Merge tag 'nfs-for-4.9-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "Highlights include:

  Stable bugfixes:
   - sunrpc: fix writ espace race causing stalls
   - NFS: Fix inode corruption in nfs_prime_dcache()
   - NFSv4: Don't report revoked delegations as valid in nfs_have_delegation()
   - NFSv4: nfs4_copy_delegation_stateid() must fail if the delegation is invalid
   - NFSv4: Open state recovery must account for file permission changes
   - NFSv4.2: Fix a reference leak in nfs42_proc_layoutstats_generic

  Features:
   - Add support for tracking multiple layout types with an ordered list
   - Add support for using multiple backchannel threads on the client
   - Add support for pNFS file layout session trunking
   - Delay xprtrdma use of DMA API (for device driver removal)
   - Add support for xprtrdma remote invalidation
   - Add support for larger xprtrdma inline thresholds
   - Use a scatter/gather list for sending xprtrdma RPC calls
   - Add support for the CB_NOTIFY_LOCK callback
   - Improve hashing sunrpc auth_creds by using both uid and gid

  Bugfixes:
   - Fix xprtrdma use of DMA API
   - Validate filenames before adding to the dcache
   - Fix corruption of xdr->nwords in xdr_copy_to_scratch
   - Fix setting buffer length in xdr_set_next_buffer()
   - Don't deadlock the state manager on the SEQUENCE status flags
   - Various delegation and stateid related fixes
   - Retry operations if an interrupted slot receives EREMOTEIO
   - Make nfs boot time y2038 safe"

* tag 'nfs-for-4.9-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (100 commits)
  NFSv4.2: Fix a reference leak in nfs42_proc_layoutstats_generic
  fs: nfs: Make nfs boot time y2038 safe
  sunrpc: replace generic auth_cred hash with auth-specific function
  sunrpc: add RPCSEC_GSS hash_cred() function
  sunrpc: add auth_unix hash_cred() function
  sunrpc: add generic_auth hash_cred() function
  sunrpc: add hash_cred() function to rpc_authops struct
  Retry operation on EREMOTEIO on an interrupted slot
  pNFS: Fix atime updates on pNFS clients
  sunrpc: queue work on system_power_efficient_wq
  NFSv4.1: Even if the stateid is OK, we may need to recover the open modes
  NFSv4: If recovery failed for a specific open stateid, then don't retry
  NFSv4: Fix retry issues with nfs41_test/free_stateid
  NFSv4: Open state recovery must account for file permission changes
  NFSv4: Mark the lock and open stateids as invalid after freeing them
  NFSv4: Don't test open_stateid unless it is set
  NFSv4: nfs4_do_handle_exception() handle revoke/expiry of a single stateid
  NFS: Always call nfs_inode_find_state_and_recover() when revoking a delegation
  NFSv4: Fix a race when updating an open_stateid
  NFSv4: Fix a race in nfs_inode_reclaim_delegation()
  ...

1 files changed, 58 insertions, 15 deletions

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 2c93a85eda51..56b2d96f9103 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -30,6 +30,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
 #include <linux/module.h>
+#include <linux/sort.h>
 #include "internal.h"
 #include "pnfs.h"
 #include "iostat.h"
@@ -99,35 +100,79 @@ unset_pnfs_layoutdriver(struct nfs_server *nfss)
 }
 
 /*
+ * When the server sends a list of layout types, we choose one in the order
+ * given in the list below.
+ *
+ * FIXME: should this list be configurable in some fashion? module param?
+ * 	  mount option? something else?
+ */
+static const u32 ld_prefs[] = {
+	LAYOUT_SCSI,
+	LAYOUT_BLOCK_VOLUME,
+	LAYOUT_OSD2_OBJECTS,
+	LAYOUT_FLEX_FILES,
+	LAYOUT_NFSV4_1_FILES,
+	0
+};
+
+static int
+ld_cmp(const void *e1, const void *e2)
+{
+	u32 ld1 = *((u32 *)e1);
+	u32 ld2 = *((u32 *)e2);
+	int i;
+
+	for (i = 0; ld_prefs[i] != 0; i++) {
+		if (ld1 == ld_prefs[i])
+			return -1;
+
+		if (ld2 == ld_prefs[i])
+			return 1;
+	}
+	return 0;
+}
+
+/*
  * Try to set the server's pnfs module to the pnfs layout type specified by id.
  * Currently only one pNFS layout driver per filesystem is supported.
  *
- * @id layout type. Zero (illegal layout type) indicates pNFS not in use.
+ * @ids array of layout types supported by MDS.
  */
 void
 set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
-		      u32 id)
+		      struct nfs_fsinfo *fsinfo)
 {
 	struct pnfs_layoutdriver_type *ld_type = NULL;
+	u32 id;
+	int i;
 
-	if (id == 0)
-		goto out_no_driver;
 	if (!(server->nfs_client->cl_exchange_flags &
 		 (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) {
-		printk(KERN_ERR "NFS: %s: id %u cl_exchange_flags 0x%x\n",
-			__func__, id, server->nfs_client->cl_exchange_flags);
+		printk(KERN_ERR "NFS: %s: cl_exchange_flags 0x%x\n",
+			__func__, server->nfs_client->cl_exchange_flags);
 		goto out_no_driver;
 	}
-	ld_type = find_pnfs_driver(id);
-	if (!ld_type) {
-		request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX, id);
+
+	sort(fsinfo->layouttype, fsinfo->nlayouttypes,
+		sizeof(*fsinfo->layouttype), ld_cmp, NULL);
+
+	for (i = 0; i < fsinfo->nlayouttypes; i++) {
+		id = fsinfo->layouttype[i];
 		ld_type = find_pnfs_driver(id);
 		if (!ld_type) {
-			dprintk("%s: No pNFS module found for %u.\n",
-				__func__, id);
-			goto out_no_driver;
+			request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX,
+					id);
+			ld_type = find_pnfs_driver(id);
 		}
+		if (ld_type)
+			break;
+	}
+
+	if (!ld_type) {
+		dprintk("%s: No pNFS module found!\n", __func__);
+		goto out_no_driver;
 	}
+
 	server->pnfs_curr_ld = ld_type;
 	if (ld_type->set_layoutdriver
 	    && ld_type->set_layoutdriver(server, mntfh)) {
@@ -2185,10 +2230,8 @@ static void pnfs_ld_handle_read_error(struct nfs_pgio_header *hdr)
  */
 void pnfs_ld_read_done(struct nfs_pgio_header *hdr)
 {
-	if (likely(!hdr->pnfs_error)) {
-		__nfs4_read_done_cb(hdr);
+	if (likely(!hdr->pnfs_error))
 		hdr->mds_ops->rpc_call_done(&hdr->task, hdr);
-	}
 	trace_nfs4_pnfs_read(hdr, hdr->pnfs_error);
 	if (unlikely(hdr->pnfs_error))
 		pnfs_ld_handle_read_error(hdr);