summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJosef Bacik <josef@redhat.com>2011-07-18 19:21:35 +0200
committerAl Viro <viro@zeniv.linux.org.uk>2011-07-21 02:47:56 +0200
commit982d816581eeeacfe5b2b7c6d47d13a157616eff (patch)
tree1f1cb5725646e9de13969c8894b26ab3d5e3102e
parentreiserfs: make reiserfs default to barrier=flush (diff)
downloadlinux-982d816581eeeacfe5b2b7c6d47d13a157616eff.tar.xz
linux-982d816581eeeacfe5b2b7c6d47d13a157616eff.zip
fs: add SEEK_HOLE and SEEK_DATA flags
This just gets us ready to support the SEEK_HOLE and SEEK_DATA flags. Turns out using fiemap in things like cp cause more problems than it solves, so lets try and give userspace an interface that doesn't suck. We need to match solaris here, and the definitions are *o* If /whence/ is SEEK_HOLE, the offset of the start of the next hole greater than or equal to the supplied offset is returned. The definition of a hole is provided near the end of the DESCRIPTION. *o* If /whence/ is SEEK_DATA, the file pointer is set to the start of the next non-hole file region greater than or equal to the supplied offset. So in the generic case the entire file is data and there is a virtual hole at the end. That means we will just return i_size for SEEK_HOLE and will return the same offset for SEEK_DATA. This is how Solaris does it so we have to do it the same way. Thanks, Signed-off-by: Josef Bacik <josef@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
-rw-r--r--Documentation/filesystems/porting10
-rw-r--r--fs/read_write.c44
-rw-r--r--include/linux/fs.h4
3 files changed, 54 insertions, 4 deletions
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 0eeb3954dea3..6b96773e27cb 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -411,3 +411,13 @@ to some pointer to returning that pointer. On errors return ERR_PTR(...).
argument; instead of passing IPERM_FLAG_RCU we add MAY_NOT_BLOCK into mask.
generic_permission() has also lost the check_acl argument; if you want
non-NULL to be used for that inode, put it into ->i_op->check_acl.
+
+--
+[mandatory]
+ If you implement your own ->llseek() you must handle SEEK_HOLE and
+SEEK_DATA. You can hanle this by returning -EINVAL, but it would be nicer to
+support it in some way. The generic handler assumes that the entire file is
+data and there is a virtual hole at the end of the file. So if the provided
+offset is less than i_size and SEEK_DATA is specified, return the same offset.
+If the above is true for the offset and you are given SEEK_HOLE, return the end
+of the file. If the offset is i_size or greater return -ENXIO in either case.
diff --git a/fs/read_write.c b/fs/read_write.c
index 5520f8ad5504..5907b49e4d7e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -64,6 +64,23 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin)
return file->f_pos;
offset += file->f_pos;
break;
+ case SEEK_DATA:
+ /*
+ * In the generic case the entire file is data, so as long as
+ * offset isn't at the end of the file then the offset is data.
+ */
+ if (offset >= inode->i_size)
+ return -ENXIO;
+ break;
+ case SEEK_HOLE:
+ /*
+ * There is a virtual hole at the end of the file, so as long as
+ * offset isn't i_size or larger, return i_size.
+ */
+ if (offset >= inode->i_size)
+ return -ENXIO;
+ offset = inode->i_size;
+ break;
}
if (offset < 0 && !unsigned_offsets(file))
@@ -128,12 +145,13 @@ EXPORT_SYMBOL(no_llseek);
loff_t default_llseek(struct file *file, loff_t offset, int origin)
{
+ struct inode *inode = file->f_path.dentry->d_inode;
loff_t retval;
- mutex_lock(&file->f_dentry->d_inode->i_mutex);
+ mutex_lock(&inode->i_mutex);
switch (origin) {
case SEEK_END:
- offset += i_size_read(file->f_path.dentry->d_inode);
+ offset += i_size_read(inode);
break;
case SEEK_CUR:
if (offset == 0) {
@@ -141,6 +159,26 @@ loff_t default_llseek(struct file *file, loff_t offset, int origin)
goto out;
}
offset += file->f_pos;
+ break;
+ case SEEK_DATA:
+ /*
+ * In the generic case the entire file is data, so as
+ * long as offset isn't at the end of the file then the
+ * offset is data.
+ */
+ if (offset >= inode->i_size)
+ return -ENXIO;
+ break;
+ case SEEK_HOLE:
+ /*
+ * There is a virtual hole at the end of the file, so
+ * as long as offset isn't i_size or larger, return
+ * i_size.
+ */
+ if (offset >= inode->i_size)
+ return -ENXIO;
+ offset = inode->i_size;
+ break;
}
retval = -EINVAL;
if (offset >= 0 || unsigned_offsets(file)) {
@@ -151,7 +189,7 @@ loff_t default_llseek(struct file *file, loff_t offset, int origin)
retval = offset;
}
out:
- mutex_unlock(&file->f_dentry->d_inode->i_mutex);
+ mutex_unlock(&inode->i_mutex);
return retval;
}
EXPORT_SYMBOL(default_llseek);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 824453be9fee..4a61f98823a6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -32,7 +32,9 @@
#define SEEK_SET 0 /* seek relative to beginning of file */
#define SEEK_CUR 1 /* seek relative to current file position */
#define SEEK_END 2 /* seek relative to end of file */
-#define SEEK_MAX SEEK_END
+#define SEEK_DATA 3 /* seek to the next data */
+#define SEEK_HOLE 4 /* seek to the next hole */
+#define SEEK_MAX SEEK_HOLE
struct fstrim_range {
__u64 start;