1 files changed, 254 insertions, 71 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 935a2f15b0b0..62a18914f00f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1192,7 +1192,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		read_barrier_depends();
+		smp_rmb();
 
 		/* if DD is not set pending work has not been completed */
 		if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
@@ -1620,6 +1620,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 	bi->page = page;
 	bi->page_offset = ixgbe_rx_offset(rx_ring);
 	bi->pagecnt_bias = 1;
+	rx_ring->rx_stats.alloc_rx_page++;
 
 	return true;
 }
@@ -2133,6 +2134,21 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
 #if L1_CACHE_BYTES < 128
 	prefetch(xdp->data + L1_CACHE_BYTES);
 #endif
+	/* Note, we get here by enabling legacy-rx via:
+	 *
+	 *    ethtool --set-priv-flags <dev> legacy-rx on
+	 *
+	 * In this mode, we currently get 0 extra XDP headroom as
+	 * opposed to having legacy-rx off, where we process XDP
+	 * packets going to stack via ixgbe_build_skb(). The latter
+	 * provides us currently with 192 bytes of headroom.
+	 *
+	 * For ixgbe_construct_skb() mode it means that the
+	 * xdp->data_meta will always point to xdp->data, since
+	 * the helper cannot expand the head. Should this ever
+	 * change in future for legacy-rx mode on, then lets also
+	 * add xdp->data_meta handling here.
+	 */
 
 	/* allocate a skb to store the frags */
 	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBE_RX_HDR_SIZE);
@@ -2165,6 +2181,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 				       struct xdp_buff *xdp,
 				       union ixgbe_adv_rx_desc *rx_desc)
 {
+	unsigned int metasize = xdp->data - xdp->data_meta;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
 #else
@@ -2174,10 +2191,14 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 #endif
 	struct sk_buff *skb;
 
-	/* prefetch first cache line of first page */
-	prefetch(xdp->data);
+	/* Prefetch first cache line of first page. If xdp->data_meta
+	 * is unused, this points extactly as xdp->data, otherwise we
+	 * likely have a consumer accessing first few bytes of meta
+	 * data, and then actual data.
+	 */
+	prefetch(xdp->data_meta);
 #if L1_CACHE_BYTES < 128
-	prefetch(xdp->data + L1_CACHE_BYTES);
+	prefetch(xdp->data_meta + L1_CACHE_BYTES);
 #endif
 
 	/* build an skb to around the page buffer */
@@ -2188,6 +2209,8 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	/* update pointers within the skb to store the data */
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	__skb_put(skb, xdp->data_end - xdp->data);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 
 	/* record DMA address if this is the start of a chain of buffers */
 	if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
@@ -2326,6 +2349,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		if (!skb) {
 			xdp.data = page_address(rx_buffer->page) +
 				   rx_buffer->page_offset;
+			xdp.data_meta = xdp.data;
 			xdp.data_hard_start = xdp.data -
 					      ixgbe_rx_offset(rx_ring);
 			xdp.data_end = xdp.data + size;
@@ -2516,50 +2540,174 @@ enum latency_range {
 static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector,
 			     struct ixgbe_ring_container *ring_container)
 {
-	int bytes = ring_container->total_bytes;
-	int packets = ring_container->total_packets;
-	u32 timepassed_us;
-	u64 bytes_perint;
-	u8 itr_setting = ring_container->itr;
+	unsigned int itr = IXGBE_ITR_ADAPTIVE_MIN_USECS |
+			   IXGBE_ITR_ADAPTIVE_LATENCY;
+	unsigned int avg_wire_size, packets, bytes;
+	unsigned long next_update = jiffies;
 
-	if (packets == 0)
+	/* If we don't have any rings just leave ourselves set for maximum
+	 * possible latency so we take ourselves out of the equation.
+	 */
+	if (!ring_container->ring)
 		return;
 
-	/* simple throttlerate management
-	 *   0-10MB/s   lowest (100000 ints/s)
-	 *  10-20MB/s   low    (20000 ints/s)
-	 *  20-1249MB/s bulk   (12000 ints/s)
+	/* If we didn't update within up to 1 - 2 jiffies we can assume
+	 * that either packets are coming in so slow there hasn't been
+	 * any work, or that there is so much work that NAPI is dealing
+	 * with interrupt moderation and we don't need to do anything.
 	 */
-	/* what was last interrupt timeslice? */
-	timepassed_us = q_vector->itr >> 2;
-	if (timepassed_us == 0)
-		return;
+	if (time_after(next_update, ring_container->next_update))
+		goto clear_counts;
 
-	bytes_perint = bytes / timepassed_us; /* bytes/usec */
+	packets = ring_container->total_packets;
 
-	switch (itr_setting) {
-	case lowest_latency:
-		if (bytes_perint > 10)
-			itr_setting = low_latency;
-		break;
-	case low_latency:
-		if (bytes_perint > 20)
-			itr_setting = bulk_latency;
-		else if (bytes_perint <= 10)
-			itr_setting = lowest_latency;
+	/* We have no packets to actually measure against. This means
+	 * either one of the other queues on this vector is active or
+	 * we are a Tx queue doing TSO with too high of an interrupt rate.
+	 *
+	 * When this occurs just tick up our delay by the minimum value
+	 * and hope that this extra delay will prevent us from being called
+	 * without any work on our queue.
+	 */
+	if (!packets) {
+		itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC;
+		if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS)
+			itr = IXGBE_ITR_ADAPTIVE_MAX_USECS;
+		itr += ring_container->itr & IXGBE_ITR_ADAPTIVE_LATENCY;
+		goto clear_counts;
+	}
+
+	bytes = ring_container->total_bytes;
+
+	/* If packets are less than 4 or bytes are less than 9000 assume
+	 * insufficient data to use bulk rate limiting approach. We are
+	 * likely latency driven.
+	 */
+	if (packets < 4 && bytes < 9000) {
+		itr = IXGBE_ITR_ADAPTIVE_LATENCY;
+		goto adjust_by_size;
+	}
+
+	/* Between 4 and 48 we can assume that our current interrupt delay
+	 * is only slightly too low. As such we should increase it by a small
+	 * fixed amount.
+	 */
+	if (packets < 48) {
+		itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC;
+		if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS)
+			itr = IXGBE_ITR_ADAPTIVE_MAX_USECS;
+		goto clear_counts;
+	}
+
+	/* Between 48 and 96 is our "goldilocks" zone where we are working
+	 * out "just right". Just report that our current ITR is good for us.
+	 */
+	if (packets < 96) {
+		itr = q_vector->itr >> 2;
+		goto clear_counts;
+	}
+
+	/* If packet count is 96 or greater we are likely looking at a slight
+	 * overrun of the delay we want. Try halving our delay to see if that
+	 * will cut the number of packets in half per interrupt.
+	 */
+	if (packets < 256) {
+		itr = q_vector->itr >> 3;
+		if (itr < IXGBE_ITR_ADAPTIVE_MIN_USECS)
+			itr = IXGBE_ITR_ADAPTIVE_MIN_USECS;
+		goto clear_counts;
+	}
+
+	/* The paths below assume we are dealing with a bulk ITR since number
+	 * of packets is 256 or greater. We are just going to have to compute
+	 * a value and try to bring the count under control, though for smaller
+	 * packet sizes there isn't much we can do as NAPI polling will likely
+	 * be kicking in sooner rather than later.
+	 */
+	itr = IXGBE_ITR_ADAPTIVE_BULK;
+
+adjust_by_size:
+	/* If packet counts are 256 or greater we can assume we have a gross
+	 * overestimation of what the rate should be. Instead of trying to fine
+	 * tune it just use the formula below to try and dial in an exact value
+	 * give the current packet size of the frame.
+	 */
+	avg_wire_size = bytes / packets;
+
+	/* The following is a crude approximation of:
+	 *  wmem_default / (size + overhead) = desired_pkts_per_int
+	 *  rate / bits_per_byte / (size + ethernet overhead) = pkt_rate
+	 *  (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value
+	 *
+	 * Assuming wmem_default is 212992 and overhead is 640 bytes per
+	 * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the
+	 * formula down to
+	 *
+	 *  (170 * (size + 24)) / (size + 640) = ITR
+	 *
+	 * We first do some math on the packet size and then finally bitshift
+	 * by 8 after rounding up. We also have to account for PCIe link speed
+	 * difference as ITR scales based on this.
+	 */
+	if (avg_wire_size <= 60) {
+		/* Start at 50k ints/sec */
+		avg_wire_size = 5120;
+	} else if (avg_wire_size <= 316) {
+		/* 50K ints/sec to 16K ints/sec */
+		avg_wire_size *= 40;
+		avg_wire_size += 2720;
+	} else if (avg_wire_size <= 1084) {
+		/* 16K ints/sec to 9.2K ints/sec */
+		avg_wire_size *= 15;
+		avg_wire_size += 11452;
+	} else if (avg_wire_size <= 1980) {
+		/* 9.2K ints/sec to 8K ints/sec */
+		avg_wire_size *= 5;
+		avg_wire_size += 22420;
+	} else {
+		/* plateau at a limit of 8K ints/sec */
+		avg_wire_size = 32256;
+	}
+
+	/* If we are in low latency mode half our delay which doubles the rate
+	 * to somewhere between 100K to 16K ints/sec
+	 */
+	if (itr & IXGBE_ITR_ADAPTIVE_LATENCY)
+		avg_wire_size >>= 1;
+
+	/* Resultant value is 256 times larger than it needs to be. This
+	 * gives us room to adjust the value as needed to either increase
+	 * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc.
+	 *
+	 * Use addition as we have already recorded the new latency flag
+	 * for the ITR value.
+	 */
+	switch (q_vector->adapter->link_speed) {
+	case IXGBE_LINK_SPEED_10GB_FULL:
+	case IXGBE_LINK_SPEED_100_FULL:
+	default:
+		itr += DIV_ROUND_UP(avg_wire_size,
+				    IXGBE_ITR_ADAPTIVE_MIN_INC * 256) *
+		       IXGBE_ITR_ADAPTIVE_MIN_INC;
 		break;
-	case bulk_latency:
-		if (bytes_perint <= 20)
-			itr_setting = low_latency;
+	case IXGBE_LINK_SPEED_2_5GB_FULL:
+	case IXGBE_LINK_SPEED_1GB_FULL:
+	case IXGBE_LINK_SPEED_10_FULL:
+		itr += DIV_ROUND_UP(avg_wire_size,
+				    IXGBE_ITR_ADAPTIVE_MIN_INC * 64) *
+		       IXGBE_ITR_ADAPTIVE_MIN_INC;
 		break;
 	}
 
-	/* clear work counters since we have the values we need */
+clear_counts:
+	/* write back value */
+	ring_container->itr = itr;
+
+	/* next update should occur within next jiffy */
+	ring_container->next_update = next_update + 1;
+
 	ring_container->total_bytes = 0;
 	ring_container->total_packets = 0;
-
-	/* write updated itr to ring container */
-	ring_container->itr = itr_setting;
 }
 
 /**
@@ -2601,34 +2749,19 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
 
 static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector)
 {
-	u32 new_itr = q_vector->itr;
-	u8 current_itr;
+	u32 new_itr;
 
 	ixgbe_update_itr(q_vector, &q_vector->tx);
 	ixgbe_update_itr(q_vector, &q_vector->rx);
 
-	current_itr = max(q_vector->rx.itr, q_vector->tx.itr);
+	/* use the smallest value of new ITR delay calculations */
+	new_itr = min(q_vector->rx.itr, q_vector->tx.itr);
 
-	switch (current_itr) {
-	/* counts and packets in update_itr are dependent on these numbers */
-	case lowest_latency:
-		new_itr = IXGBE_100K_ITR;
-		break;
-	case low_latency:
-		new_itr = IXGBE_20K_ITR;
-		break;
-	case bulk_latency:
-		new_itr = IXGBE_12K_ITR;
-		break;
-	default:
-		break;
-	}
+	/* Clear latency flag if set, shift into correct position */
+	new_itr &= ~IXGBE_ITR_ADAPTIVE_LATENCY;
+	new_itr <<= 2;
 
 	if (new_itr != q_vector->itr) {
-		/* do an exponential smoothing */
-		new_itr = (10 * new_itr * q_vector->itr) /
-			  ((9 * new_itr) + q_vector->itr);
-
 		/* save the algorithm value here */
 		q_vector->itr = new_itr;
 
@@ -6771,6 +6904,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot;
 	u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0;
 	u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0;
+	u64 alloc_rx_page = 0;
 	u64 bytes = 0, packets = 0, hw_csum_rx_error = 0;
 
 	if (test_bit(__IXGBE_DOWN, &adapter->state) ||
@@ -6791,6 +6925,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct ixgbe_ring *rx_ring = adapter->rx_ring[i];
 		non_eop_descs += rx_ring->rx_stats.non_eop_descs;
+		alloc_rx_page += rx_ring->rx_stats.alloc_rx_page;
 		alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed;
 		alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed;
 		hw_csum_rx_error += rx_ring->rx_stats.csum_err;
@@ -6798,6 +6933,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 		packets += rx_ring->stats.packets;
 	}
 	adapter->non_eop_descs = non_eop_descs;
+	adapter->alloc_rx_page = alloc_rx_page;
 	adapter->alloc_rx_page_failed = alloc_rx_page_failed;
 	adapter->alloc_rx_buff_failed = alloc_rx_buff_failed;
 	adapter->hw_csum_rx_error = hw_csum_rx_error;
@@ -7554,9 +7690,9 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter)
  * ixgbe_service_timer - Timer Call-back
  * @data: pointer to adapter cast into an unsigned long
  **/
-static void ixgbe_service_timer(unsigned long data)
+static void ixgbe_service_timer(struct timer_list *t)
 {
-	struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)data;
+	struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer);
 	unsigned long next_event_offset;
 
 	/* poll faster when waiting for link */
@@ -9223,13 +9359,10 @@ free_jump:
 	return err;
 }
 
-static int ixgbe_setup_tc_cls_u32(struct net_device *dev,
+static int ixgbe_setup_tc_cls_u32(struct ixgbe_adapter *adapter,
 				  struct tc_cls_u32_offload *cls_u32)
 {
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
-
-	if (!is_classid_clsact_ingress(cls_u32->common.classid) ||
-	    cls_u32->common.chain_index)
+	if (cls_u32->common.chain_index)
 		return -EOPNOTSUPP;
 
 	switch (cls_u32->command) {
@@ -9248,6 +9381,43 @@ static int ixgbe_setup_tc_cls_u32(struct net_device *dev,
 	}
 }
 
+static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				   void *cb_priv)
+{
+	struct ixgbe_adapter *adapter = cb_priv;
+
+	if (!tc_can_offload(adapter->netdev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSU32:
+		return ixgbe_setup_tc_cls_u32(adapter, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int ixgbe_setup_tc_block(struct net_device *dev,
+				struct tc_block_offload *f)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
+					     adapter, adapter);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
+					adapter);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int ixgbe_setup_tc_mqprio(struct net_device *dev,
 				 struct tc_mqprio_qopt *mqprio)
 {
@@ -9259,9 +9429,9 @@ static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			    void *type_data)
 {
 	switch (type) {
-	case TC_SETUP_CLSU32:
-		return ixgbe_setup_tc_cls_u32(dev, type_data);
-	case TC_SETUP_MQPRIO:
+	case TC_SETUP_BLOCK:
+		return ixgbe_setup_tc_block(dev, type_data);
+	case TC_SETUP_QDISC_MQPRIO:
 		return ixgbe_setup_tc_mqprio(dev, type_data);
 	default:
 		return -EOPNOTSUPP;
@@ -9733,6 +9903,17 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 	limit = find_last_bit(&adapter->fwd_bitmask, 32);
 	adapter->ring_feature[RING_F_VMDQ].limit = limit + 1;
 	ixgbe_fwd_ring_down(fwd_adapter->netdev, fwd_adapter);
+
+	/* go back to full RSS if we're done with our VMQs */
+	if (adapter->ring_feature[RING_F_VMDQ].limit == 1) {
+		int rss = min_t(int, ixgbe_max_rss_indices(adapter),
+				num_online_cpus());
+
+		adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED;
+		adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
+		adapter->ring_feature[RING_F_RSS].limit = rss;
+	}
+
 	ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev));
 	netdev_dbg(pdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n",
 		   fwd_adapter->pool, adapter->num_rx_pools,
@@ -9823,7 +10004,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	return 0;
 }
 
-static int ixgbe_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 
@@ -9932,7 +10113,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_udp_tunnel_add	= ixgbe_add_udp_tunnel_port,
 	.ndo_udp_tunnel_del	= ixgbe_del_udp_tunnel_port,
 	.ndo_features_check	= ixgbe_features_check,
-	.ndo_xdp		= ixgbe_xdp,
+	.ndo_bpf		= ixgbe_xdp,
 	.ndo_xdp_xmit		= ixgbe_xdp_xmit,
 	.ndo_xdp_flush		= ixgbe_xdp_flush,
 };
@@ -10355,8 +10536,7 @@ skip_sriov:
 	ether_addr_copy(hw->mac.addr, hw->mac.perm_addr);
 	ixgbe_mac_set_default_filter(adapter);
 
-	setup_timer(&adapter->service_timer, &ixgbe_service_timer,
-		    (unsigned long) adapter);
+	timer_setup(&adapter->service_timer, ixgbe_service_timer, 0);
 
 	if (ixgbe_removed(hw->hw_addr)) {
 		err = -EIO;
@@ -10712,6 +10892,9 @@ skip_bad_vf_detection:
 	if (!test_bit(__IXGBE_SERVICE_INITED, &adapter->state))
 		return PCI_ERS_RESULT_DISCONNECT;
 
+	if (!netif_device_present(netdev))
+		return PCI_ERS_RESULT_DISCONNECT;
+
 	rtnl_lock();
 	netif_device_detach(netdev);