nfs: page cache invalidation for dio
Make sure to properly invalidate the pagecache before performing direct I/O,
so that no stale pages are left around. This matches what the generic
direct I/O code does. Also take the i_mutex over the direct write submission
to avoid the lifelock vs truncate waiting for i_dio_count to decrease, and
to avoid having the pagecache easily repopulated while direct I/O is in
progrss. Again matching the generic direct I/O code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 85e4e4b..b8797ae 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -939,9 +939,12 @@
struct inode *inode = mapping->host;
struct nfs_direct_req *dreq;
struct nfs_lock_context *l_ctx;
+ loff_t end;
size_t count;
count = iov_length(iov, nr_segs);
+ end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
+
nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n",
@@ -958,16 +961,25 @@
if (!count)
goto out;
+ mutex_lock(&inode->i_mutex);
+
result = nfs_sync_mapping(mapping);
if (result)
- goto out;
+ goto out_unlock;
+
+ if (mapping->nrpages) {
+ result = invalidate_inode_pages2_range(mapping,
+ pos >> PAGE_CACHE_SHIFT, end);
+ if (result)
+ goto out_unlock;
+ }
task_io_account_write(count);
result = -ENOMEM;
dreq = nfs_direct_req_alloc();
if (!dreq)
- goto out;
+ goto out_unlock;
dreq->inode = inode;
dreq->bytes_left = count;
@@ -982,6 +994,14 @@
dreq->iocb = iocb;
result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
+
+ if (mapping->nrpages) {
+ invalidate_inode_pages2_range(mapping,
+ pos >> PAGE_CACHE_SHIFT, end);
+ }
+
+ mutex_unlock(&inode->i_mutex);
+
if (!result) {
result = nfs_direct_wait(dreq);
if (result > 0) {
@@ -994,8 +1014,13 @@
spin_unlock(&inode->i_lock);
}
}
+ nfs_direct_req_release(dreq);
+ return result;
+
out_release:
nfs_direct_req_release(dreq);
+out_unlock:
+ mutex_unlock(&inode->i_mutex);
out:
return result;
}