From: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
With delayed allocation we use i_data_sem to update i_disksize. We need
to update i_disksize only if the new size specified is greater than the
current value and we need to make sure we don't race with other
i_disksize update. With delayed allocation we will switch to the
write_begin function for non-delayed allocation if we are low on free
blocks. This means the write_begin function for non-delayed allocation
also needs to use the same locking.
We also need to check and update i_disksize even if the new size is less
that inode.i_size because of delayed allocation.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Signed-off-by: "Theodore Ts'o" <tytso@xxxxxxx>
---
fs/ext4/ext4.h | 11 ++++++++++
fs/ext4/extents.c | 9 ++++---
fs/ext4/inode.c | 54 +++++++++++++++++++++++++++++-----------------------
3 files changed, 46 insertions(+), 28 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e13b9de..3e47b99 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1218,6 +1218,17 @@ do { \
#define EXT4_FREEBLOCKS_WATERMARK 0
#endif
+static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
+{
+ /*
+ * XXX: replace with spinlock if seen contended -bzzz
+ */
+ down_write(&EXT4_I(inode)->i_data_sem);
+ if (newsize > EXT4_I(inode)->i_disksize)
+ EXT4_I(inode)->i_disksize = newsize;
+ up_write(&EXT4_I(inode)->i_data_sem);
+ return ;
+}
/*
* Inodes and files operations
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 797f060..e8758df 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2878,10 +2878,11 @@ static void ext4_falloc_update_inode(struct inode *inode,
* Update only when preallocation was requested beyond
* the file size.
*/
- if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- new_size > i_size_read(inode)) {
- i_size_write(inode, new_size);
- EXT4_I(inode)->i_disksize = new_size;
+ if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+ if (new_size > i_size_read(inode))
+ i_size_write(inode, new_size);
+ if (new_size > EXT4_I(inode)->i_disksize)
+ ext4_update_i_disksize(inode, new_size);
}
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 634f0bc..22fcbb6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1434,16 +1434,18 @@ static int ext4_ordered_write_end(struct file *file,
ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
- /*
- * generic_write_end() will run mark_inode_dirty() if i_size
- * changes. So let's piggyback the i_disksize mark_inode_dirty
- * into that.
- */
loff_t new_i_size;
new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = new_i_size;
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ ext4_update_i_disksize(inode, new_i_size);
+ /* We need to mark inode dirty even if
+ * new_i_size is less that inode->i_size
+ * bu greater than i_disksize.(hint delalloc)
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ }
+
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = ret2;
@@ -1468,8 +1470,14 @@ static int ext4_writeback_write_end(struct file *file,
loff_t new_i_size;
new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = new_i_size;
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ ext4_update_i_disksize(inode, new_i_size);
+ /* We need to mark inode dirty even if
+ * new_i_size is less that inode->i_size
+ * bu greater than i_disksize.(hint delalloc)
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ }
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
@@ -1494,6 +1502,7 @@ static int ext4_journalled_write_end(struct file *file,
int ret = 0, ret2;
int partial = 0;
unsigned from, to;
+ loff_t new_i_size;
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
@@ -1508,11 +1517,12 @@ static int ext4_journalled_write_end(struct file *file,
to, &partial, write_end_fn);
if (!partial)
SetPageUptodate(page);
- if (pos+copied > inode->i_size)
+ new_i_size = pos + copied;
+ if (new_i_size > inode->i_size)
i_size_write(inode, pos+copied);
EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
- if (inode->i_size > EXT4_I(inode)->i_disksize) {
- EXT4_I(inode)->i_disksize = inode->i_size;
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ ext4_update_i_disksize(inode, new_i_size);
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
@@ -2227,18 +2237,9 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
if (disksize > i_size_read(inode))
disksize = i_size_read(inode);
if (disksize > EXT4_I(inode)->i_disksize) {
- /*
- * XXX: replace with spinlock if seen contended -bzzz
- */
- down_write(&EXT4_I(inode)->i_data_sem);
- if (disksize > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = disksize;
- up_write(&EXT4_I(inode)->i_data_sem);
-
- if (EXT4_I(inode)->i_disksize == disksize) {
- ret = ext4_mark_inode_dirty(handle, inode);
- return ret;
- }
+ ext4_update_i_disksize(inode, disksize);
+ ret = ext4_mark_inode_dirty(handle, inode);
+ return ret;
}
ret = 0;
}
@@ -2654,6 +2655,11 @@ static int ext4_da_write_end(struct file *file,
EXT4_I(inode)->i_disksize = new_i_size;
}
up_write(&EXT4_I(inode)->i_data_sem);
+ /* We need to mark inode dirty even if
+ * new_i_size is less that inode->i_size
+ * bu greater than i_disksize.(hint delalloc)
+ */
+ ext4_mark_inode_dirty(handle, inode);
}
}
ret2 = generic_write_end(file, mapping, pos, len, copied,
--
1.5.6.1.205.ge2c7.dirty
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
