Merge branch 'for-3.11' of git://linux-nfs.org/~bfields/linux

Pull nfsd changes from Bruce Fields:
 "Changes this time include:

   - 4.1 enabled on the server by default: the last 4.1-specific issues
     I know of are fixed, so we're not going to find the rest of the
     bugs without more exposure.
   - Experimental support for NFSv4.2 MAC Labeling (to allow running
     selinux over NFS), from Dave Quigley.
   - Fixes for some delicate cache/upcall races that could cause rare
     server hangs; thanks to Neil Brown and Bodo Stroesser for extreme
     debugging persistence.
   - Fixes for some bugs found at the recent NFS bakeathon, mostly v4
     and v4.1-specific, but also a generic bug handling fragmented rpc
     calls"

* 'for-3.11' of git://linux-nfs.org/~bfields/linux: (31 commits)
  nfsd4: support minorversion 1 by default
  nfsd4: allow destroy_session over destroyed session
  svcrpc: fix failures to handle -1 uid's
  sunrpc: Don't schedule an upcall on a replaced cache entry.
  net/sunrpc: xpt_auth_cache should be ignored when expired.
  sunrpc/cache: ensure items removed from cache do not have pending upcalls.
  sunrpc/cache: use cache_fresh_unlocked consistently and correctly.
  sunrpc/cache: remove races with queuing an upcall.
  nfsd4: return delegation immediately if lease fails
  nfsd4: do not throw away 4.1 lock state on last unlock
  nfsd4: delegation-based open reclaims should bypass permissions
  svcrpc: don't error out on small tcp fragment
  svcrpc: fix handling of too-short rpc's
  nfsd4: minor read_buf cleanup
  nfsd4: fix decoding of compounds across page boundaries
  nfsd4: clean up nfs4_open_delegation
  NFSD: Don't give out read delegations on creates
  nfsd4: allow client to send no cb_sec flavors
  nfsd4: fail attempts to request gss on the backchannel
  nfsd4: implement minimal SP4_MACH_CRED
  ...

6 files changed, 63 insertions, 51 deletions

diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index defa9d3..27ce262 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -139,11 +139,12 @@ void gss_mech_unregister(struct gss_api_mech *gm)
 }
 EXPORT_SYMBOL_GPL(gss_mech_unregister);
 
-static struct gss_api_mech *gss_mech_get(struct gss_api_mech *gm)
+struct gss_api_mech *gss_mech_get(struct gss_api_mech *gm)
 {
 	__module_get(gm->gm_owner);
 	return gm;
 }
+EXPORT_SYMBOL(gss_mech_get);
 
 static struct gss_api_mech *
 _gss_mech_get_by_name(const char *name)
@@ -360,6 +361,7 @@ gss_pseudoflavor_to_service(struct gss_api_mech *gm, u32 pseudoflavor)
 	}
 	return 0;
 }
+EXPORT_SYMBOL(gss_pseudoflavor_to_service);
 
 char *
 gss_service_to_auth_domain_name(struct gss_api_mech *gm, u32 service)
@@ -379,6 +381,7 @@ gss_mech_put(struct gss_api_mech * gm)
 	if (gm)
 		module_put(gm->gm_owner);
 }
+EXPORT_SYMBOL(gss_mech_put);
 
 /* The mech could probably be determined from the token instead, but it's just
  * as easy for now to pass it in. */
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index b05ace4..d0347d1 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -377,8 +377,7 @@ rsc_init(struct cache_head *cnew, struct cache_head *ctmp)
 	new->handle.data = tmp->handle.data;
 	tmp->handle.data = NULL;
 	new->mechctx = NULL;
-	new->cred.cr_group_info = NULL;
-	new->cred.cr_principal = NULL;
+	init_svc_cred(&new->cred);
 }
 
 static void
@@ -392,9 +391,7 @@ update_rsc(struct cache_head *cnew, struct cache_head *ctmp)
 	memset(&new->seqdata, 0, sizeof(new->seqdata));
 	spin_lock_init(&new->seqdata.sd_lock);
 	new->cred = tmp->cred;
-	tmp->cred.cr_group_info = NULL;
-	new->cred.cr_principal = tmp->cred.cr_principal;
-	tmp->cred.cr_principal = NULL;
+	init_svc_cred(&tmp->cred);
 }
 
 static struct cache_head *
@@ -487,7 +484,7 @@ static int rsc_parse(struct cache_detail *cd,
 		len = qword_get(&mesg, buf, mlen);
 		if (len < 0)
 			goto out;
-		gm = gss_mech_get_by_name(buf);
+		gm = rsci.cred.cr_gss_mech = gss_mech_get_by_name(buf);
 		status = -EOPNOTSUPP;
 		if (!gm)
 			goto out;
@@ -517,7 +514,6 @@ static int rsc_parse(struct cache_detail *cd,
 	rscp = rsc_update(cd, &rsci, rscp);
 	status = 0;
 out:
-	gss_mech_put(gm);
 	rsc_free(&rsci);
 	if (rscp)
 		cache_put(&rscp->h, cd);
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 80fe5c8..49eb370 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -50,12 +50,6 @@ 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 < seconds_since_boot()) ||
-		(detail->flush_time > h->last_refresh);
-}
-
 struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 				       struct cache_head *key, int hash)
 {
@@ -201,7 +195,7 @@ static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h)
 	return sunrpc_cache_pipe_upcall(cd, h);
 }
 
-static inline int cache_is_valid(struct cache_detail *detail, struct cache_head *h)
+static inline int cache_is_valid(struct cache_head *h)
 {
 	if (!test_bit(CACHE_VALID, &h->flags))
 		return -EAGAIN;
@@ -227,16 +221,15 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h
 	int rv;
 
 	write_lock(&detail->hash_lock);
-	rv = cache_is_valid(detail, h);
-	if (rv != -EAGAIN) {
-		write_unlock(&detail->hash_lock);
-		return rv;
+	rv = cache_is_valid(h);
+	if (rv == -EAGAIN) {
+		set_bit(CACHE_NEGATIVE, &h->flags);
+		cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY);
+		rv = -ENOENT;
 	}
-	set_bit(CACHE_NEGATIVE, &h->flags);
-	cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY);
 	write_unlock(&detail->hash_lock);
 	cache_fresh_unlocked(h, detail);
-	return -ENOENT;
+	return rv;
 }
 
 /*
@@ -260,7 +253,7 @@ int cache_check(struct cache_detail *detail,
 	long refresh_age, age;
 
 	/* First decide return status as best we can */
-	rv = cache_is_valid(detail, h);
+	rv = cache_is_valid(h);
 
 	/* now see if we want to start an upcall */
 	refresh_age = (h->expiry_time - h->last_refresh);
@@ -269,19 +262,17 @@ int cache_check(struct cache_detail *detail,
 	if (rqstp == NULL) {
 		if (rv == -EAGAIN)
 			rv = -ENOENT;
-	} else if (rv == -EAGAIN || age > refresh_age/2) {
+	} else if (rv == -EAGAIN ||
+		   (h->expiry_time != 0 && age > refresh_age/2)) {
 		dprintk("RPC:       Want update, refage=%ld, age=%ld\n",
 				refresh_age, age);
 		if (!test_and_set_bit(CACHE_PENDING, &h->flags)) {
 			switch (cache_make_upcall(detail, h)) {
 			case -EINVAL:
-				clear_bit(CACHE_PENDING, &h->flags);
-				cache_revisit_request(h);
 				rv = try_to_negate_entry(detail, h);
 				break;
 			case -EAGAIN:
-				clear_bit(CACHE_PENDING, &h->flags);
-				cache_revisit_request(h);
+				cache_fresh_unlocked(h, detail);
 				break;
 			}
 		}
@@ -293,7 +284,7 @@ int cache_check(struct cache_detail *detail,
 			 * Request was not deferred; handle it as best
 			 * we can ourselves:
 			 */
-			rv = cache_is_valid(detail, h);
+			rv = cache_is_valid(h);
 			if (rv == -EAGAIN)
 				rv = -ETIMEDOUT;
 		}
@@ -310,7 +301,7 @@ EXPORT_SYMBOL_GPL(cache_check);
  * a current pointer into that list and into the table
  * for that entry.
  *
- * Each time clean_cache is called it finds the next non-empty entry
+ * Each time cache_clean is called it finds the next non-empty entry
  * in the current table and walks the list in that entry
  * looking for entries that can be removed.
  *
@@ -457,9 +448,8 @@ static int cache_clean(void)
 			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);
+			set_bit(CACHE_CLEANED, &ch->flags);
+			cache_fresh_unlocked(ch, d);
 			cache_put(ch, d);
 		}
 	} else
@@ -1036,23 +1026,32 @@ static int cache_release(struct inode *inode, struct file *filp,
 
 static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch)
 {
-	struct cache_queue *cq;
+	struct cache_queue *cq, *tmp;
+	struct cache_request *cr;
+	struct list_head dequeued;
+
+	INIT_LIST_HEAD(&dequeued);
 	spin_lock(&queue_lock);
-	list_for_each_entry(cq, &detail->queue, list)
+	list_for_each_entry_safe(cq, tmp, &detail->queue, list)
 		if (!cq->reader) {
-			struct cache_request *cr = container_of(cq, struct cache_request, q);
+			cr = container_of(cq, struct cache_request, q);
 			if (cr->item != ch)
 				continue;
+			if (test_bit(CACHE_PENDING, &ch->flags))
+				/* Lost a race and it is pending again */
+				break;
 			if (cr->readers != 0)
 				continue;
-			list_del(&cr->q.list);
-			spin_unlock(&queue_lock);
-			cache_put(cr->item, detail);
-			kfree(cr->buf);
-			kfree(cr);
-			return;
+			list_move(&cr->q.list, &dequeued);
 		}
 	spin_unlock(&queue_lock);
+	while (!list_empty(&dequeued)) {
+		cr = list_entry(dequeued.next, struct cache_request, q.list);
+		list_del(&cr->q.list);
+		cache_put(cr->item, detail);
+		kfree(cr->buf);
+		kfree(cr);
+	}
 }
 
 /*
@@ -1166,6 +1165,7 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h)
 
 	char *buf;
 	struct cache_request *crq;
+	int ret = 0;
 
 	if (!detail->cache_request)
 		return -EINVAL;
@@ -1174,6 +1174,9 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h)
 		warn_no_listener(detail);
 		return -EINVAL;
 	}
+	if (test_bit(CACHE_CLEANED, &h->flags))
+		/* Too late to make an upcall */
+		return -EAGAIN;
 
 	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!buf)
@@ -1191,10 +1194,18 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h)
 	crq->len = 0;
 	crq->readers = 0;
 	spin_lock(&queue_lock);
-	list_add_tail(&crq->q.list, &detail->queue);
+	if (test_bit(CACHE_PENDING, &h->flags))
+		list_add_tail(&crq->q.list, &detail->queue);
+	else
+		/* Lost a race, no longer PENDING, so don't enqueue */
+		ret = -EAGAIN;
 	spin_unlock(&queue_lock);
 	wake_up(&queue_wait);
-	return 0;
+	if (ret == -EAGAIN) {
+		kfree(buf);
+		kfree(crq);
+	}
+	return ret;
 }
 EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall);
 
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index 06bdf5a..621ca7b 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -347,13 +347,13 @@ ip_map_cached_get(struct svc_xprt *xprt)
 		spin_lock(&xprt->xpt_lock);
 		ipm = xprt->xpt_auth_cache;
 		if (ipm != NULL) {
-			if (!cache_valid(&ipm->h)) {
+			sn = net_generic(xprt->xpt_net, sunrpc_net_id);
+			if (cache_is_expired(sn->ip_map_cache, &ipm->h)) {
 				/*
 				 * The entry has been invalidated since it was
 				 * remembered, e.g. by a second mount from the
 				 * same IP address.
 				 */
-				sn = net_generic(xprt->xpt_net, sunrpc_net_id);
 				xprt->xpt_auth_cache = NULL;
 				spin_unlock(&xprt->xpt_lock);
 				cache_put(&ipm->h, sn->ip_map_cache);
@@ -493,8 +493,6 @@ static int unix_gid_parse(struct cache_detail *cd,
 	if (rv)
 		return -EINVAL;
 	uid = make_kuid(&init_user_ns, id);
-	if (!uid_valid(uid))
-		return -EINVAL;
 	ug.uid = uid;
 
 	expiry = get_expiry(&mesg);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 0f679df..305374d 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -917,7 +917,10 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk)
 	len = svsk->sk_datalen;
 	npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	for (i = 0; i < npages; i++) {
-		BUG_ON(svsk->sk_pages[i] == NULL);
+		if (svsk->sk_pages[i] == NULL) {
+			WARN_ON_ONCE(1);
+			continue;
+		}
 		put_page(svsk->sk_pages[i]);
 		svsk->sk_pages[i] = NULL;
 	}
@@ -1092,8 +1095,10 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 		goto err_noclose;
 	}
 
-	if (svc_sock_reclen(svsk) < 8)
+	if (svsk->sk_datalen < 8) {
+		svsk->sk_datalen = 0;
 		goto err_delete; /* client is nuts. */
+	}
 
 	rqstp->rq_arg.len = svsk->sk_datalen;
 	rqstp->rq_arg.page_base = 0;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 412de7c..ddf0602 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2534,7 +2534,6 @@ static struct rpc_xprt_ops bc_tcp_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xprt_release_xprt,
 	.alloc_slot		= xprt_alloc_slot,
-	.rpcbind		= xs_local_rpcbind,
 	.buf_alloc		= bc_malloc,
 	.buf_free		= bc_free,
 	.send_request		= bc_send_request,