Merge branch 'enic-report-per-queue-stats'

Nelson Escobar says:

====================
enic: Report per queue stats

Patch #1: Use a macro instead of static const variables for array sizes.  I
          didn't want to add more static const variables in the next patch
          so clean up the existing ones first.

Patch #2: Collect per queue statistics

Patch #3: Report per queue stats in netdev qstats

Patch #4: Report some per queue stats in ethtool

 # NETIF="eno6" tools/testing/selftests/drivers/net/stats.py
KTAP version 1
1..5
ok 1 stats.check_pause # XFAIL pause not supported by the device
ok 2 stats.check_fec # XFAIL FEC not supported by the device
ok 3 stats.pkt_byte_sum
ok 4 stats.qstat_by_ifindex
ok 5 stats.check_down

 # tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
     --dump qstats-get --json '{"ifindex": "34"}'
[{'ifindex': 34,
  'rx-bytes': 66762680,
  'rx-csum-unnecessary': 1009345,
  'rx-hw-drop-overruns': 0,
  'rx-hw-drops': 0,
  'rx-packets': 1009673,
  'tx-bytes': 137936674899,
  'tx-csum-none': 125,
  'tx-hw-gso-packets': 2408712,
  'tx-needs-csum': 2431531,
  'tx-packets': 15475466,
  'tx-stop': 0,
  'tx-wake': 0}]

v2: https://lore.kernel.org/20240905010900.24152-1-neescoba@cisco.com
v1: https://lore.kernel.org/20240823235401.29996-1-neescoba@cisco.com
====================

Link: https://patch.msgid.link/20240912005039.10797-1-neescoba@cisco.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/cisco/enic/enic.h

@@ -128,6 +128,40 @@ struct vxlan_offload {
 	u8 flags;
 };
 
+struct enic_wq_stats {
+	u64 packets;		/* pkts queued for Tx */
+	u64 stopped;		/* Tx ring almost full, queue stopped */
+	u64 wake;		/* Tx ring no longer full, queue woken up*/
+	u64 tso;		/* non-encap tso pkt */
+	u64 encap_tso;		/* encap tso pkt */
+	u64 encap_csum;		/* encap HW csum */
+	u64 csum_partial;	/* skb->ip_summed = CHECKSUM_PARTIAL */
+	u64 csum_none;		/* HW csum not required */
+	u64 bytes;		/* bytes queued for Tx */
+	u64 add_vlan;		/* HW adds vlan tag */
+	u64 cq_work;		/* Tx completions processed */
+	u64 cq_bytes;		/* Tx bytes processed */
+	u64 null_pkt;		/* skb length <= 0 */
+	u64 skb_linear_fail;	/* linearize failures */
+	u64 desc_full_awake;	/* TX ring full while queue awake */
+};
+
+struct enic_rq_stats {
+	u64 packets;			/* pkts received */
+	u64 bytes;			/* bytes received */
+	u64 l4_rss_hash;		/* hashed on l4 */
+	u64 l3_rss_hash;		/* hashed on l3 */
+	u64 csum_unnecessary;		/* HW verified csum */
+	u64 csum_unnecessary_encap;	/* HW verified csum on encap packet */
+	u64 vlan_stripped;		/* HW stripped vlan */
+	u64 napi_complete;		/* napi complete intr reenabled */
+	u64 napi_repoll;		/* napi poll again */
+	u64 bad_fcs;			/* bad pkts */
+	u64 pkt_truncated;		/* truncated pkts */
+	u64 no_skb;			/* out of skbs */
+	u64 desc_skip;			/* Rx pkt went into later buffer */
+};
+
 /* Per-instance private data structure */
 struct enic {
 	struct net_device *netdev;
@@ -162,16 +196,16 @@ struct enic {
 	/* work queue cache line section */
 	____cacheline_aligned struct vnic_wq wq[ENIC_WQ_MAX];
 	spinlock_t wq_lock[ENIC_WQ_MAX];
+	struct enic_wq_stats wq_stats[ENIC_WQ_MAX];
 	unsigned int wq_count;
 	u16 loop_enable;
 	u16 loop_tag;
 
 	/* receive queue cache line section */
 	____cacheline_aligned struct vnic_rq rq[ENIC_RQ_MAX];
+	struct enic_rq_stats rq_stats[ENIC_RQ_MAX];
 	unsigned int rq_count;
 	struct vxlan_offload vxlan;
-	u64 rq_truncated_pkts;
-	u64 rq_bad_fcs;
 	struct napi_struct napi[ENIC_RQ_MAX + ENIC_WQ_MAX];
 
 	/* interrupt resource cache line section */

drivers/net/ethernet/cisco/enic/enic_ethtool.c

@@ -32,6 +32,41 @@ struct enic_stat {
 	.index = offsetof(struct vnic_gen_stats, stat) / sizeof(u64)\
 }
 
+#define ENIC_PER_RQ_STAT(stat) { \
+	.name = "rq[%d]_"#stat, \
+	.index = offsetof(struct enic_rq_stats, stat) / sizeof(u64) \
+}
+
+#define ENIC_PER_WQ_STAT(stat) { \
+	.name = "wq[%d]_"#stat, \
+	.index = offsetof(struct enic_wq_stats, stat) / sizeof(u64) \
+}
+
+static const struct enic_stat enic_per_rq_stats[] = {
+	ENIC_PER_RQ_STAT(l4_rss_hash),
+	ENIC_PER_RQ_STAT(l3_rss_hash),
+	ENIC_PER_RQ_STAT(csum_unnecessary_encap),
+	ENIC_PER_RQ_STAT(vlan_stripped),
+	ENIC_PER_RQ_STAT(napi_complete),
+	ENIC_PER_RQ_STAT(napi_repoll),
+	ENIC_PER_RQ_STAT(no_skb),
+	ENIC_PER_RQ_STAT(desc_skip),
+};
+
+#define NUM_ENIC_PER_RQ_STATS   ARRAY_SIZE(enic_per_rq_stats)
+
+static const struct enic_stat enic_per_wq_stats[] = {
+	ENIC_PER_WQ_STAT(encap_tso),
+	ENIC_PER_WQ_STAT(encap_csum),
+	ENIC_PER_WQ_STAT(add_vlan),
+	ENIC_PER_WQ_STAT(cq_work),
+	ENIC_PER_WQ_STAT(cq_bytes),
+	ENIC_PER_WQ_STAT(null_pkt),
+	ENIC_PER_WQ_STAT(skb_linear_fail),
+	ENIC_PER_WQ_STAT(desc_full_awake),
+};
+
+#define NUM_ENIC_PER_WQ_STATS   ARRAY_SIZE(enic_per_wq_stats)
 static const struct enic_stat enic_tx_stats[] = {
 	ENIC_TX_STAT(tx_frames_ok),
 	ENIC_TX_STAT(tx_unicast_frames_ok),
@@ -46,6 +81,8 @@ static const struct enic_stat enic_tx_stats[] = {
 	ENIC_TX_STAT(tx_tso),
 };
 
+#define NUM_ENIC_TX_STATS	ARRAY_SIZE(enic_tx_stats)
+
 static const struct enic_stat enic_rx_stats[] = {
 	ENIC_RX_STAT(rx_frames_ok),
 	ENIC_RX_STAT(rx_frames_total),
@@ -70,13 +107,13 @@ static const struct enic_stat enic_rx_stats[] = {
 	ENIC_RX_STAT(rx_frames_to_max),
 };
 
+#define NUM_ENIC_RX_STATS	ARRAY_SIZE(enic_rx_stats)
+
 static const struct enic_stat enic_gen_stats[] = {
 	ENIC_GEN_STAT(dma_map_error),
 };
 
-static const unsigned int enic_n_tx_stats = ARRAY_SIZE(enic_tx_stats);
-static const unsigned int enic_n_rx_stats = ARRAY_SIZE(enic_rx_stats);
-static const unsigned int enic_n_gen_stats = ARRAY_SIZE(enic_gen_stats);
+#define NUM_ENIC_GEN_STATS	ARRAY_SIZE(enic_gen_stats)
 
 static void enic_intr_coal_set_rx(struct enic *enic, u32 timer)
 {
@@ -141,22 +178,38 @@ static void enic_get_drvinfo(struct net_device *netdev,
 static void enic_get_strings(struct net_device *netdev, u32 stringset,
 	u8 *data)
 {
+	struct enic *enic = netdev_priv(netdev);
 	unsigned int i;
+	unsigned int j;
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		for (i = 0; i < enic_n_tx_stats; i++) {
+		for (i = 0; i < NUM_ENIC_TX_STATS; i++) {
 			memcpy(data, enic_tx_stats[i].name, ETH_GSTRING_LEN);
 			data += ETH_GSTRING_LEN;
 		}
-		for (i = 0; i < enic_n_rx_stats; i++) {
+		for (i = 0; i < NUM_ENIC_RX_STATS; i++) {
 			memcpy(data, enic_rx_stats[i].name, ETH_GSTRING_LEN);
 			data += ETH_GSTRING_LEN;
 		}
-		for (i = 0; i < enic_n_gen_stats; i++) {
+		for (i = 0; i < NUM_ENIC_GEN_STATS; i++) {
 			memcpy(data, enic_gen_stats[i].name, ETH_GSTRING_LEN);
 			data += ETH_GSTRING_LEN;
 		}
+		for (i = 0; i < enic->rq_count; i++) {
+			for (j = 0; j < NUM_ENIC_PER_RQ_STATS; j++) {
+				snprintf(data, ETH_GSTRING_LEN,
+					 enic_per_rq_stats[j].name, i);
+				data += ETH_GSTRING_LEN;
+			}
+		}
+		for (i = 0; i < enic->wq_count; i++) {
+			for (j = 0; j < NUM_ENIC_PER_WQ_STATS; j++) {
+				snprintf(data, ETH_GSTRING_LEN,
+					 enic_per_wq_stats[j].name, i);
+				data += ETH_GSTRING_LEN;
+			}
+		}
 		break;
 	}
 }
@@ -242,9 +295,19 @@ static int enic_set_ringparam(struct net_device *netdev,
 
 static int enic_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct enic *enic = netdev_priv(netdev);
+	unsigned int n_per_rq_stats;
+	unsigned int n_per_wq_stats;
+	unsigned int n_stats;
+
 	switch (sset) {
 	case ETH_SS_STATS:
-		return enic_n_tx_stats + enic_n_rx_stats + enic_n_gen_stats;
+		n_per_rq_stats = NUM_ENIC_PER_RQ_STATS * enic->rq_count;
+		n_per_wq_stats = NUM_ENIC_PER_WQ_STATS * enic->wq_count;
+		n_stats = NUM_ENIC_TX_STATS + NUM_ENIC_RX_STATS +
+			NUM_ENIC_GEN_STATS +
+			n_per_rq_stats + n_per_wq_stats;
+		return n_stats;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -256,6 +319,7 @@ static void enic_get_ethtool_stats(struct net_device *netdev,
 	struct enic *enic = netdev_priv(netdev);
 	struct vnic_stats *vstats;
 	unsigned int i;
+	unsigned int j;
 	int err;
 
 	err = enic_dev_stats_dump(enic, &vstats);
@@ -266,12 +330,30 @@ static void enic_get_ethtool_stats(struct net_device *netdev,
 	if (err == -ENOMEM)
 		return;
 
-	for (i = 0; i < enic_n_tx_stats; i++)
+	for (i = 0; i < NUM_ENIC_TX_STATS; i++)
 		*(data++) = ((u64 *)&vstats->tx)[enic_tx_stats[i].index];
-	for (i = 0; i < enic_n_rx_stats; i++)
+	for (i = 0; i < NUM_ENIC_RX_STATS; i++)
 		*(data++) = ((u64 *)&vstats->rx)[enic_rx_stats[i].index];
-	for (i = 0; i < enic_n_gen_stats; i++)
+	for (i = 0; i < NUM_ENIC_GEN_STATS; i++)
 		*(data++) = ((u64 *)&enic->gen_stats)[enic_gen_stats[i].index];
+	for (i = 0; i < enic->rq_count; i++) {
+		struct enic_rq_stats *rqstats = &enic->rq_stats[i];
+		int index;
+
+		for (j = 0; j < NUM_ENIC_PER_RQ_STATS; j++) {
+			index = enic_per_rq_stats[j].index;
+			*(data++) = ((u64 *)rqstats)[index];
+		}
+	}
+	for (i = 0; i < enic->wq_count; i++) {
+		struct enic_wq_stats *wqstats = &enic->wq_stats[i];
+		int index;
+
+		for (j = 0; j < NUM_ENIC_PER_WQ_STATS; j++) {
+			index = enic_per_wq_stats[j].index;
+			*(data++) = ((u64 *)wqstats)[index];
+		}
+	}
 }
 
 static u32 enic_get_msglevel(struct net_device *netdev)