Merge branch 'netdev-RT'

Sebastian Andrzej Siewior says:

====================
net: dev: PREEMPT_RT fixups.

this series removes or replaces preempt_disable() and local_irq_save()
sections which are problematic on PREEMPT_RT.
Patch 2 makes netif_rx() work from any context after I found suggestions
for it in an old thread. Should that work, then the context-specific
variants could be removed.

v2…v3:
   - #2
     - Export __netif_rx() so it can be used by everyone.
     - Add a lockdep assert to check for interrupt context.
     - Update the kernel doc and mention that the skb is posted to
       backlog NAPI.
     - Use __netif_rx() also in drivers/net/*.c.
     - Added Toke''s review tag and kept Eric's desptite the changes
       made.

v1…v2:
  - #1 and #2
    - merge patch 1 und 2 from the series (as per Toke).
    - updated patch description and corrected the first commit number (as
      per Eric).
   - #2
     - Provide netif_rx() as in v1 and additionally __netif_rx() without
       local_bh disable()+enable() for the loopback driver. __netif_rx() is
       not exported (loopback is built-in only) so it won't be used
       drivers. If this doesn't work then we can still export/ define a
       wrapper as Eric suggested.
     - Added a comment that netif_rx() considered legacy.
   - #3
     - Moved ____napi_schedule() into rps_ipi_queued() and
       renamed it napi_schedule_rps().
   https://lore.kernel.org/all/20220204201259.1095226-1-bigeasy@linutronix.de/

v1:
   https://lore.kernel.org/all/20220202122848.647635-1-bigeasy@linutronix.de
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/amt.c

@@ -2373,7 +2373,7 @@ static bool amt_membership_query_handler(struct amt_dev *amt,
 	skb->pkt_type = PACKET_MULTICAST;
 	skb->ip_summed = CHECKSUM_NONE;
 	len = skb->len;
-	if (netif_rx(skb) == NET_RX_SUCCESS) {
+	if (__netif_rx(skb) == NET_RX_SUCCESS) {
 		amt_update_gw_status(amt, AMT_STATUS_RECEIVED_QUERY, true);
 		dev_sw_netstats_rx_add(amt->dev, len);
 	} else {
@@ -2470,7 +2470,7 @@ static bool amt_update_handler(struct amt_dev *amt, struct sk_buff *skb)
 	skb->pkt_type = PACKET_MULTICAST;
 	skb->ip_summed = CHECKSUM_NONE;
 	len = skb->len;
-	if (netif_rx(skb) == NET_RX_SUCCESS) {
+	if (__netif_rx(skb) == NET_RX_SUCCESS) {
 		amt_update_relay_status(tunnel, AMT_STATUS_RECEIVED_UPDATE,
 					true);
 		dev_sw_netstats_rx_add(amt->dev, len);

drivers/net/geneve.c

@@ -925,7 +925,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		}
 
 		skb->protocol = eth_type_trans(skb, geneve->dev);
-		netif_rx(skb);
+		__netif_rx(skb);
 		dst_release(&rt->dst);
 		return -EMSGSIZE;
 	}
@@ -1021,7 +1021,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		}
 
 		skb->protocol = eth_type_trans(skb, geneve->dev);
-		netif_rx(skb);
+		__netif_rx(skb);
 		dst_release(dst);
 		return -EMSGSIZE;
 	}

drivers/net/gtp.c

@@ -207,7 +207,7 @@ static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb,
 
 	dev_sw_netstats_rx_add(pctx->dev, skb->len);
 
-	netif_rx(skb);
+	__netif_rx(skb);
 	return 0;
 
 err:

drivers/net/loopback.c

@@ -78,7 +78,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
 
 	skb_orphan(skb);
 
-	/* Before queueing this packet to netif_rx(),
+	/* Before queueing this packet to __netif_rx(),
 	 * make sure dst is refcounted.
 	 */
 	skb_dst_force(skb);
@@ -86,7 +86,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
 	skb->protocol = eth_type_trans(skb, dev);
 
 	len = skb->len;
-	if (likely(netif_rx(skb) == NET_RX_SUCCESS))
+	if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
 		dev_lstats_add(dev, len);
 
 	return NETDEV_TX_OK;

drivers/net/macsec.c

@@ -1033,7 +1033,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb)
 				else
 					nskb->pkt_type = PACKET_MULTICAST;
 
-				netif_rx(nskb);
+				__netif_rx(nskb);
 			}
 			continue;
 		}
@@ -1056,7 +1056,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb)
 
 		nskb->dev = ndev;
 
-		if (netif_rx(nskb) == NET_RX_SUCCESS) {
+		if (__netif_rx(nskb) == NET_RX_SUCCESS) {
 			u64_stats_update_begin(&secy_stats->syncp);
 			secy_stats->stats.InPktsUntagged++;
 			u64_stats_update_end(&secy_stats->syncp);
@@ -1288,7 +1288,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 
 		macsec_reset_skb(nskb, macsec->secy.netdev);
 
-		ret = netif_rx(nskb);
+		ret = __netif_rx(nskb);
 		if (ret == NET_RX_SUCCESS) {
 			u64_stats_update_begin(&secy_stats->syncp);
 			secy_stats->stats.InPktsUnknownSCI++;

drivers/net/macvlan.c

@@ -410,7 +410,7 @@ static void macvlan_forward_source_one(struct sk_buff *skb,
 	if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr))
 		nskb->pkt_type = PACKET_HOST;
 
-	ret = netif_rx(nskb);
+	ret = __netif_rx(nskb);
 	macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false);
 }
 
@@ -468,7 +468,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 			/* forward to original port. */
 			vlan = src;
 			ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?:
-			      netif_rx(skb);
+			      __netif_rx(skb);
 			handle_res = RX_HANDLER_CONSUMED;
 			goto out;
 		}

drivers/net/mhi_net.c

@@ -225,7 +225,7 @@ static void mhi_net_dl_callback(struct mhi_device *mhi_dev,
 		u64_stats_inc(&mhi_netdev->stats.rx_packets);
 		u64_stats_add(&mhi_netdev->stats.rx_bytes, skb->len);
 		u64_stats_update_end(&mhi_netdev->stats.rx_syncp);
-		netif_rx(skb);
+		__netif_rx(skb);
 	}
 
 	/* Refill if RX buffers queue becomes low */

drivers/net/ntb_netdev.c

@@ -119,7 +119,7 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data,
 	skb->protocol = eth_type_trans(skb, ndev);
 	skb->ip_summed = CHECKSUM_NONE;
 
-	if (netif_rx(skb) == NET_RX_DROP) {
+	if (__netif_rx(skb) == NET_RX_DROP) {
 		ndev->stats.rx_errors++;
 		ndev->stats.rx_dropped++;
 	} else {

drivers/net/rionet.c

@@ -109,7 +109,7 @@ static int rionet_rx_clean(struct net_device *ndev)
 		skb_put(rnet->rx_skb[i], RIO_MAX_MSG_SIZE);
 		rnet->rx_skb[i]->protocol =
 		    eth_type_trans(rnet->rx_skb[i], ndev);
-		error = netif_rx(rnet->rx_skb[i]);
+		error = __netif_rx(rnet->rx_skb[i]);
 
 		if (error == NET_RX_DROP) {
 			ndev->stats.rx_dropped++;

drivers/net/sb1000.c

@@ -872,7 +872,7 @@ printk("cm0: IP identification: %02x%02x  fragment offset: %02x%02x\n", buffer[3
 
 	/* datagram completed: send to upper level */
 	skb_trim(skb, dlen);
-	netif_rx(skb);
+	__netif_rx(skb);
 	stats->rx_bytes+=dlen;
 	stats->rx_packets++;
 	lp->rx_skb[ns] = NULL;

drivers/net/veth.c

@@ -287,7 +287,7 @@ static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
 {
 	return __dev_forward_skb(dev, skb) ?: xdp ?
 		veth_xdp_rx(rq, skb) :
-		netif_rx(skb);
+		__netif_rx(skb);
 }
 
 /* return true if the specified skb has chances of GRO aggregation

drivers/net/vrf.c

@@ -418,7 +418,7 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	skb->protocol = eth_type_trans(skb, dev);
 
-	if (likely(netif_rx(skb) == NET_RX_SUCCESS))
+	if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
 		vrf_rx_stats(dev, len);
 	else
 		this_cpu_inc(dev->dstats->rx_drps);

drivers/net/vxlan.c

@@ -2541,7 +2541,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 	tx_stats->tx_bytes += len;
 	u64_stats_update_end(&tx_stats->syncp);
 
-	if (netif_rx(skb) == NET_RX_SUCCESS) {
+	if (__netif_rx(skb) == NET_RX_SUCCESS) {
 		u64_stats_update_begin(&rx_stats->syncp);
 		rx_stats->rx_packets++;
 		rx_stats->rx_bytes += len;

include/linux/netdevice.h

@@ -3672,8 +3672,18 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
 void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog);
 int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
 int netif_rx(struct sk_buff *skb);
-int netif_rx_ni(struct sk_buff *skb);
-int netif_rx_any_context(struct sk_buff *skb);
+int __netif_rx(struct sk_buff *skb);
+
+static inline int netif_rx_ni(struct sk_buff *skb)
+{
+	return netif_rx(skb);
+}
+
+static inline int netif_rx_any_context(struct sk_buff *skb)
+{
+	return netif_rx(skb);
+}
+
 int netif_receive_skb(struct sk_buff *skb);
 int netif_receive_skb_core(struct sk_buff *skb);
 void netif_receive_skb_list_internal(struct list_head *head);

include/trace/events/net.h

@@ -260,13 +260,6 @@ DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry,
 	TP_ARGS(skb)
 );
 
-DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_ni_entry,
-
-	TP_PROTO(const struct sk_buff *skb),
-
-	TP_ARGS(skb)
-);
-
 DECLARE_EVENT_CLASS(net_dev_rx_exit_template,
 
 	TP_PROTO(int ret),
@@ -312,13 +305,6 @@ DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit,
 	TP_ARGS(ret)
 );
 
-DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_ni_exit,
-
-	TP_PROTO(int ret),
-
-	TP_ARGS(ret)
-);
-
 DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit,
 
 	TP_PROTO(int ret),

net/core/dev.c

@@ -216,18 +216,38 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
 	return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];
 }
 
-static inline void rps_lock(struct softnet_data *sd)
+static inline void rps_lock_irqsave(struct softnet_data *sd,
+				    unsigned long *flags)
 {
-#ifdef CONFIG_RPS
-	spin_lock(&sd->input_pkt_queue.lock);
-#endif
+	if (IS_ENABLED(CONFIG_RPS))
+		spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags);
+	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_save(*flags);
 }
 
-static inline void rps_unlock(struct softnet_data *sd)
+static inline void rps_lock_irq_disable(struct softnet_data *sd)
 {
-#ifdef CONFIG_RPS
-	spin_unlock(&sd->input_pkt_queue.lock);
-#endif
+	if (IS_ENABLED(CONFIG_RPS))
+		spin_lock_irq(&sd->input_pkt_queue.lock);
+	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_disable();
+}
+
+static inline void rps_unlock_irq_restore(struct softnet_data *sd,
+					  unsigned long *flags)
+{
+	if (IS_ENABLED(CONFIG_RPS))
+		spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags);
+	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_restore(*flags);
+}
+
+static inline void rps_unlock_irq_enable(struct softnet_data *sd)
+{
+	if (IS_ENABLED(CONFIG_RPS))
+		spin_unlock_irq(&sd->input_pkt_queue.lock);
+	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_enable();
 }
 
 static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev,
@@ -4456,11 +4476,11 @@ static void rps_trigger_softirq(void *data)
  * If yes, queue it to our IPI list and return 1
  * If no, return 0
  */
-static int rps_ipi_queued(struct softnet_data *sd)
+static int napi_schedule_rps(struct softnet_data *sd)
 {
-#ifdef CONFIG_RPS
 	struct softnet_data *mysd = this_cpu_ptr(&softnet_data);
 
+#ifdef CONFIG_RPS
 	if (sd != mysd) {
 		sd->rps_ipi_next = mysd->rps_ipi_list;
 		mysd->rps_ipi_list = sd;
@@ -4469,6 +4489,7 @@ static int rps_ipi_queued(struct softnet_data *sd)
 		return 1;
 	}
 #endif /* CONFIG_RPS */
+	__napi_schedule_irqoff(&mysd->backlog);
 	return 0;
 }
 
@@ -4525,9 +4546,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 
 	sd = &per_cpu(softnet_data, cpu);
 
-	local_irq_save(flags);
-
-	rps_lock(sd);
+	rps_lock_irqsave(sd, &flags);
 	if (!netif_running(skb->dev))
 		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
@@ -4536,26 +4555,21 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 enqueue:
 			__skb_queue_tail(&sd->input_pkt_queue, skb);
 			input_queue_tail_incr_save(sd, qtail);
-			rps_unlock(sd);
-			local_irq_restore(flags);
+			rps_unlock_irq_restore(sd, &flags);
 			return NET_RX_SUCCESS;
 		}
 
 		/* Schedule NAPI for backlog device
 		 * We can use non atomic operation since we own the queue lock
 		 */
-		if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) {
-			if (!rps_ipi_queued(sd))
-				____napi_schedule(sd, &sd->backlog);
-		}
+		if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state))
+			napi_schedule_rps(sd);
 		goto enqueue;
 	}
 
 drop:
 	sd->dropped++;
-	rps_unlock(sd);
-
-	local_irq_restore(flags);
+	rps_unlock_irq_restore(sd, &flags);
 
 	atomic_long_inc(&skb->dev->rx_dropped);
 	kfree_skb(skb);
@@ -4796,7 +4810,6 @@ static int netif_rx_internal(struct sk_buff *skb)
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu;
 
-		preempt_disable();
 		rcu_read_lock();
 
 		cpu = get_rps_cpu(skb->dev, skb, &rflow);
@@ -4806,78 +4819,67 @@ static int netif_rx_internal(struct sk_buff *skb)
 		ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 
 		rcu_read_unlock();
-		preempt_enable();
 	} else
 #endif
 	{
 		unsigned int qtail;
 
-		ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
-		put_cpu();
+		ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail);
 	}
 	return ret;
 }
 
+/**
+ *	__netif_rx	-	Slightly optimized version of netif_rx
+ *	@skb: buffer to post
+ *
+ *	This behaves as netif_rx except that it does not disable bottom halves.
+ *	As a result this function may only be invoked from the interrupt context
+ *	(either hard or soft interrupt).
+ */
+int __netif_rx(struct sk_buff *skb)
+{
+	int ret;
+
+	lockdep_assert_once(hardirq_count() | softirq_count());
+
+	trace_netif_rx_entry(skb);
+	ret = netif_rx_internal(skb);
+	trace_netif_rx_exit(ret);
+	return ret;
+}
+EXPORT_SYMBOL(__netif_rx);
+
 /**
  *	netif_rx	-	post buffer to the network code
  *	@skb: buffer to post
  *
  *	This function receives a packet from a device driver and queues it for
- *	the upper (protocol) levels to process.  It always succeeds. The buffer
- *	may be dropped during processing for congestion control or by the
- *	protocol layers.
+ *	the upper (protocol) levels to process via the backlog NAPI device. It
+ *	always succeeds. The buffer may be dropped during processing for
+ *	congestion control or by the protocol layers.
+ *	The network buffer is passed via the backlog NAPI device. Modern NIC
+ *	driver should use NAPI and GRO.
+ *	This function can used from any context.
  *
  *	return values:
  *	NET_RX_SUCCESS	(no congestion)
  *	NET_RX_DROP     (packet was dropped)
  *
  */
-
 int netif_rx(struct sk_buff *skb)
 {
 	int ret;
 
+	local_bh_disable();
 	trace_netif_rx_entry(skb);
-
 	ret = netif_rx_internal(skb);
 	trace_netif_rx_exit(ret);
-
+	local_bh_enable();
 	return ret;
 }
 EXPORT_SYMBOL(netif_rx);
 
-int netif_rx_ni(struct sk_buff *skb)
-{
-	int err;
-
-	trace_netif_rx_ni_entry(skb);
-
-	preempt_disable();
-	err = netif_rx_internal(skb);
-	if (local_softirq_pending())
-		do_softirq();
-	preempt_enable();
-	trace_netif_rx_ni_exit(err);
-
-	return err;
-}
-EXPORT_SYMBOL(netif_rx_ni);
-
-int netif_rx_any_context(struct sk_buff *skb)
-{
-	/*
-	 * If invoked from contexts which do not invoke bottom half
-	 * processing either at return from interrupt or when softrqs are
-	 * reenabled, use netif_rx_ni() which invokes bottomhalf processing
-	 * directly.
-	 */
-	if (in_interrupt())
-		return netif_rx(skb);
-	else
-		return netif_rx_ni(skb);
-}
-EXPORT_SYMBOL(netif_rx_any_context);
-
 static __latent_entropy void net_tx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -5650,8 +5652,7 @@ static void flush_backlog(struct work_struct *work)
 	local_bh_disable();
 	sd = this_cpu_ptr(&softnet_data);
 
-	local_irq_disable();
-	rps_lock(sd);
+	rps_lock_irq_disable(sd);
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
@@ -5659,8 +5660,7 @@ static void flush_backlog(struct work_struct *work)
 			input_queue_head_incr(sd);
 		}
 	}
-	rps_unlock(sd);
-	local_irq_enable();
+	rps_unlock_irq_enable(sd);
 
 	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
@@ -5678,16 +5678,14 @@ static bool flush_required(int cpu)
 	struct softnet_data *sd = &per_cpu(softnet_data, cpu);
 	bool do_flush;
 
-	local_irq_disable();
-	rps_lock(sd);
+	rps_lock_irq_disable(sd);
 
 	/* as insertion into process_queue happens with the rps lock held,
 	 * process_queue access may race only with dequeue
 	 */
 	do_flush = !skb_queue_empty(&sd->input_pkt_queue) ||
 		   !skb_queue_empty_lockless(&sd->process_queue);
-	rps_unlock(sd);
-	local_irq_enable();
+	rps_unlock_irq_enable(sd);
 
 	return do_flush;
 #endif
@@ -5802,8 +5800,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
 
 		}
 
-		local_irq_disable();
-		rps_lock(sd);
+		rps_lock_irq_disable(sd);
 		if (skb_queue_empty(&sd->input_pkt_queue)) {
 			/*
 			 * Inline a custom version of __napi_complete().
@@ -5819,8 +5816,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
 			skb_queue_splice_tail_init(&sd->input_pkt_queue,
 						   &sd->process_queue);
 		}
-		rps_unlock(sd);
-		local_irq_enable();
+		rps_unlock_irq_enable(sd);
 	}
 
 	return work;