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 <kalpak.shah@sun.com>
Andreas Dilger <adilger@sun.com>
Eric Sandeen <sandeen@redhat.com>
Mark Fasheh <mfasheh@suse.com>

Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: linux-api@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org

4 files changed, 465 insertions, 0 deletions

diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt
new file mode 100644
index 0000000..1e3defc
--- /dev/null
+++ b/Documentation/filesystems/fiemap.txt
@@ -0,0 +1,228 @@
+============
+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 it's 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 it's 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 it's 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 the last extent in the file. A mapping attempt past this
+extent will return nothing.
+
+* 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, it's
+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 it's 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 it's 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.
+
+
+Flag checking should be done at the beginning of the ->fiemap callback via the
+fiemap_check_flags() helper:
+
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+
+The struct fieinfo should be passed in as recieved from ioctl_fiemap(). The
+set of fiemap flags which the fs understands should be passed via fs_flags. If
+fiemap_check_flags 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_check_flags(), it should immediately exit, returning that error back to
+ioctl_fiemap().
+
+
+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.
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 7db32b3..045d960 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -16,6 +16,9 @@
 
 #include <asm/ioctls.h>
 
+/* 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:
diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h
new file mode 100644
index 0000000..671decb
--- /dev/null
+++ b/include/linux/fiemap.h
@@ -0,0 +1,64 @@
+/*
+ * FS_IOC_FIEMAP ioctl infrastructure.
+ *
+ * Some portions copyright (C) 2007 Cluster File Systems, Inc
+ *
+ * Authors: Mark Fasheh <mfasheh@suse.com>
+ *          Kalpak Shah <kalpak.shah@sun.com>
+ *          Andreas Dilger <adilger@sun.com>
+ */
+
+#ifndef _LINUX_FIEMAP_H
+#define _LINUX_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_reserved[3];
+};
+
+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) */
+};
+
+#define FIEMAP_MAX_OFFSET	(~0ULL)
+
+#define FIEMAP_FLAG_SYNC	0x00000001 /* sync file data before map */
+#define FIEMAP_FLAG_XATTR	0x00000002 /* map extended attribute tree */
+
+#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_BYPASS. */
+#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. */
+
+#endif /* _LINUX_FIEMAP_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 580b513..194fb23 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -231,6 +231,7 @@ extern int dir_notify_enable;
 #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
 #define	FS_IOC_GETVERSION		_IOR('v', 1, long)
 #define	FS_IOC_SETVERSION		_IOW('v', 2, long)
+#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
 #define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
 #define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
 #define FS_IOC32_GETVERSION		_IOR('v', 1, int)
@@ -291,6 +292,7 @@ extern int dir_notify_enable;
 #include <linux/mutex.h>
 #include <linux/capability.h>
 #include <linux/semaphore.h>
+#include <linux/fiemap.h>
 
 #include <asm/atomic.h>
 #include <asm/byteorder.h>
@@ -1179,6 +1181,20 @@ extern void dentry_unhash(struct dentry *dentry);
 extern int file_permission(struct file *, int);
 
 /*
+ * VFS FS_IOC_FIEMAP helper definitions.
+ */
+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_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+			    u64 phys, u64 len, u32 flags);
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+
+/*
  * File types
  *
  * NOTE! These match bits 12..15 of stat.st_mode
@@ -1287,6 +1303,8 @@ struct inode_operations {
 	void (*truncate_range)(struct inode *, loff_t, loff_t);
 	long (*fallocate)(struct inode *inode, int mode, loff_t offset,
 			  loff_t len);
+	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+		      u64 len);
 };
 
 struct seq_file;