Hook ext4 to the vfs fiemap interface.

ext4_ext_walk_space() was reinstated to be used for iterating over file
extents with a callback; it is used by the ext4 fiemap implementation.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: linux-ext4@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org

5 files changed, 271 insertions, 2 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index c50c04cc6d7b..f46a513a5157 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1067,6 +1067,8 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *,
                                                 ext4_lblk_t, int, int *);
 struct buffer_head *ext4_bread(handle_t *, struct inode *,
                                                 ext4_lblk_t, int, int *);
+int ext4_get_block(struct inode *inode, sector_t iblock,
+                                struct buffer_head *bh_result, int create);
 int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
                                 ext4_lblk_t iblock, unsigned long maxblocks,
                                 struct buffer_head *bh_result,
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index d33dc56d6986..bec7ce59fc0d 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -124,6 +124,19 @@ struct ext4_ext_path {
 #define EXT4_EXT_CACHE_GAP      1
 #define EXT4_EXT_CACHE_EXTENT   2
 
+/*
+ * to be called by ext4_ext_walk_space()
+ * negative retcode - error
+ * positive retcode - signal for ext4_ext_walk_space(), see below
+ * callback must return valid extent (passed or newly created)
+ */
+typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
+                                        struct ext4_ext_cache *,
+                                        struct ext4_extent *, void *);
+
+#define EXT_CONTINUE   0
+#define EXT_BREAK      1
+#define EXT_REPEAT     2
 
 #define EXT_MAX_BLOCK   0xffffffff
 
@@ -224,6 +237,8 @@ extern int ext4_ext_try_to_merge(struct inode *inode,
                                  struct ext4_extent *);
 extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
 extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *);
+extern int ext4_ext_walk_space(struct inode *, ext4_lblk_t, ext4_lblk_t,
+                                                        ext_prepare_callback, void *);
 extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
                                                         struct ext4_ext_path *);
 extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index c8f81f2fb28e..ea2ce3c0ae66 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -40,6 +40,7 @@
 #include <linux/slab.h>
 #include <linux/falloc.h>
 #include <asm/uaccess.h>
+#include <linux/fiemap.h>
 #include "ext4_jbd2.h"
 #include "ext4_extents.h"
 
@@ -1626,6 +1627,113 @@ cleanup:
         return err;
 }
 
+int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
+                        ext4_lblk_t num, ext_prepare_callback func,
+                        void *cbdata)
+{
+        struct ext4_ext_path *path = NULL;
+        struct ext4_ext_cache cbex;
+        struct ext4_extent *ex;
+        ext4_lblk_t next, start = 0, end = 0;
+        ext4_lblk_t last = block + num;
+        int depth, exists, err = 0;
+
+        BUG_ON(func == NULL);
+        BUG_ON(inode == NULL);
+
+        while (block < last && block != EXT_MAX_BLOCK) {
+                num = last - block;
+                /* find extent for this block */
+                path = ext4_ext_find_extent(inode, block, path);
+                if (IS_ERR(path)) {
+                        err = PTR_ERR(path);
+                        path = NULL;
+                        break;
+                }
+
+                depth = ext_depth(inode);
+                BUG_ON(path[depth].p_hdr == NULL);
+                ex = path[depth].p_ext;
+                next = ext4_ext_next_allocated_block(path);
+
+                exists = 0;
+                if (!ex) {
+                        /* there is no extent yet, so try to allocate
+                         * all requested space */
+                        start = block;
+                        end = block + num;
+                } else if (le32_to_cpu(ex->ee_block) > block) {
+                        /* need to allocate space before found extent */
+                        start = block;
+                        end = le32_to_cpu(ex->ee_block);
+                        if (block + num < end)
+                                end = block + num;
+                } else if (block >= le32_to_cpu(ex->ee_block)
+                                        + ext4_ext_get_actual_len(ex)) {
+                        /* need to allocate space after found extent */
+                        start = block;
+                        end = block + num;
+                        if (end >= next)
+                                end = next;
+                } else if (block >= le32_to_cpu(ex->ee_block)) {
+                        /*
+                         * some part of requested space is covered
+                         * by found extent
+                         */
+                        start = block;
+                        end = le32_to_cpu(ex->ee_block)
+                                + ext4_ext_get_actual_len(ex);
+                        if (block + num < end)
+                                end = block + num;
+                        exists = 1;
+                } else {
+                        BUG();
+                }
+                BUG_ON(end <= start);
+
+                if (!exists) {
+                        cbex.ec_block = start;
+                        cbex.ec_len = end - start;
+                        cbex.ec_start = 0;
+                        cbex.ec_type = EXT4_EXT_CACHE_GAP;
+                } else {
+                        cbex.ec_block = le32_to_cpu(ex->ee_block);
+                        cbex.ec_len = ext4_ext_get_actual_len(ex);
+                        cbex.ec_start = ext_pblock(ex);
+                        cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
+                }
+
+                BUG_ON(cbex.ec_len == 0);
+                err = func(inode, path, &cbex, ex, cbdata);
+                ext4_ext_drop_refs(path);
+
+                if (err < 0)
+                        break;
+
+                if (err == EXT_REPEAT)
+                        continue;
+                else if (err == EXT_BREAK) {
+                        err = 0;
+                        break;
+                }
+
+                if (ext_depth(inode) != depth) {
+                        /* depth was changed. we have to realloc path */
+                        kfree(path);
+                        path = NULL;
+                }
+
+                block = cbex.ec_block + cbex.ec_len;
+        }
+
+        if (path) {
+                ext4_ext_drop_refs(path);
+                kfree(path);
+        }
+
+        return err;
+}
+
 static void
 ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
                         __u32 len, ext4_fsblk_t start, int type)
@@ -2971,3 +3079,143 @@ retry:
         mutex_unlock(&inode->i_mutex);
         return ret > 0 ? ret2 : ret;
 }
+
+/*
+ * Callback function called for each extent to gather FIEMAP information.
+ */
+int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
+                       struct ext4_ext_cache *newex, struct ext4_extent *ex,
+                       void *data)
+{
+        struct fiemap_extent_info *fieinfo = data;
+        unsigned long 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 == EXT4_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 && ext4_ext_is_uninitialized(ex))
+                flags |= FIEMAP_EXTENT_UNWRITTEN;
+
+        /*
+         * If this extent reaches EXT_MAX_BLOCK, it must be last.
+         *
+         * Or if ext4_ext_next_allocated_block is EXT_MAX_BLOCK,
+         * this also indicates no more allocated blocks.
+         *
+         * XXX this might miss a single-block extent at EXT_MAX_BLOCK
+         */
+        if (logical + length - 1 == EXT_MAX_BLOCK ||
+            ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK)
+                flags |= FIEMAP_EXTENT_LAST;
+
+        error = fiemap_fill_next_extent(fieinfo, logical, physical,
+                                        length, flags);
+        if (error < 0)
+                return error;
+        if (error == 1)
+                return EXT_BREAK;
+
+        return EXT_CONTINUE;
+}
+
+/* fiemap flags we can handle specified here */
+#define EXT4_FIEMAP_FLAGS       (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
+
+int ext4_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo)
+{
+        __u64 physical = 0;
+        __u64 length;
+        __u32 flags = FIEMAP_EXTENT_LAST;
+        int blockbits = inode->i_sb->s_blocksize_bits;
+        int error = 0;
+
+        /* in-inode? */
+        if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+                struct ext4_iloc iloc;
+                int offset;     /* offset of xattr in inode */
+
+                error = ext4_get_inode_loc(inode, &iloc);
+                if (error)
+                        return error;
+                physical = iloc.bh->b_blocknr << blockbits;
+                offset = EXT4_GOOD_OLD_INODE_SIZE +
+                                EXT4_I(inode)->i_extra_isize;
+                physical += offset;
+                length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
+                flags |= FIEMAP_EXTENT_DATA_INLINE;
+        } else { /* external block */
+                physical = EXT4_I(inode)->i_file_acl << blockbits;
+                length = inode->i_sb->s_blocksize;
+        }
+
+        if (physical)
+                error = fiemap_fill_next_extent(fieinfo, 0, physical,
+                                                length, flags);
+        return (error < 0 ? error : 0);
+}
+
+int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                __u64 start, __u64 len)
+{
+        ext4_lblk_t start_blk;
+        ext4_lblk_t len_blks;
+        int error = 0;
+
+        /* fallback to generic here if not in extents fmt */
+        if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+                return generic_block_fiemap(inode, fieinfo, start, len,
+                        ext4_get_block);
+
+        if (fiemap_check_flags(fieinfo, EXT4_FIEMAP_FLAGS))
+                return -EBADR;
+
+        if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+                error = ext4_xattr_fiemap(inode, fieinfo);
+        } else {
+                start_blk = start >> inode->i_sb->s_blocksize_bits;
+                len_blks = len >> inode->i_sb->s_blocksize_bits;
+
+                /*
+                 * Walk the extent tree gathering extent information.
+                 * ext4_ext_fiemap_cb will push extents back to user.
+                 */
+                down_write(&EXT4_I(inode)->i_data_sem);
+                error = ext4_ext_walk_space(inode, start_blk, len_blks,
+                                          ext4_ext_fiemap_cb, fieinfo);
+                up_write(&EXT4_I(inode)->i_data_sem);
+        }
+
+        return error;
+}
+
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 62796b7e1d1b..6d5be156202a 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -140,6 +140,9 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
         return 0;
 }
 
+extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                __u64 start, __u64 len);
+
 const struct file_operations ext4_file_operations = {
         .llseek         = generic_file_llseek,
         .read           = do_sync_read,
@@ -170,5 +173,6 @@ const struct inode_operations ext4_file_inode_operations = {
 #endif
         .permission     = ext4_permission,
         .fallocate      = ext4_fallocate,
+        .fiemap         = ext4_fiemap,
 };
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index bd770c360c14..a4747867411f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1135,8 +1135,8 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
-static int ext4_get_block(struct inode *inode, sector_t iblock,
-                        struct buffer_head *bh_result, int create)
+int ext4_get_block(struct inode *inode, sector_t iblock,
+                   struct buffer_head *bh_result, int create)
 {
         handle_t *handle = ext4_journal_current_handle();
         int ret = 0, started = 0;