Expose c0 and SW encap ICM for RDMA

These two series from Mark and Shun extend RDMA mlx5 API.

Mark's series provides c0 register used to match egress
traffic sent by local device.

Shun's series adds new type for ICM area.

Link: https://lore.kernel.org/all/cover.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>

3 files changed, 49 insertions, 9 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 38d89d80b4a9..273c9ba48f09 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -2075,6 +2075,7 @@ destroy_flow_table:
 	rhashtable_destroy(&tc_info->flow_table);
 free_tc_info:
 	kfree(tc_info);
+	bp->tc_info = NULL;
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 1dee27349367..f52830dfb26a 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6474,6 +6474,14 @@ static void tg3_dump_state(struct tg3 *tp)
 	int i;
 	u32 *regs;
 
+	/* If it is a PCI error, all registers will be 0xffff,
+	 * we don't dump them out, just report the error and return
+	 */
+	if (tp->pdev->error_state != pci_channel_io_normal) {
+		netdev_err(tp->dev, "PCI channel ERROR!\n");
+		return;
+	}
+
 	regs = kzalloc(TG3_REG_BLK_SIZE, GFP_ATOMIC);
 	if (!regs)
 		return;
@@ -6889,7 +6897,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 				       desc_idx, *post_ptr);
 		drop_it_no_recycle:
 			/* Other statistics kept track of by card. */
-			tp->rx_dropped++;
+			tnapi->rx_dropped++;
 			goto next_pkt;
 		}
 
@@ -7918,8 +7926,10 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
 
 	segs = skb_gso_segment(skb, tp->dev->features &
 				    ~(NETIF_F_TSO | NETIF_F_TSO6));
-	if (IS_ERR(segs) || !segs)
+	if (IS_ERR(segs) || !segs) {
+		tnapi->tx_dropped++;
 		goto tg3_tso_bug_end;
+	}
 
 	skb_list_walk_safe(segs, seg, next) {
 		skb_mark_not_on_list(seg);
@@ -8190,7 +8200,7 @@ dma_error:
 drop:
 	dev_kfree_skb_any(skb);
 drop_nofree:
-	tp->tx_dropped++;
+	tnapi->tx_dropped++;
 	return NETDEV_TX_OK;
 }
 
@@ -9405,7 +9415,7 @@ static void __tg3_set_rx_mode(struct net_device *);
 /* tp->lock is held. */
 static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 {
-	int err;
+	int err, i;
 
 	tg3_stop_fw(tp);
 
@@ -9426,6 +9436,13 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 
 		/* And make sure the next sample is new data */
 		memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
+
+		for (i = 0; i < TG3_IRQ_MAX_VECS; ++i) {
+			struct tg3_napi *tnapi = &tp->napi[i];
+
+			tnapi->rx_dropped = 0;
+			tnapi->tx_dropped = 0;
+		}
 	}
 
 	return err;
@@ -11250,7 +11267,8 @@ static void tg3_reset_task(struct work_struct *work)
 	rtnl_lock();
 	tg3_full_lock(tp, 0);
 
-	if (tp->pcierr_recovery || !netif_running(tp->dev)) {
+	if (tp->pcierr_recovery || !netif_running(tp->dev) ||
+	    tp->pdev->error_state != pci_channel_io_normal) {
 		tg3_flag_clear(tp, RESET_TASK_PENDING);
 		tg3_full_unlock(tp);
 		rtnl_unlock();
@@ -11975,6 +11993,9 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 {
 	struct rtnl_link_stats64 *old_stats = &tp->net_stats_prev;
 	struct tg3_hw_stats *hw_stats = tp->hw_stats;
+	unsigned long rx_dropped;
+	unsigned long tx_dropped;
+	int i;
 
 	stats->rx_packets = old_stats->rx_packets +
 		get_stat64(&hw_stats->rx_ucast_packets) +
@@ -12021,8 +12042,26 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 	stats->rx_missed_errors = old_stats->rx_missed_errors +
 		get_stat64(&hw_stats->rx_discards);
 
-	stats->rx_dropped = tp->rx_dropped;
-	stats->tx_dropped = tp->tx_dropped;
+	/* Aggregate per-queue counters. The per-queue counters are updated
+	 * by a single writer, race-free. The result computed by this loop
+	 * might not be 100% accurate (counters can be updated in the middle of
+	 * the loop) but the next tg3_get_nstats() will recompute the current
+	 * value so it is acceptable.
+	 *
+	 * Note that these counters wrap around at 4G on 32bit machines.
+	 */
+	rx_dropped = (unsigned long)(old_stats->rx_dropped);
+	tx_dropped = (unsigned long)(old_stats->tx_dropped);
+
+	for (i = 0; i < tp->irq_cnt; i++) {
+		struct tg3_napi *tnapi = &tp->napi[i];
+
+		rx_dropped += tnapi->rx_dropped;
+		tx_dropped += tnapi->tx_dropped;
+	}
+
+	stats->rx_dropped = rx_dropped;
+	stats->tx_dropped = tx_dropped;
 }
 
 static int tg3_get_regs_len(struct net_device *dev)
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ae5c01bd1110..5016475e5005 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -3018,6 +3018,7 @@ struct tg3_napi {
 	u16				*rx_rcb_prod_idx;
 	struct tg3_rx_prodring_set	prodring;
 	struct tg3_rx_buffer_desc	*rx_rcb;
+	unsigned long			rx_dropped;
 
 	u32				tx_prod	____cacheline_aligned;
 	u32				tx_cons;
@@ -3026,6 +3027,7 @@ struct tg3_napi {
 	u32				prodmbox;
 	struct tg3_tx_buffer_desc	*tx_ring;
 	struct tg3_tx_ring_info		*tx_buffers;
+	unsigned long			tx_dropped;
 
 	dma_addr_t			status_mapping;
 	dma_addr_t			rx_rcb_mapping;
@@ -3220,8 +3222,6 @@ struct tg3 {
 
 
 	/* begin "everything else" cacheline(s) section */
-	unsigned long			rx_dropped;
-	unsigned long			tx_dropped;
 	struct rtnl_link_stats64	net_stats_prev;
 	struct tg3_ethtool_stats	estats_prev;