[PATCH RFC 1/2] net: mana: Add support for coalesced RX packets on CQE

[PATCH RFC 1/2] net: mana: Add support for coalesced RX packets on CQE

[Haiyang Zhang]

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-frames 4
To turn it off:
  ethtool -C <nic> rx-frames 1

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 32 ++++++-----
 .../ethernet/microsoft/mana/mana_ethtool.c    | 55 +++++++++++++++++++
 include/net/mana/mana.h                       |  2 +
 3 files changed, 74 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 1ad154f9db1a..a46a1adf83bc 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1330,7 +1330,7 @@ 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;
+	req->cqe_coalescing_enable = apc->cqe_coalescing_enable;
 
 	if (update_key)
 		memcpy(&req->hashkey, apc->hashkey, MANA_HASH_KEY_SIZE);
@@ -1864,11 +1864,12 @@ 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 = {};
@@ -1912,7 +1913,7 @@ 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);
@@ -2047,9 +2048,11 @@ 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 = 0;
 
 	apc = netdev_priv(ndev);
 
@@ -2064,9 +2067,8 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 		goto drop;
 
 	case CQE_RX_COALESCED_4:
-		netdev_err(ndev, "RX coalescing is unsupported\n");
-		apc->eth_stats.rx_coalesced_err++;
-		return;
+		coalesced = true;
+		break;
 
 	case CQE_RX_OBJECT_FENCE:
 		complete(&rxq->fence_event);
@@ -2079,14 +2081,10 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 		return;
 	}
 
-	pktlen = oob->ppi[0].pkt_len;
-
-	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);
+nextpkt:
+	pktlen = oob->ppi[i].pkt_len;
+	if (pktlen == 0)
 		return;
-	}
 
 	curr = rxq->buf_index;
 	rxbuf_oob = &rxq->rx_oobs[curr];
@@ -2097,12 +2095,15 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 	/* 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_rx_skb(old_buf, old_fp, oob, rxq, i);
 
 drop:
 	mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu);
 
 	mana_post_pkt_rxq(rxq);
+
+	if (coalesced && (++i < MANA_RXCOMP_OOB_NUM_PPI))
+		goto nextpkt;
 }
 
 static void mana_poll_rx_cq(struct mana_cq *cq)
@@ -3276,6 +3277,7 @@ 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 0e2f4343ac67..1b9ed5c9bbff 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -397,6 +397,58 @@ static void mana_get_channels(struct net_device *ndev,
 	channel->combined_count = apc->num_queues;
 }
 
+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);
+
+	ec->rx_max_coalesced_frames =
+		apc->cqe_coalescing_enable ? MANA_RXCOMP_OOB_NUM_PPI : 1;
+
+	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 (ec->rx_max_coalesced_frames != 1 &&
+	    ec->rx_max_coalesced_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,
+				   ec->rx_max_coalesced_frames);
+		return -EINVAL;
+	}
+
+	saved_cqe_coalescing_enable = apc->cqe_coalescing_enable;
+	apc->cqe_coalescing_enable =
+		ec->rx_max_coalesced_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) {
+		netdev_err(ndev, "Set rx-frames to %u failed:%d\n",
+			   ec->rx_max_coalesced_frames, err);
+		NL_SET_ERR_MSG_FMT(extack, "Set rx-frames to %u failed:%d\n",
+				   ec->rx_max_coalesced_frames, err);
+
+		apc->cqe_coalescing_enable = saved_cqe_coalescing_enable;
+	}
+
+	return err;
+}
+
 static int mana_set_channels(struct net_device *ndev,
 			     struct ethtool_channels *channels)
 {
@@ -517,6 +569,7 @@ static int mana_get_link_ksettings(struct net_device *ndev,
 }
 
 const struct ethtool_ops mana_ethtool_ops = {
+	.supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES,
 	.get_ethtool_stats	= mana_get_ethtool_stats,
 	.get_sset_count		= mana_get_sset_count,
 	.get_strings		= mana_get_strings,
@@ -527,6 +580,8 @@ 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 d7e089c6b694..51d26ebeff6c 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -556,6 +556,8 @@ struct mana_port_context {
 	bool port_is_up;
 	bool port_st_save; /* Saved port state */
 
+	u8 cqe_coalescing_enable;
+
 	struct mana_ethtool_stats eth_stats;
 
 	struct mana_ethtool_phy_stats phy_stats;
-- 
2.34.1

[PATCH RFC 2/2] net: mana: Add ethtool counters for RX CQEs in coalesced type

[Haiyang Zhang]

From: Haiyang Zhang <haiyangz@microsoft.com>

For RX CQEs with type CQE_RX_COALESCED_4, to measure the coalescing
efficiency, add counters to count how many CQEs contain 2, 3, 4 packets
respectively.
Also, add a counter for the error case of first packet with lenth == 0.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 25 +++++++++++++++++--
 .../ethernet/microsoft/mana/mana_ethtool.c    | 17 ++++++++++---
 include/net/mana/mana.h                       | 10 +++++---
 3 files changed, 42 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index a46a1adf83bc..78824567d80b 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -2083,8 +2083,22 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 
 nextpkt:
 	pktlen = oob->ppi[i].pkt_len;
-	if (pktlen == 0)
+	if (pktlen == 0) {
+		/* Collect coalesced CQE count based on packets processed.
+		 * Coalesced CQEs have at least 2 packets, so index is i - 2.
+		 */
+		if (i > 1) {
+			u64_stats_update_begin(&rxq->stats.syncp);
+			rxq->stats.coalesced_cqe[i - 2]++;
+			u64_stats_update_end(&rxq->stats.syncp);
+		} else if (i == 0) {
+			/* Error case stat */
+			u64_stats_update_begin(&rxq->stats.syncp);
+			rxq->stats.pkt_len0_err++;
+			u64_stats_update_end(&rxq->stats.syncp);
+		}
 		return;
+	}
 
 	curr = rxq->buf_index;
 	rxbuf_oob = &rxq->rx_oobs[curr];
@@ -2102,8 +2116,15 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
 
 	mana_post_pkt_rxq(rxq);
 
-	if (coalesced && (++i < MANA_RXCOMP_OOB_NUM_PPI))
+	if (!coalesced)
+		return;
+
+	if (++i < MANA_RXCOMP_OOB_NUM_PPI)
 		goto nextpkt;
+
+	u64_stats_update_begin(&rxq->stats.syncp);
+	rxq->stats.coalesced_cqe[MANA_RXCOMP_OOB_NUM_PPI - 2]++;
+	u64_stats_update_end(&rxq->stats.syncp);
 }
 
 static void mana_poll_rx_cq(struct mana_cq *cq)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 1b9ed5c9bbff..773f50b1a4f4 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)},
 };
@@ -151,7 +149,7 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
 	unsigned int num_queues = apc->num_queues;
-	int i;
+	int i, j;
 
 	if (stringset != ETH_SS_STATS)
 		return;
@@ -170,6 +168,9 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 		ethtool_sprintf(&data, "rx_%d_xdp_drop", i);
 		ethtool_sprintf(&data, "rx_%d_xdp_tx", i);
 		ethtool_sprintf(&data, "rx_%d_xdp_redirect", i);
+		ethtool_sprintf(&data, "rx_%d_pkt_len0_err", i);
+		for (j = 0; j < MANA_RXCOMP_OOB_NUM_PPI - 1; j++)
+			ethtool_sprintf(&data, "rx_%d_coalesced_cqe_%d", i, j + 2);
 	}
 
 	for (i = 0; i < num_queues; i++) {
@@ -203,6 +204,8 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
 	u64 xdp_xmit;
 	u64 xdp_drop;
 	u64 xdp_tx;
+	u64 pkt_len0_err;
+	u64 coalesced_cqe[MANA_RXCOMP_OOB_NUM_PPI - 1];
 	u64 tso_packets;
 	u64 tso_bytes;
 	u64 tso_inner_packets;
@@ -211,7 +214,7 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
 	u64 short_pkt_fmt;
 	u64 csum_partial;
 	u64 mana_map_err;
-	int q, i = 0;
+	int q, i = 0, j;
 
 	if (!apc->port_is_up)
 		return;
@@ -241,6 +244,9 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
 			xdp_drop = rx_stats->xdp_drop;
 			xdp_tx = rx_stats->xdp_tx;
 			xdp_redirect = rx_stats->xdp_redirect;
+			pkt_len0_err = rx_stats->pkt_len0_err;
+			for (j = 0; j < MANA_RXCOMP_OOB_NUM_PPI - 1; j++)
+				coalesced_cqe[j] = rx_stats->coalesced_cqe[j];
 		} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
 
 		data[i++] = packets;
@@ -248,6 +254,9 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
 		data[i++] = xdp_drop;
 		data[i++] = xdp_tx;
 		data[i++] = xdp_redirect;
+		data[i++] = pkt_len0_err;
+		for (j = 0; j < MANA_RXCOMP_OOB_NUM_PPI - 1; j++)
+			data[i++] = coalesced_cqe[j];
 	}
 
 	for (q = 0; q < num_queues; q++) {
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 51d26ebeff6c..f8dd19860103 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -61,8 +61,11 @@ enum TRI_STATE {
 
 #define MAX_PORTS_IN_MANA_DEV 256
 
+/* Maximum number of packets per coalesced CQE */
+#define MANA_RXCOMP_OOB_NUM_PPI 4
+
 /* Update this count whenever the respective structures are changed */
-#define MANA_STATS_RX_COUNT 5
+#define MANA_STATS_RX_COUNT (6 + MANA_RXCOMP_OOB_NUM_PPI - 1)
 #define MANA_STATS_TX_COUNT 11
 
 #define MANA_RX_FRAG_ALIGNMENT 64
@@ -73,6 +76,8 @@ struct mana_stats_rx {
 	u64 xdp_drop;
 	u64 xdp_tx;
 	u64 xdp_redirect;
+	u64 pkt_len0_err;
+	u64 coalesced_cqe[MANA_RXCOMP_OOB_NUM_PPI - 1];
 	struct u64_stats_sync syncp;
 };
 
@@ -227,8 +232,6 @@ struct mana_rxcomp_perpkt_info {
 	u32 pkt_hash;
 }; /* HW DATA */
 
-#define MANA_RXCOMP_OOB_NUM_PPI 4
-
 /* Receive completion OOB */
 struct mana_rxcomp_oob {
 	struct mana_cqe_header cqe_hdr;
@@ -378,7 +381,6 @@ 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;
 };
 
-- 
2.34.1

Re: [PATCH RFC 1/2] net: mana: Add support for coalesced RX packets on CQE

[Simon Horman]

On Tue, Dec 16, 2025 at 07:57:54AM -0800, Haiyang Zhang wrote:
> 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-frames 4
> To turn it off:
>   ethtool -C <nic> rx-frames 1
> 
> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>

...

> diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
> index 0e2f4343ac67..1b9ed5c9bbff 100644
> --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
> +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
> @@ -397,6 +397,58 @@ static void mana_get_channels(struct net_device *ndev,
>  	channel->combined_count = apc->num_queues;
>  }
>  
> +static int mana_get_coalesce(struct net_device *ndev,
> +			     struct ethtool_coalesce *ec,
> +			     struct kernel_ethtool_coalesce *kernel_coal,
> +			     struct netlink_ext_ack *extack)

...

> +	if (err) {
> +		netdev_err(ndev, "Set rx-frames to %u failed:%d\n",
> +			   ec->rx_max_coalesced_frames, err);
> +		NL_SET_ERR_MSG_FMT(extack, "Set rx-frames to %u failed:%d\n",
> +				   ec->rx_max_coalesced_frames, err);

nit: I don't think the trailing '\n' is necessary here.

     Flagged by coccinelle.

> +
> +		apc->cqe_coalescing_enable = saved_cqe_coalescing_enable;
> +	}
> +
> +	return err;
> +}

...

RE: [EXTERNAL] Re: [PATCH RFC 1/2] net: mana: Add support for coalesced RX packets on CQE

[Haiyang Zhang]

> -----Original Message-----
> From: Simon Horman <horms@kernel.org>
> Sent: Monday, January 5, 2026 6:49 AM
> To: Haiyang Zhang <haiyangz@linux.microsoft.com>
> Cc: linux-hyperv@vger.kernel.org; netdev@vger.kernel.org; KY Srinivasan
> <kys@microsoft.com>; Haiyang Zhang <haiyangz@microsoft.com>; Wei Liu
> <wei.liu@kernel.org>; Dexuan Cui <DECUI@microsoft.com>; Andrew Lunn
> <andrew+netdev@lunn.ch>; David S. Miller <davem@davemloft.net>; Eric
> Dumazet <edumazet@google.com>; Jakub Kicinski <kuba@kernel.org>; Paolo
> Abeni <pabeni@redhat.com>; Long Li <longli@microsoft.com>; Konstantin
> Taranov <kotaranov@microsoft.com>; Erni Sri Satya Vennela
> <ernis@linux.microsoft.com>; Shradha Gupta
> <shradhagupta@linux.microsoft.com>; Saurabh Sengar
> <ssengar@linux.microsoft.com>; Aditya Garg
> <gargaditya@linux.microsoft.com>; Dipayaan Roy
> <dipayanroy@linux.microsoft.com>; Shiraz Saleem
> <shirazsaleem@microsoft.com>; linux-kernel@vger.kernel.org; linux-
> rdma@vger.kernel.org; Paul Rosswurm <paulros@microsoft.com>
> Subject: [EXTERNAL] Re: [PATCH RFC 1/2] net: mana: Add support for
> coalesced RX packets on CQE
> 
> On Tue, Dec 16, 2025 at 07:57:54AM -0800, Haiyang Zhang wrote:
> > 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-frames 4
> > To turn it off:
> >   ethtool -C <nic> rx-frames 1
> >
> > Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
> 
> ...
> 
> > diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
> b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
> > index 0e2f4343ac67..1b9ed5c9bbff 100644
> > --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
> > +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
> > @@ -397,6 +397,58 @@ static void mana_get_channels(struct net_device
> *ndev,
> >  	channel->combined_count = apc->num_queues;
> >  }
> >
> > +static int mana_get_coalesce(struct net_device *ndev,
> > +			     struct ethtool_coalesce *ec,
> > +			     struct kernel_ethtool_coalesce *kernel_coal,
> > +			     struct netlink_ext_ack *extack)
> 
> ...
> 
> > +	if (err) {
> > +		netdev_err(ndev, "Set rx-frames to %u failed:%d\n",
> > +			   ec->rx_max_coalesced_frames, err);
> > +		NL_SET_ERR_MSG_FMT(extack, "Set rx-frames to %u failed:%d\n",
> > +				   ec->rx_max_coalesced_frames, err);
> 
> nit: I don't think the trailing '\n' is necessary here.
> 
Will update it.

Thanks,
- Haiyang