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

Pull networking changes from David Miller:

1) Allow to dump, monitor, and change the bridge multicast database
   using netlink.  From Cong Wang.

2) RFC 5961 TCP blind data injection attack mitigation, from Eric
   Dumazet.

3) Networking user namespace support from Eric W. Biederman.

4) tuntap/virtio-net multiqueue support by Jason Wang.

5) Support for checksum offload of encapsulated packets (basically,
   tunneled traffic can still be checksummed by HW).  From Joseph
   Gasparakis.

6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
   Daniel Borkmann.

7) Bridge port parameters over netlink and BPDU blocking support
   from Stephen Hemminger.

8) Improve data access patterns during inet socket demux by rearranging
   socket layout, from Eric Dumazet.

9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
   Jon Maloy.

10) Update TCP socket hash sizing to be more in line with current day
    realities.  The existing heurstics were choosen a decade ago.
    From Eric Dumazet.

11) Fix races, queue bloat, and excessive wakeups in ATM and
    associated drivers, from Krzysztof Mazur and David Woodhouse.

12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
    in VXLAN driver, from David Stevens.

13) Add "oops_only" mode to netconsole, from Amerigo Wang.

14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
    allow DCB netlink to work on namespaces other than the initial
    namespace.  From John Fastabend.

15) Support PTP in the Tigon3 driver, from Matt Carlson.

16) tun/vhost zero copy fixes and improvements, plus turn it on
    by default, from Michael S. Tsirkin.

17) Support per-association statistics in SCTP, from Michele
    Baldessari.

And many, many, driver updates, cleanups, and improvements.  Too
numerous to mention individually.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  net/mlx4_en: Add support for destination MAC in steering rules
  net/mlx4_en: Use generic etherdevice.h functions.
  net: ethtool: Add destination MAC address to flow steering API
  bridge: add support of adding and deleting mdb entries
  bridge: notify mdb changes via netlink
  ndisc: Unexport ndisc_{build,send}_skb().
  uapi: add missing netconf.h to export list
  pkt_sched: avoid requeues if possible
  solos-pci: fix double-free of TX skb in DMA mode
  bnx2: Fix accidental reversions.
  bna: Driver Version Updated to 3.1.2.1
  bna: Firmware update
  bna: Add RX State
  bna: Rx Page Based Allocation
  bna: TX Intr Coalescing Fix
  bna: Tx and Rx Optimizations
  bna: Code Cleanup and Enhancements
  ath9k: check pdata variable before dereferencing it
  ath5k: RX timestamp is reported at end of frame
  ath9k_htc: RX timestamp is reported at end of frame
  ...

1 files changed, 79 insertions, 206 deletions

diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 83516e3369c9..f8408d6e961c 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -50,7 +50,6 @@
 #include <linux/etherdevice.h>
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
-#include <linux/inet_lro.h>
 #include <linux/dca.h>
 #include <linux/ip.h>
 #include <linux/inet.h>
@@ -96,8 +95,6 @@ MODULE_LICENSE("Dual BSD/GPL");
 
 #define MYRI10GE_EEPROM_STRINGS_SIZE 256
 #define MYRI10GE_MAX_SEND_DESC_TSO ((65536 / 2048) * 2)
-#define MYRI10GE_MAX_LRO_DESCRIPTORS 8
-#define MYRI10GE_LRO_MAX_PKTS 64
 
 #define MYRI10GE_NO_CONFIRM_DATA htonl(0xffffffff)
 #define MYRI10GE_NO_RESPONSE_RESULT 0xffffffff
@@ -165,8 +162,6 @@ struct myri10ge_rx_done {
 	dma_addr_t bus;
 	int cnt;
 	int idx;
-	struct net_lro_mgr lro_mgr;
-	struct net_lro_desc lro_desc[MYRI10GE_MAX_LRO_DESCRIPTORS];
 };
 
 struct myri10ge_slice_netstats {
@@ -338,11 +333,6 @@ static int myri10ge_debug = -1;	/* defaults above */
 module_param(myri10ge_debug, int, 0);
 MODULE_PARM_DESC(myri10ge_debug, "Debug level (0=none,...,16=all)");
 
-static int myri10ge_lro_max_pkts = MYRI10GE_LRO_MAX_PKTS;
-module_param(myri10ge_lro_max_pkts, int, S_IRUGO);
-MODULE_PARM_DESC(myri10ge_lro_max_pkts,
-		 "Number of LRO packets to be aggregated");
-
 static int myri10ge_fill_thresh = 256;
 module_param(myri10ge_fill_thresh, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(myri10ge_fill_thresh, "Number of empty rx slots allowed");
@@ -1197,36 +1187,6 @@ static inline void myri10ge_vlan_ip_csum(struct sk_buff *skb, __wsum hw_csum)
 	}
 }
 
-static inline void
-myri10ge_rx_skb_build(struct sk_buff *skb, u8 * va,
-		      struct skb_frag_struct *rx_frags, int len, int hlen)
-{
-	struct skb_frag_struct *skb_frags;
-
-	skb->len = skb->data_len = len;
-	/* attach the page(s) */
-
-	skb_frags = skb_shinfo(skb)->frags;
-	while (len > 0) {
-		memcpy(skb_frags, rx_frags, sizeof(*skb_frags));
-		len -= skb_frag_size(rx_frags);
-		skb_frags++;
-		rx_frags++;
-		skb_shinfo(skb)->nr_frags++;
-	}
-
-	/* pskb_may_pull is not available in irq context, but
-	 * skb_pull() (for ether_pad and eth_type_trans()) requires
-	 * the beginning of the packet in skb_headlen(), move it
-	 * manually */
-	skb_copy_to_linear_data(skb, va, hlen);
-	skb_shinfo(skb)->frags[0].page_offset += hlen;
-	skb_frag_size_sub(&skb_shinfo(skb)->frags[0], hlen);
-	skb->data_len -= hlen;
-	skb->tail += hlen;
-	skb_pull(skb, MXGEFW_PAD);
-}
-
 static void
 myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx,
 			int bytes, int watchdog)
@@ -1304,18 +1264,50 @@ myri10ge_unmap_rx_page(struct pci_dev *pdev,
 	}
 }
 
-#define MYRI10GE_HLEN 64	/* The number of bytes to copy from a
-				 * page into an skb */
+/*
+ * GRO does not support acceleration of tagged vlan frames, and
+ * this NIC does not support vlan tag offload, so we must pop
+ * the tag ourselves to be able to achieve GRO performance that
+ * is comparable to LRO.
+ */
+
+static inline void
+myri10ge_vlan_rx(struct net_device *dev, void *addr, struct sk_buff *skb)
+{
+	u8 *va;
+	struct vlan_ethhdr *veh;
+	struct skb_frag_struct *frag;
+	__wsum vsum;
+
+	va = addr;
+	va += MXGEFW_PAD;
+	veh = (struct vlan_ethhdr *)va;
+	if ((dev->features & NETIF_F_HW_VLAN_RX) == NETIF_F_HW_VLAN_RX &&
+	    veh->h_vlan_proto == htons(ETH_P_8021Q)) {
+		/* fixup csum if needed */
+		if (skb->ip_summed == CHECKSUM_COMPLETE) {
+			vsum = csum_partial(va + ETH_HLEN, VLAN_HLEN, 0);
+			skb->csum = csum_sub(skb->csum, vsum);
+		}
+		/* pop tag */
+		__vlan_hwaccel_put_tag(skb, ntohs(veh->h_vlan_TCI));
+		memmove(va + VLAN_HLEN, va, 2 * ETH_ALEN);
+		skb->len -= VLAN_HLEN;
+		skb->data_len -= VLAN_HLEN;
+		frag = skb_shinfo(skb)->frags;
+		frag->page_offset += VLAN_HLEN;
+		skb_frag_size_set(frag, skb_frag_size(frag) - VLAN_HLEN);
+	}
+}
 
 static inline int
-myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum,
-		 bool lro_enabled)
+myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum)
 {
 	struct myri10ge_priv *mgp = ss->mgp;
 	struct sk_buff *skb;
-	struct skb_frag_struct rx_frags[MYRI10GE_MAX_FRAGS_PER_FRAME];
+	struct skb_frag_struct *rx_frags;
 	struct myri10ge_rx_buf *rx;
-	int i, idx, hlen, remainder, bytes;
+	int i, idx, remainder, bytes;
 	struct pci_dev *pdev = mgp->pdev;
 	struct net_device *dev = mgp->dev;
 	u8 *va;
@@ -1332,67 +1324,48 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum,
 	idx = rx->cnt & rx->mask;
 	va = page_address(rx->info[idx].page) + rx->info[idx].page_offset;
 	prefetch(va);
+
+	skb = napi_get_frags(&ss->napi);
+	if (unlikely(skb == NULL)) {
+		ss->stats.rx_dropped++;
+		for (i = 0, remainder = len; remainder > 0; i++) {
+			myri10ge_unmap_rx_page(pdev, &rx->info[idx], bytes);
+			put_page(rx->info[idx].page);
+			rx->cnt++;
+			idx = rx->cnt & rx->mask;
+			remainder -= MYRI10GE_ALLOC_SIZE;
+		}
+		return 0;
+	}
+	rx_frags = skb_shinfo(skb)->frags;
 	/* Fill skb_frag_struct(s) with data from our receive */
 	for (i = 0, remainder = len; remainder > 0; i++) {
 		myri10ge_unmap_rx_page(pdev, &rx->info[idx], bytes);
-		__skb_frag_set_page(&rx_frags[i], rx->info[idx].page);
-		rx_frags[i].page_offset = rx->info[idx].page_offset;
-		if (remainder < MYRI10GE_ALLOC_SIZE)
-			skb_frag_size_set(&rx_frags[i], remainder);
-		else
-			skb_frag_size_set(&rx_frags[i], MYRI10GE_ALLOC_SIZE);
+		skb_fill_page_desc(skb, i, rx->info[idx].page,
+				   rx->info[idx].page_offset,
+				   remainder < MYRI10GE_ALLOC_SIZE ?
+				   remainder : MYRI10GE_ALLOC_SIZE);
 		rx->cnt++;
 		idx = rx->cnt & rx->mask;
 		remainder -= MYRI10GE_ALLOC_SIZE;
 	}
 
-	if (lro_enabled) {
-		rx_frags[0].page_offset += MXGEFW_PAD;
-		skb_frag_size_sub(&rx_frags[0], MXGEFW_PAD);
-		len -= MXGEFW_PAD;
-		lro_receive_frags(&ss->rx_done.lro_mgr, rx_frags,
-				  /* opaque, will come back in get_frag_header */
-				  len, len,
-				  (void *)(__force unsigned long)csum, csum);
-
-		return 1;
-	}
-
-	hlen = MYRI10GE_HLEN > len ? len : MYRI10GE_HLEN;
-
-	/* allocate an skb to attach the page(s) to. This is done
-	 * after trying LRO, so as to avoid skb allocation overheads */
-
-	skb = netdev_alloc_skb(dev, MYRI10GE_HLEN + 16);
-	if (unlikely(skb == NULL)) {
-		ss->stats.rx_dropped++;
-		do {
-			i--;
-			__skb_frag_unref(&rx_frags[i]);
-		} while (i != 0);
-		return 0;
-	}
+	/* remove padding */
+	rx_frags[0].page_offset += MXGEFW_PAD;
+	rx_frags[0].size -= MXGEFW_PAD;
+	len -= MXGEFW_PAD;
 
-	/* Attach the pages to the skb, and trim off any padding */
-	myri10ge_rx_skb_build(skb, va, rx_frags, len, hlen);
-	if (skb_frag_size(&skb_shinfo(skb)->frags[0]) <= 0) {
-		skb_frag_unref(skb, 0);
-		skb_shinfo(skb)->nr_frags = 0;
-	} else {
-		skb->truesize += bytes * skb_shinfo(skb)->nr_frags;
+	skb->len = len;
+	skb->data_len = len;
+	skb->truesize += len;
+	if (dev->features & NETIF_F_RXCSUM) {
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum = csum;
 	}
-	skb->protocol = eth_type_trans(skb, dev);
+	myri10ge_vlan_rx(mgp->dev, va, skb);
 	skb_record_rx_queue(skb, ss - &mgp->ss[0]);
 
-	if (dev->features & NETIF_F_RXCSUM) {
-		if ((skb->protocol == htons(ETH_P_IP)) ||
-		    (skb->protocol == htons(ETH_P_IPV6))) {
-			skb->csum = csum;
-			skb->ip_summed = CHECKSUM_COMPLETE;
-		} else
-			myri10ge_vlan_ip_csum(skb, csum);
-	}
-	netif_receive_skb(skb);
+	napi_gro_frags(&ss->napi);
 	return 1;
 }
 
@@ -1480,18 +1453,11 @@ myri10ge_clean_rx_done(struct myri10ge_slice_state *ss, int budget)
 	u16 length;
 	__wsum checksum;
 
-	/*
-	 * Prevent compiler from generating more than one ->features memory
-	 * access to avoid theoretical race condition with functions that
-	 * change NETIF_F_LRO flag at runtime.
-	 */
-	bool lro_enabled = !!(ACCESS_ONCE(mgp->dev->features) & NETIF_F_LRO);
-
 	while (rx_done->entry[idx].length != 0 && work_done < budget) {
 		length = ntohs(rx_done->entry[idx].length);
 		rx_done->entry[idx].length = 0;
 		checksum = csum_unfold(rx_done->entry[idx].checksum);
-		rx_ok = myri10ge_rx_done(ss, length, checksum, lro_enabled);
+		rx_ok = myri10ge_rx_done(ss, length, checksum);
 		rx_packets += rx_ok;
 		rx_bytes += rx_ok * (unsigned long)length;
 		cnt++;
@@ -1503,9 +1469,6 @@ myri10ge_clean_rx_done(struct myri10ge_slice_state *ss, int budget)
 	ss->stats.rx_packets += rx_packets;
 	ss->stats.rx_bytes += rx_bytes;
 
-	if (lro_enabled)
-		lro_flush_all(&rx_done->lro_mgr);
-
 	/* restock receive rings if needed */
 	if (ss->rx_small.fill_cnt - ss->rx_small.cnt < myri10ge_fill_thresh)
 		myri10ge_alloc_rx_pages(mgp, &ss->rx_small,
@@ -1779,7 +1742,6 @@ static const char myri10ge_gstrings_slice_stats[][ETH_GSTRING_LEN] = {
 	"tx_pkt_start", "tx_pkt_done", "tx_req", "tx_done",
 	"rx_small_cnt", "rx_big_cnt",
 	"wake_queue", "stop_queue", "tx_linearized",
-	"LRO aggregated", "LRO flushed", "LRO avg aggr", "LRO no_desc",
 };
 
 #define MYRI10GE_NET_STATS_LEN      21
@@ -1880,14 +1842,6 @@ myri10ge_get_ethtool_stats(struct net_device *netdev,
 		data[i++] = (unsigned int)ss->tx.wake_queue;
 		data[i++] = (unsigned int)ss->tx.stop_queue;
 		data[i++] = (unsigned int)ss->tx.linearized;
-		data[i++] = ss->rx_done.lro_mgr.stats.aggregated;
-		data[i++] = ss->rx_done.lro_mgr.stats.flushed;
-		if (ss->rx_done.lro_mgr.stats.flushed)
-			data[i++] = ss->rx_done.lro_mgr.stats.aggregated /
-			    ss->rx_done.lro_mgr.stats.flushed;
-		else
-			data[i++] = 0;
-		data[i++] = ss->rx_done.lro_mgr.stats.no_desc;
 	}
 }
 
@@ -1931,7 +1885,7 @@ static int myri10ge_led(struct myri10ge_priv *mgp, int on)
 	}
 	if (!on)
 		pattern = swab32(readl(mgp->sram + pattern_off + 4));
-	writel(htonl(pattern), mgp->sram + pattern_off);
+	writel(swab32(pattern), mgp->sram + pattern_off);
 	return 0;
 }
 
@@ -2271,67 +2225,6 @@ static void myri10ge_free_irq(struct myri10ge_priv *mgp)
 		pci_disable_msix(pdev);
 }
 
-static int
-myri10ge_get_frag_header(struct skb_frag_struct *frag, void **mac_hdr,
-			 void **ip_hdr, void **tcpudp_hdr,
-			 u64 * hdr_flags, void *priv)
-{
-	struct ethhdr *eh;
-	struct vlan_ethhdr *veh;
-	struct iphdr *iph;
-	u8 *va = skb_frag_address(frag);
-	unsigned long ll_hlen;
-	/* passed opaque through lro_receive_frags() */
-	__wsum csum = (__force __wsum) (unsigned long)priv;
-
-	/* find the mac header, aborting if not IPv4 */
-
-	eh = (struct ethhdr *)va;
-	*mac_hdr = eh;
-	ll_hlen = ETH_HLEN;
-	if (eh->h_proto != htons(ETH_P_IP)) {
-		if (eh->h_proto == htons(ETH_P_8021Q)) {
-			veh = (struct vlan_ethhdr *)va;
-			if (veh->h_vlan_encapsulated_proto != htons(ETH_P_IP))
-				return -1;
-
-			ll_hlen += VLAN_HLEN;
-
-			/*
-			 *  HW checksum starts ETH_HLEN bytes into
-			 *  frame, so we must subtract off the VLAN
-			 *  header's checksum before csum can be used
-			 */
-			csum = csum_sub(csum, csum_partial(va + ETH_HLEN,
-							   VLAN_HLEN, 0));
-		} else {
-			return -1;
-		}
-	}
-	*hdr_flags = LRO_IPV4;
-
-	iph = (struct iphdr *)(va + ll_hlen);
-	*ip_hdr = iph;
-	if (iph->protocol != IPPROTO_TCP)
-		return -1;
-	if (ip_is_fragment(iph))
-		return -1;
-	*hdr_flags |= LRO_TCP;
-	*tcpudp_hdr = (u8 *) (*ip_hdr) + (iph->ihl << 2);
-
-	/* verify the IP checksum */
-	if (unlikely(ip_fast_csum((u8 *) iph, iph->ihl)))
-		return -1;
-
-	/* verify the  checksum */
-	if (unlikely(csum_tcpudp_magic(iph->saddr, iph->daddr,
-				       ntohs(iph->tot_len) - (iph->ihl << 2),
-				       IPPROTO_TCP, csum)))
-		return -1;
-
-	return 0;
-}
-
 static int myri10ge_get_txrx(struct myri10ge_priv *mgp, int slice)
 {
 	struct myri10ge_cmd cmd;
@@ -2401,8 +2294,7 @@ static int myri10ge_open(struct net_device *dev)
 	struct myri10ge_priv *mgp = netdev_priv(dev);
 	struct myri10ge_cmd cmd;
 	int i, status, big_pow2, slice;
-	u8 *itable;
-	struct net_lro_mgr *lro_mgr;
+	u8 __iomem *itable;
 
 	if (mgp->running != MYRI10GE_ETH_STOPPED)
 		return -EBUSY;
@@ -2513,19 +2405,6 @@ static int myri10ge_open(struct net_device *dev)
 			goto abort_with_rings;
 		}
 
-		lro_mgr = &ss->rx_done.lro_mgr;
-		lro_mgr->dev = dev;
-		lro_mgr->features = LRO_F_NAPI;
-		lro_mgr->ip_summed = CHECKSUM_COMPLETE;
-		lro_mgr->ip_summed_aggr = CHECKSUM_UNNECESSARY;
-		lro_mgr->max_desc = MYRI10GE_MAX_LRO_DESCRIPTORS;
-		lro_mgr->lro_arr = ss->rx_done.lro_desc;
-		lro_mgr->get_frag_header = myri10ge_get_frag_header;
-		lro_mgr->max_aggr = myri10ge_lro_max_pkts;
-		lro_mgr->frag_align_pad = 2;
-		if (lro_mgr->max_aggr > MAX_SKB_FRAGS)
-			lro_mgr->max_aggr = MAX_SKB_FRAGS;
-
 		/* must happen prior to any irq */
 		napi_enable(&(ss)->napi);
 	}
@@ -2878,7 +2757,7 @@ again:
 					flags_next |= next_is_first *
 					    MXGEFW_FLAGS_FIRST;
 					rdma_count |= -(chop | next_is_first);
-					rdma_count += chop & !next_is_first;
+					rdma_count += chop & ~next_is_first;
 				} else if (likely(cum_len_next >= 0)) {	/* header ends */
 					int small;
 
@@ -3143,15 +3022,6 @@ static int myri10ge_set_mac_address(struct net_device *dev, void *addr)
 	return 0;
 }
 
-static netdev_features_t myri10ge_fix_features(struct net_device *dev,
-	netdev_features_t features)
-{
-	if (!(features & NETIF_F_RXCSUM))
-		features &= ~NETIF_F_LRO;
-
-	return features;
-}
-
 static int myri10ge_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct myri10ge_priv *mgp = netdev_priv(dev);
@@ -3878,7 +3748,6 @@ static const struct net_device_ops myri10ge_netdev_ops = {
 	.ndo_get_stats64	= myri10ge_get_stats,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= myri10ge_change_mtu,
-	.ndo_fix_features	= myri10ge_fix_features,
 	.ndo_set_rx_mode	= myri10ge_set_multicast_list,
 	.ndo_set_mac_address	= myri10ge_set_mac_address,
 };
@@ -3967,9 +3836,9 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto abort_with_mtrr;
 	}
 	hdr_offset =
-	    ntohl(__raw_readl(mgp->sram + MCP_HEADER_PTR_OFFSET)) & 0xffffc;
+	    swab32(readl(mgp->sram + MCP_HEADER_PTR_OFFSET)) & 0xffffc;
 	ss_offset = hdr_offset + offsetof(struct mcp_gen_header, string_specs);
-	mgp->sram_size = ntohl(__raw_readl(mgp->sram + ss_offset));
+	mgp->sram_size = swab32(readl(mgp->sram + ss_offset));
 	if (mgp->sram_size > mgp->board_span ||
 	    mgp->sram_size <= MYRI10GE_FW_OFFSET) {
 		dev_err(&pdev->dev,
@@ -4018,7 +3887,11 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	netdev->netdev_ops = &myri10ge_netdev_ops;
 	netdev->mtu = myri10ge_initial_mtu;
-	netdev->hw_features = mgp->features | NETIF_F_LRO | NETIF_F_RXCSUM;
+	netdev->hw_features = mgp->features | NETIF_F_RXCSUM;
+
+	/* fake NETIF_F_HW_VLAN_RX for good GRO performance */
+	netdev->hw_features |= NETIF_F_HW_VLAN_RX;
+
 	netdev->features = netdev->hw_features;
 
 	if (dac_enabled)