A large part of this code is from the generic VFS code in fs/ioctl.c in the upstream kernel. Index: linux-2.6.16.60-0.37/fs/ext3/ioctl.c =================================================================== --- linux-2.6.16.60-0.37.orig/fs/ext3/ioctl.c +++ linux-2.6.16.60-0.37/fs/ext3/ioctl.c @@ -15,7 +15,161 @@ #include #include #include +#include "fiemap.h" +/* So that the fiemap access checks can't overflow on 32 bit machines. */ +#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) + +/** + * fiemap_fill_next_extent - Fiemap helper function + * @fieinfo: Fiemap context passed into ->fiemap + * @logical: Extent logical start offset, in bytes + * @phys: Extent physical start offset, in bytes + * @len: Extent length, in bytes + * @flags: FIEMAP_EXTENT flags that describe this extent + * @lun: LUN on which this extent resides + * + * Called from file system ->fiemap callback. Will populate extent + * info as passed in via arguments and copy to user memory. On + * success, extent count on fieinfo is incremented. + * + * Returns 0 on success, -errno on error, 1 if this was the last + * extent that will fit in user array. + */ +#define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC) +#define SET_NO_DIRECT_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED \ + |FIEMAP_EXTENT_NET) +#define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED) +#define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE) +int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, + u64 phys, u64 len, u32 flags, dev_t dev) +{ + struct fiemap_extent extent = { 0 }; + struct fiemap_extent *dest = fieinfo->fi_extents_start; + + /* only count the extents */ + if (fieinfo->fi_extents_max == 0) { + fieinfo->fi_extents_mapped++; + return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; + } + + if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) + return 1; + + if (flags & SET_UNKNOWN_FLAGS) + flags |= FIEMAP_EXTENT_UNKNOWN; + if (flags & SET_NO_DIRECT_FLAGS) + flags |= FIEMAP_EXTENT_NO_DIRECT; + if (flags & SET_NOT_ALIGNED_FLAGS) + flags |= FIEMAP_EXTENT_NOT_ALIGNED; + if (flags & SET_NO_UNMOUNTED_IO_FLAGS) + flags |= FIEMAP_EXTENT_ENCODED; + + extent.fe_logical = logical; + extent.fe_physical = phys; + extent.fe_length = len; + extent.fe_flags = flags; + extent.fe_device = new_encode_dev(dev); + + dest += fieinfo->fi_extents_mapped; + if (copy_to_user(dest, &extent, sizeof(extent))) + return -EFAULT; + + fieinfo->fi_extents_mapped++; + if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) + return 1; + + return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; +} + +static int fiemap_check_ranges(struct super_block *sb, + u64 start, u64 len, u64 *new_len) +{ + *new_len = len; + + if (len == 0) + return -EINVAL; + + if (start > sb->s_maxbytes) + return -EFBIG; + + /* + * Shrink request scope to what the fs can actually handle. + */ + if ((len > sb->s_maxbytes) || + (sb->s_maxbytes - len) < start) + *new_len = sb->s_maxbytes - start; + + return 0; +} + +/* + * fiemap_check_flags - check validity of requested flags for fiemap + * @fieinfo: Fiemap context passed into ->fiemap + * @fs_flags: Set of fiemap flags that the file system understands + * + * Called from file system ->fiemap callback. This will compute the + * intersection of valid fiemap flags and those that the fs supports. That + * value is then compared against the user supplied flags. In case of bad user + * flags, the invalid values will be written into the fieinfo structure, and + * -EBADR is returned, which tells ioctl_fiemap() to return those values to + * userspace. For this reason, a return code of -EBADR should be preserved. + * + * Returns 0 on success, -EBADR on bad flags. +*/ +int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags) +{ + u32 incompat_flags; + + incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags); + if (incompat_flags) { + fieinfo->fi_flags = incompat_flags; + return -EBADR; + } + + return 0; +} + +int ioctl_fiemap(struct inode *inode, struct file *filp, unsigned long arg) +{ + struct fiemap fiemap; + u64 len; + struct fiemap_extent_info fieinfo = {0, }; + struct super_block *sb = inode->i_sb; + int error = 0; + + if (copy_from_user(&fiemap, (struct fiemap __user *) arg, + sizeof(struct fiemap))) + return -EFAULT; + + if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) + return -EINVAL; + + error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length, + &len); + if (error) + return error; + + fieinfo.fi_flags = fiemap.fm_flags; + fieinfo.fi_extents_max = fiemap.fm_extent_count; + fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap)); + + if (fiemap.fm_extent_count != 0 && + !access_ok(VERIFY_WRITE, (void *)arg, + offsetof(typeof(fiemap), fm_extents[fiemap.fm_extent_count]))) + return -EFAULT; + + if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC) + filemap_write_and_wait(inode->i_mapping); + + error = ext3_fiemap(inode, &fieinfo, fiemap.fm_start, len); + fiemap.fm_flags = fieinfo.fi_flags; + fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; + if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap))) + error = -EFAULT; + + return error; +} int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, unsigned long arg) @@ -262,7 +416,9 @@ flags_err: return err; } - + case EXT3_IOC_FIEMAP: { + return ioctl_fiemap(inode, filp, arg); + } default: return -ENOTTY; Index: linux-2.6.16.60-0.37/include/linux/ext3_fs.h =================================================================== --- linux-2.6.16.60-0.37.orig/include/linux/ext3_fs.h +++ linux-2.6.16.60-0.37/include/linux/ext3_fs.h @@ -261,15 +261,19 @@ struct ext3_new_group_data { #define EXT3_IOC_SETFLAGS _IOW('f', 2, long) #define EXT3_IOC_GETVERSION _IOR('f', 3, long) #define EXT3_IOC_SETVERSION _IOW('f', 4, long) +#define EXT3_IOC_GETRSVSZ _IOR('f', 5, long) +#define EXT3_IOC_SETRSVSZ _IOW('f', 6, long) #define EXT3_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) #define EXT3_IOC_GROUP_ADD _IOW('f', 8,struct ext3_new_group_input) +#define EXT3_IOC_FIEMAP _IOWR('f', 11, struct fiemap) #define EXT3_IOC_GETVERSION_OLD _IOR('v', 1, long) #define EXT3_IOC_SETVERSION_OLD _IOW('v', 2, long) #ifdef CONFIG_JBD_DEBUG #define EXT3_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) #endif -#define EXT3_IOC_GETRSVSZ _IOR('f', 5, long) -#define EXT3_IOC_SETRSVSZ _IOW('f', 6, long) + +/* FIEMAP flags supported by ext3 */ +#define EXT3_FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC) /* * Mount options @@ -997,6 +1001,9 @@ extern int ext3_writepage_trans_blocks(s /* ioctl.c */ extern int ext3_ioctl (struct inode *, struct file *, unsigned int, unsigned long); +struct fiemap_extent_info; +extern int ext3_fiemap(struct inode *, struct fiemap_extent_info *, __u64, + __u64); /* namei.c */ extern int ext3_orphan_add(handle_t *, struct inode *); Index: linux-2.6.16.60-0.37/include/linux/ext3_extents.h =================================================================== --- linux-2.6.16.60-0.37.orig/include/linux/ext3_extents.h +++ linux-2.6.16.60-0.37/include/linux/ext3_extents.h @@ -170,7 +170,10 @@ struct ext3_extents_helpers { */ typedef int (*ext_prepare_callback)(struct ext3_extents_tree *, struct ext3_ext_path *, - struct ext3_ext_cache *); + struct ext3_ext_cache *, + struct ext3_extent *); + +#define HAVE_EXT_PREPARE_CB_EXTENT #define EXT_CONTINUE 0 #define EXT_BREAK 1 @@ -180,6 +183,25 @@ typedef int (*ext_prepare_callback)(stru #define EXT_MAX_BLOCK 0xffffffff #define EXT_UNSET_BLOCK 1 +/* + * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an + * initialized extent. This is 2^15 and not (2^16 - 1), since we use the + * MSB of ee_len field in the extent datastructure to signify if this + * particular extent is an initialized extent or an uninitialized (i.e. + * preallocated). + * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an + * uninitialized extent. + * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an + * uninitialized one. In other words, if MSB of ee_len is set, it is an + * uninitialized extent with only one special scenario when ee_len = 0x8000. + * In this case we can not have an uninitialized extent of zero length and + * thus we make it as a special case of initialized extent with 0x8000 length. + * This way we get better extent-to-group alignment for initialized extents. + * Hence, the maximum number of blocks we can have in an *initialized* + * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767). + */ +#define EXT_INIT_MAX_LEN (1UL << 15) +#define EXT_UNINIT_MAX_LEN (EXT_INIT_MAX_LEN - 1) #define EXT_FIRST_EXTENT(__hdr__) \ ((struct ext3_extent *) (((char *) (__hdr__)) + \ @@ -243,6 +265,12 @@ struct ext3_extent_tree_stats { int leaf_num; }; +static inline int ext3_ext_is_uninitialized(struct ext3_extent *ext) +{ + /* Extent with ee_len of 0x8000 is treated as an initialized extent */ + return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN); +} + extern int ext3_ext_search_left(struct ext3_extents_tree *, struct ext3_ext_path *, unsigned long *, unsigned long *); extern int ext3_ext_search_right(struct ext3_extents_tree *, struct ext3_ext_path *, unsigned long *, unsigned long *); extern void ext3_init_tree_desc(struct ext3_extents_tree *, struct inode *); Index: linux-2.6.16.60-0.37/fs/ext3/extents.c =================================================================== --- linux-2.6.16.60-0.37.orig/fs/ext3/extents.c +++ linux-2.6.16.60-0.37/fs/ext3/extents.c @@ -41,6 +41,7 @@ #include #include #include +#include "fiemap.h" #include @@ -1488,7 +1489,7 @@ int ext3_ext_walk_space(struct ext3_exte EXT_ASSERT(cbex.ec_len > 0); EXT_ASSERT(path[depth].p_hdr); - err = func(tree, path, &cbex); + err = func(tree, path, &cbex, ex); ext3_ext_drop_refs(path); if (err < 0) @@ -2502,7 +2503,109 @@ int ext3_ext_calc_blockmap_metadata(stru ext3_init_tree_desc(&tree, inode); return ext3_ext_calc_metadata_amount(&tree, blocks); } - + +/* + * Callback function called for each extent to gather FIEMAP information. + */ +int ext3_ext_fiemap_cb(struct ext3_extents_tree *tree, + struct ext3_ext_path *path, struct ext3_ext_cache *newex, + struct ext3_extent *ex) +{ + struct fiemap_extent_info *fieinfo = (struct fiemap_extent_info *)tree->private; + struct inode *inode = tree->inode; + unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; + __u64 logical; + __u64 physical; + __u64 length; + __u32 flags = 0; + int error; + + logical = (__u64)newex->ec_block << blksize_bits; + + if (newex->ec_type == EXT3_EXT_CACHE_GAP) { + pgoff_t offset; + struct page *page; + struct buffer_head *bh = NULL; + + offset = logical >> PAGE_SHIFT; + page = find_get_page(inode->i_mapping, offset); + if (!page || !page_has_buffers(page)) + return EXT_CONTINUE; + + bh = page_buffers(page); + + if (!bh) + return EXT_CONTINUE; + + if (buffer_delay(bh)) { + flags |= FIEMAP_EXTENT_DELALLOC; + page_cache_release(page); + } else { + page_cache_release(page); + return EXT_CONTINUE; + } + } + + physical = (__u64)newex->ec_start << blksize_bits; + length = (__u64)newex->ec_len << blksize_bits; + + if (ex && ext3_ext_is_uninitialized(ex)) + flags |= FIEMAP_EXTENT_UNWRITTEN; + + /* + * If this extent reaches EXT_MAX_BLOCK, it must be last. + * + * Or if ext3_ext_next_allocated_block is EXT_MAX_BLOCK, + * this indicates no more allocated blocks. + * + * XXX this might miss a single-block extent at EXT_MAX_BLOCK + */ + if (ext3_ext_next_allocated_block(path) == EXT_MAX_BLOCK || + newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) + flags |= FIEMAP_EXTENT_LAST; + + error = fiemap_fill_next_extent(fieinfo, logical, physical, + length, flags, inode->i_sb->s_dev); + if (error < 0) + return error; + if (error == 1) + return EXT_BREAK; + + return EXT_CONTINUE; +} + +int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len) +{ + struct ext3_extents_tree tree; + unsigned long start_blk; + unsigned long len_blks; + int error = 0; + + if (!(EXT3_I(inode)->i_flags & EXT3_EXTENTS_FL)) + return -EOPNOTSUPP; + + if (fiemap_check_flags(fieinfo, EXT3_FIEMAP_FLAGS_COMPAT)) + return -EBADR; + + start_blk = start >> inode->i_sb->s_blocksize_bits; + len_blks = (len + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; + + ext3_init_tree_desc(&tree, inode); + tree.private = fieinfo; + + /* + * Walk the extent tree gathering extent information. + * ext3_ext_fiemap_cb will push extents back to user. + */ + down(&EXT3_I(inode)->truncate_sem); + error = ext3_ext_walk_space(&tree, start_blk, len_blks, + ext3_ext_fiemap_cb); + up(&EXT3_I(inode)->truncate_sem); + + return error; +} + EXPORT_SYMBOL(ext3_init_tree_desc); EXPORT_SYMBOL(ext3_mark_inode_dirty); EXPORT_SYMBOL(ext3_ext_invalidate_cache); Index: linux-2.6.16.60-0.37/fs/ext3/fiemap.h =================================================================== --- /dev/null +++ linux-2.6.16.60-0.37/fs/ext3/fiemap.h @@ -0,0 +1,85 @@ +/* + * FIEMAP ioctl infrastructure. + * + * Copyright 2008 Sun Microsystems, Inc. + * + * Author: Kalpak Shah + * Andreas Dilger + */ + +#ifndef _LINUX_EXT3_FIEMAP_H +#define _LINUX_EXT3_FIEMAP_H + +struct fiemap_extent { + __u64 fe_logical; /* logical offset in bytes for the start of + * the extent from the beginning of the file */ + __u64 fe_physical; /* physical offset in bytes for the start + * of the extent from the beginning of the disk */ + __u64 fe_length; /* length in bytes for this extent */ + __u64 fe_reserved64[2]; + __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */ + __u32 fe_device; /* device number for this extent */ + __u32 fe_reserved[2]; +}; + +struct fiemap { + __u64 fm_start; /* logical offset (inclusive) at + * which to start mapping (in) */ + __u64 fm_length; /* logical length of mapping which + * userspace wants (in) */ + __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */ + __u32 fm_mapped_extents;/* number of extents that were mapped (out) */ + __u32 fm_extent_count; /* size of fm_extents array (in) */ + __u32 fm_reserved; + struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ +}; + +/* + * FIEMAP helper definition. + */ +struct fiemap_extent_info { + unsigned int fi_flags; /* Flags as passed from user */ + unsigned int fi_extents_mapped; /* Number of mapped extents */ + unsigned int fi_extents_max; /* Size of fiemap_extent array*/ + struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */ +}; + +int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); +int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, + u64 phys, u64 len, u32 flags, u32 lun); + +#define FIEMAP_MAX_OFFSET (~0ULL) + +#define FIEMAP_FLAG_SYNC 0x00000001 /* sync file data before map */ +#define FIEMAP_FLAG_XATTR 0x00000002 /* map extended attribute tree */ + +/* ldiskfs only supports FLAG_SYNC flag currently */ +#define FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR) + +#define FIEMAP_EXTENT_LAST 0x00000001 /* Last extent in file. */ +#define FIEMAP_EXTENT_UNKNOWN 0x00000002 /* Data location unknown. */ +#define FIEMAP_EXTENT_DELALLOC 0x00000004 /* Location still pending. + * Sets EXTENT_UNKNOWN. */ +#define FIEMAP_EXTENT_ENCODED 0x00000008 /* Data can not be read + * while fs is unmounted */ +#define FIEMAP_EXTENT_DATA_ENCRYPTED 0x00000080 /* Data is encrypted by fs. + * Sets EXTENT_NO_DIRECT. */ +#define FIEMAP_EXTENT_NOT_ALIGNED 0x00000100 /* Extent offsets may not be + * block aligned. */ +#define FIEMAP_EXTENT_DATA_INLINE 0x00000200 /* Data mixed with metadata. + * Sets EXTENT_NOT_ALIGNED.*/ +#define FIEMAP_EXTENT_DATA_TAIL 0x00000400 /* Multiple files in block. + * Sets EXTENT_NOT_ALIGNED.*/ +#define FIEMAP_EXTENT_UNWRITTEN 0x00000800 /* Space allocated, but + * no data (i.e. zero). */ +#define FIEMAP_EXTENT_MERGED 0x00001000 /* File does not natively + * support extents. Result + * merged for efficiency. */ + +/* Lustre specific flags - use a high bit, don't conflict with upstream flag */ +#define FIEMAP_EXTENT_NO_DIRECT 0x40000000 /* Data mapping undefined */ +#define FIEMAP_EXTENT_NET 0x80000000 /* Data stored remotely. + * Sets NO_DIRECT flag */ + +#endif /* _LINUX_EXT3_FIEMAP_H */ +