ext4: improve llseek error handling for overly large seek offsets

The llseek system call should return EINVAL if passed a seek offset
which results in a write error.  What this maximum offset should be
depends on whether or not the huge_file file system feature is set,
and whether or not the file is extent based or not.


If the file has no "EXT4_EXTENTS_FL" flag, the maximum size which can be 
written (write systemcall) is different from the maximum size which can be 
sought (lseek systemcall).

For example, the following 2 cases demonstrates the differences
between the maximum size which can be written, versus the seek offset
allowed by the llseek system call:

#1: mkfs.ext3 <dev>; mount -t ext4 <dev>
#2: mkfs.ext3 <dev>; tune2fs -Oextent,huge_file <dev>; mount -t ext4 <dev>

Table. the max file size which we can write or seek
       at each filesystem feature tuning and file flag setting
+============+===============================+===============================+
| \ File flag|                               |                               |
|      \     |     !EXT4_EXTENTS_FL          |        EXT4_EXTETNS_FL        |
|case       \|                               |                               |
+------------+-------------------------------+-------------------------------+
| #1         |   write:      2194719883264   | write:       --------------   |
|            |   seek:       2199023251456   | seek:        --------------   |
+------------+-------------------------------+-------------------------------+
| #2         |   write:      4402345721856   | write:       17592186044415   |
|            |   seek:      17592186044415   | seek:        17592186044415   |
+------------+-------------------------------+-------------------------------+

The differences exist because ext4 has 2 maxbytes which are sb->s_maxbytes
(= extent-mapped maxbytes) and EXT4_SB(sb)->s_bitmap_maxbytes (= block-mapped 
maxbytes).  Although generic_file_llseek uses only extent-mapped maxbytes.
(llseek of ext4_file_operations is generic_file_llseek which uses
sb->s_maxbytes.)

Therefore we create ext4 llseek function which uses 2 maxbytes.

The new own function originates from generic_file_llseek().
If the file flag, "EXT4_EXTENTS_FL" is not set, the function alters 
inode->i_sb->s_maxbytes into EXT4_SB(inode->i_sb)->s_bitmap_maxbytes.

Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>

3 files changed, 45 insertions, 2 deletions

diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 374510f72ba..ece76fb6a40 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -39,7 +39,7 @@ static int ext4_release_dir(struct inode *inode,
                                 struct file *filp);
 
 const struct file_operations ext4_dir_operations = {
-        .llseek         = generic_file_llseek,
+        .llseek         = ext4_llseek,
         .read           = generic_read_dir,
         .readdir        = ext4_readdir,         /* we take BKL. needed?*/
         .unlocked_ioctl = ext4_ioctl,
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4c5fe37b237..e1c01552a3d 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2006,6 +2006,7 @@ extern const struct file_operations ext4_dir_operations;
 /* file.c */
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
+extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
 
 /* namei.c */
 extern const struct inode_operations ext4_dir_inode_operations;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ee92b66d455..5a5c55ddcee 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -130,8 +130,50 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
         return dquot_file_open(inode, filp);
 }
 
+/*
+ * ext4_llseek() copied from generic_file_llseek() to handle both
+ * block-mapped and extent-mapped maxbytes values. This should
+ * otherwise be identical with generic_file_llseek().
+ */
+loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
+{
+        struct inode *inode = file->f_mapping->host;
+        loff_t maxbytes;
+
+        if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+                maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
+        else
+                maxbytes = inode->i_sb->s_maxbytes;
+        mutex_lock(&inode->i_mutex);
+        switch (origin) {
+        case SEEK_END:
+                offset += inode->i_size;
+                break;
+        case SEEK_CUR:
+                if (offset == 0) {
+                        mutex_unlock(&inode->i_mutex);
+                        return file->f_pos;
+                }
+                offset += file->f_pos;
+                break;
+        }
+
+        if (offset < 0 || offset > maxbytes) {
+                mutex_unlock(&inode->i_mutex);
+                return -EINVAL;
+        }
+
+        if (offset != file->f_pos) {
+                file->f_pos = offset;
+                file->f_version = 0;
+        }
+        mutex_unlock(&inode->i_mutex);
+
+        return offset;
+}
+
 const struct file_operations ext4_file_operations = {
-        .llseek         = generic_file_llseek,
+        .llseek         = ext4_llseek,
         .read           = do_sync_read,
         .write          = do_sync_write,
         .aio_read       = generic_file_aio_read,