The problem is:
1. write cached data to a file
2. read directly from the same file (via another fd)
The 2nd operation may read stale data, i.e. the one that was in a file
before the 1st op. Problem is in how fuse manages writeback.
When direct op occurs the core kernel code calls filemap_write_and_wait
to flush all the cached ops in flight. But fuse acks the writeback right
after the ->writepages callback exits w/o waiting for the real write to
happen. Thus the subsequent direct op proceeds while the real writeback
is still in flight. This is a problem for backends that reorder operation.
Fix this by making the fuse direct IO callback explicitly wait on the
in-flight writeback to finish.
Original patch by: Pavel Emelyanov <xemul@xxxxxxxxxx>
Signed-off-by: Maxim Patlasov <MPatlasov@xxxxxxxxxxxxx>
---
fs/fuse/file.c | 40 ++++++++++++++++++++++++++++++++++++++++
1 files changed, 40 insertions(+), 0 deletions(-)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b73fe2a..741e9b4 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -348,6 +348,31 @@ u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id)
return (u64) v0 + ((u64) v1 << 32);
}
+static bool fuse_range_is_writeback(struct inode *inode, pgoff_t idx_from,
+ pgoff_t idx_to)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ struct fuse_req *req;
+ bool found = false;
+
+ spin_lock(&fc->lock);
+ list_for_each_entry(req, &fi->writepages, writepages_entry) {
+ pgoff_t curr_index;
+
+ BUG_ON(req->inode != inode);
+ curr_index = req->misc.write.in.offset >> PAGE_CACHE_SHIFT;
+ if (!(idx_from >= curr_index + req->num_pages ||
+ idx_to < curr_index)) {
+ found = true;
+ break;
+ }
+ }
+ spin_unlock(&fc->lock);
+
+ return found;
+}
+
/*
* Check if page is under writeback
*
@@ -392,6 +417,19 @@ static int fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index)
return 0;
}
+static void fuse_wait_on_writeback(struct inode *inode, pgoff_t start,
+ size_t bytes)
+{
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ pgoff_t idx_from, idx_to;
+
+ idx_from = start >> PAGE_CACHE_SHIFT;
+ idx_to = (start + bytes - 1) >> PAGE_CACHE_SHIFT;
+
+ wait_event(fi->page_waitq,
+ !fuse_range_is_writeback(inode, idx_from, idx_to));
+}
+
static int fuse_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file->f_path.dentry->d_inode;
@@ -1178,6 +1216,8 @@ ssize_t fuse_direct_io(struct file *file, const char __user *buf,
break;
}
+ fuse_wait_on_writeback(file->f_mapping->host, pos, nbytes);
+
if (write)
nres = fuse_send_write(req, file, pos, nbytes, owner);
else
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
