netdev: add queue stats

These stats are commonly. Support reporting those via netdev-genl queue
stats.

name: rx-hw-drops
name: rx-hw-drop-overruns
name: rx-csum-unnecessary
name: rx-csum-none
name: rx-csum-bad
name: rx-hw-gro-packets
name: rx-hw-gro-bytes
name: rx-hw-gro-wire-packets
name: rx-hw-gro-wire-bytes
name: rx-hw-drop-ratelimits
name: tx-hw-drops
name: tx-hw-drop-errors
name: tx-csum-none
name: tx-needs-csum
name: tx-hw-gso-packets
name: tx-hw-gso-bytes
name: tx-hw-gso-wire-packets
name: tx-hw-gso-wire-bytes
name: tx-hw-drop-ratelimits

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

5 files changed, 190 insertions, 2 deletions

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 679c4130707cd7..2be4b3714d1757 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -335,6 +335,110 @@ attribute-sets:
           Allocation failure may, or may not result in a packet drop, depending
           on driver implementation and whether system recovers quickly.
         type: uint
+      -
+        name: rx-hw-drops
+        doc: |
+          Number of all packets which entered the device, but never left it,
+          including but not limited to: packets dropped due to lack of buffer
+          space, processing errors, explicit or implicit policies and packet
+          filters.
+        type: uint
+      -
+        name: rx-hw-drop-overruns
+        doc: |
+          Number of packets dropped due to transient lack of resources, such as
+          buffer space, host descriptors etc.
+        type: uint
+      -
+        name: rx-csum-unnecessary
+        doc: Number of packets that were marked as CHECKSUM_UNNECESSARY.
+        type: uint
+      -
+        name: rx-csum-none
+        doc: Number of packets that were not checksummed by device.
+        type: uint
+      -
+        name: rx-csum-bad
+        doc: |
+          Number of packets with bad checksum. The packets are not discarded,
+          but still delivered to the stack.
+        type: uint
+      -
+        name: rx-hw-gro-packets
+        doc: |
+          Number of packets that were coalesced from smaller packets by the device.
+          Counts only packets coalesced with the HW-GRO netdevice feature,
+          LRO-coalesced packets are not counted.
+        type: uint
+      -
+        name: rx-hw-gro-bytes
+        doc: See `rx-hw-gro-packets`.
+        type: uint
+      -
+        name: rx-hw-gro-wire-packets
+        doc: |
+          Number of packets that were coalesced to bigger packetss with the HW-GRO
+          netdevice feature. LRO-coalesced packets are not counted.
+        type: uint
+      -
+        name: rx-hw-gro-wire-bytes
+        doc: See `rx-hw-gro-wire-packets`.
+        type: uint
+      -
+        name: rx-hw-drop-ratelimits
+        doc: |
+          Number of the packets dropped by the device due to the received
+          packets bitrate exceeding the device rate limit.
+        type: uint
+      -
+        name: tx-hw-drops
+        doc: |
+          Number of packets that arrived at the device but never left it,
+          encompassing packets dropped for reasons such as processing errors, as
+          well as those affected by explicitly defined policies and packet
+          filtering criteria.
+        type: uint
+      -
+        name: tx-hw-drop-errors
+        doc: Number of packets dropped because they were invalid or malformed.
+        type: uint
+      -
+        name: tx-csum-none
+        doc: |
+          Number of packets that did not require the device to calculate the
+          checksum.
+        type: uint
+      -
+        name: tx-needs-csum
+        doc: |
+          Number of packets that required the device to calculate the checksum.
+        type: uint
+      -
+        name: tx-hw-gso-packets
+        doc: |
+          Number of packets that necessitated segmentation into smaller packets
+          by the device.
+        type: uint
+      -
+        name: tx-hw-gso-bytes
+        doc: See `tx-hw-gso-packets`.
+        type: uint
+      -
+        name: tx-hw-gso-wire-packets
+        doc: |
+          Number of wire-sized packets generated by processing
+          `tx-hw-gso-packets`
+        type: uint
+      -
+        name: tx-hw-gso-wire-bytes
+        doc: See `tx-hw-gso-wire-packets`.
+        type: uint
+      -
+        name: tx-hw-drop-ratelimits
+        doc: |
+          Number of the packets dropped by the device due to the transmit
+          packets bitrate exceeding the device rate limit.
+        type: uint
 
 operations:
   list:
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 1ec4085853738d..c7ac4539eafc55 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -9,11 +9,38 @@ struct netdev_queue_stats_rx {
 	u64 bytes;
 	u64 packets;
 	u64 alloc_fail;
+
+	u64 hw_drops;
+	u64 hw_drop_overruns;
+
+	u64 csum_unnecessary;
+	u64 csum_none;
+	u64 csum_bad;
+
+	u64 hw_gro_packets;
+	u64 hw_gro_bytes;
+	u64 hw_gro_wire_packets;
+	u64 hw_gro_wire_bytes;
+
+	u64 hw_drop_ratelimits;
 };
 
 struct netdev_queue_stats_tx {
 	u64 bytes;
 	u64 packets;
+
+	u64 hw_drops;
+	u64 hw_drop_errors;
+
+	u64 csum_none;
+	u64 needs_csum;
+
+	u64 hw_gso_packets;
+	u64 hw_gso_bytes;
+	u64 hw_gso_wire_packets;
+	u64 hw_gso_wire_bytes;
+
+	u64 hw_drop_ratelimits;
 };
 
 /**
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index bb65ee840cdac8..cf24f1d9adf833 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -146,6 +146,25 @@ enum {
 	NETDEV_A_QSTATS_TX_PACKETS,
 	NETDEV_A_QSTATS_TX_BYTES,
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
+	NETDEV_A_QSTATS_RX_HW_DROPS,
+	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
+	NETDEV_A_QSTATS_RX_CSUM_NONE,
+	NETDEV_A_QSTATS_RX_CSUM_BAD,
+	NETDEV_A_QSTATS_RX_HW_GRO_PACKETS,
+	NETDEV_A_QSTATS_RX_HW_GRO_BYTES,
+	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS,
+	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES,
+	NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS,
+	NETDEV_A_QSTATS_TX_HW_DROPS,
+	NETDEV_A_QSTATS_TX_HW_DROP_ERRORS,
+	NETDEV_A_QSTATS_TX_CSUM_NONE,
+	NETDEV_A_QSTATS_TX_NEEDS_CSUM,
+	NETDEV_A_QSTATS_TX_HW_GSO_PACKETS,
+	NETDEV_A_QSTATS_TX_HW_GSO_BYTES,
+	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS,
+	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES,
+	NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS,
 
 	__NETDEV_A_QSTATS_MAX,
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index dd6510f2c65259..4b5054087309ef 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -489,7 +489,17 @@ netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx)
 {
 	if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) ||
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) ||
-	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail))
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROPS, rx->hw_drops) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, rx->hw_drop_overruns) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, rx->csum_unnecessary) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_NONE, rx->csum_none) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_BAD, rx->csum_bad) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, rx->hw_gro_packets) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_BYTES, rx->hw_gro_bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, rx->hw_gro_wire_packets) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, rx->hw_gro_wire_bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, rx->hw_drop_ratelimits))
 		return -EMSGSIZE;
 	return 0;
 }
@@ -498,7 +508,16 @@ static int
 netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx)
 {
 	if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) ||
-	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes))
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROPS, tx->hw_drops) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, tx->hw_drop_errors) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_CSUM_NONE, tx->csum_none) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_NEEDS_CSUM, tx->needs_csum) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, tx->hw_gso_packets) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_BYTES, tx->hw_gso_bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, tx->hw_gso_wire_packets) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, tx->hw_gso_wire_bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits))
 		return -EMSGSIZE;
 	return 0;
 }
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index bb65ee840cdac8..cf24f1d9adf833 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -146,6 +146,25 @@ enum {
 	NETDEV_A_QSTATS_TX_PACKETS,
 	NETDEV_A_QSTATS_TX_BYTES,
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
+	NETDEV_A_QSTATS_RX_HW_DROPS,
+	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
+	NETDEV_A_QSTATS_RX_CSUM_NONE,
+	NETDEV_A_QSTATS_RX_CSUM_BAD,
+	NETDEV_A_QSTATS_RX_HW_GRO_PACKETS,
+	NETDEV_A_QSTATS_RX_HW_GRO_BYTES,
+	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS,
+	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES,
+	NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS,
+	NETDEV_A_QSTATS_TX_HW_DROPS,
+	NETDEV_A_QSTATS_TX_HW_DROP_ERRORS,
+	NETDEV_A_QSTATS_TX_CSUM_NONE,
+	NETDEV_A_QSTATS_TX_NEEDS_CSUM,
+	NETDEV_A_QSTATS_TX_HW_GSO_PACKETS,
+	NETDEV_A_QSTATS_TX_HW_GSO_BYTES,
+	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS,
+	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES,
+	NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS,
 
 	__NETDEV_A_QSTATS_MAX,
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)