--- /dev/null
- fiemap_check_flags() helper::
+.. SPDX-License-Identifier: GPL-2.0
+
+============
+Fiemap Ioctl
+============
+
+The fiemap ioctl is an efficient method for userspace to get file
+extent mappings. Instead of block-by-block mapping (such as bmap), fiemap
+returns a list of extents.
+
+
+Request Basics
+--------------
+
+A fiemap request is encoded within struct fiemap::
+
+ struct fiemap {
+ __u64 fm_start; /* logical offset (inclusive) at
+ * which to start mapping (in) */
+ __u64 fm_length; /* logical length of mapping which
+ * userspace cares about (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) */
+ };
+
+
+fm_start, and fm_length specify the logical range within the file
+which the process would like mappings for. Extents returned mirror
+those on disk - that is, the logical offset of the 1st returned extent
+may start before fm_start, and the range covered by the last returned
+extent may end after fm_length. All offsets and lengths are in bytes.
+
+Certain flags to modify the way in which mappings are looked up can be
+set in fm_flags. If the kernel doesn't understand some particular
+flags, it will return EBADR and the contents of fm_flags will contain
+the set of flags which caused the error. If the kernel is compatible
+with all flags passed, the contents of fm_flags will be unmodified.
+It is up to userspace to determine whether rejection of a particular
+flag is fatal to its operation. This scheme is intended to allow the
+fiemap interface to grow in the future but without losing
+compatibility with old software.
+
+fm_extent_count specifies the number of elements in the fm_extents[] array
+that can be used to return extents. If fm_extent_count is zero, then the
+fm_extents[] array is ignored (no extents will be returned), and the
+fm_mapped_extents count will hold the number of extents needed in
+fm_extents[] to hold the file's current mapping. Note that there is
+nothing to prevent the file from changing between calls to FIEMAP.
+
+The following flags can be set in fm_flags:
+
+FIEMAP_FLAG_SYNC
+ If this flag is set, the kernel will sync the file before mapping extents.
+
+FIEMAP_FLAG_XATTR
+ If this flag is set, the extents returned will describe the inodes
+ extended attribute lookup tree, instead of its data tree.
+
+
+Extent Mapping
+--------------
+
+Extent information is returned within the embedded fm_extents array
+which userspace must allocate along with the fiemap structure. The
+number of elements in the fiemap_extents[] array should be passed via
+fm_extent_count. The number of extents mapped by kernel will be
+returned via fm_mapped_extents. If the number of fiemap_extents
+allocated is less than would be required to map the requested range,
+the maximum number of extents that can be mapped in the fm_extent[]
+array will be returned and fm_mapped_extents will be equal to
+fm_extent_count. In that case, the last extent in the array will not
+complete the requested range and will not have the FIEMAP_EXTENT_LAST
+flag set (see the next section on extent flags).
+
+Each extent is described by a single fiemap_extent structure as
+returned in fm_extents::
+
+ struct fiemap_extent {
+ __u64 fe_logical; /* logical offset in bytes for the start of
+ * the extent */
+ __u64 fe_physical; /* physical offset in bytes for the start
+ * of the extent */
+ __u64 fe_length; /* length in bytes for the extent */
+ __u64 fe_reserved64[2];
+ __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */
+ __u32 fe_reserved[3];
+ };
+
+All offsets and lengths are in bytes and mirror those on disk. It is valid
+for an extents logical offset to start before the request or its logical
+length to extend past the request. Unless FIEMAP_EXTENT_NOT_ALIGNED is
+returned, fe_logical, fe_physical, and fe_length will be aligned to the
+block size of the file system. With the exception of extents flagged as
+FIEMAP_EXTENT_MERGED, adjacent extents will not be merged.
+
+The fe_flags field contains flags which describe the extent returned.
+A special flag, FIEMAP_EXTENT_LAST is always set on the last extent in
+the file so that the process making fiemap calls can determine when no
+more extents are available, without having to call the ioctl again.
+
+Some flags are intentionally vague and will always be set in the
+presence of other more specific flags. This way a program looking for
+a general property does not have to know all existing and future flags
+which imply that property.
+
+For example, if FIEMAP_EXTENT_DATA_INLINE or FIEMAP_EXTENT_DATA_TAIL
+are set, FIEMAP_EXTENT_NOT_ALIGNED will also be set. A program looking
+for inline or tail-packed data can key on the specific flag. Software
+which simply cares not to try operating on non-aligned extents
+however, can just key on FIEMAP_EXTENT_NOT_ALIGNED, and not have to
+worry about all present and future flags which might imply unaligned
+data. Note that the opposite is not true - it would be valid for
+FIEMAP_EXTENT_NOT_ALIGNED to appear alone.
+
+FIEMAP_EXTENT_LAST
+ This is generally the last extent in the file. A mapping attempt past
+ this extent may return nothing. Some implementations set this flag to
+ indicate this extent is the last one in the range queried by the user
+ (via fiemap->fm_length).
+
+FIEMAP_EXTENT_UNKNOWN
+ The location of this extent is currently unknown. This may indicate
+ the data is stored on an inaccessible volume or that no storage has
+ been allocated for the file yet.
+
+FIEMAP_EXTENT_DELALLOC
+ This will also set FIEMAP_EXTENT_UNKNOWN.
+
+ Delayed allocation - while there is data for this extent, its
+ physical location has not been allocated yet.
+
+FIEMAP_EXTENT_ENCODED
+ This extent does not consist of plain filesystem blocks but is
+ encoded (e.g. encrypted or compressed). Reading the data in this
+ extent via I/O to the block device will have undefined results.
+
+Note that it is *always* undefined to try to update the data
+in-place by writing to the indicated location without the
+assistance of the filesystem, or to access the data using the
+information returned by the FIEMAP interface while the filesystem
+is mounted. In other words, user applications may only read the
+extent data via I/O to the block device while the filesystem is
+unmounted, and then only if the FIEMAP_EXTENT_ENCODED flag is
+clear; user applications must not try reading or writing to the
+filesystem via the block device under any other circumstances.
+
+FIEMAP_EXTENT_DATA_ENCRYPTED
+ This will also set FIEMAP_EXTENT_ENCODED
+ The data in this extent has been encrypted by the file system.
+
+FIEMAP_EXTENT_NOT_ALIGNED
+ Extent offsets and length are not guaranteed to be block aligned.
+
+FIEMAP_EXTENT_DATA_INLINE
+ This will also set FIEMAP_EXTENT_NOT_ALIGNED
+ Data is located within a meta data block.
+
+FIEMAP_EXTENT_DATA_TAIL
+ This will also set FIEMAP_EXTENT_NOT_ALIGNED
+ Data is packed into a block with data from other files.
+
+FIEMAP_EXTENT_UNWRITTEN
+ Unwritten extent - the extent is allocated but its data has not been
+ initialized. This indicates the extent's data will be all zero if read
+ through the filesystem but the contents are undefined if read directly from
+ the device.
+
+FIEMAP_EXTENT_MERGED
+ This will be set when a file does not support extents, i.e., it uses a block
+ based addressing scheme. Since returning an extent for each block back to
+ userspace would be highly inefficient, the kernel will try to merge most
+ adjacent blocks into 'extents'.
+
+
+VFS -> File System Implementation
+---------------------------------
+
+File systems wishing to support fiemap must implement a ->fiemap callback on
+their inode_operations structure. The fs ->fiemap call is responsible for
+defining its set of supported fiemap flags, and calling a helper function on
+each discovered extent::
+
+ struct inode_operations {
+ ...
+
+ int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+ u64 len);
+
+->fiemap is passed struct fiemap_extent_info which describes the
+fiemap request::
+
+ 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 */
+ };
+
+It is intended that the file system should not need to access any of this
+structure directly. Filesystem handlers should be tolerant to signals and return
+EINTR once fatal signal received.
+
+
+Flag checking should be done at the beginning of the ->fiemap callback via the
- int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
++fiemap_prep() helper::
+
- fiemap_check_flags finds invalid user flags, it will place the bad values in
++ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
++ u64 start, u64 *len, u32 supported_flags);
+
+The struct fieinfo should be passed in as received from ioctl_fiemap(). The
+set of fiemap flags which the fs understands should be passed via fs_flags. If
- fiemap_check_flags(), it should immediately exit, returning that error back to
- ioctl_fiemap().
++fiemap_prep finds invalid user flags, it will place the bad values in
+fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from
++fiemap_prep(), it should immediately exit, returning that error back to
++ioctl_fiemap(). Additionally the range is validate against the supported
++maximum file size.
+
+
+For each extent in the request range, the file system should call
+the helper function, fiemap_fill_next_extent()::
+
+ int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+ u64 phys, u64 len, u32 flags, u32 dev);
+
+fiemap_fill_next_extent() will use the passed values to populate the
+next free extent in the fm_extents array. 'General' extent flags will
+automatically be set from specific flags on behalf of the calling file
+system so that the userspace API is not broken.
+
+fiemap_fill_next_extent() returns 0 on success, and 1 when the
+user-supplied fm_extents array is full. If an error is encountered
+while copying the extent to user memory, -EFAULT will be returned.
clone_offset += clone_len;
start_sector += clone_len >> 9;
file_offset += clone_len;
-
- ret = btrfs_get_io_geometry(fs_info, btrfs_op(orig_bio),
- start_sector << 9, submit_len, &geom);
- if (ret)
- goto out_err;
} while (submit_len > 0);
+ return BLK_QC_T_NONE;
-submit:
- status = btrfs_submit_dio_bio(bio, inode, file_offset, async_submit);
- if (!status)
- return 0;
-
- bio_put(bio);
out_err:
- dip->errors = 1;
- /*
- * Before atomic variable goto zero, we must make sure dip->errors is
- * perceived to be set. This ordering is ensured by the fact that an
- * atomic operations with a return value are fully ordered as per
- * atomic_t.txt
- */
- if (atomic_dec_and_test(&dip->pending_bios))
- bio_io_error(dip->orig_bio);
-
- /* bio_end_io() will handle error, so we needn't return it */
- return 0;
-}
-
-static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
- loff_t file_offset)
-{
- struct btrfs_dio_private *dip = NULL;
- struct bio *bio = NULL;
- struct btrfs_io_bio *io_bio;
- bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
- int ret = 0;
-
- bio = btrfs_bio_clone(dio_bio);
-
- dip = kzalloc(sizeof(*dip), GFP_NOFS);
- if (!dip) {
- ret = -ENOMEM;
- goto free_ordered;
- }
-
- dip->private = dio_bio->bi_private;
- dip->inode = inode;
- dip->logical_offset = file_offset;
- dip->bytes = dio_bio->bi_iter.bi_size;
- dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
- bio->bi_private = dip;
- dip->orig_bio = bio;
- dip->dio_bio = dio_bio;
- atomic_set(&dip->pending_bios, 0);
- io_bio = btrfs_io_bio(bio);
- io_bio->logical = file_offset;
-
- if (write) {
- bio->bi_end_io = btrfs_endio_direct_write;
- } else {
- bio->bi_end_io = btrfs_endio_direct_read;
- dip->subio_endio = btrfs_subio_endio_read;
- }
-
- /*
- * Reset the range for unsubmitted ordered extents (to a 0 length range)
- * even if we fail to submit a bio, because in such case we do the
- * corresponding error handling below and it must not be done a second
- * time by btrfs_direct_IO().
- */
- if (write) {
- struct btrfs_dio_data *dio_data = current->journal_info;
-
- dio_data->unsubmitted_oe_range_end = dip->logical_offset +
- dip->bytes;
- dio_data->unsubmitted_oe_range_start =
- dio_data->unsubmitted_oe_range_end;
- }
-
- ret = btrfs_submit_direct_hook(dip);
- if (!ret)
- return;
-
- btrfs_io_bio_free_csum(io_bio);
-
-free_ordered:
- /*
- * If we arrived here it means either we failed to submit the dip
- * or we either failed to clone the dio_bio or failed to allocate the
- * dip. If we cloned the dio_bio and allocated the dip, we can just
- * call bio_endio against our io_bio so that we get proper resource
- * cleanup if we fail to submit the dip, otherwise, we must do the
- * same as btrfs_endio_direct_[write|read] because we can't call these
- * callbacks - they require an allocated dip and a clone of dio_bio.
- */
- if (bio && dip) {
- bio_io_error(bio);
- /*
- * The end io callbacks free our dip, do the final put on bio
- * and all the cleanup and final put for dio_bio (through
- * dio_end_io()).
- */
- dip = NULL;
- bio = NULL;
- } else {
- if (write)
- __endio_write_update_ordered(inode,
- file_offset,
- dio_bio->bi_iter.bi_size,
- false);
- else
- unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
- file_offset + dio_bio->bi_iter.bi_size - 1);
-
- dio_bio->bi_status = BLK_STS_IOERR;
- /*
- * Releases and cleans up our dio_bio, no need to bio_put()
- * nor bio_endio()/bio_io_error() against dio_bio.
- */
- dio_end_io(dio_bio);
- }
- if (bio)
- bio_put(bio);
- kfree(dip);
-}
-
-static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
- const struct iov_iter *iter, loff_t offset)
-{
- int seg;
- int i;
- unsigned int blocksize_mask = fs_info->sectorsize - 1;
- ssize_t retval = -EINVAL;
-
- if (offset & blocksize_mask)
- goto out;
-
- if (iov_iter_alignment(iter) & blocksize_mask)
- goto out;
-
- /* If this is a write we don't need to check anymore */
- if (iov_iter_rw(iter) != READ || !iter_is_iovec(iter))
- return 0;
- /*
- * Check to make sure we don't have duplicate iov_base's in this
- * iovec, if so return EINVAL, otherwise we'll get csum errors
- * when reading back.
- */
- for (seg = 0; seg < iter->nr_segs; seg++) {
- for (i = seg + 1; i < iter->nr_segs; i++) {
- if (iter->iov[seg].iov_base == iter->iov[i].iov_base)
- goto out;
- }
- }
- retval = 0;
-out:
- return retval;
+ dip->dio_bio->bi_status = status;
+ btrfs_dio_private_put(dip);
+ return BLK_QC_T_NONE;
}
-static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct btrfs_dio_data dio_data = { 0 };
- struct extent_changeset *data_reserved = NULL;
- loff_t offset = iocb->ki_pos;
- size_t count = 0;
- int flags = 0;
- bool wakeup = true;
- bool relock = false;
- ssize_t ret;
-
- if (check_direct_IO(fs_info, iter, offset))
- return 0;
-
- inode_dio_begin(inode);
-
- /*
- * The generic stuff only does filemap_write_and_wait_range, which
- * isn't enough if we've written compressed pages to this area, so
- * we need to flush the dirty pages again to make absolutely sure
- * that any outstanding dirty pages are on disk.
- */
- count = iov_iter_count(iter);
- if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
- &BTRFS_I(inode)->runtime_flags))
- filemap_fdatawrite_range(inode->i_mapping, offset,
- offset + count - 1);
-
- if (iov_iter_rw(iter) == WRITE) {
- /*
- * If the write DIO is beyond the EOF, we need update
- * the isize, but it is protected by i_mutex. So we can
- * not unlock the i_mutex at this case.
- */
- if (offset + count <= inode->i_size) {
- dio_data.overwrite = 1;
- inode_unlock(inode);
- relock = true;
- } else if (iocb->ki_flags & IOCB_NOWAIT) {
- ret = -EAGAIN;
- goto out;
- }
- ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
- offset, count);
- if (ret)
- goto out;
-
- /*
- * We need to know how many extents we reserved so that we can
- * do the accounting properly if we go over the number we
- * originally calculated. Abuse current->journal_info for this.
- */
- dio_data.reserve = round_up(count,
- fs_info->sectorsize);
- dio_data.unsubmitted_oe_range_start = (u64)offset;
- dio_data.unsubmitted_oe_range_end = (u64)offset;
- current->journal_info = &dio_data;
- down_read(&BTRFS_I(inode)->dio_sem);
- } else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
- &BTRFS_I(inode)->runtime_flags)) {
- inode_dio_end(inode);
- flags = DIO_LOCKING | DIO_SKIP_HOLES;
- wakeup = false;
- }
-
- ret = __blockdev_direct_IO(iocb, inode,
- fs_info->fs_devices->latest_bdev,
- iter, btrfs_get_blocks_direct, NULL,
- btrfs_submit_direct, flags);
- if (iov_iter_rw(iter) == WRITE) {
- up_read(&BTRFS_I(inode)->dio_sem);
- current->journal_info = NULL;
- if (ret < 0 && ret != -EIOCBQUEUED) {
- if (dio_data.reserve)
- btrfs_delalloc_release_space(inode, data_reserved,
- offset, dio_data.reserve, true);
- /*
- * On error we might have left some ordered extents
- * without submitting corresponding bios for them, so
- * cleanup them up to avoid other tasks getting them
- * and waiting for them to complete forever.
- */
- if (dio_data.unsubmitted_oe_range_start <
- dio_data.unsubmitted_oe_range_end)
- __endio_write_update_ordered(inode,
- dio_data.unsubmitted_oe_range_start,
- dio_data.unsubmitted_oe_range_end -
- dio_data.unsubmitted_oe_range_start,
- false);
- } else if (ret >= 0 && (size_t)ret < count)
- btrfs_delalloc_release_space(inode, data_reserved,
- offset, count - (size_t)ret, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), count);
- }
-out:
- if (wakeup)
- inode_dio_end(inode);
- if (relock)
- inode_lock(inode);
+const struct iomap_ops btrfs_dio_iomap_ops = {
+ .iomap_begin = btrfs_dio_iomap_begin,
+ .iomap_end = btrfs_dio_iomap_end,
+};
- extent_changeset_free(data_reserved);
- return ret;
-}
+const struct iomap_dio_ops btrfs_dops = {
+ .submit_io = btrfs_submit_direct,
+};
- #define BTRFS_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC)
-
static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
projects / kernel.git / commitdiff