1 files changed, 71 insertions, 28 deletions

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index af3af685a9e3..88a6d2196ece 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -473,13 +473,18 @@ try_again:
         do {
                 /*
                  * Subrequests are always contiguous, non overlapping
-                 * and in order. If not, it's a programming error.
+                 * and in order - but may be repeated (mirrored writes).
                  */
-                WARN_ON_ONCE(subreq->wb_offset !=
-                     (head->wb_offset + total_bytes));
-
-                /* keep track of how many bytes this group covers */
-                total_bytes += subreq->wb_bytes;
+                if (subreq->wb_offset == (head->wb_offset + total_bytes)) {
+                        /* keep track of how many bytes this group covers */
+                        total_bytes += subreq->wb_bytes;
+                } else if (WARN_ON_ONCE(subreq->wb_offset < head->wb_offset ||
+                            ((subreq->wb_offset + subreq->wb_bytes) >
+                             (head->wb_offset + total_bytes)))) {
+                        nfs_page_group_unlock(head);
+                        spin_unlock(&inode->i_lock);
+                        return ERR_PTR(-EIO);
+                }
 
                 if (!nfs_lock_request(subreq)) {
                         /* releases page group bit lock and
@@ -786,7 +791,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
         spin_unlock(cinfo->lock);
         if (!cinfo->dreq) {
                 inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-                inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+                inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
                              BDI_RECLAIMABLE);
                 __mark_inode_dirty(req->wb_context->dentry->d_inode,
                                    I_DIRTY_DATASYNC);
@@ -842,9 +847,9 @@ EXPORT_SYMBOL_GPL(nfs_init_cinfo);
  */
 void
 nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-                        struct nfs_commit_info *cinfo)
+                        struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
-        if (pnfs_mark_request_commit(req, lseg, cinfo))
+        if (pnfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx))
                 return;
         nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo);
 }
@@ -853,7 +858,7 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
         dec_zone_page_state(page, NR_UNSTABLE_NFS);
-        dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
+        dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE);
 }
 
 /* Called holding inode (/cinfo) lock */
@@ -900,7 +905,8 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
                 }
                 if (nfs_write_need_commit(hdr)) {
                         memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
-                        nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+                        nfs_mark_request_commit(req, hdr->lseg, &cinfo,
+                                hdr->pgio_mirror_idx);
                         goto next;
                 }
 remove_req:
@@ -1091,6 +1097,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 {
         struct nfs_open_context *ctx = nfs_file_open_context(file);
         struct nfs_lock_context *l_ctx;
+        struct file_lock_context *flctx = file_inode(file)->i_flctx;
         struct nfs_page *req;
         int do_flush, status;
         /*
@@ -1109,7 +1116,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
                 do_flush = req->wb_page != page || req->wb_context != ctx;
                 /* for now, flush if more than 1 request in page_group */
                 do_flush |= req->wb_this_page != req;
-                if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) {
+                if (l_ctx && flctx &&
+                    !(list_empty_careful(&flctx->flc_posix) &&
+                      list_empty_careful(&flctx->flc_flock))) {
                         do_flush |= l_ctx->lockowner.l_owner != current->files
                                 || l_ctx->lockowner.l_pid != current->tgid;
                 }
@@ -1170,6 +1179,13 @@ out:
         return PageUptodate(page) != 0;
 }
 
+static bool
+is_whole_file_wrlock(struct file_lock *fl)
+{
+        return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX &&
+                        fl->fl_type == F_WRLCK;
+}
+
 /* If we know the page is up to date, and we're not using byte range locks (or
  * if we have the whole file locked for writing), it may be more efficient to
  * extend the write to cover the entire page in order to avoid fragmentation
@@ -1180,17 +1196,36 @@ out:
  */
 static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode)
 {
+        int ret;
+        struct file_lock_context *flctx = inode->i_flctx;
+        struct file_lock *fl;
+
         if (file->f_flags & O_DSYNC)
                 return 0;
         if (!nfs_write_pageuptodate(page, inode))
                 return 0;
         if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
                 return 1;
-        if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 &&
-                        inode->i_flock->fl_end == OFFSET_MAX &&
-                        inode->i_flock->fl_type != F_RDLCK))
-                return 1;
-        return 0;
+        if (!flctx || (list_empty_careful(&flctx->flc_flock) &&
+                       list_empty_careful(&flctx->flc_posix)))
+                return 0;
+
+        /* Check to see if there are whole file write locks */
+        ret = 0;
+        spin_lock(&flctx->flc_lock);
+        if (!list_empty(&flctx->flc_posix)) {
+                fl = list_first_entry(&flctx->flc_posix, struct file_lock,
+                                        fl_list);
+                if (is_whole_file_wrlock(fl))
+                        ret = 1;
+        } else if (!list_empty(&flctx->flc_flock)) {
+                fl = list_first_entry(&flctx->flc_flock, struct file_lock,
+                                        fl_list);
+                if (fl->fl_type == F_WRLCK)
+                        ret = 1;
+        }
+        spin_unlock(&flctx->flc_lock);
+        return ret;
 }
 
 /*
@@ -1240,15 +1275,15 @@ static int flush_task_priority(int how)
 
 static void nfs_initiate_write(struct nfs_pgio_header *hdr,
                                struct rpc_message *msg,
+                               const struct nfs_rpc_ops *rpc_ops,
                                struct rpc_task_setup *task_setup_data, int how)
 {
-        struct inode *inode = hdr->inode;
         int priority = flush_task_priority(how);
 
         task_setup_data->priority = priority;
-        NFS_PROTO(inode)->write_setup(hdr, msg);
+        rpc_ops->write_setup(hdr, msg);
 
-        nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client,
+        nfs4_state_protect_write(NFS_SERVER(hdr->inode)->nfs_client,
                                  &task_setup_data->rpc_client, msg, hdr);
 }
 
@@ -1298,8 +1333,14 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_write);
 
 void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 {
+        struct nfs_pgio_mirror *mirror;
+
         pgio->pg_ops = &nfs_pgio_rw_ops;
-        pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
+
+        nfs_pageio_stop_mirroring(pgio);
+
+        mirror = &pgio->pg_mirrors[0];
+        mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 
@@ -1465,6 +1506,7 @@ void nfs_commitdata_release(struct nfs_commit_data *data)
 EXPORT_SYMBOL_GPL(nfs_commitdata_release);
 
 int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
+                        const struct nfs_rpc_ops *nfs_ops,
                         const struct rpc_call_ops *call_ops,
                         int how, int flags)
 {
@@ -1486,7 +1528,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
                 .priority = priority,
         };
         /* Set up the initial task struct.  */
-        NFS_PROTO(data->inode)->commit_setup(data, &msg);
+        nfs_ops->commit_setup(data, &msg);
 
         dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid);
 
@@ -1554,17 +1596,18 @@ EXPORT_SYMBOL_GPL(nfs_init_commit);
 
 void nfs_retry_commit(struct list_head *page_list,
                       struct pnfs_layout_segment *lseg,
-                      struct nfs_commit_info *cinfo)
+                      struct nfs_commit_info *cinfo,
+                      u32 ds_commit_idx)
 {
         struct nfs_page *req;
 
         while (!list_empty(page_list)) {
                 req = nfs_list_entry(page_list->next);
                 nfs_list_remove_request(req);
-                nfs_mark_request_commit(req, lseg, cinfo);
+                nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx);
                 if (!cinfo->dreq) {
                         dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-                        dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+                        dec_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
                                      BDI_RECLAIMABLE);
                 }
                 nfs_unlock_and_release_request(req);
@@ -1589,10 +1632,10 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
         /* Set up the argument struct */
         nfs_init_commit(data, head, NULL, cinfo);
         atomic_inc(&cinfo->mds->rpcs_out);
-        return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops,
-                                   how, 0);
+        return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
+                                   data->mds_ops, how, 0);
  out_bad:
-        nfs_retry_commit(head, NULL, cinfo);
+        nfs_retry_commit(head, NULL, cinfo, 0);
         cinfo->completion_ops->error_cleanup(NFS_I(inode));
         return -ENOMEM;
 }