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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 46 insertions, 26 deletions

diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 84ab9eea2768..1b0661e3573b 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -28,7 +28,7 @@
 
 #include "fm10k.h"
 
-#define DRV_VERSION	"0.12.2-k"
+#define DRV_VERSION	"0.15.2-k"
 const char fm10k_driver_version[] = DRV_VERSION;
 char fm10k_driver_name[] = "fm10k";
 static const char fm10k_driver_string[] =
@@ -41,6 +41,9 @@ MODULE_DESCRIPTION("Intel(R) Ethernet Switch Host Interface Driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 
+/* single workqueue for entire fm10k driver */
+struct workqueue_struct *fm10k_workqueue = NULL;
+
 /**
  * fm10k_init_module - Driver Registration Routine
  *
@@ -52,6 +55,10 @@ static int __init fm10k_init_module(void)
 	pr_info("%s - version %s\n", fm10k_driver_string, fm10k_driver_version);
 	pr_info("%s\n", fm10k_copyright);
 
+	/* create driver workqueue */
+	if (!fm10k_workqueue)
+		fm10k_workqueue = create_workqueue("fm10k");
+
 	fm10k_dbg_init();
 
 	return fm10k_register_pci_driver();
@@ -69,6 +76,11 @@ static void __exit fm10k_exit_module(void)
 	fm10k_unregister_pci_driver();
 
 	fm10k_dbg_exit();
+
+	/* destroy driver workqueue */
+	flush_workqueue(fm10k_workqueue);
+	destroy_workqueue(fm10k_workqueue);
+	fm10k_workqueue = NULL;
 }
 module_exit(fm10k_exit_module);
 
@@ -209,7 +221,7 @@ static inline bool fm10k_page_is_reserved(struct page *page)
 
 static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer,
 				    struct page *page,
-				    unsigned int truesize)
+				    unsigned int __maybe_unused truesize)
 {
 	/* avoid re-using remote pages */
 	if (unlikely(fm10k_page_is_reserved(page)))
@@ -240,7 +252,6 @@ static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer,
 
 /**
  * fm10k_add_rx_frag - Add contents of Rx buffer to sk_buff
- * @rx_ring: rx descriptor ring to transact packets on
  * @rx_buffer: buffer containing page to add
  * @rx_desc: descriptor containing length of buffer written by hardware
  * @skb: sk_buff to place the data into
@@ -253,8 +264,7 @@ static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer,
  * The function will then update the page offset if necessary and return
  * true if the buffer can be reused by the interface.
  **/
-static bool fm10k_add_rx_frag(struct fm10k_ring *rx_ring,
-			      struct fm10k_rx_buffer *rx_buffer,
+static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer,
 			      union fm10k_rx_desc *rx_desc,
 			      struct sk_buff *skb)
 {
@@ -330,7 +340,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring,
 				      DMA_FROM_DEVICE);
 
 	/* pull page into skb */
-	if (fm10k_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) {
+	if (fm10k_add_rx_frag(rx_buffer, rx_desc, skb)) {
 		/* hand second half of page back to the ring */
 		fm10k_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
@@ -412,7 +422,7 @@ static void fm10k_rx_hwtstamp(struct fm10k_ring *rx_ring,
 }
 
 static void fm10k_type_trans(struct fm10k_ring *rx_ring,
-			     union fm10k_rx_desc *rx_desc,
+			     union fm10k_rx_desc __maybe_unused *rx_desc,
 			     struct sk_buff *skb)
 {
 	struct net_device *dev = rx_ring->netdev;
@@ -509,8 +519,6 @@ static bool fm10k_is_non_eop(struct fm10k_ring *rx_ring,
 
 /**
  * fm10k_pull_tail - fm10k specific version of skb_pull_tail
- * @rx_ring: rx descriptor ring packet is being transacted on
- * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being adjusted
  *
  * This function is an fm10k specific version of __pskb_pull_tail.  The
@@ -520,9 +528,7 @@ static bool fm10k_is_non_eop(struct fm10k_ring *rx_ring,
  * As a result we can do things like drop a frag and maintain an accurate
  * truesize for the skb.
  */
-static void fm10k_pull_tail(struct fm10k_ring *rx_ring,
-			    union fm10k_rx_desc *rx_desc,
-			    struct sk_buff *skb)
+static void fm10k_pull_tail(struct sk_buff *skb)
 {
 	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
 	unsigned char *va;
@@ -576,7 +582,7 @@ static bool fm10k_cleanup_headers(struct fm10k_ring *rx_ring,
 
 	/* place header in linear portion of buffer */
 	if (skb_is_nonlinear(skb))
-		fm10k_pull_tail(rx_ring, rx_desc, skb);
+		fm10k_pull_tail(skb);
 
 	/* if eth_skb_pad returns an error the skb was freed */
 	if (eth_skb_pad(skb))
@@ -711,10 +717,6 @@ static struct ethhdr *fm10k_gre_is_nvgre(struct sk_buff *skb)
 	if (nvgre_hdr->flags & FM10K_NVGRE_RESERVED0_FLAGS)
 		return NULL;
 
-	/* verify protocol is transparent Ethernet bridging */
-	if (nvgre_hdr->proto != htons(ETH_P_TEB))
-		return NULL;
-
 	/* report start of ethernet header */
 	if (nvgre_hdr->flags & NVGRE_TNI)
 		return (struct ethhdr *)(nvgre_hdr + 1);
@@ -722,15 +724,13 @@ static struct ethhdr *fm10k_gre_is_nvgre(struct sk_buff *skb)
 	return (struct ethhdr *)(&nvgre_hdr->tni);
 }
 
-static __be16 fm10k_tx_encap_offload(struct sk_buff *skb)
+__be16 fm10k_tx_encap_offload(struct sk_buff *skb)
 {
+	u8 l4_hdr = 0, inner_l4_hdr = 0, inner_l4_hlen;
 	struct ethhdr *eth_hdr;
-	u8 l4_hdr = 0;
 
-/* fm10k supports 184 octets of outer+inner headers. Minus 20 for inner L4. */
-#define FM10K_MAX_ENCAP_TRANSPORT_OFFSET	164
-	if (skb_inner_transport_header(skb) - skb_mac_header(skb) >
-	    FM10K_MAX_ENCAP_TRANSPORT_OFFSET)
+	if (skb->inner_protocol_type != ENCAP_TYPE_ETHER ||
+	    skb->inner_protocol != htons(ETH_P_TEB))
 		return 0;
 
 	switch (vlan_get_protocol(skb)) {
@@ -760,12 +760,33 @@ static __be16 fm10k_tx_encap_offload(struct sk_buff *skb)
 
 	switch (eth_hdr->h_proto) {
 	case htons(ETH_P_IP):
+		inner_l4_hdr = inner_ip_hdr(skb)->protocol;
+		break;
 	case htons(ETH_P_IPV6):
+		inner_l4_hdr = inner_ipv6_hdr(skb)->nexthdr;
+		break;
+	default:
+		return 0;
+	}
+
+	switch (inner_l4_hdr) {
+	case IPPROTO_TCP:
+		inner_l4_hlen = inner_tcp_hdrlen(skb);
+		break;
+	case IPPROTO_UDP:
+		inner_l4_hlen = 8;
 		break;
 	default:
 		return 0;
 	}
 
+	/* The hardware allows tunnel offloads only if the combined inner and
+	 * outer header is 184 bytes or less
+	 */
+	if (skb_inner_transport_header(skb) + inner_l4_hlen -
+	    skb_mac_header(skb) > FM10K_TUNNEL_HEADER_LENGTH)
+		return 0;
+
 	return eth_hdr->h_proto;
 }
 
@@ -934,10 +955,10 @@ static int __fm10k_maybe_stop_tx(struct fm10k_ring *tx_ring, u16 size)
 {
 	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 
+	/* Memory barrier before checking head and tail */
 	smp_mb();
 
-	/* We need to check again in a case another CPU has just
-	 * made room available. */
+	/* Check again in a case another CPU has just made room available */
 	if (likely(fm10k_desc_unused(tx_ring) < size))
 		return -EBUSY;
 
@@ -1182,7 +1203,6 @@ void fm10k_tx_timeout_reset(struct fm10k_intfc *interface)
 {
 	/* Do the reset outside of interrupt context */
 	if (!test_bit(__FM10K_DOWN, &interface->state)) {
-		netdev_err(interface->netdev, "Reset interface\n");
 		interface->tx_timeout_count++;
 		interface->flags |= FM10K_FLAG_RESET_REQUESTED;
 		fm10k_service_event_schedule(interface);