nfs: count DIO good bytes correctly with mirroring

When resending to MDS, we might resend multiple mirroring
requests to MDS. As a result, nfs_direct_good_bytes() ends
up counting bytes multiple times, causing application to
get wrong return results in read/write syscalls.

Fix it by tracking start of a dreq and checking the range of
pgio header.

Cc: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Peng Tao <tao.peng@primarydata.com>

1 files changed, 8 insertions, 4 deletions

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 4fad6b727eb4..3715b4957abc 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -88,6 +88,7 @@ struct nfs_direct_req {
 
         ssize_t                 count,          /* bytes actually processed */
                                 bytes_left,     /* bytes left to be sent */
+                                io_start,       /* start of IO */
                                 error;          /* any reported error */
         struct completion       completion;     /* wait for i/o completion */
 
@@ -130,10 +131,11 @@ nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
 
         WARN_ON_ONCE(hdr->pgio_mirror_idx >= dreq->mirror_count);
 
-        dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes;
-
-        if (hdr->pgio_mirror_idx == 0)
-                dreq->count += hdr->good_bytes;
+        count = dreq->mirrors[hdr->pgio_mirror_idx].count;
+        if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
+                count = hdr->io_start + hdr->good_bytes - dreq->io_start;
+                dreq->mirrors[hdr->pgio_mirror_idx].count = count;
+        }
 
         /* update the dreq->count by finding the minimum agreed count from all
          * mirrors */
@@ -594,6 +596,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 
         dreq->inode = inode;
         dreq->bytes_left = count;
+        dreq->io_start = pos;
         dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
         l_ctx = nfs_get_lock_context(dreq->ctx);
         if (IS_ERR(l_ctx)) {
@@ -1002,6 +1005,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
 
         dreq->inode = inode;
         dreq->bytes_left = count;
+        dreq->io_start = pos;
         dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
         l_ctx = nfs_get_lock_context(dreq->ctx);
         if (IS_ERR(l_ctx)) {