6.18.51-rc1 review

@@ -790,7 +790,7 @@ void __icmp_send(struct sk_buff *skb_in,
 
 	/* RFC says return as much as we can without exceeding 576 bytes. */
 
-	room = dst_mtu(&rt->dst);
+	room = dst4_mtu(&rt->dst);
 	if (room > 576)
 		room = 576;
 	room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;

@@ -1303,7 +1303,7 @@ static int ip_setup_cork(struct sock *sk
 		return -EFAULT;
 
 	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+			 dst4_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
 
 	if (!inetdev_valid_mtu(cork->fragsize))
 		return -ENETUNREACH;

@@ -1442,7 +1442,7 @@ struct sk_buff *__ip_make_skb(struct soc
 	pmtudisc = READ_ONCE(inet->pmtudisc);
 	if (pmtudisc == IP_PMTUDISC_DO ||
 	    pmtudisc == IP_PMTUDISC_PROBE ||
-	    (skb->len <= dst_mtu(&rt->dst) &&
+	    (skb->len <= dst4_mtu(&rt->dst) &&
 	     ip_dont_fragment(sk, &rt->dst)))
 		df = htons(IP_DF);
 

@@ -1634,7 +1634,7 @@ int do_ip_getsockopt(struct sock *sk, in
 		val = 0;
 		dst = sk_dst_get(sk);
 		if (dst) {
-			val = dst_mtu(dst);
+			val = dst4_mtu(dst);
 			dst_release(dst);
 		}
 		if (!val)

@@ -1895,7 +1895,7 @@ static int ipmr_prepare_xmit(struct net
 			return -1;
 	}
 
-	if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) {
+	if (skb->len+encap > dst4_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) {
 		/* Do not fragment multicasts. Alas, IPv4 does not
 		 * allow to send ICMP, so that packets will disappear
 		 * to blackhole.

@@ -303,7 +303,7 @@ void nf_send_reset(struct net *net, stru
 		goto free_nskb;
 
 	/* "Never happens" */
-	if (nskb->len > dst_mtu(skb_dst(nskb)))
+	if (nskb->len > dst4_mtu(skb_dst(nskb)))
 		goto free_nskb;
 
 	nf_ct_attach(nskb, oldskb);

@@ -373,7 +373,7 @@ void tcp_v4_mtu_reduced(struct sock *sk)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct dst_entry *dst;
-	u32 mtu;
+	u32 mtu, dmtu;
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
 		return;

@@ -385,15 +385,14 @@ void tcp_v4_mtu_reduced(struct sock *sk)
 	/* Something is about to be wrong... Remember soft error
 	 * for the case, if this connection will not able to recover.
 	 */
-	if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
+	dmtu = dst4_mtu(dst);
+	if (mtu < dmtu && ip_dont_fragment(sk, dst))
 		WRITE_ONCE(sk->sk_err_soft, EMSGSIZE);
 
-	mtu = dst_mtu(dst);
-
 	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
 	    ip_sk_accept_pmtu(sk) &&
-	    inet_csk(sk)->icsk_pmtu_cookie > mtu) {
-		tcp_sync_mss(sk, mtu);
+	    inet_csk(sk)->icsk_pmtu_cookie > dmtu) {
+		tcp_sync_mss(sk, dmtu);
 
 		/* Resend the TCP packet because it's
 		 * clear that the old packet has been

@@ -1817,7 +1816,7 @@ struct sock *tcp_v4_syn_recv_sock(const
 #endif
 	tcp_ca_openreq_child(newsk, dst);
 
-	tcp_sync_mss(newsk, dst_mtu(dst));
+	tcp_sync_mss(newsk, dst4_mtu(dst));
 	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);

@@ -963,7 +963,7 @@ static netdev_tx_t ipip6_tunnel_xmit(str
 	iph6 = ipv6_hdr(skb);
 
 	if (df) {
-		mtu = dst_mtu(&rt->dst) - t_hlen;
+		mtu = dst4_mtu(&rt->dst) - t_hlen;
 
 		if (mtu < IPV4_MIN_MTU) {
 			DEV_STATS_INC(dev, collisions);

@@ -1686,6 +1686,11 @@ static inline int tcp_full_space(const s
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
+static inline u32 tcp_dst_advmss(const struct dst_entry *dst)
+{
+	return max_t(u32, dst_metric_advmss(dst), TCP_MIN_MSS);
+}
+
 static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh)
 {
 	int unused_mem = sk_unused_reserved_mem(sk);

@@ -1817,7 +1817,7 @@ struct sock *tcp_v4_syn_recv_sock(const
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst4_mtu(dst));
-	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
 

@@ -445,7 +445,7 @@ void tcp_openreq_init_rwin(struct reques
 	u32 rcv_wnd;
 	int mss;
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 	window_clamp = READ_ONCE(tp->window_clamp);
 	/* Set this up on the first call only */
 	req->rsk_window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW);

@@ -129,7 +129,7 @@ static __u16 tcp_advertise_mss(struct so
 	int mss = tp->advmss;
 
 	if (dst) {
-		unsigned int metric = dst_metric_advmss(dst);
+		unsigned int metric = tcp_dst_advmss(dst);
 
 		if (metric < mss) {
 			mss = metric;

@@ -3906,7 +3906,7 @@ struct sk_buff *tcp_make_synack(const st
 	}
 	skb_dst_set(skb, dst);
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	memset(&opts, 0, sizeof(opts));
 	now = tcp_clock_ns();

@@ -4062,7 +4062,7 @@ static void tcp_connect_init(struct sock
 
 	if (!tp->window_clamp)
 		WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW));
-	tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	tp->advmss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(sk);
 

@@ -1501,7 +1501,7 @@ static struct sock *tcp_v6_syn_recv_sock
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst6_mtu(dst));
-	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
 

@@ -506,6 +506,31 @@ out:
 	return res;
 }
 
+/* Configured/administrative MTU of a route, for advertising the TCP MSS.
+ *
+ * Unlike ip_dst_mtu_maybe_forward(), this deliberately ignores the
+ * ICMP-learned path MTU (rt->rt_pmtu).  The advertised MSS bounds what the
+ * peer may send to us and must reflect our receive capability (the device or
+ * route-configured MTU), not a path MTU learned on the reverse (send)
+ * direction, which may not apply to the peer->us path and outlives the fnhe
+ * for the whole connection.  See RFC 2923 section 2.3 and the comment above
+ * tcp_advertise_mss().
+ */
+static inline unsigned int ip_dst_mtu_configured(const struct dst_entry *dst)
+{
+	unsigned int mtu, res;
+
+	rcu_read_lock();
+	mtu = dst_metric_raw(dst, RTAX_MTU);
+	if (!mtu)
+		mtu = READ_ONCE(dst_dev_rcu(dst)->mtu);
+	mtu = min_t(unsigned int, mtu, IP_MAX_MTU);
+	res = mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+	rcu_read_unlock();
+
+	return res;
+}
+
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 					  const struct sk_buff *skb)
 {

@@ -352,6 +352,43 @@ out:
 	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
+/* Configured/administrative MTU of a route, for advertising the TCP MSS.
+ *
+ * Unlike ip6_dst_mtu_maybe_forward(), this ignores any ICMPv6-learned path
+ * MTU (which is kept on the RTF_CACHE exception route) and returns the MTU of
+ * the underlying route (fib6_pmtu) or the egress device.  The advertised MSS
+ * bounds what the peer may send to us and must reflect our receive
+ * capability, not a path MTU learned on the reverse (send) direction.  See
+ * RFC 2923 section 2.3 and the comment above tcp_advertise_mss().
+ */
+static inline unsigned int ip6_dst_mtu_configured(const struct dst_entry *dst)
+{
+	const struct rt6_info *rt = dst_rt6_info(dst);
+	const struct fib6_info *from;
+	struct inet6_dev *idev;
+	unsigned int mtu = 0;
+
+	rcu_read_lock();
+	/* IPv6 keeps the learned PMTU and the configured MTU in the same
+	 * RTAX_MTU slot: the learned value sits on this (possibly RTF_CACHE)
+	 * dst, the configured one on the underlying route.  Reach the latter
+	 * via ->from (fib6_pmtu), populated by ip6_route_info_create().
+	 */
+	from = rcu_dereference(rt->from);
+	if (from)
+		mtu = from->fib6_pmtu;
+	if (!mtu) {
+		mtu = IPV6_MIN_MTU;
+		idev = __in6_dev_get(dst_dev_rcu(dst));
+		if (idev)
+			mtu = max_t(unsigned int, mtu, READ_ONCE(idev->cnf.mtu6));
+	}
+	rcu_read_unlock();
+
+	mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
+	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+}
+
 u32 ip6_mtu_from_fib6(const struct fib6_result *res,
 		      const struct in6_addr *daddr,
 		      const struct in6_addr *saddr);

@@ -1360,8 +1360,8 @@ static unsigned int ipv4_default_advmss(
 
 	rcu_read_lock();
 	net = dst_dev_net_rcu(dst);
-	advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
-				   net->ipv4.ip_rt_min_advmss);
+	advmss = max_t(unsigned int, ip_dst_mtu_configured(dst) - header_size,
+		       net->ipv4.ip_rt_min_advmss);
 	rcu_read_unlock();
 
 	return min(advmss, IPV4_MAX_PMTU - header_size);

@@ -3254,7 +3254,7 @@ EXPORT_SYMBOL_GPL(ip6_sk_redirect);
 
 static unsigned int ip6_default_advmss(const struct dst_entry *dst)
 {
-	unsigned int mtu = dst6_mtu(dst);
+	unsigned int mtu = ip6_dst_mtu_configured(dst);
 	struct net *net;
 
 	mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);

@@ -800,7 +800,23 @@ nfsd4_create(struct svc_rqst *rqstp, str
 	if (status)
 		return status;
 
+	/* Sanitize cr_type to avoid returning ATTRNOTSUPP. */
+	switch (create->cr_type) {
+	case NF4LNK:
+	case NF4BLK:
+	case NF4CHR:
+	case NF4SOCK:
+	case NF4FIFO:
+	case NF4DIR:
+		break;
+	default:
+		status = nfserr_badtype;
+		goto out_aftermask;
+	}
+
 	status = nfsd4_acl_to_attr(create->cr_type, create->cr_acl, &attrs);
+	if (status != nfs_ok)
+		goto out_aftermask;
 	current->fs->umask = create->cr_umask;
 	switch (create->cr_type) {
 	case NF4LNK:

@@ -867,6 +883,7 @@ out:
 	fh_put(&resfh);
 out_umask:
 	current->fs->umask = 0;
+out_aftermask:
 	nfsd_attrs_free(&attrs);
 	return status;
 }

@@ -1411,6 +1411,21 @@ static int create_proc_exports_entry(voi
 
 unsigned int nfsd_net_id;
 
+struct nfsd_genl_rqstp {
+	struct sockaddr		rq_daddr;
+	struct sockaddr		rq_saddr;
+	unsigned long		rq_flags;
+	ktime_t			rq_stime;
+	__be32			rq_xid;
+	u32			rq_vers;
+	u32			rq_prog;
+	u32			rq_proc;
+
+	/* NFSv4 compound */
+	u32			rq_opcnt;
+	u32			rq_opnum[16];
+};
+
 static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb,
 					    struct netlink_callback *cb,
 					    struct nfsd_genl_rqstp *genl_rqstp)

@@ -60,21 +60,6 @@ struct readdir_cd {
 /* Maximum number of operations per session compound */
 #define NFSD_MAX_OPS_PER_COMPOUND	200
 
-struct nfsd_genl_rqstp {
-	struct sockaddr		rq_daddr;
-	struct sockaddr		rq_saddr;
-	unsigned long		rq_flags;
-	ktime_t			rq_stime;
-	__be32			rq_xid;
-	u32			rq_vers;
-	u32			rq_prog;
-	u32			rq_proc;
-
-	/* NFSv4 compound */
-	u32			rq_opcnt;
-	u32			rq_opnum[16];
-};
-
 extern struct svc_program	nfsd_programs[];
 extern const struct svc_version	nfsd_version2, nfsd_version3, nfsd_version4;
 extern struct mutex		nfsd_mutex;

@@ -1412,8 +1412,8 @@ static int create_proc_exports_entry(voi
 unsigned int nfsd_net_id;
 
 struct nfsd_genl_rqstp {
-	struct sockaddr		rq_daddr;
-	struct sockaddr		rq_saddr;
+	struct sockaddr_storage	rq_daddr;
+	struct sockaddr_storage	rq_saddr;
 	unsigned long		rq_flags;
 	ktime_t			rq_stime;
 	__be32			rq_xid;

@@ -1448,7 +1448,7 @@ static int nfsd_genl_rpc_status_compose_
 			NFSD_A_RPC_STATUS_PAD))
 		goto out_cancel;
 
-	switch (genl_rqstp->rq_saddr.sa_family) {
+	switch (genl_rqstp->rq_saddr.ss_family) {
 	case AF_INET: {
 		const struct sockaddr_in *s_in, *d_in;
 

@@ -1539,7 +1539,7 @@ int nfsd_nl_rpc_status_get_dumpit(struct
 		list_for_each_entry_rcu(rqstp,
 				&nn->nfsd_serv->sv_pools[i].sp_all_threads,
 				rq_all) {
-			struct nfsd_genl_rqstp genl_rqstp;
+			struct nfsd_genl_rqstp genl_rqstp = {};
 			unsigned int status_counter;
 
 			if (rqstp_index++ < thread_skip) /* already consumed */

@@ -1563,9 +1563,9 @@ int nfsd_nl_rpc_status_get_dumpit(struct
 			genl_rqstp.rq_stime = rqstp->rq_stime;
 			genl_rqstp.rq_opcnt = 0;
 			memcpy(&genl_rqstp.rq_daddr, svc_daddr(rqstp),
-			       sizeof(struct sockaddr));
+			       sizeof(struct sockaddr_storage));
 			memcpy(&genl_rqstp.rq_saddr, svc_addr(rqstp),
-			       sizeof(struct sockaddr));
+			       sizeof(struct sockaddr_storage));
 
 #ifdef CONFIG_NFSD_V4
 			if (rqstp->rq_vers == NFS4_VERSION &&

@@ -69,6 +69,7 @@ struct nfsd_net {
 	bool grace_end_forced;
 	bool client_tracking_active;
 	time64_t boot_time;
+	time64_t boot_time_bt;	/* same instant in CLOCK_BOOTTIME */
 
 	struct dentry *nfsd_client_dir;
 

@@ -6769,7 +6769,7 @@ bool nfsd4_force_end_grace(struct nfsd_n
  */
 static bool clients_still_reclaiming(struct nfsd_net *nn)
 {
-	time64_t double_grace_period_end = nn->boot_time +
+	time64_t double_grace_period_end = nn->boot_time_bt +
 					   2 * nn->nfsd4_lease;
 
 	if (READ_ONCE(nn->grace_end_forced))

@@ -9120,6 +9120,7 @@ static int nfs4_state_create_net(struct
 	nn->conf_name_tree = RB_ROOT;
 	nn->unconf_name_tree = RB_ROOT;
 	nn->boot_time = ktime_get_real_seconds();
+	nn->boot_time_bt = ktime_get_boottime_seconds();
 	nn->grace_ended = false;
 	nn->grace_end_forced = false;
 	nn->client_tracking_active = false;

@@ -62,11 +62,6 @@ static DEFINE_PER_CPU(unsigned long, nfs
 static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions);
 
-struct nfsd_fcache_disposal {
-	spinlock_t lock;
-	struct list_head freeme;
-};
-
 static struct kmem_cache		*nfsd_file_slab;
 static struct kmem_cache		*nfsd_file_mark_slab;
 static struct list_lru			nfsd_file_lru;

@@ -422,25 +417,25 @@ nfsd_file_dispose_list(struct list_head
 }
 
 /**
- * nfsd_file_dispose_list_delayed - move list of dead files to net's freeme list
+ * nfsd_file_dispose_list_delayed - queue dead files for nfsd thread disposal
  * @dispose: list of nfsd_files to be disposed
  *
- * Transfers each file to the "freeme" list for its nfsd_net, to eventually
- * be disposed of by the per-net garbage collector.
+ * Transfers each file to the dispose list in its nfsd_net and wakes an nfsd
+ * thread to do the actual close.  This keeps the cost of fput() in the nfsd
+ * threads rather than in the shrinker or GC worker.
  */
 static void
 nfsd_file_dispose_list_delayed(struct list_head *dispose)
 {
-	while(!list_empty(dispose)) {
+	while (!list_empty(dispose)) {
 		struct nfsd_file *nf = list_first_entry(dispose,
 						struct nfsd_file, nf_gc);
 		struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id);
-		struct nfsd_fcache_disposal *l = nn->fcache_disposal;
 		struct svc_serv *serv;
 
-		spin_lock(&l->lock);
-		list_move_tail(&nf->nf_gc, &l->freeme);
-		spin_unlock(&l->lock);
+		spin_lock(&nn->fcache_dispose_lock);
+		list_move_tail(&nf->nf_gc, &nn->fcache_dispose_list);
+		spin_unlock(&nn->fcache_dispose_lock);
 
 		/*
 		 * The filecache laundrette is shut down after the

@@ -464,17 +459,15 @@ nfsd_file_dispose_list_delayed(struct li
  */
 void nfsd_file_net_dispose(struct nfsd_net *nn)
 {
-	struct nfsd_fcache_disposal *l = nn->fcache_disposal;
-
-	if (!list_empty(&l->freeme)) {
+	if (!list_empty(&nn->fcache_dispose_list)) {
 		LIST_HEAD(dispose);
 		int i;
 
-		spin_lock(&l->lock);
-		for (i = 0; i < 8 && !list_empty(&l->freeme); i++)
-			list_move(l->freeme.next, &dispose);
-		spin_unlock(&l->lock);
-		if (!list_empty(&l->freeme)) {
+		spin_lock(&nn->fcache_dispose_lock);
+		for (i = 0; i < 8 && !list_empty(&nn->fcache_dispose_list); i++)
+			list_move(nn->fcache_dispose_list.next, &dispose);
+		spin_unlock(&nn->fcache_dispose_lock);
+		if (!list_empty(&nn->fcache_dispose_list)) {
 			/*
 			 * Wake up another thread to share the work
 			 * *before* doing any actual disposing.

@@ -698,11 +691,11 @@ nfsd_file_queue_for_close(struct inode *
 }
 
 /**
- * nfsd_file_close_inode - attempt a delayed close of a nfsd_file
+ * nfsd_file_close_inode - attempt a deferred close of a nfsd_file
  * @inode: inode of the file to attempt to remove
  *
  * Close out any open nfsd_files that can be reaped for @inode. The
- * actual freeing is deferred to the dispose_list_delayed infrastructure.
+ * actual freeing is deferred to the nfsd service threads.
  *
  * This is used by the fsnotify callbacks and setlease notifier.
  */

@@ -906,42 +899,14 @@ __nfsd_file_cache_purge(struct net *net)
 	nfsd_file_dispose_list(&dispose);
 }
 
-static struct nfsd_fcache_disposal *
-nfsd_alloc_fcache_disposal(void)
-{
-	struct nfsd_fcache_disposal *l;
-
-	l = kmalloc(sizeof(*l), GFP_KERNEL);
-	if (!l)
-		return NULL;
-	spin_lock_init(&l->lock);
-	INIT_LIST_HEAD(&l->freeme);
-	return l;
-}
-
-static void
-nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l)
-{
-	nfsd_file_dispose_list(&l->freeme);
-	kfree(l);
-}
-
-static void
-nfsd_free_fcache_disposal_net(struct net *net)
-{
-	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-	struct nfsd_fcache_disposal *l = nn->fcache_disposal;
-
-	nfsd_free_fcache_disposal(l);
-}
-
 int
 nfsd_file_cache_start_net(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	nn->fcache_disposal = nfsd_alloc_fcache_disposal();
-	return nn->fcache_disposal ? 0 : -ENOMEM;
+	spin_lock_init(&nn->fcache_dispose_lock);
+	INIT_LIST_HEAD(&nn->fcache_dispose_list);
+	return 0;
 }
 
 /**

@@ -960,8 +925,10 @@ nfsd_file_cache_purge(struct net *net)
 void
 nfsd_file_cache_shutdown_net(struct net *net)
 {
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
 	nfsd_file_cache_purge(net);
-	nfsd_free_fcache_disposal_net(net);
+	nfsd_file_dispose_list(&nn->fcache_dispose_list);
 }
 
 void

@@ -201,7 +201,8 @@ struct nfsd_net {
 	/* utsname taken from the process that starts the server */
 	char			nfsd_name[UNX_MAXNODENAME+1];
 
-	struct nfsd_fcache_disposal *fcache_disposal;
+	spinlock_t		fcache_dispose_lock;
+	struct list_head	fcache_dispose_list;
 
 	siphash_key_t		siphash_key;
 

@@ -1445,18 +1445,30 @@ static void nfs4_put_copy(struct nfsd4_c
 {
 	if (!refcount_dec_and_test(&copy->refcount))
 		return;
+	/* Drop the task_struct pinned in nfsd4_copy(); NULL on sync copies. */
+	if (copy->copy_task)
+		put_task_struct(copy->copy_task);
 	kfree(copy->cp_src);
 	kfree(copy);
 }
 
+static void release_copy_files(struct nfsd4_copy *copy);
+
 static void nfsd4_stop_copy(struct nfsd4_copy *copy)
 {
 	trace_nfsd_copy_async_cancel(copy);
-	if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags)) {
-		kthread_stop(copy->copy_task);
-		copy->nfserr = nfs_ok;
-		set_bit(NFSD4_COPY_F_COMPLETED, &copy->cp_flags);
-	}
+	/*
+	 * Join the kthread before releasing its resources. The task_struct is
+	 * pinned in nfsd4_copy(), so kthread_stop() is safe even after the
+	 * one-shot kthread has exited. The caller already unlinked the copy,
+	 * so this runs once per copy.
+	 */
+	set_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags);
+	kthread_stop(copy->copy_task);
+	copy->nfserr = nfs_ok;
+	set_bit(NFSD4_COPY_F_COMPLETED, &copy->cp_flags);
+
+	release_copy_files(copy);
 	nfs4_put_copy(copy);
 }
 

@@ -1469,7 +1481,13 @@ static struct nfsd4_copy *nfsd4_unhash_c
 		copy = list_first_entry(&clp->async_copies, struct nfsd4_copy,
 					copies);
 		refcount_inc(&copy->refcount);
-		copy->cp_clp = NULL;
+		/*
+		 * Unlinking hides the copy from the reaper, so drop its
+		 * s2s_cp_stateids entry here while cp_clp is still valid.
+		 */
+		nfs4_free_copy_state(copy);
+		/* Pairs with smp_load_acquire() in nfsd4_send_cb_offload(). */
+		smp_store_release(&copy->cp_clp, NULL);
 		if (!list_empty(&copy->copies))
 			list_del_init(&copy->copies);
 	}

@@ -1481,8 +1499,11 @@ void nfsd4_shutdown_copy(struct nfs4_cli
 {
 	struct nfsd4_copy *copy;
 
-	while ((copy = nfsd4_unhash_copy(clp)) != NULL)
+	while ((copy = nfsd4_unhash_copy(clp)) != NULL) {
 		nfsd4_stop_copy(copy);
+		/* Reaper can't reach the unhashed copy; drop its membership ref. */
+		nfs4_put_copy(copy);
+	}
 }
 #ifdef CONFIG_NFSD_V4_2_INTER_SSC
 

@@ -1773,6 +1794,8 @@ static void nfsd4_cb_offload_release(str
 		container_of(cbo, struct nfsd4_copy, cp_cb_offload);
 
 	set_bit(NFSD4_COPY_F_OFFLOAD_DONE, &copy->cp_flags);
+	/* Drop the copy reference taken in nfsd4_send_cb_offload(). */
+	nfs4_put_copy(copy);
 }
 
 static int nfsd4_cb_offload_done(struct nfsd4_callback *cb,

@@ -1900,34 +1923,52 @@ static void release_copy_files(struct nf
 		nfsd_file_put(copy->nf_dst);
 }
 
+/*
+ * Called from the reaper and from nfsd4_copy()'s error path; in both
+ * cases the copy is already unreachable from clp->async_copies.
+ */
 static void cleanup_async_copy(struct nfsd4_copy *copy)
 {
 	nfs4_free_copy_state(copy);
 	release_copy_files(copy);
-	if (copy->cp_clp) {
-		spin_lock(&copy->cp_clp->async_lock);
-		if (!list_empty(&copy->copies))
-			list_del_init(&copy->copies);
-		spin_unlock(&copy->cp_clp->async_lock);
-	}
 	nfs4_put_copy(copy);
 }
 
 static void nfsd4_send_cb_offload(struct nfsd4_copy *copy)
 {
 	struct nfsd4_cb_offload *cbo = &copy->cp_cb_offload;
+	struct nfs4_client *clp;
+
+	/*
+	 * Pairs with smp_store_release(&cp_clp) in find_async_copy() and
+	 * nfsd4_unhash_copy(); the set_bit/clear_bit writers are unordered.
+	 * cp_clp is NULL once the copy was canceled; skip the callback, the
+	 * canceling path owns the notification.
+	 */
+	clp = smp_load_acquire(&copy->cp_clp);
+	if (!clp) {
+		set_bit(NFSD4_COPY_F_OFFLOAD_DONE, &copy->cp_flags);
+		return;
+	}
 
 	memcpy(&cbo->co_res, &copy->cp_res, sizeof(copy->cp_res));
 	memcpy(&cbo->co_fh, &copy->fh, sizeof(copy->fh));
 	cbo->co_nfserr = copy->nfserr;
 	cbo->co_retries = 5;
 
-	nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops,
+	/*
+	 * Hold the copy across the in-flight callback; co_cb is embedded in
+	 * the copy, so it must outlive the callback. The reference is dropped
+	 * in nfsd4_cb_offload_release().
+	 */
+	refcount_inc(&copy->refcount);
+
+	nfsd4_init_cb(&cbo->co_cb, clp, &nfsd4_cb_offload_ops,
 		      NFSPROC4_CLNT_CB_OFFLOAD);
 	nfsd41_cb_referring_call(&cbo->co_cb, &cbo->co_referring_sessionid,
 				 cbo->co_referring_slotid,
 				 cbo->co_referring_seqno);
-	trace_nfsd_cb_offload(copy->cp_clp, &cbo->co_res.cb_stateid,
+	trace_nfsd_cb_offload(clp, &cbo->co_res.cb_stateid,
 			      &cbo->co_fh, copy->cp_count, copy->nfserr);
 	nfsd4_try_run_cb(&cbo->co_cb);
 }

@@ -1969,16 +2010,20 @@ static int nfsd4_do_async_copy(void *dat
 	}
 
 do_callback:
-	/* The kthread exits forthwith. Ensure that a subsequent
-	 * OFFLOAD_CANCEL won't try to kill it again. */
-	set_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags);
-
+	/*
+	 * Don't set NFSD4_COPY_F_STOPPED here: it tells a teardown caller it
+	 * may skip kthread_stop(), which would then release nf_dst and the
+	 * client while still in use. Only nfsd4_stop_copy() sets it, after
+	 * joining.
+	 */
 	set_bit(NFSD4_COPY_F_COMPLETED, &copy->cp_flags);
 	trace_nfsd_copy_async_done(copy);
 	atomic_dec(&copy->cp_nn->pending_async_copies);
 	if (copy->cp_res.wr_bytes_written > 0 && copy->attr_update)
 		nfsd_update_cmtime_attr(copy->nf_dst->nf_file, 0);
 	nfsd4_send_cb_offload(copy);
+	/* Drop the kthread's reference (taken in nfsd4_copy()); copy may be freed after this. */
+	nfs4_put_copy(copy);
 	return 0;
 }
 

@@ -2017,6 +2062,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struc
 	memcpy(&copy->fh, &cstate->current_fh.fh_handle,
 		sizeof(struct knfsd_fh));
 	if (nfsd4_copy_is_async(copy)) {
+		struct task_struct *task;
+
 		async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
 		if (!async_copy)
 			goto out_err;

@@ -2045,15 +2092,27 @@ nfsd4_copy(struct svc_rqst *rqstp, struc
 		       NFS4_MAX_SESSIONID_LEN);
 		async_copy->cp_cb_offload.co_referring_slotid = cstate->slot->sl_index;
 		async_copy->cp_cb_offload.co_referring_seqno = cstate->slot->sl_seqid;
-		async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
-				async_copy, "%s", "copy thread");
-		if (IS_ERR(async_copy->copy_task))
+		task = kthread_create(nfsd4_do_async_copy, async_copy,
+				      "%s", "copy thread");
+		if (IS_ERR(task))
 			goto out_dec_async_copy_err;
+		/*
+		 * Pin the task_struct so kthread_stop() is safe after this
+		 * one-shot kthread exits. Released by nfs4_put_copy().
+		 */
+		get_task_struct(task);
+		async_copy->copy_task = task;
+		/*
+		 * Take the kthread's ref and wake it before publishing, so the
+		 * publisher touches async_copy no further and teardown can
+		 * drain it.
+		 */
+		refcount_inc(&async_copy->refcount);
+		wake_up_process(async_copy->copy_task);
 		spin_lock(&async_copy->cp_clp->async_lock);
 		list_add(&async_copy->copies,
 				&async_copy->cp_clp->async_copies);
 		spin_unlock(&async_copy->cp_clp->async_lock);
-		wake_up_process(async_copy->copy_task);
 		status = nfs_ok;
 	} else {
 		status = nfsd4_do_copy(copy, copy->nf_src->nf_file,

@@ -2107,8 +2166,18 @@ find_async_copy(struct nfs4_client *clp,
 
 	spin_lock(&clp->async_lock);
 	copy = find_async_copy_locked(clp, stateid);
-	if (copy)
+	if (copy) {
 		refcount_inc(&copy->refcount);
+		nfs4_free_copy_state(copy);
+		/*
+		 * Mirror nfsd4_unhash_copy(): unlink and clear cp_clp under
+		 * async_lock so the reaper can't reach it. Caller drops the
+		 * membership ref after nfsd4_stop_copy().
+		 */
+		smp_store_release(&copy->cp_clp, NULL);
+		if (!list_empty(&copy->copies))
+			list_del_init(&copy->copies);
+	}
 	spin_unlock(&clp->async_lock);
 	return copy;
 }

@@ -2127,8 +2196,11 @@ nfsd4_offload_cancel(struct svc_rqst *rq
 		struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 		return manage_cpntf_state(nn, &os->stateid, clp, NULL);
-	} else
+	} else {
 		nfsd4_stop_copy(copy);
+		/* find_async_copy() unlinked it from the reaper; drop the membership ref. */
+		nfs4_put_copy(copy);
+	}
 
 	return nfs_ok;
 }

@@ -55,6 +55,17 @@
 /* We only care about NFSD_MAY_READ/WRITE for this cache */
 #define NFSD_FILE_MAY_MASK	(NFSD_MAY_READ|NFSD_MAY_WRITE|NFSD_MAY_LOCALIO)
 
+/* If the shrinker runs between calls to list_lru_walk_node() in
+ * nfsd_file_gc(), the "remaining" count will be wrong.  This could
+ * result in premature freeing of some files.  This may not matter much
+ * but is easy to fix with this spinlock which temporarily disables
+ * the shrinker.
+ *
+ * It also serializes callers of nfsd_file_dispose_list_delayed()
+ * against per-net shutdown.
+ */
+static DEFINE_SPINLOCK(nfsd_gc_lock);
+
 static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_allocations);

@@ -423,10 +434,16 @@ nfsd_file_dispose_list(struct list_head
  * Transfers each file to the dispose list in its nfsd_net and wakes an nfsd
  * thread to do the actual close.  This keeps the cost of fput() in the nfsd
  * threads rather than in the shrinker or GC worker.
+ *
+ * All callers must hold nfsd_gc_lock, so that nfsd_file_cache_shutdown_net()
+ * can synchronize against them before draining the per-net dispose list.
+ * This guarantees nf_net is still live when we call net_generic().
  */
 static void
 nfsd_file_dispose_list_delayed(struct list_head *dispose)
 {
+	lockdep_assert_held(&nfsd_gc_lock);
+
 	while (!list_empty(dispose)) {
 		struct nfsd_file *nf = list_first_entry(dispose,
 						struct nfsd_file, nf_gc);

@@ -557,13 +574,6 @@ nfsd_file_gc_cb(struct list_head *item,
 	return nfsd_file_lru_cb(item, lru, arg);
 }
 
-/* If the shrinker runs between calls to list_lru_walk_node() in
- * nfsd_file_gc(), the "remaining" count will be wrong.  This could
- * result in premature freeing of some files.  This may not matter much
- * but is easy to fix with this spinlock which temporarily disables
- * the shrinker.
- */
-static DEFINE_SPINLOCK(nfsd_gc_lock);
 static void
 nfsd_file_gc(void)
 {

@@ -586,9 +596,9 @@ nfsd_file_gc(void)
 				remaining = 0;
 		}
 	}
+	nfsd_file_dispose_list_delayed(&dispose);
 	spin_unlock(&nfsd_gc_lock);
 	trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru));
-	nfsd_file_dispose_list_delayed(&dispose);
 }
 
 static void

@@ -616,9 +626,9 @@ nfsd_file_lru_scan(struct shrinker *s, s
 
 	ret = list_lru_shrink_walk(&nfsd_file_lru, sc,
 				   nfsd_file_lru_cb, &dispose);
+	nfsd_file_dispose_list_delayed(&dispose);
 	spin_unlock(&nfsd_gc_lock);
 	trace_nfsd_file_shrinker_removed(ret, list_lru_count(&nfsd_file_lru));
-	nfsd_file_dispose_list_delayed(&dispose);
 	return ret;
 }
 

@@ -704,8 +714,10 @@ nfsd_file_close_inode(struct inode *inod
 {
 	LIST_HEAD(dispose);
 
+	spin_lock(&nfsd_gc_lock);
 	nfsd_file_queue_for_close(inode, &dispose);
 	nfsd_file_dispose_list_delayed(&dispose);
+	spin_unlock(&nfsd_gc_lock);
 }
 
 /**

@@ -928,6 +940,14 @@ nfsd_file_cache_shutdown_net(struct net
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	nfsd_file_cache_purge(net);
+	/*
+	 * Ensure any in-progress shrinker, GC, or fsnotify/lease callback
+	 * (all of which hold nfsd_gc_lock while calling
+	 * nfsd_file_dispose_list_delayed()) has fully completed before
+	 * draining the per-net dispose list.
+	 */
+	spin_lock(&nfsd_gc_lock);
+	spin_unlock(&nfsd_gc_lock);
 	nfsd_file_dispose_list(&nn->fcache_dispose_list);
 }
 

@@ -101,6 +101,9 @@ struct nfsd_net {
 	 */
 	struct list_head client_lru;
 	struct list_head close_lru;
+
+	/* protects del_recall_lru and delegation hash/unhash */
+	spinlock_t deleg_lock ____cacheline_aligned;
 	struct list_head del_recall_lru;
 
 	/* protected by blocked_locks_lock */

176 lines not on this page · raw message

@@ -123,7 +123,7 @@ struct nfs4_stid {
 #define SC_TYPE_LAYOUT		BIT(3)
 	unsigned short		sc_type;
 
-/* state_lock protects sc_status for delegation stateids.
+/* nn->deleg_lock protects sc_status for delegation stateids.
  * ->cl_lock protects sc_status for open and lock stateids.
  * ->st_mutex also protect sc_status for open stateids.
  * ->ls_lock protects sc_status for layout stateids.

@@ -102,7 +102,8 @@ struct nfsd_net {
 	struct list_head client_lru;
 	struct list_head close_lru;
 
-	/* protects del_recall_lru and delegation hash/unhash */
+	/* protects del_recall_lru and delegation hash/unhash;
+	 * nests outside client_lock */
 	spinlock_t deleg_lock ____cacheline_aligned;
 	struct list_head del_recall_lru;
 

@@ -111,7 +112,8 @@ struct nfsd_net {
 
 	struct delayed_work laundromat_work;
 
-	/* client_lock protects the client lru list and session hash table */
+	/* client_lock protects the client lru list and session hash
+	 * table; nests inside deleg_lock */
 	spinlock_t client_lock;
 
 	/* protects blocked_locks_lru */

@@ -7052,6 +7052,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 		.new_timeo = nn->nfsd4_lease
 	};
 	struct nfs4_cpntf_state *cps;
+	struct nfs4_client *clp;
 	copy_stateid_t *cps_t;
 	int i;
 

@@ -7080,6 +7081,18 @@ nfs4_laundromat(struct nfsd_net *nn)
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
 		if (!state_expired(&lt, dp->dl_time))
 			break;
+		clp = dp->dl_stid.sc_client;
+		spin_lock(&nn->client_lock);
+		if (is_client_expired(clp)) {
+			spin_unlock(&nn->client_lock);
+			continue;
+		}
+		/*
+		 * Pin without reviving: get_client_locked() would
+		 * flip a courtesy client back to NFSD4_ACTIVE.
+		 */
+		atomic_inc(&clp->cl_rpc_users);
+		spin_unlock(&nn->client_lock);
 		refcount_inc(&dp->dl_stid.sc_count);
 		unhash_delegation_locked(dp, SC_STATUS_REVOKED);
 		list_add(&dp->dl_recall_lru, &reaplist);

@@ -7088,8 +7101,18 @@ nfs4_laundromat(struct nfsd_net *nn)
 	while (!list_empty(&reaplist)) {
 		dp = list_first_entry(&reaplist, struct nfs4_delegation,
 					dl_recall_lru);
+		clp = dp->dl_stid.sc_client;
 		list_del_init(&dp->dl_recall_lru);
 		revoke_delegation(dp);
+		/*
+		 * Unpin without renewing: put_client_renew() would
+		 * renew the reaped client's lease.
+		 */
+		if (atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock)) {
+			if (is_client_expired(clp))
+				wake_up_all(&expiry_wq);
+			spin_unlock(&nn->client_lock);
+		}
 	}
 
 	spin_lock(&nn->client_lock);

@@ -1841,13 +1841,23 @@ void nfsd4_revoke_states(struct nfsd_net
 		struct nfs4_client *clp;
 	retry:
 		list_for_each_entry(clp, head, cl_idhash) {
-			struct nfs4_stid *stid = find_one_sb_stid(clp, sb,
-								  sc_types);
+			struct nfs4_stid *stid;
+
+			/*
+			 * force_expire_client() ignores cl_rpc_users once
+			 * its wait_event() has passed, so pinning cannot
+			 * keep an already-expiring client alive; the
+			 * expiry path revokes its states instead.
+			 */
+			if (is_client_expired(clp))
+				continue;
+			stid = find_one_sb_stid(clp, sb, sc_types);
 			if (stid) {
 				struct nfs4_ol_stateid *stp;
 				struct nfs4_delegation *dp;
 				struct nfs4_layout_stateid *ls;
 
+				atomic_inc(&clp->cl_rpc_users);
 				spin_unlock(&nn->client_lock);
 				switch (stid->sc_type) {
 				case SC_TYPE_OPEN:

@@ -1931,6 +1941,9 @@ void nfsd4_revoke_states(struct nfsd_net
 					 */
 					nn->nfs40_last_revoke =
 						ktime_get_boottime_seconds();
+				if (atomic_dec_and_test(&clp->cl_rpc_users) &&
+				    is_client_expired(clp))
+					wake_up_all(&expiry_wq);
 				goto retry;
 			}
 		}

@@ -3217,6 +3230,11 @@ static void force_expire_client(struct n
 
 	trace_nfsd_clid_admin_expired(&clp->cl_clientid);
 
+	/*
+	 * cl_time is cleared under client_lock before the wait so a
+	 * revocation walk pinning cl_rpc_users under it either skips
+	 * this client or is seen by this wait_event().
+	 */
 	spin_lock(&nn->client_lock);
 	clp->cl_time = 0;
 	spin_unlock(&nn->client_lock);

@@ -3307,6 +3307,7 @@ cifs_setattr_nounix(struct dentry *diren
 	kgid_t gid = INVALID_GID;
 	struct inode *inode = d_inode(direntry);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	unsigned int sbflags = cifs_sb->mnt_cifs_flags;
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
 	struct cifsFileInfo *cfile = NULL;
 	const char *full_path;

@@ -3321,7 +3322,7 @@ cifs_setattr_nounix(struct dentry *diren
 	cifs_dbg(FYI, "setattr on file %pd attrs->ia_valid 0x%x\n",
 		 direntry, attrs->ia_valid);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
+	if (sbflags & CIFS_MOUNT_NO_PERM)
 		attrs->ia_valid |= ATTR_FORCE;
 
 	rc = setattr_prepare(&nop_mnt_idmap, direntry, attrs);

@@ -38,12 +38,12 @@ struct cifs_fscache_inode_coherency_data
 /*
  * fscache.c
  */
-extern int cifs_fscache_get_super_cookie(struct cifs_tcon *);
-extern void cifs_fscache_release_super_cookie(struct cifs_tcon *);
+int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon);
+void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon);
 
-extern void cifs_fscache_get_inode_cookie(struct inode *inode);
-extern void cifs_fscache_release_inode_cookie(struct inode *);
-extern void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update);
+void cifs_fscache_get_inode_cookie(struct inode *inode);
+void cifs_fscache_release_inode_cookie(struct inode *inode);
+void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update);
 
 static inline
 void cifs_fscache_fill_coherency(struct inode *inode,

@@ -359,18 +359,20 @@ static inline enum cifs_symlink_type cif
 	return CIFS_SYMLINK_TYPE_NONE;
 }
 
-extern int smb3_init_fs_context(struct fs_context *fc);
-extern void smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx);
-extern void smb3_cleanup_fs_context(struct smb3_fs_context *ctx);
+int smb3_init_fs_context(struct fs_context *fc);
+void smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx);
+void smb3_cleanup_fs_context(struct smb3_fs_context *ctx);
 
 static inline struct smb3_fs_context *smb3_fc2context(const struct fs_context *fc)
 {
 	return fc->fs_private;
 }
 
-extern int smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx);
-extern int smb3_sync_session_ctx_passwords(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses);
-extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
+int smb3_fs_context_dup(struct smb3_fs_context *new_ctx,
+			struct smb3_fs_context *ctx);
+int smb3_sync_session_ctx_passwords(struct cifs_sb_info *cifs_sb,
+				    struct cifs_ses *ses);
+void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
 
 /*
  * max deferred close timeout (jiffies) - 2^30

@@ -378,7 +380,7 @@ extern void smb3_update_mnt_flags(struct
 #define SMB3_MAX_DCLOSETIMEO (1 << 30)
 #define SMB3_DEF_DCLOSETIMEO (1 * HZ) /* even 1 sec enough to help eg open/write/close/open/read */
 #define MAX_CACHED_FIDS 16
-extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp);
+char *cifs_sanitize_prepath(char *prepath, gfp_t gfp);
 
 extern struct mutex cifs_mount_mutex;
 

@@ -3202,7 +3202,7 @@ cifs_setattr_unix(struct dentry *direntr
 	if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
 		attrs->ia_valid &= ~ATTR_MODE;
 
-	args = kmalloc(sizeof(*args), GFP_KERNEL);
+	args = kmalloc_obj(*args);
 	if (args == NULL) {
 		rc = -ENOMEM;
 		goto out;

@@ -3395,9 +3395,9 @@ cifs_setattr_nounix(struct dentry *diren
 				goto cifs_setattr_exit;
 			}
 		}
-	} else
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID))
+	} else if (!(sbflags & CIFS_MOUNT_SET_UID)) {
 		attrs->ia_valid &= ~(ATTR_UID | ATTR_GID);
+	}
 
 	/* skip mode change if it's just for clearing setuid/setgid */
 	if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))

@@ -3198,9 +3198,13 @@ cifs_setattr_unix(struct dentry *direntr
 		attrs->ia_valid &= ~(ATTR_CTIME | ATTR_MTIME);
 	}
 
-	/* skip mode change if it's just for clearing setuid/setgid */
-	if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
-		attrs->ia_valid &= ~ATTR_MODE;
+	/*
+	 * This function is only called when Unix extensions are in effect,
+	 * so the mode is always sent to and stored on the server.  Do not
+	 * skip the mode change when clearing setuid/setgid bits: dropping
+	 * ATTR_MODE here would leave those bits set on the server after a
+	 * write, which is a security issue.
+	 */
 
 	args = kmalloc_obj(*args);
 	if (args == NULL) {

@@ -3399,8 +3403,23 @@ cifs_setattr_nounix(struct dentry *diren
 		attrs->ia_valid &= ~(ATTR_UID | ATTR_GID);
 	}
 
-	/* skip mode change if it's just for clearing setuid/setgid */
-	if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
+	/*
+	 * Skip the mode change if it is only being done to clear the
+	 * setuid/setgid bits *and* the mode is emulated via the DOS
+	 * read-only attribute (the default, non-ACL case), which cannot
+	 * represent the setuid/setgid bits anyway.
+	 *
+	 * When the mode is instead stored on the server - i.e. with the
+	 * cifsacl or modefromsid mount options (via an ACL) or with the
+	 * SMB3.1.1 POSIX extensions - the cleared mode must be pushed to
+	 * the server.  Dropping ATTR_MODE here would leave the setuid/
+	 * setgid bit set on the server after a write, which is a security
+	 * issue (the bits are not stripped as they are on local
+	 * filesystems).
+	 */
+	if ((attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) &&
+	    !((sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) ||
+	      cifs_sb_master_tcon(cifs_sb)->posix_extensions))
 		attrs->ia_valid &= ~ATTR_MODE;
 
 	if (attrs->ia_valid & ATTR_MODE) {

@@ -82,7 +82,6 @@ extern char *cifs_build_path_to_root(str
 				     struct cifs_sb_info *cifs_sb,
 				     struct cifs_tcon *tcon,
 				     int add_treename);
-extern char *build_wildcard_path_from_dentry(struct dentry *direntry);
 char *cifs_build_devname(char *nodename, const char *prepath);
 extern void delete_mid(struct mid_q_entry *mid);
 void __release_mid(struct kref *refcount);

@@ -166,8 +165,6 @@ extern bool is_valid_oplock_break(char *
 extern bool backup_cred(struct cifs_sb_info *);
 extern bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 eof,
 				   bool from_readdir);
-extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
-			    unsigned int bytes_written);
 void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result);
 extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, int);
 extern int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,

@@ -194,8 +191,6 @@ extern void header_assemble(struct smb_h
 extern int small_smb_init_no_tc(const int smb_cmd, const int wct,
 				struct cifs_ses *ses,
 				void **request_buf);
-extern enum securityEnum select_sectype(struct TCP_Server_Info *server,
-				enum securityEnum requested);
 extern int CIFS_SessSetup(const unsigned int xid, struct cifs_ses *ses,
 			  struct TCP_Server_Info *server,
 			  const struct nls_table *nls_cp);

@@ -651,7 +646,6 @@ void cifs_free_hash(struct shash_desc **
 
 int cifs_try_adding_channels(struct cifs_ses *ses);
 bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface);
-void cifs_ses_mark_for_reconnect(struct cifs_ses *ses);
 
 int
 cifs_ses_get_chan_index(struct cifs_ses *ses,

@@ -39,15 +39,11 @@ extern struct mid_q_entry *smb2_setup_as
 			struct TCP_Server_Info *server, struct smb_rqst *rqst);
 extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server,
 						__u64 ses_id, __u32  tid);
-extern void smb2_echo_request(struct work_struct *work);
 extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode);
 extern bool smb2_is_valid_oplock_break(char *buffer,
 				       struct TCP_Server_Info *srv);
 extern int smb3_handle_read_data(struct TCP_Server_Info *server,
 				 struct mid_q_entry *mid);
-extern int smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon,
-				struct cifs_sb_info *cifs_sb, const char *path,
-				__u32 *reparse_tag);
 struct inode *smb2_create_reparse_inode(struct cifs_open_info_data *data,
 				     struct super_block *sb,
 				     const unsigned int xid,

@@ -300,17 +296,9 @@ extern int smb2_query_info_compound(cons
 				    struct kvec *rsp, int *buftype,
 				    struct cifs_sb_info *cifs_sb);
 /* query path info from the server using SMB311 POSIX extensions*/
-int smb311_posix_query_path_info(const unsigned int xid,
-				 struct cifs_tcon *tcon,
-				 struct cifs_sb_info *cifs_sb,
-				 const char *full_path,
-				 struct cifs_open_info_data *data);
 int posix_info_parse(const void *beg, const void *end,
 		     struct smb2_posix_info_parsed *out);
 int posix_info_sid_size(const void *beg, const void *end);
-int smb2_make_nfs_node(unsigned int xid, struct inode *inode,
-		       struct dentry *dentry, struct cifs_tcon *tcon,
-		       const char *full_path, umode_t mode, dev_t dev);
 int smb2_rename_pending_delete(const char *full_path,
 			       struct dentry *dentry,
 			       const unsigned int xid);

@@ -2110,8 +2110,6 @@ extern mempool_t cifs_io_subrequest_pool
 
 /* Operations for different SMB versions */
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
-extern struct smb_version_operations smb1_operations;
-extern struct smb_version_values smb1_values;
 extern struct smb_version_operations smb20_operations;
 extern struct smb_version_values smb20_values;
 #endif /* CIFS_ALLOW_INSECURE_LEGACY */

@@ -14,6 +14,7 @@
 #ifdef CONFIG_CIFS_DFS_UPCALL
 #include "dfs_cache.h"
 #endif
+#include "smb1proto.h"
 
 struct statfs;
 struct smb_rqst;

@@ -430,16 +431,6 @@ extern int CIFSSMBSetFileSize(const unsi
 			      struct cifsFileInfo *cfile, __u64 size,
 			      bool set_allocation);
 
-struct cifs_unix_set_info_args {
-	__u64	ctime;
-	__u64	atime;
-	__u64	mtime;
-	__u64	mode;
-	kuid_t	uid;
-	kgid_t	gid;
-	dev_t	device;
-};
-
 extern int CIFSSMBUnixSetFileInfo(const unsigned int xid,
 				  struct cifs_tcon *tcon,
 				  const struct cifs_unix_set_info_args *args,

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+/*
+ *
+ *   Copyright (c) International Business Machines  Corp., 2002,2008
+ *   Author(s): Steve French ([email protected])
+ *
+ */
+#ifndef _SMB1PROTO_H
+#define _SMB1PROTO_H
+
+struct cifs_unix_set_info_args {
+	__u64	ctime;
+	__u64	atime;
+	__u64	mtime;
+	__u64	mode;
+	kuid_t	uid;
+	kgid_t	gid;
+	dev_t	device;
+};
+
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
+
+/*
+ * cifssmb.c
+ */
+
+/*
+ * smb1ops.c
+ */
+extern struct smb_version_operations smb1_operations;
+extern struct smb_version_values smb1_values;
+
+/*
+ * smb1transport.c
+ */
+
+#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
+#endif /* _SMB1PROTO_H */

@@ -238,146 +238,6 @@ cifs_get_next_mid(struct TCP_Server_Info
 	return mid;
 }
 
-/*
-	return codes:
-		0	not a transact2, or all data present
-		>0	transact2 with that much data missing
-		-EINVAL	invalid transact2
- */
-static int
-check2ndT2(char *buf)
-{
-	struct smb_hdr *pSMB = (struct smb_hdr *)buf;
-	struct smb_t2_rsp *pSMBt;
-	int remaining;
-	__u16 total_data_size, data_in_this_rsp;
-
-	if (pSMB->Command != SMB_COM_TRANSACTION2)
-		return 0;
-
-	/* check for plausible wct, bcc and t2 data and parm sizes */
-	/* check for parm and data offset going beyond end of smb */
-	if (pSMB->WordCount != 10) { /* coalesce_t2 depends on this */
-		cifs_dbg(FYI, "Invalid transact2 word count\n");
-		return -EINVAL;
-	}
-
-	pSMBt = (struct smb_t2_rsp *)pSMB;
-
-	total_data_size = get_unaligned_le16(&pSMBt->t2_rsp.TotalDataCount);
-	data_in_this_rsp = get_unaligned_le16(&pSMBt->t2_rsp.DataCount);
-
-	if (total_data_size == data_in_this_rsp)
-		return 0;
-	else if (total_data_size < data_in_this_rsp) {
-		cifs_dbg(FYI, "total data %d smaller than data in frame %d\n",
-			 total_data_size, data_in_this_rsp);
-		return -EINVAL;
-	}
-
-	remaining = total_data_size - data_in_this_rsp;
-
-	cifs_dbg(FYI, "missing %d bytes from transact2, check next response\n",
-		 remaining);
-	if (total_data_size > CIFSMaxBufSize) {
-		cifs_dbg(VFS, "TotalDataSize %d is over maximum buffer %d\n",
-			 total_data_size, CIFSMaxBufSize);
-		return -EINVAL;
-	}
-	return remaining;
-}
-
-static int
-coalesce_t2(char *second_buf, struct smb_hdr *target_hdr)
-{
-	struct smb_t2_rsp *pSMBs = (struct smb_t2_rsp *)second_buf;
-	struct smb_t2_rsp *pSMBt  = (struct smb_t2_rsp *)target_hdr;
-	char *data_area_of_tgt;
-	char *data_area_of_src;
-	int remaining;
-	unsigned int byte_count, total_in_tgt;
-	__u16 tgt_total_cnt, src_total_cnt, total_in_src;
-
-	src_total_cnt = get_unaligned_le16(&pSMBs->t2_rsp.TotalDataCount);
-	tgt_total_cnt = get_unaligned_le16(&pSMBt->t2_rsp.TotalDataCount);
-
-	if (tgt_total_cnt != src_total_cnt)
-		cifs_dbg(FYI, "total data count of primary and secondary t2 differ source=%hu target=%hu\n",
-			 src_total_cnt, tgt_total_cnt);
-
-	total_in_tgt = get_unaligned_le16(&pSMBt->t2_rsp.DataCount);
-
-	remaining = tgt_total_cnt - total_in_tgt;
-
-	if (remaining < 0) {
-		cifs_dbg(FYI, "Server sent too much data. tgt_total_cnt=%hu total_in_tgt=%u\n",
-			 tgt_total_cnt, total_in_tgt);
-		return -EPROTO;
-	}
-
-	if (remaining == 0) {
-		/* nothing to do, ignore */
-		cifs_dbg(FYI, "no more data remains\n");
-		return 0;
-	}
-
-	total_in_src = get_unaligned_le16(&pSMBs->t2_rsp.DataCount);
-	if (remaining < total_in_src)
-		cifs_dbg(FYI, "transact2 2nd response contains too much data\n");
-
-	/* find end of first SMB data area */
-	data_area_of_tgt = (char *)&pSMBt->hdr.Protocol +
-				get_unaligned_le16(&pSMBt->t2_rsp.DataOffset);
-
-	/* validate target area */
-	data_area_of_src = (char *)&pSMBs->hdr.Protocol +
-				get_unaligned_le16(&pSMBs->t2_rsp.DataOffset);
-
-	data_area_of_tgt += total_in_tgt;
-
-	total_in_tgt += total_in_src;
-	/* is the result too big for the field? */
-	if (total_in_tgt > USHRT_MAX) {
-		cifs_dbg(FYI, "coalesced DataCount too large (%u)\n",
-			 total_in_tgt);
-		return -EPROTO;
-	}
-	put_unaligned_le16(total_in_tgt, &pSMBt->t2_rsp.DataCount);
-
-	/* fix up the BCC */
-	byte_count = get_bcc(target_hdr);
-	byte_count += total_in_src;
-	/* is the result too big for the field? */
-	if (byte_count > USHRT_MAX) {
-		cifs_dbg(FYI, "coalesced BCC too large (%u)\n", byte_count);
-		return -EPROTO;
-	}
-	put_bcc(byte_count, target_hdr);
-
-	byte_count = be32_to_cpu(target_hdr->smb_buf_length);
-	byte_count += total_in_src;
-	/* don't allow buffer to overflow */
-	if (byte_count > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
-		cifs_dbg(FYI, "coalesced BCC exceeds buffer size (%u)\n",
-			 byte_count);
-		return -ENOBUFS;
-	}
-	target_hdr->smb_buf_length = cpu_to_be32(byte_count);
-
-	/* copy second buffer into end of first buffer */
-	memcpy(data_area_of_tgt, data_area_of_src, total_in_src);
-
-	if (remaining != total_in_src) {
-		/* more responses to go */
-		cifs_dbg(FYI, "waiting for more secondary responses\n");
-		return 1;
-	}
-
-	/* we are done */
-	cifs_dbg(FYI, "found the last secondary response\n");
-	return 0;
-}
-
 static void
 cifs_downgrade_oplock(struct TCP_Server_Info *server,
 		      struct cifsInodeInfo *cinode, __u32 oplock,

@@ -387,37 +247,6 @@ cifs_downgrade_oplock(struct TCP_Server_
 }
 
 static bool
-cifs_check_trans2(struct mid_q_entry *mid, struct TCP_Server_Info *server,
-		  char *buf, int malformed)
-{
-	if (malformed)
-		return false;
-	if (check2ndT2(buf) <= 0)
-		return false;
-	mid->multiRsp = true;
-	if (mid->resp_buf) {
-		/* merge response - fix up 1st*/
-		malformed = coalesce_t2(buf, mid->resp_buf);
-		if (malformed > 0)
-			return true;
-		/* All parts received or packet is malformed. */
-		mid->multiEnd = true;
-		dequeue_mid(mid, malformed);
-		return true;
-	}
-	if (!server->large_buf) {
-		/*FIXME: switch to already allocated largebuf?*/
-		cifs_dbg(VFS, "1st trans2 resp needs bigbuf\n");
-	} else {
-		/* Have first buffer */
-		mid->resp_buf = buf;
-		mid->large_buf = true;
-		server->bigbuf = NULL;
-	}
-	return true;
-}
-
-static bool
 cifs_need_neg(struct TCP_Server_Info *server)
 {
 	return server->maxBuf == 0;

@@ -33,6 +33,8 @@ extern struct smb_version_values smb1_va
 /*
  * smb1transport.c
  */
+bool cifs_check_trans2(struct mid_q_entry *mid, struct TCP_Server_Info *server,
+		       char *buf, int malformed);
 
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 #endif /* _SMB1PROTO_H */

174 lines not on this page · raw message

@@ -708,10 +708,18 @@ bool
 cifs_check_trans2(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 		  char *buf, int malformed)
 {
-	if (malformed)
-		return false;
-	if (check2ndT2(buf) <= 0)
+	if (malformed || check2ndT2(buf) <= 0) {
+		/* mid->multiRsp blocks the server buf detach in handle_mid();
+		 * returning false here would leak resp_buf and leave a dangling
+		 * server->smallbuf/bigbuf after the user thread frees resp_buf.
+		 */
+		if (mid->multiRsp) {
+			mid->multiEnd = true;
+			dequeue_mid(mid, true);
+			return true;
+		}
 		return false;
+	}
 	mid->multiRsp = true;
 	if (mid->resp_buf) {
 		/* merge response - fix up 1st*/

@@ -655,12 +655,31 @@ coalesce_t2(char *second_buf, struct smb
 	data_area_of_tgt = (char *)&pSMBt->hdr.Protocol +
 				get_unaligned_le16(&pSMBt->t2_rsp.DataOffset);
 
-	/* validate target area */
 	data_area_of_src = (char *)&pSMBs->hdr.Protocol +
 				get_unaligned_le16(&pSMBs->t2_rsp.DataOffset);
 
 	data_area_of_tgt += total_in_tgt;
 
+	/*
+	 * DataOffset fields are server-supplied and not validated against
+	 * buffer bounds; check both data pointers before mutating the
+	 * target header.
+	 */
+	if (data_area_of_tgt < (char *)target_hdr +
+				sizeof(struct smb_t2_rsp) + sizeof(__le16) ||
+	    data_area_of_tgt + total_in_src >
+	    (char *)target_hdr + CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
+		cifs_dbg(VFS, "%s: target data area out of bounds\n", __func__);
+		return -EPROTO;
+	}
+	if (data_area_of_src < second_buf +
+				sizeof(struct smb_t2_rsp) + sizeof(__le16) ||
+	    data_area_of_src + total_in_src >
+	    second_buf + smbCalcSize((struct smb_hdr *)second_buf)) {
+		cifs_dbg(VFS, "%s: secondary data area out of bounds\n", __func__);
+		return -EPROTO;
+	}
+
 	total_in_tgt += total_in_src;
 	/* is the result too big for the field? */
 	if (total_in_tgt > USHRT_MAX) {

@@ -1307,11 +1307,11 @@ static const struct proc_ops cifs_mount_
 };
 
 #else
-inline void cifs_proc_init(void)
+void cifs_proc_init(void)
 {
 }
 
-inline void cifs_proc_clean(void)
+void cifs_proc_clean(void)
 {
 }
 #endif /* PROC_FS */

@@ -27,10 +27,8 @@ struct cifs_spnego_msg {
 	uint8_t		data[];
 };
 
-#ifdef __KERNEL__
 extern struct key_type cifs_spnego_key_type;
 extern struct key *cifs_get_spnego_key(struct cifs_ses *sesInfo,
 				       struct TCP_Server_Info *server);
-#endif /* KERNEL */
 
 #endif /* _CIFS_SPNEGO_H */

@@ -54,7 +54,6 @@
 #define SFM_MAP_UNI_RSVD	1
 #define SFU_MAP_UNI_RSVD	2
 
-#ifdef __KERNEL__
 int cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
 		    const struct nls_table *cp, int map_type);
 int cifs_utf16_bytes(const __le16 *from, int maxbytes,

@@ -69,8 +68,6 @@ extern int cifs_remap(struct cifs_sb_inf
 extern __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen,
 				     int *utf16_len, const struct nls_table *cp,
 				     int remap);
-#endif
-
 wchar_t cifs_toupper(wchar_t in);
 
 #endif /* _CIFS_UNICODE_H */

@@ -28,6 +28,8 @@
 #include <linux/splice.h>
 #include <linux/uuid.h>
 #include <linux/xattr.h>
+#include <linux/mm.h>
+#include <linux/key-type.h>
 #include <uapi/linux/magic.h>
 #include <net/ipv6.h>
 #include "cifsfs.h"

@@ -35,10 +37,9 @@
 #define DECLARE_GLOBALS_HERE
 #include "cifsglob.h"
 #include "cifsproto.h"
+#include "smb2proto.h"
 #include "cifs_debug.h"
 #include "cifs_fs_sb.h"
-#include <linux/mm.h>
-#include <linux/key-type.h>
 #include "cifs_spnego.h"
 #include "fscache.h"
 #ifdef CONFIG_CIFS_DFS_UPCALL

@@ -2112,7 +2112,7 @@ extern mempool_t cifs_io_subrequest_pool
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 extern struct smb_version_operations smb20_operations;
 extern struct smb_version_values smb20_values;
-#endif /* CIFS_ALLOW_INSECURE_LEGACY */
+#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 extern struct smb_version_operations smb21_operations;
 extern struct smb_version_values smb21_values;
 extern struct smb_version_values smbdefault_values;

@@ -2383,4 +2383,10 @@ static inline int cifs_open_create_optio
  */
 #define CIFS_INO_BLOCKS(size) DIV_ROUND_UP_ULL((u64)(size), 512)
 
+struct cifs_calc_sig_ctx {
+	struct md5_ctx *md5;
+	struct hmac_sha256_ctx *hmac;
+	struct shash_desc *shash;
+};
+
 #endif	/* _CIFS_GLOB_H */

@@ -590,7 +590,7 @@ extern int cifs_do_set_acl(const unsigne
 			   const struct nls_table *nls_codepage, int remap);
 extern int CIFSGetExtAttr(const unsigned int xid, struct cifs_tcon *tcon,
 			const int netfid, __u64 *pExtAttrBits, __u64 *pMask);
-#endif /* CIFS_ALLOW_INSECURE_LEGACY */
+#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb);
 extern bool couldbe_mf_symlink(const struct cifs_fattr *fattr);
 extern int check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,

@@ -622,11 +622,6 @@ int cifs_create_mf_symlink(unsigned int
 			   struct cifs_sb_info *cifs_sb,
 			   const unsigned char *path, char *pbuf,
 			   unsigned int *pbytes_written);
-struct cifs_calc_sig_ctx {
-	struct md5_ctx *md5;
-	struct hmac_sha256_ctx *hmac;
-	struct shash_desc *shash;
-};
 int __cifs_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server,
 			  char *signature, struct cifs_calc_sig_ctx *ctx);
 enum securityEnum cifs_select_sectype(struct TCP_Server_Info *,

@@ -775,4 +770,9 @@ static inline void cifs_free_open_info(s
 	memset(data, 0, sizeof(*data));
 }
 
+#define smb_EIO2(trace, info, info2) ({		\
+	trace_smb3_eio(trace, info, info2);	\
+	-EIO;					\
+})
+
 #endif			/* _CIFSPROTO_H */

146 lines not on this page · raw message

@@ -44,7 +44,7 @@ struct bucket {
 	unsigned int count;
 };
 
-/**
+/*
  * has_low_entropy() - Compute Shannon entropy of the sampled data.
  * @bkt:	Bytes counts of the sample.
  * @slen:	Size of the sample.

@@ -82,7 +82,7 @@ static bool has_low_entropy(struct bucke
 #define BYTE_DIST_BAD		0
 #define BYTE_DIST_GOOD		1
 #define BYTE_DIST_MAYBE		2
-/**
+/*
  * calc_byte_distribution() - Compute byte distribution on the sampled data.
  * @bkt:	Byte counts of the sample.
  * @slen:	Size of the sample.

@@ -182,7 +182,7 @@ static int collect_sample(const struct i
 	return s;
 }
 
-/**
+/*
  * is_compressible() - Determines if a chunk of data is compressible.
  * @data: Iterator containing uncompressed data.
  *

@@ -261,6 +261,21 @@ out:
 	return ret;
 }
 
+/*
+ * should_compress() - Determines if a request (write) or the response to a
+ *		       request (read) should be compressed.
+ * @tcon: tcon of the request is being sent to
+ * @rqst: request to evaluate
+ *
+ * Return: true iff:
+ * - compression was successfully negotiated with server
+ * - server has enabled compression for the share
+ * - it's a read or write request
+ * - (write only) request length is >= SMB_COMPRESS_MIN_LEN
+ * - (write only) is_compressible() returns 1
+ *
+ * Return false otherwise.
+ */
 bool should_compress(const struct cifs_tcon *tcon, const struct smb_rqst *rq)
 {
 	const struct smb2_hdr *shdr = rq->rq_iov->iov_base;

@@ -29,26 +29,11 @@
 #ifdef CONFIG_CIFS_COMPRESSION
 typedef int (*compress_send_fn)(struct TCP_Server_Info *, int, struct smb_rqst *);
 
-int smb_compress(struct TCP_Server_Info *server, struct smb_rqst *rq, compress_send_fn send_fn);
 
-/**
- * should_compress() - Determines if a request (write) or the response to a
- *		       request (read) should be compressed.
- * @tcon: tcon of the request is being sent to
- * @rqst: request to evaluate
- *
- * Return: true iff:
- * - compression was successfully negotiated with server
- * - server has enabled compression for the share
- * - it's a read or write request
- * - (write only) request length is >= SMB_COMPRESS_MIN_LEN
- * - (write only) is_compressible() returns 1
- *
- * Return false otherwise.
- */
+int smb_compress(struct TCP_Server_Info *server, struct smb_rqst *rq, compress_send_fn send_fn);
 bool should_compress(const struct cifs_tcon *tcon, const struct smb_rqst *rq);
 
-/**
+/*
  * smb_compress_alg_valid() - Validate a compression algorithm.
  * @alg: Compression algorithm to check.
  * @valid_none: Conditional check whether NONE algorithm should be

148 lines not on this page · raw message

@@ -458,7 +458,7 @@ out_err:
 
 int
 cifs_atomic_open(struct inode *inode, struct dentry *direntry,
-		 struct file *file, unsigned oflags, umode_t mode)
+		 struct file *file, unsigned int oflags, umode_t mode)
 {
 	int rc;
 	unsigned int xid;

@@ -15,8 +15,6 @@
 #include "cifsglob.h"
 #include "cifsproto.h"
 
-#ifdef __KERNEL__
-
 int dns_resolve_name(const char *dom, const char *name,
 		     size_t namelen, struct sockaddr *ip_addr);
 

@@ -36,6 +34,4 @@ static inline int dns_resolve_unc(const
 	return dns_resolve_name(dom, name, namelen, ip_addr);
 }
 
-#endif /* KERNEL */
-
 #endif /* _DNS_RESOLVE_H */

@@ -505,7 +505,7 @@ cifs_parse_smb_version(struct fs_context
 	case Smb_20:
 		cifs_errorf(fc, "vers=2.0 mount not permitted when legacy dialects disabled\n");
 		return 1;
-#endif /* CIFS_ALLOW_INSECURE_LEGACY */
+#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 	case Smb_21:
 		ctx->ops = &smb21_operations;
 		ctx->vals = &smb21_values;

@@ -18,6 +18,7 @@
 #include "nterr.h"
 #include "cifs_unicode.h"
 #include "smb2pdu.h"
+#include "smb2proto.h"
 #include "cifsfs.h"
 #ifdef CONFIG_CIFS_DFS_UPCALL
 #include "dns_resolve.h"

@@ -200,7 +200,7 @@ cifs_set_port(struct sockaddr *addr, con
 }
 
 /*****************************************************************************
-convert a NT status code to a dos class/code
+ *convert a NT status code to a dos class/code
  *****************************************************************************/
 /* NT status -> dos error map */
 static const struct {

@@ -163,7 +163,8 @@ int smb2_parse_symlink_response(struct c
 					 cifs_sb);
 }
 
-int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, void *buf)
+int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
+		   __u32 *oplock, void *buf)
 {
 	int rc;
 	__le16 *smb2_path;

@@ -21,7 +21,6 @@
 #include "cifs_unicode.h"
 #include "fscache.h"
 #include "smb2glob.h"
-#include "smb2pdu.h"
 #include "smb2proto.h"
 #include "cached_dir.h"
 #include "../common/smb2status.h"

@@ -10,10 +10,9 @@
 #include <linux/errno.h>
 #include "cifsglob.h"
 #include "cifs_debug.h"
-#include "smb2pdu.h"
 #include "smb2proto.h"
-#include "../common/smb2status.h"
 #include "smb2glob.h"
+#include "../common/smb2status.h"
 #include "trace.h"
 
 struct status_to_posix_error {

@@ -17,9 +17,9 @@
 #include <uapi/linux/magic.h>
 #include "cifsfs.h"
 #include "cifsglob.h"
-#include "smb2pdu.h"
-#include "smb2proto.h"
 #include "cifsproto.h"
+#include "smb2proto.h"
+#include "smb2pdu.h"
 #include "cifs_debug.h"
 #include "cifs_unicode.h"
 #include "../common/smb2status.h"

@@ -26,8 +26,8 @@
 #include <linux/netfs.h>
 #include <trace/events/netfs.h>
 #include "cifsglob.h"
-#include "cifsacl.h"
 #include "cifsproto.h"
+#include "cifsacl.h"
 #include "smb2proto.h"
 #include "cifs_unicode.h"
 #include "cifs_debug.h"

@@ -3921,7 +3921,8 @@ int SMB2_query_info(const unsigned int x
 /* currently unused, as now we are doing compounding instead (see smb311_posix_query_path_info) */
 int
 SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon,
-		u64 persistent_fid, u64 volatile_fid, struct smb311_posix_qinfo *data, u32 *plen)
+			u64 persistent_fid, u64 volatile_fid,
+			struct smb311_posix_qinfo *data, u32 *plen)
 {
 	size_t output_len = sizeof(struct smb311_posix_qinfo) +
 			(sizeof(struct smb_sid) * 2) + (PATH_MAX * 2);

@@ -9,8 +9,10 @@
  */
 #ifndef _SMB2PROTO_H
 #define _SMB2PROTO_H
+
 #include <linux/nls.h>
 #include <linux/key-type.h>
+#include "cached_dir.h"
 
 struct statfs;
 struct smb_rqst;

174 lines not on this page · raw message

@@ -608,6 +608,11 @@ CIFSTCon(const unsigned int xid, struct
 		tcon->tid = smb_buffer_response->Tid;
 		bcc_ptr = pByteArea(smb_buffer_response);
 		bytes_left = get_bcc(smb_buffer_response);
+		if (bytes_left < 2) {
+			rc = smb_EIO2(smb_eio_trace_tcon_bcc_too_small,
+				      bytes_left, 2);
+			goto out;
+		}
 		length = strnlen(bcc_ptr, bytes_left - 2);
 		if (smb_buffer->Flags2 & SMBFLG2_UNICODE)
 			is_unicode = true;

@@ -663,6 +668,7 @@ CIFSTCon(const unsigned int xid, struct
 			reset_cifs_unix_caps(xid, tcon, NULL, NULL);
 		}
 	}
+out:
 	cifs_buf_release(smb_buffer);
 	return rc;
 }

@@ -133,6 +133,7 @@
 	EM(smb_eio_trace_sym_slash,			"sym_slash") \
 	EM(smb_eio_trace_sym_target_len,		"sym_target_len") \
 	EM(smb_eio_trace_symlink_file_size,		"symlink_file_size") \
+	EM(smb_eio_trace_tcon_bcc_too_small,		"tcon_bcc_too_small") \
 	EM(smb_eio_trace_tdis_in_reconnect,		"tdis_in_reconnect") \
 	EM(smb_eio_trace_tx_chained_async,		"tx_chained_async") \
 	EM(smb_eio_trace_tx_compress_failed,		"tx_compress_failed") \

@@ -214,7 +215,7 @@
 #define EM(a, b) a,
 #define E_(a, b) a
 
-enum smb_eio_trace		{ smb_eio_traces } __mode(byte);
+enum smb_eio_trace		{ smb_eio_traces };
 enum smb3_rw_credits_trace	{ smb3_rw_credits_traces } __mode(byte);
 enum smb3_tcon_ref_trace	{ smb3_tcon_ref_traces } __mode(byte);
 

@@ -200,18 +200,28 @@ renew_client_locked(struct nfs4_client *
 	clp->cl_state = NFSD4_ACTIVE;
 }
 
+/*
+ * Finish a cl_rpc_users unpin with the client_lock held. A
+ * revocation walk clears @renew so the client whose state it is
+ * revoking is not revived; every other caller renews the lease of
+ * a still-active client.
+ */
+static void __put_client_locked(struct nfs4_client *clp, bool renew)
+{
+	if (is_client_expired(clp))
+		wake_up_all(&expiry_wq);
+	else if (renew)
+		renew_client_locked(clp);
+}
+
 static void put_client_renew_locked(struct nfs4_client *clp)
 {
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
 
 	lockdep_assert_held(&nn->client_lock);
 
-	if (!atomic_dec_and_test(&clp->cl_rpc_users))
-		return;
-	if (!is_client_expired(clp))
-		renew_client_locked(clp);
-	else
-		wake_up_all(&expiry_wq);
+	if (atomic_dec_and_test(&clp->cl_rpc_users))
+		__put_client_locked(clp, true);
 }
 
 static void put_client_renew(struct nfs4_client *clp)

@@ -220,10 +230,27 @@ static void put_client_renew(struct nfs4
 
 	if (!atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock))
 		return;
-	if (!is_client_expired(clp))
-		renew_client_locked(clp);
-	else
-		wake_up_all(&expiry_wq);
+	__put_client_locked(clp, true);
+	spin_unlock(&nn->client_lock);
+}
+
+static void put_client_no_renew_locked(struct nfs4_client *clp)
+{
+	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+	lockdep_assert_held(&nn->client_lock);
+
+	if (atomic_dec_and_test(&clp->cl_rpc_users))
+		__put_client_locked(clp, false);
+}
+
+static void put_client_no_renew(struct nfs4_client *clp)
+{
+	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+	if (!atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock))
+		return;
+	__put_client_locked(clp, false);
 	spin_unlock(&nn->client_lock);
 }
 

@@ -1941,9 +1968,7 @@ void nfsd4_revoke_states(struct nfsd_net
 					 */
 					nn->nfs40_last_revoke =
 						ktime_get_boottime_seconds();
-				if (atomic_dec_and_test(&clp->cl_rpc_users) &&
-				    is_client_expired(clp))
-					wake_up_all(&expiry_wq);
+				put_client_no_renew_locked(clp);
 				goto retry;
 			}
 		}

@@ -7047,9 +7072,7 @@ retry:
 				nfsd4_drop_revoked_stid(stid);
 				nfs4_put_stid(stid);
 				spin_lock(&nn->client_lock);
-				if (atomic_dec_and_test(&clp->cl_rpc_users) &&
-				    is_client_expired(clp))
-					wake_up_all(&expiry_wq);
+				put_client_no_renew_locked(clp);
 				goto retry;
 			}
 		spin_unlock(&clp->cl_lock);

@@ -7122,15 +7145,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 		clp = dp->dl_stid.sc_client;
 		list_del_init(&dp->dl_recall_lru);
 		revoke_delegation(dp);
-		/*
-		 * Unpin without renewing: put_client_renew() would
-		 * renew the reaped client's lease.
-		 */
-		if (atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock)) {
-			if (is_client_expired(clp))
-				wake_up_all(&expiry_wq);
-			spin_unlock(&nn->client_lock);
-		}
+		put_client_no_renew(clp);
 	}
 
 	spin_lock(&nn->client_lock);

@@ -351,6 +351,16 @@ free_blocked_lock(struct nfsd4_blocked_l
 	kref_put(&nbl->nbl_kref, free_nbl);
 }
 
+/* A blocked lock's flc_owner is its nfs4_lockowner. */
+static struct nfs4_client *
+nbl_client(struct nfsd4_blocked_lock *nbl)
+{
+	struct nfs4_lockowner *lo;
+
+	lo = (struct nfs4_lockowner *)nbl->nbl_lock.c.flc_owner;
+	return lo->lo_owner.so_client;
+}
+
 static void
 remove_blocked_locks(struct nfs4_lockowner *lo)
 {

@@ -7175,22 +7185,29 @@ nfs4_laundromat(struct nfsd_net *nn)
 	 * indefinitely once the lock does become free.
 	 */
 	BUG_ON(!list_empty(&reaplist));
+	spin_lock(&nn->client_lock);
 	spin_lock(&nn->blocked_locks_lock);
-	while (!list_empty(&nn->blocked_locks_lru)) {
-		nbl = list_first_entry(&nn->blocked_locks_lru,
-					struct nfsd4_blocked_lock, nbl_lru);
+	list_for_each_safe(pos, next, &nn->blocked_locks_lru) {
+		nbl = list_entry(pos, struct nfsd4_blocked_lock, nbl_lru);
 		if (!state_expired(&lt, nbl->nbl_time))
 			break;
+		clp = nbl_client(nbl);
+		if (is_client_expired(clp))
+			continue;
+		atomic_inc(&clp->cl_rpc_users);
 		list_move(&nbl->nbl_lru, &reaplist);
 		list_del_init(&nbl->nbl_list);
 	}
 	spin_unlock(&nn->blocked_locks_lock);
+	spin_unlock(&nn->client_lock);
 
 	while (!list_empty(&reaplist)) {
 		nbl = list_first_entry(&reaplist,
 					struct nfsd4_blocked_lock, nbl_lru);
+		clp = nbl_client(nbl);
 		list_del_init(&nbl->nbl_lru);
 		free_blocked_lock(nbl);
+		put_client_no_renew(clp);
 	}
 #ifdef CONFIG_NFSD_V4_2_INTER_SSC
 	/* service the server-to-server copy delayed unmount list */

@@ -7165,11 +7165,16 @@ nfs4_laundromat(struct nfsd_net *nn)
 		if (!state_expired(&lt, oo->oo_time))
 			break;
 		list_del_init(&oo->oo_close_lru);
+		clp = oo->oo_owner.so_client;
+		if (is_client_expired(clp))
+			continue;
 		stp = oo->oo_last_closed_stid;
 		oo->oo_last_closed_stid = NULL;
+		atomic_inc(&clp->cl_rpc_users);
 		spin_unlock(&nn->client_lock);
 		nfs4_put_stid(&stp->st_stid);
 		spin_lock(&nn->client_lock);
+		put_client_no_renew_locked(clp);
 	}
 	spin_unlock(&nn->client_lock);
 

@@ -1136,7 +1136,6 @@ static ssize_t read_block_state(struct f
 	ssize_t index, written = 0;
 	struct zram *zram = file->private_data;
 	unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
-	struct timespec64 ts;
 
 	kbuf = kvmalloc(count, GFP_KERNEL);
 	if (!kbuf)

@@ -1151,6 +1150,7 @@ static ssize_t read_block_state(struct f
 
 	for (index = *ppos; index < nr_pages; index++) {
 		int copied;
+		struct timespec64 ts;
 
 		zram_slot_lock(zram, index);
 		if (!zram_allocated(zram, index))

@@ -1135,7 +1135,7 @@ static ssize_t read_block_state(struct f
 	char *kbuf;
 	ssize_t index, written = 0;
 	struct zram *zram = file->private_data;
-	unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+	unsigned long nr_pages;
 
 	kbuf = kvmalloc(count, GFP_KERNEL);
 	if (!kbuf)

@@ -1148,6 +1148,8 @@ static ssize_t read_block_state(struct f
 		return -EINVAL;
 	}
 
+	nr_pages = zram->disksize >> PAGE_SHIFT;
+
 	for (index = *ppos; index < nr_pages; index++) {
 		int copied;
 		struct timespec64 ts;

@@ -501,7 +501,8 @@ out:
 
 #ifdef CONFIG_ZRAM_WRITEBACK
 static ssize_t writeback_limit_enable_store(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t len)
+					    struct device_attribute *attr,
+					    const char *buf, size_t len)
 {
 	struct zram *zram = dev_to_zram(dev);
 	u64 val;

@@ -510,18 +511,19 @@ static ssize_t writeback_limit_enable_st
 	if (kstrtoull(buf, 10, &val))
 		return ret;
 
-	down_read(&zram->init_lock);
+	down_write(&zram->init_lock);
 	spin_lock(&zram->wb_limit_lock);
 	zram->wb_limit_enable = val;
 	spin_unlock(&zram->wb_limit_lock);
-	up_read(&zram->init_lock);
+	up_write(&zram->init_lock);
 	ret = len;
 
 	return ret;
 }
 
 static ssize_t writeback_limit_enable_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
+					   struct device_attribute *attr,
+					   char *buf)
 {
 	bool val;
 	struct zram *zram = dev_to_zram(dev);

@@ -536,7 +538,8 @@ static ssize_t writeback_limit_enable_sh
 }
 
 static ssize_t writeback_limit_store(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t len)
+				     struct device_attribute *attr,
+				     const char *buf, size_t len)
 {
 	struct zram *zram = dev_to_zram(dev);
 	u64 val;

@@ -545,11 +548,11 @@ static ssize_t writeback_limit_store(str
 	if (kstrtoull(buf, 10, &val))
 		return ret;
 
-	down_read(&zram->init_lock);
+	down_write(&zram->init_lock);
 	spin_lock(&zram->wb_limit_lock);
 	zram->bd_wb_limit = val;
 	spin_unlock(&zram->wb_limit_lock);
-	up_read(&zram->init_lock);
+	up_write(&zram->init_lock);
 	ret = len;
 
 	return ret;