[PATCH net-next,V4, 2/3] net: mana: Add support for RX CQE Coalescing

[Haiyang Zhang <haiyangz@linux.microsoft.com>]

From: Haiyang Zhang <haiyangz@microsoft.com>

Our NIC can have up to 4 RX packets on 1 CQE. To support this feature,
check and process the type CQE_RX_COALESCED_4. The default setting is
disabled, to avoid possible regression on latency.

And, add ethtool handler to switch this feature. To turn it on, run:
  ethtool -C <nic> rx-cqe-frames 4
To turn it off:
  ethtool -C <nic> rx-cqe-frames 1

The rx-cqe-nsec is the time out value in nanoseconds after the first
packet arrival in a coalesced CQE to be sent. It's read-only for this
NIC.

Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
v4:
  Fixed the old_buf issue found by AI.

---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 74 ++++++++++++-------
 .../ethernet/microsoft/mana/mana_ethtool.c    | 60 ++++++++++++++-
 include/net/mana/mana.h                       |  8 +-
 3 files changed, 113 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index ea71de39f996..fa30046dcd3d 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1365,6 +1365,7 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 			     sizeof(resp));
 
 	req->hdr.req.msg_version = GDMA_MESSAGE_V2;
+	req->hdr.resp.msg_version = GDMA_MESSAGE_V2;
 
 	req->vport = apc->port_handle;
 	req->num_indir_entries = apc->indir_table_sz;
@@ -1376,7 +1377,9 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 	req->update_hashkey = update_key;
 	req->update_indir_tab = update_tab;
 	req->default_rxobj = apc->default_rxobj;
-	req->cqe_coalescing_enable = 0;
+
+	if (rx != TRI_STATE_FALSE)
+		req->cqe_coalescing_enable = apc->cqe_coalescing_enable;
 
 	if (update_key)
 		memcpy(&req->hashkey, apc->hashkey, MANA_HASH_KEY_SIZE);
@@ -1405,8 +1408,13 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 		netdev_err(ndev, "vPort RX configuration failed: 0x%x\n",
 			   resp.hdr.status);
 		err = -EPROTO;
+		goto out;
 	}
 
+	if (resp.hdr.response.msg_version >= GDMA_MESSAGE_V2)
+		apc->cqe_coalescing_timeout_ns =
+			resp.cqe_coalescing_timeout_ns;
+
 	netdev_info(ndev, "Configured steering vPort %llu entries %u\n",
 		    apc->port_handle, apc->indir_table_sz);
 out:
@@ -1915,11 +1923,12 @@ static struct sk_buff *mana_build_skb(struct mana_rxq *rxq, void *buf_va,
 }
 
 static void mana_rx_skb(void *buf_va, bool from_pool,
-			struct mana_rxcomp_oob *cqe, struct mana_rxq *rxq)
+			struct mana_rxcomp_oob *cqe, struct mana_rxq *rxq,
+			int i)
 {
 	struct mana_stats_rx *rx_stats = &rxq->stats;
 	struct net_device *ndev = rxq->ndev;
-	uint pkt_len = cqe->ppi[0].pkt_len;
+	uint pkt_len = cqe->ppi[i].pkt_len;
 	u16 rxq_idx = rxq->rxq_idx;
 	struct napi_struct *napi;
 	struct xdp_buff xdp = {};
@@ -1963,7 +1972,7 @@ static void mana_rx_skb(void *buf_va, bool from_pool,
 	}
 
 	if (cqe->rx_hashtype != 0 && (ndev->features & NETIF_F_RXHASH)) {
-		hash_value = cqe->ppi[0].pkt_hash;
+		hash_value = cqe->ppi[i].pkt_hash;
 
 		if (cqe->rx_hashtype & MANA_HASH_L4)
 			skb_set_hash(skb, hash_value, PKT_HASH_TYPE_L4);
@@ -2098,9 +2107,11 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 	struct mana_recv_buf_oob *rxbuf_oob;
 	struct mana_port_context *apc;
 	struct device *dev = gc->dev;
+	bool coalesced = false;
 	void *old_buf = NULL;
 	u32 curr, pktlen;
 	bool old_fp;
+	int i;
 
 	apc = netdev_priv(ndev);
 
@@ -2112,13 +2123,16 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 		++ndev->stats.rx_dropped;
 		rxbuf_oob = &rxq->rx_oobs[rxq->buf_index];
 		netdev_warn_once(ndev, "Dropped a truncated packet\n");
-		goto drop;
 
-	case CQE_RX_COALESCED_4:
-		netdev_err(ndev, "RX coalescing is unsupported\n");
-		apc->eth_stats.rx_coalesced_err++;
+		mana_move_wq_tail(rxq->gdma_rq,
+				  rxbuf_oob->wqe_inf.wqe_size_in_bu);
+		mana_post_pkt_rxq(rxq);
 		return;
 
+	case CQE_RX_COALESCED_4:
+		coalesced = true;
+		break;
+
 	case CQE_RX_OBJECT_FENCE:
 		complete(&rxq->fence_event);
 		return;
@@ -2130,30 +2144,37 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 		return;
 	}
 
-	pktlen = oob->ppi[0].pkt_len;
+	for (i = 0; i < MANA_RXCOMP_OOB_NUM_PPI; i++) {
+		old_buf = NULL;
+		pktlen = oob->ppi[i].pkt_len;
+		if (pktlen == 0) {
+			if (i == 0)
+				netdev_err_once(
+					ndev,
+					"RX pkt len=0, rq=%u, cq=%u, rxobj=0x%llx\n",
+					rxq->gdma_id, cq->gdma_id, rxq->rxobj);
+			break;
+		}
 
-	if (pktlen == 0) {
-		/* data packets should never have packetlength of zero */
-		netdev_err(ndev, "RX pkt len=0, rq=%u, cq=%u, rxobj=0x%llx\n",
-			   rxq->gdma_id, cq->gdma_id, rxq->rxobj);
-		return;
-	}
+		curr = rxq->buf_index;
+		rxbuf_oob = &rxq->rx_oobs[curr];
+		WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1);
 
-	curr = rxq->buf_index;
-	rxbuf_oob = &rxq->rx_oobs[curr];
-	WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1);
+		mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp);
 
-	mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp);
+		/* Unsuccessful refill will have old_buf == NULL.
+		 * In this case, mana_rx_skb() will drop the packet.
+		 */
+		mana_rx_skb(old_buf, old_fp, oob, rxq, i);
 
-	/* Unsuccessful refill will have old_buf == NULL.
-	 * In this case, mana_rx_skb() will drop the packet.
-	 */
-	mana_rx_skb(old_buf, old_fp, oob, rxq);
+		mana_move_wq_tail(rxq->gdma_rq,
+				  rxbuf_oob->wqe_inf.wqe_size_in_bu);
 
-drop:
-	mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu);
+		mana_post_pkt_rxq(rxq);
 
-	mana_post_pkt_rxq(rxq);
+		if (!coalesced)
+			break;
+	}
 }
 
 static void mana_poll_rx_cq(struct mana_cq *cq)
@@ -3332,6 +3353,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	apc->port_handle = INVALID_MANA_HANDLE;
 	apc->pf_filter_handle = INVALID_MANA_HANDLE;
 	apc->port_idx = port_idx;
+	apc->cqe_coalescing_enable = 0;
 
 	mutex_init(&apc->vport_mutex);
 	apc->vport_use_count = 0;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index f2d220b371b5..4b234b16e57a 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -20,8 +20,6 @@ static const struct mana_stats_desc mana_eth_stats[] = {
 					tx_cqe_unknown_type)},
 	{"tx_linear_pkt_cnt", offsetof(struct mana_ethtool_stats,
 				       tx_linear_pkt_cnt)},
-	{"rx_coalesced_err", offsetof(struct mana_ethtool_stats,
-					rx_coalesced_err)},
 	{"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
 					rx_cqe_unknown_type)},
 };
@@ -390,6 +388,61 @@ static void mana_get_channels(struct net_device *ndev,
 	channel->combined_count = apc->num_queues;
 }
 
+#define MANA_RX_CQE_NSEC_DEF 2048
+static int mana_get_coalesce(struct net_device *ndev,
+			     struct ethtool_coalesce *ec,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+
+	kernel_coal->rx_cqe_frames =
+		apc->cqe_coalescing_enable ? MANA_RXCOMP_OOB_NUM_PPI : 1;
+
+	kernel_coal->rx_cqe_nsecs = apc->cqe_coalescing_timeout_ns;
+
+	/* Return the default timeout value for old FW not providing
+	 * this value.
+	 */
+	if (apc->port_is_up && apc->cqe_coalescing_enable &&
+	    !kernel_coal->rx_cqe_nsecs)
+		kernel_coal->rx_cqe_nsecs = MANA_RX_CQE_NSEC_DEF;
+
+	return 0;
+}
+
+static int mana_set_coalesce(struct net_device *ndev,
+			     struct ethtool_coalesce *ec,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	u8 saved_cqe_coalescing_enable;
+	int err;
+
+	if (kernel_coal->rx_cqe_frames != 1 &&
+	    kernel_coal->rx_cqe_frames != MANA_RXCOMP_OOB_NUM_PPI) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "rx-frames must be 1 or %u, got %u",
+				   MANA_RXCOMP_OOB_NUM_PPI,
+				   kernel_coal->rx_cqe_frames);
+		return -EINVAL;
+	}
+
+	saved_cqe_coalescing_enable = apc->cqe_coalescing_enable;
+	apc->cqe_coalescing_enable =
+		kernel_coal->rx_cqe_frames == MANA_RXCOMP_OOB_NUM_PPI;
+
+	if (!apc->port_is_up)
+		return 0;
+
+	err = mana_config_rss(apc, TRI_STATE_TRUE, false, false);
+	if (err)
+		apc->cqe_coalescing_enable = saved_cqe_coalescing_enable;
+
+	return err;
+}
+
 static int mana_set_channels(struct net_device *ndev,
 			     struct ethtool_channels *channels)
 {
@@ -510,6 +563,7 @@ static int mana_get_link_ksettings(struct net_device *ndev,
 }
 
 const struct ethtool_ops mana_ethtool_ops = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_RX_CQE_FRAMES,
 	.get_ethtool_stats	= mana_get_ethtool_stats,
 	.get_sset_count		= mana_get_sset_count,
 	.get_strings		= mana_get_strings,
@@ -520,6 +574,8 @@ const struct ethtool_ops mana_ethtool_ops = {
 	.set_rxfh		= mana_set_rxfh,
 	.get_channels		= mana_get_channels,
 	.set_channels		= mana_set_channels,
+	.get_coalesce		= mana_get_coalesce,
+	.set_coalesce		= mana_set_coalesce,
 	.get_ringparam          = mana_get_ringparam,
 	.set_ringparam          = mana_set_ringparam,
 	.get_link_ksettings	= mana_get_link_ksettings,
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index a078af283bdd..a7f89e7ddc56 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -378,7 +378,6 @@ struct mana_ethtool_stats {
 	u64 tx_cqe_err;
 	u64 tx_cqe_unknown_type;
 	u64 tx_linear_pkt_cnt;
-	u64 rx_coalesced_err;
 	u64 rx_cqe_unknown_type;
 };
 
@@ -557,6 +556,9 @@ struct mana_port_context {
 	bool port_is_up;
 	bool port_st_save; /* Saved port state */
 
+	u8 cqe_coalescing_enable;
+	u32 cqe_coalescing_timeout_ns;
+
 	struct mana_ethtool_stats eth_stats;
 
 	struct mana_ethtool_phy_stats phy_stats;
@@ -902,6 +904,10 @@ struct mana_cfg_rx_steer_req_v2 {
 
 struct mana_cfg_rx_steer_resp {
 	struct gdma_resp_hdr hdr;
+
+	/* V2 */
+	u32 cqe_coalescing_timeout_ns;
+	u32 reserved1;
 }; /* HW DATA */
 
 /* Register HW vPort */
-- 
2.34.1