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

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

9 files changed, 226 insertions, 103 deletions

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 1dd1938f594f..8d3a2bfe186a 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -333,9 +333,9 @@ void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
 			len = buf_len;
 		/* write the full 16-byte chunks */
 		if (hw->debug_mask & mask) {
-			char prefix[20];
+			char prefix[27];
 
-			snprintf(prefix, 20,
+			snprintf(prefix, sizeof(prefix),
 				 "i40evf %02x:%02x.%x: \t0x",
 				 hw->bus.bus_id,
 				 hw->bus.device,
@@ -1104,7 +1104,7 @@ void i40e_vf_parse_hw_config(struct i40e_hw *hw,
 	hw->dev_caps.num_rx_qp = msg->num_queue_pairs;
 	hw->dev_caps.num_tx_qp = msg->num_queue_pairs;
 	hw->dev_caps.num_msix_vectors_vf = msg->max_vectors;
-	hw->dev_caps.dcb = msg->vf_offload_flags &
+	hw->dev_caps.dcb = msg->vf_cap_flags &
 			   VIRTCHNL_VF_OFFLOAD_L2;
 	hw->dev_caps.fcoe = 0;
 	for (i = 0; i < msg->num_vsis; i++) {
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h
index 5e314fd3c016..a90737786c34 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h
@@ -54,7 +54,7 @@ struct i40e_dma_mem {
 	void *va;
 	dma_addr_t pa;
 	u32 size;
-} __packed;
+};
 
 #define i40e_allocate_dma_mem(h, m, unused, s, a) \
 	i40evf_allocate_dma_mem_d(h, m, s, a)
@@ -63,7 +63,7 @@ struct i40e_dma_mem {
 struct i40e_virt_mem {
 	void *va;
 	u32 size;
-} __packed;
+};
 #define i40e_allocate_virt_mem(h, m, s) i40evf_allocate_virt_mem_d(h, m, s)
 #define i40e_free_virt_mem(h, m) i40evf_free_virt_mem_d(h, m)
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 12b02e530503..c32c62462c84 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -275,7 +275,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 	netdev_tx_completed_queue(txring_txq(tx_ring),
 				  total_packets, total_bytes);
 
-#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
+#define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2))
 	if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
 		     (I40E_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
 		/* Make sure that anybody stopping the queue after this
@@ -357,19 +357,31 @@ void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
 static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 {
 	enum i40e_latency_range new_latency_range = rc->latency_range;
-	struct i40e_q_vector *qv = rc->ring->q_vector;
 	u32 new_itr = rc->itr;
 	int bytes_per_int;
-	int usecs;
+	unsigned int usecs, estimated_usecs;
 
 	if (rc->total_packets == 0 || !rc->itr)
 		return false;
 
+	usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
+	bytes_per_int = rc->total_bytes / usecs;
+
+	/* The calculations in this algorithm depend on interrupts actually
+	 * firing at the ITR rate. This may not happen if the packet rate is
+	 * really low, or if we've been napi polling. Check to make sure
+	 * that's not the case before we continue.
+	 */
+	estimated_usecs = jiffies_to_usecs(jiffies - rc->last_itr_update);
+	if (estimated_usecs > usecs) {
+		new_latency_range = I40E_LOW_LATENCY;
+		goto reset_latency;
+	}
+
 	/* simple throttlerate management
 	 *   0-10MB/s   lowest (50000 ints/s)
 	 *  10-20MB/s   low    (20000 ints/s)
 	 *  20-1249MB/s bulk   (18000 ints/s)
-	 *  > 40000 Rx packets per second (8000 ints/s)
 	 *
 	 * The math works out because the divisor is in 10^(-6) which
 	 * turns the bytes/us input value into MB/s values, but
@@ -377,9 +389,6 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	 * are in 2 usec increments in the ITR registers, and make sure
 	 * to use the smoothed values that the countdown timer gives us.
 	 */
-	usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
-	bytes_per_int = rc->total_bytes / usecs;
-
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
 		if (bytes_per_int > 10)
@@ -392,24 +401,13 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 			new_latency_range = I40E_LOWEST_LATENCY;
 		break;
 	case I40E_BULK_LATENCY:
-	case I40E_ULTRA_LATENCY:
 	default:
 		if (bytes_per_int <= 20)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	}
 
-	/* this is to adjust RX more aggressively when streaming small
-	 * packets.  The value of 40000 was picked as it is just beyond
-	 * what the hardware can receive per second if in low latency
-	 * mode.
-	 */
-#define RX_ULTRA_PACKET_RATE 40000
-
-	if ((((rc->total_packets * 1000000) / usecs) > RX_ULTRA_PACKET_RATE) &&
-	    (&qv->rx == rc))
-		new_latency_range = I40E_ULTRA_LATENCY;
-
+reset_latency:
 	rc->latency_range = new_latency_range;
 
 	switch (new_latency_range) {
@@ -422,21 +420,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 	case I40E_BULK_LATENCY:
 		new_itr = I40E_ITR_18K;
 		break;
-	case I40E_ULTRA_LATENCY:
-		new_itr = I40E_ITR_8K;
-		break;
 	default:
 		break;
 	}
 
 	rc->total_bytes = 0;
 	rc->total_packets = 0;
+	rc->last_itr_update = jiffies;
 
 	if (new_itr != rc->itr) {
 		rc->itr = new_itr;
 		return true;
 	}
-
 	return false;
 }
 
@@ -1299,7 +1294,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
 	bool failure = false;
 
-	while (likely(total_rx_packets < budget)) {
+	while (likely(total_rx_packets < (unsigned int)budget)) {
 		struct i40e_rx_buffer *rx_buffer;
 		union i40e_rx_desc *rx_desc;
 		unsigned int size;
@@ -1406,7 +1401,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
 
 	/* guarantee a trip back through this routine if there was a failure */
-	return failure ? budget : total_rx_packets;
+	return failure ? budget : (int)total_rx_packets;
 }
 
 static u32 i40e_buildreg_itr(const int type, const u16 itr)
@@ -1575,7 +1570,6 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 
 	/* If work not completed, return budget and polling will return */
 	if (!clean_complete) {
-		const cpumask_t *aff_mask = &q_vector->affinity_mask;
 		int cpu_id = smp_processor_id();
 
 		/* It is possible that the interrupt affinity has changed but,
@@ -1585,14 +1579,22 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 		 * continue to poll, otherwise we must stop polling so the
 		 * interrupt can move to the correct cpu.
 		 */
-		if (likely(cpumask_test_cpu(cpu_id, aff_mask))) {
+		if (!cpumask_test_cpu(cpu_id, &q_vector->affinity_mask)) {
+			/* Tell napi that we are done polling */
+			napi_complete_done(napi, work_done);
+
+			/* Force an interrupt */
+			i40evf_force_wb(vsi, q_vector);
+
+			/* Return budget-1 so that polling stops */
+			return budget - 1;
+		}
 tx_only:
-			if (arm_wb) {
-				q_vector->tx.ring[0].tx_stats.tx_force_wb++;
-				i40e_enable_wb_on_itr(vsi, q_vector);
-			}
-			return budget;
+		if (arm_wb) {
+			q_vector->tx.ring[0].tx_stats.tx_force_wb++;
+			i40e_enable_wb_on_itr(vsi, q_vector);
 		}
+		return budget;
 	}
 
 	if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR)
@@ -1601,14 +1603,7 @@ tx_only:
 	/* Work is done so exit the polling mode and re-enable the interrupt */
 	napi_complete_done(napi, work_done);
 
-	/* If we're prematurely stopping polling to fix the interrupt
-	 * affinity we want to make sure polling starts back up so we
-	 * issue a call to i40evf_force_wb which triggers a SW interrupt.
-	 */
-	if (!clean_complete)
-		i40evf_force_wb(vsi, q_vector);
-	else
-		i40e_update_enable_itr(vsi, q_vector);
+	i40e_update_enable_itr(vsi, q_vector);
 
 	return min(work_done, budget - 1);
 }
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 901282c87cf6..0d9f98bc07bd 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -98,10 +98,6 @@ enum i40e_dyn_idx_t {
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
-#define i40e_pf_get_default_rss_hena(pf) \
-	(((pf)->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) ? \
-	  I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
-
 /* Supported Rx Buffer Sizes (a multiple of 128) */
 #define I40E_RXBUFFER_256   256
 #define I40E_RXBUFFER_1536  1536  /* 128B aligned standard Ethernet frame */
@@ -117,6 +113,7 @@ enum i40e_dyn_idx_t {
  * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab)
  */
 #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
+#define I40E_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2))
 #define i40e_rx_desc i40e_32byte_rx_desc
 
 #define I40E_RX_DMA_ATTR \
@@ -428,7 +425,6 @@ enum i40e_latency_range {
 	I40E_LOWEST_LATENCY = 0,
 	I40E_LOW_LATENCY = 1,
 	I40E_BULK_LATENCY = 2,
-	I40E_ULTRA_LATENCY = 3,
 };
 
 struct i40e_ring_container {
@@ -436,6 +432,7 @@ struct i40e_ring_container {
 	struct i40e_ring *ring;
 	unsigned int total_bytes;	/* total bytes processed this int */
 	unsigned int total_packets;	/* total packets processed this int */
+	unsigned long last_itr_update;	/* jiffies of last ITR update */
 	u16 count;
 	enum i40e_latency_range latency_range;
 	u16 itr;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index bde7f24af1c6..2ea919d9cdcf 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -159,6 +159,7 @@ struct i40e_link_status {
 	enum i40e_aq_link_speed link_speed;
 	u8 link_info;
 	u8 an_info;
+	u8 req_fec_info;
 	u8 fec_info;
 	u8 ext_info;
 	u8 loopback;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 6cc92089fecb..82f69031e5cd 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -39,6 +39,18 @@
 #include <linux/tcp.h>
 #include <linux/sctp.h>
 #include <linux/ipv6.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/delay.h>
+#include <linux/gfp.h>
+#include <linux/skbuff.h>
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/socket.h>
+#include <linux/jiffies.h>
 #include <net/ip6_checksum.h>
 #include <net/udp.h>
 
@@ -109,7 +121,7 @@ struct i40e_q_vector {
 #define ITR_COUNTDOWN_START 100
 	u8 itr_countdown;	/* when 0 or 1 update ITR */
 	int v_idx;	/* vector index in list */
-	char name[IFNAMSIZ + 9];
+	char name[IFNAMSIZ + 15];
 	bool arm_wb_state;
 	cpumask_t affinity_mask;
 	struct irq_affinity_notify affinity_notify;
@@ -183,6 +195,7 @@ struct i40evf_adapter {
 	struct work_struct adminq_task;
 	struct delayed_work client_task;
 	struct delayed_work init_task;
+	wait_queue_head_t down_waitqueue;
 	struct i40e_q_vector *q_vectors;
 	struct list_head vlan_filter_list;
 	char misc_vector_name[IFNAMSIZ + 9];
@@ -225,8 +238,6 @@ struct i40evf_adapter {
 /* duplicates for common code */
 #define I40E_FLAG_DCB_ENABLED			0
 #define I40E_FLAG_RX_CSUM_ENABLED		I40EVF_FLAG_RX_CSUM_ENABLED
-#define I40E_FLAG_WB_ON_ITR_CAPABLE		I40EVF_FLAG_WB_ON_ITR_CAPABLE
-#define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE	I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE
 #define I40E_FLAG_LEGACY_RX			I40EVF_FLAG_LEGACY_RX
 	/* flags for admin queue service task */
 	u32 aq_required;
@@ -250,6 +261,8 @@ struct i40evf_adapter {
 #define I40EVF_FLAG_AQ_RELEASE_PROMISC		BIT(16)
 #define I40EVF_FLAG_AQ_REQUEST_ALLMULTI		BIT(17)
 #define I40EVF_FLAG_AQ_RELEASE_ALLMULTI		BIT(18)
+#define I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING	BIT(19)
+#define I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING	BIT(20)
 
 	/* OS defined structs */
 	struct net_device *netdev;
@@ -266,19 +279,19 @@ struct i40evf_adapter {
 	enum virtchnl_link_speed link_speed;
 	enum virtchnl_ops current_op;
 #define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \
-			    (_a)->vf_res->vf_offload_flags & \
+			    (_a)->vf_res->vf_cap_flags & \
 				VIRTCHNL_VF_OFFLOAD_IWARP : \
 			    0)
 #define CLIENT_ENABLED(_a) ((_a)->cinst)
 /* RSS by the PF should be preferred over RSS via other methods. */
-#define RSS_PF(_a) ((_a)->vf_res->vf_offload_flags & \
+#define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \
 		    VIRTCHNL_VF_OFFLOAD_RSS_PF)
-#define RSS_AQ(_a) ((_a)->vf_res->vf_offload_flags & \
+#define RSS_AQ(_a) ((_a)->vf_res->vf_cap_flags & \
 		    VIRTCHNL_VF_OFFLOAD_RSS_AQ)
-#define RSS_REG(_a) (!((_a)->vf_res->vf_offload_flags & \
+#define RSS_REG(_a) (!((_a)->vf_res->vf_cap_flags & \
 		       (VIRTCHNL_VF_OFFLOAD_RSS_AQ | \
 			VIRTCHNL_VF_OFFLOAD_RSS_PF)))
-#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_offload_flags & \
+#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
 			  VIRTCHNL_VF_OFFLOAD_VLAN)
 	struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
 	struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
@@ -347,6 +360,8 @@ void i40evf_get_hena(struct i40evf_adapter *adapter);
 void i40evf_set_hena(struct i40evf_adapter *adapter);
 void i40evf_set_rss_key(struct i40evf_adapter *adapter);
 void i40evf_set_rss_lut(struct i40evf_adapter *adapter);
+void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter);
+void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter);
 void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 				enum virtchnl_ops v_opcode,
 				i40e_status v_retval, u8 *msg, u16 msglen);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 9bb2cc7dd4e4..65874d6b3ab9 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -165,7 +165,7 @@ static void i40evf_get_ethtool_stats(struct net_device *netdev,
 				     struct ethtool_stats *stats, u64 *data)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
-	int i, j;
+	unsigned int i, j;
 	char *p;
 
 	for (i = 0; i < I40EVF_GLOBAL_STATS_LEN; i++) {
@@ -197,7 +197,7 @@ static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 	int i;
 
 	if (sset == ETH_SS_STATS) {
-		for (i = 0; i < I40EVF_GLOBAL_STATS_LEN; i++) {
+		for (i = 0; i < (int)I40EVF_GLOBAL_STATS_LEN; i++) {
 			memcpy(p, i40evf_gstrings_stats[i].stat_string,
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
@@ -258,29 +258,50 @@ static u32 i40evf_get_priv_flags(struct net_device *netdev)
 static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
-	u64 changed_flags;
+	u32 orig_flags, new_flags, changed_flags;
 	u32 i;
 
-	changed_flags = adapter->flags;
+	orig_flags = READ_ONCE(adapter->flags);
+	new_flags = orig_flags;
 
 	for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
 		const struct i40evf_priv_flags *priv_flags;
 
 		priv_flags = &i40evf_gstrings_priv_flags[i];
 
-		if (priv_flags->read_only)
-			continue;
-
 		if (flags & BIT(i))
-			adapter->flags |= priv_flags->flag;
+			new_flags |= priv_flags->flag;
 		else
-			adapter->flags &= ~(priv_flags->flag);
+			new_flags &= ~(priv_flags->flag);
+
+		if (priv_flags->read_only &&
+		    ((orig_flags ^ new_flags) & ~BIT(i)))
+			return -EOPNOTSUPP;
+	}
+
+	/* Before we finalize any flag changes, any checks which we need to
+	 * perform to determine if the new flags will be supported should go
+	 * here...
+	 */
+
+	/* Compare and exchange the new flags into place. If we failed, that
+	 * is if cmpxchg returns anything but the old value, this means
+	 * something else must have modified the flags variable since we
+	 * copied it. We'll just punt with an error and log something in the
+	 * message buffer.
+	 */
+	if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) {
+		dev_warn(&adapter->pdev->dev,
+			 "Unable to update adapter->flags as it was modified by another thread...\n");
+		return -EAGAIN;
 	}
 
-	/* check for flags that changed */
-	changed_flags ^= adapter->flags;
+	changed_flags = orig_flags ^ new_flags;
 
-	/* Process any additional changes needed as a result of flag changes. */
+	/* Process any additional changes needed as a result of flag changes.
+	 * The changed_flags value reflects the list of bits that were changed
+	 * in the code above.
+	 */
 
 	/* issue a reset to force legacy-rx change to take effect */
 	if (changed_flags & I40EVF_FLAG_LEGACY_RX) {
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 7c213a347909..1825d956bb00 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -520,7 +520,7 @@ static void i40evf_irq_affinity_notify(struct irq_affinity_notify *notify,
 	struct i40e_q_vector *q_vector =
 		container_of(notify, struct i40e_q_vector, affinity_notify);
 
-	q_vector->affinity_mask = *mask;
+	cpumask_copy(&q_vector->affinity_mask, mask);
 }
 
 /**
@@ -543,9 +543,9 @@ static void i40evf_irq_affinity_release(struct kref *ref) {}
 static int
 i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 {
-	int vector, err, q_vectors;
-	int rx_int_idx = 0, tx_int_idx = 0;
-	int irq_num;
+	unsigned int vector, q_vectors;
+	unsigned int rx_int_idx = 0, tx_int_idx = 0;
+	int irq_num, err;
 
 	i40evf_irq_disable(adapter);
 	/* Decrement for Other and TCP Timer vectors */
@@ -556,18 +556,15 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 		irq_num = adapter->msix_entries[vector + NONQ_VECS].vector;
 
 		if (q_vector->tx.ring && q_vector->rx.ring) {
-			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
-				 "i40evf-%s-%s-%d", basename,
-				 "TxRx", rx_int_idx++);
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "i40evf-%s-TxRx-%d", basename, rx_int_idx++);
 			tx_int_idx++;
 		} else if (q_vector->rx.ring) {
-			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
-				 "i40evf-%s-%s-%d", basename,
-				 "rx", rx_int_idx++);
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "i40evf-%s-rx-%d", basename, rx_int_idx++);
 		} else if (q_vector->tx.ring) {
-			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
-				 "i40evf-%s-%s-%d", basename,
-				 "tx", tx_int_idx++);
+			snprintf(q_vector->name, sizeof(q_vector->name),
+				 "i40evf-%s-tx-%d", basename, tx_int_idx++);
 		} else {
 			/* skip this unused q_vector */
 			continue;
@@ -587,8 +584,10 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename)
 		q_vector->affinity_notify.release =
 						   i40evf_irq_affinity_release;
 		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
-		/* assign the mask for this irq */
-		irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
+		/* get_cpu_mask returns a static constant mask with
+		 * a permanent lifetime so it's ok to use here.
+		 */
+		irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx));
 	}
 
 	return 0;
@@ -1143,6 +1142,7 @@ void i40evf_down(struct i40evf_adapter *adapter)
 	}
 
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
 }
 
 /**
@@ -1241,7 +1241,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		tx_ring->dev = &adapter->pdev->dev;
 		tx_ring->count = adapter->tx_desc_count;
 		tx_ring->tx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF);
-		if (adapter->flags & I40E_FLAG_WB_ON_ITR_CAPABLE)
+		if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE)
 			tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR;
 
 		rx_ring = &adapter->rx_rings[i];
@@ -1417,7 +1417,7 @@ static int i40evf_init_rss(struct i40evf_adapter *adapter)
 
 	if (!RSS_PF(adapter)) {
 		/* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */
-		if (adapter->vf_res->vf_offload_flags &
+		if (adapter->vf_res->vf_cap_flags &
 		    VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
 			adapter->hena = I40E_DEFAULT_RSS_HENA_EXPANDED;
 		else
@@ -1458,6 +1458,7 @@ static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter)
 		q_vector->adapter = adapter;
 		q_vector->vsi = &adapter->vsi;
 		q_vector->v_idx = q_idx;
+		cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask);
 		netif_napi_add(adapter->netdev, &q_vector->napi,
 			       i40evf_napi_poll, NAPI_POLL_WEIGHT);
 	}
@@ -1678,6 +1679,16 @@ static void i40evf_watchdog_task(struct work_struct *work)
 		goto watchdog_done;
 	}
 
+	if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) {
+		i40evf_enable_vlan_stripping(adapter);
+		goto watchdog_done;
+	}
+
+	if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) {
+		i40evf_disable_vlan_stripping(adapter);
+		goto watchdog_done;
+	}
+
 	if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_QUEUES) {
 		i40evf_configure_queues(adapter);
 		goto watchdog_done;
@@ -1794,6 +1805,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter)
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
 	adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
 	adapter->state = __I40EVF_DOWN;
+	wake_up(&adapter->down_waitqueue);
 	dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n");
 }
 
@@ -1877,7 +1889,7 @@ static void i40evf_reset_task(struct work_struct *work)
 	}
 
 continue_reset:
-	if (netif_running(adapter->netdev)) {
+	if (netif_running(netdev)) {
 		netif_carrier_off(netdev);
 		netif_tx_stop_all_queues(netdev);
 		adapter->link_up = false;
@@ -1939,12 +1951,13 @@ continue_reset:
 		i40evf_irq_enable(adapter, true);
 	} else {
 		adapter->state = __I40EVF_DOWN;
+		wake_up(&adapter->down_waitqueue);
 	}
 
 	return;
 reset_err:
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
-	i40evf_close(adapter->netdev);
+	i40evf_close(netdev);
 }
 
 /**
@@ -1957,8 +1970,8 @@ static void i40evf_adminq_task(struct work_struct *work)
 		container_of(work, struct i40evf_adapter, adminq_task);
 	struct i40e_hw *hw = &adapter->hw;
 	struct i40e_arq_event_info event;
-	struct virtchnl_msg *v_msg;
-	i40e_status ret;
+	enum virtchnl_ops v_op;
+	i40e_status ret, v_ret;
 	u32 val, oldval;
 	u16 pending;
 
@@ -1970,15 +1983,15 @@ static void i40evf_adminq_task(struct work_struct *work)
 	if (!event.msg_buf)
 		goto out;
 
-	v_msg = (struct virtchnl_msg *)&event.desc;
 	do {
 		ret = i40evf_clean_arq_element(hw, &event, &pending);
-		if (ret || !v_msg->v_opcode)
+		v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high);
+		v_ret = (i40e_status)le32_to_cpu(event.desc.cookie_low);
+
+		if (ret || !v_op)
 			break; /* No event to process or error cleaning ARQ */
 
-		i40evf_virtchnl_completion(adapter, v_msg->v_opcode,
-					   (i40e_status)v_msg->v_retval,
-					   event.msg_buf,
+		i40evf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf,
 					   event.msg_len);
 		if (pending != 0)
 			memset(event.msg_buf, 0, I40EVF_MAX_AQ_BUF_SIZE);
@@ -2238,6 +2251,7 @@ err_setup_tx:
 static int i40evf_close(struct net_device *netdev)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	int status;
 
 	if (adapter->state <= __I40EVF_DOWN_PENDING)
 		return 0;
@@ -2255,7 +2269,18 @@ static int i40evf_close(struct net_device *netdev)
 	 * still active and can DMA into memory. Resources are cleared in
 	 * i40evf_virtchnl_completion() after we get confirmation from the PF
 	 * driver that the rings have been stopped.
+	 *
+	 * Also, we wait for state to transition to __I40EVF_DOWN before
+	 * returning. State change occurs in i40evf_virtchnl_completion() after
+	 * VF resources are released (which occurs after PF driver processes and
+	 * responds to admin queue commands).
 	 */
+
+	status = wait_event_timeout(adapter->down_waitqueue,
+				    adapter->state == __I40EVF_DOWN,
+				    msecs_to_jiffies(200));
+	if (!status)
+		netdev_warn(netdev, "Device resources not yet released\n");
 	return 0;
 }
 
@@ -2282,6 +2307,28 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu)
 }
 
 /**
+ * i40e_set_features - set the netdev feature flags
+ * @netdev: ptr to the netdev being adjusted
+ * @features: the feature set that the stack is suggesting
+ * Note: expects to be called while under rtnl_lock()
+ **/
+static int i40evf_set_features(struct net_device *netdev,
+			       netdev_features_t features)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+
+	if (!VLAN_ALLOWED(adapter))
+		return -EINVAL;
+
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING;
+	else
+		adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING;
+
+	return 0;
+}
+
+/**
  * i40evf_features_check - Validate encapsulated packet conforms to limits
  * @skb: skb buff
  * @netdev: This physical port's netdev
@@ -2356,7 +2403,7 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev,
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	features &= ~I40EVF_VLAN_FEATURES;
-	if (adapter->vf_res->vf_offload_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
+	if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
 		features |= I40EVF_VLAN_FEATURES;
 	return features;
 }
@@ -2374,6 +2421,7 @@ static const struct net_device_ops i40evf_netdev_ops = {
 	.ndo_vlan_rx_kill_vid	= i40evf_vlan_rx_kill_vid,
 	.ndo_features_check	= i40evf_features_check,
 	.ndo_fix_features	= i40evf_fix_features,
+	.ndo_set_features	= i40evf_set_features,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= i40evf_netpoll,
 #endif
@@ -2443,7 +2491,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 	/* advertise to stack only if offloads for encapsulated packets is
 	 * supported
 	 */
-	if (vfres->vf_offload_flags & VIRTCHNL_VF_OFFLOAD_ENCAP) {
+	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ENCAP) {
 		hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL	|
 				   NETIF_F_GSO_GRE		|
 				   NETIF_F_GSO_GRE_CSUM		|
@@ -2453,7 +2501,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 				   NETIF_F_GSO_PARTIAL		|
 				   0;
 
-		if (!(vfres->vf_offload_flags &
+		if (!(vfres->vf_cap_flags &
 		      VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM))
 			netdev->gso_partial_features |=
 				NETIF_F_GSO_UDP_TUNNEL_CSUM;
@@ -2481,7 +2529,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 	adapter->vsi.work_limit = I40E_DEFAULT_IRQ_WORK;
 	vsi->netdev = adapter->netdev;
 	vsi->qs_handle = adapter->vsi_res->qset_handle;
-	if (vfres->vf_offload_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
+	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
 		adapter->rss_key_size = vfres->rss_key_size;
 		adapter->rss_lut_size = vfres->rss_lut_size;
 	} else {
@@ -2625,7 +2673,7 @@ static void i40evf_init_task(struct work_struct *work)
 
 	/* MTU range: 68 - 9710 */
 	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = I40E_MAX_RXBUFFER - (ETH_HLEN + ETH_FCS_LEN);
+	netdev->max_mtu = I40E_MAX_RXBUFFER - I40E_PACKET_HDR_PAD;
 
 	if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
 		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
@@ -2649,7 +2697,7 @@ static void i40evf_init_task(struct work_struct *work)
 	if (err)
 		goto err_sw_init;
 	i40evf_map_rings_to_vectors(adapter);
-	if (adapter->vf_res->vf_offload_flags &
+	if (adapter->vf_res->vf_cap_flags &
 	    VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
 		adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE;
 
@@ -2683,6 +2731,7 @@ static void i40evf_init_task(struct work_struct *work)
 	adapter->state = __I40EVF_DOWN;
 	set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
 	i40evf_misc_irq_enable(adapter);
+	wake_up(&adapter->down_waitqueue);
 
 	adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL);
 	adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL);
@@ -2844,6 +2893,9 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	schedule_delayed_work(&adapter->init_task,
 			      msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
 
+	/* Setup the wait queue for indicating transition to down status */
+	init_waitqueue_head(&adapter->down_waitqueue);
+
 	return 0;
 
 err_ioremap:
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index d2bb250a71af..85876f4fb1fb 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -821,6 +821,46 @@ void i40evf_set_rss_lut(struct i40evf_adapter *adapter)
 }
 
 /**
+ * i40evf_enable_vlan_stripping
+ * @adapter: adapter structure
+ *
+ * Request VLAN header stripping to be enabled
+ **/
+void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter)
+{
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		dev_err(&adapter->pdev->dev, "Cannot enable stripping, command %d pending\n",
+			adapter->current_op);
+		return;
+	}
+	adapter->current_op = VIRTCHNL_OP_ENABLE_VLAN_STRIPPING;
+	adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING;
+	i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING,
+			   NULL, 0);
+}
+
+/**
+ * i40evf_disable_vlan_stripping
+ * @adapter: adapter structure
+ *
+ * Request VLAN header stripping to be disabled
+ **/
+void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter)
+{
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		dev_err(&adapter->pdev->dev, "Cannot disable stripping, command %d pending\n",
+			adapter->current_op);
+		return;
+	}
+	adapter->current_op = VIRTCHNL_OP_DISABLE_VLAN_STRIPPING;
+	adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING;
+	i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING,
+			   NULL, 0);
+}
+
+/**
  * i40evf_print_link_message - print link up or down
  * @adapter: adapter structure
  *
@@ -991,8 +1031,10 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 	case VIRTCHNL_OP_DISABLE_QUEUES:
 		i40evf_free_all_tx_resources(adapter);
 		i40evf_free_all_rx_resources(adapter);
-		if (adapter->state == __I40EVF_DOWN_PENDING)
+		if (adapter->state == __I40EVF_DOWN_PENDING) {
 			adapter->state = __I40EVF_DOWN;
+			wake_up(&adapter->down_waitqueue);
+		}
 		break;
 	case VIRTCHNL_OP_VERSION:
 	case VIRTCHNL_OP_CONFIG_IRQ_MAP: