[PATCH net-next 2/6] eth: mpnic: Rx checksum offload

[Daniel Zahka <daniel.zahka@gmail.com>]

The device reports two Rx completion fields to the driver related to
checksums: l2_csum and l4_csum_unnecessary. l2_csum is the ones'
complement sum of the frame starting from the end of the ethernet
header. l4_csum_unnecessary means the device validated the l4 checksum of
the packet. This is only supported for tcp or udp in
ipv4/ipv6/4-in-6/6-in-6.

Report checksum none/complete/unnecessary counts via netdev qstats API.

Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
---
 drivers/net/ethernet/meta/mpnic/mpnic_csr.h    |  2 ++
 drivers/net/ethernet/meta/mpnic/mpnic_netdev.c | 14 ++++++++++-
 drivers/net/ethernet/meta/mpnic/mpnic_netdev.h |  3 +++
 drivers/net/ethernet/meta/mpnic/mpnic_txrx.c   | 34 ++++++++++++++++++++++++++
 drivers/net/ethernet/meta/mpnic/mpnic_txrx.h   |  3 +++
 5 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
index 62304be203e6..1c86f114ab0c 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
@@ -60,6 +60,8 @@ enum {
 #define MPNIC_RCD_AL_PAGE_FIN		DESC_BIT(53)
 
 /* Metadata Completion Descriptors */
+#define MPNIC_RCD_META_L2_CSUM			DESC_GENMASK(47, 32)
+#define MPNIC_RCD_META_L4_CSUM_UNNECESSARY	DESC_BIT(52)
 #define MPNIC_RCD_META_ERR_MAC_EOP		DESC_BIT(53)
 #define MPNIC_RCD_META_ERR_TRUNCATED_FRAME	DESC_BIT(54)
 #define MPNIC_RCD_META_UNCORRECTABLE_ERR_MASK	\
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
index 3de5abc20f9a..91b70fe8483c 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
@@ -167,10 +167,12 @@ static void mpnic_get_queue_stats_rx(struct net_device *dev, int idx,
 {
 	struct mpnic_net *mpn = netdev_priv(dev);
 	struct mpnic_ring *rxr = mpn->rx[idx];
+	u64 csum_unnecessary, csum_complete;
 	u64 bytes, packets, alloc_failed;
 	struct mpnic_queue_stats *stats;
 	struct mpnic_q_triad *qt;
 	unsigned int start;
+	u64 csum_none;
 
 	if (!rxr)
 		return;
@@ -181,6 +183,9 @@ static void mpnic_get_queue_stats_rx(struct net_device *dev, int idx,
 		bytes = u64_stats_read(&stats->rcq.bytes);
 		packets = u64_stats_read(&stats->rcq.packets);
 		alloc_failed = u64_stats_read(&stats->rcq.alloc_failed);
+		csum_complete = u64_stats_read(&stats->rcq.csum_complete);
+		csum_unnecessary = u64_stats_read(&stats->rcq.csum_unnecessary);
+		csum_none = u64_stats_read(&stats->rcq.csum_none);
 	} while (u64_stats_fetch_retry(&stats->syncp, start));
 
 	qt = container_of(rxr, struct mpnic_q_triad, cmpl);
@@ -190,6 +195,9 @@ static void mpnic_get_queue_stats_rx(struct net_device *dev, int idx,
 	rx->bytes = bytes;
 	rx->packets = packets;
 	rx->alloc_fail = alloc_failed;
+	rx->csum_complete = csum_complete;
+	rx->csum_unnecessary = csum_unnecessary;
+	rx->csum_none = csum_none;
 }
 
 static void mpnic_get_queue_stats_tx(struct net_device *dev, int idx,
@@ -248,6 +256,9 @@ static void mpnic_get_base_stats(struct net_device *dev,
 	rx->bytes = base->rx.bytes;
 	rx->packets = base->rx.packets;
 	rx->alloc_fail = base->rx.alloc_failed;
+	rx->csum_complete = base->rx.csum_complete;
+	rx->csum_unnecessary = base->rx.csum_unnecessary;
+	rx->csum_none = base->rx.csum_none;
 }
 
 static const struct netdev_stat_ops mpnic_stat_ops = {
@@ -310,7 +321,8 @@ struct net_device *mpnic_netdev_alloc(struct mpnic_dev *mpd)
 
 	netdev->features |=
 		NETIF_F_SG |
-		NETIF_F_HW_CSUM;
+		NETIF_F_HW_CSUM |
+		NETIF_F_RXCSUM;
 
 	netdev->hw_features |= netdev->features;
 	netdev->vlan_features |= netdev->features;
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h
index 94f7a3355c5c..76ec9811e79e 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h
@@ -26,6 +26,9 @@ struct mpnic_base_stats {
 		u64 dropped;
 		u64 alloc_failed;
 		u64 errors;
+		u64 csum_complete;
+		u64 csum_unnecessary;
+		u64 csum_none;
 	} rx;
 
 	unsigned int num_tx_queues;
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
index edb087b12a1e..680625810ec0 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
@@ -655,9 +655,34 @@ static void mpnic_put_pkt_buff(struct mpnic_pkt_ctxt *ctxt, bool napi)
 	page_pool_put_full_page(page->pp, page, napi);
 }
 
+static void mpnic_rx_csum(u64 rcd, struct sk_buff *skb,
+			  unsigned int *csum_complete,
+			  unsigned int *csum_unnecessary,
+			  unsigned int *csum_none)
+{
+	skb_checksum_none_assert(skb);
+
+	if (!(skb->dev->features & NETIF_F_RXCSUM)) {
+		(*csum_none)++;
+		return;
+	}
+
+	if (FIELD_GET(MPNIC_RCD_META_L4_CSUM_UNNECESSARY, rcd)) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		(*csum_unnecessary)++;
+	} else {
+		u16 csum = FIELD_GET(MPNIC_RCD_META_L2_CSUM, rcd);
+
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum = (__force __wsum)csum;
+		(*csum_complete)++;
+	}
+}
+
 static int mpnic_clean_rcq(struct mpnic_napi_vector *nv,
 			   struct mpnic_q_triad *qt, int budget)
 {
+	unsigned int csum_complete = 0, csum_unnecessary = 0, csum_none = 0;
 	unsigned int packets = 0, bytes = 0, dropped = 0, errors = 0;
 	struct mpnic_ring *rcq = &qt->cmpl;
 	struct mpnic_rcq_state *state;
@@ -700,6 +725,8 @@ static int mpnic_clean_rcq(struct mpnic_napi_vector *nv,
 			}
 
 			if (likely(skb)) {
+				mpnic_rx_csum(rcd, skb, &csum_complete,
+					      &csum_unnecessary, &csum_none);
 				napi_gro_receive(&nv->napi, skb);
 			} else {
 				mpnic_put_pkt_buff(&state->pkt, true);
@@ -732,6 +759,9 @@ static int mpnic_clean_rcq(struct mpnic_napi_vector *nv,
 	u64_stats_add(&rcq->stats.rcq.dropped, dropped);
 	u64_stats_add(&rcq->stats.rcq.alloc_failed, alloc_failed);
 	u64_stats_add(&rcq->stats.rcq.errors, errors);
+	u64_stats_add(&rcq->stats.rcq.csum_complete, csum_complete);
+	u64_stats_add(&rcq->stats.rcq.csum_unnecessary, csum_unnecessary);
+	u64_stats_add(&rcq->stats.rcq.csum_none, csum_none);
 	u64_stats_update_end(&rcq->stats.syncp);
 
 	/* Allocate buffers, force dma_wmb(), and then start writing tails */
@@ -806,6 +836,10 @@ static void mpnic_aggregate_ring_rcq_counters(struct mpnic_base_stats *base,
 	base->rx.dropped += u64_stats_read(&rcq->stats.rcq.dropped);
 	base->rx.alloc_failed += u64_stats_read(&rcq->stats.rcq.alloc_failed);
 	base->rx.errors += u64_stats_read(&rcq->stats.rcq.errors);
+	base->rx.csum_complete += u64_stats_read(&rcq->stats.rcq.csum_complete);
+	base->rx.csum_unnecessary +=
+		u64_stats_read(&rcq->stats.rcq.csum_unnecessary);
+	base->rx.csum_none += u64_stats_read(&rcq->stats.rcq.csum_none);
 }
 
 static struct mpnic_base_stats *mpnic_base_stats_prepare(struct mpnic_net *mpn)
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
index a6dff9dc32d6..714f09f4160e 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
@@ -103,6 +103,9 @@ struct mpnic_queue_stats {
 			u64_stats_t dropped;
 			u64_stats_t alloc_failed;
 			u64_stats_t errors;
+			u64_stats_t csum_complete;
+			u64_stats_t csum_unnecessary;
+			u64_stats_t csum_none;
 		} rcq;
 		struct {
 			u64_stats_t alloc_failed;

-- 
2.52.0