Merge tag 'nfs-for-4.10-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable bugfixes:
   - Fix a pnfs deadlock between read resends and layoutreturn
   - Don't invalidate the layout stateid while a layout return is
     outstanding
   - Don't schedule a layoutreturn if the layout stateid is marked as
     invalid
   - On a pNFS error, do not send LAYOUTGET until the LAYOUTRETURN is
     complete
   - SUNRPC: fix refcounting problems with auth_gss messages.

  Features:
   - Add client support for the NFSv4 umask attribute.
   - NFSv4: Correct support for flock() stateids.
   - Add a LAYOUTRETURN operation to CLOSE and DELEGRETURN when
     return-on-close is specified
   - Allow the pNFS/flexfiles layoutstat information to piggyback on
     LAYOUTRETURN
   - Optimise away redundant GETATTR calls when doing state recovery
     and/or when not required by cache revalidation rules or
     close-to-open cache consistency.
   - Attribute cache improvements
   - RPC/RDMA support for SG_GAP devices

  Bugfixes:
   - NFS: Fix performance regressions in readdir
   - pNFS/flexfiles: Fix a deadlock on LAYOUTGET
   - NFSv4: Add missing nfs_put_lock_context()
   - NFSv4.1: Fix regression in callback retry handling
   - Fix false positive NFSv4.0 trunking detection.
   - pNFS/flexfiles: Only send layoutstats updates for mirrors that were
     updated
   - Various layout stateid related bugfixes
   - RPC/RDMA bugfixes"

* tag 'nfs-for-4.10-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (82 commits)
  SUNRPC: fix refcounting problems with auth_gss messages.
  nfs: add support for the umask attribute
  pNFS/flexfiles: Ensure we have enough buffer for layoutreturn
  pNFS/flexfiles: Remove a redundant parameter in ff_layout_encode_ioerr()
  pNFS/flexfiles: Fix a deadlock on LAYOUTGET
  pNFS: Layoutreturn must free the layout after the layout-private data
  pNFS/flexfiles: Fix ff_layout_add_ds_error_locked()
  NFSv4: Add missing nfs_put_lock_context()
  pNFS: Release NFS_LAYOUT_RETURN when invalidating the layout stateid
  NFSv4.1: Don't schedule lease recovery in nfs4_schedule_session_recovery()
  NFSv4.1: Handle NFS4ERR_BADSESSION/NFS4ERR_DEADSESSION replies to OP_SEQUENCE
  NFS: Only look at the change attribute cache state in nfs_check_verifier
  NFS: Fix incorrect size revalidation when holding a delegation
  NFS: Fix incorrect mapping revalidation when holding a delegation
  pNFS/flexfiles: Support sending layoutstats in layoutreturn
  pNFS/flexfiles: Minor refactoring before adding iostats to layoutreturn
  NFS: Fix up read of mirror stats
  pNFS/flexfiles: Clean up layoutstats
  pNFS/flexfiles: Refactor encoding of the layoutreturn payload
  pNFS: Add a layoutreturn callback to performa layout-private setup
  ...

1 files changed, 67 insertions, 32 deletions

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index e9aa235e9d10..f073a6d2c6a5 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -110,20 +110,52 @@ out:
 #if defined(CONFIG_NFS_V4_1)
 
 /*
- * Lookup a layout by filehandle.
+ * Lookup a layout inode by stateid
  *
- * Note: gets a refcount on the layout hdr and on its respective inode.
- * Caller must put the layout hdr and the inode.
+ * Note: returns a refcount on the inode and superblock
+ */
+static struct inode *nfs_layout_find_inode_by_stateid(struct nfs_client *clp,
+		const nfs4_stateid *stateid)
+{
+	struct nfs_server *server;
+	struct inode *inode;
+	struct pnfs_layout_hdr *lo;
+
+restart:
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		list_for_each_entry(lo, &server->layouts, plh_layouts) {
+			if (stateid != NULL &&
+			    !nfs4_stateid_match_other(stateid, &lo->plh_stateid))
+				continue;
+			inode = igrab(lo->plh_inode);
+			if (!inode)
+				continue;
+			if (!nfs_sb_active(inode->i_sb)) {
+				rcu_read_lock();
+				spin_unlock(&clp->cl_lock);
+				iput(inode);
+				spin_lock(&clp->cl_lock);
+				goto restart;
+			}
+			return inode;
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * Lookup a layout inode by filehandle.
+ *
+ * Note: returns a refcount on the inode and superblock
  *
- * TODO: keep track of all layouts (and delegations) in a hash table
- * hashed by filehandle.
  */
-static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
-		struct nfs_fh *fh)
+static struct inode *nfs_layout_find_inode_by_fh(struct nfs_client *clp,
+		const struct nfs_fh *fh)
 {
 	struct nfs_server *server;
 	struct nfs_inode *nfsi;
-	struct inode *ino;
+	struct inode *inode;
 	struct pnfs_layout_hdr *lo;
 
 restart:
@@ -134,37 +166,38 @@ restart:
 				continue;
 			if (nfsi->layout != lo)
 				continue;
-			ino = igrab(lo->plh_inode);
-			if (!ino)
-				break;
-			spin_lock(&ino->i_lock);
-			/* Is this layout in the process of being freed? */
-			if (nfsi->layout != lo) {
-				spin_unlock(&ino->i_lock);
-				iput(ino);
+			inode = igrab(lo->plh_inode);
+			if (!inode)
+				continue;
+			if (!nfs_sb_active(inode->i_sb)) {
+				rcu_read_lock();
+				spin_unlock(&clp->cl_lock);
+				iput(inode);
+				spin_lock(&clp->cl_lock);
 				goto restart;
 			}
-			pnfs_get_layout_hdr(lo);
-			spin_unlock(&ino->i_lock);
-			return lo;
+			return inode;
 		}
 	}
 
 	return NULL;
 }
 
-static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp,
-		struct nfs_fh *fh)
+static struct inode *nfs_layout_find_inode(struct nfs_client *clp,
+		const struct nfs_fh *fh,
+		const nfs4_stateid *stateid)
 {
-	struct pnfs_layout_hdr *lo;
+	struct inode *inode;
 
 	spin_lock(&clp->cl_lock);
 	rcu_read_lock();
-	lo = get_layout_by_fh_locked(clp, fh);
+	inode = nfs_layout_find_inode_by_stateid(clp, stateid);
+	if (!inode)
+		inode = nfs_layout_find_inode_by_fh(clp, fh);
 	rcu_read_unlock();
 	spin_unlock(&clp->cl_lock);
 
-	return lo;
+	return inode;
 }
 
 /*
@@ -213,18 +246,20 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
 	LIST_HEAD(free_me_list);
 
-	lo = get_layout_by_fh(clp, &args->cbl_fh);
-	if (!lo) {
-		trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, NULL,
-				&args->cbl_stateid, -rv);
+	ino = nfs_layout_find_inode(clp, &args->cbl_fh, &args->cbl_stateid);
+	if (!ino)
 		goto out;
-	}
 
-	ino = lo->plh_inode;
 	pnfs_layoutcommit_inode(ino, false);
 
 
 	spin_lock(&ino->i_lock);
+	lo = NFS_I(ino)->layout;
+	if (!lo) {
+		spin_unlock(&ino->i_lock);
+		goto out;
+	}
+	pnfs_get_layout_hdr(lo);
 	rv = pnfs_check_callback_stateid(lo, &args->cbl_stateid);
 	if (rv != NFS_OK)
 		goto unlock;
@@ -258,10 +293,10 @@ unlock:
 	/* Free all lsegs that are attached to commit buckets */
 	nfs_commit_inode(ino, 0);
 	pnfs_put_layout_hdr(lo);
+out:
 	trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, ino,
 			&args->cbl_stateid, -rv);
-	iput(ino);
-out:
+	nfs_iput_and_deactive(ino);
 	return rv;
 }