Almost all read/write operation handles data with chunks(segments or pages)
and result has integral behaviour for folowing scenario:
for_each_chunk() {
res = op(....);
if(IS_ERROR(res))
return progress ? progress : res;
progress += res;
}
prepare_write may has integral behaviour in case of blksize < pgsize,
for example we successfully allocated/read some blocks, but not all of them,
and than some error happend. Currently we eliminate this progress by doing
vmtrunate() after prepare_has failed.
It is good to have ability to signal about this progress. Interprete positive
prepare_write() ret code as bytes num that fs ready to handle at this moment.
I've ask SAW, he think it is sane. This size always less than PAGE_CACHE_SIZE
so it less than AOP_TRUNCATED_PAGE too.
BTH: This approach was used in OpenVZ 2.6.9 kernel in order to make FS with
delayed allocation more correct, and its works well.
I think not everybody will happy about this, but let's discuss all advantages
and disadvantages of this change.
Signed-off-by: Dmitriy Monakhov <dmonakhov@xxxxxxxxxx>
-------------
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 62632f5..b4f6eac 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -239,7 +239,11 @@ static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec,
page_cache_release(page);
continue;
}
- goto unlock;
+ if (ret > 0 && ret < PAGE_CACHE_SIZE)
+ /* prepare_write demands limit size of bytes. */
+ size = min(size, (unsigned)ret);
+ else
+ goto unlock;
}
transfer_result = lo_do_transfer(lo, WRITE, page, offset,
bvec->bv_page, bv_offs, size, IV);
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 1e5d2ba..b5eebe8 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -454,6 +454,17 @@ static int ecryptfs_write_inode_size_to_header(struct file *lower_file,
}
lower_a_ops = lower_inode->i_mapping->a_ops;
rc = lower_a_ops->prepare_write(lower_file, header_page, 0, 8);
+ if (unlikely(rc > 0 && rc < PAGE_CACHE_SIZE)) {
+ /*
+ * prepare_write can handle less bytes whan we need. This is not likely
+ * to happend realy because usualy we need only one block. In order to
+ * preserve prepare/commit balanced invoke commit end fail.
+ */
+ int ret;
+ ret = lower_a_ops->commit_write(lower_file, header_page, 0, rc);
+ rc = ret ? ret : -ENOSPC;
+ goto unlock;
+ }
file_size = (u64)i_size_read(inode);
ecryptfs_printk(KERN_DEBUG, "Writing size: [0x%.16x]\n", file_size);
file_size = cpu_to_be64(file_size);
@@ -462,6 +473,7 @@ static int ecryptfs_write_inode_size_to_header(struct file *lower_file,
kunmap_atomic(header_virt, KM_USER0);
flush_dcache_page(header_page);
rc = lower_a_ops->commit_write(lower_file, header_page, 0, 8);
+unlock:
if (rc < 0)
ecryptfs_printk(KERN_ERR, "Error commiting header page "
"write\n");
diff --git a/fs/namei.c b/fs/namei.c
index b305589..723db81 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2704,6 +2704,16 @@ retry:
page_cache_release(page);
goto retry;
}
+ if (unlikely(err > 0 && err < PAGE_CACHE_SIZE)) {
+ /*
+ * prepare_write can handle less bytes whan we need. This is not likely
+ * to happend realy because usualy we need only one block. In order to
+ * preserve prepare/commit balanced invoke commit end fail.
+ */
+ int ret;
+ ret = mapping->a_ops->commit_write(NULL, page, 0, err);
+ err = ret ? ret : -ENOSPC;
+ }
if (err)
goto fail_map;
kaddr = kmap_atomic(page, KM_USER0);
diff --git a/fs/splice.c b/fs/splice.c
index 2fca6eb..d2b92bf 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -652,6 +652,17 @@ find_page:
if (unlikely(ret)) {
loff_t isize = i_size_read(mapping->host);
+ if (ret > 0 && ret < PAGE_CACHE_SIZE) {
+ /*
+ * prepare_write demands limit size of bytes. In order to
+ * preserve prepare/commit balanced invoke commit end fail.
+ * Initial i_size saved, so vmtruncate safely restore it later.
+ */
+ int ret2;
+ ret2 = mapping->a_ops->commit_write(file, page, offset,
+ offset + ret);
+ ret = ret2 ? ret2 : -ENOSPC;
+ }
if (ret != AOP_TRUNCATED_PAGE)
unlock_page(page);
page_cache_release(page);
diff --git a/mm/filemap.c b/mm/filemap.c
index 5fe315a..529eb9e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2188,6 +2188,11 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
}
status = a_ops->prepare_write(file, page, offset, offset+bytes);
+ if (unlikely(status > 0 && status < PAGE_CACHE_SIZE)) {
+ /* prepare_write demands limit size of bytes at this iteration.*/
+ bytes = min(bytes, (size_t)status);
+ status = 0;
+ }
if (unlikely(status)) {
loff_t isize = i_size_read(inode);
