Merge branch 'for-2.6.35' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.35' of git://linux-nfs.org/~bfields/linux: (45 commits)
  Revert "nfsd4: distinguish expired from stale stateids"
  nfsd: safer initialization order in find_file()
  nfs4: minor callback code simplification, comment
  NFSD: don't report compiled-out versions as present
  nfsd4: implement reclaim_complete
  nfsd4: nfsd4_destroy_session must set callback client under the state lock
  nfsd4: keep a reference count on client while in use
  nfsd4: mark_client_expired
  nfsd4: introduce nfs4_client.cl_refcount
  nfsd4: refactor expire_client
  nfsd4: extend the client_lock to cover cl_lru
  nfsd4: use list_move in move_to_confirmed
  nfsd4: fold release_session into expire_client
  nfsd4: rename sessionid_lock to client_lock
  nfsd4: fix bare destroy_session null dereference
  nfsd4: use local variable in nfs4svc_encode_compoundres
  nfsd: further comment typos
  sunrpc: centralise most calls to svc_xprt_received
  nfsd4: fix unlikely race in session replay case
  nfsd4: fix filehandle comment
  ...

net/sunrpc/cache.c

@@ -50,11 +50,17 @@ static void cache_init(struct cache_head *h)
 	h->last_refresh = now;
 }
 
+static inline int cache_is_expired(struct cache_detail *detail, struct cache_head *h)
+{
+	return  (h->expiry_time < get_seconds()) ||
+		(detail->flush_time > h->last_refresh);
+}
+
 struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 				       struct cache_head *key, int hash)
 {
 	struct cache_head **head,  **hp;
-	struct cache_head *new = NULL;
+	struct cache_head *new = NULL, *freeme = NULL;
 
 	head = &detail->hash_table[hash];
 
@@ -63,6 +69,9 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 	for (hp=head; *hp != NULL ; hp = &(*hp)->next) {
 		struct cache_head *tmp = *hp;
 		if (detail->match(tmp, key)) {
+			if (cache_is_expired(detail, tmp))
+				/* This entry is expired, we will discard it. */
+				break;
 			cache_get(tmp);
 			read_unlock(&detail->hash_lock);
 			return tmp;
@@ -87,6 +96,13 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 	for (hp=head; *hp != NULL ; hp = &(*hp)->next) {
 		struct cache_head *tmp = *hp;
 		if (detail->match(tmp, key)) {
+			if (cache_is_expired(detail, tmp)) {
+				*hp = tmp->next;
+				tmp->next = NULL;
+				detail->entries --;
+				freeme = tmp;
+				break;
+			}
 			cache_get(tmp);
 			write_unlock(&detail->hash_lock);
 			cache_put(new, detail);
@@ -99,6 +115,8 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 	cache_get(new);
 	write_unlock(&detail->hash_lock);
 
+	if (freeme)
+		cache_put(freeme, detail);
 	return new;
 }
 EXPORT_SYMBOL_GPL(sunrpc_cache_lookup);
@@ -184,10 +202,7 @@ static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h)
 
 static inline int cache_is_valid(struct cache_detail *detail, struct cache_head *h)
 {
-	if (!test_bit(CACHE_VALID, &h->flags) ||
-	    h->expiry_time < get_seconds())
-		return -EAGAIN;
-	else if (detail->flush_time > h->last_refresh)
+	if (!test_bit(CACHE_VALID, &h->flags))
 		return -EAGAIN;
 	else {
 		/* entry is valid */
@@ -398,31 +413,27 @@ static int cache_clean(void)
 		/* Ok, now to clean this strand */
 
 		cp = & current_detail->hash_table[current_index];
-		ch = *cp;
-		for (; ch; cp= & ch->next, ch= *cp) {
+		for (ch = *cp ; ch ; cp = & ch->next, ch = *cp) {
 			if (current_detail->nextcheck > ch->expiry_time)
 				current_detail->nextcheck = ch->expiry_time+1;
-			if (ch->expiry_time >= get_seconds() &&
-			    ch->last_refresh >= current_detail->flush_time)
+			if (!cache_is_expired(current_detail, ch))
 				continue;
-			if (test_and_clear_bit(CACHE_PENDING, &ch->flags))
-				cache_dequeue(current_detail, ch);
 
-			if (atomic_read(&ch->ref.refcount) == 1)
-				break;
-		}
-		if (ch) {
 			*cp = ch->next;
 			ch->next = NULL;
 			current_detail->entries--;
 			rv = 1;
+			break;
 		}
+
 		write_unlock(&current_detail->hash_lock);
 		d = current_detail;
 		if (!ch)
 			current_index ++;
 		spin_unlock(&cache_list_lock);
 		if (ch) {
+			if (test_and_clear_bit(CACHE_PENDING, &ch->flags))
+				cache_dequeue(current_detail, ch);
 			cache_revisit_request(ch);
 			cache_put(ch, d);
 		}
@@ -1234,8 +1245,10 @@ static int content_open(struct inode *inode, struct file *file,
 	if (!cd || !try_module_get(cd->owner))
 		return -EACCES;
 	han = __seq_open_private(file, &cache_content_op, sizeof(*han));
-	if (han == NULL)
+	if (han == NULL) {
+		module_put(cd->owner);
 		return -ENOMEM;
+	}
 
 	han->cd = cd;
 	return 0;

net/sunrpc/svc_xprt.c

@@ -744,8 +744,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		if (rqstp->rq_deferred) {
 			svc_xprt_received(xprt);
 			len = svc_deferred_recv(rqstp);
-		} else
+		} else {
 			len = xprt->xpt_ops->xpo_recvfrom(rqstp);
+			svc_xprt_received(xprt);
+		}
 		dprintk("svc: got len=%d\n", len);
 	}
 
@@ -893,12 +895,12 @@ void svc_delete_xprt(struct svc_xprt *xprt)
 	 */
 	if (test_bit(XPT_TEMP, &xprt->xpt_flags))
 		serv->sv_tmpcnt--;
+	spin_unlock_bh(&serv->sv_lock);
 
 	while ((dr = svc_deferred_dequeue(xprt)) != NULL)
 		kfree(dr);
 
 	svc_xprt_put(xprt);
-	spin_unlock_bh(&serv->sv_lock);
 }
 
 void svc_close_xprt(struct svc_xprt *xprt)

net/sunrpc/svcsock.c

@@ -547,7 +547,6 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 			dprintk("svc: recvfrom returned error %d\n", -err);
 			set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		}
-		svc_xprt_received(&svsk->sk_xprt);
 		return -EAGAIN;
 	}
 	len = svc_addr_len(svc_addr(rqstp));
@@ -562,11 +561,6 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 	svsk->sk_sk->sk_stamp = skb->tstamp;
 	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
 
-	/*
-	 * Maybe more packets - kick another thread ASAP.
-	 */
-	svc_xprt_received(&svsk->sk_xprt);
-
 	len  = skb->len - sizeof(struct udphdr);
 	rqstp->rq_arg.len = len;
 
@@ -917,7 +911,6 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 		if (len < want) {
 			dprintk("svc: short recvfrom while reading record "
 				"length (%d of %d)\n", len, want);
-			svc_xprt_received(&svsk->sk_xprt);
 			goto err_again; /* record header not complete */
 		}
 
@@ -953,7 +946,6 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	if (len < svsk->sk_reclen) {
 		dprintk("svc: incomplete TCP record (%d of %d)\n",
 			len, svsk->sk_reclen);
-		svc_xprt_received(&svsk->sk_xprt);
 		goto err_again;	/* record not complete */
 	}
 	len = svsk->sk_reclen;
@@ -961,14 +953,11 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 
 	return len;
  error:
-	if (len == -EAGAIN) {
+	if (len == -EAGAIN)
 		dprintk("RPC: TCP recv_record got EAGAIN\n");
-		svc_xprt_received(&svsk->sk_xprt);
-	}
 	return len;
  err_delete:
 	set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
-	svc_xprt_received(&svsk->sk_xprt);
  err_again:
 	return -EAGAIN;
 }
@@ -1110,7 +1099,6 @@ out:
 	svsk->sk_tcplen = 0;
 
 	svc_xprt_copy_addrs(rqstp, &svsk->sk_xprt);
-	svc_xprt_received(&svsk->sk_xprt);
 	if (serv->sv_stats)
 		serv->sv_stats->nettcpcnt++;
 
@@ -1119,7 +1107,6 @@ out:
 err_again:
 	if (len == -EAGAIN) {
 		dprintk("RPC: TCP recvfrom got EAGAIN\n");
-		svc_xprt_received(&svsk->sk_xprt);
 		return len;
 	}
 error:

net/sunrpc/xprtrdma/svc_rdma_recvfrom.c

@@ -566,7 +566,6 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
 		ret, rqstp->rq_arg.len,	rqstp->rq_arg.head[0].iov_base,
 		rqstp->rq_arg.head[0].iov_len);
 
-	svc_xprt_received(rqstp->rq_xprt);
 	return ret;
 }
 
@@ -665,7 +664,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		rqstp->rq_arg.head[0].iov_len);
 	rqstp->rq_prot = IPPROTO_MAX;
 	svc_xprt_copy_addrs(rqstp, xprt);
-	svc_xprt_received(xprt);
 	return ret;
 
  close_out:
@@ -678,6 +676,5 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	 */
 	set_bit(XPT_CLOSE, &xprt->xpt_flags);
 defer:
-	svc_xprt_received(xprt);
 	return 0;
 }