From c4b929b85bdb64afacbbf6453b1f2bf7e14c9e89 Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Wed, 8 Oct 2008 19:44:18 -0400 Subject: vfs: vfs-level fiemap interface Basic vfs-level fiemap infrastructure, which sets up a new ->fiemap inode operation. Userspace can get extent information on a file via fiemap ioctl. As input, the fiemap ioctl takes a struct fiemap which includes an array of struct fiemap_extent (fm_extents). Size of the extent array is passed as fm_extent_count and number of extents returned will be written into fm_mapped_extents. Offset and length fields on the fiemap structure (fm_start, fm_length) describe a logical range which will be searched for extents. All extents returned will at least partially contain this range. The actual extent offsets and ranges returned will be unmodified from their offset and range on-disk. The fiemap ioctl returns '0' on success. On error, -1 is returned and errno is set. If errno is equal to EBADR, then fm_flags will contain those flags which were passed in which the kernel did not understand. On all other errors, the contents of fm_extents is undefined. As fiemap evolved, there have been many authors of the vfs patch. As far as I can tell, the list includes: Kalpak Shah Andreas Dilger Eric Sandeen Mark Fasheh Signed-off-by: Mark Fasheh Signed-off-by: "Theodore Ts'o" Cc: Michael Kerrisk Cc: linux-api@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org --- fs/ioctl.c | 155 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 155 insertions(+) (limited to 'fs/ioctl.c') diff --git a/fs/ioctl.c b/fs/ioctl.c index 7db32b3382d3..045d9601fbbd 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -16,6 +16,9 @@ #include +/* So that the fiemap access checks can't overflow on 32 bit machines. */ +#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) + /** * vfs_ioctl - call filesystem specific ioctl methods * @filp: open file to invoke ioctl method on @@ -71,6 +74,156 @@ static int ioctl_fibmap(struct file *filp, int __user *p) return put_user(res, p); } +/** + * 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 + * + * 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_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) +{ + struct fiemap_extent extent; + 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_UNMOUNTED_IO_FLAGS) + flags |= FIEMAP_EXTENT_ENCODED; + if (flags & SET_NOT_ALIGNED_FLAGS) + flags |= FIEMAP_EXTENT_NOT_ALIGNED; + + memset(&extent, 0, sizeof(extent)); + extent.fe_logical = logical; + extent.fe_physical = phys; + extent.fe_length = len; + extent.fe_flags = flags; + + 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; +} +EXPORT_SYMBOL(fiemap_fill_next_extent); + +/** + * 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; +} +EXPORT_SYMBOL(fiemap_check_flags); + +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; +} + +static int ioctl_fiemap(struct file *filp, unsigned long arg) +{ + struct fiemap fiemap; + struct fiemap_extent_info fieinfo = { 0, }; + struct inode *inode = filp->f_path.dentry->d_inode; + struct super_block *sb = inode->i_sb; + u64 len; + int error; + + if (!inode->i_op->fiemap) + return -EOPNOTSUPP; + + 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, fieinfo.fi_extents_start, + fieinfo.fi_extents_max * sizeof(struct fiemap_extent))) + return -EFAULT; + + if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC) + filemap_write_and_wait(inode->i_mapping); + + error = inode->i_op->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; +} + static int file_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { @@ -80,6 +233,8 @@ static int file_ioctl(struct file *filp, unsigned int cmd, switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); + case FS_IOC_FIEMAP: + return ioctl_fiemap(filp, arg); case FIGETBSZ: return put_user(inode->i_sb->s_blocksize, p); case FIONREAD: -- cgit v1.2.3 From 68c9d702bb72f367f3b148963ec6cf5e07ff7f65 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 3 Oct 2008 17:32:43 -0400 Subject: generic block based fiemap implementation Any block based fs (this patch includes ext3) just has to declare its own fiemap() function and then call this generic function with its own get_block_t. This works well for block based filesystems that will map multiple contiguous blocks at one time, but will work for filesystems that only map one block at a time, you will just end up with an "extent" for each block. One gotcha is this will not play nicely where there is hole+data after the EOF. This function will assume its hit the end of the data as soon as it hits a hole after the EOF, so if there is any data past that it will not pick that up. AFAIK no block based fs does this anyway, but its in the comments of the function anyway just in case. Signed-off-by: Josef Bacik Signed-off-by: Mark Fasheh Signed-off-by: "Theodore Ts'o" Cc: linux-fsdevel@vger.kernel.org --- fs/ext2/ext2.h | 2 + fs/ext2/file.c | 1 + fs/ext2/inode.c | 8 ++++ fs/ext3/file.c | 1 + fs/ext3/inode.c | 8 ++++ fs/ioctl.c | 118 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/ext3_fs.h | 2 + include/linux/fs.h | 3 ++ 8 files changed, 143 insertions(+) (limited to 'fs/ioctl.c') diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 47d88da2d33b..bae998c1e44e 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *); extern int ext2_setattr (struct dentry *, struct iattr *); extern void ext2_set_inode_flags(struct inode *inode); extern void ext2_get_inode_flags(struct ext2_inode_info *); +extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len); int __ext2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 5f2fa9c36293..45ed07122182 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = { #endif .setattr = ext2_setattr, .permission = ext2_permission, + .fiemap = ext2_fiemap, }; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 991d6dfeb51f..7658b33e2653 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "ext2.h" #include "acl.h" #include "xip.h" @@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_ } +int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + return generic_block_fiemap(inode, fieinfo, start, len, + ext2_get_block); +} + static int ext2_writepage(struct page *page, struct writeback_control *wbc) { return block_write_full_page(page, ext2_get_block, wbc); diff --git a/fs/ext3/file.c b/fs/ext3/file.c index acc4913d3019..3be1e0689c9a 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = { .removexattr = generic_removexattr, #endif .permission = ext3_permission, + .fiemap = ext3_fiemap, }; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 507d8689b111..ebfec4d0148e 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "xattr.h" #include "acl.h" @@ -981,6 +982,13 @@ out: return ret; } +int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + return generic_block_fiemap(inode, fieinfo, start, len, + ext3_get_block); +} + /* * `handle' can be NULL if create is zero */ diff --git a/fs/ioctl.c b/fs/ioctl.c index 045d9601fbbd..33a6b7ecb8b8 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -13,6 +13,8 @@ #include #include #include +#include +#include #include @@ -224,6 +226,122 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg) return error; } +#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits) +#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits); + +/* + * @inode - the inode to map + * @arg - the pointer to userspace where we copy everything to + * @get_block - the fs's get_block function + * + * This does FIEMAP for block based inodes. Basically it will just loop + * through get_block until we hit the number of extents we want to map, or we + * go past the end of the file and hit a hole. + * + * If it is possible to have data blocks beyond a hole past @inode->i_size, then + * please do not use this function, it will stop at the first unmapped block + * beyond i_size + */ +int generic_block_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, u64 start, + u64 len, get_block_t *get_block) +{ + struct buffer_head tmp; + unsigned int start_blk; + long long length = 0, map_len = 0; + u64 logical = 0, phys = 0, size = 0; + u32 flags = FIEMAP_EXTENT_MERGED; + int ret = 0; + + if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC))) + return ret; + + start_blk = logical_to_blk(inode, start); + + /* guard against change */ + mutex_lock(&inode->i_mutex); + + length = (long long)min_t(u64, len, i_size_read(inode)); + map_len = length; + + do { + /* + * we set b_size to the total size we want so it will map as + * many contiguous blocks as possible at once + */ + memset(&tmp, 0, sizeof(struct buffer_head)); + tmp.b_size = map_len; + + ret = get_block(inode, start_blk, &tmp, 0); + if (ret) + break; + + /* HOLE */ + if (!buffer_mapped(&tmp)) { + /* + * first hole after going past the EOF, this is our + * last extent + */ + if (length <= 0) { + flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST; + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, + flags); + break; + } + + length -= blk_to_logical(inode, 1); + + /* if we have holes up to/past EOF then we're done */ + if (length <= 0) + break; + + start_blk++; + } else { + if (length <= 0 && size) { + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, + flags); + if (ret) + break; + } + + logical = blk_to_logical(inode, start_blk); + phys = blk_to_logical(inode, tmp.b_blocknr); + size = tmp.b_size; + flags = FIEMAP_EXTENT_MERGED; + + length -= tmp.b_size; + start_blk += logical_to_blk(inode, size); + + /* + * if we are past the EOF we need to loop again to see + * if there is a hole so we can mark this extent as the + * last one, and if not keep mapping things until we + * find a hole, or we run out of slots in the extent + * array + */ + if (length <= 0) + continue; + + ret = fiemap_fill_next_extent(fieinfo, logical, phys, + size, flags); + if (ret) + break; + } + cond_resched(); + } while (1); + + mutex_unlock(&inode->i_mutex); + + /* if ret is 1 then we just hit the end of the extent array */ + if (ret == 1) + ret = 0; + + return ret; +} +EXPORT_SYMBOL(generic_block_fiemap); + static int file_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 80171ee89a22..8120fa1bc235 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -837,6 +837,8 @@ extern void ext3_truncate (struct inode *); extern void ext3_set_inode_flags(struct inode *); extern void ext3_get_inode_flags(struct ext3_inode_info *); extern void ext3_set_aops(struct inode *inode); +extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len); /* ioctl.c */ extern int ext3_ioctl (struct inode *, struct file *, unsigned int, diff --git a/include/linux/fs.h b/include/linux/fs.h index 194fb237a307..385c9a197df1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1998,6 +1998,9 @@ extern int vfs_fstat(unsigned int, struct kstat *); extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg); +extern int generic_block_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, u64 start, + u64 len, get_block_t *get_block); extern void get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); -- cgit v1.2.3 From 06270d5d6aefb46b88bf44a7c5b1b9b3ef352c48 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 12 Oct 2008 07:15:19 +0300 Subject: provide generic_block_fiemap() only with BLOCK=y This fixes the following compile error with CONFIG_BLOCK=n caused by commit 68c9d702bb72f367f3b148963ec6cf5e07ff7f65 ("generic block based fiemap implementation"): CC fs/ioctl.o fs/ioctl.c: In function 'generic_block_fiemap': fs/ioctl.c:249: error: storage size of 'tmp' isn't known fs/ioctl.c:272: error: invalid application of 'sizeof' to incomplete type 'struct buffer_head' fs/ioctl.c:280: error: implicit declaration of function 'buffer_mapped' fs/ioctl.c:249: warning: unused variable 'tmp' make[2]: *** [fs/ioctl.o] Error 1 Signed-off-by: Adrian Bunk Acked-by: Josef Bacik Signed-off-by: Linus Torvalds --- fs/ioctl.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs/ioctl.c') diff --git a/fs/ioctl.c b/fs/ioctl.c index 33a6b7ecb8b8..d152856c371b 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -226,6 +226,8 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg) return error; } +#ifdef CONFIG_BLOCK + #define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits) #define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits); @@ -342,6 +344,8 @@ int generic_block_fiemap(struct inode *inode, } EXPORT_SYMBOL(generic_block_fiemap); +#endif /* CONFIG_BLOCK */ + static int file_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { -- cgit v1.2.3