Merge tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - support "prefer busy polling" NAPI operation mode, where we defer
     softirq for some time expecting applications to periodically busy
     poll

   - AF_XDP: improve efficiency by more batching and hindering the
     adjacency cache prefetcher

   - af_packet: make packet_fanout.arr size configurable up to 64K

   - tcp: optimize TCP zero copy receive in presence of partial or
     unaligned reads making zero copy a performance win for much smaller
     messages

   - XDP: add bulk APIs for returning / freeing frames

   - sched: support fragmenting IP packets as they come out of conntrack

   - net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs

  BPF:

   - BPF switch from crude rlimit-based to memcg-based memory accounting

   - BPF type format information for kernel modules and related tracing
     enhancements

   - BPF implement task local storage for BPF LSM

   - allow the FENTRY/FEXIT/RAW_TP tracing programs to use
     bpf_sk_storage

  Protocols:

   - mptcp: improve multiple xmit streams support, memory accounting and
     many smaller improvements

   - TLS: support CHACHA20-POLY1305 cipher

   - seg6: add support for SRv6 End.DT4/DT6 behavior

   - sctp: Implement RFC 6951: UDP Encapsulation of SCTP

   - ppp_generic: add ability to bridge channels directly

   - bridge: Connectivity Fault Management (CFM) support as is defined
     in IEEE 802.1Q section 12.14.

  Drivers:

   - mlx5: make use of the new auxiliary bus to organize the driver
     internals

   - mlx5: more accurate port TX timestamping support

   - mlxsw:
      - improve the efficiency of offloaded next hop updates by using
        the new nexthop object API
      - support blackhole nexthops
      - support IEEE 802.1ad (Q-in-Q) bridging

   - rtw88: major bluetooth co-existance improvements

   - iwlwifi: support new 6 GHz frequency band

   - ath11k: Fast Initial Link Setup (FILS)

   - mt7915: dual band concurrent (DBDC) support

   - net: ipa: add basic support for IPA v4.5

  Refactor:

   - a few pieces of in_interrupt() cleanup work from Sebastian Andrzej
     Siewior

   - phy: add support for shared interrupts; get rid of multiple driver
     APIs and have the drivers write a full IRQ handler, slight growth
     of driver code should be compensated by the simpler API which also
     allows shared IRQs

   - add common code for handling netdev per-cpu counters

   - move TX packet re-allocation from Ethernet switch tag drivers to a
     central place

   - improve efficiency and rename nla_strlcpy

   - number of W=1 warning cleanups as we now catch those in a patchwork
     build bot

  Old code removal:

   - wan: delete the DLCI / SDLA drivers

   - wimax: move to staging

   - wifi: remove old WDS wifi bridging support"

* tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1922 commits)
  net: hns3: fix expression that is currently always true
  net: fix proc_fs init handling in af_packet and tls
  nfc: pn533: convert comma to semicolon
  af_vsock: Assign the vsock transport considering the vsock address flags
  af_vsock: Set VMADDR_FLAG_TO_HOST flag on the receive path
  vsock_addr: Check for supported flag values
  vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag
  vm_sockets: Add flags field in the vsock address data structure
  net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled
  tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit
  net: mscc: ocelot: install MAC addresses in .ndo_set_rx_mode from process context
  nfc: s3fwrn5: Release the nfc firmware
  net: vxget: clean up sparse warnings
  mlxsw: spectrum_router: Use eXtended mezzanine to offload IPv4 router
  mlxsw: spectrum: Set KVH XLT cache mode for Spectrum2/3
  mlxsw: spectrum_router_xm: Introduce basic XM cache flushing
  mlxsw: reg: Add Router LPM Cache Enable Register
  mlxsw: reg: Add Router LPM Cache ML Delete Register
  mlxsw: spectrum_router_xm: Implement L-value tracking for M-index
  mlxsw: reg: Add XM Router M Table Register
  ...

1 files changed, 99 insertions, 38 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index ac7a7ae4614a..a46334906c94 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1069,19 +1069,6 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
 }
 EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
 
-struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
-{
-	struct net_device *dev;
-
-	ASSERT_RTNL();
-	for_each_netdev(net, dev)
-		if (dev->type == type)
-			return dev;
-
-	return NULL;
-}
-EXPORT_SYMBOL(__dev_getfirstbyhwtype);
-
 struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 {
 	struct net_device *dev, *ret = NULL;
@@ -3206,7 +3193,7 @@ int skb_checksum_help(struct sk_buff *skb)
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		goto out_set_summed;
 
-	if (unlikely(skb_shinfo(skb)->gso_size)) {
+	if (unlikely(skb_is_gso(skb))) {
 		skb_warn_bad_offload(skb);
 		return -EINVAL;
 	}
@@ -3495,6 +3482,11 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 	if (gso_segs > dev->gso_max_segs)
 		return features & ~NETIF_F_GSO_MASK;
 
+	if (!skb_shinfo(skb)->gso_type) {
+		skb_warn_bad_offload(skb);
+		return features & ~NETIF_F_GSO_MASK;
+	}
+
 	/* Support for GSO partial features requires software
 	 * intervention before we can actually process the packets
 	 * so we need to strip support for any partial features now
@@ -3867,6 +3859,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 		return skb;
 
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
+	qdisc_skb_cb(skb)->mru = 0;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
 	switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
@@ -4950,6 +4943,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	}
 
 	qdisc_skb_cb(skb)->pkt_len = skb->len;
+	qdisc_skb_cb(skb)->mru = 0;
 	skb->tc_at_ingress = 1;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
@@ -6454,7 +6448,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 
 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
 
-		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
+		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+			      NAPIF_STATE_PREFER_BUSY_POLL);
 
 		/* If STATE_MISSED was set, leave STATE_SCHED set,
 		 * because we will call napi->poll() one more time.
@@ -6491,10 +6486,30 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)
 
 #if defined(CONFIG_NET_RX_BUSY_POLL)
 
-#define BUSY_POLL_BUDGET 8
+static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
+{
+	if (!skip_schedule) {
+		gro_normal_list(napi);
+		__napi_schedule(napi);
+		return;
+	}
 
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
+	if (napi->gro_bitmask) {
+		/* flush too old packets
+		 * If HZ < 1000, flush all packets.
+		 */
+		napi_gro_flush(napi, HZ >= 1000);
+	}
+
+	gro_normal_list(napi);
+	clear_bit(NAPI_STATE_SCHED, &napi->state);
+}
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
+			   u16 budget)
 {
+	bool skip_schedule = false;
+	unsigned long timeout;
 	int rc;
 
 	/* Busy polling means there is a high chance device driver hard irq
@@ -6511,29 +6526,33 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 
 	local_bh_disable();
 
+	if (prefer_busy_poll) {
+		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
+		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
+		if (napi->defer_hard_irqs_count && timeout) {
+			hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
+			skip_schedule = true;
+		}
+	}
+
 	/* All we really want here is to re-enable device interrupts.
 	 * Ideally, a new ndo_busy_poll_stop() could avoid another round.
 	 */
-	rc = napi->poll(napi, BUSY_POLL_BUDGET);
+	rc = napi->poll(napi, budget);
 	/* We can't gro_normal_list() here, because napi->poll() might have
 	 * rearmed the napi (napi_complete_done()) in which case it could
 	 * already be running on another CPU.
 	 */
-	trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+	trace_napi_poll(napi, rc, budget);
 	netpoll_poll_unlock(have_poll_lock);
-	if (rc == BUSY_POLL_BUDGET) {
-		/* As the whole budget was spent, we still own the napi so can
-		 * safely handle the rx_list.
-		 */
-		gro_normal_list(napi);
-		__napi_schedule(napi);
-	}
+	if (rc == budget)
+		__busy_poll_stop(napi, skip_schedule);
 	local_bh_enable();
 }
 
 void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg)
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
@@ -6561,17 +6580,23 @@ restart:
 			 * we avoid dirtying napi->state as much as we can.
 			 */
 			if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
-				   NAPIF_STATE_IN_BUSY_POLL))
+				   NAPIF_STATE_IN_BUSY_POLL)) {
+				if (prefer_busy_poll)
+					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
+			}
 			if (cmpxchg(&napi->state, val,
 				    val | NAPIF_STATE_IN_BUSY_POLL |
-					  NAPIF_STATE_SCHED) != val)
+					  NAPIF_STATE_SCHED) != val) {
+				if (prefer_busy_poll)
+					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
+			}
 			have_poll_lock = netpoll_poll_lock(napi);
 			napi_poll = napi->poll;
 		}
-		work = napi_poll(napi, BUSY_POLL_BUDGET);
-		trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
+		work = napi_poll(napi, budget);
+		trace_napi_poll(napi, work, budget);
 		gro_normal_list(napi);
 count:
 		if (work > 0)
@@ -6584,7 +6609,7 @@ count:
 
 		if (unlikely(need_resched())) {
 			if (napi_poll)
-				busy_poll_stop(napi, have_poll_lock);
+				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
 			preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
@@ -6595,7 +6620,7 @@ count:
 		cpu_relax();
 	}
 	if (napi_poll)
-		busy_poll_stop(napi, have_poll_lock);
+		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
 	preempt_enable();
 out:
 	rcu_read_unlock();
@@ -6646,8 +6671,10 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
 	if (!napi_disable_pending(napi) &&
-	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
+	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) {
+		clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 		__napi_schedule_irqoff(napi);
+	}
 
 	return HRTIMER_NORESTART;
 }
@@ -6705,6 +6732,7 @@ void napi_disable(struct napi_struct *n)
 
 	hrtimer_cancel(&n->timer);
 
+	clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
 	clear_bit(NAPI_STATE_DISABLE, &n->state);
 }
 EXPORT_SYMBOL(napi_disable);
@@ -6777,6 +6805,19 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
+	/* The NAPI context has more processing work, but busy-polling
+	 * is preferred. Exit early.
+	 */
+	if (napi_prefer_busy_poll(n)) {
+		if (napi_complete_done(n, work)) {
+			/* If timeout is not set, we need to make sure
+			 * that the NAPI is re-scheduled.
+			 */
+			napi_schedule(n);
+		}
+		goto out_unlock;
+	}
+
 	if (n->gro_bitmask) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
@@ -6915,7 +6956,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
 EXPORT_SYMBOL(netdev_has_upper_dev);
 
 /**
- * netdev_has_upper_dev_all - Check if device is linked to an upper device
+ * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device
  * @dev: device
  * @upper_dev: upper device to check
  *
@@ -8153,7 +8194,7 @@ EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
 
 /**
- * netdev_lower_change - Dispatch event about lower device state change
+ * netdev_lower_state_changed - Dispatch event about lower device state change
  * @lower_dev: device
  * @lower_state_info: state to dispatch
  *
@@ -8898,7 +8939,7 @@ static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
 		return dev->netdev_ops->ndo_bpf;
 	default:
 		return NULL;
-	};
+	}
 }
 
 static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
@@ -9602,6 +9643,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		}
 	}
 
+	if ((features & NETIF_F_HW_TLS_TX) && !(features & NETIF_F_HW_CSUM)) {
+		netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+		features &= ~NETIF_F_HW_TLS_TX;
+	}
+
 	return features;
 }
 
@@ -9777,7 +9823,7 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 		rx[i].dev = dev;
 
 		/* XDP RX-queue setup */
-		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i);
+		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0);
 		if (err < 0)
 			goto err_rxq_info;
 	}
@@ -10380,6 +10426,21 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
 }
 EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
 
+/**
+ *	dev_get_tstats64 - ndo_get_stats64 implementation
+ *	@dev: device to get statistics from
+ *	@s: place to store stats
+ *
+ *	Populate @s from dev->stats and dev->tstats. Can be used as
+ *	ndo_get_stats64() callback.
+ */
+void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s)
+{
+	netdev_stats_to_stats64(s, &dev->stats);
+	dev_fetch_sw_netstats(s, dev->tstats);
+}
+EXPORT_SYMBOL_GPL(dev_get_tstats64);
+
 struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
 {
 	struct netdev_queue *queue = dev_ingress_queue(dev);