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

2 files changed, 82 insertions, 0 deletions

diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h
new file mode 100644
index 000000000000..671decbd2aeb
--- /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 580b513668fe..194fb237a307 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;