Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

6 files changed, 126 insertions, 91 deletions

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index ff649ebef637..bc6d21b471be 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1604,6 +1604,22 @@ efx_ef10_mcdi_read_response(struct efx_nic *efx, efx_dword_t *outbuf,
 	memcpy(outbuf, pdu + offset, outlen);
 }
 
+static void efx_ef10_mcdi_reboot_detected(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	/* All our allocations have been reset */
+	efx_ef10_reset_mc_allocations(efx);
+
+	/* The datapath firmware might have been changed */
+	nic_data->must_check_datapath_caps = true;
+
+	/* MAC statistics have been cleared on the NIC; clear the local
+	 * statistic that we update with efx_update_diff_stat().
+	 */
+	nic_data->stats[EF10_STAT_port_rx_bad_bytes] = 0;
+}
+
 static int efx_ef10_mcdi_poll_reboot(struct efx_nic *efx)
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
@@ -1623,17 +1639,7 @@ static int efx_ef10_mcdi_poll_reboot(struct efx_nic *efx)
 		return 0;
 
 	nic_data->warm_boot_count = rc;
-
-	/* All our allocations have been reset */
-	efx_ef10_reset_mc_allocations(efx);
-
-	/* The datapath firmware might have been changed */
-	nic_data->must_check_datapath_caps = true;
-
-	/* MAC statistics have been cleared on the NIC; clear the local
-	 * statistic that we update with efx_update_diff_stat().
-	 */
-	nic_data->stats[EF10_STAT_port_rx_bad_bytes] = 0;
+	efx_ef10_mcdi_reboot_detected(efx);
 
 	return -EIO;
 }
@@ -1849,7 +1855,9 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned int write_ptr;
 	efx_qword_t *txd;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
@@ -4670,6 +4678,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
 	.mcdi_poll_response = efx_ef10_mcdi_poll_response,
 	.mcdi_read_response = efx_ef10_mcdi_read_response,
 	.mcdi_poll_reboot = efx_ef10_mcdi_poll_reboot,
+	.mcdi_reboot_detected = efx_ef10_mcdi_reboot_detected,
 	.irq_enable_master = efx_port_dummy_op_void,
 	.irq_test_generate = efx_ef10_irq_test_generate,
 	.irq_disable_non_ev = efx_port_dummy_op_void,
@@ -4774,6 +4783,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.mcdi_poll_response = efx_ef10_mcdi_poll_response,
 	.mcdi_read_response = efx_ef10_mcdi_read_response,
 	.mcdi_poll_reboot = efx_ef10_mcdi_poll_reboot,
+	.mcdi_reboot_detected = efx_ef10_mcdi_reboot_detected,
 	.irq_enable_master = efx_port_dummy_op_void,
 	.irq_test_generate = efx_ef10_irq_test_generate,
 	.irq_disable_non_ev = efx_port_dummy_op_void,
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 974637d3ae25..6e11ee6173ce 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -2062,7 +2062,7 @@ static void efx_init_napi_channel(struct efx_channel *channel)
 	netif_napi_add(channel->napi_dev, &channel->napi_str,
 		       efx_poll, napi_weight);
 	napi_hash_add(&channel->napi_str);
-	efx_channel_init_lock(channel);
+	efx_channel_busy_poll_init(channel);
 }
 
 static void efx_init_napi(struct efx_nic *efx)
@@ -2125,7 +2125,7 @@ static int efx_busy_poll(struct napi_struct *napi)
 	if (!netif_running(efx->net_dev))
 		return LL_FLUSH_FAILED;
 
-	if (!efx_channel_lock_poll(channel))
+	if (!efx_channel_try_lock_poll(channel))
 		return LL_FLUSH_BUSY;
 
 	old_rx_packets = channel->rx_queue.rx_packets;
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index f08266f0eca2..5a1c5a8f278a 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -321,7 +321,9 @@ void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned write_ptr;
 	unsigned old_write_count = tx_queue->write_count;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index a9b9460de0d6..41fb6b60a3f0 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -1028,10 +1028,21 @@ static void efx_mcdi_ev_death(struct efx_nic *efx, int rc)
 
 		/* Consume the status word since efx_mcdi_rpc_finish() won't */
 		for (count = 0; count < MCDI_STATUS_DELAY_COUNT; ++count) {
-			if (efx_mcdi_poll_reboot(efx))
+			rc = efx_mcdi_poll_reboot(efx);
+			if (rc)
 				break;
 			udelay(MCDI_STATUS_DELAY_US);
 		}
+
+		/* On EF10, a CODE_MC_REBOOT event can be received without the
+		 * reboot detection in efx_mcdi_poll_reboot() being triggered.
+		 * If zero was returned from the final call to
+		 * efx_mcdi_poll_reboot(), the MC reboot wasn't noticed but the
+		 * MC has definitely rebooted so prepare for the reset.
+		 */
+		if (!rc && efx->type->mcdi_reboot_detected)
+			efx->type->mcdi_reboot_detected(efx);
+
 		mcdi->new_epoch = true;
 
 		/* Nobody was waiting for an MCDI request, so trigger a reset */
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index c530e1c4cb4f..a8ddd122f685 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -219,6 +219,7 @@ struct efx_tx_buffer {
  * @tso_packets: Number of packets via the TSO xmit path
  * @pushes: Number of times the TX push feature has been used
  * @pio_packets: Number of times the TX PIO feature has been used
+ * @xmit_more_available: Are any packets waiting to be pushed to the NIC
  * @empty_read_count: If the completion path has seen the queue as empty
  *	and the transmission path has not yet checked this, the value of
  *	@read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0.
@@ -253,6 +254,7 @@ struct efx_tx_queue {
 	unsigned int tso_packets;
 	unsigned int pushes;
 	unsigned int pio_packets;
+	bool xmit_more_available;
 	/* Statistics to supplement MAC stats */
 	unsigned long tx_packets;
 
@@ -431,21 +433,8 @@ struct efx_channel {
 	struct net_device *napi_dev;
 	struct napi_struct napi_str;
 #ifdef CONFIG_NET_RX_BUSY_POLL
-	unsigned int state;
-	spinlock_t state_lock;
-#define EFX_CHANNEL_STATE_IDLE		0
-#define EFX_CHANNEL_STATE_NAPI		(1 << 0)  /* NAPI owns this channel */
-#define EFX_CHANNEL_STATE_POLL		(1 << 1)  /* poll owns this channel */
-#define EFX_CHANNEL_STATE_DISABLED	(1 << 2)  /* channel is disabled */
-#define EFX_CHANNEL_STATE_NAPI_YIELD	(1 << 3)  /* NAPI yielded this channel */
-#define EFX_CHANNEL_STATE_POLL_YIELD	(1 << 4)  /* poll yielded this channel */
-#define EFX_CHANNEL_OWNED \
-	(EFX_CHANNEL_STATE_NAPI | EFX_CHANNEL_STATE_POLL)
-#define EFX_CHANNEL_LOCKED \
-	(EFX_CHANNEL_OWNED | EFX_CHANNEL_STATE_DISABLED)
-#define EFX_CHANNEL_USER_PEND \
-	(EFX_CHANNEL_STATE_POLL | EFX_CHANNEL_STATE_POLL_YIELD)
-#endif /* CONFIG_NET_RX_BUSY_POLL */
+	unsigned long busy_poll_state;
+#endif
 	struct efx_special_buffer eventq;
 	unsigned int eventq_mask;
 	unsigned int eventq_read_ptr;
@@ -480,98 +469,94 @@ struct efx_channel {
 };
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
-static inline void efx_channel_init_lock(struct efx_channel *channel)
+enum efx_channel_busy_poll_state {
+	EFX_CHANNEL_STATE_IDLE = 0,
+	EFX_CHANNEL_STATE_NAPI = BIT(0),
+	EFX_CHANNEL_STATE_NAPI_REQ_BIT = 1,
+	EFX_CHANNEL_STATE_NAPI_REQ = BIT(1),
+	EFX_CHANNEL_STATE_POLL_BIT = 2,
+	EFX_CHANNEL_STATE_POLL = BIT(2),
+	EFX_CHANNEL_STATE_DISABLE_BIT = 3,
+};
+
+static inline void efx_channel_busy_poll_init(struct efx_channel *channel)
 {
-	spin_lock_init(&channel->state_lock);
+	WRITE_ONCE(channel->busy_poll_state, EFX_CHANNEL_STATE_IDLE);
 }
 
 /* Called from the device poll routine to get ownership of a channel. */
 static inline bool efx_channel_lock_napi(struct efx_channel *channel)
 {
-	bool rc = true;
-
-	spin_lock_bh(&channel->state_lock);
-	if (channel->state & EFX_CHANNEL_LOCKED) {
-		WARN_ON(channel->state & EFX_CHANNEL_STATE_NAPI);
-		channel->state |= EFX_CHANNEL_STATE_NAPI_YIELD;
-		rc = false;
-	} else {
-		/* we don't care if someone yielded */
-		channel->state = EFX_CHANNEL_STATE_NAPI;
+	unsigned long prev, old = READ_ONCE(channel->busy_poll_state);
+
+	while (1) {
+		switch (old) {
+		case EFX_CHANNEL_STATE_POLL:
+			/* Ensure efx_channel_try_lock_poll() wont starve us */
+			set_bit(EFX_CHANNEL_STATE_NAPI_REQ_BIT,
+				&channel->busy_poll_state);
+			/* fallthrough */
+		case EFX_CHANNEL_STATE_POLL | EFX_CHANNEL_STATE_NAPI_REQ:
+			return false;
+		default:
+			break;
+		}
+		prev = cmpxchg(&channel->busy_poll_state, old,
+			       EFX_CHANNEL_STATE_NAPI);
+		if (unlikely(prev != old)) {
+			/* This is likely to mean we've just entered polling
+			 * state. Go back round to set the REQ bit.
+			 */
+			old = prev;
+			continue;
+		}
+		return true;
 	}
-	spin_unlock_bh(&channel->state_lock);
-	return rc;
 }
 
 static inline void efx_channel_unlock_napi(struct efx_channel *channel)
 {
-	spin_lock_bh(&channel->state_lock);
-	WARN_ON(channel->state &
-		(EFX_CHANNEL_STATE_POLL | EFX_CHANNEL_STATE_NAPI_YIELD));
-
-	channel->state &= EFX_CHANNEL_STATE_DISABLED;
-	spin_unlock_bh(&channel->state_lock);
+	/* Make sure write has completed from efx_channel_lock_napi() */
+	smp_wmb();
+	WRITE_ONCE(channel->busy_poll_state, EFX_CHANNEL_STATE_IDLE);
 }
 
 /* Called from efx_busy_poll(). */
-static inline bool efx_channel_lock_poll(struct efx_channel *channel)
+static inline bool efx_channel_try_lock_poll(struct efx_channel *channel)
 {
-	bool rc = true;
-
-	spin_lock_bh(&channel->state_lock);
-	if ((channel->state & EFX_CHANNEL_LOCKED)) {
-		channel->state |= EFX_CHANNEL_STATE_POLL_YIELD;
-		rc = false;
-	} else {
-		/* preserve yield marks */
-		channel->state |= EFX_CHANNEL_STATE_POLL;
-	}
-	spin_unlock_bh(&channel->state_lock);
-	return rc;
+	return cmpxchg(&channel->busy_poll_state, EFX_CHANNEL_STATE_IDLE,
+			EFX_CHANNEL_STATE_POLL) == EFX_CHANNEL_STATE_IDLE;
 }
 
-/* Returns true if NAPI tried to get the channel while it was locked. */
 static inline void efx_channel_unlock_poll(struct efx_channel *channel)
 {
-	spin_lock_bh(&channel->state_lock);
-	WARN_ON(channel->state & EFX_CHANNEL_STATE_NAPI);
-
-	/* will reset state to idle, unless channel is disabled */
-	channel->state &= EFX_CHANNEL_STATE_DISABLED;
-	spin_unlock_bh(&channel->state_lock);
+	clear_bit_unlock(EFX_CHANNEL_STATE_POLL_BIT, &channel->busy_poll_state);
 }
 
-/* True if a socket is polling, even if it did not get the lock. */
 static inline bool efx_channel_busy_polling(struct efx_channel *channel)
 {
-	WARN_ON(!(channel->state & EFX_CHANNEL_OWNED));
-	return channel->state & EFX_CHANNEL_USER_PEND;
+	return test_bit(EFX_CHANNEL_STATE_POLL_BIT, &channel->busy_poll_state);
 }
 
 static inline void efx_channel_enable(struct efx_channel *channel)
 {
-	spin_lock_bh(&channel->state_lock);
-	channel->state = EFX_CHANNEL_STATE_IDLE;
-	spin_unlock_bh(&channel->state_lock);
+	clear_bit_unlock(EFX_CHANNEL_STATE_DISABLE_BIT,
+			 &channel->busy_poll_state);
 }
 
-/* False if the channel is currently owned. */
+/* Stop further polling or napi access.
+ * Returns false if the channel is currently busy polling.
+ */
 static inline bool efx_channel_disable(struct efx_channel *channel)
 {
-	bool rc = true;
-
-	spin_lock_bh(&channel->state_lock);
-	if (channel->state & EFX_CHANNEL_OWNED)
-		rc = false;
-	channel->state |= EFX_CHANNEL_STATE_DISABLED;
-	spin_unlock_bh(&channel->state_lock);
-
-	return rc;
+	set_bit(EFX_CHANNEL_STATE_DISABLE_BIT, &channel->busy_poll_state);
+	/* Implicit barrier in efx_channel_busy_polling() */
+	return !efx_channel_busy_polling(channel);
 }
 
 #else /* CONFIG_NET_RX_BUSY_POLL */
 
-static inline void efx_channel_init_lock(struct efx_channel *channel)
+static inline void efx_channel_busy_poll_init(struct efx_channel *channel)
 {
 }
 
@@ -584,7 +569,7 @@ static inline void efx_channel_unlock_napi(struct efx_channel *channel)
 {
 }
 
-static inline bool efx_channel_lock_poll(struct efx_channel *channel)
+static inline bool efx_channel_try_lock_poll(struct efx_channel *channel)
 {
 	return false;
 }
@@ -1277,6 +1262,7 @@ struct efx_nic_type {
 	void (*mcdi_read_response)(struct efx_nic *efx, efx_dword_t *pdu,
 				   size_t pdu_offset, size_t pdu_len);
 	int (*mcdi_poll_reboot)(struct efx_nic *efx);
+	void (*mcdi_reboot_detected)(struct efx_nic *efx);
 	void (*irq_enable_master)(struct efx_nic *efx);
 	void (*irq_test_generate)(struct efx_nic *efx);
 	void (*irq_disable_non_ev)(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 1833a0146571..67f6afaa022f 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -431,8 +431,20 @@ finish_packet:
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tx_packets++;
 
@@ -722,6 +734,7 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
 	tx_queue->read_count = 0;
 	tx_queue->old_read_count = 0;
 	tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID;
+	tx_queue->xmit_more_available = false;
 
 	/* Set up TX descriptor ring */
 	efx_nic_init_tx(tx_queue);
@@ -747,6 +760,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
 
 		++tx_queue->read_count;
 	}
+	tx_queue->xmit_more_available = false;
 	netdev_tx_reset_queue(tx_queue->core_txq);
 }
 
@@ -1302,8 +1316,20 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tso_bursts++;
 	return NETDEV_TX_OK;