Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
  21234e3a84c7 ("net/mlx5e: Fix use after free in mlx5e_fs_init()")
  c7eafc5ed068 ("net/mlx5e: Convert ethtool_steering member of flow_steering struct to pointer")
https://lore.kernel.org/all/20220825104410.67d4709c@canb.auug.org.au/
https://lore.kernel.org/all/20220823055533.334471-1-saeed@kernel.org/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 52 insertions, 40 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 1b7f385643b4..94374d529ea4 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -310,11 +310,12 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
 				 void *owner, u32 size)
 {
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
 	struct sock *sk = (struct sock *)owner;
 
 	/* same check as in sock_kmalloc() */
-	if (size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+	if (size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
 		atomic_add(size, &sk->sk_omem_alloc);
 		return 0;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index e698dbab6fdb..d66c73c1c734 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4624,7 +4624,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 	struct softnet_data *sd;
 	unsigned int old_flow, new_flow;
 
-	if (qlen < (netdev_max_backlog >> 1))
+	if (qlen < (READ_ONCE(netdev_max_backlog) >> 1))
 		return false;
 
 	sd = this_cpu_ptr(&softnet_data);
@@ -4672,7 +4672,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	if (!netif_running(skb->dev))
 		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
-	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
+	if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) {
 		if (qlen) {
 enqueue:
 			__skb_queue_tail(&sd->input_pkt_queue, skb);
@@ -4928,7 +4928,7 @@ static int netif_rx_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	net_timestamp_check(netdev_tstamp_prequeue, skb);
+	net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	trace_netif_rx(skb);
 
@@ -5281,7 +5281,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 	int ret = NET_RX_DROP;
 	__be16 type;
 
-	net_timestamp_check(!netdev_tstamp_prequeue, skb);
+	net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	trace_netif_receive_skb(skb);
 
@@ -5664,7 +5664,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	net_timestamp_check(netdev_tstamp_prequeue, skb);
+	net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
@@ -5694,7 +5694,7 @@ void netif_receive_skb_list_internal(struct list_head *head)
 
 	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
-		net_timestamp_check(netdev_tstamp_prequeue, skb);
+		net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 		skb_list_del_init(skb);
 		if (!skb_defer_rx_timestamp(skb))
 			list_add_tail(&skb->list, &sublist);
@@ -5918,7 +5918,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		net_rps_action_and_irq_enable(sd);
 	}
 
-	napi->weight = dev_rx_weight;
+	napi->weight = READ_ONCE(dev_rx_weight);
 	while (again) {
 		struct sk_buff *skb;
 
@@ -6665,8 +6665,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	unsigned long time_limit = jiffies +
-		usecs_to_jiffies(netdev_budget_usecs);
-	int budget = netdev_budget;
+		usecs_to_jiffies(READ_ONCE(netdev_budget_usecs));
+	int budget = READ_ONCE(netdev_budget);
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
 
@@ -10284,7 +10284,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list)
 				return dev;
 
 		if (time_after(jiffies, warning_time +
-			       netdev_unregister_timeout_secs * HZ)) {
+			       READ_ONCE(netdev_unregister_timeout_secs) * HZ)) {
 			list_for_each_entry(dev, list, todo_list) {
 				pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
 					 dev->name, netdev_refcnt_read(dev));
diff --git a/net/core/filter.c b/net/core/filter.c
index e8508aaafd27..c191db80ce93 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1214,10 +1214,11 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
 static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
 	u32 filter_size = bpf_prog_size(fp->prog->len);
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
 
 	/* same check as in sock_kmalloc() */
-	if (filter_size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
+	if (filter_size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) {
 		atomic_add(filter_size, &sk->sk_omem_alloc);
 		return true;
 	}
@@ -1548,7 +1549,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
+	if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
 		err = -ENOMEM;
 	else
 		err = reuseport_attach_prog(sk, prog);
@@ -1615,7 +1616,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 		}
 	} else {
 		/* BPF_PROG_TYPE_SOCKET_FILTER */
-		if (bpf_prog_size(prog->len) > sysctl_optmem_max) {
+		if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
 			err = -ENOMEM;
 			goto err_prog_put;
 		}
@@ -5034,14 +5035,14 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 		/* Only some socketops are supported */
 		switch (optname) {
 		case SO_RCVBUF:
-			val = min_t(u32, val, sysctl_rmem_max);
+			val = min_t(u32, val, READ_ONCE(sysctl_rmem_max));
 			val = min_t(int, val, INT_MAX / 2);
 			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 			WRITE_ONCE(sk->sk_rcvbuf,
 				   max_t(int, val * 2, SOCK_MIN_RCVBUF));
 			break;
 		case SO_SNDBUF:
-			val = min_t(u32, val, sysctl_wmem_max);
+			val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
 			val = min_t(int, val, INT_MAX / 2);
 			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 			WRITE_ONCE(sk->sk_sndbuf,
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index 541c7a72a28a..21619c70a82b 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -26,7 +26,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 
 	cell = this_cpu_ptr(gcells->cells);
 
-	if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
+	if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) {
 drop:
 		dev_core_stats_rx_dropped_inc(dev);
 		kfree_skb(skb);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 833d2214f36f..e93edb810103 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -309,14 +309,17 @@ static int neigh_del_timer(struct neighbour *n)
 
 static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
 {
+	struct sk_buff_head tmp;
 	unsigned long flags;
 	struct sk_buff *skb;
 
+	skb_queue_head_init(&tmp);
 	spin_lock_irqsave(&list->lock, flags);
 	skb = skb_peek(list);
 	while (skb != NULL) {
 		struct sk_buff *skb_next = skb_peek_next(skb, list);
 		struct net_device *dev = skb->dev;
+
 		if (net == NULL || net_eq(dev_net(dev), net)) {
 			struct in_device *in_dev;
 
@@ -326,13 +329,16 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
 				in_dev->arp_parms->qlen--;
 			rcu_read_unlock();
 			__skb_unlink(skb, list);
-
-			dev_put(dev);
-			kfree_skb(skb);
+			__skb_queue_tail(&tmp, skb);
 		}
 		skb = skb_next;
 	}
 	spin_unlock_irqrestore(&list->lock, flags);
+
+	while ((skb = __skb_dequeue(&tmp))) {
+		dev_put(skb->dev);
+		kfree_skb(skb);
+	}
 }
 
 static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 35d9d5958dc6..48ecfbf29174 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4206,9 +4206,8 @@ normal:
 				SKB_GSO_CB(nskb)->csum_start =
 					skb_headroom(nskb) + doffset;
 			} else {
-				skb_copy_bits(head_skb, offset,
-					      skb_put(nskb, len),
-					      len);
+				if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len))
+					goto err;
 			}
 			continue;
 		}
@@ -4799,7 +4798,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
 {
 	bool ret;
 
-	if (likely(sysctl_tstamp_allow_data || tsonly))
+	if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly))
 		return true;
 
 	read_lock_bh(&sk->sk_callback_lock);
diff --git a/net/core/sock.c b/net/core/sock.c
index 4cb957d934a2..788c1372663c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1101,7 +1101,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		val = min_t(u32, val, sysctl_wmem_max);
+		val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
 set_sndbuf:
 		/* Ensure val * 2 fits into an int, to prevent max_t()
 		 * from treating it as a negative value.
@@ -1133,7 +1133,7 @@ set_sndbuf:
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		__sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max));
+		__sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max)));
 		break;
 
 	case SO_RCVBUFFORCE:
@@ -2536,7 +2536,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
 
 	/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
 	if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
-	    sysctl_optmem_max)
+	    READ_ONCE(sysctl_optmem_max))
 		return NULL;
 
 	skb = alloc_skb(size, priority);
@@ -2554,8 +2554,10 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
  */
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 {
-	if ((unsigned int)size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
+
+	if ((unsigned int)size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
 		void *mem;
 		/* First do the add, to avoid the race if kmalloc
 		 * might sleep.
@@ -3309,8 +3311,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	timer_setup(&sk->sk_timer, NULL, 0);
 
 	sk->sk_allocation	=	GFP_KERNEL;
-	sk->sk_rcvbuf		=	sysctl_rmem_default;
-	sk->sk_sndbuf		=	sysctl_wmem_default;
+	sk->sk_rcvbuf		=	READ_ONCE(sysctl_rmem_default);
+	sk->sk_sndbuf		=	READ_ONCE(sysctl_wmem_default);
 	sk->sk_state		=	TCP_CLOSE;
 	sk_set_socket(sk, sock);
 
@@ -3365,7 +3367,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id		=	0;
-	sk->sk_ll_usec		=	sysctl_net_busy_read;
+	sk->sk_ll_usec		=	READ_ONCE(sysctl_net_busy_read);
 #endif
 
 	sk->sk_max_pacing_rate = ~0UL;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 71a13596ea2b..725891527814 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -234,14 +234,17 @@ static int set_default_qdisc(struct ctl_table *table, int write,
 static int proc_do_dev_weight(struct ctl_table *table, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
-	int ret;
+	static DEFINE_MUTEX(dev_weight_mutex);
+	int ret, weight;
 
+	mutex_lock(&dev_weight_mutex);
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	if (ret != 0)
-		return ret;
-
-	dev_rx_weight = weight_p * dev_weight_rx_bias;
-	dev_tx_weight = weight_p * dev_weight_tx_bias;
+	if (!ret && write) {
+		weight = READ_ONCE(weight_p);
+		WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias);
+		WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias);
+	}
+	mutex_unlock(&dev_weight_mutex);
 
 	return ret;
 }