1 if the cache is valid - */ -static int -ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block, - struct ext4_extent *ex) -{ - struct ext4_ext_cache cex; - int ret = 0; - - if (ext4_ext_check_cache(inode, block, &cex)) { - ex->ee_block = cpu_to_le32(cex.ec_block); - ext4_ext_store_pblock(ex, cex.ec_start); - ex->ee_len = cpu_to_le16(cex.ec_len); - ret = 1; - } - - return ret; -} - - -/* * ext4_ext_rm_idx: * removes index from the index block. */ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, - struct ext4_ext_path *path) + struct ext4_ext_path *path, int depth) { int err; ext4_fsblk_t leaf; /* free index block */ - path--; + depth--; + path = path + depth; leaf = ext4_idx_pblock(path->p_idx); if (unlikely(path->p_hdr->eh_entries == 0)) { EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0"); @@ -2205,6 +2258,19 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, ext4_free_blocks(handle, inode, NULL, leaf, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); + + while (--depth >= 0) { + if (path->p_idx != EXT_FIRST_INDEX(path->p_hdr)) + break; + path--; + err = ext4_ext_get_access(handle, inode, path); + if (err) + break; + path->p_idx->ei_block = (path+1)->p_idx->ei_block; + err = ext4_ext_dirty(handle, inode, path); + if (err) + break; + } return err; } @@ -2257,7 +2323,13 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) { int index; - int depth = ext_depth(inode); + int depth; + + /* If we are converting the inline data, only one is needed here. */ + if (ext4_has_inline_data(inode)) + return 1; + + depth = ext_depth(inode); if (chunk) index = depth * 2; @@ -2275,10 +2347,13 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned short ee_len = ext4_ext_get_actual_len(ex); ext4_fsblk_t pblk; - int flags = EXT4_FREE_BLOCKS_FORGET; + int flags = 0; if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) - flags |= EXT4_FREE_BLOCKS_METADATA; + flags |= EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET; + else if (ext4_should_journal_data(inode)) + flags |= EXT4_FREE_BLOCKS_FORGET; + /* * For bigalloc file systems, we never free a partial cluster * at the beginning of the extent. Instead, we make a note @@ -2538,7 +2613,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, /* if this leaf is free, then we should * remove it from index block above */ if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL) - err = ext4_ext_rm_idx(handle, inode, path + depth); + err = ext4_ext_rm_idx(handle, inode, path, depth); out: return err; @@ -2570,10 +2645,10 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, { struct super_block *sb = inode->i_sb; int depth = ext_depth(inode); - struct ext4_ext_path *path; + struct ext4_ext_path *path = NULL; ext4_fsblk_t partial_cluster = 0; handle_t *handle; - int i, err; + int i = 0, err = 0; ext_debug("truncate since %u to %u\n", start, end); @@ -2605,9 +2680,17 @@ again: return PTR_ERR(path); } depth = ext_depth(inode); + /* Leaf not may not exist only if inode has no blocks at all */ ex = path[depth].p_ext; - if (!ex) - goto cont; + if (!ex) { + if (depth) { + EXT4_ERROR_INODE(inode, + "path[%d].p_hdr == NULL", + depth); + err = -EIO; + } + goto out; + } ee_block = le32_to_cpu(ex->ee_block); @@ -2637,29 +2720,34 @@ again: if (err < 0) goto out; } - ext4_ext_drop_refs(path); - kfree(path); } -cont: - /* * We start scanning from right side, freeing all the blocks * after i_size and walking into the tree depth-wise. */ depth = ext_depth(inode); - path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS); - if (path == NULL) { - ext4_journal_stop(handle); - return -ENOMEM; - } - path[0].p_depth = depth; - path[0].p_hdr = ext_inode_hdr(inode); + if (path) { + int k = i = depth; + while (--k > 0) + path[k].p_block = + le16_to_cpu(path[k].p_hdr->eh_entries)+1; + } else { + path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), + GFP_NOFS); + if (path == NULL) { + ext4_journal_stop(handle); + return -ENOMEM; + } + path[0].p_depth = depth; + path[0].p_hdr = ext_inode_hdr(inode); + i = 0; - if (ext4_ext_check(inode, path[0].p_hdr, depth)) { - err = -EIO; - goto out; + if (ext4_ext_check(inode, path[0].p_hdr, depth)) { + err = -EIO; + goto out; + } } - i = err = 0; + err = 0; while (i >= 0 && err == 0) { if (i == depth) { @@ -2728,7 +2816,7 @@ cont: /* index is empty, remove it; * handle must be already prepared by the * truncatei_leaf() */ - err = ext4_ext_rm_idx(handle, inode, path + i); + err = ext4_ext_rm_idx(handle, inode, path, i); } /* root level has p_bh == NULL, brelse() eats this */ brelse(path[i].p_bh); @@ -2773,8 +2861,10 @@ cont: out: ext4_ext_drop_refs(path); kfree(path); - if (err == -EAGAIN) + if (err == -EAGAIN) { + path = NULL; goto again; + } ext4_journal_stop(handle); return err; @@ -2883,6 +2973,9 @@ static int ext4_split_extent_at(handle_t *handle, unsigned int ee_len, depth; int err = 0; + BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) == + (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)); + ext_debug("ext4_split_extents_at: inode %lu, logical" "block %llu\n", inode->i_ino, (unsigned long long)split); @@ -2912,9 +3005,9 @@ static int ext4_split_extent_at(handle_t *handle, ext4_ext_mark_initialized(ex); if (!(flags & EXT4_GET_BLOCKS_PRE_IO)) - ext4_ext_try_to_merge(inode, path, ex); + ext4_ext_try_to_merge(handle, inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); goto out; } @@ -2941,13 +3034,20 @@ static int ext4_split_extent_at(handle_t *handle, err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) { - err = ext4_ext_zeroout(inode, &orig_ex); + if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { + if (split_flag & EXT4_EXT_DATA_VALID1) + err = ext4_ext_zeroout(inode, ex2); + else + err = ext4_ext_zeroout(inode, ex); + } else + err = ext4_ext_zeroout(inode, &orig_ex); + if (err) goto fix_extent_len; /* update the extent length and mark as initialized */ ex->ee_len = cpu_to_le16(ee_len); - ext4_ext_try_to_merge(inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + depth); + ext4_ext_try_to_merge(handle, inode, path, ex); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); goto out; } else if (err) goto fix_extent_len; @@ -2994,12 +3094,13 @@ static int ext4_split_extent(handle_t *handle, uninitialized = ext4_ext_is_uninitialized(ex); if (map->m_lblk + map->m_len < ee_block + ee_len) { - split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ? - EXT4_EXT_MAY_ZEROOUT : 0; + split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT; flags1 = flags | EXT4_GET_BLOCKS_PRE_IO; if (uninitialized) split_flag1 |= EXT4_EXT_MARK_UNINIT1 | EXT4_EXT_MARK_UNINIT2; + if (split_flag & EXT4_EXT_DATA_VALID2) + split_flag1 |= EXT4_EXT_DATA_VALID1; err = ext4_split_extent_at(handle, inode, path, map->m_lblk + map->m_len, split_flag1, flags1); if (err) @@ -3012,8 +3113,8 @@ static int ext4_split_extent(handle_t *handle, return PTR_ERR(path); if (map->m_lblk >= ee_block) { - split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ? - EXT4_EXT_MAY_ZEROOUT : 0; + split_flag1 = split_flag & (EXT4_EXT_MAY_ZEROOUT | + EXT4_EXT_DATA_VALID2); if (uninitialized) split_flag1 |= EXT4_EXT_MARK_UNINIT1; if (split_flag & EXT4_EXT_MARK_UNINIT2) @@ -3029,7 +3130,6 @@ out: return err ? err : map->m_len; } -#define EXT4_EXT_ZERO_LEN 7 /* * This function is called by ext4_ext_map_blocks() if someone tries to write * to an uninitialized extent. It may result in splitting the uninitialized @@ -3055,13 +3155,14 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, struct ext4_map_blocks *map, struct ext4_ext_path *path) { + struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; struct ext4_extent zero_ex; struct ext4_extent *ex; ext4_lblk_t ee_block, eof_block; unsigned int ee_len, depth; - int allocated; + int allocated, max_zeroout = 0; int err = 0; int split_flag = 0; @@ -3069,6 +3170,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, "block %llu, max_blocks %u\n", inode->i_ino, (unsigned long long)map->m_lblk, map->m_len); + sbi = EXT4_SB(inode->i_sb); eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map->m_len) @@ -3168,9 +3270,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, */ split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; - /* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */ - if (ee_len <= 2*EXT4_EXT_ZERO_LEN && - (EXT4_EXT_MAY_ZEROOUT & split_flag)) { + if (EXT4_EXT_MAY_ZEROOUT & split_flag) + max_zeroout = sbi->s_extent_max_zeroout_kb >> + inode->i_sb->s_blocksize_bits; + + /* If extent is less than s_max_zeroout_kb, zeroout directly */ + if (max_zeroout && (ee_len <= max_zeroout)) { err = ext4_ext_zeroout(inode, ex); if (err) goto out; @@ -3179,8 +3284,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, if (err) goto out; ext4_ext_mark_initialized(ex); - ext4_ext_try_to_merge(inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + depth); + ext4_ext_try_to_merge(handle, inode, path, ex); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); goto out; } @@ -3194,9 +3299,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, split_map.m_lblk = map->m_lblk; split_map.m_len = map->m_len; - if (allocated > map->m_len) { - if (allocated <= EXT4_EXT_ZERO_LEN && - (EXT4_EXT_MAY_ZEROOUT & split_flag)) { + if (max_zeroout && (allocated > map->m_len)) { + if (allocated <= max_zeroout) { /* case 3 */ zero_ex.ee_block = cpu_to_le32(map->m_lblk); @@ -3208,9 +3312,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, goto out; split_map.m_lblk = map->m_lblk; split_map.m_len = allocated; - } else if ((map->m_lblk - ee_block + map->m_len < - EXT4_EXT_ZERO_LEN) && - (EXT4_EXT_MAY_ZEROOUT & split_flag)) { + } else if (map->m_lblk - ee_block + map->m_len < max_zeroout) { /* case 2 */ if (map->m_lblk != ee_block) { zero_ex.ee_block = ex->ee_block; @@ -3230,7 +3332,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, } allocated = ext4_split_extent(handle, inode, path, - &split_map, split_flag, 0); + &split_map, split_flag, 0); if (allocated < 0) err = allocated; @@ -3244,7 +3346,7 @@ out: * to an uninitialized extent. * * Writing to an uninitialized extent may result in splitting the uninitialized - * extent into multiple /initialized uninitialized extents (up to three) + * extent into multiple initialized/uninitialized extents (up to three) * There are three possibilities: * a> There is no split required: Entire extent should be uninitialized * b> Splits in two extents: Write is happening at either end of the extent @@ -3291,26 +3393,47 @@ static int ext4_split_unwritten_extents(handle_t *handle, split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; split_flag |= EXT4_EXT_MARK_UNINIT2; - + if (flags & EXT4_GET_BLOCKS_CONVERT) + split_flag |= EXT4_EXT_DATA_VALID2; flags |= EXT4_GET_BLOCKS_PRE_IO; return ext4_split_extent(handle, inode, path, map, split_flag, flags); } static int ext4_convert_unwritten_extents_endio(handle_t *handle, - struct inode *inode, - struct ext4_ext_path *path) + struct inode *inode, + struct ext4_map_blocks *map, + struct ext4_ext_path *path) { struct ext4_extent *ex; + ext4_lblk_t ee_block; + unsigned int ee_len; int depth; int err = 0; depth = ext_depth(inode); ex = path[depth].p_ext; + ee_block = le32_to_cpu(ex->ee_block); + ee_len = ext4_ext_get_actual_len(ex); ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical" "block %llu, max_blocks %u\n", inode->i_ino, - (unsigned long long)le32_to_cpu(ex->ee_block), - ext4_ext_get_actual_len(ex)); + (unsigned long long)ee_block, ee_len); + + /* If extent is larger than requested then split is required */ + if (ee_block != map->m_lblk || ee_len > map->m_len) { + err = ext4_split_unwritten_extents(handle, inode, map, path, + EXT4_GET_BLOCKS_CONVERT); + if (err < 0) + goto out; + ext4_ext_drop_refs(path); + path = ext4_ext_find_extent(inode, map->m_lblk, path); + if (IS_ERR(path)) { + err = PTR_ERR(path); + goto out; + } + depth = ext_depth(inode); + ex = path[depth].p_ext; + } err = ext4_ext_get_access(handle, inode, path + depth); if (err) @@ -3321,10 +3444,10 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, /* note: ext4_ext_correct_indexes() isn't needed here because * borders are not changed */ - ext4_ext_try_to_merge(inode, path, ex); + ext4_ext_try_to_merge(handle, inode, path, ex); /* Mark modified extent as dirty */ - err = ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); out: ext4_ext_show_leaf(inode, path); return err; @@ -3394,115 +3517,34 @@ out: /** * ext4_find_delalloc_range: find delayed allocated block in the given range. * - * Goes through the buffer heads in the range [lblk_start, lblk_end] and returns - * whether there are any buffers marked for delayed allocation. It returns '1' - * on the first delalloc'ed buffer head found. If no buffer head in the given - * range is marked for delalloc, it returns 0. - * lblk_start should always be <= lblk_end. - * search_hint_reverse is to indicate that searching in reverse from lblk_end to - * lblk_start might be more efficient (i.e., we will likely hit the delalloc'ed - * block sooner). This is useful when blocks are truncated sequentially from - * lblk_start towards lblk_end. + * Return 1 if there is a delalloc block in the range, otherwise 0. */ static int ext4_find_delalloc_range(struct inode *inode, ext4_lblk_t lblk_start, - ext4_lblk_t lblk_end, - int search_hint_reverse) + ext4_lblk_t lblk_end) { - struct address_space *mapping = inode->i_mapping; - struct buffer_head *head, *bh = NULL; - struct page *page; - ext4_lblk_t i, pg_lblk; - pgoff_t index; + struct extent_status es; - if (!test_opt(inode->i_sb, DELALLOC)) - return 0; - - /* reverse search wont work if fs block size is less than page size */ - if (inode->i_blkbits < PAGE_CACHE_SHIFT) - search_hint_reverse = 0; - - if (search_hint_reverse) - i = lblk_end; + es.start = lblk_start; + ext4_es_find_extent(inode, &es); + if (es.len == 0) + return 0; /* there is no delay extent in this tree */ + else if (es.start <= lblk_start && lblk_start < es.start + es.len) + return 1; + else if (lblk_start <= es.start && es.start <= lblk_end) + return 1; else - i = lblk_start; - - index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits); - - while ((i >= lblk_start) && (i <= lblk_end)) { - page = find_get_page(mapping, index); - if (!page) - goto nextpage; - - if (!page_has_buffers(page)) - goto nextpage; - - head = page_buffers(page); - if (!head) - goto nextpage; - - bh = head; - pg_lblk = index << (PAGE_CACHE_SHIFT - - inode->i_blkbits); - do { - if (unlikely(pg_lblk < lblk_start)) { - /* - * This is possible when fs block size is less - * than page size and our cluster starts/ends in - * middle of the page. So we need to skip the - * initial few blocks till we reach the 'lblk' - */ - pg_lblk++; - continue; - } - - /* Check if the buffer is delayed allocated and that it - * is not yet mapped. (when da-buffers are mapped during - * their writeout, their da_mapped bit is set.) - */ - if (buffer_delay(bh) && !buffer_da_mapped(bh)) { - page_cache_release(page); - trace_ext4_find_delalloc_range(inode, - lblk_start, lblk_end, - search_hint_reverse, - 1, i); - return 1; - } - if (search_hint_reverse) - i--; - else - i++; - } while ((i >= lblk_start) && (i <= lblk_end) && - ((bh = bh->b_this_page) != head)); -nextpage: - if (page) - page_cache_release(page); - /* - * Move to next page. 'i' will be the first lblk in the next - * page. - */ - if (search_hint_reverse) - index--; - else - index++; - i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - } - - trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end, - search_hint_reverse, 0, 0); - return 0; + return 0; } -int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk, - int search_hint_reverse) +int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t lblk_start, lblk_end; lblk_start = lblk & (~(sbi->s_cluster_ratio - 1)); lblk_end = lblk_start + sbi->s_cluster_ratio - 1; - return ext4_find_delalloc_range(inode, lblk_start, lblk_end, - search_hint_reverse); + return ext4_find_delalloc_range(inode, lblk_start, lblk_end); } /** @@ -3563,7 +3605,7 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1)); lblk_to = lblk_from + c_offset - 1; - if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0)) + if (ext4_find_delalloc_range(inode, lblk_from, lblk_to)) allocated_clusters--; } @@ -3573,7 +3615,7 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, lblk_from = lblk_start + num_blks; lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1; - if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0)) + if (ext4_find_delalloc_range(inode, lblk_from, lblk_to)) allocated_clusters--; } @@ -3588,7 +3630,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, { int ret = 0; int err = 0; - ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio; + ext4_io_end_t *io = ext4_inode_aio(inode); ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical " "block %llu, max_blocks %u, flags %x, allocated %u\n", @@ -3596,13 +3638,15 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, flags, allocated); ext4_ext_show_leaf(inode, path); - trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated, - newblock); + trace_ext4_ext_handle_uninitialized_extents(inode, map, flags, + allocated, newblock); /* get_block() before submit the IO, split the extent */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { ret = ext4_split_unwritten_extents(handle, inode, map, path, flags); + if (ret <= 0) + goto out; /* * Flag the inode(non aio case) or end_io struct (aio case) * that this IO needs to conversion to written when IO is @@ -3618,7 +3662,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, } /* IO end_io complete, convert the filled extent to written */ if ((flags & EXT4_GET_BLOCKS_CONVERT)) { - ret = ext4_convert_unwritten_extents_endio(handle, inode, + ret = ext4_convert_unwritten_extents_endio(handle, inode, map, path); if (ret >= 0) { ext4_update_inode_fsync_trans(handle, inode, 1); @@ -3842,12 +3886,13 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_extent newex, *ex, *ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_fsblk_t newblock = 0; - int free_on_err = 0, err = 0, depth, ret; + int free_on_err = 0, err = 0, depth; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; - ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio; + ext4_io_end_t *io = ext4_inode_aio(inode); ext4_lblk_t cluster_offset; + int set_unwritten = 0; ext_debug("blocks %u/%u requested for inode %lu\n", map->m_lblk, map->m_len, inode->i_ino); @@ -3857,7 +3902,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) { if (!newex.ee_start_lo && !newex.ee_start_hi) { if ((sbi->s_cluster_ratio > 1) && - ext4_find_delalloc_cluster(inode, map->m_lblk, 0)) + ext4_find_delalloc_cluster(inode, map->m_lblk)) map->m_flags |= EXT4_MAP_FROM_CLUSTER; if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { @@ -3937,15 +3982,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ee_len, ee_start); goto out; } - ret = ext4_ext_handle_uninitialized_extents( + allocated = ext4_ext_handle_uninitialized_extents( handle, inode, map, path, flags, allocated, newblock); - return ret; + goto out3; } } if ((sbi->s_cluster_ratio > 1) && - ext4_find_delalloc_cluster(inode, map->m_lblk, 0)) + ext4_find_delalloc_cluster(inode, map->m_lblk)) map->m_flags |= EXT4_MAP_FROM_CLUSTER; /* @@ -4070,13 +4115,8 @@ got_allocated_blocks: * For non asycn direct IO case, flag the inode state * that we need to perform conversion when IO is done. */ - if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { - if (io) - ext4_set_io_unwritten_flag(inode, io); - else - ext4_set_inode_state(inode, - EXT4_STATE_DIO_UNWRITTEN); - } + if ((flags & EXT4_GET_BLOCKS_PRE_IO)) + set_unwritten = 1; if (ext4_should_dioread_nolock(inode)) map->m_flags |= EXT4_MAP_UNINIT; } @@ -4088,6 +4128,15 @@ got_allocated_blocks: if (!err) err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); + + if (!err && set_unwritten) { + if (io) + ext4_set_io_unwritten_flag(inode, io); + else + ext4_set_inode_state(inode, + EXT4_STATE_DIO_UNWRITTEN); + } + if (err && free_on_err) { int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ? EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0; @@ -4210,8 +4259,8 @@ out2: kfree(path); } - trace_ext4_ext_map_blocks_exit(inode, map->m_lblk, - newblock, map->m_len, err ? err : allocated); +out3: + trace_ext4_ext_map_blocks_exit(inode, map, err ? err : allocated); return err ? err : allocated; } @@ -4229,7 +4278,7 @@ void ext4_ext_truncate(struct inode *inode) * finish any pending end_io work so we won't run the risk of * converting any truncated blocks to initialized later */ - ext4_flush_completed_IO(inode); + ext4_flush_unwritten_io(inode); /* * probably first extent we're gonna free will be last in block @@ -4270,6 +4319,8 @@ void ext4_ext_truncate(struct inode *inode) last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); + err = ext4_es_remove_extent(inode, last_block, + EXT_MAX_BLOCKS - last_block); err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); /* In a multi-transaction truncate, we only make the final @@ -4360,6 +4411,10 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (mode & FALLOC_FL_PUNCH_HOLE) return ext4_punch_hole(file, offset, len); + ret = ext4_convert_inline_data(inode); + if (ret) + return ret; + trace_ext4_fallocate_enter(inode, offset, len, mode); map.m_lblk = offset >> blkbits; /* @@ -4389,6 +4444,9 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) */ if (len <= EXT_UNINIT_MAX_LEN << blkbits) flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; + + /* Prevent race condition between unwritten */ + ext4_flush_unwritten_io(inode); retry: while (ret >= 0 && ret < max_blocks) { map.m_lblk = map.m_lblk + ret; @@ -4420,6 +4478,8 @@ retry: ext4_falloc_update_inode(inode, mode, new_size, (map.m_flags & EXT4_MAP_NEW)); ext4_mark_inode_dirty(handle, inode); + if ((file->f_flags & O_SYNC) && ret >= max_blocks) + ext4_handle_sync(handle); ret2 = ext4_journal_stop(handle); if (ret2) break; @@ -4493,206 +4553,43 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset, } /* - * Callback function called for each extent to gather FIEMAP information. + * If newex is not existing extent (newex->ec_start equals zero) find + * delayed extent at start of newex and update newex accordingly and + * return start of the next delayed extent. + * + * If newex is existing extent (newex->ec_start is not equal zero) + * return start of next delayed extent or EXT_MAX_BLOCKS if no delayed + * extent found. Leave newex unmodified. */ -static int ext4_ext_fiemap_cb(struct inode *inode, ext4_lblk_t next, - struct ext4_ext_cache *newex, struct ext4_extent *ex, - void *data) +static int ext4_find_delayed_extent(struct inode *inode, + struct ext4_ext_cache *newex) { - __u64 logical; - __u64 physical; - __u64 length; - __u32 flags = 0; - int ret = 0; - struct fiemap_extent_info *fieinfo = data; - unsigned char blksize_bits; + struct extent_status es; + ext4_lblk_t next_del; - blksize_bits = inode->i_sb->s_blocksize_bits; - logical = (__u64)newex->ec_block << blksize_bits; + es.start = newex->ec_block; + next_del = ext4_es_find_extent(inode, &es); if (newex->ec_start == 0) { /* * No extent in extent-tree contains block @newex->ec_start, * then the block may stay in 1)a hole or 2)delayed-extent. - * - * Holes or delayed-extents are processed as follows. - * 1. lookup dirty pages with specified range in pagecache. - * If no page is got, then there is no delayed-extent and - * return with EXT_CONTINUE. - * 2. find the 1st mapped buffer, - * 3. check if the mapped buffer is both in the request range - * and a delayed buffer. If not, there is no delayed-extent, - * then return. - * 4. a delayed-extent is found, the extent will be collected. */ - ext4_lblk_t end = 0; - pgoff_t last_offset; - pgoff_t offset; - pgoff_t index; - pgoff_t start_index = 0; - struct page **pages = NULL; - struct buffer_head *bh = NULL; - struct buffer_head *head = NULL; - unsigned int nr_pages = PAGE_SIZE / sizeof(struct page *); - - pages = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (pages == NULL) - return -ENOMEM; - - offset = logical >> PAGE_SHIFT; -repeat: - last_offset = offset; - head = NULL; - ret = find_get_pages_tag(inode->i_mapping, &offset, - PAGECACHE_TAG_DIRTY, nr_pages, pages); - - if (!(flags & FIEMAP_EXTENT_DELALLOC)) { - /* First time, try to find a mapped buffer. */ - if (ret == 0) { -out: - for (index = 0; index < ret; index++) - page_cache_release(pages[index]); - /* just a hole. */ - kfree(pages); - return EXT_CONTINUE; - } - index = 0; - -next_page: - /* Try to find the 1st mapped buffer. */ - end = ((__u64)pages[index]->index << PAGE_SHIFT) >> - blksize_bits; - if (!page_has_buffers(pages[index])) - goto out; - head = page_buffers(pages[index]); - if (!head) - goto out; - - index++; - bh = head; - do { - if (end >= newex->ec_block + - newex->ec_len) - /* The buffer is out of - * the request range. - */ - goto out; - - if (buffer_mapped(bh) && - end >= newex->ec_block) { - start_index = index - 1; - /* get the 1st mapped buffer. */ - goto found_mapped_buffer; - } - - bh = bh->b_this_page; - end++; - } while (bh != head); - - /* No mapped buffer in the range found in this page, - * We need to look up next page. - */ - if (index >= ret) { - /* There is no page left, but we need to limit - * newex->ec_len. - */ - newex->ec_len = end - newex->ec_block; - goto out; - } - goto next_page; - } else { - /*Find contiguous delayed buffers. */ - if (ret > 0 && pages[0]->index == last_offset) - head = page_buffers(pages[0]); - bh = head; - index = 1; - start_index = 0; - } - -found_mapped_buffer: - if (bh != NULL && buffer_delay(bh)) { - /* 1st or contiguous delayed buffer found. */ - if (!(flags & FIEMAP_EXTENT_DELALLOC)) { - /* - * 1st delayed buffer found, record - * the start of extent. - */ - flags |= FIEMAP_EXTENT_DELALLOC; - newex->ec_block = end; - logical = (__u64)end << blksize_bits; - } - /* Find contiguous delayed buffers. */ - do { - if (!buffer_delay(bh)) - goto found_delayed_extent; - bh = bh->b_this_page; - end++; - } while (bh != head); - - for (; index < ret; index++) { - if (!page_has_buffers(pages[index])) { - bh = NULL; - break; - } - head = page_buffers(pages[index]); - if (!head) { - bh = NULL; - break; - } - - if (pages[index]->index != - pages[start_index]->index + index - - start_index) { - /* Blocks are not contiguous. */ - bh = NULL; - break; - } - bh = head; - do { - if (!buffer_delay(bh)) - /* Delayed-extent ends. */ - goto found_delayed_extent; - bh = bh->b_this_page; - end++; - } while (bh != head); - } - } else if (!(flags & FIEMAP_EXTENT_DELALLOC)) - /* a hole found. */ - goto out; + if (es.len == 0) + /* A hole found. */ + return 0; -found_delayed_extent: - newex->ec_len = min(end - newex->ec_block, - (ext4_lblk_t)EXT_INIT_MAX_LEN); - if (ret == nr_pages && bh != NULL && - newex->ec_len < EXT_INIT_MAX_LEN && - buffer_delay(bh)) { - /* Have not collected an extent and continue. */ - for (index = 0; index < ret; index++) - page_cache_release(pages[index]); - goto repeat; + if (es.start > newex->ec_block) { + /* A hole found. */ + newex->ec_len = min(es.start - newex->ec_block, + newex->ec_len); + return 0; } - for (index = 0; index < ret; index++) - page_cache_release(pages[index]); - kfree(pages); + newex->ec_len = es.start + es.len - newex->ec_block; } - physical = (__u64)newex->ec_start << blksize_bits; - length = (__u64)newex->ec_len << blksize_bits; - - if (ex && ext4_ext_is_uninitialized(ex)) - flags |= FIEMAP_EXTENT_UNWRITTEN; - - if (next == EXT_MAX_BLOCKS) - flags |= FIEMAP_EXTENT_LAST; - - ret = fiemap_fill_next_extent(fieinfo, logical, physical, - length, flags); - if (ret < 0) - return ret; - if (ret == 1) - return EXT_BREAK; - return EXT_CONTINUE; + return next_del; } /* fiemap flags we can handle specified here */ #define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR) @@ -4755,9 +4652,32 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) loff_t first_page_offset, last_page_offset; int credits, err = 0; + /* + * Write out all dirty pages to avoid race conditions + * Then release them. + */ + if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { + err = filemap_write_and_wait_range(mapping, + offset, offset + length - 1); + + if (err) + return err; + } + + mutex_lock(&inode->i_mutex); + /* It's not possible punch hole on append only file */ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { + err = -EPERM; + goto out_mutex; + } + if (IS_SWAPFILE(inode)) { + err = -ETXTBSY; + goto out_mutex; + } + /* No need to punch hole beyond i_size */ if (offset >= inode->i_size) - return 0; + goto out_mutex; /* * If the hole extends beyond i_size, set the hole @@ -4775,35 +4695,26 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) first_page_offset = first_page << PAGE_CACHE_SHIFT; last_page_offset = last_page << PAGE_CACHE_SHIFT; - /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - err = filemap_write_and_wait_range(mapping, - offset, offset + length - 1); - - if (err) - return err; - } - /* Now release the pages */ if (last_page_offset > first_page_offset) { truncate_pagecache_range(inode, first_page_offset, last_page_offset - 1); } - /* finish any pending end_io work */ - ext4_flush_completed_IO(inode); + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + err = ext4_flush_unwritten_io(inode); + if (err) + goto out_dio; + inode_dio_wait(inode); credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_dio; + } - err = ext4_orphan_add(handle, inode); - if (err) - goto out; /* * Now we need to zero out the non-page-aligned data in the @@ -4878,6 +4789,8 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) ext4_ext_invalidate_cache(inode); ext4_discard_preallocations(inode); + err = ext4_es_remove_extent(inode, first_block, + stop_block - first_block); err = ext4_ext_remove_space(inode, first_block, stop_block - 1); ext4_ext_invalidate_cache(inode); @@ -4889,18 +4802,31 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) up_write(&EXT4_I(inode)->i_data_sem); out: - ext4_orphan_del(handle, inode); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); +out_dio: + ext4_inode_resume_unlocked_dio(inode); +out_mutex: + mutex_unlock(&inode->i_mutex); return err; } + int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { ext4_lblk_t start_blk; int error = 0; + if (ext4_has_inline_data(inode)) { + int has_inline = 1; + + error = ext4_inline_data_fiemap(inode, fieinfo, &has_inline); + + if (has_inline) + return error; + } + /* fallback to generic here if not in extents fmt */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return generic_block_fiemap(inode, fieinfo, start, len, @@ -4922,11 +4848,11 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; /* - * Walk the extent tree gathering extent information. - * ext4_ext_fiemap_cb will push extents back to user. + * Walk the extent tree gathering extent information + * and pushing extents back to the user. */ - error = ext4_ext_walk_space(inode, start_blk, len_blks, - ext4_ext_fiemap_cb, fieinfo); + error = ext4_fill_fiemap_extents(inode, start_blk, + len_blks, fieinfo); } return error; diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c new file mode 100644 index 00000000000..564d981a2fc --- /dev/null +++ b/fs/ext4/extents_status.c @@ -0,0 +1,500 @@ +/* + * fs/ext4/extents_status.c + * + * Written by Yongqiang Yang <xiaoqiangnk@gmail.com> + * Modified by + * Allison Henderson <achender@linux.vnet.ibm.com> + * Hugh Dickins <hughd@google.com> + * Zheng Liu <wenqing.lz@taobao.com> + * + * Ext4 extents status tree core functions. + */ +#include <linux/rbtree.h> +#include "ext4.h" +#include "extents_status.h" +#include "ext4_extents.h" + +#include <trace/events/ext4.h> + +/* + * According to previous discussion in Ext4 Developer Workshop, we + * will introduce a new structure called io tree to track all extent + * status in order to solve some problems that we have met + * (e.g. Reservation space warning), and provide extent-level locking. + * Delay extent tree is the first step to achieve this goal. It is + * original built by Yongqiang Yang. At that time it is called delay + * extent tree, whose goal is only track delay extent in memory to + * simplify the implementation of fiemap and bigalloc, and introduce + * lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called + * delay extent tree at the following comment. But for better + * understand what it does, it has been rename to extent status tree. + * + * Currently the first step has been done. All delay extents are + * tracked in the tree. It maintains the delay extent when a delay + * allocation is issued, and the delay extent is written out or + * invalidated. Therefore the implementation of fiemap and bigalloc + * are simplified, and SEEK_DATA/SEEK_HOLE are introduced. + * + * The following comment describes the implemenmtation of extent + * status tree and future works. + */ + +/* + * extents status tree implementation for ext4. + * + * + * ========================================================================== + * Extents status encompass delayed extents and extent locks + * + * 1. Why delayed extent implementation ? + * + * Without delayed extent, ext4 identifies a delayed extent by looking + * up page cache, this has several deficiencies - complicated, buggy, + * and inefficient code. + * + * FIEMAP, SEEK_HOLE/DATA, bigalloc, punch hole and writeout all need + * to know if a block or a range of blocks are belonged to a delayed + * extent. + * + * Let us have a look at how they do without delayed extents implementation. + * -- FIEMAP + * FIEMAP looks up page cache to identify delayed allocations from holes. + * + * -- SEEK_HOLE/DATA + * SEEK_HOLE/DATA has the same problem as FIEMAP. + * + * -- bigalloc + * bigalloc looks up page cache to figure out if a block is + * already under delayed allocation or not to determine whether + * quota reserving is needed for the cluster. + * + * -- punch hole + * punch hole looks up page cache to identify a delayed extent. + * + * -- writeout + * Writeout looks up whole page cache to see if a buffer is + * mapped, If there are not very many delayed buffers, then it is + * time comsuming. + * + * With delayed extents implementation, FIEMAP, SEEK_HOLE/DATA, + * bigalloc and writeout can figure out if a block or a range of + * blocks is under delayed allocation(belonged to a delayed extent) or + * not by searching the delayed extent tree. + * + * + * ========================================================================== + * 2. ext4 delayed extents impelmentation + * + * -- delayed extent + * A delayed extent is a range of blocks which are contiguous + * logically and under delayed allocation. Unlike extent in + * ext4, delayed extent in ext4 is a in-memory struct, there is + * no corresponding on-disk data. There is no limit on length of + * delayed extent, so a delayed extent can contain as many blocks + * as they are contiguous logically. + * + * -- delayed extent tree + * Every inode has a delayed extent tree and all under delayed + * allocation blocks are added to the tree as delayed extents. + * Delayed extents in the tree are ordered by logical block no. + * + * -- operations on a delayed extent tree + * There are three operations on a delayed extent tree: find next + * delayed extent, adding a space(a range of blocks) and removing + * a space. + * + * -- race on a delayed extent tree + * Delayed extent tree is protected inode->i_es_lock. + * + * + * ========================================================================== + * 3. performance analysis + * -- overhead + * 1. There is a cache extent for write access, so if writes are + * not very random, adding space operaions are in O(1) time. + * + * -- gain + * 2. Code is much simpler, more readable, more maintainable and + * more efficient. + * + * + * ========================================================================== + * 4. TODO list + * -- Track all extent status + * + * -- Improve get block process + * + * -- Extent-level locking + */ + +static struct kmem_cache *ext4_es_cachep; + +int __init ext4_init_es(void) +{ + ext4_es_cachep = KMEM_CACHE(extent_status, SLAB_RECLAIM_ACCOUNT); + if (ext4_es_cachep == NULL) + return -ENOMEM; + return 0; +} + +void ext4_exit_es(void) +{ + if (ext4_es_cachep) + kmem_cache_destroy(ext4_es_cachep); +} + +void ext4_es_init_tree(struct ext4_es_tree *tree) +{ + tree->root = RB_ROOT; + tree->cache_es = NULL; +} + +#ifdef ES_DEBUG__ +static void ext4_es_print_tree(struct inode *inode) +{ + struct ext4_es_tree *tree; + struct rb_node *node; + + printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino); + tree = &EXT4_I(inode)->i_es_tree; + node = rb_first(&tree->root); + while (node) { + struct extent_status *es; + es = rb_entry(node, struct extent_status, rb_node); + printk(KERN_DEBUG " [%u/%u)", es->start, es->len); + node = rb_next(node); + } + printk(KERN_DEBUG "\n"); +} +#else +#define ext4_es_print_tree(inode) +#endif + +static inline ext4_lblk_t extent_status_end(struct extent_status *es) +{ + BUG_ON(es->start + es->len < es->start); + return es->start + es->len - 1; +} + +/* + * search through the tree for an delayed extent with a given offset. If + * it can't be found, try to find next extent. + */ +static struct extent_status *__es_tree_search(struct rb_root *root, + ext4_lblk_t offset) +{ + struct rb_node *node = root->rb_node; + struct extent_status *es = NULL; + + while (node) { + es = rb_entry(node, struct extent_status, rb_node); + if (offset < es->start) + node = node->rb_left; + else if (offset > extent_status_end(es)) + node = node->rb_right; + else + return es; + } + + if (es && offset < es->start) + return es; + + if (es && offset > extent_status_end(es)) { + node = rb_next(&es->rb_node); + return node ? rb_entry(node, struct extent_status, rb_node) : + NULL; + } + + return NULL; +} + +/* + * ext4_es_find_extent: find the 1st delayed extent covering @es->start + * if it exists, otherwise, the next extent after @es->start. + * + * @inode: the inode which owns delayed extents + * @es: delayed extent that we found + * + * Returns the first block of the next extent after es, otherwise + * EXT_MAX_BLOCKS if no delay extent is found. + * Delayed extent is returned via @es. + */ +ext4_lblk_t ext4_es_find_extent(struct inode *inode, struct extent_status *es) +{ + struct ext4_es_tree *tree = NULL; + struct extent_status *es1 = NULL; + struct rb_node *node; + ext4_lblk_t ret = EXT_MAX_BLOCKS; + + trace_ext4_es_find_extent_enter(inode, es->start); + + read_lock(&EXT4_I(inode)->i_es_lock); + tree = &EXT4_I(inode)->i_es_tree; + + /* find delay extent in cache firstly */ + if (tree->cache_es) { + es1 = tree->cache_es; + if (in_range(es->start, es1->start, es1->len)) { + es_debug("%u cached by [%u/%u)\n", + es->start, es1->start, es1->len); + goto out; + } + } + + es->len = 0; + es1 = __es_tree_search(&tree->root, es->start); + +out: + if (es1) { + tree->cache_es = es1; + es->start = es1->start; + es->len = es1->len; + node = rb_next(&es1->rb_node); + if (node) { + es1 = rb_entry(node, struct extent_status, rb_node); + ret = es1->start; + } + } + + read_unlock(&EXT4_I(inode)->i_es_lock); + + trace_ext4_es_find_extent_exit(inode, es, ret); + return ret; +} + +static struct extent_status * +ext4_es_alloc_extent(ext4_lblk_t start, ext4_lblk_t len) +{ + struct extent_status *es; + es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC); + if (es == NULL) + return NULL; + es->start = start; + es->len = len; + return es; +} + +static void ext4_es_free_extent(struct extent_status *es) +{ + kmem_cache_free(ext4_es_cachep, es); +} + +static struct extent_status * +ext4_es_try_to_merge_left(struct ext4_es_tree *tree, struct extent_status *es) +{ + struct extent_status *es1; + struct rb_node *node; + + node = rb_prev(&es->rb_node); + if (!node) + return es; + + es1 = rb_entry(node, struct extent_status, rb_node); + if (es->start == extent_status_end(es1) + 1) { + es1->len += es->len; + rb_erase(&es->rb_node, &tree->root); + ext4_es_free_extent(es); + es = es1; + } + + return es; +} + +static struct extent_status * +ext4_es_try_to_merge_right(struct ext4_es_tree *tree, struct extent_status *es) +{ + struct extent_status *es1; + struct rb_node *node; + + node = rb_next(&es->rb_node); + if (!node) + return es; + + es1 = rb_entry(node, struct extent_status, rb_node); + if (es1->start == extent_status_end(es) + 1) { + es->len += es1->len; + rb_erase(node, &tree->root); + ext4_es_free_extent(es1); + } + + return es; +} + +static int __es_insert_extent(struct ext4_es_tree *tree, ext4_lblk_t offset, + ext4_lblk_t len) +{ + struct rb_node **p = &tree->root.rb_node; + struct rb_node *parent = NULL; + struct extent_status *es; + ext4_lblk_t end = offset + len - 1; + + BUG_ON(end < offset); + es = tree->cache_es; + if (es && offset == (extent_status_end(es) + 1)) { + es_debug("cached by [%u/%u)\n", es->start, es->len); + es->len += len; + es = ext4_es_try_to_merge_right(tree, es); + goto out; + } else if (es && es->start == end + 1) { + es_debug("cached by [%u/%u)\n", es->start, es->len); + es->start = offset; + es->len += len; + es = ext4_es_try_to_merge_left(tree, es); + goto out; + } else if (es && es->start <= offset && + end <= extent_status_end(es)) { + es_debug("cached by [%u/%u)\n", es->start, es->len); + goto out; + } + + while (*p) { + parent = *p; + es = rb_entry(parent, struct extent_status, rb_node); + + if (offset < es->start) { + if (es->start == end + 1) { + es->start = offset; + es->len += len; + es = ext4_es_try_to_merge_left(tree, es); + goto out; + } + p = &(*p)->rb_left; + } else if (offset > extent_status_end(es)) { + if (offset == extent_status_end(es) + 1) { + es->len += len; + es = ext4_es_try_to_merge_right(tree, es); + goto out; + } + p = &(*p)->rb_right; + } else { + if (extent_status_end(es) <= end) + es->len = offset - es->start + len; + goto out; + } + } + + es = ext4_es_alloc_extent(offset, len); + if (!es) + return -ENOMEM; + rb_link_node(&es->rb_node, parent, p); + rb_insert_color(&es->rb_node, &tree->root); + +out: + tree->cache_es = es; + return 0; +} + +/* + * ext4_es_insert_extent() adds a space to a delayed extent tree. + * Caller holds inode->i_es_lock. + * + * ext4_es_insert_extent is called by ext4_da_write_begin and + * ext4_es_remove_extent. + * + * Return 0 on success, error code on failure. + */ +int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t offset, + ext4_lblk_t len) +{ + struct ext4_es_tree *tree; + int err = 0; + + trace_ext4_es_insert_extent(inode, offset, len); + es_debug("add [%u/%u) to extent status tree of inode %lu\n", + offset, len, inode->i_ino); + + write_lock(&EXT4_I(inode)->i_es_lock); + tree = &EXT4_I(inode)->i_es_tree; + err = __es_insert_extent(tree, offset, len); + write_unlock(&EXT4_I(inode)->i_es_lock); + + ext4_es_print_tree(inode); + + return err; +} + +/* + * ext4_es_remove_extent() removes a space from a delayed extent tree. + * Caller holds inode->i_es_lock. + * + * Return 0 on success, error code on failure. + */ +int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t offset, + ext4_lblk_t len) +{ + struct rb_node *node; + struct ext4_es_tree *tree; + struct extent_status *es; + struct extent_status orig_es; + ext4_lblk_t len1, len2, end; + int err = 0; + + trace_ext4_es_remove_extent(inode, offset, len); + es_debug("remove [%u/%u) from extent status tree of inode %lu\n", + offset, len, inode->i_ino); + + end = offset + len - 1; + BUG_ON(end < offset); + write_lock(&EXT4_I(inode)->i_es_lock); + tree = &EXT4_I(inode)->i_es_tree; + es = __es_tree_search(&tree->root, offset); + if (!es) + goto out; + if (es->start > end) + goto out; + + /* Simply invalidate cache_es. */ + tree->cache_es = NULL; + + orig_es.start = es->start; + orig_es.len = es->len; + len1 = offset > es->start ? offset - es->start : 0; + len2 = extent_status_end(es) > end ? + extent_status_end(es) - end : 0; + if (len1 > 0) + es->len = len1; + if (len2 > 0) { + if (len1 > 0) { + err = __es_insert_extent(tree, end + 1, len2); + if (err) { + es->start = orig_es.start; + es->len = orig_es.len; + goto out; + } + } else { + es->start = end + 1; + es->len = len2; + } + goto out; + } + + if (len1 > 0) { + node = rb_next(&es->rb_node); + if (node) + es = rb_entry(node, struct extent_status, rb_node); + else + es = NULL; + } + + while (es && extent_status_end(es) <= end) { + node = rb_next(&es->rb_node); + rb_erase(&es->rb_node, &tree->root); + ext4_es_free_extent(es); + if (!node) { + es = NULL; + break; + } + es = rb_entry(node, struct extent_status, rb_node); + } + + if (es && es->start < end + 1) { + len1 = extent_status_end(es) - end; + es->start = end + 1; + es->len = len1; + } + +out: + write_unlock(&EXT4_I(inode)->i_es_lock); + ext4_es_print_tree(inode); + return err; +} diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h new file mode 100644 index 00000000000..077f82db092 --- /dev/null +++ b/fs/ext4/extents_status.h @@ -0,0 +1,45 @@ +/* + * fs/ext4/extents_status.h + * + * Written by Yongqiang Yang <xiaoqiangnk@gmail.com> + * Modified by + * Allison Henderson <achender@linux.vnet.ibm.com> + * Zheng Liu <wenqing.lz@taobao.com> + * + */ + +#ifndef _EXT4_EXTENTS_STATUS_H +#define _EXT4_EXTENTS_STATUS_H + +/* + * Turn on ES_DEBUG__ to get lots of info about extent status operations. + */ +#ifdef ES_DEBUG__ +#define es_debug(fmt, ...) printk(fmt, ##__VA_ARGS__) +#else +#define es_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__) +#endif + +struct extent_status { + struct rb_node rb_node; + ext4_lblk_t start; /* first block extent covers */ + ext4_lblk_t len; /* length of extent in block */ +}; + +struct ext4_es_tree { + struct rb_root root; + struct extent_status *cache_es; /* recently accessed extent */ +}; + +extern int __init ext4_init_es(void); +extern void ext4_exit_es(void); +extern void ext4_es_init_tree(struct ext4_es_tree *tree); + +extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t len); +extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t len); +extern ext4_lblk_t ext4_es_find_extent(struct inode *inode, + struct extent_status *es); + +#endif /* _EXT4_EXTENTS_STATUS_H */ diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8c7642a0005..405565a6227 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -24,6 +24,7 @@ #include <linux/mount.h> #include <linux/path.h> #include <linux/quotaops.h> +#include <linux/pagevec.h> #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" @@ -55,11 +56,11 @@ static int ext4_release_file(struct inode *inode, struct file *filp) return 0; } -static void ext4_aiodio_wait(struct inode *inode) +void ext4_unwritten_wait(struct inode *inode) { wait_queue_head_t *wq = ext4_ioend_wq(inode); - wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0)); + wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0)); } /* @@ -90,11 +91,83 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov, } static ssize_t +ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + struct blk_plug plug; + int unaligned_aio = 0; + ssize_t ret; + int overwrite = 0; + size_t length = iov_length(iov, nr_segs); + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && + !is_sync_kiocb(iocb)) + unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos); + + /* Unaligned direct AIO must be serialized; see comment above */ + if (unaligned_aio) { + mutex_lock(ext4_aio_mutex(inode)); + ext4_unwritten_wait(inode); + } + + BUG_ON(iocb->ki_pos != pos); + + mutex_lock(&inode->i_mutex); + blk_start_plug(&plug); + + iocb->private = &overwrite; + + /* check whether we do a DIO overwrite or not */ + if (ext4_should_dioread_nolock(inode) && !unaligned_aio && + !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) { + struct ext4_map_blocks map; + unsigned int blkbits = inode->i_blkbits; + int err, len; + + map.m_lblk = pos >> blkbits; + map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits) + - map.m_lblk; + len = map.m_len; + + err = ext4_map_blocks(NULL, inode, &map, 0); + /* + * 'err==len' means that all of blocks has been preallocated no + * matter they are initialized or not. For excluding + * uninitialized extents, we need to check m_flags. There are + * two conditions that indicate for initialized extents. + * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned; + * 2) If we do a real lookup, non-flags are returned. + * So we should check these two conditions. + */ + if (err == len && (map.m_flags & EXT4_MAP_MAPPED)) + overwrite = 1; + } + + ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + mutex_unlock(&inode->i_mutex); + + if (ret > 0 || ret == -EIOCBQUEUED) { + ssize_t err; + + err = generic_write_sync(file, pos, ret); + if (err < 0 && ret > 0) + ret = err; + } + blk_finish_plug(&plug); + + if (unaligned_aio) + mutex_unlock(ext4_aio_mutex(inode)); + + return ret; +} + +static ssize_t ext4_file_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; - int unaligned_aio = 0; ssize_t ret; /* @@ -114,29 +187,12 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, nr_segs = iov_shorten((struct iovec *)iov, nr_segs, sbi->s_bitmap_maxbytes - pos); } - } else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) && - !is_sync_kiocb(iocb))) { - unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos); - } - - /* Unaligned direct AIO must be serialized; see comment above */ - if (unaligned_aio) { - static unsigned long unaligned_warn_time; - - /* Warn about this once per day */ - if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ)) - ext4_msg(inode->i_sb, KERN_WARNING, - "Unaligned AIO/DIO on inode %ld by %s; " - "performance will be poor.", - inode->i_ino, current->comm); - mutex_lock(ext4_aio_mutex(inode)); - ext4_aiodio_wait(inode); } - ret = generic_file_aio_write(iocb, iov, nr_segs, pos); - - if (unaligned_aio) - mutex_unlock(ext4_aio_mutex(inode)); + if (unlikely(iocb->ki_filp->f_flags & O_DIRECT)) + ret = ext4_file_dio_write(iocb, iov, nr_segs, pos); + else + ret = generic_file_aio_write(iocb, iov, nr_segs, pos); return ret; } @@ -144,6 +200,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ext4_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) @@ -154,7 +211,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &ext4_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } @@ -181,9 +237,21 @@ static int ext4_file_open(struct inode * inode, struct file * filp) path.dentry = mnt->mnt_root; cp = d_path(&path, buf, sizeof(buf)); if (!IS_ERR(cp)) { + handle_t *handle; + int err; + + handle = ext4_journal_start_sb(sb, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + err = ext4_journal_get_write_access(handle, sbi->s_sbh); + if (err) { + ext4_journal_stop(handle); + return err; + } strlcpy(sbi->s_es->s_last_mounted, cp, sizeof(sbi->s_es->s_last_mounted)); - ext4_mark_super_dirty(sb); + ext4_handle_dirty_super(handle, sb); + ext4_journal_stop(handle); } } /* @@ -211,11 +279,329 @@ static int ext4_file_open(struct inode * inode, struct file * filp) } /* - * ext4_llseek() copied from generic_file_llseek() to handle both - * block-mapped and extent-mapped maxbytes values. This should - * otherwise be identical with generic_file_llseek(). + * Here we use ext4_map_blocks() to get a block mapping for a extent-based + * file rather than ext4_ext_walk_space() because we can introduce + * SEEK_DATA/SEEK_HOLE for block-mapped and extent-mapped file at the same + * function. When extent status tree has been fully implemented, it will + * track all extent status for a file and we can directly use it to + * retrieve the offset for SEEK_DATA/SEEK_HOLE. */ -loff_t ext4_llseek(struct file *file, loff_t offset, int origin) + +/* + * When we retrieve the offset for SEEK_DATA/SEEK_HOLE, we would need to + * lookup page cache to check whether or not there has some data between + * [startoff, endoff] because, if this range contains an unwritten extent, + * we determine this extent as a data or a hole according to whether the + * page cache has data or not. + */ +static int ext4_find_unwritten_pgoff(struct inode *inode, + int whence, + struct ext4_map_blocks *map, + loff_t *offset) +{ + struct pagevec pvec; + unsigned int blkbits; + pgoff_t index; + pgoff_t end; + loff_t endoff; + loff_t startoff; + loff_t lastoff; + int found = 0; + + blkbits = inode->i_sb->s_blocksize_bits; + startoff = *offset; + lastoff = startoff; + endoff = (map->m_lblk + map->m_len) << blkbits; + + index = startoff >> PAGE_CACHE_SHIFT; + end = endoff >> PAGE_CACHE_SHIFT; + + pagevec_init(&pvec, 0); + do { + int i, num; + unsigned long nr_pages; + + num = min_t(pgoff_t, end - index, PAGEVEC_SIZE); + nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, + (pgoff_t)num); + if (nr_pages == 0) { + if (whence == SEEK_DATA) + break; + + BUG_ON(whence != SEEK_HOLE); + /* + * If this is the first time to go into the loop and + * offset is not beyond the end offset, it will be a + * hole at this offset + */ + if (lastoff == startoff || lastoff < endoff) + found = 1; + break; + } + + /* + * If this is the first time to go into the loop and + * offset is smaller than the first page offset, it will be a + * hole at this offset. + */ + if (lastoff == startoff && whence == SEEK_HOLE && + lastoff < page_offset(pvec.pages[0])) { + found = 1; + break; + } + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + struct buffer_head *bh, *head; + + /* + * If the current offset is not beyond the end of given + * range, it will be a hole. + */ + if (lastoff < endoff && whence == SEEK_HOLE && + page->index > end) { + found = 1; + *offset = lastoff; + goto out; + } + + lock_page(page); + + if (unlikely(page->mapping != inode->i_mapping)) { + unlock_page(page); + continue; + } + + if (!page_has_buffers(page)) { + unlock_page(page); + continue; + } + + if (page_has_buffers(page)) { + lastoff = page_offset(page); + bh = head = page_buffers(page); + do { + if (buffer_uptodate(bh) || + buffer_unwritten(bh)) { + if (whence == SEEK_DATA) + found = 1; + } else { + if (whence == SEEK_HOLE) + found = 1; + } + if (found) { + *offset = max_t(loff_t, + startoff, lastoff); + unlock_page(page); + goto out; + } + lastoff += bh->b_size; + bh = bh->b_this_page; + } while (bh != head); + } + + lastoff = page_offset(page) + PAGE_SIZE; + unlock_page(page); + } + + /* + * The no. of pages is less than our desired, that would be a + * hole in there. + */ + if (nr_pages < num && whence == SEEK_HOLE) { + found = 1; + *offset = lastoff; + break; + } + + index = pvec.pages[i - 1]->index + 1; + pagevec_release(&pvec); + } while (index <= end); + +out: + pagevec_release(&pvec); + return found; +} + +/* + * ext4_seek_data() retrieves the offset for SEEK_DATA. + */ +static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize) +{ + struct inode *inode = file->f_mapping->host; + struct ext4_map_blocks map; + struct extent_status es; + ext4_lblk_t start, last, end; + loff_t dataoff, isize; + int blkbits; + int ret = 0; + + mutex_lock(&inode->i_mutex); + + isize = i_size_read(inode); + if (offset >= isize) { + mutex_unlock(&inode->i_mutex); + return -ENXIO; + } + + blkbits = inode->i_sb->s_blocksize_bits; + start = offset >> blkbits; + last = start; + end = isize >> blkbits; + dataoff = offset; + + do { + map.m_lblk = last; + map.m_len = end - last + 1; + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) { + if (last != start) + dataoff = last << blkbits; + break; + } + + /* + * If there is a delay extent at this offset, + * it will be as a data. + */ + es.start = last; + (void)ext4_es_find_extent(inode, &es); + if (last >= es.start && + last < es.start + es.len) { + if (last != start) + dataoff = last << blkbits; + break; + } + + /* + * If there is a unwritten extent at this offset, + * it will be as a data or a hole according to page + * cache that has data or not. + */ + if (map.m_flags & EXT4_MAP_UNWRITTEN) { + int unwritten; + unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA, + &map, &dataoff); + if (unwritten) + break; + } + + last++; + dataoff = last << blkbits; + } while (last <= end); + + mutex_unlock(&inode->i_mutex); + + if (dataoff > isize) + return -ENXIO; + + if (dataoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) + return -EINVAL; + if (dataoff > maxsize) + return -EINVAL; + + if (dataoff != file->f_pos) { + file->f_pos = dataoff; + file->f_version = 0; + } + + return dataoff; +} + +/* + * ext4_seek_hole() retrieves the offset for SEEK_HOLE. + */ +static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize) +{ + struct inode *inode = file->f_mapping->host; + struct ext4_map_blocks map; + struct extent_status es; + ext4_lblk_t start, last, end; + loff_t holeoff, isize; + int blkbits; + int ret = 0; + + mutex_lock(&inode->i_mutex); + + isize = i_size_read(inode); + if (offset >= isize) { + mutex_unlock(&inode->i_mutex); + return -ENXIO; + } + + blkbits = inode->i_sb->s_blocksize_bits; + start = offset >> blkbits; + last = start; + end = isize >> blkbits; + holeoff = offset; + + do { + map.m_lblk = last; + map.m_len = end - last + 1; + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) { + last += ret; + holeoff = last << blkbits; + continue; + } + + /* + * If there is a delay extent at this offset, + * we will skip this extent. + */ + es.start = last; + (void)ext4_es_find_extent(inode, &es); + if (last >= es.start && + last < es.start + es.len) { + last = es.start + es.len; + holeoff = last << blkbits; + continue; + } + + /* + * If there is a unwritten extent at this offset, + * it will be as a data or a hole according to page + * cache that has data or not. + */ + if (map.m_flags & EXT4_MAP_UNWRITTEN) { + int unwritten; + unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE, + &map, &holeoff); + if (!unwritten) { + last += ret; + holeoff = last << blkbits; + continue; + } + } + + /* find a hole */ + break; + } while (last <= end); + + mutex_unlock(&inode->i_mutex); + + if (holeoff > isize) + holeoff = isize; + + if (holeoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) + return -EINVAL; + if (holeoff > maxsize) + return -EINVAL; + + if (holeoff != file->f_pos) { + file->f_pos = holeoff; + file->f_version = 0; + } + + return holeoff; +} + +/* + * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values + * by calling generic_file_llseek_size() with the appropriate maxbytes + * value for each. + */ +loff_t ext4_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; loff_t maxbytes; @@ -225,7 +611,19 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin) else maxbytes = inode->i_sb->s_maxbytes; - return generic_file_llseek_size(file, offset, origin, maxbytes); + switch (whence) { + case SEEK_SET: + case SEEK_CUR: + case SEEK_END: + return generic_file_llseek_size(file, offset, whence, + maxbytes, i_size_read(inode)); + case SEEK_DATA: + return ext4_seek_data(file, offset, maxbytes); + case SEEK_HOLE: + return ext4_seek_hole(file, offset, maxbytes); + } + + return -EINVAL; } const struct file_operations ext4_file_operations = { @@ -250,12 +648,10 @@ const struct file_operations ext4_file_operations = { const struct inode_operations ext4_file_inode_operations = { .setattr = ext4_setattr, .getattr = ext4_getattr, -#ifdef CONFIG_EXT4_FS_XATTR .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = ext4_listxattr, .removexattr = generic_removexattr, -#endif .get_acl = ext4_get_acl, .fiemap = ext4_fiemap, }; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index bb6c7d81131..3278e64e57b 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -34,87 +34,6 @@ #include <trace/events/ext4.h> -static void dump_completed_IO(struct inode * inode) -{ -#ifdef EXT4FS_DEBUG - struct list_head *cur, *before, *after; - ext4_io_end_t *io, *io0, *io1; - unsigned long flags; - - if (list_empty(&EXT4_I(inode)->i_completed_io_list)){ - ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino); - return; - } - - ext4_debug("Dump inode %lu completed_io list \n", inode->i_ino); - spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); - list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list){ - cur = &io->list; - before = cur->prev; - io0 = container_of(before, ext4_io_end_t, list); - after = cur->next; - io1 = container_of(after, ext4_io_end_t, list); - - ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n", - io, inode->i_ino, io0, io1); - } - spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); -#endif -} - -/* - * This function is called from ext4_sync_file(). - * - * When IO is completed, the work to convert unwritten extents to - * written is queued on workqueue but may not get immediately - * scheduled. When fsync is called, we need to ensure the - * conversion is complete before fsync returns. - * The inode keeps track of a list of pending/completed IO that - * might needs to do the conversion. This function walks through - * the list and convert the related unwritten extents for completed IO - * to written. - * The function return the number of pending IOs on success. - */ -int ext4_flush_completed_IO(struct inode *inode) -{ - ext4_io_end_t *io; - struct ext4_inode_info *ei = EXT4_I(inode); - unsigned long flags; - int ret = 0; - int ret2 = 0; - - dump_completed_IO(inode); - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - while (!list_empty(&ei->i_completed_io_list)){ - io = list_entry(ei->i_completed_io_list.next, - ext4_io_end_t, list); - list_del_init(&io->list); - io->flag |= EXT4_IO_END_IN_FSYNC; - /* - * Calling ext4_end_io_nolock() to convert completed - * IO to written. - * - * When ext4_sync_file() is called, run_queue() may already - * about to flush the work corresponding to this io structure. - * It will be upset if it founds the io structure related - * to the work-to-be schedule is freed. - * - * Thus we need to keep the io structure still valid here after - * conversion finished. The io structure has a flag to - * avoid double converting from both fsync and background work - * queue work. - */ - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - ret = ext4_end_io_nolock(io); - if (ret < 0) - ret2 = ret; - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - io->flag &= ~EXT4_IO_END_IN_FSYNC; - } - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - return (ret2 < 0) ? ret2 : 0; -} - /* * If we're not journaling and this is a just-created file, we have to * sync our parent directory (if it was freshly created) since @@ -125,7 +44,6 @@ int ext4_flush_completed_IO(struct inode *inode) */ static int ext4_sync_parent(struct inode *inode) { - struct writeback_control wbc; struct dentry *dentry = NULL; struct inode *next; int ret = 0; @@ -135,14 +53,7 @@ static int ext4_sync_parent(struct inode *inode) inode = igrab(inode); while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); - dentry = NULL; - spin_lock(&inode->i_lock); - if (!list_empty(&inode->i_dentry)) { - dentry = list_first_entry(&inode->i_dentry, - struct dentry, d_alias); - dget(dentry); - } - spin_unlock(&inode->i_lock); + dentry = d_find_any_alias(inode); if (!dentry) break; next = igrab(dentry->d_parent->d_inode); @@ -154,10 +65,7 @@ static int ext4_sync_parent(struct inode *inode) ret = sync_mapping_buffers(inode->i_mapping); if (ret) break; - memset(&wbc, 0, sizeof(wbc)); - wbc.sync_mode = WB_SYNC_ALL; - wbc.nr_to_write = 0; /* only write out the inode */ - ret = sync_inode(inode, &wbc); + ret = sync_inode_metadata(inode, 1); if (ret) break; } @@ -201,8 +109,6 @@ static int __sync_inode(struct inode *inode, int datasync) * * What we do is just kick off a commit and wait on it. This will snapshot the * inode to disk. - * - * i_mutex lock is held when entering and exiting this function */ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) @@ -210,7 +116,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) struct inode *inode = file->f_mapping->host; struct ext4_inode_info *ei = EXT4_I(inode); journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; - int ret; + int ret, err; tid_t commit_tid; bool needs_barrier = false; @@ -226,13 +132,13 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (inode->i_sb->s_flags & MS_RDONLY) goto out; - ret = ext4_flush_completed_IO(inode); + ret = ext4_flush_unwritten_io(inode); if (ret < 0) goto out; if (!journal) { ret = __sync_inode(inode, datasync); - if (!ret && !list_empty(&inode->i_dentry)) + if (!ret && !hlist_empty(&inode->i_dentry)) ret = ext4_sync_parent(inode); goto out; } @@ -262,8 +168,11 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) needs_barrier = true; jbd2_log_start_commit(journal, commit_tid); ret = jbd2_log_wait_commit(journal, commit_tid); - if (needs_barrier) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + if (needs_barrier) { + err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + if (!ret) + ret = err; + } out: mutex_unlock(&inode->i_mutex); trace_ext4_sync_file_exit(inode, ret); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index d48e8b14928..3f32c801244 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -315,7 +315,6 @@ out: err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!fatal) fatal = err; - ext4_mark_super_dirty(sb); } else ext4_error(sb, "bit already cleared for inode %lu", ino); @@ -698,6 +697,15 @@ got_group: if (!gdp) goto fail; + /* + * Check free inodes count before loading bitmap. + */ + if (ext4_free_inodes_count(sb, gdp) == 0) { + if (++group == ngroups) + group = 0; + continue; + } + brelse(inode_bitmap_bh); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); if (!inode_bitmap_bh) @@ -717,6 +725,10 @@ repeat_in_this_group: "inode=%lu", ino + 1); continue; } + BUFFER_TRACE(inode_bitmap_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, inode_bitmap_bh); + if (err) + goto fail; ext4_lock_group(sb, group); ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data); ext4_unlock_group(sb, group); @@ -730,6 +742,11 @@ repeat_in_this_group: goto out; got: + BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); + err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh); + if (err) + goto fail; + /* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { @@ -745,7 +762,6 @@ got: BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap"); err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh); - brelse(block_bitmap_bh); /* recheck and clear flag under lock if we still need to */ ext4_lock_group(sb, group); @@ -754,22 +770,16 @@ got: ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); ext4_block_bitmap_csum_set(sb, group, gdp, - block_bitmap_bh, - EXT4_BLOCKS_PER_GROUP(sb) / - 8); + block_bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); } ext4_unlock_group(sb, group); + brelse(block_bitmap_bh); if (err) goto fail; } - BUFFER_TRACE(inode_bitmap_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, inode_bitmap_bh); - if (err) - goto fail; - BUFFER_TRACE(group_desc_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, group_desc_bh); if (err) @@ -817,11 +827,6 @@ got: } ext4_unlock_group(sb, group); - BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh); - if (err) - goto fail; - BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh); if (err) @@ -830,7 +835,6 @@ got: percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter); - ext4_mark_super_dirty(sb); if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); @@ -898,6 +902,10 @@ got: ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize; + ei->i_inline_off = 0; + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_INLINE_DATA)) + ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + ret = inode; dquot_initialize(inode); err = dquot_alloc_inode(inode); @@ -1054,7 +1062,8 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) if (!bitmap_bh) continue; - x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); + x = ext4_count_free(bitmap_bh->b_data, + EXT4_INODES_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n", (unsigned long) i, ext4_free_inodes_count(sb, gdp), x); bitmap_count += x; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 830e1b2bf14..20862f96e8a 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -22,6 +22,7 @@ #include "ext4_jbd2.h" #include "truncate.h" +#include "ext4_extents.h" /* Needed for EXT_MAX_BLOCKS */ #include <trace/events/ext4.h> @@ -755,8 +756,7 @@ cleanup: partial--; } out: - trace_ext4_ind_map_blocks_exit(inode, map->m_lblk, - map->m_pblk, map->m_len, err); + trace_ext4_ind_map_blocks_exit(inode, map, err); return err; } @@ -807,16 +807,30 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, retry: if (rw == READ && ext4_should_dioread_nolock(inode)) { - if (unlikely(!list_empty(&ei->i_completed_io_list))) { + if (unlikely(atomic_read(&EXT4_I(inode)->i_unwritten))) { mutex_lock(&inode->i_mutex); - ext4_flush_completed_IO(inode); + ext4_flush_unwritten_io(inode); mutex_unlock(&inode->i_mutex); } + /* + * Nolock dioread optimization may be dynamically disabled + * via ext4_inode_block_unlocked_dio(). Check inode's state + * while holding extra i_dio_count ref. + */ + atomic_inc(&inode->i_dio_count); + smp_mb(); + if (unlikely(ext4_test_inode_state(inode, + EXT4_STATE_DIOREAD_LOCK))) { + inode_dio_done(inode); + goto locked; + } ret = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, nr_segs, ext4_get_block, NULL, NULL, 0); + inode_dio_done(inode); } else { +locked: ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, ext4_get_block); @@ -1398,6 +1412,7 @@ void ext4_ind_truncate(struct inode *inode) down_write(&ei->i_data_sem); ext4_discard_preallocations(inode); + ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); /* * The orphan list entry will now protect us from any crash which diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c new file mode 100644 index 00000000000..387c47c6cda --- /dev/null +++ b/fs/ext4/inline.c @@ -0,0 +1,1884 @@ +/* + * Copyright (c) 2012 Taobao. + * Written by Tao Ma <boyu.mt@taobao.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#include "ext4_jbd2.h" +#include "ext4.h" +#include "xattr.h" +#include "truncate.h" +#include <linux/fiemap.h> + +#define EXT4_XATTR_SYSTEM_DATA "data" +#define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS)) +#define EXT4_INLINE_DOTDOT_SIZE 4 + +int ext4_get_inline_size(struct inode *inode) +{ + if (EXT4_I(inode)->i_inline_off) + return EXT4_I(inode)->i_inline_size; + + return 0; +} + +static int get_max_inline_xattr_value_size(struct inode *inode, + struct ext4_iloc *iloc) +{ + struct ext4_xattr_ibody_header *header; + struct ext4_xattr_entry *entry; + struct ext4_inode *raw_inode; + int free, min_offs; + + min_offs = EXT4_SB(inode->i_sb)->s_inode_size - + EXT4_GOOD_OLD_INODE_SIZE - + EXT4_I(inode)->i_extra_isize - + sizeof(struct ext4_xattr_ibody_header); + + /* + * We need to subtract another sizeof(__u32) since an in-inode xattr + * needs an empty 4 bytes to indicate the gap between the xattr entry + * and the name/value pair. + */ + if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) + return EXT4_XATTR_SIZE(min_offs - + EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA)) - + EXT4_XATTR_ROUND - sizeof(__u32)); + + raw_inode = ext4_raw_inode(iloc); + header = IHDR(inode, raw_inode); + entry = IFIRST(header); + + /* Compute min_offs. */ + for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { + if (!entry->e_value_block && entry->e_value_size) { + size_t offs = le16_to_cpu(entry->e_value_offs); + if (offs < min_offs) + min_offs = offs; + } + } + free = min_offs - + ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32); + + if (EXT4_I(inode)->i_inline_off) { + entry = (struct ext4_xattr_entry *) + ((void *)raw_inode + EXT4_I(inode)->i_inline_off); + + free += le32_to_cpu(entry->e_value_size); + goto out; + } + + free -= EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA)); + + if (free > EXT4_XATTR_ROUND) + free = EXT4_XATTR_SIZE(free - EXT4_XATTR_ROUND); + else + free = 0; + +out: + return free; +} + +/* + * Get the maximum size we now can store in an inode. + * If we can't find the space for a xattr entry, don't use the space + * of the extents since we have no space to indicate the inline data. + */ +int ext4_get_max_inline_size(struct inode *inode) +{ + int error, max_inline_size; + struct ext4_iloc iloc; + + if (EXT4_I(inode)->i_extra_isize == 0) + return 0; + + error = ext4_get_inode_loc(inode, &iloc); + if (error) { + ext4_error_inode(inode, __func__, __LINE__, 0, + "can't get inode location %lu", + inode->i_ino); + return 0; + } + + down_read(&EXT4_I(inode)->xattr_sem); + max_inline_size = get_max_inline_xattr_value_size(inode, &iloc); + up_read(&EXT4_I(inode)->xattr_sem); + + brelse(iloc.bh); + + if (!max_inline_size) + return 0; + + return max_inline_size + EXT4_MIN_INLINE_DATA_SIZE; +} + +int ext4_has_inline_data(struct inode *inode) +{ + return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) && + EXT4_I(inode)->i_inline_off; +} + +/* + * this function does not take xattr_sem, which is OK because it is + * currently only used in a code path coming form ext4_iget, before + * the new inode has been unlocked + */ +int ext4_find_inline_data_nolock(struct inode *inode) +{ + struct ext4_xattr_ibody_find is = { + .s = { .not_found = -ENODATA, }, + }; + struct ext4_xattr_info i = { + .name_index = EXT4_XATTR_INDEX_SYSTEM, + .name = EXT4_XATTR_SYSTEM_DATA, + }; + int error; + + if (EXT4_I(inode)->i_extra_isize == 0) + return 0; + + error = ext4_get_inode_loc(inode, &is.iloc); + if (error) + return error; + + error = ext4_xattr_ibody_find(inode, &i, &is); + if (error) + goto out; + + if (!is.s.not_found) { + EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - + (void *)ext4_raw_inode(&is.iloc)); + EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + + le32_to_cpu(is.s.here->e_value_size); + ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + } +out: + brelse(is.iloc.bh); + return error; +} + +static int ext4_read_inline_data(struct inode *inode, void *buffer, + unsigned int len, + struct ext4_iloc *iloc) +{ + struct ext4_xattr_entry *entry; + struct ext4_xattr_ibody_header *header; + int cp_len = 0; + struct ext4_inode *raw_inode; + + if (!len) + return 0; + + BUG_ON(len > EXT4_I(inode)->i_inline_size); + + cp_len = len < EXT4_MIN_INLINE_DATA_SIZE ? + len : EXT4_MIN_INLINE_DATA_SIZE; + + raw_inode = ext4_raw_inode(iloc); + memcpy(buffer, (void *)(raw_inode->i_block), cp_len); + + len -= cp_len; + buffer += cp_len; + + if (!len) + goto out; + + header = IHDR(inode, raw_inode); + entry = (struct ext4_xattr_entry *)((void *)raw_inode + + EXT4_I(inode)->i_inline_off); + len = min_t(unsigned int, len, + (unsigned int)le32_to_cpu(entry->e_value_size)); + + memcpy(buffer, + (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs), len); + cp_len += len; + +out: + return cp_len; +} + +/* + * write the buffer to the inline inode. + * If 'create' is set, we don't need to do the extra copy in the xattr + * value since it is already handled by ext4_xattr_ibody_inline_set. + * That saves us one memcpy. + */ +void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, + void *buffer, loff_t pos, unsigned int len) +{ + struct ext4_xattr_entry *entry; + struct ext4_xattr_ibody_header *header; + struct ext4_inode *raw_inode; + int cp_len = 0; + + BUG_ON(!EXT4_I(inode)->i_inline_off); + BUG_ON(pos + len > EXT4_I(inode)->i_inline_size); + + raw_inode = ext4_raw_inode(iloc); + buffer += pos; + + if (pos < EXT4_MIN_INLINE_DATA_SIZE) { + cp_len = pos + len > EXT4_MIN_INLINE_DATA_SIZE ? + EXT4_MIN_INLINE_DATA_SIZE - pos : len; + memcpy((void *)raw_inode->i_block + pos, buffer, cp_len); + + len -= cp_len; + buffer += cp_len; + pos += cp_len; + } + + if (!len) + return; + + pos -= EXT4_MIN_INLINE_DATA_SIZE; + header = IHDR(inode, raw_inode); + entry = (struct ext4_xattr_entry *)((void *)raw_inode + + EXT4_I(inode)->i_inline_off); + + memcpy((void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs) + pos, + buffer, len); +} + +static int ext4_create_inline_data(handle_t *handle, + struct inode *inode, unsigned len) +{ + int error; + void *value = NULL; + struct ext4_xattr_ibody_find is = { + .s = { .not_found = -ENODATA, }, + }; + struct ext4_xattr_info i = { + .name_index = EXT4_XATTR_INDEX_SYSTEM, + .name = EXT4_XATTR_SYSTEM_DATA, + }; + + error = ext4_get_inode_loc(inode, &is.iloc); + if (error) + return error; + + error = ext4_journal_get_write_access(handle, is.iloc.bh); + if (error) + goto out; + + if (len > EXT4_MIN_INLINE_DATA_SIZE) { + value = EXT4_ZERO_XATTR_VALUE; + len -= EXT4_MIN_INLINE_DATA_SIZE; + } else { + value = ""; + len = 0; + } + + /* Insert the the xttr entry. */ + i.value = value; + i.value_len = len; + + error = ext4_xattr_ibody_find(inode, &i, &is); + if (error) + goto out; + + BUG_ON(!is.s.not_found); + + error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + if (error) { + if (error == -ENOSPC) + ext4_clear_inode_state(inode, + EXT4_STATE_MAY_INLINE_DATA); + goto out; + } + + memset((void *)ext4_raw_inode(&is.iloc)->i_block, + 0, EXT4_MIN_INLINE_DATA_SIZE); + + EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - + (void *)ext4_raw_inode(&is.iloc)); + EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE; + ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); + ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA); + get_bh(is.iloc.bh); + error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); + +out: + brelse(is.iloc.bh); + return error; +} + +static int ext4_update_inline_data(handle_t *handle, struct inode *inode, + unsigned int len) +{ + int error; + void *value = NULL; + struct ext4_xattr_ibody_find is = { + .s = { .not_found = -ENODATA, }, + }; + struct ext4_xattr_info i = { + .name_index = EXT4_XATTR_INDEX_SYSTEM, + .name = EXT4_XATTR_SYSTEM_DATA, + }; + + /* If the old space is ok, write the data directly. */ + if (len <= EXT4_I(inode)->i_inline_size) + return 0; + + error = ext4_get_inode_loc(inode, &is.iloc); + if (error) + return error; + + error = ext4_xattr_ibody_find(inode, &i, &is); + if (error) + goto out; + + BUG_ON(is.s.not_found); + + len -= EXT4_MIN_INLINE_DATA_SIZE; + value = kzalloc(len, GFP_NOFS); + if (!value) + goto out; + + error = ext4_xattr_ibody_get(inode, i.name_index, i.name, + value, len); + if (error == -ENODATA) + goto out; + + error = ext4_journal_get_write_access(handle, is.iloc.bh); + if (error) + goto out; + + /* Update the xttr entry. */ + i.value = value; + i.value_len = len; + + error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + if (error) + goto out; + + EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - + (void *)ext4_raw_inode(&is.iloc)); + EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + + le32_to_cpu(is.s.here->e_value_size); + ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + get_bh(is.iloc.bh); + error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); + +out: + kfree(value); + brelse(is.iloc.bh); + return error; +} + +int ext4_prepare_inline_data(handle_t *handle, struct inode *inode, + unsigned int len) +{ + int ret, size; + struct ext4_inode_info *ei = EXT4_I(inode); + + if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) + return -ENOSPC; + + size = ext4_get_max_inline_size(inode); + if (size < len) + return -ENOSPC; + + down_write(&EXT4_I(inode)->xattr_sem); + + if (ei->i_inline_off) + ret = ext4_update_inline_data(handle, inode, len); + else + ret = ext4_create_inline_data(handle, inode, len); + + up_write(&EXT4_I(inode)->xattr_sem); + + return ret; +} + +static int ext4_destroy_inline_data_nolock(handle_t *handle, + struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_xattr_ibody_find is = { + .s = { .not_found = 0, }, + }; + struct ext4_xattr_info i = { + .name_index = EXT4_XATTR_INDEX_SYSTEM, + .name = EXT4_XATTR_SYSTEM_DATA, + .value = NULL, + .value_len = 0, + }; + int error; + + if (!ei->i_inline_off) + return 0; + + error = ext4_get_inode_loc(inode, &is.iloc); + if (error) + return error; + + error = ext4_xattr_ibody_find(inode, &i, &is); + if (error) + goto out; + + error = ext4_journal_get_write_access(handle, is.iloc.bh); + if (error) + goto out; + + error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + if (error) + goto out; + + memset((void *)ext4_raw_inode(&is.iloc)->i_block, + 0, EXT4_MIN_INLINE_DATA_SIZE); + + if (EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_INCOMPAT_EXTENTS)) { + if (S_ISDIR(inode->i_mode) || + S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { + ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); + ext4_ext_tree_init(handle, inode); + } + } + ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA); + + get_bh(is.iloc.bh); + error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); + + EXT4_I(inode)->i_inline_off = 0; + EXT4_I(inode)->i_inline_size = 0; + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); +out: + brelse(is.iloc.bh); + if (error == -ENODATA) + error = 0; + return error; +} + +static int ext4_read_inline_page(struct inode *inode, struct page *page) +{ + void *kaddr; + int ret = 0; + size_t len; + struct ext4_iloc iloc; + + BUG_ON(!PageLocked(page)); + BUG_ON(!ext4_has_inline_data(inode)); + BUG_ON(page->index); + + if (!EXT4_I(inode)->i_inline_off) { + ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.", + inode->i_ino); + goto out; + } + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + goto out; + + len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode)); + kaddr = kmap_atomic(page); + ret = ext4_read_inline_data(inode, kaddr, len, &iloc); + flush_dcache_page(page); + kunmap_atomic(kaddr); + zero_user_segment(page, len, PAGE_CACHE_SIZE); + SetPageUptodate(page); + brelse(iloc.bh); + +out: + return ret; +} + +int ext4_readpage_inline(struct inode *inode, struct page *page) +{ + int ret = 0; + + down_read(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + up_read(&EXT4_I(inode)->xattr_sem); + return -EAGAIN; + } + + /* + * Current inline data can only exist in the 1st page, + * So for all the other pages, just set them uptodate. + */ + if (!page->index) + ret = ext4_read_inline_page(inode, page); + else if (!PageUptodate(page)) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + } + + up_read(&EXT4_I(inode)->xattr_sem); + + unlock_page(page); + return ret >= 0 ? 0 : ret; +} + +static int ext4_convert_inline_data_to_extent(struct address_space *mapping, + struct inode *inode, + unsigned flags) +{ + int ret, needed_blocks; + handle_t *handle = NULL; + int retries = 0, sem_held = 0; + struct page *page = NULL; + unsigned from, to; + struct ext4_iloc iloc; + + if (!ext4_has_inline_data(inode)) { + /* + * clear the flag so that no new write + * will trap here again. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + return 0; + } + + needed_blocks = ext4_writepage_trans_blocks(inode); + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + return ret; + +retry: + handle = ext4_journal_start(inode, needed_blocks); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + handle = NULL; + goto out; + } + + /* We cannot recurse into the filesystem as the transaction is already + * started */ + flags |= AOP_FLAG_NOFS; + + page = grab_cache_page_write_begin(mapping, 0, flags); + if (!page) { + ret = -ENOMEM; + goto out; + } + + down_write(&EXT4_I(inode)->xattr_sem); + sem_held = 1; + /* If some one has already done this for us, just exit. */ + if (!ext4_has_inline_data(inode)) { + ret = 0; + goto out; + } + + from = 0; + to = ext4_get_inline_size(inode); + if (!PageUptodate(page)) { + ret = ext4_read_inline_page(inode, page); + if (ret < 0) + goto out; + } + + ret = ext4_destroy_inline_data_nolock(handle, inode); + if (ret) + goto out; + + if (ext4_should_dioread_nolock(inode)) + ret = __block_write_begin(page, from, to, ext4_get_block_write); + else + ret = __block_write_begin(page, from, to, ext4_get_block); + + if (!ret && ext4_should_journal_data(inode)) { + ret = ext4_walk_page_buffers(handle, page_buffers(page), + from, to, NULL, + do_journal_get_write_access); + } + + if (ret) { + unlock_page(page); + page_cache_release(page); + ext4_orphan_add(handle, inode); + up_write(&EXT4_I(inode)->xattr_sem); + sem_held = 0; + ext4_journal_stop(handle); + handle = NULL; + ext4_truncate_failed_write(inode); + /* + * If truncate 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)) + goto retry; + + block_commit_write(page, from, to); +out: + if (page) { + unlock_page(page); + page_cache_release(page); + } + if (sem_held) + up_write(&EXT4_I(inode)->xattr_sem); + if (handle) + ext4_journal_stop(handle); + brelse(iloc.bh); + return ret; +} + +/* + * Try to write data in the inode. + * If the inode has inline data, check whether the new write can be + * in the inode also. If not, create the page the handle, move the data + * to the page make it update and let the later codes create extent for it. + */ +int ext4_try_to_write_inline_data(struct address_space *mapping, + struct inode *inode, + loff_t pos, unsigned len, + unsigned flags, + struct page **pagep) +{ + int ret; + handle_t *handle; + struct page *page; + struct ext4_iloc iloc; + + if (pos + len > ext4_get_max_inline_size(inode)) + goto convert; + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + return ret; + + /* + * The possible write could happen in the inode, + * so try to reserve the space in inode first. + */ + handle = ext4_journal_start(inode, 1); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + handle = NULL; + goto out; + } + + ret = ext4_prepare_inline_data(handle, inode, pos + len); + if (ret && ret != -ENOSPC) + goto out; + + /* We don't have space in inline inode, so convert it to extent. */ + if (ret == -ENOSPC) { + ext4_journal_stop(handle); + brelse(iloc.bh); + goto convert; + } + + flags |= AOP_FLAG_NOFS; + + page = grab_cache_page_write_begin(mapping, 0, flags); + if (!page) { + ret = -ENOMEM; + goto out; + } + + *pagep = page; + down_read(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + ret = 0; + unlock_page(page); + page_cache_release(page); + goto out_up_read; + } + + if (!PageUptodate(page)) { + ret = ext4_read_inline_page(inode, page); + if (ret < 0) + goto out_up_read; + } + + ret = 1; + handle = NULL; +out_up_read: + up_read(&EXT4_I(inode)->xattr_sem); +out: + if (handle) + ext4_journal_stop(handle); + brelse(iloc.bh); + return ret; +convert: + return ext4_convert_inline_data_to_extent(mapping, + inode, flags); +} + +int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, + unsigned copied, struct page *page) +{ + int ret; + void *kaddr; + struct ext4_iloc iloc; + + if (unlikely(copied < len)) { + if (!PageUptodate(page)) { + copied = 0; + goto out; + } + } + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) { + ext4_std_error(inode->i_sb, ret); + copied = 0; + goto out; + } + + down_write(&EXT4_I(inode)->xattr_sem); + BUG_ON(!ext4_has_inline_data(inode)); + + kaddr = kmap_atomic(page); + ext4_write_inline_data(inode, &iloc, kaddr, pos, len); + kunmap_atomic(kaddr); + SetPageUptodate(page); + /* clear page dirty so that writepages wouldn't work for us. */ + ClearPageDirty(page); + + up_write(&EXT4_I(inode)->xattr_sem); + brelse(iloc.bh); +out: + return copied; +} + +struct buffer_head * +ext4_journalled_write_inline_data(struct inode *inode, + unsigned len, + struct page *page) +{ + int ret; + void *kaddr; + struct ext4_iloc iloc; + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) { + ext4_std_error(inode->i_sb, ret); + return NULL; + } + + down_write(&EXT4_I(inode)->xattr_sem); + kaddr = kmap_atomic(page); + ext4_write_inline_data(inode, &iloc, kaddr, 0, len); + kunmap_atomic(kaddr); + up_write(&EXT4_I(inode)->xattr_sem); + + return iloc.bh; +} + +/* + * Try to make the page cache and handle ready for the inline data case. + * We can call this function in 2 cases: + * 1. The inode is created and the first write exceeds inline size. We can + * clear the inode state safely. + * 2. The inode has inline data, then we need to read the data, make it + * update and dirty so that ext4_da_writepages can handle it. We don't + * need to start the journal since the file's metatdata isn't changed now. + */ +static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, + struct inode *inode, + unsigned flags, + void **fsdata) +{ + int ret = 0, inline_size; + struct page *page; + + page = grab_cache_page_write_begin(mapping, 0, flags); + if (!page) + return -ENOMEM; + + down_read(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + goto out; + } + + inline_size = ext4_get_inline_size(inode); + + if (!PageUptodate(page)) { + ret = ext4_read_inline_page(inode, page); + if (ret < 0) + goto out; + } + + ret = __block_write_begin(page, 0, inline_size, + ext4_da_get_block_prep); + if (ret) { + ext4_truncate_failed_write(inode); + goto out; + } + + SetPageDirty(page); + SetPageUptodate(page); + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + *fsdata = (void *)CONVERT_INLINE_DATA; + +out: + up_read(&EXT4_I(inode)->xattr_sem); + if (page) { + unlock_page(page); + page_cache_release(page); + } + return ret; +} + +/* + * Prepare the write for the inline data. + * If the the data can be written into the inode, we just read + * the page and make it uptodate, and start the journal. + * Otherwise read the page, makes it dirty so that it can be + * handle in writepages(the i_disksize update is left to the + * normal ext4_da_write_end). + */ +int ext4_da_write_inline_data_begin(struct address_space *mapping, + struct inode *inode, + loff_t pos, unsigned len, + unsigned flags, + struct page **pagep, + void **fsdata) +{ + int ret, inline_size; + handle_t *handle; + struct page *page; + struct ext4_iloc iloc; + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + return ret; + + handle = ext4_journal_start(inode, 1); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + handle = NULL; + goto out; + } + + inline_size = ext4_get_max_inline_size(inode); + + ret = -ENOSPC; + if (inline_size >= pos + len) { + ret = ext4_prepare_inline_data(handle, inode, pos + len); + if (ret && ret != -ENOSPC) + goto out; + } + + if (ret == -ENOSPC) { + ret = ext4_da_convert_inline_data_to_extent(mapping, + inode, + flags, + fsdata); + goto out; + } + + /* + * We cannot recurse into the filesystem as the transaction + * is already started. + */ + flags |= AOP_FLAG_NOFS; + + page = grab_cache_page_write_begin(mapping, 0, flags); + if (!page) { + ret = -ENOMEM; + goto out; + } + + down_read(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + ret = 0; + goto out_release_page; + } + + if (!PageUptodate(page)) { + ret = ext4_read_inline_page(inode, page); + if (ret < 0) + goto out_release_page; + } + + up_read(&EXT4_I(inode)->xattr_sem); + *pagep = page; + handle = NULL; + brelse(iloc.bh); + return 1; +out_release_page: + up_read(&EXT4_I(inode)->xattr_sem); + unlock_page(page); + page_cache_release(page); +out: + if (handle) + ext4_journal_stop(handle); + brelse(iloc.bh); + return ret; +} + +int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, + unsigned len, unsigned copied, + struct page *page) +{ + int i_size_changed = 0; + + copied = ext4_write_inline_data_end(inode, pos, len, copied, page); + + /* + * 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; + } + 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) + mark_inode_dirty(inode); + + return copied; +} + +#ifdef INLINE_DIR_DEBUG +void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, + void *inline_start, int inline_size) +{ + int offset; + unsigned short de_len; + struct ext4_dir_entry_2 *de = inline_start; + void *dlimit = inline_start + inline_size; + + trace_printk("inode %lu\n", dir->i_ino); + offset = 0; + while ((void *)de < dlimit) { + de_len = ext4_rec_len_from_disk(de->rec_len, inline_size); + trace_printk("de: off %u rlen %u name %*.s nlen %u ino %u\n", + offset, de_len, de->name_len, de->name, + de->name_len, le32_to_cpu(de->inode)); + if (ext4_check_dir_entry(dir, NULL, de, bh, + inline_start, inline_size, offset)) + BUG(); + + offset += de_len; + de = (struct ext4_dir_entry_2 *) ((char *) de + de_len); + } +} +#else +#define ext4_show_inline_dir(dir, bh, inline_start, inline_size) +#endif + +/* + * Add a new entry into a inline dir. + * It will return -ENOSPC if no space is available, and -EIO + * and -EEXIST if directory entry already exists. + */ +static int ext4_add_dirent_to_inline(handle_t *handle, + struct dentry *dentry, + struct inode *inode, + struct ext4_iloc *iloc, + void *inline_start, int inline_size) +{ + struct inode *dir = dentry->d_parent->d_inode; + const char *name = dentry->d_name.name; + int namelen = dentry->d_name.len; + unsigned short reclen; + int err; + struct ext4_dir_entry_2 *de; + + reclen = EXT4_DIR_REC_LEN(namelen); + err = ext4_find_dest_de(dir, inode, iloc->bh, + inline_start, inline_size, + name, namelen, &de); + if (err) + return err; + + err = ext4_journal_get_write_access(handle, iloc->bh); + if (err) + return err; + ext4_insert_dentry(inode, de, inline_size, name, namelen); + + ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size); + + /* + * XXX shouldn't update any times until successful + * completion of syscall, but too many callers depend + * on this. + * + * XXX similarly, too many callers depend on + * ext4_new_inode() setting the times, but error + * recovery deletes the inode, so the worst that can + * happen is that the times are slightly out of date + * and/or different from the directory change time. + */ + dir->i_mtime = dir->i_ctime = ext4_current_time(dir); + ext4_update_dx_flag(dir); + dir->i_version++; + ext4_mark_inode_dirty(handle, dir); + return 1; +} + +static void *ext4_get_inline_xattr_pos(struct inode *inode, + struct ext4_iloc *iloc) +{ + struct ext4_xattr_entry *entry; + struct ext4_xattr_ibody_header *header; + + BUG_ON(!EXT4_I(inode)->i_inline_off); + + header = IHDR(inode, ext4_raw_inode(iloc)); + entry = (struct ext4_xattr_entry *)((void *)ext4_raw_inode(iloc) + + EXT4_I(inode)->i_inline_off); + + return (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs); +} + +/* Set the final de to cover the whole block. */ +static void ext4_update_final_de(void *de_buf, int old_size, int new_size) +{ + struct ext4_dir_entry_2 *de, *prev_de; + void *limit; + int de_len; + + de = (struct ext4_dir_entry_2 *)de_buf; + if (old_size) { + limit = de_buf + old_size; + do { + prev_de = de; + de_len = ext4_rec_len_from_disk(de->rec_len, old_size); + de_buf += de_len; + de = (struct ext4_dir_entry_2 *)de_buf; + } while (de_buf < limit); + + prev_de->rec_len = ext4_rec_len_to_disk(de_len + new_size - + old_size, new_size); + } else { + /* this is just created, so create an empty entry. */ + de->inode = 0; + de->rec_len = ext4_rec_len_to_disk(new_size, new_size); + } +} + +static int ext4_update_inline_dir(handle_t *handle, struct inode *dir, + struct ext4_iloc *iloc) +{ + int ret; + int old_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; + int new_size = get_max_inline_xattr_value_size(dir, iloc); + + if (new_size - old_size <= EXT4_DIR_REC_LEN(1)) + return -ENOSPC; + + ret = ext4_update_inline_data(handle, dir, + new_size + EXT4_MIN_INLINE_DATA_SIZE); + if (ret) + return ret; + + ext4_update_final_de(ext4_get_inline_xattr_pos(dir, iloc), old_size, + EXT4_I(dir)->i_inline_size - + EXT4_MIN_INLINE_DATA_SIZE); + dir->i_size = EXT4_I(dir)->i_disksize = EXT4_I(dir)->i_inline_size; + return 0; +} + +static void ext4_restore_inline_data(handle_t *handle, struct inode *inode, + struct ext4_iloc *iloc, + void *buf, int inline_size) +{ + ext4_create_inline_data(handle, inode, inline_size); + ext4_write_inline_data(inode, iloc, buf, 0, inline_size); + ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); +} + +static int ext4_finish_convert_inline_dir(handle_t *handle, + struct inode *inode, + struct buffer_head *dir_block, + void *buf, + int inline_size) +{ + int err, csum_size = 0, header_size = 0; + struct ext4_dir_entry_2 *de; + struct ext4_dir_entry_tail *t; + void *target = dir_block->b_data; + + /* + * First create "." and ".." and then copy the dir information + * back to the block. + */ + de = (struct ext4_dir_entry_2 *)target; + de = ext4_init_dot_dotdot(inode, de, + inode->i_sb->s_blocksize, csum_size, + le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1); + header_size = (void *)de - target; + + memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE, + inline_size - EXT4_INLINE_DOTDOT_SIZE); + + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + csum_size = sizeof(struct ext4_dir_entry_tail); + + inode->i_size = inode->i_sb->s_blocksize; + i_size_write(inode, inode->i_sb->s_blocksize); + EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize; + ext4_update_final_de(dir_block->b_data, + inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size, + inode->i_sb->s_blocksize - csum_size); + + if (csum_size) { + t = EXT4_DIRENT_TAIL(dir_block->b_data, + inode->i_sb->s_blocksize); + initialize_dirent_tail(t, inode->i_sb->s_blocksize); + } + set_buffer_uptodate(dir_block); + err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); + if (err) + goto out; + set_buffer_verified(dir_block); +out: + return err; +} + +static int ext4_convert_inline_data_nolock(handle_t *handle, + struct inode *inode, + struct ext4_iloc *iloc) +{ + int error; + void *buf = NULL; + struct buffer_head *data_bh = NULL; + struct ext4_map_blocks map; + int inline_size; + + inline_size = ext4_get_inline_size(inode); + buf = kmalloc(inline_size, GFP_NOFS); + if (!buf) { + error = -ENOMEM; + goto out; + } + + error = ext4_read_inline_data(inode, buf, inline_size, iloc); + if (error < 0) + goto out; + + error = ext4_destroy_inline_data_nolock(handle, inode); + if (error) + goto out; + + map.m_lblk = 0; + map.m_len = 1; + map.m_flags = 0; + error = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_CREATE); + if (error < 0) + goto out_restore; + if (!(map.m_flags & EXT4_MAP_MAPPED)) { + error = -EIO; + goto out_restore; + } + + data_bh = sb_getblk(inode->i_sb, map.m_pblk); + if (!data_bh) { + error = -EIO; + goto out_restore; + } + + lock_buffer(data_bh); + error = ext4_journal_get_create_access(handle, data_bh); + if (error) { + unlock_buffer(data_bh); + error = -EIO; + goto out_restore; + } + memset(data_bh->b_data, 0, inode->i_sb->s_blocksize); + + if (!S_ISDIR(inode->i_mode)) { + memcpy(data_bh->b_data, buf, inline_size); + set_buffer_uptodate(data_bh); + error = ext4_handle_dirty_metadata(handle, + inode, data_bh); + } else { + error = ext4_finish_convert_inline_dir(handle, inode, data_bh, + buf, inline_size); + } + + unlock_buffer(data_bh); +out_restore: + if (error) + ext4_restore_inline_data(handle, inode, iloc, buf, inline_size); + +out: + brelse(data_bh); + kfree(buf); + return error; +} + +/* + * Try to add the new entry to the inline data. + * If succeeds, return 0. If not, extended the inline dir and copied data to + * the new created block. + */ +int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry, + struct inode *inode) +{ + int ret, inline_size; + void *inline_start; + struct ext4_iloc iloc; + struct inode *dir = dentry->d_parent->d_inode; + + ret = ext4_get_inode_loc(dir, &iloc); + if (ret) + return ret; + + down_write(&EXT4_I(dir)->xattr_sem); + if (!ext4_has_inline_data(dir)) + goto out; + + inline_start = (void *)ext4_raw_inode(&iloc)->i_block + + EXT4_INLINE_DOTDOT_SIZE; + inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; + + ret = ext4_add_dirent_to_inline(handle, dentry, inode, &iloc, + inline_start, inline_size); + if (ret != -ENOSPC) + goto out; + + /* check whether it can be inserted to inline xattr space. */ + inline_size = EXT4_I(dir)->i_inline_size - + EXT4_MIN_INLINE_DATA_SIZE; + if (!inline_size) { + /* Try to use the xattr space.*/ + ret = ext4_update_inline_dir(handle, dir, &iloc); + if (ret && ret != -ENOSPC) + goto out; + + inline_size = EXT4_I(dir)->i_inline_size - + EXT4_MIN_INLINE_DATA_SIZE; + } + + if (inline_size) { + inline_start = ext4_get_inline_xattr_pos(dir, &iloc); + + ret = ext4_add_dirent_to_inline(handle, dentry, inode, &iloc, + inline_start, inline_size); + + if (ret != -ENOSPC) + goto out; + } + + /* + * The inline space is filled up, so create a new block for it. + * As the extent tree will be created, we have to save the inline + * dir first. + */ + ret = ext4_convert_inline_data_nolock(handle, dir, &iloc); + +out: + ext4_mark_inode_dirty(handle, dir); + up_write(&EXT4_I(dir)->xattr_sem); + brelse(iloc.bh); + return ret; +} + +int ext4_read_inline_dir(struct file *filp, + void *dirent, filldir_t filldir, + int *has_inline_data) +{ + int error = 0; + unsigned int offset, parent_ino; + int i, stored; + struct ext4_dir_entry_2 *de; + struct super_block *sb; + struct inode *inode = filp->f_path.dentry->d_inode; + int ret, inline_size = 0; + struct ext4_iloc iloc; + void *dir_buf = NULL; + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + return ret; + + down_read(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + up_read(&EXT4_I(inode)->xattr_sem); + *has_inline_data = 0; + goto out; + } + + inline_size = ext4_get_inline_size(inode); + dir_buf = kmalloc(inline_size, GFP_NOFS); + if (!dir_buf) { + ret = -ENOMEM; + up_read(&EXT4_I(inode)->xattr_sem); + goto out; + } + + ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc); + up_read(&EXT4_I(inode)->xattr_sem); + if (ret < 0) + goto out; + + sb = inode->i_sb; + stored = 0; + parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); + + while (!error && !stored && filp->f_pos < inode->i_size) { +revalidate: + /* + * If the version has changed since the last call to + * readdir(2), then we might be pointing to an invalid + * dirent right now. Scan from the start of the inline + * dir to make sure. + */ + if (filp->f_version != inode->i_version) { + for (i = 0; + i < inode->i_size && i < offset;) { + if (!i) { + /* skip "." and ".." if needed. */ + i += EXT4_INLINE_DOTDOT_SIZE; + continue; + } + de = (struct ext4_dir_entry_2 *) + (dir_buf + i); + /* It's too expensive to do a full + * dirent test each time round this + * loop, but we do have to test at + * least that it is non-zero. A + * failure will be detected in the + * dirent test below. */ + if (ext4_rec_len_from_disk(de->rec_len, + inline_size) < EXT4_DIR_REC_LEN(1)) + break; + i += ext4_rec_len_from_disk(de->rec_len, + inline_size); + } + offset = i; + filp->f_pos = offset; + filp->f_version = inode->i_version; + } + + while (!error && filp->f_pos < inode->i_size) { + if (filp->f_pos == 0) { + error = filldir(dirent, ".", 1, 0, inode->i_ino, + DT_DIR); + if (error) + break; + stored++; + + error = filldir(dirent, "..", 2, 0, parent_ino, + DT_DIR); + if (error) + break; + stored++; + + filp->f_pos = offset = EXT4_INLINE_DOTDOT_SIZE; + continue; + } + + de = (struct ext4_dir_entry_2 *)(dir_buf + offset); + if (ext4_check_dir_entry(inode, filp, de, + iloc.bh, dir_buf, + inline_size, offset)) { + ret = stored; + goto out; + } + offset += ext4_rec_len_from_disk(de->rec_len, + inline_size); + if (le32_to_cpu(de->inode)) { + /* We might block in the next section + * if the data destination is + * currently swapped out. So, use a + * version stamp to detect whether or + * not the directory has been modified + * during the copy operation. + */ + u64 version = filp->f_version; + + error = filldir(dirent, de->name, + de->name_len, + filp->f_pos, + le32_to_cpu(de->inode), + get_dtype(sb, de->file_type)); + if (error) + break; + if (version != filp->f_version) + goto revalidate; + stored++; + } + filp->f_pos += ext4_rec_len_from_disk(de->rec_len, + inline_size); + } + offset = 0; + } +out: + kfree(dir_buf); + brelse(iloc.bh); + return ret; +} + +struct buffer_head *ext4_get_first_inline_block(struct inode *inode, + struct ext4_dir_entry_2 **parent_de, + int *retval) +{ + struct ext4_iloc iloc; + + *retval = ext4_get_inode_loc(inode, &iloc); + if (*retval) + return NULL; + + *parent_de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; + + return iloc.bh; +} + +/* + * Try to create the inline data for the new dir. + * If it succeeds, return 0, otherwise return the error. + * In case of ENOSPC, the caller should create the normal disk layout dir. + */ +int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent, + struct inode *inode) +{ + int ret, inline_size = EXT4_MIN_INLINE_DATA_SIZE; + struct ext4_iloc iloc; + struct ext4_dir_entry_2 *de; + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + return ret; + + ret = ext4_prepare_inline_data(handle, inode, inline_size); + if (ret) + goto out; + + /* + * For inline dir, we only save the inode information for the ".." + * and create a fake dentry to cover the left space. + */ + de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; + de->inode = cpu_to_le32(parent->i_ino); + de = (struct ext4_dir_entry_2 *)((void *)de + EXT4_INLINE_DOTDOT_SIZE); + de->inode = 0; + de->rec_len = ext4_rec_len_to_disk( + inline_size - EXT4_INLINE_DOTDOT_SIZE, + inline_size); + set_nlink(inode, 2); + inode->i_size = EXT4_I(inode)->i_disksize = inline_size; +out: + brelse(iloc.bh); + return ret; +} + +struct buffer_head *ext4_find_inline_entry(struct inode *dir, + const struct qstr *d_name, + struct ext4_dir_entry_2 **res_dir, + int *has_inline_data) +{ + int ret; + struct ext4_iloc iloc; + void *inline_start; + int inline_size; + + if (ext4_get_inode_loc(dir, &iloc)) + return NULL; + + down_read(&EXT4_I(dir)->xattr_sem); + if (!ext4_has_inline_data(dir)) { + *has_inline_data = 0; + goto out; + } + + inline_start = (void *)ext4_raw_inode(&iloc)->i_block + + EXT4_INLINE_DOTDOT_SIZE; + inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; + ret = search_dir(iloc.bh, inline_start, inline_size, + dir, d_name, 0, res_dir); + if (ret == 1) + goto out_find; + if (ret < 0) + goto out; + + if (ext4_get_inline_size(dir) == EXT4_MIN_INLINE_DATA_SIZE) + goto out; + + inline_start = ext4_get_inline_xattr_pos(dir, &iloc); + inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE; + + ret = search_dir(iloc.bh, inline_start, inline_size, + dir, d_name, 0, res_dir); + if (ret == 1) + goto out_find; + +out: + brelse(iloc.bh); + iloc.bh = NULL; +out_find: + up_read(&EXT4_I(dir)->xattr_sem); + return iloc.bh; +} + +int ext4_delete_inline_entry(handle_t *handle, + struct inode *dir, + struct ext4_dir_entry_2 *de_del, + struct buffer_head *bh, + int *has_inline_data) +{ + int err, inline_size; + struct ext4_iloc iloc; + void *inline_start; + + err = ext4_get_inode_loc(dir, &iloc); + if (err) + return err; + + down_write(&EXT4_I(dir)->xattr_sem); + if (!ext4_has_inline_data(dir)) { + *has_inline_data = 0; + goto out; + } + + if ((void *)de_del - ((void *)ext4_raw_inode(&iloc)->i_block) < + EXT4_MIN_INLINE_DATA_SIZE) { + inline_start = (void *)ext4_raw_inode(&iloc)->i_block + + EXT4_INLINE_DOTDOT_SIZE; + inline_size = EXT4_MIN_INLINE_DATA_SIZE - + EXT4_INLINE_DOTDOT_SIZE; + } else { + inline_start = ext4_get_inline_xattr_pos(dir, &iloc); + inline_size = ext4_get_inline_size(dir) - + EXT4_MIN_INLINE_DATA_SIZE; + } + + err = ext4_journal_get_write_access(handle, bh); + if (err) + goto out; + + err = ext4_generic_delete_entry(handle, dir, de_del, bh, + inline_start, inline_size, 0); + if (err) + goto out; + + BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); + err = ext4_mark_inode_dirty(handle, dir); + if (unlikely(err)) + goto out; + + ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size); +out: + up_write(&EXT4_I(dir)->xattr_sem); + brelse(iloc.bh); + if (err != -ENOENT) + ext4_std_error(dir->i_sb, err); + return err; +} + +/* + * Get the inline dentry at offset. + */ +static inline struct ext4_dir_entry_2 * +ext4_get_inline_entry(struct inode *inode, + struct ext4_iloc *iloc, + unsigned int offset, + void **inline_start, + int *inline_size) +{ + void *inline_pos; + + BUG_ON(offset > ext4_get_inline_size(inode)); + + if (offset < EXT4_MIN_INLINE_DATA_SIZE) { + inline_pos = (void *)ext4_raw_inode(iloc)->i_block; + *inline_size = EXT4_MIN_INLINE_DATA_SIZE; + } else { + inline_pos = ext4_get_inline_xattr_pos(inode, iloc); + offset -= EXT4_MIN_INLINE_DATA_SIZE; + *inline_size = ext4_get_inline_size(inode) - + EXT4_MIN_INLINE_DATA_SIZE; + } + + if (inline_start) + *inline_start = inline_pos; + return (struct ext4_dir_entry_2 *)(inline_pos + offset); +} + +int empty_inline_dir(struct inode *dir, int *has_inline_data) +{ + int err, inline_size; + struct ext4_iloc iloc; + void *inline_pos; + unsigned int offset; + struct ext4_dir_entry_2 *de; + int ret = 1; + + err = ext4_get_inode_loc(dir, &iloc); + if (err) { + EXT4_ERROR_INODE(dir, "error %d getting inode %lu block", + err, dir->i_ino); + return 1; + } + + down_read(&EXT4_I(dir)->xattr_sem); + if (!ext4_has_inline_data(dir)) { + *has_inline_data = 0; + goto out; + } + + de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; + if (!le32_to_cpu(de->inode)) { + ext4_warning(dir->i_sb, + "bad inline directory (dir #%lu) - no `..'", + dir->i_ino); + ret = 1; + goto out; + } + + offset = EXT4_INLINE_DOTDOT_SIZE; + while (offset < dir->i_size) { + de = ext4_get_inline_entry(dir, &iloc, offset, + &inline_pos, &inline_size); + if (ext4_check_dir_entry(dir, NULL, de, + iloc.bh, inline_pos, + inline_size, offset)) { + ext4_warning(dir->i_sb, + "bad inline directory (dir #%lu) - " + "inode %u, rec_len %u, name_len %d" + "inline size %d\n", + dir->i_ino, le32_to_cpu(de->inode), + le16_to_cpu(de->rec_len), de->name_len, + inline_size); + ret = 1; + goto out; + } + if (le32_to_cpu(de->inode)) { + ret = 0; + goto out; + } + offset += ext4_rec_len_from_disk(de->rec_len, inline_size); + } + +out: + up_read(&EXT4_I(dir)->xattr_sem); + brelse(iloc.bh); + return ret; +} + +int ext4_destroy_inline_data(handle_t *handle, struct inode *inode) +{ + int ret; + + down_write(&EXT4_I(inode)->xattr_sem); + ret = ext4_destroy_inline_data_nolock(handle, inode); + up_write(&EXT4_I(inode)->xattr_sem); + + return ret; +} + +int ext4_inline_data_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, + int *has_inline) +{ + __u64 physical = 0; + __u64 length; + __u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_LAST; + int error = 0; + struct ext4_iloc iloc; + + down_read(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + *has_inline = 0; + goto out; + } + + error = ext4_get_inode_loc(inode, &iloc); + if (error) + goto out; + + physical = iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits; + physical += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data; + physical += offsetof(struct ext4_inode, i_block); + length = i_size_read(inode); + + if (physical) + error = fiemap_fill_next_extent(fieinfo, 0, physical, + length, flags); + brelse(iloc.bh); +out: + up_read(&EXT4_I(inode)->xattr_sem); + return (error < 0 ? error : 0); +} + +/* + * Called during xattr set, and if we can sparse space 'needed', + * just create the extent tree evict the data to the outer block. + * + * We use jbd2 instead of page cache to move data to the 1st block + * so that the whole transaction can be committed as a whole and + * the data isn't lost because of the delayed page cache write. + */ +int ext4_try_to_evict_inline_data(handle_t *handle, + struct inode *inode, + int needed) +{ + int error; + struct ext4_xattr_entry *entry; + struct ext4_xattr_ibody_header *header; + struct ext4_inode *raw_inode; + struct ext4_iloc iloc; + + error = ext4_get_inode_loc(inode, &iloc); + if (error) + return error; + + raw_inode = ext4_raw_inode(&iloc); + header = IHDR(inode, raw_inode); + entry = (struct ext4_xattr_entry *)((void *)raw_inode + + EXT4_I(inode)->i_inline_off); + if (EXT4_XATTR_LEN(entry->e_name_len) + + EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) { + error = -ENOSPC; + goto out; + } + + error = ext4_convert_inline_data_nolock(handle, inode, &iloc); +out: + brelse(iloc.bh); + return error; +} + +void ext4_inline_data_truncate(struct inode *inode, int *has_inline) +{ + handle_t *handle; + int inline_size, value_len, needed_blocks; + size_t i_size; + void *value = NULL; + struct ext4_xattr_ibody_find is = { + .s = { .not_found = -ENODATA, }, + }; + struct ext4_xattr_info i = { + .name_index = EXT4_XATTR_INDEX_SYSTEM, + .name = EXT4_XATTR_SYSTEM_DATA, + }; + + + needed_blocks = ext4_writepage_trans_blocks(inode); + handle = ext4_journal_start(inode, needed_blocks); + if (IS_ERR(handle)) + return; + + down_write(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + *has_inline = 0; + ext4_journal_stop(handle); + return; + } + + if (ext4_orphan_add(handle, inode)) + goto out; + + if (ext4_get_inode_loc(inode, &is.iloc)) + goto out; + + down_write(&EXT4_I(inode)->i_data_sem); + i_size = inode->i_size; + inline_size = ext4_get_inline_size(inode); + EXT4_I(inode)->i_disksize = i_size; + + if (i_size < inline_size) { + /* Clear the content in the xattr space. */ + if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) { + if (ext4_xattr_ibody_find(inode, &i, &is)) + goto out_error; + + BUG_ON(is.s.not_found); + + value_len = le32_to_cpu(is.s.here->e_value_size); + value = kmalloc(value_len, GFP_NOFS); + if (!value) + goto out_error; + + if (ext4_xattr_ibody_get(inode, i.name_index, i.name, + value, value_len)) + goto out_error; + + i.value = value; + i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ? + i_size - EXT4_MIN_INLINE_DATA_SIZE : 0; + if (ext4_xattr_ibody_inline_set(handle, inode, &i, &is)) + goto out_error; + } + + /* Clear the content within i_blocks. */ + if (i_size < EXT4_MIN_INLINE_DATA_SIZE) + memset(ext4_raw_inode(&is.iloc)->i_block + i_size, 0, + EXT4_MIN_INLINE_DATA_SIZE - i_size); + + EXT4_I(inode)->i_inline_size = i_size < + EXT4_MIN_INLINE_DATA_SIZE ? + EXT4_MIN_INLINE_DATA_SIZE : i_size; + } + +out_error: + up_write(&EXT4_I(inode)->i_data_sem); +out: + brelse(is.iloc.bh); + up_write(&EXT4_I(inode)->xattr_sem); + kfree(value); + if (inode->i_nlink) + ext4_orphan_del(handle, inode); + + inode->i_mtime = inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); + if (IS_SYNC(inode)) + ext4_handle_sync(handle); + + ext4_journal_stop(handle); + return; +} + +int ext4_convert_inline_data(struct inode *inode) +{ + int error, needed_blocks; + handle_t *handle; + struct ext4_iloc iloc; + + if (!ext4_has_inline_data(inode)) { + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + return 0; + } + + needed_blocks = ext4_writepage_trans_blocks(inode); + + iloc.bh = NULL; + error = ext4_get_inode_loc(inode, &iloc); + if (error) + return error; + + handle = ext4_journal_start(inode, needed_blocks); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + goto out_free; + } + + down_write(&EXT4_I(inode)->xattr_sem); + if (!ext4_has_inline_data(inode)) { + up_write(&EXT4_I(inode)->xattr_sem); + goto out; + } + + error = ext4_convert_inline_data_nolock(handle, inode, &iloc); + up_write(&EXT4_I(inode)->xattr_sem); +out: + ext4_journal_stop(handle); +out_free: + brelse(iloc.bh); + return error; +} diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 02bc8cbe728..cbfe13bf5b2 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -233,6 +233,11 @@ void ext4_evict_inode(struct inode *inode) if (is_bad_inode(inode)) goto no_delete; + /* + * Protect us against freezing - iput() caller didn't have to have any + * protection against it + */ + sb_start_intwrite(inode->i_sb); handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); @@ -242,6 +247,7 @@ void ext4_evict_inode(struct inode *inode) * cleaned up. */ ext4_orphan_del(NULL, inode); + sb_end_intwrite(inode->i_sb); goto no_delete; } @@ -273,6 +279,7 @@ void ext4_evict_inode(struct inode *inode) stop_handle: ext4_journal_stop(handle); ext4_orphan_del(NULL, inode); + sb_end_intwrite(inode->i_sb); goto no_delete; } } @@ -301,6 +308,7 @@ void ext4_evict_inode(struct inode *inode) else ext4_free_inode(handle, inode); ext4_journal_stop(handle); + sb_end_intwrite(inode->i_sb); return; no_delete: ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ @@ -346,6 +354,15 @@ void ext4_da_update_reserve_space(struct inode *inode, used = ei->i_reserved_data_blocks; } + if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) { + ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d " + "with only %d reserved metadata blocks\n", __func__, + inode->i_ino, ei->i_allocated_meta_blocks, + ei->i_reserved_meta_blocks); + WARN_ON(1); + ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks; + } + /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks; @@ -467,49 +484,6 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx, } /* - * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map. - */ -static void set_buffers_da_mapped(struct inode *inode, - struct ext4_map_blocks *map) -{ - struct address_space *mapping = inode->i_mapping; - struct pagevec pvec; - int i, nr_pages; - pgoff_t index, end; - - index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits); - end = (map->m_lblk + map->m_len - 1) >> - (PAGE_CACHE_SHIFT - inode->i_blkbits); - - pagevec_init(&pvec, 0); - while (index <= end) { - nr_pages = pagevec_lookup(&pvec, mapping, index, - min(end - index + 1, - (pgoff_t)PAGEVEC_SIZE)); - if (nr_pages == 0) - break; - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; - struct buffer_head *bh, *head; - - if (unlikely(page->mapping != mapping) || - !PageDirty(page)) - break; - - if (page_has_buffers(page)) { - bh = head = page_buffers(page); - do { - set_buffer_da_mapped(bh); - bh = bh->b_this_page; - } while (bh != head); - } - index++; - } - pagevec_release(&pvec); - } -} - -/* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. * @@ -544,7 +518,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, * 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 (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) + down_read((&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); @@ -552,10 +527,20 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, retval = ext4_ind_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } - up_read((&EXT4_I(inode)->i_data_sem)); + if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) + up_read((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { - int ret = check_block_validity(inode, map); + int ret; + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { + /* delayed alloc may be allocated by fallocate and + * coverted to initialized by directIO. + * we need to handle delayed extent here. + */ + down_write((&EXT4_I(inode)->i_data_sem)); + goto delayed_mapped; + } + ret = check_block_validity(inode, map); if (ret != 0) return ret; } @@ -633,12 +618,15 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED); - /* If we have successfully mapped the delayed allocated blocks, - * set the BH_Da_Mapped bit on them. Its important to do this - * under the protection of i_data_sem. - */ - if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) - set_buffers_da_mapped(inode, map); + if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { + int ret; +delayed_mapped: + /* delayed allocation blocks has been allocated */ + ret = ext4_es_remove_extent(inode, map->m_lblk, + map->m_len); + if (ret < 0) + retval = ret; + } } up_write((&EXT4_I(inode)->i_data_sem)); @@ -661,10 +649,13 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, int ret = 0, started = 0; int dio_credits; + if (ext4_has_inline_data(inode)) + return -ERANGE; + map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; - if (flags && !handle) { + if (flags && !(flags & EXT4_GET_BLOCKS_NO_LOCK) && !handle) { /* Direct IO write... */ if (map.m_len > DIO_MAX_BLOCKS) map.m_len = DIO_MAX_BLOCKS; @@ -713,11 +704,13 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, err = ext4_map_blocks(handle, inode, &map, create ? EXT4_GET_BLOCKS_CREATE : 0); + /* ensure we send some value back into *errp */ + *errp = 0; + if (err < 0) *errp = err; if (err <= 0) return NULL; - *errp = 0; bh = sb_getblk(inode->i_sb, map.m_pblk); if (!bh) { @@ -777,13 +770,13 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, return NULL; } -static int walk_page_buffers(handle_t *handle, - struct buffer_head *head, - unsigned from, - unsigned to, - int *partial, - int (*fn)(handle_t *handle, - struct buffer_head *bh)) +int ext4_walk_page_buffers(handle_t *handle, + struct buffer_head *head, + unsigned from, + unsigned to, + int *partial, + int (*fn)(handle_t *handle, + struct buffer_head *bh)) { struct buffer_head *bh; unsigned block_start, block_end; @@ -833,8 +826,8 @@ static int walk_page_buffers(handle_t *handle, * is elevated. We'll still have enough credits for the tiny quotafile * write. */ -static int do_journal_get_write_access(handle_t *handle, - struct buffer_head *bh) +int do_journal_get_write_access(handle_t *handle, + struct buffer_head *bh) { int dirty = buffer_dirty(bh); int ret; @@ -857,7 +850,7 @@ static int do_journal_get_write_access(handle_t *handle, return ret; } -static int ext4_get_block_write(struct inode *inode, sector_t iblock, +static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, @@ -881,6 +874,17 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; + if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { + ret = ext4_try_to_write_inline_data(mapping, inode, pos, len, + flags, pagep); + if (ret < 0) + goto out; + if (ret == 1) { + ret = 0; + goto out; + } + } + retry: handle = ext4_journal_start(inode, needed_blocks); if (IS_ERR(handle)) { @@ -898,6 +902,7 @@ retry: ret = -ENOMEM; goto out; } + *pagep = page; if (ext4_should_dioread_nolock(inode)) @@ -906,8 +911,9 @@ retry: ret = __block_write_begin(page, pos, len, ext4_get_block); if (!ret && ext4_should_journal_data(inode)) { - ret = walk_page_buffers(handle, page_buffers(page), - from, to, NULL, do_journal_get_write_access); + ret = ext4_walk_page_buffers(handle, page_buffers(page), + from, to, NULL, + do_journal_get_write_access); } if (ret) { @@ -962,7 +968,12 @@ static int ext4_generic_write_end(struct file *file, struct inode *inode = mapping->host; handle_t *handle = ext4_journal_current_handle(); - copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + if (ext4_has_inline_data(inode)) + copied = ext4_write_inline_data_end(inode, pos, len, + copied, page); + else + copied = block_write_end(file, mapping, pos, + len, copied, page, fsdata); /* * No need to use i_size_read() here, the i_size @@ -1113,16 +1124,21 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (copied < len) { - if (!PageUptodate(page)) - copied = 0; - page_zero_new_buffers(page, from+copied, to); - } + if (ext4_has_inline_data(inode)) + copied = ext4_write_inline_data_end(inode, pos, len, + copied, page); + else { + if (copied < len) { + if (!PageUptodate(page)) + copied = 0; + page_zero_new_buffers(page, from+copied, to); + } - ret = walk_page_buffers(handle, page_buffers(page), from, - to, &partial, write_end_fn); - if (!partial) - SetPageUptodate(page); + ret = ext4_walk_page_buffers(handle, page_buffers(page), from, + to, &partial, write_end_fn); + if (!partial) + SetPageUptodate(page); + } new_i_size = pos + copied; if (new_i_size > inode->i_size) i_size_write(inode, pos+copied); @@ -1171,6 +1187,17 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) struct ext4_inode_info *ei = EXT4_I(inode); unsigned int md_needed; int ret; + ext4_lblk_t save_last_lblock; + int save_len; + + /* + * We will charge metadata quota at writeout time; this saves + * us from metadata over-estimation, though we may go over by + * a small amount in the end. Here we just reserve for data. + */ + ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); + if (ret) + return ret; /* * recalculate the amount of metadata blocks to reserve @@ -1179,32 +1206,31 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) */ repeat: spin_lock(&ei->i_block_reservation_lock); + /* + * ext4_calc_metadata_amount() has side effects, which we have + * to be prepared undo if we fail to claim space. + */ + save_len = ei->i_da_metadata_calc_len; + save_last_lblock = ei->i_da_metadata_calc_last_lblock; md_needed = EXT4_NUM_B2C(sbi, ext4_calc_metadata_amount(inode, lblock)); trace_ext4_da_reserve_space(inode, md_needed); - spin_unlock(&ei->i_block_reservation_lock); /* - * We will charge metadata quota at writeout time; this saves - * us from metadata over-estimation, though we may go over by - * a small amount in the end. Here we just reserve for data. - */ - ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); - if (ret) - return ret; - /* * We do still charge estimated metadata to the sb though; * we cannot afford to run out of free blocks. */ if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) { - dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); + ei->i_da_metadata_calc_len = save_len; + ei->i_da_metadata_calc_last_lblock = save_last_lblock; + spin_unlock(&ei->i_block_reservation_lock); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { yield(); goto repeat; } + dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); return -ENOSPC; } - spin_lock(&ei->i_block_reservation_lock); ei->i_reserved_data_blocks++; ei->i_reserved_meta_blocks += md_needed; spin_unlock(&ei->i_block_reservation_lock); @@ -1270,6 +1296,7 @@ static void ext4_da_page_release_reservation(struct page *page, struct inode *inode = page->mapping->host; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int num_clusters; + ext4_fsblk_t lblk; head = page_buffers(page); bh = head; @@ -1279,20 +1306,23 @@ static void ext4_da_page_release_reservation(struct page *page, if ((offset <= curr_off) && (buffer_delay(bh))) { to_release++; clear_buffer_delay(bh); - clear_buffer_da_mapped(bh); } curr_off = next_off; } while ((bh = bh->b_this_page) != head); + if (to_release) { + lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + ext4_es_remove_extent(inode, lblk, to_release); + } + /* If we have released all the blocks belonging to a cluster, then we * need to release the reserved space for that cluster. */ num_clusters = EXT4_NUM_B2C(sbi, to_release); while (num_clusters > 0) { - ext4_fsblk_t lblk; lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) + ((num_clusters - 1) << sbi->s_cluster_bits); if (sbi->s_cluster_ratio == 1 || - !ext4_find_delalloc_cluster(inode, lblk, 1)) + !ext4_find_delalloc_cluster(inode, lblk)) ext4_da_release_space(inode, 1); num_clusters--; @@ -1398,8 +1428,6 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, clear_buffer_delay(bh); bh->b_blocknr = pblock; } - if (buffer_da_mapped(bh)) - clear_buffer_da_mapped(bh); if (buffer_unwritten(bh) || buffer_mapped(bh)) BUG_ON(bh->b_blocknr != pblock); @@ -1469,9 +1497,16 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd) struct pagevec pvec; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; + ext4_lblk_t start, last; index = mpd->first_page; end = mpd->next_page - 1; + + start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits); + ext4_es_remove_extent(inode, start, last - start + 1); + + pagevec_init(&pvec, 0); while (index <= end) { nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); if (nr_pages == 0) @@ -1625,15 +1660,6 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) for (i = 0; i < map.m_len; i++) unmap_underlying_metadata(bdev, map.m_pblk + i); - - if (ext4_should_order_data(mpd->inode)) { - err = ext4_jbd2_file_inode(handle, mpd->inode); - if (err) { - /* Only if the journal is aborted */ - mpd->retval = err; - goto submit_io; - } - } } /* @@ -1764,7 +1790,19 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, * file system block. */ down_read((&EXT4_I(inode)->i_data_sem)); - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + if (ext4_has_inline_data(inode)) { + /* + * We will soon create blocks for this page, and let + * us pretend as if the blocks aren't allocated yet. + * In case of clusters, we have to handle the work + * of mapping from cluster so that the reserved space + * is calculated properly. + */ + if ((EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) && + ext4_find_delalloc_cluster(inode, map->m_lblk)) + map->m_flags |= EXT4_MAP_FROM_CLUSTER; + retval = 0; + } else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) retval = ext4_ext_map_blocks(NULL, inode, map, 0); else retval = ext4_ind_map_blocks(NULL, inode, map, 0); @@ -1783,6 +1821,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, goto out_unlock; } + retval = ext4_es_insert_extent(inode, map->m_lblk, map->m_len); + if (retval) + goto out_unlock; + /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served * and it should not appear on the bh->b_state. */ @@ -1811,8 +1853,8 @@ out_unlock: * 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, int create) +int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, + struct buffer_head *bh, int create) { struct ext4_map_blocks map; int ret = 0; @@ -1886,15 +1928,29 @@ static int __ext4_journalled_writepage(struct page *page, { struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; - struct buffer_head *page_bufs; + struct buffer_head *page_bufs = NULL; handle_t *handle = NULL; - int ret = 0; - int err; + int ret = 0, err = 0; + int inline_data = ext4_has_inline_data(inode); + struct buffer_head *inode_bh = NULL; ClearPageChecked(page); - page_bufs = page_buffers(page); - BUG_ON(!page_bufs); - walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); + + if (inline_data) { + BUG_ON(page->index != 0); + BUG_ON(len > ext4_get_max_inline_size(inode)); + inode_bh = ext4_journalled_write_inline_data(inode, len, page); + if (inode_bh == NULL) + goto out; + } else { + page_bufs = page_buffers(page); + if (!page_bufs) { + BUG(); + goto out; + } + ext4_walk_page_buffers(handle, page_bufs, 0, len, + NULL, bget_one); + } /* As soon as we unlock the page, it can go away, but we have * references to buffers so we are safe */ unlock_page(page); @@ -1907,11 +1963,18 @@ static int __ext4_journalled_writepage(struct page *page, BUG_ON(!ext4_handle_valid(handle)); - ret = walk_page_buffers(handle, page_bufs, 0, len, NULL, - do_journal_get_write_access); + if (inline_data) { + ret = ext4_journal_get_write_access(handle, inode_bh); + + err = ext4_handle_dirty_metadata(handle, inode, inode_bh); - err = walk_page_buffers(handle, page_bufs, 0, len, NULL, - write_end_fn); + } else { + ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, + do_journal_get_write_access); + + err = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, + write_end_fn); + } if (ret == 0) ret = err; EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; @@ -1919,15 +1982,15 @@ static int __ext4_journalled_writepage(struct page *page, if (!ret) ret = err; - walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one); + if (!ext4_has_inline_data(inode)) + ext4_walk_page_buffers(handle, page_bufs, 0, len, + NULL, bput_one); ext4_set_inode_state(inode, EXT4_STATE_JDATA); out: + brelse(inode_bh); return ret; } -static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode); -static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); - /* * Note that we don't need to start a transaction unless we're journaling data * because we should have holes filled from ext4_page_mkwrite(). We even don't @@ -1941,7 +2004,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); * 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) + * - shrink_page_list via the kswapd/direct reclaim (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) * * We don't do any block allocation in this function. If we have page with @@ -2001,8 +2064,8 @@ static int ext4_writepage(struct page *page, commit_write = 1; } page_bufs = page_buffers(page); - if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, - ext4_bh_delay_or_unwritten)) { + if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL, + ext4_bh_delay_or_unwritten)) { /* * We don't want to do block allocation, so redirty * the page and return. We may reach here when we do @@ -2068,7 +2131,8 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode) * mpage_da_map_and_submit to map a single contiguous memory region * and then write them. */ -static int write_cache_pages_da(struct address_space *mapping, +static int write_cache_pages_da(handle_t *handle, + struct address_space *mapping, struct writeback_control *wbc, struct mpage_da_data *mpd, pgoff_t *done_index) @@ -2147,6 +2211,17 @@ static int write_cache_pages_da(struct address_space *mapping, wait_on_page_writeback(page); BUG_ON(PageWriteback(page)); + /* + * If we have inline data and arrive here, it means that + * we will soon create the block for the 1st page, so + * we'd better clear the inline data here. + */ + if (ext4_has_inline_data(inode)) { + BUG_ON(ext4_test_inode_state(inode, + EXT4_STATE_MAY_INLINE_DATA)); + ext4_destroy_inline_data(handle, inode); + } + if (mpd->next_page != page->index) mpd->first_page = page->index; mpd->next_page = page->index + 1; @@ -2353,7 +2428,8 @@ retry: * contiguous region of logical blocks that need * blocks to be allocated by ext4 and submit them. */ - ret = write_cache_pages_da(mapping, wbc, &mpd, &done_index); + ret = write_cache_pages_da(handle, mapping, + wbc, &mpd, &done_index); /* * If we have a contiguous extent of pages and we * haven't done the I/O yet, map the blocks and submit @@ -2417,7 +2493,6 @@ out_writepages: return ret; } -#define FALL_BACK_TO_NONDELALLOC 1 static int ext4_nonda_switch(struct super_block *sb) { s64 free_blocks, dirty_blocks; @@ -2434,6 +2509,16 @@ static int ext4_nonda_switch(struct super_block *sb) free_blocks = EXT4_C2B(sbi, percpu_counter_read_positive(&sbi->s_freeclusters_counter)); dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); + /* + * Start pushing delalloc when 1/2 of free blocks are dirty. + */ + if (dirty_blocks && (free_blocks < 2 * dirty_blocks) && + !writeback_in_progress(sb->s_bdi) && + down_read_trylock(&sb->s_umount)) { + writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE); + up_read(&sb->s_umount); + } + if (2 * free_blocks < 3 * dirty_blocks || free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) { /* @@ -2442,13 +2527,6 @@ static int ext4_nonda_switch(struct super_block *sb) */ return 1; } - /* - * Even if we don't switch but are nearing capacity, - * start pushing delalloc when 1/2 of free blocks are dirty. - */ - if (free_blocks < 2 * dirty_blocks) - writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE); - return 0; } @@ -2471,6 +2549,19 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, } *fsdata = (void *)0; trace_ext4_da_write_begin(inode, pos, len, flags); + + if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { + ret = ext4_da_write_inline_data_begin(mapping, inode, + pos, len, flags, + pagep, fsdata); + if (ret < 0) + goto out; + if (ret == 1) { + ret = 0; + goto out; + } + } + retry: /* * With delayed allocation, we don't log the i_disksize update @@ -2572,22 +2663,13 @@ static int ext4_da_write_end(struct file *file, * changes. So let's piggyback the i_disksize mark_inode_dirty * into that. */ - new_i_size = pos + copied; if (copied && new_i_size > EXT4_I(inode)->i_disksize) { - if (ext4_da_should_update_i_disksize(page, end)) { + if (ext4_has_inline_data(inode) || + ext4_da_should_update_i_disksize(page, end)) { down_write(&EXT4_I(inode)->i_data_sem); - if (new_i_size > EXT4_I(inode)->i_disksize) { - /* - * Updating i_disksize when extending file - * without needing block allocation - */ - if (ext4_should_order_data(inode)) - ret = ext4_jbd2_file_inode(handle, - inode); - + if (new_i_size > EXT4_I(inode)->i_disksize) EXT4_I(inode)->i_disksize = new_i_size; - } up_write(&EXT4_I(inode)->i_data_sem); /* We need to mark inode dirty even if * new_i_size is less that inode->i_size @@ -2596,8 +2678,16 @@ static int ext4_da_write_end(struct file *file, ext4_mark_inode_dirty(handle, inode); } } - ret2 = generic_write_end(file, mapping, pos, len, copied, + + if (write_mode != CONVERT_INLINE_DATA && + ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && + ext4_has_inline_data(inode)) + ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied, + page); + else + ret2 = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + copied = ret2; if (ret2 < 0) ret = ret2; @@ -2690,6 +2780,12 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) journal_t *journal; int err; + /* + * We can get here for an inline file via the FIBMAP ioctl + */ + if (ext4_has_inline_data(inode)) + return 0; + if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && test_opt(inode->i_sb, DELALLOC)) { /* @@ -2735,14 +2831,30 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) static int ext4_readpage(struct file *file, struct page *page) { + int ret = -EAGAIN; + struct inode *inode = page->mapping->host; + trace_ext4_readpage(page); - return mpage_readpage(page, ext4_get_block); + + if (ext4_has_inline_data(inode)) + ret = ext4_readpage_inline(inode, page); + + if (ret == -EAGAIN) + return mpage_readpage(page, ext4_get_block); + + return ret; } static int ext4_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { + struct inode *inode = mapping->host; + + /* If the file has inline data, no need to do readpages. */ + if (ext4_has_inline_data(inode)) + return 0; + return mpage_readpages(mapping, pages, nr_pages, ext4_get_block); } @@ -2768,8 +2880,6 @@ static void ext4_invalidatepage_free_endio(struct page *page, unsigned long offs static void ext4_invalidatepage(struct page *page, unsigned long offset) { - journal_t *journal = EXT4_JOURNAL(page->mapping->host); - trace_ext4_invalidatepage(page, offset); /* @@ -2777,16 +2887,34 @@ static void ext4_invalidatepage(struct page *page, unsigned long offset) */ if (ext4_should_dioread_nolock(page->mapping->host)) ext4_invalidatepage_free_endio(page, offset); + + /* No journalling happens on data buffers when this function is used */ + WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page))); + + block_invalidatepage(page, offset); +} + +static int __ext4_journalled_invalidatepage(struct page *page, + unsigned long offset) +{ + journal_t *journal = EXT4_JOURNAL(page->mapping->host); + + trace_ext4_journalled_invalidatepage(page, offset); + /* * If it's a full truncate we just forget about the pending dirtying */ if (offset == 0) ClearPageChecked(page); - if (journal) - jbd2_journal_invalidatepage(journal, page, offset); - else - block_invalidatepage(page, offset); + return jbd2_journal_invalidatepage(journal, page, offset); +} + +/* Wrapper for aops... */ +static void ext4_journalled_invalidatepage(struct page *page, + unsigned long offset) +{ + WARN_ON(__ext4_journalled_invalidatepage(page, offset) < 0); } static int ext4_releasepage(struct page *page, gfp_t wait) @@ -2809,7 +2937,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait) * We allocate an uinitialized extent if blocks haven't been allocated. * The extent will be converted to initialized after the IO is complete. */ -static int ext4_get_block_write(struct inode *inode, sector_t iblock, +int ext4_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n", @@ -2818,15 +2946,21 @@ static int ext4_get_block_write(struct inode *inode, sector_t iblock, EXT4_GET_BLOCKS_IO_CREATE_EXT); } +static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + ext4_debug("ext4_get_block_write_nolock: inode %lu, create flag %d\n", + inode->i_ino, create); + return _ext4_get_block(inode, iblock, bh_result, + EXT4_GET_BLOCKS_NO_LOCK); +} + static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private, int ret, bool is_async) { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; ext4_io_end_t *io_end = iocb->private; - struct workqueue_struct *wq; - unsigned long flags; - struct ext4_inode_info *ei; /* if not async direct IO or dio with 0 bytes write, just return */ if (!io_end || !size) @@ -2855,24 +2989,14 @@ out: io_end->iocb = iocb; io_end->result = ret; } - wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq; - - /* Add the io_end to per-inode completed aio dio list*/ - ei = EXT4_I(io_end->inode); - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - list_add_tail(&io_end->list, &ei->i_completed_io_list); - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - /* queue the work to convert unwritten extents to written */ - queue_work(wq, &io_end->work); + ext4_add_complete_io(io_end); } static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) { ext4_io_end_t *io_end = bh->b_private; - struct workqueue_struct *wq; struct inode *inode; - unsigned long flags; if (!test_clear_buffer_uninit(bh) || !io_end) goto out; @@ -2891,15 +3015,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) */ inode = io_end->inode; ext4_set_io_unwritten_flag(inode, io_end); - - /* Add the io_end to per-inode completed io list*/ - spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); - list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list); - spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); - - wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq; - /* queue the work to convert unwritten extents to written */ - queue_work(wq, &io_end->work); + ext4_add_complete_io(io_end); out: bh->b_private = NULL; bh->b_end_io = NULL; @@ -2942,10 +3058,10 @@ retry: * fall back to buffered IO. * * For holes, we fallocate those blocks, mark them as uninitialized - * If those blocks were preallocated, we mark sure they are splited, but + * If those blocks were preallocated, we mark sure they are split, but * still keep the range to write as uninitialized. * - * The unwrritten extents will be converted to written when DIO is completed. + * The unwritten extents will be converted to written when DIO is completed. * For async direct IO, since the IO may still pending when return, we * set up an end_io call back function, which will do the conversion * when async direct IO completed. @@ -2963,92 +3079,120 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, struct inode *inode = file->f_mapping->host; ssize_t ret; size_t count = iov_length(iov, nr_segs); - + int overwrite = 0; + get_block_t *get_block_func = NULL; + int dio_flags = 0; loff_t final_size = offset + count; - if (rw == WRITE && final_size <= inode->i_size) { - /* - * We could direct write to holes and fallocate. - * - * Allocated blocks to fill the hole are marked as uninitialized - * to prevent parallel buffered read to expose the stale data - * before DIO complete the data IO. - * - * As to previously fallocated extents, ext4 get_block - * will just simply mark the buffer mapped but still - * keep the extents uninitialized. - * - * for non AIO case, we will convert those unwritten extents - * to written after return back from blockdev_direct_IO. - * - * for async DIO, the conversion needs to be defered when - * the IO is completed. The ext4 end_io callback function - * will be called to take care of the conversion work. - * Here for async case, we allocate an io_end structure to - * hook to the iocb. - */ - iocb->private = NULL; - EXT4_I(inode)->cur_aio_dio = NULL; - if (!is_sync_kiocb(iocb)) { - ext4_io_end_t *io_end = - ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) - return -ENOMEM; - io_end->flag |= EXT4_IO_END_DIRECT; - iocb->private = io_end; - /* - * we save the io structure for current async - * direct IO, so that later ext4_map_blocks() - * could flag the io structure whether there - * is a unwritten extents needs to be converted - * when IO is completed. - */ - EXT4_I(inode)->cur_aio_dio = iocb->private; - } - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, - ext4_get_block_write, - ext4_end_io_dio, - NULL, - DIO_LOCKING); - if (iocb->private) - EXT4_I(inode)->cur_aio_dio = NULL; + /* Use the old path for reads and writes beyond i_size. */ + if (rw != WRITE || final_size > inode->i_size) + return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); + + BUG_ON(iocb->private == NULL); + + /* If we do a overwrite dio, i_mutex locking can be released */ + overwrite = *((int *)iocb->private); + + if (overwrite) { + atomic_inc(&inode->i_dio_count); + down_read(&EXT4_I(inode)->i_data_sem); + mutex_unlock(&inode->i_mutex); + } + + /* + * We could direct write to holes and fallocate. + * + * Allocated blocks to fill the hole are marked as + * uninitialized to prevent parallel buffered read to expose + * the stale data before DIO complete the data IO. + * + * As to previously fallocated extents, ext4 get_block will + * just simply mark the buffer mapped but still keep the + * extents uninitialized. + * + * For non AIO case, we will convert those unwritten extents + * to written after return back from blockdev_direct_IO. + * + * For async DIO, the conversion needs to be deferred when the + * IO is completed. The ext4 end_io callback function will be + * called to take care of the conversion work. Here for async + * case, we allocate an io_end structure to hook to the iocb. + */ + iocb->private = NULL; + ext4_inode_aio_set(inode, NULL); + if (!is_sync_kiocb(iocb)) { + ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_end) { + ret = -ENOMEM; + goto retake_lock; + } + io_end->flag |= EXT4_IO_END_DIRECT; + iocb->private = io_end; /* - * The io_end structure takes a reference to the inode, - * that structure needs to be destroyed and the - * reference to the inode need to be dropped, when IO is - * complete, even with 0 byte write, or failed. - * - * In the successful AIO DIO case, the io_end structure will be - * desctroyed and the reference to the inode will be dropped - * after the end_io call back function is called. - * - * In the case there is 0 byte write, or error case, since - * VFS direct IO won't invoke the end_io call back function, - * we need to free the end_io structure here. + * we save the io structure for current async direct + * IO, so that later ext4_map_blocks() could flag the + * io structure whether there is a unwritten extents + * needs to be converted when IO is completed. */ - if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) { - ext4_free_io_end(iocb->private); - iocb->private = NULL; - } else if (ret > 0 && ext4_test_inode_state(inode, + ext4_inode_aio_set(inode, io_end); + } + + if (overwrite) { + get_block_func = ext4_get_block_write_nolock; + } else { + get_block_func = ext4_get_block_write; + dio_flags = DIO_LOCKING; + } + ret = __blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iov, + offset, nr_segs, + get_block_func, + ext4_end_io_dio, + NULL, + dio_flags); + + if (iocb->private) + ext4_inode_aio_set(inode, NULL); + /* + * The io_end structure takes a reference to the inode, that + * structure needs to be destroyed and the reference to the + * inode need to be dropped, when IO is complete, even with 0 + * byte write, or failed. + * + * In the successful AIO DIO case, the io_end structure will + * be destroyed and the reference to the inode will be dropped + * after the end_io call back function is called. + * + * In the case there is 0 byte write, or error case, since VFS + * direct IO won't invoke the end_io call back function, we + * need to free the end_io structure here. + */ + if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) { + ext4_free_io_end(iocb->private); + iocb->private = NULL; + } else if (ret > 0 && !overwrite && ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN)) { - int err; - /* - * for non AIO case, since the IO is already - * completed, we could do the conversion right here - */ - err = ext4_convert_unwritten_extents(inode, - offset, ret); - if (err < 0) - ret = err; - ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); - } - return ret; + int err; + /* + * for non AIO case, since the IO is already + * completed, we could do the conversion right here + */ + err = ext4_convert_unwritten_extents(inode, + offset, ret); + if (err < 0) + ret = err; + ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); + } + +retake_lock: + /* take i_mutex locking again if we do a ovewrite dio */ + if (overwrite) { + inode_dio_done(inode); + up_read(&EXT4_I(inode)->i_data_sem); + mutex_lock(&inode->i_mutex); } - /* for write the the end of file case, we fall back to old way */ - return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); + return ret; } static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, @@ -3065,6 +3209,10 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, if (ext4_should_journal_data(inode)) return 0; + /* Let buffer I/O handle the inline data case. */ + if (ext4_has_inline_data(inode)) + return 0; + trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); @@ -3132,7 +3280,7 @@ static const struct address_space_operations ext4_journalled_aops = { .write_end = ext4_journalled_write_end, .set_page_dirty = ext4_journalled_set_page_dirty, .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, + .invalidatepage = ext4_journalled_invalidatepage, .releasepage = ext4_releasepage, .direct_IO = ext4_direct_IO, .is_partially_uptodate = block_is_partially_uptodate, @@ -3227,7 +3375,7 @@ int ext4_discard_partial_page_buffers(handle_t *handle, * handle: The journal handle * inode: The files inode * page: A locked page that contains the offset "from" - * from: The starting byte offset (from the begining of the file) + * from: The starting byte offset (from the beginning of the file) * to begin discarding * len: The length of bytes to discard * flags: Optional flags that may be used: @@ -3235,11 +3383,11 @@ int ext4_discard_partial_page_buffers(handle_t *handle, * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED * Only zero the regions of the page whose buffer heads * have already been unmapped. This flag is appropriate - * for updateing the contents of a page whose blocks may + * for updating the contents of a page whose blocks may * have already been released, and we only want to zero * out the regions that correspond to those released blocks. * - * Returns zero on sucess or negative on failure. + * Returns zero on success or negative on failure. */ static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, struct inode *inode, struct page *page, loff_t from, @@ -3400,7 +3548,7 @@ int ext4_can_truncate(struct inode *inode) * @offset: The offset where the hole will begin * @len: The length of the hole * - * Returns: 0 on sucess or negative on failure + * Returns: 0 on success or negative on failure */ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) @@ -3462,6 +3610,14 @@ void ext4_truncate(struct inode *inode) if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); + if (ext4_has_inline_data(inode)) { + int has_inline = 1; + + ext4_inline_data_truncate(inode, &has_inline); + if (has_inline) + return; + } + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ext4_ext_truncate(inode); else @@ -3687,6 +3843,19 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, } } +static inline void ext4_iget_extra_inode(struct inode *inode, + struct ext4_inode *raw_inode, + struct ext4_inode_info *ei) +{ + __le32 *magic = (void *)raw_inode + + EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; + if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { + ext4_set_inode_state(inode, EXT4_STATE_XATTR); + ext4_find_inline_data_nolock(inode); + } else + EXT4_I(inode)->i_inline_off = 0; +} + struct inode *ext4_iget(struct super_block *sb, unsigned long ino) { struct ext4_iloc iloc; @@ -3757,6 +3926,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ + ei->i_inline_off = 0; ei->i_dir_start_lookup = 0; ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); /* We now have enough fields to check if the inode was active or not. @@ -3829,11 +3999,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; } else { - __le32 *magic = (void *)raw_inode + - EXT4_GOOD_OLD_INODE_SIZE + - ei->i_extra_isize; - if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) - ext4_set_inode_state(inode, EXT4_STATE_XATTR); + ext4_iget_extra_inode(inode, raw_inode, ei); } } @@ -3856,17 +4022,19 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_file_acl); ret = -EIO; goto bad_inode; - } else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - (S_ISLNK(inode->i_mode) && - !ext4_inode_is_fast_symlink(inode))) - /* Validate extent which is part of inode */ - ret = ext4_ext_check_inode(inode); - } else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - (S_ISLNK(inode->i_mode) && - !ext4_inode_is_fast_symlink(inode))) { - /* Validate block references which are part of inode */ - ret = ext4_ind_check_inode(inode); + } else if (!ext4_has_inline_data(inode)) { + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + if ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + (S_ISLNK(inode->i_mode) && + !ext4_inode_is_fast_symlink(inode)))) + /* Validate extent which is part of inode */ + ret = ext4_ext_check_inode(inode); + } else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + (S_ISLNK(inode->i_mode) && + !ext4_inode_is_fast_symlink(inode))) { + /* Validate block references which are part of inode */ + ret = ext4_ind_check_inode(inode); + } } if (ret) goto bad_inode; @@ -3922,7 +4090,7 @@ static int ext4_inode_blocks_set(handle_t *handle, if (i_blocks <= ~0U) { /* - * i_blocks can be represnted in a 32 bit variable + * i_blocks can be represented in a 32 bit variable * as multiple of 512 bytes */ raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); @@ -3966,6 +4134,7 @@ static int ext4_do_update_inode(handle_t *handle, struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; int err = 0, rc, block; + int need_datasync = 0; uid_t i_uid; gid_t i_gid; @@ -4016,7 +4185,10 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - ext4_isize_set(raw_inode, ei->i_disksize); + if (ei->i_disksize != ext4_isize(raw_inode)) { + ext4_isize_set(raw_inode, ei->i_disksize); + need_datasync = 1; + } if (ei->i_disksize > 0x7fffffffULL) { struct super_block *sb = inode->i_sb; if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, @@ -4034,7 +4206,7 @@ static int ext4_do_update_inode(handle_t *handle, EXT4_SET_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_LARGE_FILE); ext4_handle_sync(handle); - err = ext4_handle_dirty_super_now(handle, sb); + err = ext4_handle_dirty_super(handle, sb); } } raw_inode->i_generation = cpu_to_le32(inode->i_generation); @@ -4049,9 +4221,10 @@ static int ext4_do_update_inode(handle_t *handle, cpu_to_le32(new_encode_dev(inode->i_rdev)); raw_inode->i_block[2] = 0; } - } else + } else if (!ext4_has_inline_data(inode)) { for (block = 0; block < EXT4_N_BLOCKS; block++) raw_inode->i_block[block] = ei->i_data[block]; + } raw_inode->i_disk_version = cpu_to_le32(inode->i_version); if (ei->i_extra_isize) { @@ -4069,7 +4242,7 @@ static int ext4_do_update_inode(handle_t *handle, err = rc; ext4_clear_inode_state(inode, EXT4_STATE_NEW); - ext4_update_inode_fsync_trans(handle, inode, 0); + ext4_update_inode_fsync_trans(handle, inode, need_datasync); out_brelse: brelse(bh); ext4_std_error(inode->i_sb, err); @@ -4083,7 +4256,7 @@ out_brelse: * * - Within generic_file_write() for O_SYNC files. * Here, there will be no transaction running. We wait for any running - * trasnaction to commit. + * transaction to commit. * * - Within sys_sync(), kupdate and such. * We wait on commit, if tol to. @@ -4148,6 +4321,47 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) } /* + * In data=journal mode ext4_journalled_invalidatepage() may fail to invalidate + * buffers that are attached to a page stradding i_size and are undergoing + * commit. In that case we have to wait for commit to finish and try again. + */ +static void ext4_wait_for_tail_page_commit(struct inode *inode) +{ + struct page *page; + unsigned offset; + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; + tid_t commit_tid = 0; + int ret; + + offset = inode->i_size & (PAGE_CACHE_SIZE - 1); + /* + * All buffers in the last page remain valid? Then there's nothing to + * do. We do the check mainly to optimize the common PAGE_CACHE_SIZE == + * blocksize case + */ + if (offset > PAGE_CACHE_SIZE - (1 << inode->i_blkbits)) + return; + while (1) { + page = find_lock_page(inode->i_mapping, + inode->i_size >> PAGE_CACHE_SHIFT); + if (!page) + return; + ret = __ext4_journalled_invalidatepage(page, offset); + unlock_page(page); + page_cache_release(page); + if (ret != -EBUSY) + return; + commit_tid = 0; + read_lock(&journal->j_state_lock); + if (journal->j_committing_transaction) + commit_tid = journal->j_committing_transaction->t_tid; + read_unlock(&journal->j_state_lock); + if (commit_tid) + jbd2_log_wait_commit(journal, commit_tid); + } +} + +/* * ext4_setattr() * * Called from notify_change. @@ -4212,7 +4426,6 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid & ATTR_SIZE) { - inode_dio_wait(inode); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -4261,8 +4474,29 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid & ATTR_SIZE) { - if (attr->ia_size != i_size_read(inode)) - truncate_setsize(inode, attr->ia_size); + if (attr->ia_size != inode->i_size) { + loff_t oldsize = inode->i_size; + + i_size_write(inode, attr->ia_size); + /* + * Blocks are going to be removed from the inode. Wait + * for dio in flight. Temporarily disable + * dioread_nolock to prevent livelock. + */ + if (orphan) { + if (!ext4_should_journal_data(inode)) { + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + ext4_inode_resume_unlocked_dio(inode); + } else + ext4_wait_for_tail_page_commit(inode); + } + /* + * Truncate pagecache after we've waited for commit + * in data=journal mode to make pages freeable. + */ + truncate_pagecache(inode, oldsize, inode->i_size); + } ext4_truncate(inode); } @@ -4327,7 +4561,7 @@ static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) * worse case, the indexs blocks spread over different block groups * * If datablocks are discontiguous, they are possible to spread over - * different block groups too. If they are contiuguous, with flexbg, + * different block groups too. If they are contiguous, with flexbg, * they could still across block group boundary. * * Also account for superblock, inode, quota and xattr blocks @@ -4503,14 +4737,6 @@ static int ext4_expand_extra_isize(struct inode *inode, * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. - * - * Is this efficient/effective? Well, we're being nice to the system - * by cleaning up our inodes proactively so they can be reaped - * without I/O. But we are potentially leaving up to five seconds' - * worth of inodes floating about which prune_icache wants us to - * write out. One way to fix that would be to get prune_icache() - * to do a write_super() to free up some memory. It has the desired - * effect. */ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) { @@ -4649,6 +4875,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) return err; } + /* Wait for all existing dio workers */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + jbd2_journal_lock_updates(journal); /* @@ -4668,6 +4898,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); + ext4_inode_resume_unlocked_dio(inode); /* Finally we can mark the inode as dirty. */ @@ -4701,11 +4932,8 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) get_block_t *get_block; int retries = 0; - /* - * This check is racy but catches the common case. We rely on - * __block_page_mkwrite() to do a reliable check. - */ - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && @@ -4736,8 +4964,9 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) * journal_start/journal_stop which can block and take a long time */ if (page_has_buffers(page)) { - if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped)) { + if (!ext4_walk_page_buffers(NULL, page_buffers(page), + 0, len, NULL, + ext4_bh_unmapped)) { /* Wait so that we don't change page under IO */ wait_on_page_writeback(page); ret = VM_FAULT_LOCKED; @@ -4758,7 +4987,7 @@ retry_alloc: } ret = __block_page_mkwrite(vma, vmf, get_block); if (!ret && ext4_should_journal_data(inode)) { - if (walk_page_buffers(handle, page_buffers(page), 0, + if (ext4_walk_page_buffers(handle, page_buffers(page), 0, PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) { unlock_page(page); ret = VM_FAULT_SIGBUS; @@ -4773,5 +5002,6 @@ retry_alloc: out_ret: ret = block_page_mkwrite_return(ret); out: + sb_end_pagefault(inode->i_sb); return ret; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 6ec6f9ee2fe..5747f52f7c7 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -233,7 +233,7 @@ group_extend_out: case EXT4_IOC_MOVE_EXT: { struct move_extent me; - struct file *donor_filp; + struct fd donor; int err; if (!(filp->f_mode & FMODE_READ) || @@ -245,11 +245,11 @@ group_extend_out: return -EFAULT; me.moved_len = 0; - donor_filp = fget(me.donor_fd); - if (!donor_filp) + donor = fdget(me.donor_fd); + if (!donor.file) return -EBADF; - if (!(donor_filp->f_mode & FMODE_WRITE)) { + if (!(donor.file->f_mode & FMODE_WRITE)) { err = -EBADF; goto mext_out; } @@ -258,14 +258,15 @@ group_extend_out: EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { ext4_msg(sb, KERN_ERR, "Online defrag not supported with bigalloc"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto mext_out; } err = mnt_want_write_file(filp); if (err) goto mext_out; - err = ext4_move_extents(filp, donor_filp, me.orig_start, + err = ext4_move_extents(filp, donor.file, me.orig_start, me.donor_start, me.len, &me.moved_len); mnt_drop_write_file(filp); @@ -273,7 +274,7 @@ group_extend_out: &me, sizeof(me))) err = -EFAULT; mext_out: - fput(donor_filp); + fdput(donor); return err; } @@ -365,31 +366,16 @@ group_add_out: return -EOPNOTSUPP; } - if (EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_META_BG)) { - ext4_msg(sb, KERN_ERR, - "Online resizing not (yet) supported with meta_bg"); - return -EOPNOTSUPP; - } - if (copy_from_user(&n_blocks_count, (__u64 __user *)arg, sizeof(__u64))) { return -EFAULT; } - if (n_blocks_count > MAX_32_NUM && - !EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_64BIT)) { - ext4_msg(sb, KERN_ERR, - "File system only supports 32-bit block numbers"); - return -EOPNOTSUPP; - } - err = ext4_resize_begin(sb); if (err) return err; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) goto resizefs_out; @@ -401,7 +387,7 @@ group_add_out: } if (err == 0) err = err2; - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); resizefs_out: ext4_resize_end(sb); return err; @@ -419,13 +405,6 @@ resizefs_out: if (!blk_queue_discard(q)) return -EOPNOTSUPP; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { - ext4_msg(sb, KERN_ERR, - "FITRIM not supported with bigalloc"); - return -EOPNOTSUPP; - } - if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 1cd6994fc44..1bf6fe785c4 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -24,6 +24,7 @@ #include "ext4_jbd2.h" #include "mballoc.h" #include <linux/debugfs.h> +#include <linux/log2.h> #include <linux/slab.h> #include <trace/events/ext4.h> @@ -969,7 +970,6 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, block++; pnum = block / blocks_per_page; - poff = block % blocks_per_page; page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); if (!page) return -EIO; @@ -1339,17 +1339,17 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); } -static int mb_find_extent(struct ext4_buddy *e4b, int order, int block, +static int mb_find_extent(struct ext4_buddy *e4b, int block, int needed, struct ext4_free_extent *ex) { int next = block; - int max; + int max, order; void *buddy; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); BUG_ON(ex == NULL); - buddy = mb_find_buddy(e4b, order, &max); + buddy = mb_find_buddy(e4b, 0, &max); BUG_ON(buddy == NULL); BUG_ON(block >= max); if (mb_test_bit(block, buddy)) { @@ -1359,12 +1359,9 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block, return 0; } - /* FIXME dorp order completely ? */ - if (likely(order == 0)) { - /* find actual order */ - order = mb_find_order_for_block(e4b, block); - block = block >> order; - } + /* find actual order */ + order = mb_find_order_for_block(e4b, block); + block = block >> order; ex->fe_len = 1 << order; ex->fe_start = block << order; @@ -1376,7 +1373,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block, ex->fe_start += next; while (needed > ex->fe_len && - (buddy = mb_find_buddy(e4b, order, &max))) { + mb_find_buddy(e4b, order, &max)) { if (block + 1 >= max) break; @@ -1550,7 +1547,7 @@ static void ext4_mb_check_limits(struct ext4_allocation_context *ac, /* recheck chunk's availability - we don't know * when it was found (within this lock-unlock * period or not) */ - max = mb_find_extent(e4b, 0, bex->fe_start, gex->fe_len, &ex); + max = mb_find_extent(e4b, bex->fe_start, gex->fe_len, &ex); if (max >= gex->fe_len) { ext4_mb_use_best_found(ac, e4b); return; @@ -1642,7 +1639,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, return err; ext4_lock_group(ac->ac_sb, group); - max = mb_find_extent(e4b, 0, ex.fe_start, ex.fe_len, &ex); + max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { ac->ac_b_ex = ex; @@ -1663,17 +1660,20 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, int max; int err; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); + struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL)) return 0; + if (grp->bb_free == 0) + return 0; err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return err; ext4_lock_group(ac->ac_sb, group); - max = mb_find_extent(e4b, 0, ac->ac_g_ex.fe_start, + max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) { @@ -1789,7 +1789,7 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, break; } - mb_find_extent(e4b, 0, i, ac->ac_g_ex.fe_len, &ex); + mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex); BUG_ON(ex.fe_len <= 0); if (free < ex.fe_len) { ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, @@ -1841,7 +1841,7 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, while (i < EXT4_CLUSTERS_PER_GROUP(sb)) { if (!mb_test_bit(i, bitmap)) { - max = mb_find_extent(e4b, 0, i, sbi->s_stripe, &ex); + max = mb_find_extent(e4b, i, sbi->s_stripe, &ex); if (max >= sbi->s_stripe) { ac->ac_found++; ac->ac_b_ex = ex; @@ -1863,6 +1863,12 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); + free = grp->bb_free; + if (free == 0) + return 0; + if (cr <= 2 && free < ac->ac_g_ex.fe_len) + return 0; + /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { int ret = ext4_mb_init_group(ac->ac_sb, group); @@ -1870,10 +1876,7 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, return 0; } - free = grp->bb_free; fragments = grp->bb_fragments; - if (free == 0) - return 0; if (fragments == 0) return 0; @@ -2077,8 +2080,9 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) struct super_block *sb = seq->private; ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i; - int err; + int err, buddy_loaded = 0; struct ext4_buddy e4b; + struct ext4_group_info *grinfo; struct sg { struct ext4_group_info info; ext4_grpblk_t counters[16]; @@ -2095,15 +2099,21 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + sizeof(struct ext4_group_info); - err = ext4_mb_load_buddy(sb, group, &e4b); - if (err) { - seq_printf(seq, "#%-5u: I/O error\n", group); - return 0; + grinfo = ext4_get_group_info(sb, group); + /* Load the group info in memory only if not already loaded. */ + if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { + err = ext4_mb_load_buddy(sb, group, &e4b); + if (err) { + seq_printf(seq, "#%-5u: I/O error\n", group); + return 0; + } + buddy_loaded = 1; } - ext4_lock_group(sb, group); + memcpy(&sg, ext4_get_group_info(sb, group), i); - ext4_unlock_group(sb, group); - ext4_mb_unload_buddy(&e4b); + + if (buddy_loaded) + ext4_mb_unload_buddy(&e4b); seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free, sg.info.bb_fragments, sg.info.bb_first_free); @@ -2157,6 +2167,39 @@ static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) return cachep; } +/* + * Allocate the top-level s_group_info array for the specified number + * of groups + */ +int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + unsigned size; + struct ext4_group_info ***new_groupinfo; + + size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> + EXT4_DESC_PER_BLOCK_BITS(sb); + if (size <= sbi->s_group_info_size) + return 0; + + size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size); + new_groupinfo = ext4_kvzalloc(size, GFP_KERNEL); + if (!new_groupinfo) { + ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); + return -ENOMEM; + } + if (sbi->s_group_info) { + memcpy(new_groupinfo, sbi->s_group_info, + sbi->s_group_info_size * sizeof(*sbi->s_group_info)); + ext4_kvfree(sbi->s_group_info); + } + sbi->s_group_info = new_groupinfo; + sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); + ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", + sbi->s_group_info_size); + return 0; +} + /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc) @@ -2189,12 +2232,11 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]; i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); - meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL); + meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_KERNEL); if (meta_group_info[i] == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate buddy mem"); goto exit_group_info; } - memset(meta_group_info[i], 0, kmem_cache_size(cachep)); set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(meta_group_info[i]->bb_state)); @@ -2246,49 +2288,14 @@ static int ext4_mb_init_backend(struct super_block *sb) ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_super_block *es = sbi->s_es; - int num_meta_group_infos; - int num_meta_group_infos_max; - int array_size; + int err; struct ext4_group_desc *desc; struct kmem_cache *cachep; - /* This is the number of blocks used by GDT */ - num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); - - /* - * This is the total number of blocks used by GDT including - * the number of reserved blocks for GDT. - * The s_group_info array is allocated with this value - * to allow a clean online resize without a complex - * manipulation of pointer. - * The drawback is the unused memory when no resize - * occurs but it's very low in terms of pages - * (see comments below) - * Need to handle this properly when META_BG resizing is allowed - */ - num_meta_group_infos_max = num_meta_group_infos + - le16_to_cpu(es->s_reserved_gdt_blocks); + err = ext4_mb_alloc_groupinfo(sb, ngroups); + if (err) + return err; - /* - * array_size is the size of s_group_info array. We round it - * to the next power of two because this approximation is done - * internally by kmalloc so we can have some more memory - * for free here (e.g. may be used for META_BG resize). - */ - array_size = 1; - while (array_size < sizeof(*sbi->s_group_info) * - num_meta_group_infos_max) - array_size = array_size << 1; - /* An 8TB filesystem with 64-bit pointers requires a 4096 byte - * kmalloc. A 128kb malloc should suffice for a 256TB filesystem. - * So a two level scheme suffices for now. */ - sbi->s_group_info = ext4_kvzalloc(array_size, GFP_KERNEL); - if (sbi->s_group_info == NULL) { - ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); - return -ENOMEM; - } sbi->s_buddy_cache = new_inode(sb); if (sbi->s_buddy_cache == NULL) { ext4_msg(sb, KERN_ERR, "can't get new inode"); @@ -2316,7 +2323,7 @@ err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); while (i-- > 0) kmem_cache_free(cachep, ext4_get_group_info(sb, i)); - i = num_meta_group_infos; + i = sbi->s_group_info_size; while (i-- > 0) kfree(sbi->s_group_info[i]); iput(sbi->s_buddy_cache); @@ -2600,9 +2607,17 @@ static void ext4_free_data_callback(struct super_block *sb, mb_debug(1, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); - if (test_opt(sb, DISCARD)) - ext4_issue_discard(sb, entry->efd_group, - entry->efd_start_cluster, entry->efd_count); + if (test_opt(sb, DISCARD)) { + err = ext4_issue_discard(sb, entry->efd_group, + entry->efd_start_cluster, + entry->efd_count); + if (err && err != -EOPNOTSUPP) + ext4_msg(sb, KERN_WARNING, "discard request in" + " group:%d block:%d count:%d failed" + " with %d", entry->efd_group, + entry->efd_start_cluster, + entry->efd_count, err); + } err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); /* we expect to find existing buddy because it's pinned */ @@ -2798,8 +2813,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, } len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len; ext4_free_group_clusters_set(sb, gdp, len); - ext4_block_bitmap_csum_set(sb, ac->ac_b_ex.fe_group, gdp, bitmap_bh, - EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_block_bitmap_csum_set(sb, ac->ac_b_ex.fe_group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, ac->ac_b_ex.fe_group, gdp); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); @@ -2825,7 +2839,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); out_err: - ext4_mark_super_dirty(sb); brelse(bitmap_bh); return err; } @@ -4003,7 +4016,6 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ - memset(ac, 0, sizeof(struct ext4_allocation_context)); ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1); ac->ac_status = AC_STATUS_CONTINUE; ac->ac_sb = sb; @@ -4286,7 +4298,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, } } - ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); + ac = kmem_cache_zalloc(ext4_ac_cachep, GFP_NOFS); if (!ac) { ar->len = 0; *errp = -ENOMEM; @@ -4306,8 +4318,10 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, repeat: /* allocate space in core */ *errp = ext4_mb_regular_allocator(ac); - if (*errp) + if (*errp) { + ext4_discard_allocated_blocks(ac); goto errout; + } /* as we've just preallocated more space than * user requested orinally, we store allocated @@ -4329,10 +4343,10 @@ repeat: ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; goto repeat; - } else if (*errp) - errout: + } else if (*errp) { ext4_discard_allocated_blocks(ac); - else { + goto errout; + } else { block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); ar->len = ac->ac_b_ex.fe_len; } @@ -4343,6 +4357,7 @@ repeat: *errp = -ENOSPC; } +errout: if (*errp) { ac->ac_b_ex.fe_len = 0; ar->len = 0; @@ -4652,6 +4667,16 @@ do_more: * with group lock held. generate_buddy look at * them with group lock_held */ + if (test_opt(sb, DISCARD)) { + err = ext4_issue_discard(sb, block_group, bit, count); + if (err && err != -EOPNOTSUPP) + ext4_msg(sb, KERN_WARNING, "discard request in" + " group:%d block:%d count:%lu failed" + " with %d", block_group, bit, count, + err); + } + + ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); mb_free_blocks(inode, &e4b, bit, count_clusters); @@ -4659,8 +4684,7 @@ do_more: ret = ext4_free_group_clusters(sb, gdp) + count_clusters; ext4_free_group_clusters_set(sb, gdp, ret); - ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh, - EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); @@ -4694,7 +4718,6 @@ do_more: put_bh(bitmap_bh); goto do_more; } - ext4_mark_super_dirty(sb); error_return: brelse(bitmap_bh); ext4_std_error(sb, err); @@ -4705,7 +4728,7 @@ error_return: * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block - * @block: start physcial block to add to the block group + * @block: start physical block to add to the block group * @count: number of blocks to free * * This marks the blocks as free in the bitmap and buddy. @@ -4805,8 +4828,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, mb_free_blocks(NULL, &e4b, bit, count); blk_free_count = blocks_freed + ext4_free_group_clusters(sb, desc); ext4_free_group_clusters_set(sb, desc, blk_free_count); - ext4_block_bitmap_csum_set(sb, block_group, desc, bitmap_bh, - EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_block_bitmap_csum_set(sb, block_group, desc, bitmap_bh); ext4_group_desc_csum_set(sb, block_group, desc); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, @@ -4848,10 +4870,11 @@ error_return: * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ -static void ext4_trim_extent(struct super_block *sb, int start, int count, +static int ext4_trim_extent(struct super_block *sb, int start, int count, ext4_group_t group, struct ext4_buddy *e4b) { struct ext4_free_extent ex; + int ret = 0; trace_ext4_trim_extent(sb, group, start, count); @@ -4867,9 +4890,10 @@ static void ext4_trim_extent(struct super_block *sb, int start, int count, */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); - ext4_issue_discard(sb, group, start, count); + ret = ext4_issue_discard(sb, group, start, count); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); + return ret; } /** @@ -4898,7 +4922,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, void *bitmap; ext4_grpblk_t next, count = 0, free_count = 0; struct ext4_buddy e4b; - int ret; + int ret = 0; trace_ext4_trim_all_free(sb, group, start, max); @@ -4925,8 +4949,11 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, next = mb_find_next_bit(bitmap, max + 1, start); if ((next - start) >= minblocks) { - ext4_trim_extent(sb, start, - next - start, group, &e4b); + ret = ext4_trim_extent(sb, start, + next - start, group, &e4b); + if (ret && ret != -EOPNOTSUPP) + break; + ret = 0; count += next - start; } free_count += next - start; @@ -4947,8 +4974,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, break; } - if (!ret) + if (!ret) { + ret = count; EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); + } out: ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); @@ -4956,7 +4985,7 @@ out: ext4_debug("trimmed %d blocks in the group %d\n", count, group); - return count; + return ret; } /** @@ -4984,10 +5013,12 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) start = range->start >> sb->s_blocksize_bits; end = start + (range->len >> sb->s_blocksize_bits) - 1; - minlen = range->minlen >> sb->s_blocksize_bits; + minlen = EXT4_NUM_B2C(EXT4_SB(sb), + range->minlen >> sb->s_blocksize_bits); - if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)) || - unlikely(start >= max_blks)) + if (minlen > EXT4_CLUSTERS_PER_GROUP(sb) || + start >= max_blks || + range->len < sb->s_blocksize) return -EINVAL; if (end >= max_blks) end = max_blks - 1; @@ -5044,6 +5075,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); out: - range->len = trimmed * sb->s_blocksize; + range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; return ret; } diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index c070618c21c..3ccd889ba95 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -65,11 +65,6 @@ extern u8 mb_enable_debug; #define MB_DEFAULT_MIN_TO_SCAN 10 /* - * How many groups mballoc will scan looking for the best chunk - */ -#define MB_DEFAULT_MAX_GROUPS_TO_SCAN 5 - -/* * with 'ext4_mb_stats' allocator will collect stats that will be * shown at umount. The collecting costs though! */ diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index f1bb32ec016..db8226d595f 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include "ext4_jbd2.h" +#include "ext4_extents.h" /* * The contiguous blocks details which can be diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index f99a1311e84..fe7c63f4717 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -44,6 +44,11 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) { struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data); + /* + * We protect against freezing so that we don't create dirty buffers + * on frozen filesystem. + */ + sb_start_write(sb); ext4_mmp_csum_set(sb, mmp); mark_buffer_dirty(bh); lock_buffer(bh); @@ -51,6 +56,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) get_bh(bh); submit_bh(WRITE_SYNC, bh); wait_on_buffer(bh); + sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) return 1; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index c5826c623e7..d9cc5ee42f5 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include "ext4_jbd2.h" #include "ext4.h" +#include "ext4_extents.h" /** * get_ext_path - Find an extent path for designated logical block number. @@ -141,55 +142,21 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, } /** - * mext_check_null_inode - NULL check for two inodes - * - * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. - */ -static int -mext_check_null_inode(struct inode *inode1, struct inode *inode2, - const char *function, unsigned int line) -{ - int ret = 0; - - if (inode1 == NULL) { - __ext4_error(inode2->i_sb, function, line, - "Both inodes should not be NULL: " - "inode1 NULL inode2 %lu", inode2->i_ino); - ret = -EIO; - } else if (inode2 == NULL) { - __ext4_error(inode1->i_sb, function, line, - "Both inodes should not be NULL: " - "inode1 %lu inode2 NULL", inode1->i_ino); - ret = -EIO; - } - return ret; -} - -/** * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem * - * @orig_inode: original inode structure - * @donor_inode: donor inode structure - * Acquire write lock of i_data_sem of the two inodes (orig and donor) by - * i_ino order. + * Acquire write lock of i_data_sem of the two inodes */ static void -double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) +double_down_write_data_sem(struct inode *first, struct inode *second) { - struct inode *first = orig_inode, *second = donor_inode; + if (first < second) { + down_write(&EXT4_I(first)->i_data_sem); + down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING); + } else { + down_write(&EXT4_I(second)->i_data_sem); + down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING); - /* - * Use the inode number to provide the stable locking order instead - * of its address, because the C language doesn't guarantee you can - * compare pointers that don't come from the same array. - */ - if (donor_inode->i_ino < orig_inode->i_ino) { - first = donor_inode; - second = orig_inode; } - - down_write(&EXT4_I(first)->i_data_sem); - down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING); } /** @@ -604,9 +571,8 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, diff = donor_off - le32_to_cpu(tmp_dext->ee_block); ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff); - tmp_dext->ee_block = - cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff); - tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff); + le32_add_cpu(&tmp_dext->ee_block, diff); + le16_add_cpu(&tmp_dext->ee_len, -diff); if (max_count < ext4_ext_get_actual_len(tmp_dext)) tmp_dext->ee_len = cpu_to_le16(max_count); @@ -629,6 +595,43 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, } /** + * mext_check_coverage - Check that all extents in range has the same type + * + * @inode: inode in question + * @from: block offset of inode + * @count: block count to be checked + * @uninit: extents expected to be uninitialized + * @err: pointer to save error value + * + * Return 1 if all extents in range has expected type, and zero otherwise. + */ +static int +mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count, + int uninit, int *err) +{ + struct ext4_ext_path *path = NULL; + struct ext4_extent *ext; + ext4_lblk_t last = from + count; + while (from < last) { + *err = get_ext_path(inode, from, &path); + if (*err) + return 0; + ext = path[ext_depth(inode)].p_ext; + if (!ext) { + ext4_ext_drop_refs(path); + return 0; + } + if (uninit != ext4_ext_is_uninitialized(ext)) { + ext4_ext_drop_refs(path); + return 0; + } + from += ext4_ext_get_actual_len(ext); + ext4_ext_drop_refs(path); + } + return 1; +} + +/** * mext_replace_branches - Replace original extents with new extents * * @handle: journal handle @@ -663,9 +666,6 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, int replaced_count = 0; int dext_alen; - /* Protect extent trees against block allocations via delalloc */ - double_down_write_data_sem(orig_inode, donor_inode); - /* Get the original extent for the block "orig_off" */ *err = get_ext_path(orig_inode, orig_off, &orig_path); if (*err) @@ -764,12 +764,122 @@ out: ext4_ext_invalidate_cache(orig_inode); ext4_ext_invalidate_cache(donor_inode); - double_up_write_data_sem(orig_inode, donor_inode); - return replaced_count; } /** + * mext_page_double_lock - Grab and lock pages on both @inode1 and @inode2 + * + * @inode1: the inode structure + * @inode2: the inode structure + * @index: page index + * @page: result page vector + * + * Grab two locked pages for inode's by inode order + */ +static int +mext_page_double_lock(struct inode *inode1, struct inode *inode2, + pgoff_t index, struct page *page[2]) +{ + struct address_space *mapping[2]; + unsigned fl = AOP_FLAG_NOFS; + + BUG_ON(!inode1 || !inode2); + if (inode1 < inode2) { + mapping[0] = inode1->i_mapping; + mapping[1] = inode2->i_mapping; + } else { + mapping[0] = inode2->i_mapping; + mapping[1] = inode1->i_mapping; + } + + page[0] = grab_cache_page_write_begin(mapping[0], index, fl); + if (!page[0]) + return -ENOMEM; + + page[1] = grab_cache_page_write_begin(mapping[1], index, fl); + if (!page[1]) { + unlock_page(page[0]); + page_cache_release(page[0]); + return -ENOMEM; + } + + if (inode1 > inode2) { + struct page *tmp; + tmp = page[0]; + page[0] = page[1]; + page[1] = tmp; + } + return 0; +} + +/* Force page buffers uptodate w/o dropping page's lock */ +static int +mext_page_mkuptodate(struct page *page, unsigned from, unsigned to) +{ + struct inode *inode = page->mapping->host; + sector_t block; + struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; + unsigned int blocksize, block_start, block_end; + int i, err, nr = 0, partial = 0; + BUG_ON(!PageLocked(page)); + BUG_ON(PageWriteback(page)); + + if (PageUptodate(page)) + return 0; + + blocksize = 1 << inode->i_blkbits; + if (!page_has_buffers(page)) + create_empty_buffers(page, blocksize, 0); + + head = page_buffers(page); + block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + for (bh = head, block_start = 0; bh != head || !block_start; + block++, block_start = block_end, bh = bh->b_this_page) { + block_end = block_start + blocksize; + if (block_end <= from || block_start >= to) { + if (!buffer_uptodate(bh)) + partial = 1; + continue; + } + if (buffer_uptodate(bh)) + continue; + if (!buffer_mapped(bh)) { + int err = 0; + err = ext4_get_block(inode, block, bh, 0); + if (err) { + SetPageError(page); + return err; + } + if (!buffer_mapped(bh)) { + zero_user(page, block_start, blocksize); + if (!err) + set_buffer_uptodate(bh); + continue; + } + } + BUG_ON(nr >= MAX_BUF_PER_PAGE); + arr[nr++] = bh; + } + /* No io required */ + if (!nr) + goto out; + + for (i = 0; i < nr; i++) { + bh = arr[i]; + if (!bh_uptodate_or_lock(bh)) { + err = bh_submit_read(bh); + if (err) + return err; + } + } +out: + if (!partial) + SetPageUptodate(page); + return 0; +} + +/** * move_extent_per_page - Move extent data per page * * @o_filp: file structure of original file @@ -791,26 +901,24 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, int block_len_in_page, int uninit, int *err) { struct inode *orig_inode = o_filp->f_dentry->d_inode; - struct address_space *mapping = orig_inode->i_mapping; - struct buffer_head *bh; - struct page *page = NULL; - const struct address_space_operations *a_ops = mapping->a_ops; + struct page *pagep[2] = {NULL, NULL}; handle_t *handle; ext4_lblk_t orig_blk_offset; long long offs = orig_page_offset << PAGE_CACHE_SHIFT; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int w_flags = 0; unsigned int tmp_data_size, data_size, replaced_size; - void *fsdata; - int i, jblocks; - int err2 = 0; + int err2, jblocks, retries = 0; int replaced_count = 0; + int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; /* * It needs twice the amount of ordinary journal buffers because * inode and donor_inode may change each different metadata blocks. */ +again: + *err = 0; jblocks = ext4_writepage_trans_blocks(orig_inode) * 2; handle = ext4_journal_start(orig_inode, jblocks); if (IS_ERR(handle)) { @@ -824,19 +932,6 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, orig_blk_offset = orig_page_offset * blocks_per_page + data_offset_in_page; - /* - * If orig extent is uninitialized one, - * it's not necessary force the page into memory - * and then force it to be written out again. - * Just swap data blocks between orig and donor. - */ - if (uninit) { - replaced_count = mext_replace_branches(handle, orig_inode, - donor_inode, orig_blk_offset, - block_len_in_page, err); - goto out2; - } - offs = (long long)orig_blk_offset << orig_inode->i_blkbits; /* Calculate data_size */ @@ -858,75 +953,120 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, replaced_size = data_size; - *err = a_ops->write_begin(o_filp, mapping, offs, data_size, w_flags, - &page, &fsdata); + *err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset, + pagep); if (unlikely(*err < 0)) - goto out; - - if (!PageUptodate(page)) { - mapping->a_ops->readpage(o_filp, page); - lock_page(page); - } - + goto stop_journal; /* - * try_to_release_page() doesn't call releasepage in writeback mode. - * We should care about the order of writing to the same file - * by multiple move extent processes. - * It needs to call wait_on_page_writeback() to wait for the - * writeback of the page. + * If orig extent was uninitialized it can become initialized + * at any time after i_data_sem was dropped, in order to + * serialize with delalloc we have recheck extent while we + * hold page's lock, if it is still the case data copy is not + * necessary, just swap data blocks between orig and donor. */ - wait_on_page_writeback(page); + if (uninit) { + double_down_write_data_sem(orig_inode, donor_inode); + /* If any of extents in range became initialized we have to + * fallback to data copying */ + uninit = mext_check_coverage(orig_inode, orig_blk_offset, + block_len_in_page, 1, err); + if (*err) + goto drop_data_sem; - /* Release old bh and drop refs */ - try_to_release_page(page, 0); + uninit &= mext_check_coverage(donor_inode, orig_blk_offset, + block_len_in_page, 1, err); + if (*err) + goto drop_data_sem; + + if (!uninit) { + double_up_write_data_sem(orig_inode, donor_inode); + goto data_copy; + } + if ((page_has_private(pagep[0]) && + !try_to_release_page(pagep[0], 0)) || + (page_has_private(pagep[1]) && + !try_to_release_page(pagep[1], 0))) { + *err = -EBUSY; + goto drop_data_sem; + } + replaced_count = mext_replace_branches(handle, orig_inode, + donor_inode, orig_blk_offset, + block_len_in_page, err); + drop_data_sem: + double_up_write_data_sem(orig_inode, donor_inode); + goto unlock_pages; + } +data_copy: + *err = mext_page_mkuptodate(pagep[0], from, from + replaced_size); + if (*err) + goto unlock_pages; + + /* At this point all buffers in range are uptodate, old mapping layout + * is no longer required, try to drop it now. */ + if ((page_has_private(pagep[0]) && !try_to_release_page(pagep[0], 0)) || + (page_has_private(pagep[1]) && !try_to_release_page(pagep[1], 0))) { + *err = -EBUSY; + goto unlock_pages; + } replaced_count = mext_replace_branches(handle, orig_inode, donor_inode, - orig_blk_offset, block_len_in_page, - &err2); - if (err2) { + orig_blk_offset, + block_len_in_page, err); + if (*err) { if (replaced_count) { block_len_in_page = replaced_count; replaced_size = block_len_in_page << orig_inode->i_blkbits; } else - goto out; + goto unlock_pages; } + /* Perform all necessary steps similar write_begin()/write_end() + * but keeping in mind that i_size will not change */ + *err = __block_write_begin(pagep[0], from, from + replaced_size, + ext4_get_block); + if (!*err) + *err = block_commit_write(pagep[0], from, from + replaced_size); - if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0); - - bh = page_buffers(page); - for (i = 0; i < data_offset_in_page; i++) - bh = bh->b_this_page; - - for (i = 0; i < block_len_in_page; i++) { - *err = ext4_get_block(orig_inode, - (sector_t)(orig_blk_offset + i), bh, 0); - if (*err < 0) - goto out; - - if (bh->b_this_page != NULL) - bh = bh->b_this_page; - } - - *err = a_ops->write_end(o_filp, mapping, offs, data_size, replaced_size, - page, fsdata); - page = NULL; - -out: - if (unlikely(page)) { - if (PageLocked(page)) - unlock_page(page); - page_cache_release(page); - ext4_journal_stop(handle); - } -out2: + if (unlikely(*err < 0)) + goto repair_branches; + + /* Even in case of data=writeback it is reasonable to pin + * inode to transaction, to prevent unexpected data loss */ + *err = ext4_jbd2_file_inode(handle, orig_inode); + +unlock_pages: + unlock_page(pagep[0]); + page_cache_release(pagep[0]); + unlock_page(pagep[1]); + page_cache_release(pagep[1]); +stop_journal: ext4_journal_stop(handle); - - if (err2) - *err = err2; - + /* Buffer was busy because probably is pinned to journal transaction, + * force transaction commit may help to free it. */ + if (*err == -EBUSY && ext4_should_retry_alloc(orig_inode->i_sb, + &retries)) + goto again; return replaced_count; + +repair_branches: + /* + * This should never ever happen! + * Extents are swapped already, but we are not able to copy data. + * Try to swap extents to it's original places + */ + double_down_write_data_sem(orig_inode, donor_inode); + replaced_count = mext_replace_branches(handle, donor_inode, orig_inode, + orig_blk_offset, + block_len_in_page, &err2); + double_up_write_data_sem(orig_inode, donor_inode); + if (replaced_count != block_len_in_page) { + EXT4_ERROR_INODE_BLOCK(orig_inode, (sector_t)(orig_blk_offset), + "Unable to copy data block," + " data will be lost."); + *err = -EIO; + } + replaced_count = 0; + goto unlock_pages; } /** @@ -969,14 +1109,6 @@ mext_check_arguments(struct inode *orig_inode, return -EINVAL; } - /* Files should be in the same ext4 FS */ - if (orig_inode->i_sb != donor_inode->i_sb) { - ext4_debug("ext4 move extent: The argument files " - "should be in same FS [ino:orig %lu, donor %lu]\n", - orig_inode->i_ino, donor_inode->i_ino); - return -EINVAL; - } - /* Ext4 move extent supports only extent based file */ if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) { ext4_debug("ext4 move extent: orig file is not extents " @@ -1002,7 +1134,6 @@ mext_check_arguments(struct inode *orig_inode, } if ((orig_start >= EXT_MAX_BLOCKS) || - (donor_start >= EXT_MAX_BLOCKS) || (*len > EXT_MAX_BLOCKS) || (orig_start + *len >= EXT_MAX_BLOCKS)) { ext4_debug("ext4 move extent: Can't handle over [%u] blocks " @@ -1072,35 +1203,19 @@ mext_check_arguments(struct inode *orig_inode, * @inode1: the inode structure * @inode2: the inode structure * - * Lock two inodes' i_mutex by i_ino order. - * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. + * Lock two inodes' i_mutex */ -static int +static void mext_inode_double_lock(struct inode *inode1, struct inode *inode2) { - int ret = 0; - - BUG_ON(inode1 == NULL && inode2 == NULL); - - ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__); - if (ret < 0) - goto out; - - if (inode1 == inode2) { - mutex_lock(&inode1->i_mutex); - goto out; - } - - if (inode1->i_ino < inode2->i_ino) { + BUG_ON(inode1 == inode2); + if (inode1 < inode2) { mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT); mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD); } else { mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT); mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD); } - -out: - return ret; } /** @@ -1109,28 +1224,13 @@ out: * @inode1: the inode that is released first * @inode2: the inode that is released second * - * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. */ -static int +static void mext_inode_double_unlock(struct inode *inode1, struct inode *inode2) { - int ret = 0; - - BUG_ON(inode1 == NULL && inode2 == NULL); - - ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__); - if (ret < 0) - goto out; - - if (inode1) - mutex_unlock(&inode1->i_mutex); - - if (inode2 && inode2 != inode1) - mutex_unlock(&inode2->i_mutex); - -out: - return ret; + mutex_unlock(&inode1->i_mutex); + mutex_unlock(&inode2->i_mutex); } /** @@ -1187,16 +1287,23 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0; ext4_lblk_t rest_blocks; pgoff_t orig_page_offset = 0, seq_end_page; - int ret1, ret2, depth, last_extent = 0; + int ret, depth, last_extent = 0; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; int data_offset_in_page; int block_len_in_page; int uninit; - /* orig and donor should be different file */ - if (orig_inode->i_ino == donor_inode->i_ino) { + if (orig_inode->i_sb != donor_inode->i_sb) { + ext4_debug("ext4 move extent: The argument files " + "should be in same FS [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + /* orig and donor should be different inodes */ + if (orig_inode == donor_inode) { ext4_debug("ext4 move extent: The argument files should not " - "be same file [ino:orig %lu, donor %lu]\n", + "be same inode [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } @@ -1208,18 +1315,27 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } - + /* TODO: This is non obvious task to swap blocks for inodes with full + jornaling enabled */ + if (ext4_should_journal_data(orig_inode) || + ext4_should_journal_data(donor_inode)) { + return -EINVAL; + } /* Protect orig and donor inodes against a truncate */ - ret1 = mext_inode_double_lock(orig_inode, donor_inode); - if (ret1 < 0) - return ret1; + mext_inode_double_lock(orig_inode, donor_inode); + + /* Wait for all existing dio workers */ + ext4_inode_block_unlocked_dio(orig_inode); + ext4_inode_block_unlocked_dio(donor_inode); + inode_dio_wait(orig_inode); + inode_dio_wait(donor_inode); /* Protect extent tree against block allocations via delalloc */ double_down_write_data_sem(orig_inode, donor_inode); /* Check the filesystem environment whether move_extent can be done */ - ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start, + ret = mext_check_arguments(orig_inode, donor_inode, orig_start, donor_start, &len); - if (ret1) + if (ret) goto out; file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits; @@ -1227,13 +1343,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, if (file_end < block_end) len -= block_end - file_end; - ret1 = get_ext_path(orig_inode, block_start, &orig_path); - if (ret1) + ret = get_ext_path(orig_inode, block_start, &orig_path); + if (ret) goto out; /* Get path structure to check the hole */ - ret1 = get_ext_path(orig_inode, block_start, &holecheck_path); - if (ret1) + ret = get_ext_path(orig_inode, block_start, &holecheck_path); + if (ret) goto out; depth = ext_depth(orig_inode); @@ -1252,13 +1368,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, last_extent = mext_next_extent(orig_inode, holecheck_path, &ext_cur); if (last_extent < 0) { - ret1 = last_extent; + ret = last_extent; goto out; } last_extent = mext_next_extent(orig_inode, orig_path, &ext_dummy); if (last_extent < 0) { - ret1 = last_extent; + ret = last_extent; goto out; } seq_start = le32_to_cpu(ext_cur->ee_block); @@ -1272,7 +1388,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, if (le32_to_cpu(ext_cur->ee_block) > block_end) { ext4_debug("ext4 move extent: The specified range of file " "may be the hole\n"); - ret1 = -EINVAL; + ret = -EINVAL; goto out; } @@ -1292,7 +1408,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, last_extent = mext_next_extent(orig_inode, holecheck_path, &ext_cur); if (last_extent < 0) { - ret1 = last_extent; + ret = last_extent; break; } add_blocks = ext4_ext_get_actual_len(ext_cur); @@ -1349,18 +1465,18 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, orig_page_offset, data_offset_in_page, block_len_in_page, uninit, - &ret1); + &ret); /* Count how many blocks we have exchanged */ *moved_len += block_len_in_page; - if (ret1 < 0) + if (ret < 0) break; if (*moved_len > len) { EXT4_ERROR_INODE(orig_inode, "We replaced blocks too much! " "sum of replaced: %llu requested: %llu", *moved_len, len); - ret1 = -EIO; + ret = -EIO; break; } @@ -1374,22 +1490,22 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, } double_down_write_data_sem(orig_inode, donor_inode); - if (ret1 < 0) + if (ret < 0) break; /* Decrease buffer counter */ if (holecheck_path) ext4_ext_drop_refs(holecheck_path); - ret1 = get_ext_path(orig_inode, seq_start, &holecheck_path); - if (ret1) + ret = get_ext_path(orig_inode, seq_start, &holecheck_path); + if (ret) break; depth = holecheck_path->p_depth; /* Decrease buffer counter */ if (orig_path) ext4_ext_drop_refs(orig_path); - ret1 = get_ext_path(orig_inode, seq_start, &orig_path); - if (ret1) + ret = get_ext_path(orig_inode, seq_start, &orig_path); + if (ret) break; ext_cur = holecheck_path[depth].p_ext; @@ -1412,12 +1528,9 @@ out: kfree(holecheck_path); } double_up_write_data_sem(orig_inode, donor_inode); - ret2 = mext_inode_double_unlock(orig_inode, donor_inode); - - if (ret1) - return ret1; - else if (ret2) - return ret2; + ext4_inode_resume_unlocked_dio(orig_inode); + ext4_inode_resume_unlocked_dio(donor_inode); + mext_inode_double_unlock(orig_inode, donor_inode); - return 0; + return ret; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 5845cd97bf8..f9ed946a448 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -55,6 +55,13 @@ static struct buffer_head *ext4_append(handle_t *handle, { struct buffer_head *bh; + if (unlikely(EXT4_SB(inode->i_sb)->s_max_dir_size_kb && + ((inode->i_size >> 10) >= + EXT4_SB(inode->i_sb)->s_max_dir_size_kb))) { + *err = -ENOSPC; + return NULL; + } + *block = inode->i_size >> inode->i_sb->s_blocksize_bits; bh = ext4_bread(handle, inode, *block, 1, err); @@ -67,6 +74,12 @@ static struct buffer_head *ext4_append(handle_t *handle, bh = NULL; } } + if (!bh && !(*err)) { + *err = -EIO; + ext4_error(inode->i_sb, + "Directory hole detected on inode %lu\n", + inode->i_ino); + } return bh; } @@ -189,13 +202,8 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, struct inode *inode); /* checksumming functions */ -#define EXT4_DIRENT_TAIL(block, blocksize) \ - ((struct ext4_dir_entry_tail *)(((void *)(block)) + \ - ((blocksize) - \ - sizeof(struct ext4_dir_entry_tail)))) - -static void initialize_dirent_tail(struct ext4_dir_entry_tail *t, - unsigned int blocksize) +void initialize_dirent_tail(struct ext4_dir_entry_tail *t, + unsigned int blocksize) { memset(t, 0, sizeof(struct ext4_dir_entry_tail)); t->det_rec_len = ext4_rec_len_to_disk( @@ -248,6 +256,12 @@ static __le32 ext4_dirent_csum(struct inode *inode, return cpu_to_le32(csum); } +static void warn_no_space_for_csum(struct inode *inode) +{ + ext4_warning(inode->i_sb, "no space in directory inode %lu leaf for " + "checksum. Please run e2fsck -D.", inode->i_ino); +} + int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) { struct ext4_dir_entry_tail *t; @@ -258,8 +272,7 @@ int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) t = get_dirent_tail(inode, dirent); if (!t) { - EXT4_ERROR_INODE(inode, "metadata_csum set but no space in dir " - "leaf for checksum. Please run e2fsck -D."); + warn_no_space_for_csum(inode); return 0; } @@ -281,8 +294,7 @@ static void ext4_dirent_csum_set(struct inode *inode, t = get_dirent_tail(inode, dirent); if (!t) { - EXT4_ERROR_INODE(inode, "metadata_csum set but no space in dir " - "leaf for checksum. Please run e2fsck -D."); + warn_no_space_for_csum(inode); return; } @@ -290,9 +302,9 @@ static void ext4_dirent_csum_set(struct inode *inode, (void *)t - (void *)dirent); } -static inline int ext4_handle_dirty_dirent_node(handle_t *handle, - struct inode *inode, - struct buffer_head *bh) +int ext4_handle_dirty_dirent_node(handle_t *handle, + struct inode *inode, + struct buffer_head *bh) { ext4_dirent_csum_set(inode, (struct ext4_dir_entry *)bh->b_data); return ext4_handle_dirty_metadata(handle, inode, bh); @@ -364,8 +376,7 @@ static int ext4_dx_csum_verify(struct inode *inode, count = le16_to_cpu(c->count); if (count_offset + (limit * sizeof(struct dx_entry)) > EXT4_BLOCK_SIZE(inode->i_sb) - sizeof(struct dx_tail)) { - EXT4_ERROR_INODE(inode, "metadata_csum set but no space for " - "tree checksum found. Run e2fsck -D."); + warn_no_space_for_csum(inode); return 1; } t = (struct dx_tail *)(((struct dx_entry *)c) + limit); @@ -395,8 +406,7 @@ static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent) count = le16_to_cpu(c->count); if (count_offset + (limit * sizeof(struct dx_entry)) > EXT4_BLOCK_SIZE(inode->i_sb) - sizeof(struct dx_tail)) { - EXT4_ERROR_INODE(inode, "metadata_csum set but no space for " - "tree checksum. Run e2fsck -D."); + warn_no_space_for_csum(inode); return; } t = (struct dx_tail *)(((struct dx_entry *)c) + limit); @@ -594,8 +604,11 @@ dx_probe(const struct qstr *d_name, struct inode *dir, u32 hash; frame->bh = NULL; - if (!(bh = ext4_bread (NULL,dir, 0, 0, err))) + if (!(bh = ext4_bread(NULL, dir, 0, 0, err))) { + if (*err == 0) + *err = ERR_BAD_DX_DIR; goto fail; + } root = (struct dx_root *) bh->b_data; if (root->info.hash_version != DX_HASH_TEA && root->info.hash_version != DX_HASH_HALF_MD4 && @@ -696,8 +709,11 @@ dx_probe(const struct qstr *d_name, struct inode *dir, frame->entries = entries; frame->at = at; if (!indirect--) return frame; - if (!(bh = ext4_bread (NULL,dir, dx_get_block(at), 0, err))) + if (!(bh = ext4_bread(NULL, dir, dx_get_block(at), 0, err))) { + if (!(*err)) + *err = ERR_BAD_DX_DIR; goto fail2; + } at = entries = ((struct dx_node *) bh->b_data)->entries; if (!buffer_verified(bh) && @@ -706,7 +722,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir, ext4_warning(dir->i_sb, "Node failed checksum"); brelse(bh); *err = ERR_BAD_DX_DIR; - goto fail; + goto fail2; } set_buffer_verified(bh); @@ -807,8 +823,15 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash, */ while (num_frames--) { if (!(bh = ext4_bread(NULL, dir, dx_get_block(p->at), - 0, &err))) + 0, &err))) { + if (!err) { + ext4_error(dir->i_sb, + "Directory hole detected on inode %lu\n", + dir->i_ino); + return -EIO; + } return err; /* Failure */ + } if (!buffer_verified(bh) && !ext4_dx_csum_verify(dir, @@ -839,12 +862,19 @@ static int htree_dirblock_to_tree(struct file *dir_file, { struct buffer_head *bh; struct ext4_dir_entry_2 *de, *top; - int err, count = 0; + int err = 0, count = 0; dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); - if (!(bh = ext4_bread (NULL, dir, block, 0, &err))) + if (!(bh = ext4_bread(NULL, dir, block, 0, &err))) { + if (!err) { + err = -EIO; + ext4_error(dir->i_sb, + "Directory hole detected on inode %lu\n", + dir->i_ino); + } return err; + } if (!buffer_verified(bh) && !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) @@ -857,6 +887,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, EXT4_DIR_REC_LEN(0)); for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) { if (ext4_check_dir_entry(dir, NULL, de, bh, + bh->b_data, bh->b_size, (block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb)) + ((char *)de - bh->b_data))) { /* On error, skip the f_pos to the next block. */ @@ -974,6 +1005,15 @@ errout: return (err); } +static inline int search_dirblock(struct buffer_head *bh, + struct inode *dir, + const struct qstr *d_name, + unsigned int offset, + struct ext4_dir_entry_2 **res_dir) +{ + return search_dir(bh, bh->b_data, dir->i_sb->s_blocksize, dir, + d_name, offset, res_dir); +} /* * Directory block splitting, compacting @@ -1048,13 +1088,6 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) dx_set_count(entries, count + 1); } -static void ext4_update_dx_flag(struct inode *inode) -{ - if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_COMPAT_DIR_INDEX)) - ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); -} - /* * NOTE! unlike strncmp, ext4_match returns 1 for success, 0 for failure. * @@ -1074,11 +1107,13 @@ static inline int ext4_match (int len, const char * const name, /* * Returns 0 if not found, -1 on failure, and 1 on success */ -static inline int search_dirblock(struct buffer_head *bh, - struct inode *dir, - const struct qstr *d_name, - unsigned int offset, - struct ext4_dir_entry_2 ** res_dir) +int search_dir(struct buffer_head *bh, + char *search_buf, + int buf_size, + struct inode *dir, + const struct qstr *d_name, + unsigned int offset, + struct ext4_dir_entry_2 **res_dir) { struct ext4_dir_entry_2 * de; char * dlimit; @@ -1086,8 +1121,8 @@ static inline int search_dirblock(struct buffer_head *bh, const char *name = d_name->name; int namelen = d_name->len; - de = (struct ext4_dir_entry_2 *) bh->b_data; - dlimit = bh->b_data + dir->i_sb->s_blocksize; + de = (struct ext4_dir_entry_2 *)search_buf; + dlimit = search_buf + buf_size; while ((char *) de < dlimit) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ @@ -1095,7 +1130,8 @@ static inline int search_dirblock(struct buffer_head *bh, if ((char *) de + namelen <= dlimit && ext4_match (namelen, name, de)) { /* found a match - just to be sure, do a full check */ - if (ext4_check_dir_entry(dir, NULL, de, bh, offset)) + if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, + bh->b_size, offset)) return -1; *res_dir = de; return 1; @@ -1111,6 +1147,21 @@ static inline int search_dirblock(struct buffer_head *bh, return 0; } +static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, + struct ext4_dir_entry *de) +{ + struct super_block *sb = dir->i_sb; + + if (!is_dx(dir)) + return 0; + if (block == 0) + return 1; + if (de->inode == 0 && + ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) == + sb->s_blocksize) + return 1; + return 0; +} /* * ext4_find_entry() @@ -1125,7 +1176,8 @@ static inline int search_dirblock(struct buffer_head *bh, */ static struct buffer_head * ext4_find_entry (struct inode *dir, const struct qstr *d_name, - struct ext4_dir_entry_2 ** res_dir) + struct ext4_dir_entry_2 **res_dir, + int *inlined) { struct super_block *sb; struct buffer_head *bh_use[NAMEI_RA_SIZE]; @@ -1146,6 +1198,18 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, namelen = d_name->len; if (namelen > EXT4_NAME_LEN) return NULL; + + if (ext4_has_inline_data(dir)) { + int has_inline_data = 1; + ret = ext4_find_inline_entry(dir, d_name, res_dir, + &has_inline_data); + if (has_inline_data) { + if (inlined) + *inlined = 1; + return ret; + } + } + if ((namelen <= 2) && (name[0] == '.') && (name[1] == '.' || name[1] == '\0')) { /* @@ -1211,6 +1275,8 @@ restart: goto next; } if (!buffer_verified(bh) && + !is_dx_internal_node(dir, block, + (struct ext4_dir_entry *)bh->b_data) && !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) { EXT4_ERROR_INODE(dir, "checksumming directory " @@ -1267,8 +1333,15 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q return NULL; do { block = dx_get_block(frame->at); - if (!(bh = ext4_bread(NULL, dir, block, 0, err))) + if (!(bh = ext4_bread(NULL, dir, block, 0, err))) { + if (!(*err)) { + *err = -EIO; + ext4_error(dir->i_sb, + "Directory hole detected on inode %lu\n", + dir->i_ino); + } goto errout; + } if (!buffer_verified(bh) && !ext4_dirent_csum_verify(dir, @@ -1312,7 +1385,7 @@ errout: return NULL; } -static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; struct ext4_dir_entry_2 *de; @@ -1321,7 +1394,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru if (dentry->d_name.len > EXT4_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - bh = ext4_find_entry(dir, &dentry->d_name, &de); + bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); inode = NULL; if (bh) { __u32 ino = le32_to_cpu(de->inode); @@ -1355,7 +1428,7 @@ struct dentry *ext4_get_parent(struct dentry *child) struct ext4_dir_entry_2 * de; struct buffer_head *bh; - bh = ext4_find_entry(child->d_inode, &dotdot, &de); + bh = ext4_find_entry(child->d_inode, &dotdot, &de, NULL); if (!bh) return ERR_PTR(-ENOENT); ino = le32_to_cpu(de->inode); @@ -1553,6 +1626,63 @@ errout: return NULL; } +int ext4_find_dest_de(struct inode *dir, struct inode *inode, + struct buffer_head *bh, + void *buf, int buf_size, + const char *name, int namelen, + struct ext4_dir_entry_2 **dest_de) +{ + struct ext4_dir_entry_2 *de; + unsigned short reclen = EXT4_DIR_REC_LEN(namelen); + int nlen, rlen; + unsigned int offset = 0; + char *top; + + de = (struct ext4_dir_entry_2 *)buf; + top = buf + buf_size - reclen; + while ((char *) de <= top) { + if (ext4_check_dir_entry(dir, NULL, de, bh, + buf, buf_size, offset)) + return -EIO; + if (ext4_match(namelen, name, de)) + return -EEXIST; + nlen = EXT4_DIR_REC_LEN(de->name_len); + rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); + if ((de->inode ? rlen - nlen : rlen) >= reclen) + break; + de = (struct ext4_dir_entry_2 *)((char *)de + rlen); + offset += rlen; + } + if ((char *) de > top) + return -ENOSPC; + + *dest_de = de; + return 0; +} + +void ext4_insert_dentry(struct inode *inode, + struct ext4_dir_entry_2 *de, + int buf_size, + const char *name, int namelen) +{ + + int nlen, rlen; + + nlen = EXT4_DIR_REC_LEN(de->name_len); + rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); + if (de->inode) { + struct ext4_dir_entry_2 *de1 = + (struct ext4_dir_entry_2 *)((char *)de + nlen); + de1->rec_len = ext4_rec_len_to_disk(rlen - nlen, buf_size); + de->rec_len = ext4_rec_len_to_disk(nlen, buf_size); + de = de1; + } + de->file_type = EXT4_FT_UNKNOWN; + de->inode = cpu_to_le32(inode->i_ino); + ext4_set_de_type(inode->i_sb, de, inode->i_mode); + de->name_len = namelen; + memcpy(de->name, name, namelen); +} /* * Add a new entry into a directory (leaf) block. If de is non-NULL, * it points to a directory entry which is guaranteed to be large @@ -1568,12 +1698,10 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, struct inode *dir = dentry->d_parent->d_inode; const char *name = dentry->d_name.name; int namelen = dentry->d_name.len; - unsigned int offset = 0; unsigned int blocksize = dir->i_sb->s_blocksize; unsigned short reclen; - int nlen, rlen, err; - char *top; int csum_size = 0; + int err; if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) @@ -1581,22 +1709,11 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, reclen = EXT4_DIR_REC_LEN(namelen); if (!de) { - de = (struct ext4_dir_entry_2 *)bh->b_data; - top = bh->b_data + (blocksize - csum_size) - reclen; - while ((char *) de <= top) { - if (ext4_check_dir_entry(dir, NULL, de, bh, offset)) - return -EIO; - if (ext4_match(namelen, name, de)) - return -EEXIST; - nlen = EXT4_DIR_REC_LEN(de->name_len); - rlen = ext4_rec_len_from_disk(de->rec_len, blocksize); - if ((de->inode? rlen - nlen: rlen) >= reclen) - break; - de = (struct ext4_dir_entry_2 *)((char *)de + rlen); - offset += rlen; - } - if ((char *) de > top) - return -ENOSPC; + err = ext4_find_dest_de(dir, inode, + bh, bh->b_data, blocksize - csum_size, + name, namelen, &de); + if (err) + return err; } BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bh); @@ -1606,19 +1723,8 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, } /* By now the buffer is marked for journaling */ - nlen = EXT4_DIR_REC_LEN(de->name_len); - rlen = ext4_rec_len_from_disk(de->rec_len, blocksize); - if (de->inode) { - struct ext4_dir_entry_2 *de1 = (struct ext4_dir_entry_2 *)((char *)de + nlen); - de1->rec_len = ext4_rec_len_to_disk(rlen - nlen, blocksize); - de->rec_len = ext4_rec_len_to_disk(nlen, blocksize); - de = de1; - } - de->file_type = EXT4_FT_UNKNOWN; - de->inode = cpu_to_le32(inode->i_ino); - ext4_set_de_type(dir->i_sb, de, inode->i_mode); - de->name_len = namelen; - memcpy(de->name, name, namelen); + ext4_insert_dentry(inode, de, blocksize, name, namelen); + /* * XXX shouldn't update any times until successful * completion of syscall, but too many callers depend @@ -1791,6 +1897,17 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, blocksize = sb->s_blocksize; if (!dentry->d_name.len) return -EINVAL; + + if (ext4_has_inline_data(dir)) { + retval = ext4_try_add_inline_entry(handle, dentry, inode); + if (retval < 0) + return retval; + if (retval == 1) { + retval = 0; + return retval; + } + } + if (is_dx(dir)) { retval = ext4_dx_add_entry(handle, dentry, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) @@ -1801,9 +1918,15 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, } blocks = dir->i_size >> sb->s_blocksize_bits; for (block = 0; block < blocks; block++) { - bh = ext4_bread(handle, dir, block, 0, &retval); - if(!bh) + if (!(bh = ext4_bread(handle, dir, block, 0, &retval))) { + if (!retval) { + retval = -EIO; + ext4_error(inode->i_sb, + "Directory hole detected on inode %lu\n", + inode->i_ino); + } return retval; + } if (!buffer_verified(bh) && !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) @@ -1860,8 +1983,15 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, entries = frame->entries; at = frame->at; - if (!(bh = ext4_bread(handle,dir, dx_get_block(frame->at), 0, &err))) + if (!(bh = ext4_bread(handle, dir, dx_get_block(frame->at), 0, &err))) { + if (!err) { + err = -EIO; + ext4_error(dir->i_sb, + "Directory hole detected on inode %lu\n", + dir->i_ino); + } goto cleanup; + } if (!buffer_verified(bh) && !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) @@ -1983,36 +2113,29 @@ cleanup: } /* - * ext4_delete_entry deletes a directory entry by merging it with the - * previous entry + * ext4_generic_delete_entry deletes a directory entry by merging it + * with the previous entry */ -static int ext4_delete_entry(handle_t *handle, - struct inode *dir, - struct ext4_dir_entry_2 *de_del, - struct buffer_head *bh) +int ext4_generic_delete_entry(handle_t *handle, + struct inode *dir, + struct ext4_dir_entry_2 *de_del, + struct buffer_head *bh, + void *entry_buf, + int buf_size, + int csum_size) { struct ext4_dir_entry_2 *de, *pde; unsigned int blocksize = dir->i_sb->s_blocksize; - int csum_size = 0; - int i, err; - - if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) - csum_size = sizeof(struct ext4_dir_entry_tail); + int i; i = 0; pde = NULL; - de = (struct ext4_dir_entry_2 *) bh->b_data; - while (i < bh->b_size - csum_size) { - if (ext4_check_dir_entry(dir, NULL, de, bh, i)) + de = (struct ext4_dir_entry_2 *)entry_buf; + while (i < buf_size - csum_size) { + if (ext4_check_dir_entry(dir, NULL, de, bh, + bh->b_data, bh->b_size, i)) return -EIO; if (de == de_del) { - BUFFER_TRACE(bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, bh); - if (unlikely(err)) { - ext4_std_error(dir->i_sb, err); - return err; - } if (pde) pde->rec_len = ext4_rec_len_to_disk( ext4_rec_len_from_disk(pde->rec_len, @@ -2023,12 +2146,6 @@ static int ext4_delete_entry(handle_t *handle, else de->inode = 0; dir->i_version++; - BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_dirent_node(handle, dir, bh); - if (unlikely(err)) { - ext4_std_error(dir->i_sb, err); - return err; - } return 0; } i += ext4_rec_len_from_disk(de->rec_len, blocksize); @@ -2038,6 +2155,48 @@ static int ext4_delete_entry(handle_t *handle, return -ENOENT; } +static int ext4_delete_entry(handle_t *handle, + struct inode *dir, + struct ext4_dir_entry_2 *de_del, + struct buffer_head *bh) +{ + int err, csum_size = 0; + + if (ext4_has_inline_data(dir)) { + int has_inline_data = 1; + err = ext4_delete_inline_entry(handle, dir, de_del, bh, + &has_inline_data); + if (has_inline_data) + return err; + } + + if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + csum_size = sizeof(struct ext4_dir_entry_tail); + + BUFFER_TRACE(bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, bh); + if (unlikely(err)) + goto out; + + err = ext4_generic_delete_entry(handle, dir, de_del, + bh, bh->b_data, + dir->i_sb->s_blocksize, csum_size); + if (err) + goto out; + + BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); + err = ext4_handle_dirty_dirent_node(handle, dir, bh); + if (unlikely(err)) + goto out; + + return 0; +out: + if (err != -ENOENT) + ext4_std_error(dir->i_sb, err); + return err; +} + /* * DIR_NLINK feature is set if 1) nlinks > EXT4_LINK_MAX or 2) nlinks == 2, * since this indicates that nlinks count was previously 1. @@ -2072,8 +2231,8 @@ static int ext4_add_nondir(handle_t *handle, int err = ext4_add_entry(handle, dentry, inode); if (!err) { ext4_mark_inode_dirty(handle, inode); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; } drop_nlink(inode); @@ -2091,7 +2250,7 @@ static int ext4_add_nondir(handle_t *handle, * with d_instantiate(). */ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { handle_t *handle; struct inode *inode; @@ -2149,9 +2308,7 @@ retry: err = PTR_ERR(inode); if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); -#ifdef CONFIG_EXT4_FS_XATTR inode->i_op = &ext4_special_inode_operations; -#endif err = ext4_add_nondir(handle, dentry, inode); } ext4_journal_stop(handle); @@ -2160,21 +2317,94 @@ retry: return err; } -static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, + struct ext4_dir_entry_2 *de, + int blocksize, int csum_size, + unsigned int parent_ino, int dotdot_real_len) +{ + de->inode = cpu_to_le32(inode->i_ino); + de->name_len = 1; + de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len), + blocksize); + strcpy(de->name, "."); + ext4_set_de_type(inode->i_sb, de, S_IFDIR); + + de = ext4_next_entry(de, blocksize); + de->inode = cpu_to_le32(parent_ino); + de->name_len = 2; + if (!dotdot_real_len) + de->rec_len = ext4_rec_len_to_disk(blocksize - + (csum_size + EXT4_DIR_REC_LEN(1)), + blocksize); + else + de->rec_len = ext4_rec_len_to_disk( + EXT4_DIR_REC_LEN(de->name_len), blocksize); + strcpy(de->name, ".."); + ext4_set_de_type(inode->i_sb, de, S_IFDIR); + + return ext4_next_entry(de, blocksize); +} + +static int ext4_init_new_dir(handle_t *handle, struct inode *dir, + struct inode *inode) { - handle_t *handle; - struct inode *inode; struct buffer_head *dir_block = NULL; struct ext4_dir_entry_2 *de; struct ext4_dir_entry_tail *t; unsigned int blocksize = dir->i_sb->s_blocksize; int csum_size = 0; - int err, retries = 0; + int err; if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) csum_size = sizeof(struct ext4_dir_entry_tail); + if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { + err = ext4_try_create_inline_dir(handle, dir, inode); + if (err < 0 && err != -ENOSPC) + goto out; + if (!err) + goto out; + } + + inode->i_size = EXT4_I(inode)->i_disksize = blocksize; + if (!(dir_block = ext4_bread(handle, inode, 0, 1, &err))) { + if (!err) { + err = -EIO; + ext4_error(inode->i_sb, + "Directory hole detected on inode %lu\n", + inode->i_ino); + } + goto out; + } + BUFFER_TRACE(dir_block, "get_write_access"); + err = ext4_journal_get_write_access(handle, dir_block); + if (err) + goto out; + de = (struct ext4_dir_entry_2 *)dir_block->b_data; + ext4_init_dot_dotdot(inode, de, blocksize, csum_size, dir->i_ino, 0); + set_nlink(inode, 2); + if (csum_size) { + t = EXT4_DIRENT_TAIL(dir_block->b_data, blocksize); + initialize_dirent_tail(t, blocksize); + } + + BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata"); + err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); + if (err) + goto out; + set_buffer_verified(dir_block); +out: + brelse(dir_block); + return err; +} + +static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + handle_t *handle; + struct inode *inode; + int err, retries = 0; + if (EXT4_DIR_LINK_MAX(dir)) return -EMLINK; @@ -2198,41 +2428,9 @@ retry: inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; - inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize; - dir_block = ext4_bread(handle, inode, 0, 1, &err); - if (!dir_block) - goto out_clear_inode; - BUFFER_TRACE(dir_block, "get_write_access"); - err = ext4_journal_get_write_access(handle, dir_block); - if (err) - goto out_clear_inode; - de = (struct ext4_dir_entry_2 *) dir_block->b_data; - de->inode = cpu_to_le32(inode->i_ino); - de->name_len = 1; - de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len), - blocksize); - strcpy(de->name, "."); - ext4_set_de_type(dir->i_sb, de, S_IFDIR); - de = ext4_next_entry(de, blocksize); - de->inode = cpu_to_le32(dir->i_ino); - de->rec_len = ext4_rec_len_to_disk(blocksize - - (csum_size + EXT4_DIR_REC_LEN(1)), - blocksize); - de->name_len = 2; - strcpy(de->name, ".."); - ext4_set_de_type(dir->i_sb, de, S_IFDIR); - set_nlink(inode, 2); - - if (csum_size) { - t = EXT4_DIRENT_TAIL(dir_block->b_data, blocksize); - initialize_dirent_tail(t, blocksize); - } - - BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); + err = ext4_init_new_dir(handle, dir, inode); if (err) goto out_clear_inode; - set_buffer_verified(dir_block); err = ext4_mark_inode_dirty(handle, inode); if (!err) err = ext4_add_entry(handle, dentry, inode); @@ -2249,10 +2447,9 @@ out_clear_inode: err = ext4_mark_inode_dirty(handle, dir); if (err) goto out_clear_inode; - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); out_stop: - brelse(dir_block); ext4_journal_stop(handle); if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) goto retry; @@ -2270,6 +2467,14 @@ static int empty_dir(struct inode *inode) struct super_block *sb; int err = 0; + if (ext4_has_inline_data(inode)) { + int has_inline_data = 1; + + err = empty_inline_dir(inode, &has_inline_data); + if (has_inline_data) + return err; + } + sb = inode->i_sb; if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) || !(bh = ext4_bread(NULL, inode, 0, 0, &err))) { @@ -2318,6 +2523,11 @@ static int empty_dir(struct inode *inode) EXT4_ERROR_INODE(inode, "error %d reading directory " "lblock %u", err, lblock); + else + ext4_warning(inode->i_sb, + "bad directory (dir #%lu) - no data block", + inode->i_ino); + offset += sb->s_blocksize; continue; } @@ -2331,7 +2541,8 @@ static int empty_dir(struct inode *inode) set_buffer_verified(bh); de = (struct ext4_dir_entry_2 *) bh->b_data; } - if (ext4_check_dir_entry(inode, NULL, de, bh, offset)) { + if (ext4_check_dir_entry(inode, NULL, de, bh, + bh->b_data, bh->b_size, offset)) { de = (struct ext4_dir_entry_2 *)(bh->b_data + sb->s_blocksize); offset = (offset | (sb->s_blocksize - 1)) + 1; @@ -2362,7 +2573,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) struct ext4_iloc iloc; int err = 0, rc; - if (!ext4_handle_valid(handle)) + if (!EXT4_SB(sb)->s_journal) return 0; mutex_lock(&EXT4_SB(sb)->s_orphan_lock); @@ -2397,7 +2608,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) /* Insert this inode at the head of the on-disk orphan list... */ NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan); EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); - err = ext4_handle_dirty_super_now(handle, sb); + err = ext4_handle_dirty_super(handle, sb); rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; @@ -2436,8 +2647,8 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) struct ext4_iloc iloc; int err = 0; - /* ext4_handle_valid() assumes a valid handle_t pointer */ - if (handle && !ext4_handle_valid(handle)) + if ((!EXT4_SB(inode->i_sb)->s_journal) && + !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) return 0; mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock); @@ -2456,7 +2667,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) * transaction handle with which to update the orphan list on * disk, but we still need to remove the inode from the linked * list in memory. */ - if (sbi->s_journal && !handle) + if (!handle) goto out; err = ext4_reserve_inode_write(handle, inode, &iloc); @@ -2470,7 +2681,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) if (err) goto out_brelse; sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); - err = ext4_handle_dirty_super_now(handle, inode->i_sb); + err = ext4_handle_dirty_super(handle, inode->i_sb); } else { struct ext4_iloc iloc2; struct inode *i_prev = @@ -2518,7 +2729,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) return PTR_ERR(handle); retval = -ENOENT; - bh = ext4_find_entry(dir, &dentry->d_name, &de); + bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); if (!bh) goto end_rmdir; @@ -2583,7 +2794,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) ext4_handle_sync(handle); retval = -ENOENT; - bh = ext4_find_entry(dir, &dentry->d_name, &de); + bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); if (!bh) goto end_unlink; @@ -2765,8 +2976,39 @@ retry: return err; } -#define PARENT_INO(buffer, size) \ - (ext4_next_entry((struct ext4_dir_entry_2 *)(buffer), size)->inode) + +/* + * Try to find buffer head where contains the parent block. + * It should be the inode block if it is inlined or the 1st block + * if it is a normal dir. + */ +static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, + struct inode *inode, + int *retval, + struct ext4_dir_entry_2 **parent_de, + int *inlined) +{ + struct buffer_head *bh; + + if (!ext4_has_inline_data(inode)) { + if (!(bh = ext4_bread(handle, inode, 0, 0, retval))) { + if (!*retval) { + *retval = -EIO; + ext4_error(inode->i_sb, + "Directory hole detected on inode %lu\n", + inode->i_ino); + } + return NULL; + } + *parent_de = ext4_next_entry( + (struct ext4_dir_entry_2 *)bh->b_data, + inode->i_sb->s_blocksize); + return bh; + } + + *inlined = 1; + return ext4_get_first_inline_block(inode, parent_de, retval); +} /* * Anybody can rename anything with this: the permission checks are left to the @@ -2780,6 +3022,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, struct buffer_head *old_bh, *new_bh, *dir_bh; struct ext4_dir_entry_2 *old_de, *new_de; int retval, force_da_alloc = 0; + int inlined = 0, new_inlined = 0; + struct ext4_dir_entry_2 *parent_de; dquot_initialize(old_dir); dquot_initialize(new_dir); @@ -2799,7 +3043,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) ext4_handle_sync(handle); - old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de); + old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de, NULL); /* * Check for inode number is _not_ due to possible IO errors. * We might rmdir the source, keep it as pwd of some process @@ -2812,7 +3056,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; new_inode = new_dentry->d_inode; - new_bh = ext4_find_entry(new_dir, &new_dentry->d_name, &new_de); + new_bh = ext4_find_entry(new_dir, &new_dentry->d_name, + &new_de, &new_inlined); if (new_bh) { if (!new_inode) { brelse(new_bh); @@ -2826,16 +3071,17 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; } retval = -EIO; - dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval); + dir_bh = ext4_get_first_dir_block(handle, old_inode, + &retval, &parent_de, + &inlined); if (!dir_bh) goto end_rename; - if (!buffer_verified(dir_bh) && + if (!inlined && !buffer_verified(dir_bh) && !ext4_dirent_csum_verify(old_inode, (struct ext4_dir_entry *)dir_bh->b_data)) goto end_rename; set_buffer_verified(dir_bh); - if (le32_to_cpu(PARENT_INO(dir_bh->b_data, - old_dir->i_sb->s_blocksize)) != old_dir->i_ino) + if (le32_to_cpu(parent_de->inode) != old_dir->i_ino) goto end_rename; retval = -EMLINK; if (!new_inode && new_dir != old_dir && @@ -2864,10 +3110,13 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, ext4_current_time(new_dir); ext4_mark_inode_dirty(handle, new_dir); BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata"); - retval = ext4_handle_dirty_dirent_node(handle, new_dir, new_bh); - if (unlikely(retval)) { - ext4_std_error(new_dir->i_sb, retval); - goto end_rename; + if (!new_inlined) { + retval = ext4_handle_dirty_dirent_node(handle, + new_dir, new_bh); + if (unlikely(retval)) { + ext4_std_error(new_dir->i_sb, retval); + goto end_rename; + } } brelse(new_bh); new_bh = NULL; @@ -2895,7 +3144,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, struct buffer_head *old_bh2; struct ext4_dir_entry_2 *old_de2; - old_bh2 = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de2); + old_bh2 = ext4_find_entry(old_dir, &old_dentry->d_name, + &old_de2, NULL); if (old_bh2) { retval = ext4_delete_entry(handle, old_dir, old_de2, old_bh2); @@ -2915,11 +3165,20 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, old_dir->i_ctime = old_dir->i_mtime = ext4_current_time(old_dir); ext4_update_dx_flag(old_dir); if (dir_bh) { - PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) = - cpu_to_le32(new_dir->i_ino); + parent_de->inode = cpu_to_le32(new_dir->i_ino); BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata"); - retval = ext4_handle_dirty_dirent_node(handle, old_inode, - dir_bh); + if (!inlined) { + if (is_dx(old_inode)) { + retval = ext4_handle_dirty_dx_node(handle, + old_inode, + dir_bh); + } else { + retval = ext4_handle_dirty_dirent_node(handle, + old_inode, dir_bh); + } + } else { + retval = ext4_mark_inode_dirty(handle, old_inode); + } if (retval) { ext4_std_error(old_dir->i_sb, retval); goto end_rename; @@ -2969,23 +3228,19 @@ const struct inode_operations ext4_dir_inode_operations = { .mknod = ext4_mknod, .rename = ext4_rename, .setattr = ext4_setattr, -#ifdef CONFIG_EXT4_FS_XATTR .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = ext4_listxattr, .removexattr = generic_removexattr, -#endif .get_acl = ext4_get_acl, .fiemap = ext4_fiemap, }; const struct inode_operations ext4_special_inode_operations = { .setattr = ext4_setattr, -#ifdef CONFIG_EXT4_FS_XATTR .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = ext4_listxattr, .removexattr = generic_removexattr, -#endif .get_acl = ext4_get_acl, }; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index dcdeef169a6..0016fbca2a4 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -27,7 +27,6 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" -#include "ext4_extents.h" static struct kmem_cache *io_page_cachep, *io_end_cachep; @@ -71,6 +70,9 @@ void ext4_free_io_end(ext4_io_end_t *io) int i; BUG_ON(!io); + BUG_ON(!list_empty(&io->list)); + BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN); + if (io->page) put_page(io->page); for (i = 0; i < io->num_io_pages; i++) @@ -81,13 +83,8 @@ void ext4_free_io_end(ext4_io_end_t *io) kmem_cache_free(io_end_cachep, io); } -/* - * check a range of space and convert unwritten extents to written. - * - * Called with inode->i_mutex; we depend on this when we manipulate - * io->flag, since we could otherwise race with ext4_flush_completed_IO() - */ -int ext4_end_io_nolock(ext4_io_end_t *io) +/* check a range of space and convert unwritten extents to written. */ +static int ext4_end_io(ext4_io_end_t *io) { struct inode *inode = io->inode; loff_t offset = io->offset; @@ -106,63 +103,136 @@ int ext4_end_io_nolock(ext4_io_end_t *io) "(inode %lu, offset %llu, size %zd, error %d)", inode->i_ino, offset, size, ret); } - if (io->iocb) aio_complete(io->iocb, io->result, 0); if (io->flag & EXT4_IO_END_DIRECT) inode_dio_done(inode); /* Wake up anyone waiting on unwritten extent conversion */ - if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten)) - wake_up_all(ext4_ioend_wq(io->inode)); + if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) + wake_up_all(ext4_ioend_wq(inode)); return ret; } -/* - * work on completed aio dio IO, to convert unwritten extents to extents - */ -static void ext4_end_io_work(struct work_struct *work) +static void dump_completed_IO(struct inode *inode) +{ +#ifdef EXT4FS_DEBUG + struct list_head *cur, *before, *after; + ext4_io_end_t *io, *io0, *io1; + unsigned long flags; + + if (list_empty(&EXT4_I(inode)->i_completed_io_list)) { + ext4_debug("inode %lu completed_io list is empty\n", + inode->i_ino); + return; + } + + ext4_debug("Dump inode %lu completed_io list\n", inode->i_ino); + list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list) { + cur = &io->list; + before = cur->prev; + io0 = container_of(before, ext4_io_end_t, list); + after = cur->next; + io1 = container_of(after, ext4_io_end_t, list); + + ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n", + io, inode->i_ino, io0, io1); + } +#endif +} + +/* Add the io_end to per-inode completed end_io list. */ +void ext4_add_complete_io(ext4_io_end_t *io_end) { - ext4_io_end_t *io = container_of(work, ext4_io_end_t, work); - struct inode *inode = io->inode; - struct ext4_inode_info *ei = EXT4_I(inode); - unsigned long flags; + struct ext4_inode_info *ei = EXT4_I(io_end->inode); + struct workqueue_struct *wq; + unsigned long flags; + + BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN)); + wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq; spin_lock_irqsave(&ei->i_completed_io_lock, flags); - if (io->flag & EXT4_IO_END_IN_FSYNC) - goto requeue; - if (list_empty(&io->list)) { - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - goto free; + if (list_empty(&ei->i_completed_io_list)) { + io_end->flag |= EXT4_IO_END_QUEUED; + queue_work(wq, &io_end->work); } + list_add_tail(&io_end->list, &ei->i_completed_io_list); + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); +} - if (!mutex_trylock(&inode->i_mutex)) { - bool was_queued; -requeue: - was_queued = !!(io->flag & EXT4_IO_END_QUEUED); - io->flag |= EXT4_IO_END_QUEUED; - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - /* - * Requeue the work instead of waiting so that the work - * items queued after this can be processed. - */ - queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work); - /* - * To prevent the ext4-dio-unwritten thread from keeping - * requeueing end_io requests and occupying cpu for too long, - * yield the cpu if it sees an end_io request that has already - * been requeued. - */ - if (was_queued) - yield(); - return; +static int ext4_do_flush_completed_IO(struct inode *inode, + ext4_io_end_t *work_io) +{ + ext4_io_end_t *io; + struct list_head unwritten, complete, to_free; + unsigned long flags; + struct ext4_inode_info *ei = EXT4_I(inode); + int err, ret = 0; + + INIT_LIST_HEAD(&complete); + INIT_LIST_HEAD(&to_free); + + spin_lock_irqsave(&ei->i_completed_io_lock, flags); + dump_completed_IO(inode); + list_replace_init(&ei->i_completed_io_list, &unwritten); + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); + + while (!list_empty(&unwritten)) { + io = list_entry(unwritten.next, ext4_io_end_t, list); + BUG_ON(!(io->flag & EXT4_IO_END_UNWRITTEN)); + list_del_init(&io->list); + + err = ext4_end_io(io); + if (unlikely(!ret && err)) + ret = err; + + list_add_tail(&io->list, &complete); + } + spin_lock_irqsave(&ei->i_completed_io_lock, flags); + while (!list_empty(&complete)) { + io = list_entry(complete.next, ext4_io_end_t, list); + io->flag &= ~EXT4_IO_END_UNWRITTEN; + /* end_io context can not be destroyed now because it still + * used by queued worker. Worker thread will destroy it later */ + if (io->flag & EXT4_IO_END_QUEUED) + list_del_init(&io->list); + else + list_move(&io->list, &to_free); + } + /* If we are called from worker context, it is time to clear queued + * flag, and destroy it's end_io if it was converted already */ + if (work_io) { + work_io->flag &= ~EXT4_IO_END_QUEUED; + if (!(work_io->flag & EXT4_IO_END_UNWRITTEN)) + list_add_tail(&work_io->list, &to_free); } - list_del_init(&io->list); spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - (void) ext4_end_io_nolock(io); - mutex_unlock(&inode->i_mutex); -free: - ext4_free_io_end(io); + + while (!list_empty(&to_free)) { + io = list_entry(to_free.next, ext4_io_end_t, list); + list_del_init(&io->list); + ext4_free_io_end(io); + } + return ret; +} + +/* + * work on completed aio dio IO, to convert unwritten extents to extents + */ +static void ext4_end_io_work(struct work_struct *work) +{ + ext4_io_end_t *io = container_of(work, ext4_io_end_t, work); + ext4_do_flush_completed_IO(io->inode, io); +} + +int ext4_flush_unwritten_io(struct inode *inode) +{ + int ret; + WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex) && + !(inode->i_state & I_FREEING)); + ret = ext4_do_flush_completed_IO(inode, NULL); + ext4_unwritten_wait(inode); + return ret; } ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) @@ -195,9 +265,7 @@ static void buffer_io_error(struct buffer_head *bh) static void ext4_end_bio(struct bio *bio, int error) { ext4_io_end_t *io_end = bio->bi_private; - struct workqueue_struct *wq; struct inode *inode; - unsigned long flags; int i; sector_t bi_sector = bio->bi_sector; @@ -255,14 +323,7 @@ static void ext4_end_bio(struct bio *bio, int error) return; } - /* Add the io_end to per-inode completed io list*/ - spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); - list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list); - spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); - - wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq; - /* queue the work to convert unwritten extents to written */ - queue_work(wq, &io_end->work); + ext4_add_complete_io(io_end); } void ext4_io_submit(struct ext4_io_submit *io) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 7ea6cbb4412..d99387b89ed 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -45,6 +45,28 @@ void ext4_resize_end(struct super_block *sb) smp_mb__after_clear_bit(); } +static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb, + ext4_group_t group) { + return (group >> EXT4_DESC_PER_BLOCK_BITS(sb)) << + EXT4_DESC_PER_BLOCK_BITS(sb); +} + +static ext4_fsblk_t ext4_meta_bg_first_block_no(struct super_block *sb, + ext4_group_t group) { + group = ext4_meta_bg_first_group(sb, group); + return ext4_group_first_block_no(sb, group); +} + +static ext4_grpblk_t ext4_group_overhead_blocks(struct super_block *sb, + ext4_group_t group) { + ext4_grpblk_t overhead; + overhead = ext4_bg_num_gdb(sb, group); + if (ext4_bg_has_super(sb, group)) + overhead += 1 + + le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks); + return overhead; +} + #define outside(b, first, last) ((b) < (first) || (b) >= (last)) #define inside(b, first, last) ((b) >= (first) && (b) < (last)) @@ -57,9 +79,7 @@ static int verify_group_input(struct super_block *sb, ext4_fsblk_t end = start + input->blocks_count; ext4_group_t group = input->group; ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group; - unsigned overhead = ext4_bg_has_super(sb, group) ? - (1 + ext4_bg_num_gdb(sb, group) + - le16_to_cpu(es->s_reserved_gdt_blocks)) : 0; + unsigned overhead = ext4_group_overhead_blocks(sb, group); ext4_fsblk_t metaend = start + overhead; struct buffer_head *bh = NULL; ext4_grpblk_t free_blocks_count, offset; @@ -200,13 +220,15 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd) * be a partial of a flex group. * * @sb: super block of fs to which the groups belongs + * + * Returns 0 on a successful allocation of the metadata blocks in the + * block group. */ -static void ext4_alloc_group_tables(struct super_block *sb, +static int ext4_alloc_group_tables(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, int flexbg_size) { struct ext4_new_group_data *group_data = flex_gd->groups; - struct ext4_super_block *es = EXT4_SB(sb)->s_es; ext4_fsblk_t start_blk; ext4_fsblk_t last_blk; ext4_group_t src_group; @@ -226,23 +248,24 @@ static void ext4_alloc_group_tables(struct super_block *sb, (last_group & ~(flexbg_size - 1)))); next_group: group = group_data[0].group; + if (src_group >= group_data[0].group + flex_gd->count) + return -ENOSPC; start_blk = ext4_group_first_block_no(sb, src_group); last_blk = start_blk + group_data[src_group - group].blocks_count; - overhead = ext4_bg_has_super(sb, src_group) ? - (1 + ext4_bg_num_gdb(sb, src_group) + - le16_to_cpu(es->s_reserved_gdt_blocks)) : 0; + overhead = ext4_group_overhead_blocks(sb, src_group); start_blk += overhead; - BUG_ON(src_group >= group_data[0].group + flex_gd->count); /* We collect contiguous blocks as much as possible. */ src_group++; - for (; src_group <= last_group; src_group++) - if (!ext4_bg_has_super(sb, src_group)) + for (; src_group <= last_group; src_group++) { + overhead = ext4_group_overhead_blocks(sb, src_group); + if (overhead != 0) last_blk += group_data[src_group - group].blocks_count; else break; + } /* Allocate block bitmaps */ for (; bb_index < flex_gd->count; bb_index++) { @@ -300,6 +323,7 @@ next_group: group_data[i].free_blocks_count); } } + return 0; } static struct buffer_head *bclean(handle_t *handle, struct super_block *sb, @@ -433,11 +457,13 @@ static int setup_new_flex_group_blocks(struct super_block *sb, ext4_group_t group, count; struct buffer_head *bh = NULL; int reserved_gdb, i, j, err = 0, err2; + int meta_bg; BUG_ON(!flex_gd->count || !group_data || group_data[0].group != sbi->s_groups_count); reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks); + meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); /* This transaction may be extended/restarted along the way */ handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA); @@ -447,12 +473,25 @@ static int setup_new_flex_group_blocks(struct super_block *sb, group = group_data[0].group; for (i = 0; i < flex_gd->count; i++, group++) { unsigned long gdblocks; + ext4_grpblk_t overhead; gdblocks = ext4_bg_num_gdb(sb, group); start = ext4_group_first_block_no(sb, group); + if (meta_bg == 0 && !ext4_bg_has_super(sb, group)) + goto handle_itb; + + if (meta_bg == 1) { + ext4_group_t first_group; + first_group = ext4_meta_bg_first_group(sb, group); + if (first_group != group + 1 && + first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1) + goto handle_itb; + } + + block = start + ext4_bg_has_super(sb, group); /* Copy all of the GDT blocks into the backup in this group */ - for (j = 0, block = start + 1; j < gdblocks; j++, block++) { + for (j = 0; j < gdblocks; j++, block++) { struct buffer_head *gdb; ext4_debug("update backup group %#04llx\n", block); @@ -493,6 +532,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb, goto out; } +handle_itb: /* Initialize group tables of the grop @group */ if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED)) goto handle_bb; @@ -521,11 +561,11 @@ handle_bb: err = PTR_ERR(bh); goto out; } - if (ext4_bg_has_super(sb, group)) { + overhead = ext4_group_overhead_blocks(sb, group); + if (overhead != 0) { ext4_debug("mark backup superblock %#04llx (+0)\n", start); - ext4_set_bits(bh->b_data, 0, gdblocks + reserved_gdb + - 1); + ext4_set_bits(bh->b_data, 0, overhead); } ext4_mark_bitmap_end(group_data[i].blocks_count, sb->s_blocksize * 8, bh->b_data); @@ -743,7 +783,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, err = ext4_journal_get_write_access(handle, gdb_bh); if (unlikely(err)) - goto exit_sbh; + goto exit_dind; err = ext4_journal_get_write_access(handle, dind); if (unlikely(err)) @@ -752,7 +792,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, /* ext4_reserve_inode_write() gets a reference on the iloc */ err = ext4_reserve_inode_write(handle, inode, &iloc); if (unlikely(err)) - goto exit_dindj; + goto exit_dind; n_group_desc = ext4_kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *), @@ -798,7 +838,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, ext4_kvfree(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); - err = ext4_handle_dirty_super_now(handle, sb); + err = ext4_handle_dirty_super(handle, sb); if (err) ext4_std_error(sb, err); @@ -806,12 +846,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, exit_inode: ext4_kvfree(n_group_desc); - /* ext4_handle_release_buffer(handle, iloc.bh); */ brelse(iloc.bh); -exit_dindj: - /* ext4_handle_release_buffer(handle, dind); */ -exit_sbh: - /* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */ exit_dind: brelse(dind); exit_bh: @@ -822,6 +857,45 @@ exit_bh: } /* + * add_new_gdb_meta_bg is the sister of add_new_gdb. + */ +static int add_new_gdb_meta_bg(struct super_block *sb, + handle_t *handle, ext4_group_t group) { + ext4_fsblk_t gdblock; + struct buffer_head *gdb_bh; + struct buffer_head **o_group_desc, **n_group_desc; + unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb); + int err; + + gdblock = ext4_meta_bg_first_block_no(sb, group) + + ext4_bg_has_super(sb, group); + gdb_bh = sb_bread(sb, gdblock); + if (!gdb_bh) + return -EIO; + n_group_desc = ext4_kvmalloc((gdb_num + 1) * + sizeof(struct buffer_head *), + GFP_NOFS); + if (!n_group_desc) { + err = -ENOMEM; + ext4_warning(sb, "not enough memory for %lu groups", + gdb_num + 1); + return err; + } + + o_group_desc = EXT4_SB(sb)->s_group_desc; + memcpy(n_group_desc, o_group_desc, + EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + n_group_desc[gdb_num] = gdb_bh; + EXT4_SB(sb)->s_group_desc = n_group_desc; + EXT4_SB(sb)->s_gdb_count++; + ext4_kvfree(o_group_desc); + err = ext4_journal_get_write_access(handle, gdb_bh); + if (unlikely(err)) + brelse(gdb_bh); + return err; +} + +/* * Called when we are adding a new group which has a backup copy of each of * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks. * We need to add these reserved backup GDT blocks to the resize inode, so @@ -890,14 +964,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, } for (i = 0; i < reserved_gdb; i++) { - if ((err = ext4_journal_get_write_access(handle, primary[i]))) { - /* - int j; - for (j = 0; j < i; j++) - ext4_handle_release_buffer(handle, primary[j]); - */ + if ((err = ext4_journal_get_write_access(handle, primary[i]))) goto exit_bh; - } } if ((err = ext4_reserve_inode_write(handle, inode, &iloc))) @@ -949,16 +1017,16 @@ exit_free: * 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) +static void update_backups(struct super_block *sb, int blk_off, char *data, + int size, int meta_bg) { struct ext4_sb_info *sbi = EXT4_SB(sb); - const ext4_group_t last = sbi->s_groups_count; + ext4_group_t last; const int bpg = EXT4_BLOCKS_PER_GROUP(sb); unsigned three = 1; unsigned five = 5; unsigned seven = 7; - ext4_group_t group; + ext4_group_t group = 0; int rest = sb->s_blocksize - size; handle_t *handle; int err = 0, err2; @@ -970,10 +1038,17 @@ static void update_backups(struct super_block *sb, goto exit_err; } - ext4_superblock_csum_set(sb, (struct ext4_super_block *)data); + if (meta_bg == 0) { + group = ext4_list_backups(sb, &three, &five, &seven); + last = sbi->s_groups_count; + } else { + group = ext4_meta_bg_first_group(sb, group) + 1; + last = (ext4_group_t)(group + EXT4_DESC_PER_BLOCK(sb) - 2); + } - while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) { + while (group < sbi->s_groups_count) { struct buffer_head *bh; + ext4_fsblk_t backup_block; /* Out of journal space, and can't get more - abort - so sad */ if (ext4_handle_valid(handle) && @@ -982,13 +1057,20 @@ static void update_backups(struct super_block *sb, (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA))) break; - bh = sb_getblk(sb, group * bpg + blk_off); + if (meta_bg == 0) + backup_block = group * bpg + blk_off; + else + backup_block = (ext4_group_first_block_no(sb, group) + + ext4_bg_has_super(sb, group)); + + bh = sb_getblk(sb, backup_block); if (!bh) { err = -EIO; break; } - ext4_debug("update metadata backup %#04lx\n", - (unsigned long)bh->b_blocknr); + ext4_debug("update metadata backup %llu(+%llu)\n", + backup_block, backup_block - + ext4_group_first_block_no(sb, group)); if ((err = ext4_journal_get_write_access(handle, bh))) break; lock_buffer(bh); @@ -1001,6 +1083,13 @@ static void update_backups(struct super_block *sb, if (unlikely(err)) ext4_std_error(sb, err); brelse(bh); + + if (meta_bg == 0) + group = ext4_list_backups(sb, &three, &five, &seven); + else if (group == last) + break; + else + group = last; } if ((err2 = ext4_journal_stop(handle)) && !err) err = err2; @@ -1043,7 +1132,9 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, struct ext4_super_block *es = sbi->s_es; struct buffer_head *gdb_bh; int i, gdb_off, gdb_num, err = 0; + int meta_bg; + meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); for (i = 0; i < count; i++, group++) { int reserved_gdb = ext4_bg_has_super(sb, group) ? le16_to_cpu(es->s_reserved_gdt_blocks) : 0; @@ -1063,8 +1154,11 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group)) err = reserve_backup_gdb(handle, resize_inode, group); - } else + } else if (meta_bg != 0) { + err = add_new_gdb_meta_bg(sb, handle, group); + } else { err = add_new_gdb(handle, resize_inode, group); + } if (err) break; } @@ -1076,17 +1170,12 @@ static struct buffer_head *ext4_get_bitmap(struct super_block *sb, __u64 block) struct buffer_head *bh = sb_getblk(sb, block); if (!bh) return NULL; - - if (bitmap_uptodate(bh)) - return bh; - - lock_buffer(bh); - if (bh_submit_read(bh) < 0) { - unlock_buffer(bh); - brelse(bh); - return NULL; + if (!bh_uptodate_or_lock(bh)) { + if (bh_submit_read(bh) < 0) { + brelse(bh); + return NULL; + } } - unlock_buffer(bh); return bh; } @@ -1112,8 +1201,7 @@ static int ext4_set_bitmap_checksums(struct super_block *sb, bh = ext4_get_bitmap(sb, group_data->block_bitmap); if (!bh) return -EIO; - ext4_block_bitmap_csum_set(sb, group, gdp, bh, - EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_block_bitmap_csum_set(sb, group, gdp, bh); brelse(bh); return 0; @@ -1161,6 +1249,9 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, ext4_free_group_clusters_set(sb, gdp, EXT4_B2C(sbi, group_data->free_blocks_count)); ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb)); + if (ext4_has_group_desc_csum(sb)) + ext4_itable_unused_set(sb, gdp, + EXT4_INODES_PER_GROUP(sb)); gdp->bg_flags = cpu_to_le16(*bg_flags); ext4_group_desc_csum_set(sb, group, gdp); @@ -1216,7 +1307,7 @@ static void ext4_update_super(struct super_block *sb, } reserved_blocks = ext4_r_blocks_count(es) * 100; - do_div(reserved_blocks, ext4_blocks_count(es)); + reserved_blocks = div64_u64(reserved_blocks, ext4_blocks_count(es)); reserved_blocks *= blocks_count; do_div(reserved_blocks, 100); @@ -1227,6 +1318,7 @@ static void ext4_update_super(struct super_block *sb, le32_add_cpu(&es->s_free_inodes_count, EXT4_INODES_PER_GROUP(sb) * flex_gd->count); + ext4_debug("free blocks count %llu", ext4_free_blocks_count(es)); /* * We need to protect s_groups_count against other CPUs seeing * inconsistent state in the superblock. @@ -1261,6 +1353,8 @@ static void ext4_update_super(struct super_block *sb, percpu_counter_add(&sbi->s_freeinodes_counter, EXT4_INODES_PER_GROUP(sb) * flex_gd->count); + ext4_debug("free blocks count %llu", + percpu_counter_read(&sbi->s_freeclusters_counter)); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) && sbi->s_log_groups_per_flex) { @@ -1272,6 +1366,11 @@ static void ext4_update_super(struct super_block *sb, &sbi->s_flex_groups[flex_group].free_inodes); } + /* + * Update the fs overhead information + */ + ext4_calculate_overhead(sb); + if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: added group %u:" "%llu blocks(%llu free %llu reserved)\n", flex_gd->count, @@ -1344,16 +1443,24 @@ exit_journal: err = err2; if (!err) { - int i; + int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); + int gdb_num_end = ((group + flex_gd->count - 1) / + EXT4_DESC_PER_BLOCK(sb)); + int meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_META_BG); + sector_t old_gdb = 0; + update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es, - sizeof(struct ext4_super_block)); - for (i = 0; i < flex_gd->count; i++, group++) { + sizeof(struct ext4_super_block), 0); + for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; - int gdb_num; - gdb_num = group / EXT4_BLOCKS_PER_GROUP(sb); + gdb_bh = sbi->s_group_desc[gdb_num]; + if (old_gdb == gdb_bh->b_blocknr) + continue; update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, - gdb_bh->b_size); + gdb_bh->b_size, meta_bg); + old_gdb = gdb_bh->b_blocknr; } } exit: @@ -1397,9 +1504,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb, group_data[i].group = group + i; group_data[i].blocks_count = blocks_per_group; - overhead = ext4_bg_has_super(sb, group + i) ? - (1 + ext4_bg_num_gdb(sb, group + i) + - le16_to_cpu(es->s_reserved_gdt_blocks)) : 0; + overhead = ext4_group_overhead_blocks(sb, group + i); group_data[i].free_blocks_count = blocks_per_group - overhead; if (ext4_has_group_desc_csum(sb)) flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT | @@ -1487,6 +1592,14 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) if (err) goto out; + err = ext4_alloc_flex_bg_array(sb, input->group + 1); + if (err) + return err; + + err = ext4_mb_alloc_groupinfo(sb, input->group + 1); + if (err) + goto out; + flex_gd.count = 1; flex_gd.groups = input; flex_gd.bg_flags = &bg_flags; @@ -1539,11 +1652,13 @@ errout: err = err2; if (!err) { + ext4_fsblk_t first_block; + first_block = ext4_group_first_block_no(sb, 0); if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: extended group to %llu " "blocks\n", ext4_blocks_count(es)); - update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es, - sizeof(struct ext4_super_block)); + update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr - first_block, + (char *)es, sizeof(struct ext4_super_block), 0); } return err; } @@ -1626,6 +1741,94 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, return err; } /* ext4_group_extend */ + +static int num_desc_blocks(struct super_block *sb, ext4_group_t groups) +{ + return (groups + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); +} + +/* + * Release the resize inode and drop the resize_inode feature if there + * are no more reserved gdt blocks, and then convert the file system + * to enable meta_bg + */ +static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) +{ + handle_t *handle; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + struct ext4_inode_info *ei = EXT4_I(inode); + ext4_fsblk_t nr; + int i, ret, err = 0; + int credits = 1; + + ext4_msg(sb, KERN_INFO, "Converting file system to meta_bg"); + if (inode) { + if (es->s_reserved_gdt_blocks) { + ext4_error(sb, "Unexpected non-zero " + "s_reserved_gdt_blocks"); + return -EPERM; + } + + /* Do a quick sanity check of the resize inode */ + if (inode->i_blocks != 1 << (inode->i_blkbits - 9)) + goto invalid_resize_inode; + for (i = 0; i < EXT4_N_BLOCKS; i++) { + if (i == EXT4_DIND_BLOCK) { + if (ei->i_data[i]) + continue; + else + goto invalid_resize_inode; + } + if (ei->i_data[i]) + goto invalid_resize_inode; + } + credits += 3; /* block bitmap, bg descriptor, resize inode */ + } + + handle = ext4_journal_start_sb(sb, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + err = ext4_journal_get_write_access(handle, sbi->s_sbh); + if (err) + goto errout; + + EXT4_CLEAR_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE); + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); + sbi->s_es->s_first_meta_bg = + cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count)); + + err = ext4_handle_dirty_super(handle, sb); + if (err) { + ext4_std_error(sb, err); + goto errout; + } + + if (inode) { + nr = le32_to_cpu(ei->i_data[EXT4_DIND_BLOCK]); + ext4_free_blocks(handle, inode, NULL, nr, 1, + EXT4_FREE_BLOCKS_METADATA | + EXT4_FREE_BLOCKS_FORGET); + ei->i_data[EXT4_DIND_BLOCK] = 0; + inode->i_blocks = 0; + + err = ext4_mark_inode_dirty(handle, inode); + if (err) + ext4_std_error(sb, err); + } + +errout: + ret = ext4_journal_stop(handle); + if (!err) + err = ret; + return ret; + +invalid_resize_inode: + ext4_error(sb, "corrupted/inconsistent resize inode"); + return -EINVAL; +} + /* * ext4_resize_fs() resizes a fs to new size specified by @n_blocks_count * @@ -1638,21 +1841,31 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct buffer_head *bh; - struct inode *resize_inode; - ext4_fsblk_t o_blocks_count; - ext4_group_t o_group; - ext4_group_t n_group; - ext4_grpblk_t offset, add; + struct inode *resize_inode = NULL; + ext4_grpblk_t add, offset; unsigned long n_desc_blocks; unsigned long o_desc_blocks; - unsigned long desc_blocks; - int err = 0, flexbg_size = 1; + ext4_group_t o_group; + ext4_group_t n_group; + ext4_fsblk_t o_blocks_count; + ext4_fsblk_t n_blocks_count_retry = 0; + unsigned long last_update_time = 0; + int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex; + int meta_bg; + /* See if the device is actually as big as what was requested */ + bh = sb_bread(sb, n_blocks_count - 1); + if (!bh) { + ext4_warning(sb, "can't read last block, resize aborted"); + return -ENOSPC; + } + brelse(bh); + +retry: o_blocks_count = ext4_blocks_count(es); - if (test_opt(sb, DEBUG)) - ext4_msg(sb, KERN_DEBUG, "resizing filesystem from %llu " - "to %llu blocks", o_blocks_count, n_blocks_count); + ext4_msg(sb, KERN_INFO, "resizing filesystem from %llu " + "to %llu blocks", o_blocks_count, n_blocks_count); if (n_blocks_count < o_blocks_count) { /* On-line shrinking not supported */ @@ -1667,32 +1880,49 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset); ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset); - n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) / - EXT4_DESC_PER_BLOCK(sb); - o_desc_blocks = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / - EXT4_DESC_PER_BLOCK(sb); - desc_blocks = n_desc_blocks - o_desc_blocks; + n_desc_blocks = num_desc_blocks(sb, n_group + 1); + o_desc_blocks = num_desc_blocks(sb, sbi->s_groups_count); - if (desc_blocks && - (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE) || - le16_to_cpu(es->s_reserved_gdt_blocks) < desc_blocks)) { - ext4_warning(sb, "No reserved GDT blocks, can't resize"); - return -EPERM; - } + meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); + + if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE)) { + if (meta_bg) { + ext4_error(sb, "resize_inode and meta_bg enabled " + "simultaneously"); + return -EINVAL; + } + if (n_desc_blocks > o_desc_blocks + + le16_to_cpu(es->s_reserved_gdt_blocks)) { + n_blocks_count_retry = n_blocks_count; + n_desc_blocks = o_desc_blocks + + le16_to_cpu(es->s_reserved_gdt_blocks); + n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb); + n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb); + n_group--; /* set to last group number */ + } - resize_inode = ext4_iget(sb, EXT4_RESIZE_INO); - if (IS_ERR(resize_inode)) { - ext4_warning(sb, "Error opening resize inode"); - return PTR_ERR(resize_inode); + if (!resize_inode) + resize_inode = ext4_iget(sb, EXT4_RESIZE_INO); + if (IS_ERR(resize_inode)) { + ext4_warning(sb, "Error opening resize inode"); + return PTR_ERR(resize_inode); + } } - /* See if the device is actually as big as what was requested */ - bh = sb_bread(sb, n_blocks_count - 1); - if (!bh) { - ext4_warning(sb, "can't read last block, resize aborted"); - return -ENOSPC; + if ((!resize_inode && !meta_bg) || n_blocks_count == o_blocks_count) { + err = ext4_convert_meta_bg(sb, resize_inode); + if (err) + goto out; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } + if (n_blocks_count_retry) { + n_blocks_count = n_blocks_count_retry; + n_blocks_count_retry = 0; + goto retry; + } } - brelse(bh); /* extend the last group */ if (n_group == o_group) @@ -1705,12 +1935,15 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) goto out; } - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) && - es->s_log_groups_per_flex) - flexbg_size = 1 << es->s_log_groups_per_flex; + if (ext4_blocks_count(es) == n_blocks_count) + goto out; - o_blocks_count = ext4_blocks_count(es); - if (o_blocks_count == n_blocks_count) + err = ext4_alloc_flex_bg_array(sb, n_group + 1); + if (err) + return err; + + err = ext4_mb_alloc_groupinfo(sb, n_group + 1); + if (err) goto out; flex_gd = alloc_flex_gd(flexbg_size); @@ -1724,19 +1957,33 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) */ while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count, flexbg_size)) { - ext4_alloc_group_tables(sb, flex_gd, flexbg_size); + if (jiffies - last_update_time > HZ * 10) { + if (last_update_time) + ext4_msg(sb, KERN_INFO, + "resized to %llu blocks", + ext4_blocks_count(es)); + last_update_time = jiffies; + } + if (ext4_alloc_group_tables(sb, flex_gd, flexbg_size) != 0) + break; err = ext4_flex_group_add(sb, resize_inode, flex_gd); if (unlikely(err)) break; } + if (!err && n_blocks_count_retry) { + n_blocks_count = n_blocks_count_retry; + n_blocks_count_retry = 0; + free_flex_gd(flex_gd); + flex_gd = NULL; + goto retry; + } + out: if (flex_gd) free_flex_gd(flex_gd); - - iput(resize_inode); - if (test_opt(sb, DEBUG)) - ext4_msg(sb, KERN_DEBUG, "resized filesystem from %llu " - "upto %llu blocks", o_blocks_count, n_blocks_count); + if (resize_inode != NULL) + iput(resize_inode); + ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count); return err; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eb7aa3e4ef0..3d4fb81bacd 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -45,7 +45,7 @@ #include <linux/freezer.h> #include "ext4.h" -#include "ext4_extents.h" +#include "ext4_extents.h" /* Needed for trace points definition */ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" @@ -74,7 +74,6 @@ static const char *ext4_decode_error(struct super_block *sb, int errno, static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); -static void ext4_write_super(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data); @@ -144,9 +143,10 @@ int ext4_superblock_csum_verify(struct super_block *sb, return es->s_checksum == ext4_superblock_csum(sb, es); } -void ext4_superblock_csum_set(struct super_block *sb, - struct ext4_super_block *es) +void ext4_superblock_csum_set(struct super_block *sb) { + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) return; @@ -327,38 +327,17 @@ static void ext4_put_nojournal(handle_t *handle) /* * Wrappers for jbd2_journal_start/end. - * - * The only special thing we need to do here is to make sure that all - * journal_end calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - * - * To avoid j_barrier hold in userspace when a user calls freeze(), - * ext4 prevents a new handle from being started by s_frozen, which - * is in an upper layer. */ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) { journal_t *journal; - handle_t *handle; trace_ext4_journal_start(sb, nblocks, _RET_IP_); if (sb->s_flags & MS_RDONLY) return ERR_PTR(-EROFS); + WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE); journal = EXT4_SB(sb)->s_journal; - handle = ext4_journal_current_handle(); - - /* - * If a handle has been started, it should be allowed to - * finish, otherwise deadlock could happen between freeze - * and others(e.g. truncate) due to the restart of the - * journal handle if the filesystem is forzen and active - * handles are not stopped. - */ - if (!handle) - vfs_check_frozen(sb, SB_FREEZE_TRANS); - if (!journal) return ext4_get_nojournal(); /* @@ -373,12 +352,6 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) return jbd2_journal_start(journal, nblocks); } -/* - * The only special thing we need to do here is to make sure that all - * jbd2_journal_stop calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - */ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) { struct super_block *sb; @@ -448,7 +421,7 @@ static void __save_error_info(struct super_block *sb, const char *func, */ if (!es->s_error_count) mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ); - es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1); + le32_add_cpu(&es->s_error_count, 1); } static void save_error_info(struct super_block *sb, const char *func, @@ -878,7 +851,6 @@ static void ext4_put_super(struct super_block *sb) flush_workqueue(sbi->dio_unwritten_wq); destroy_workqueue(sbi->dio_unwritten_wq); - lock_super(sb); if (sbi->s_journal) { err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; @@ -896,7 +868,7 @@ static void ext4_put_super(struct super_block *sb) EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); } - if (sb->s_dirt || !(sb->s_flags & MS_RDONLY)) + if (!(sb->s_flags & MS_RDONLY)) ext4_commit_super(sb, 1); if (sbi->s_proc) { @@ -945,7 +917,6 @@ static void ext4_put_super(struct super_block *sb) * Now that we are completely done shutting down the * superblock, we need to actually destroy the kobject. */ - unlock_super(sb); kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); if (sbi->s_chksum_driver) @@ -968,14 +939,16 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) return NULL; ei->vfs_inode.i_version = 1; - ei->vfs_inode.i_data.writeback_index = 0; memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache)); INIT_LIST_HEAD(&ei->i_prealloc_list); spin_lock_init(&ei->i_prealloc_lock); + ext4_es_init_tree(&ei->i_es_tree); + rwlock_init(&ei->i_es_lock); ei->i_reserved_data_blocks = 0; ei->i_reserved_meta_blocks = 0; ei->i_allocated_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; + ei->i_da_metadata_calc_last_lblock = 0; spin_lock_init(&(ei->i_block_reservation_lock)); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; @@ -983,11 +956,10 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_completed_io_list); spin_lock_init(&ei->i_completed_io_lock); - ei->cur_aio_dio = NULL; ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_ioend_count, 0); - atomic_set(&ei->i_aiodio_unwritten, 0); + atomic_set(&ei->i_unwritten, 0); return &ei->vfs_inode; } @@ -1025,9 +997,7 @@ static void init_once(void *foo) struct ext4_inode_info *ei = (struct ext4_inode_info *) foo; INIT_LIST_HEAD(&ei->i_orphan); -#ifdef CONFIG_EXT4_FS_XATTR init_rwsem(&ei->xattr_sem); -#endif init_rwsem(&ei->i_data_sem); inode_init_once(&ei->vfs_inode); } @@ -1046,6 +1016,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ext4_inode_cachep); } @@ -1055,6 +1030,7 @@ void ext4_clear_inode(struct inode *inode) clear_inode(inode); dquot_drop(inode); ext4_discard_preallocations(inode); + ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); if (EXT4_I(inode)->jinode) { jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode); @@ -1137,12 +1113,18 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, struct path *path); +static int ext4_quota_on_sysfile(struct super_block *sb, int type, + int format_id); static int ext4_quota_off(struct super_block *sb, int type); +static int ext4_quota_off_sysfile(struct super_block *sb, int type); static int ext4_quota_on_mount(struct super_block *sb, int type); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); +static int ext4_quota_enable(struct super_block *sb, int type, int format_id, + unsigned int flags); +static int ext4_enable_quotas(struct super_block *sb); static const struct dquot_operations ext4_quota_operations = { .get_reserved_space = ext4_get_reserved_space, @@ -1164,6 +1146,16 @@ static const struct quotactl_ops ext4_qctl_operations = { .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk }; + +static const struct quotactl_ops ext4_qctl_sysfile_operations = { + .quota_on_meta = ext4_quota_on_sysfile, + .quota_off = ext4_quota_off_sysfile, + .quota_sync = dquot_quota_sync, + .get_info = dquot_get_dqinfo, + .set_info = dquot_set_dqinfo, + .get_dqblk = dquot_get_dqblk, + .set_dqblk = dquot_set_dqblk +}; #endif static const struct super_operations ext4_sops = { @@ -1194,7 +1186,6 @@ static const struct super_operations ext4_nojournal_sops = { .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, - .write_super = ext4_write_super, .put_super = ext4_put_super, .statfs = ext4_statfs, .remount_fs = ext4_remount, @@ -1231,6 +1222,7 @@ enum { Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, + Opt_max_dir_size_kb, }; static const match_table_t tokens = { @@ -1304,6 +1296,7 @@ static const match_table_t tokens = { {Opt_init_itable, "init_itable=%u"}, {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, + {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1454,13 +1447,8 @@ static const struct mount_opts { {Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_DATAJ}, {Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_DATAJ}, {Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA, MOPT_DATAJ}, -#ifdef CONFIG_EXT4_FS_XATTR {Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET}, {Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR}, -#else - {Opt_user_xattr, 0, MOPT_NOSUPPORT}, - {Opt_nouser_xattr, 0, MOPT_NOSUPPORT}, -#endif #ifdef CONFIG_EXT4_FS_POSIX_ACL {Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET}, {Opt_noacl, EXT4_MOUNT_POSIX_ACL, MOPT_CLEAR}, @@ -1484,6 +1472,7 @@ static const struct mount_opts { {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT}, {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT}, {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT}, + {Opt_max_dir_size_kb, 0, MOPT_GTE0}, {Opt_err, 0, 0} }; @@ -1599,6 +1588,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, if (!args->from) arg = EXT4_DEF_LI_WAIT_MULT; sbi->s_li_wait_mult = arg; + } else if (token == Opt_max_dir_size_kb) { + sbi->s_max_dir_size_kb = arg; } else if (token == Opt_stripe) { sbi->s_stripe = arg; } else if (m->flags & MOPT_DATAJ) { @@ -1654,9 +1645,7 @@ static int parse_options(char *options, struct super_block *sb, unsigned int *journal_ioprio, int is_remount) { -#ifdef CONFIG_QUOTA struct ext4_sb_info *sbi = EXT4_SB(sb); -#endif char *p; substring_t args[MAX_OPT_ARGS]; int token; @@ -1671,7 +1660,7 @@ static int parse_options(char *options, struct super_block *sb, * Initialize args struct so we know whether arg was * found; some options take optional arguments. */ - args[0].to = args[0].from = 0; + args[0].to = args[0].from = NULL; token = match_token(p, tokens, args); if (handle_mount_opt(sb, p, token, args, journal_devnum, journal_ioprio, is_remount) < 0) @@ -1705,6 +1694,16 @@ static int parse_options(char *options, struct super_block *sb, } } #endif + if (test_opt(sb, DIOREAD_NOLOCK)) { + int blocksize = + BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); + + if (blocksize < PAGE_CACHE_SIZE) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "dioread_nolock if block size != PAGE_SIZE"); + return 0; + } + } return 1; } @@ -1747,7 +1746,7 @@ static inline void ext4_show_quota_options(struct seq_file *seq, static const char *token2str(int token) { - static const struct match_token *t; + const struct match_token *t; for (t = tokens; t->token != Opt_err; t++) if (t->token == token && !strchr(t->pattern, '=')) @@ -1830,6 +1829,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, if (nodefs || (test_opt(sb, INIT_INODE_TABLE) && (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT))) SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult); + if (nodefs || sbi->s_max_dir_size_kb) + SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); ext4_show_quota_options(seq, sb); return 0; @@ -1921,34 +1922,56 @@ done: return res; } +int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct flex_groups *new_groups; + int size; + + if (!sbi->s_log_groups_per_flex) + return 0; + + size = ext4_flex_group(sbi, ngroup - 1) + 1; + if (size <= sbi->s_flex_groups_allocated) + return 0; + + size = roundup_pow_of_two(size * sizeof(struct flex_groups)); + new_groups = ext4_kvzalloc(size, GFP_KERNEL); + if (!new_groups) { + ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", + size / (int) sizeof(struct flex_groups)); + return -ENOMEM; + } + + if (sbi->s_flex_groups) { + memcpy(new_groups, sbi->s_flex_groups, + (sbi->s_flex_groups_allocated * + sizeof(struct flex_groups))); + ext4_kvfree(sbi->s_flex_groups); + } + sbi->s_flex_groups = new_groups; + sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups); + return 0; +} + static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; - ext4_group_t flex_group_count; ext4_group_t flex_group; unsigned int groups_per_flex = 0; - size_t size; - int i; + int i, err; sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) { sbi->s_log_groups_per_flex = 0; return 1; } - groups_per_flex = 1 << sbi->s_log_groups_per_flex; - - /* We allocate both existing and potentially added groups */ - 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; - size = flex_group_count * sizeof(struct flex_groups); - sbi->s_flex_groups = ext4_kvzalloc(size, GFP_KERNEL); - if (sbi->s_flex_groups == NULL) { - ext4_msg(sb, KERN_ERR, "not enough memory for %u flex groups", - flex_group_count); + groups_per_flex = 1U << sbi->s_log_groups_per_flex; + + err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count); + if (err) goto failed; - } for (i = 0; i < sbi->s_groups_count; i++) { gdp = ext4_get_group_desc(sb, i, NULL); @@ -2151,10 +2174,12 @@ static void ext4_orphan_cleanup(struct super_block *sb, } if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { - if (es->s_last_orphan) + /* don't clear list on RO mount w/ errors */ + if (es->s_last_orphan && !(s_flags & MS_RDONLY)) { jbd_debug(1, "Errors on filesystem, " "clearing orphan list.\n"); - es->s_last_orphan = 0; + es->s_last_orphan = 0; + } jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); return; } @@ -2195,7 +2220,9 @@ static void ext4_orphan_cleanup(struct super_block *sb, __func__, inode->i_ino, inode->i_size); jbd_debug(2, "truncating inode %lu to %lld bytes\n", inode->i_ino, inode->i_size); + mutex_lock(&inode->i_mutex); ext4_truncate(inode); + mutex_unlock(&inode->i_mutex); nr_truncates++; } else { ext4_msg(sb, KERN_DEBUG, @@ -2535,6 +2562,7 @@ EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump); +EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error); static struct attribute *ext4_attrs[] = { @@ -2550,6 +2578,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_stream_req), ATTR_LIST(mb_group_prealloc), ATTR_LIST(max_writeback_mb_bump), + ATTR_LIST(extent_max_zeroout_kb), ATTR_LIST(trigger_fs_error), NULL, }; @@ -2557,10 +2586,12 @@ static struct attribute *ext4_attrs[] = { /* Features this copy of ext4 supports */ EXT4_INFO_ATTR(lazy_itable_init); EXT4_INFO_ATTR(batched_discard); +EXT4_INFO_ATTR(meta_bg_resize); static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(lazy_itable_init), ATTR_LIST(batched_discard), + ATTR_LIST(meta_bg_resize), NULL, }; @@ -2661,6 +2692,16 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) "extents feature\n"); return 0; } + +#ifndef CONFIG_QUOTA + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && + !readonly) { + ext4_msg(sb, KERN_ERR, + "Filesystem with quota feature cannot be mounted RDWR " + "without CONFIG_QUOTA"); + return 0; + } +#endif /* CONFIG_QUOTA */ return 1; } @@ -2723,6 +2764,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr) sb = elr->lr_super; ngroups = EXT4_SB(sb)->s_groups_count; + sb_start_write(sb); for (group = elr->lr_next_group; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { @@ -2749,6 +2791,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr) elr->lr_next_sched = jiffies + elr->lr_timeout; elr->lr_next_group = group + 1; } + sb_end_write(sb); return ret; } @@ -3085,6 +3128,121 @@ static int set_journal_csum_feature_set(struct super_block *sb) return ret; } +/* + * Note: calculating the overhead so we can be compatible with + * historical BSD practice is quite difficult in the face of + * clusters/bigalloc. This is because multiple metadata blocks from + * different block group can end up in the same allocation cluster. + * Calculating the exact overhead in the face of clustered allocation + * requires either O(all block bitmaps) in memory or O(number of block + * groups**2) in time. We will still calculate the superblock for + * older file systems --- and if we come across with a bigalloc file + * system with zero in s_overhead_clusters the estimate will be close to + * correct especially for very large cluster sizes --- but for newer + * file systems, it's better to calculate this figure once at mkfs + * time, and store it in the superblock. If the superblock value is + * present (even for non-bigalloc file systems), we will use it. + */ +static int count_overhead(struct super_block *sb, ext4_group_t grp, + char *buf) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp; + ext4_fsblk_t first_block, last_block, b; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + int s, j, count = 0; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) + return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + sbi->s_itb_per_group + 2); + + first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + + (grp * EXT4_BLOCKS_PER_GROUP(sb)); + last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1; + for (i = 0; i < ngroups; i++) { + gdp = ext4_get_group_desc(sb, i, NULL); + b = ext4_block_bitmap(sb, gdp); + if (b >= first_block && b <= last_block) { + ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); + count++; + } + b = ext4_inode_bitmap(sb, gdp); + if (b >= first_block && b <= last_block) { + ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); + count++; + } + b = ext4_inode_table(sb, gdp); + if (b >= first_block && b + sbi->s_itb_per_group <= last_block) + for (j = 0; j < sbi->s_itb_per_group; j++, b++) { + int c = EXT4_B2C(sbi, b - first_block); + ext4_set_bit(c, buf); + count++; + } + if (i != grp) + continue; + s = 0; + if (ext4_bg_has_super(sb, grp)) { + ext4_set_bit(s++, buf); + count++; + } + for (j = ext4_bg_num_gdb(sb, grp); j > 0; j--) { + ext4_set_bit(EXT4_B2C(sbi, s++), buf); + count++; + } + } + if (!count) + return 0; + return EXT4_CLUSTERS_PER_GROUP(sb) - + ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8); +} + +/* + * Compute the overhead and stash it in sbi->s_overhead + */ +int ext4_calculate_overhead(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + ext4_fsblk_t overhead = 0; + char *buf = (char *) get_zeroed_page(GFP_KERNEL); + + if (!buf) + return -ENOMEM; + + /* + * Compute the overhead (FS structures). This is constant + * for a given filesystem unless the number of block groups + * changes so we cache the previous value until it does. + */ + + /* + * All of the blocks before first_data_block are overhead + */ + overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); + + /* + * Add the overhead found in each block group + */ + for (i = 0; i < ngroups; i++) { + int blks; + + blks = count_overhead(sb, i, buf); + overhead += blks; + if (blks) + memset(buf, 0, PAGE_SIZE); + cond_resched(); + } + /* Add the journal blocks as well */ + if (sbi->s_journal) + overhead += EXT4_B2C(sbi, sbi->s_journal->j_maxlen); + + sbi->s_overhead = overhead; + smp_wmb(); + free_page((unsigned long) buf); + return 0; +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) { char *orig_data = kstrdup(data, GFP_KERNEL); @@ -3106,7 +3264,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) unsigned int i; int needs_recovery, has_huge_files, has_bigalloc; __u64 blocks_count; - int err; + int err = 0; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; ext4_group_t first_not_zeroed; @@ -3122,9 +3280,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_sb = sb; - sbi->s_mount_opt = 0; - sbi->s_resuid = make_kuid(&init_user_ns, EXT4_DEF_RESUID); - sbi->s_resgid = make_kgid(&init_user_ns, EXT4_DEF_RESGID); sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sb_block = sb_block; if (sb->s_bdev->bd_part) @@ -3135,6 +3290,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) for (cp = sb->s_id; (cp = strchr(cp, '/'));) *cp = '!'; + /* -EINVAL is default */ ret = -EINVAL; blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); if (!blocksize) { @@ -3219,9 +3375,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (def_mount_opts & EXT4_DEFM_UID16) set_opt(sb, NO_UID32); /* xattr user namespace & acls are now defaulted on */ -#ifdef CONFIG_EXT4_FS_XATTR set_opt(sb, XATTR_USER); -#endif #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif @@ -3257,7 +3411,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * enable delayed allocation by default * Use -o nodelalloc to turn it off */ - if (!IS_EXT3_SB(sb) && + if (!IS_EXT3_SB(sb) && !IS_EXT2_SB(sb) && ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0)) set_opt(sb, DELALLOC); @@ -3296,15 +3450,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) clear_opt(sb, DELALLOC); } - blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); - if (test_opt(sb, DIOREAD_NOLOCK)) { - if (blocksize < PAGE_SIZE) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "dioread_nolock if block size != PAGE_SIZE"); - goto failed_mount; - } - } - sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0); @@ -3346,6 +3491,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY))) goto failed_mount; + blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); if (blocksize < EXT4_MIN_BLOCK_SIZE || blocksize > EXT4_MAX_BLOCK_SIZE) { ext4_msg(sb, KERN_ERR, @@ -3512,7 +3658,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) " too large to mount safely on this system"); if (sizeof(sector_t) < 8) ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); - ret = err; goto failed_mount; } @@ -3620,12 +3765,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (err) { ext4_msg(sb, KERN_ERR, "insufficient memory"); - ret = err; goto failed_mount3; } sbi->s_stripe = ext4_get_stripe_size(sbi); sbi->s_max_writeback_mb_bump = 128; + sbi->s_extent_max_zeroout_kb = 32; /* * set up enough so that it can read an inode @@ -3640,12 +3785,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->s_qcop = &ext4_qctl_operations; sb->dq_op = &ext4_quota_operations; + + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) { + /* Use qctl operations for hidden quota files. */ + sb->s_qcop = &ext4_qctl_sysfile_operations; + } #endif memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); - sbi->s_resize_flags = 0; sb->s_root = NULL; @@ -3735,6 +3884,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) no_journal: /* + * Get the # of file system overhead blocks from the + * superblock if present. + */ + if (es->s_overhead_clusters) + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + else { + err = ext4_calculate_overhead(sb); + if (err) + goto failed_mount_wq; + } + + /* * The maximum number of concurrent works can be high and * concurrency isn't really necessary. Limit it to 1. */ @@ -3742,6 +3903,7 @@ no_journal: alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!EXT4_SB(sb)->dio_unwritten_wq) { printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n"); + ret = -ENOMEM; goto failed_mount_wq; } @@ -3840,6 +4002,24 @@ no_journal: } else descr = "out journal"; +#ifdef CONFIG_QUOTA + /* Enable quota usage during mount. */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && + !(sb->s_flags & MS_RDONLY)) { + err = ext4_enable_quotas(sb); + if (err) + goto failed_mount7; + } +#endif /* CONFIG_QUOTA */ + + if (test_opt(sb, DISCARD)) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); + if (!blk_queue_discard(q)) + ext4_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but " + "the device does not support discard"); + } + ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts, *sbi->s_es->s_mount_opts ? "; " : "", orig_data); @@ -3906,7 +4086,7 @@ out_fail: kfree(sbi); out_free_orig: kfree(orig_data); - return ret; + return err ? err : ret; } /* @@ -4203,9 +4383,8 @@ static int ext4_commit_super(struct super_block *sb, int sync) 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"); - ext4_superblock_csum_set(sb, es); + ext4_superblock_csum_set(sb); mark_buffer_dirty(sbh); if (sync) { error = sync_dirty_buffer(sbh); @@ -4286,6 +4465,7 @@ static void ext4_clear_journal_err(struct super_block *sb, ext4_commit_super(sb, 1); jbd2_journal_clear_err(journal); + jbd2_journal_update_sb_errno(journal); } } @@ -4302,21 +4482,12 @@ int ext4_force_commit(struct super_block *sb) return 0; journal = EXT4_SB(sb)->s_journal; - if (journal) { - vfs_check_frozen(sb, SB_FREEZE_TRANS); + if (journal) ret = ext4_journal_force_commit(journal); - } return ret; } -static void ext4_write_super(struct super_block *sb) -{ - lock_super(sb); - ext4_commit_super(sb, 1); - unlock_super(sb); -} - static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; @@ -4325,6 +4496,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait) trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->dio_unwritten_wq); + /* + * Writeback quota in non-journalled quota case - journalled quota has + * no dirty dquots + */ + dquot_writeback_dquots(sb, -1); if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) jbd2_log_wait_commit(sbi->s_journal, target); @@ -4337,9 +4513,8 @@ static int ext4_sync_fs(struct super_block *sb, int wait) * gives us a chance to flush the journal completely and mark the fs clean. * * Note that only this function cannot bring a filesystem to be in a clean - * state independently, because ext4 prevents a new handle from being started - * by @sb->s_frozen, which stays in an upper layer. It thus needs help from - * the upper layer. + * state independently. It relies on upper layer to stop all data & metadata + * modifications. */ static int ext4_freeze(struct super_block *sb) { @@ -4366,7 +4541,7 @@ static int ext4_freeze(struct super_block *sb) EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); error = ext4_commit_super(sb, 1); out: - /* we rely on s_frozen to stop further updates */ + /* we rely on upper layer to stop further updates */ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); return error; } @@ -4380,11 +4555,9 @@ static int ext4_unfreeze(struct super_block *sb) 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); return 0; } @@ -4420,7 +4593,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) char *orig_data = kstrdup(data, GFP_KERNEL); /* Store the original options */ - lock_super(sb); old_sb_flags = sb->s_flags; old_opts.s_mount_opt = sbi->s_mount_opt; old_opts.s_mount_opt2 = sbi->s_mount_opt2; @@ -4559,7 +4731,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } ext4_setup_system_zone(sb); - if (sbi->s_journal == NULL) + if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY)) ext4_commit_super(sb, 1); #ifdef CONFIG_QUOTA @@ -4568,10 +4740,17 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (old_opts.s_qf_names[i] && old_opts.s_qf_names[i] != sbi->s_qf_names[i]) kfree(old_opts.s_qf_names[i]); + if (enable_quota) { + if (sb_any_quota_suspended(sb)) + dquot_resume(sb, -1); + else if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_QUOTA)) { + err = ext4_enable_quotas(sb); + if (err) + goto restore_opts; + } + } #endif - unlock_super(sb); - if (enable_quota) - dquot_resume(sb, -1); ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); kfree(orig_data); @@ -4595,72 +4774,25 @@ restore_opts: sbi->s_qf_names[i] = old_opts.s_qf_names[i]; } #endif - unlock_super(sb); kfree(orig_data); return err; } -/* - * Note: calculating the overhead so we can be compatible with - * historical BSD practice is quite difficult in the face of - * clusters/bigalloc. This is because multiple metadata blocks from - * different block group can end up in the same allocation cluster. - * Calculating the exact overhead in the face of clustered allocation - * requires either O(all block bitmaps) in memory or O(number of block - * groups**2) in time. We will still calculate the superblock for - * older file systems --- and if we come across with a bigalloc file - * system with zero in s_overhead_clusters the estimate will be close to - * correct especially for very large cluster sizes --- but for newer - * file systems, it's better to calculate this figure once at mkfs - * time, and store it in the superblock. If the superblock value is - * present (even for non-bigalloc file systems), we will use it. - */ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; - struct ext4_group_desc *gdp; + ext4_fsblk_t overhead = 0; u64 fsid; s64 bfree; - if (test_opt(sb, MINIX_DF)) { - sbi->s_overhead_last = 0; - } else if (es->s_overhead_clusters) { - sbi->s_overhead_last = le32_to_cpu(es->s_overhead_clusters); - } else if (sbi->s_blocks_last != ext4_blocks_count(es)) { - ext4_group_t i, ngroups = ext4_get_groups_count(sb); - ext4_fsblk_t overhead = 0; - - /* - * Compute the overhead (FS structures). This is constant - * for a given filesystem unless the number of block groups - * changes so we cache the previous value until it does. - */ - - /* - * All of the blocks before first_data_block are - * overhead - */ - overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); - - /* - * Add the overhead found in each block group - */ - for (i = 0; i < ngroups; i++) { - gdp = ext4_get_group_desc(sb, i, NULL); - overhead += ext4_num_overhead_clusters(sb, i, gdp); - cond_resched(); - } - sbi->s_overhead_last = overhead; - smp_wmb(); - sbi->s_blocks_last = ext4_blocks_count(es); - } + if (!test_opt(sb, MINIX_DF)) + overhead = sbi->s_overhead; buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; - buf->f_blocks = (ext4_blocks_count(es) - - EXT4_C2B(sbi, sbi->s_overhead_last)); + buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, overhead); bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ @@ -4693,7 +4825,7 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) static inline struct inode *dquot_to_inode(struct dquot *dquot) { - return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type]; + return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type]; } static int ext4_write_dquot(struct dquot *dquot) @@ -4830,6 +4962,74 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, return dquot_quota_on(sb, type, format_id, path); } +static int ext4_quota_enable(struct super_block *sb, int type, int format_id, + unsigned int flags) +{ + int err; + struct inode *qf_inode; + unsigned long qf_inums[MAXQUOTAS] = { + le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum) + }; + + BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)); + + if (!qf_inums[type]) + return -EPERM; + + qf_inode = ext4_iget(sb, qf_inums[type]); + if (IS_ERR(qf_inode)) { + ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]); + return PTR_ERR(qf_inode); + } + + err = dquot_enable(qf_inode, type, format_id, flags); + iput(qf_inode); + + return err; +} + +/* Enable usage tracking for all quota types. */ +static int ext4_enable_quotas(struct super_block *sb) +{ + int type, err = 0; + unsigned long qf_inums[MAXQUOTAS] = { + le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum) + }; + + sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; + for (type = 0; type < MAXQUOTAS; type++) { + if (qf_inums[type]) { + err = ext4_quota_enable(sb, type, QFMT_VFS_V1, + DQUOT_USAGE_ENABLED); + if (err) { + ext4_warning(sb, + "Failed to enable quota (type=%d) " + "tracking. Please run e2fsck to fix.", + type); + return err; + } + } + } + return 0; +} + +/* + * quota_on function that is used when QUOTA feature is set. + */ +static int ext4_quota_on_sysfile(struct super_block *sb, int type, + int format_id) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) + return -EINVAL; + + /* + * USAGE was enabled at mount time. Only need to enable LIMITS now. + */ + return ext4_quota_enable(sb, type, format_id, DQUOT_LIMITS_ENABLED); +} + static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; @@ -4856,6 +5056,18 @@ out: return dquot_quota_off(sb, type); } +/* + * quota_off function that is used when QUOTA feature is set. + */ +static int ext4_quota_off_sysfile(struct super_block *sb, int type) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) + return -EINVAL; + + /* Disable only the limits. */ + return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); +} + /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) @@ -5072,6 +5284,7 @@ static int __init ext4_init_fs(void) ext4_li_info = NULL; mutex_init(&ext4_li_mtx); + /* Build-time check for flags consistency */ ext4_check_flag_values(); for (i = 0; i < EXT4_WQ_HASH_SZ; i++) { @@ -5079,15 +5292,22 @@ static int __init ext4_init_fs(void) init_waitqueue_head(&ext4__ioend_wq[i]); } - err = ext4_init_pageio(); + err = ext4_init_es(); if (err) return err; + + err = ext4_init_pageio(); + if (err) + goto out7; + err = ext4_init_system_zone(); if (err) goto out6; ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj); - if (!ext4_kset) + if (!ext4_kset) { + err = -ENOMEM; goto out5; + } ext4_proc_root = proc_mkdir("fs/ext4", NULL); err = ext4_init_feat_adverts(); @@ -5129,6 +5349,9 @@ out5: ext4_exit_system_zone(); out6: ext4_exit_pageio(); +out7: + ext4_exit_es(); + return err; } diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index ed9354aff27..ff371193201 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -35,22 +35,18 @@ const struct inode_operations ext4_symlink_inode_operations = { .follow_link = page_follow_link_light, .put_link = page_put_link, .setattr = ext4_setattr, -#ifdef CONFIG_EXT4_FS_XATTR .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = ext4_listxattr, .removexattr = generic_removexattr, -#endif }; const struct inode_operations ext4_fast_symlink_inode_operations = { .readlink = generic_readlink, .follow_link = ext4_follow_link, .setattr = ext4_setattr, -#ifdef CONFIG_EXT4_FS_XATTR .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = ext4_listxattr, .removexattr = generic_removexattr, -#endif }; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index e56c9ed7d6e..3a91ebc2b66 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -61,11 +61,6 @@ #include "xattr.h" #include "acl.h" -#define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data)) -#define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr)) -#define BFIRST(bh) ENTRY(BHDR(bh)+1) -#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0) - #ifdef EXT4_XATTR_DEBUG # define ea_idebug(inode, f...) do { \ printk(KERN_DEBUG "inode %s:%lu: ", \ @@ -127,19 +122,16 @@ static __le32 ext4_xattr_block_csum(struct inode *inode, struct ext4_xattr_header *hdr) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - struct ext4_inode_info *ei = EXT4_I(inode); __u32 csum, old; old = hdr->h_checksum; hdr->h_checksum = 0; - if (le32_to_cpu(hdr->h_refcount) != 1) { - block_nr = cpu_to_le64(block_nr); - csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr, - sizeof(block_nr)); - } else - csum = ei->i_csum_seed; + block_nr = cpu_to_le64(block_nr); + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr, + sizeof(block_nr)); csum = ext4_chksum(sbi, csum, (__u8 *)hdr, EXT4_BLOCK_SIZE(inode->i_sb)); + hdr->h_checksum = old; return cpu_to_le32(csum); } @@ -315,7 +307,7 @@ cleanup: return error; } -static int +int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { @@ -584,21 +576,6 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last, return (*min_offs - ((void *)last - base) - sizeof(__u32)); } -struct ext4_xattr_info { - int name_index; - const char *name; - const void *value; - size_t value_len; -}; - -struct ext4_xattr_search { - struct ext4_xattr_entry *first; - void *base; - void *end; - struct ext4_xattr_entry *here; - int not_found; -}; - static int ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s) { @@ -651,9 +628,14 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s) size. Just replace. */ s->here->e_value_size = cpu_to_le32(i->value_len); - memset(val + size - EXT4_XATTR_PAD, 0, - EXT4_XATTR_PAD); /* Clear pad bytes. */ - memcpy(val, i->value, i->value_len); + if (i->value == EXT4_ZERO_XATTR_VALUE) { + memset(val, 0, size); + } else { + /* Clear pad bytes first. */ + memset(val + size - EXT4_XATTR_PAD, 0, + EXT4_XATTR_PAD); + memcpy(val, i->value, i->value_len); + } return 0; } @@ -692,9 +674,14 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s) size_t size = EXT4_XATTR_SIZE(i->value_len); void *val = s->base + min_offs - size; s->here->e_value_offs = cpu_to_le16(min_offs - size); - memset(val + size - EXT4_XATTR_PAD, 0, - EXT4_XATTR_PAD); /* Clear the pad bytes. */ - memcpy(val, i->value, i->value_len); + if (i->value == EXT4_ZERO_XATTR_VALUE) { + memset(val, 0, size); + } else { + /* Clear the pad bytes first. */ + memset(val + size - EXT4_XATTR_PAD, 0, + EXT4_XATTR_PAD); + memcpy(val, i->value, i->value_len); + } } } return 0; @@ -797,7 +784,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, int offset = (char *)s->here - bs->bh->b_data; unlock_buffer(bs->bh); - ext4_handle_release_buffer(handle, bs->bh); if (ce) { mb_cache_entry_release(ce); ce = NULL; @@ -953,14 +939,8 @@ bad_block: #undef header } -struct ext4_xattr_ibody_find { - struct ext4_xattr_search s; - struct ext4_iloc iloc; -}; - -static int -ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is) +int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is) { struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; @@ -988,10 +968,47 @@ ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, return 0; } -static int -ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is) +int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is) +{ + struct ext4_xattr_ibody_header *header; + struct ext4_xattr_search *s = &is->s; + int error; + + if (EXT4_I(inode)->i_extra_isize == 0) + return -ENOSPC; + error = ext4_xattr_set_entry(i, s); + if (error) { + if (error == -ENOSPC && + ext4_has_inline_data(inode)) { + error = ext4_try_to_evict_inline_data(handle, inode, + EXT4_XATTR_LEN(strlen(i->name) + + EXT4_XATTR_SIZE(i->value_len))); + if (error) + return error; + error = ext4_xattr_ibody_find(inode, i, is); + if (error) + return error; + error = ext4_xattr_set_entry(i, s); + } + if (error) + return error; + } + header = IHDR(inode, ext4_raw_inode(&is->iloc)); + if (!IS_LAST_ENTRY(s->first)) { + header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); + ext4_set_inode_state(inode, EXT4_STATE_XATTR); + } else { + header->h_magic = cpu_to_le32(0); + ext4_clear_inode_state(inode, EXT4_STATE_XATTR); + } + return 0; +} + +static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_search *s = &is->s; @@ -1147,9 +1164,17 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name, { handle_t *handle; int error, retries = 0; + int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb); retry: - handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb)); + /* + * In case of inline data, we may push out the data to a block, + * So reserve the journal space first. + */ + if (ext4_has_inline_data(inode)) + credits += ext4_writepage_trans_blocks(inode) + 1; + + handle = ext4_journal_start(inode, credits); if (IS_ERR(handle)) { error = PTR_ERR(handle); } else { diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 91f31ca7d9a..69eda787a96 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -21,6 +21,7 @@ #define EXT4_XATTR_INDEX_TRUSTED 4 #define EXT4_XATTR_INDEX_LUSTRE 5 #define EXT4_XATTR_INDEX_SECURITY 6 +#define EXT4_XATTR_INDEX_SYSTEM 7 struct ext4_xattr_header { __le32 h_magic; /* magic number for identification */ @@ -65,7 +66,32 @@ struct ext4_xattr_entry { EXT4_I(inode)->i_extra_isize)) #define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1)) -# ifdef CONFIG_EXT4_FS_XATTR +#define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data)) +#define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr)) +#define BFIRST(bh) ENTRY(BHDR(bh)+1) +#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0) + +#define EXT4_ZERO_XATTR_VALUE ((void *)-1) + +struct ext4_xattr_info { + int name_index; + const char *name; + const void *value; + size_t value_len; +}; + +struct ext4_xattr_search { + struct ext4_xattr_entry *first; + void *base; + void *end; + struct ext4_xattr_entry *here; + int not_found; +}; + +struct ext4_xattr_ibody_find { + struct ext4_xattr_search s; + struct ext4_iloc iloc; +}; extern const struct xattr_handler ext4_xattr_user_handler; extern const struct xattr_handler ext4_xattr_trusted_handler; @@ -90,60 +116,82 @@ extern void ext4_exit_xattr(void); extern const struct xattr_handler *ext4_xattr_handlers[]; -# else /* CONFIG_EXT4_FS_XATTR */ - -static inline int -ext4_xattr_get(struct inode *inode, int name_index, const char *name, - void *buffer, size_t size, int flags) -{ - return -EOPNOTSUPP; -} - -static inline int -ext4_xattr_set(struct inode *inode, int name_index, const char *name, - const void *value, size_t size, int flags) -{ - return -EOPNOTSUPP; -} - -static inline int -ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, - const char *name, const void *value, size_t size, int flags) -{ - return -EOPNOTSUPP; -} - -static inline void -ext4_xattr_delete_inode(handle_t *handle, struct inode *inode) -{ -} - -static inline void -ext4_xattr_put_super(struct super_block *sb) -{ -} - -static __init inline int -ext4_init_xattr(void) -{ - return 0; -} - -static inline void -ext4_exit_xattr(void) -{ -} - -static inline int -ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, - struct ext4_inode *raw_inode, handle_t *handle) -{ - return -EOPNOTSUPP; -} - -#define ext4_xattr_handlers NULL - -# endif /* CONFIG_EXT4_FS_XATTR */ +extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is); +extern int ext4_xattr_ibody_get(struct inode *inode, int name_index, + const char *name, + void *buffer, size_t buffer_size); +extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is); + +extern int ext4_has_inline_data(struct inode *inode); +extern int ext4_get_inline_size(struct inode *inode); +extern int ext4_get_max_inline_size(struct inode *inode); +extern int ext4_find_inline_data_nolock(struct inode *inode); +extern void ext4_write_inline_data(struct inode *inode, + struct ext4_iloc *iloc, + void *buffer, loff_t pos, + unsigned int len); +extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode, + unsigned int len); +extern int ext4_init_inline_data(handle_t *handle, struct inode *inode, + unsigned int len); +extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode); + +extern int ext4_readpage_inline(struct inode *inode, struct page *page); +extern int ext4_try_to_write_inline_data(struct address_space *mapping, + struct inode *inode, + loff_t pos, unsigned len, + unsigned flags, + struct page **pagep); +extern int ext4_write_inline_data_end(struct inode *inode, + loff_t pos, unsigned len, + unsigned copied, + struct page *page); +extern struct buffer_head * +ext4_journalled_write_inline_data(struct inode *inode, + unsigned len, + struct page *page); +extern int ext4_da_write_inline_data_begin(struct address_space *mapping, + struct inode *inode, + loff_t pos, unsigned len, + unsigned flags, + struct page **pagep, + void **fsdata); +extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, + unsigned len, unsigned copied, + struct page *page); +extern int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry, + struct inode *inode); +extern int ext4_try_create_inline_dir(handle_t *handle, + struct inode *parent, + struct inode *inode); +extern int ext4_read_inline_dir(struct file *filp, + void *dirent, filldir_t filldir, + int *has_inline_data); +extern struct buffer_head *ext4_find_inline_entry(struct inode *dir, + const struct qstr *d_name, + struct ext4_dir_entry_2 **res_dir, + int *has_inline_data); +extern int ext4_delete_inline_entry(handle_t *handle, + struct inode *dir, + struct ext4_dir_entry_2 *de_del, + struct buffer_head *bh, + int *has_inline_data); +extern int empty_inline_dir(struct inode *dir, int *has_inline_data); +extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode, + struct ext4_dir_entry_2 **parent_de, + int *retval); +extern int ext4_inline_data_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, + int *has_inline); +extern int ext4_try_to_evict_inline_data(handle_t *handle, + struct inode *inode, + int needed); +extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline); + +extern int ext4_convert_inline_data(struct inode *inode); #ifdef CONFIG_EXT4_FS_SECURITY extern int ext4_init_security(handle_t *handle, struct inode *inode, |