Merge tag 'nfsd-5.9' of git://git.linux-nfs.org/projects/cel/cel-2.6

Pull NFS server updates from Chuck Lever:
 "Highlights:
   - Support for user extended attributes on NFS (RFC 8276)
   - Further reduce unnecessary NFSv4 delegation recalls

  Notable fixes:
   - Fix recent krb5p regression
   - Address a few resource leaks and a rare NULL dereference

  Other:
   - De-duplicate RPC/RDMA error handling and other utility functions
   - Replace storage and display of kernel memory addresses by tracepoints"

* tag 'nfsd-5.9' of git://git.linux-nfs.org/projects/cel/cel-2.6: (38 commits)
  svcrdma: CM event handler clean up
  svcrdma: Remove transport reference counting
  svcrdma: Fix another Receive buffer leak
  SUNRPC: Refresh the show_rqstp_flags() macro
  nfsd: netns.h: delete a duplicated word
  SUNRPC: Fix ("SUNRPC: Add "@len" parameter to gss_unwrap()")
  nfsd: avoid a NULL dereference in __cld_pipe_upcall()
  nfsd4: a client's own opens needn't prevent delegations
  nfsd: Use seq_putc() in two functions
  svcrdma: Display chunk completion ID when posting a rw_ctxt
  svcrdma: Record send_ctxt completion ID in trace_svcrdma_post_send()
  svcrdma: Introduce Send completion IDs
  svcrdma: Record Receive completion ID in svc_rdma_decode_rqst
  svcrdma: Introduce Receive completion IDs
  svcrdma: Introduce infrastructure to support completion IDs
  svcrdma: Add common XDR encoders for RDMA and Read segments
  svcrdma: Add common XDR decoders for RDMA and Read segments
  SUNRPC: Add helpers for decoding list discriminators symbolically
  svcrdma: Remove declarations for functions long removed
  svcrdma: Clean up trace_svcrdma_send_failed() tracepoint
  ...

1 files changed, 40 insertions, 14 deletions

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c9056316a0b3..81ed8e8bab3f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4940,6 +4940,32 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
 	return fl;
 }
 
+static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
+						struct nfs4_file *fp)
+{
+	struct nfs4_clnt_odstate *co;
+	struct file *f = fp->fi_deleg_file->nf_file;
+	struct inode *ino = locks_inode(f);
+	int writes = atomic_read(&ino->i_writecount);
+
+	if (fp->fi_fds[O_WRONLY])
+		writes--;
+	if (fp->fi_fds[O_RDWR])
+		writes--;
+	WARN_ON_ONCE(writes < 0);
+	if (writes > 0)
+		return -EAGAIN;
+	spin_lock(&fp->fi_lock);
+	list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) {
+		if (co->co_client != clp) {
+			spin_unlock(&fp->fi_lock);
+			return -EAGAIN;
+		}
+	}
+	spin_unlock(&fp->fi_lock);
+	return 0;
+}
+
 static struct nfs4_delegation *
 nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		    struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
@@ -4959,9 +4985,12 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 
 	nf = find_readable_file(fp);
 	if (!nf) {
-		/* We should always have a readable file here */
-		WARN_ON_ONCE(1);
-		return ERR_PTR(-EBADF);
+		/*
+		 * We probably could attempt another open and get a read
+		 * delegation, but for now, don't bother until the
+		 * client actually sends us one.
+		 */
+		return ERR_PTR(-EAGAIN);
 	}
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
@@ -4991,11 +5020,19 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 	if (!fl)
 		goto out_clnt_odstate;
 
+	status = nfsd4_check_conflicting_opens(clp, fp);
+	if (status) {
+		locks_free_lock(fl);
+		goto out_clnt_odstate;
+	}
 	status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL);
 	if (fl)
 		locks_free_lock(fl);
 	if (status)
 		goto out_clnt_odstate;
+	status = nfsd4_check_conflicting_opens(clp, fp);
+	if (status)
+		goto out_clnt_odstate;
 
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
@@ -5077,17 +5114,6 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
 				goto out_no_deleg;
 			if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
 				goto out_no_deleg;
-			/*
-			 * Also, if the file was opened for write or
-			 * create, there's a good chance the client's
-			 * about to write to it, resulting in an
-			 * immediate recall (since we don't support
-			 * write delegations):
-			 */
-			if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
-				goto out_no_deleg;
-			if (open->op_create == NFS4_OPEN_CREATE)
-				goto out_no_deleg;
 			break;
 		default:
 			goto out_no_deleg;