1 files changed, 110 insertions, 218 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 5384ed30298a..d2df4e3d1032 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -84,7 +84,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = {
  * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
  *   Class, Class Mask, private data (not used) }
  */
-static DEFINE_PCI_DEVICE_TABLE(ixgbe_pci_tbl) = {
+static const struct pci_device_id ixgbe_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598), board_82598 },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_DUAL_PORT), board_82598 },
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_SINGLE_PORT), board_82598 },
@@ -440,7 +440,7 @@ static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = {
 	{IXGBE_TXDCTL(0), "TXDCTL"},
 
 	/* List Terminator */
-	{}
+	{ .name = NULL }
 };
 
 
@@ -1094,7 +1094,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		total_packets += tx_buffer->gso_segs;
 
 		/* free the skb */
-		dev_kfree_skb_any(tx_buffer->skb);
+		dev_consume_skb_any(tx_buffer->skb);
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -1521,120 +1521,6 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 		ixgbe_release_rx_desc(rx_ring, i);
 }
 
-/**
- * ixgbe_get_headlen - determine size of header for RSC/LRO/GRO/FCOE
- * @data: pointer to the start of the headers
- * @max_len: total length of section to find headers in
- *
- * This function is meant to determine the length of headers that will
- * be recognized by hardware for LRO, GRO, and RSC offloads.  The main
- * motivation of doing this is to only perform one pull for IPv4 TCP
- * packets so that we can do basic things like calculating the gso_size
- * based on the average data per packet.
- **/
-static unsigned int ixgbe_get_headlen(unsigned char *data,
-				      unsigned int max_len)
-{
-	union {
-		unsigned char *network;
-		/* l2 headers */
-		struct ethhdr *eth;
-		struct vlan_hdr *vlan;
-		/* l3 headers */
-		struct iphdr *ipv4;
-		struct ipv6hdr *ipv6;
-	} hdr;
-	__be16 protocol;
-	u8 nexthdr = 0;	/* default to not TCP */
-	u8 hlen;
-
-	/* this should never happen, but better safe than sorry */
-	if (max_len < ETH_HLEN)
-		return max_len;
-
-	/* initialize network frame pointer */
-	hdr.network = data;
-
-	/* set first protocol and move network header forward */
-	protocol = hdr.eth->h_proto;
-	hdr.network += ETH_HLEN;
-
-	/* handle any vlan tag if present */
-	if (protocol == htons(ETH_P_8021Q)) {
-		if ((hdr.network - data) > (max_len - VLAN_HLEN))
-			return max_len;
-
-		protocol = hdr.vlan->h_vlan_encapsulated_proto;
-		hdr.network += VLAN_HLEN;
-	}
-
-	/* handle L3 protocols */
-	if (protocol == htons(ETH_P_IP)) {
-		if ((hdr.network - data) > (max_len - sizeof(struct iphdr)))
-			return max_len;
-
-		/* access ihl as a u8 to avoid unaligned access on ia64 */
-		hlen = (hdr.network[0] & 0x0F) << 2;
-
-		/* verify hlen meets minimum size requirements */
-		if (hlen < sizeof(struct iphdr))
-			return hdr.network - data;
-
-		/* record next protocol if header is present */
-		if (!(hdr.ipv4->frag_off & htons(IP_OFFSET)))
-			nexthdr = hdr.ipv4->protocol;
-	} else if (protocol == htons(ETH_P_IPV6)) {
-		if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr)))
-			return max_len;
-
-		/* record next protocol */
-		nexthdr = hdr.ipv6->nexthdr;
-		hlen = sizeof(struct ipv6hdr);
-#ifdef IXGBE_FCOE
-	} else if (protocol == htons(ETH_P_FCOE)) {
-		if ((hdr.network - data) > (max_len - FCOE_HEADER_LEN))
-			return max_len;
-		hlen = FCOE_HEADER_LEN;
-#endif
-	} else {
-		return hdr.network - data;
-	}
-
-	/* relocate pointer to start of L4 header */
-	hdr.network += hlen;
-
-	/* finally sort out TCP/UDP */
-	if (nexthdr == IPPROTO_TCP) {
-		if ((hdr.network - data) > (max_len - sizeof(struct tcphdr)))
-			return max_len;
-
-		/* access doff as a u8 to avoid unaligned access on ia64 */
-		hlen = (hdr.network[12] & 0xF0) >> 2;
-
-		/* verify hlen meets minimum size requirements */
-		if (hlen < sizeof(struct tcphdr))
-			return hdr.network - data;
-
-		hdr.network += hlen;
-	} else if (nexthdr == IPPROTO_UDP) {
-		if ((hdr.network - data) > (max_len - sizeof(struct udphdr)))
-			return max_len;
-
-		hdr.network += sizeof(struct udphdr);
-	}
-
-	/*
-	 * If everything has gone correctly hdr.network should be the
-	 * data section of the packet and will be the end of the header.
-	 * If not then it probably represents the end of the last recognized
-	 * header.
-	 */
-	if ((hdr.network - data) < max_len)
-		return hdr.network - data;
-	else
-		return max_len;
-}
-
 static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring,
 				   struct sk_buff *skb)
 {
@@ -1793,7 +1679,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
 	 * we need the header to contain the greater of either ETH_HLEN or
 	 * 60 bytes if the skb->len is less than 60 for skb_pad.
 	 */
-	pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE);
+	pull_len = eth_get_headlen(va, IXGBE_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
@@ -1979,12 +1865,10 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 	/* flip page offset to other buffer */
 	rx_buffer->page_offset ^= truesize;
 
-	/*
-	 * since we are the only owner of the page and we need to
-	 * increment it, just set the value to 2 in order to avoid
-	 * an unecessary locked operation
+	/* Even if we own the page, we are not allowed to use atomic_set()
+	 * This would break get_page_unless_zero() users.
 	 */
-	atomic_set(&page->_count, 2);
+	atomic_inc(&page->_count);
 #else
 	/* move offset up to the next cache line */
 	rx_buffer->page_offset += truesize;
@@ -2191,9 +2075,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	q_vector->rx.total_packets += total_rx_packets;
 	q_vector->rx.total_bytes += total_rx_bytes;
 
-	if (cleaned_count)
-		ixgbe_alloc_rx_buffers(rx_ring, cleaned_count);
-
 	return total_rx_packets;
 }
 
@@ -3099,11 +2980,7 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
 	 * to or less than the number of on chip descriptors, which is
 	 * currently 40.
 	 */
-#if IS_ENABLED(CONFIG_BQL)
 	if (!ring->q_vector || (ring->q_vector->itr < IXGBE_100K_ITR))
-#else
-	if (!ring->q_vector || (ring->q_vector->itr < 8))
-#endif
 		txdctl |= (1 << 16);	/* WTHRESH = 1 */
 	else
 		txdctl |= (8 << 16);	/* WTHRESH = 8 */
@@ -4444,8 +4321,8 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 				IXGBE_CB(skb)->page_released = false;
 			}
 			dev_kfree_skb(skb);
+			rx_buffer->skb = NULL;
 		}
-		rx_buffer->skb = NULL;
 		if (rx_buffer->dma)
 			dma_unmap_page(dev, rx_buffer->dma,
 				       ixgbe_rx_pg_size(rx_ring),
@@ -5300,15 +5177,15 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
 {
 	struct device *dev = tx_ring->dev;
 	int orig_node = dev_to_node(dev);
-	int numa_node = -1;
+	int ring_node = -1;
 	int size;
 
 	size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
 
 	if (tx_ring->q_vector)
-		numa_node = tx_ring->q_vector->numa_node;
+		ring_node = tx_ring->q_vector->numa_node;
 
-	tx_ring->tx_buffer_info = vzalloc_node(size, numa_node);
+	tx_ring->tx_buffer_info = vzalloc_node(size, ring_node);
 	if (!tx_ring->tx_buffer_info)
 		tx_ring->tx_buffer_info = vzalloc(size);
 	if (!tx_ring->tx_buffer_info)
@@ -5320,7 +5197,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
 	tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
 
-	set_dev_node(dev, numa_node);
+	set_dev_node(dev, ring_node);
 	tx_ring->desc = dma_alloc_coherent(dev,
 					   tx_ring->size,
 					   &tx_ring->dma,
@@ -5384,15 +5261,15 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
 	int orig_node = dev_to_node(dev);
-	int numa_node = -1;
+	int ring_node = -1;
 	int size;
 
 	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
 
 	if (rx_ring->q_vector)
-		numa_node = rx_ring->q_vector->numa_node;
+		ring_node = rx_ring->q_vector->numa_node;
 
-	rx_ring->rx_buffer_info = vzalloc_node(size, numa_node);
+	rx_ring->rx_buffer_info = vzalloc_node(size, ring_node);
 	if (!rx_ring->rx_buffer_info)
 		rx_ring->rx_buffer_info = vzalloc(size);
 	if (!rx_ring->rx_buffer_info)
@@ -5404,7 +5281,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
 	rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
 
-	set_dev_node(dev, numa_node);
+	set_dev_node(dev, ring_node);
 	rx_ring->desc = dma_alloc_coherent(dev,
 					   rx_ring->size,
 					   &rx_ring->dma,
@@ -6319,25 +6196,55 @@ static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *adapter)
 	ixgbe_ping_all_vfs(adapter);
 }
 
+static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
+
+		if (tx_ring->next_to_use != tx_ring->next_to_clean)
+			return true;
+	}
+
+	return false;
+}
+
+static bool ixgbe_vf_tx_pending(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
+	u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask);
+
+	int i, j;
+
+	if (!adapter->num_vfs)
+		return false;
+
+	for (i = 0; i < adapter->num_vfs; i++) {
+		for (j = 0; j < q_per_pool; j++) {
+			u32 h, t;
+
+			h = IXGBE_READ_REG(hw, IXGBE_PVFTDHN(q_per_pool, i, j));
+			t = IXGBE_READ_REG(hw, IXGBE_PVFTDTN(q_per_pool, i, j));
+
+			if (h != t)
+				return true;
+		}
+	}
+
+	return false;
+}
+
 /**
  * ixgbe_watchdog_flush_tx - flush queues on link down
  * @adapter: pointer to the device adapter structure
  **/
 static void ixgbe_watchdog_flush_tx(struct ixgbe_adapter *adapter)
 {
-	int i;
-	int some_tx_pending = 0;
-
 	if (!netif_carrier_ok(adapter->netdev)) {
-		for (i = 0; i < adapter->num_tx_queues; i++) {
-			struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
-			if (tx_ring->next_to_use != tx_ring->next_to_clean) {
-				some_tx_pending = 1;
-				break;
-			}
-		}
-
-		if (some_tx_pending) {
+		if (ixgbe_ring_tx_pending(adapter) ||
+		    ixgbe_vf_tx_pending(adapter)) {
 			/* We've lost link, so the controller stops DMA,
 			 * but we've got queued Tx work that's never going
 			 * to get done, so reset controller to flush Tx.
@@ -6837,6 +6744,36 @@ static void ixgbe_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc,
 	tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
 }
 
+static int __ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
+{
+	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+
+	/* Herbert's original patch had:
+	 *  smp_mb__after_netif_stop_queue();
+	 * but since that doesn't exist yet, just open code it.
+	 */
+	smp_mb();
+
+	/* We need to check again in a case another CPU has just
+	 * made room available.
+	 */
+	if (likely(ixgbe_desc_unused(tx_ring) < size))
+		return -EBUSY;
+
+	/* A reprieve! - use start_queue because it doesn't call schedule */
+	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
+	++tx_ring->tx_stats.restart_queue;
+	return 0;
+}
+
+static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
+{
+	if (likely(ixgbe_desc_unused(tx_ring) >= size))
+		return 0;
+
+	return __ixgbe_maybe_stop_tx(tx_ring, size);
+}
+
 #define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \
 		       IXGBE_TXD_CMD_RS)
 
@@ -6958,8 +6895,12 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 
 	tx_ring->next_to_use = i;
 
-	/* notify HW of packet */
-	ixgbe_write_tail(tx_ring, i);
+	ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+		/* notify HW of packet */
+		ixgbe_write_tail(tx_ring, i);
+	}
 
 	return;
 dma_error:
@@ -7067,32 +7008,6 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 					      input, common, ring->queue_index);
 }
 
-static int __ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
-{
-	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
-	/* Herbert's original patch had:
-	 *  smp_mb__after_netif_stop_queue();
-	 * but since that doesn't exist yet, just open code it. */
-	smp_mb();
-
-	/* We need to check again in a case another CPU has just
-	 * made room available. */
-	if (likely(ixgbe_desc_unused(tx_ring) < size))
-		return -EBUSY;
-
-	/* A reprieve! - use start_queue because it doesn't call schedule */
-	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
-	++tx_ring->tx_stats.restart_queue;
-	return 0;
-}
-
-static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
-{
-	if (likely(ixgbe_desc_unused(tx_ring) >= size))
-		return 0;
-	return __ixgbe_maybe_stop_tx(tx_ring, size);
-}
-
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 			      void *accel_priv, select_queue_fallback_t fallback)
 {
@@ -7187,9 +7102,10 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 		tx_flags |= IXGBE_TX_FLAGS_SW_VLAN;
 	}
 
-	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
-		     !test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS,
-					    &adapter->state))) {
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    adapter->ptp_clock &&
+	    !test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS,
+				   &adapter->state)) {
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		tx_flags |= IXGBE_TX_FLAGS_TSTAMP;
 
@@ -7261,8 +7177,6 @@ xmit_fcoe:
 #endif /* IXGBE_FCOE */
 	ixgbe_tx_map(tx_ring, first, hdr_len);
 
-	ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
-
 	return NETDEV_TX_OK;
 
 out_drop:
@@ -7735,39 +7649,13 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			     const unsigned char *addr,
 			     u16 flags)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
-	int err;
-
-	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
-		return ndo_dflt_fdb_add(ndm, tb, dev, addr, flags);
-
-	/* Hardware does not support aging addresses so if a
-	 * ndm_state is given only allow permanent addresses
-	 */
-	if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
-		pr_info("%s: FDB only supports static addresses\n",
-			ixgbe_driver_name);
-		return -EINVAL;
-	}
-
+	/* guarantee we can provide a unique filter for the unicast address */
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
-		u32 rar_uc_entries = IXGBE_MAX_PF_MACVLANS;
-
-		if (netdev_uc_count(dev) < rar_uc_entries)
-			err = dev_uc_add_excl(dev, addr);
-		else
-			err = -ENOMEM;
-	} else if (is_multicast_ether_addr(addr)) {
-		err = dev_mc_add_excl(dev, addr);
-	} else {
-		err = -EINVAL;
+		if (IXGBE_MAX_PF_MACVLANS <= netdev_uc_count(dev))
+			return -ENOMEM;
 	}
 
-	/* Only return duplicate errors if NLM_F_EXCL is set */
-	if (err == -EEXIST && !(flags & NLM_F_EXCL))
-		err = 0;
-
-	return err;
+	return ndo_dflt_fdb_add(ndm, tb, dev, addr, flags);
 }
 
 static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
@@ -7830,9 +7718,17 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 {
 	struct ixgbe_fwd_adapter *fwd_adapter = NULL;
 	struct ixgbe_adapter *adapter = netdev_priv(pdev);
+	int used_pools = adapter->num_vfs + adapter->num_rx_pools;
 	unsigned int limit;
 	int pool, err;
 
+	/* Hardware has a limited number of available pools. Each VF, and the
+	 * PF require a pool. Check to ensure we don't attempt to use more
+	 * then the available number of pools.
+	 */
+	if (used_pools >= IXGBE_MAX_VF_FUNCTIONS)
+		return ERR_PTR(-EINVAL);
+
 #ifdef CONFIG_RPS
 	if (vdev->num_rx_queues != vdev->num_tx_queues) {
 		netdev_info(pdev, "%s: Only supports a single queue count for TX and RX\n",
@@ -8080,7 +7976,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct ixgbe_adapter *adapter = NULL;
 	struct ixgbe_hw *hw;
 	const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data];
-	static int cards_found;
 	int i, err, pci_using_dac, expected_gts;
 	unsigned int indices = MAX_TX_QUEUES;
 	u8 part_str[IXGBE_PBANUM_LENGTH];
@@ -8166,8 +8061,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->watchdog_timeo = 5 * HZ;
 	strlcpy(netdev->name, pci_name(pdev), sizeof(netdev->name));
 
-	adapter->bd_number = cards_found;
-
 	/* Setup hw api */
 	memcpy(&hw->mac.ops, ii->mac_ops, sizeof(hw->mac.ops));
 	hw->mac.type  = ii->mac;
@@ -8451,7 +8344,6 @@ skip_sriov:
 	ixgbe_add_sanmac_netdev(netdev);
 
 	e_dev_info("%s\n", ixgbe_default_device_descr);
-	cards_found++;
 
 #ifdef CONFIG_IXGBE_HWMON
 	if (ixgbe_sysfs_init(adapter))