Merge tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable fixes:

   - SUNRPC: Ensure bvecs are re-synced when we re-encode the RPC
     request

   - Fix an Oops in ff_layout_track_ds_error due to a PTR_ERR()
     dereference

   - Revert buggy NFS readdirplus optimisation

   - NFSv4: Handle the special Linux file open access mode

   - pnfs: Fix a problem where we gratuitously start doing I/O through
     the MDS

  Features:

   - Allow NFS client to set up multiple TCP connections to the server
     using a new 'nconnect=X' mount option. Queue length is used to
     balance load.

   - Enhance statistics reporting to report on all transports when using
     multiple connections.

   - Speed up SUNRPC by removing bh-safe spinlocks

   - Add a mechanism to allow NFSv4 to request that containers set a
     unique per-host identifier for when the hostname is not set.

   - Ensure NFSv4 updates the lease_time after a clientid update

  Bugfixes and cleanup:

   - Fix use-after-free in rpcrdma_post_recvs

   - Fix a memory leak when nfs_match_client() is interrupted

   - Fix buggy file access checking in NFSv4 open for execute

   - disable unsupported client side deduplication

   - Fix spurious client disconnections

   - Fix occasional RDMA transport deadlock

   - Various RDMA cleanups

   - Various tracepoint fixes

   - Fix the TCP callback channel to guarantee the server can actually
     send the number of callback requests that was negotiated at mount
     time"

* tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (68 commits)
  pnfs/flexfiles: Add tracepoints for detecting pnfs fallback to MDS
  pnfs: Fix a problem where we gratuitously start doing I/O through the MDS
  SUNRPC: Optimise transport balancing code
  SUNRPC: Ensure the bvecs are reset when we re-encode the RPC request
  pnfs/flexfiles: Fix PTR_ERR() dereferences in ff_layout_track_ds_error
  NFSv4: Don't use the zero stateid with layoutget
  SUNRPC: Fix up backchannel slot table accounting
  SUNRPC: Fix initialisation of struct rpc_xprt_switch
  SUNRPC: Skip zero-refcount transports
  SUNRPC: Replace division by multiplication in calculation of queue length
  NFSv4: Validate the stateid before applying it to state recovery
  nfs4.0: Refetch lease_time after clientid update
  nfs4: Rename nfs41_setup_state_renewal
  nfs4: Make nfs4_proc_get_lease_time available for nfs4.0
  nfs: Fix copy-and-paste error in debug message
  NFS: Replace 16 seq_printf() calls by seq_puts()
  NFS: Use seq_putc() in nfs_show_stats()
  Revert "NFS: readdirplus optimization by cache mechanism" (memleak)
  SUNRPC: Fix transport accounting when caller specifies an rpc_xprt
  NFS: Record task, client ID, and XID in xdr_status trace points
  ...

1 files changed, 15 insertions, 5 deletions

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 83722e936b4a..75bd5b552ba4 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1890,7 +1890,7 @@ lookup_again:
 		spin_unlock(&ino->i_lock);
 		lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding,
 					!atomic_read(&lo->plh_outstanding)));
-		if (IS_ERR(lseg) || !list_empty(&lo->plh_segs))
+		if (IS_ERR(lseg))
 			goto out_put_layout_hdr;
 		pnfs_put_layout_hdr(lo);
 		goto lookup_again;
@@ -1915,6 +1915,7 @@ lookup_again:
 	 * stateid.
 	 */
 	if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
+		int status;
 
 		/*
 		 * The first layoutget for the file. Need to serialize per
@@ -1934,13 +1935,20 @@ lookup_again:
 		}
 
 		first = true;
-		if (nfs4_select_rw_stateid(ctx->state,
+		status = nfs4_select_rw_stateid(ctx->state,
 					iomode == IOMODE_RW ? FMODE_WRITE : FMODE_READ,
-					NULL, &stateid, NULL) != 0) {
+					NULL, &stateid, NULL);
+		if (status != 0) {
 			trace_pnfs_update_layout(ino, pos, count,
 					iomode, lo, lseg,
 					PNFS_UPDATE_LAYOUT_INVALID_OPEN);
-			goto out_unlock;
+			if (status != -EAGAIN)
+				goto out_unlock;
+			spin_unlock(&ino->i_lock);
+			nfs4_schedule_stateid_recovery(server, ctx->state);
+			pnfs_clear_first_layoutget(lo);
+			pnfs_put_layout_hdr(lo);
+			goto lookup_again;
 		}
 	} else {
 		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
@@ -2029,6 +2037,8 @@ lookup_again:
 out_put_layout_hdr:
 	if (first)
 		pnfs_clear_first_layoutget(lo);
+	trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+				 PNFS_UPDATE_LAYOUT_EXIT);
 	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("%s: inode %s/%llu pNFS layout segment %s for "
@@ -2468,7 +2478,7 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 						   wb_size,
 						   IOMODE_RW,
 						   false,
-						   GFP_NOFS);
+						   GFP_KERNEL);
 		if (IS_ERR(pgio->pg_lseg)) {
 			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
 			pgio->pg_lseg = NULL;