netdev: add per-queue statistics

The ethtool-nl family does a good job exposing various protocol
related and IEEE/IETF statistics which used to get dumped under
ethtool -S, with creative names. Queue stats don't have a netlink
API, yet, and remain a lion's share of ethtool -S output for new
drivers. Not only is that bad because the names differ driver to
driver but it's also bug-prone. Intuitively drivers try to report
only the stats for active queues, but querying ethtool stats
involves multiple system calls, and the number of stats is
read separately from the stats themselves. Worse still when user
space asks for values of the stats, it doesn't inform the kernel
how big the buffer is. If number of stats increases in the meantime
kernel will overflow user buffer.

Add a netlink API for dumping queue stats. Queue information is
exposed via the netdev-genl family, so add the stats there.
Support per-queue and sum-for-device dumps. Latter will be useful
when subsequent patches add more interesting common stats than
just bytes and packets.

The API does not currently distinguish between HW and SW stats.
The expectation is that the source of the stats will either not
matter much (good packets) or be obvious (skb alloc errors).

Acked-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240306195509.1502746-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 76 insertions, 0 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 416a800d72ba..4230c7f3b959 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1955,6 +1955,7 @@ enum netdev_reg_state {
  *
  *	@sysfs_rx_queue_group:	Space for optional per-rx queue attributes
  *	@rtnl_link_ops:	Rtnl_link_ops
+ *	@stat_ops:	Optional ops for queue-aware statistics
  *
  *	@gso_max_size:	Maximum size of generic segmentation offload
  *	@tso_max_size:	Device (as in HW) limit on the max TSO request size
@@ -2335,6 +2336,8 @@ struct net_device {
 
 	const struct rtnl_link_ops *rtnl_link_ops;
 
+	const struct netdev_stat_ops *stat_ops;
+
 	/* for setting kernel sock attribute on TCP connection setup */
 #define GSO_MAX_SEGS		65535u
 #define GSO_LEGACY_MAX_SIZE	65536u
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 8b8ed4e13d74..d633347eeda5 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -4,6 +4,60 @@
 
 #include <linux/netdevice.h>
 
+struct netdev_queue_stats_rx {
+	u64 bytes;
+	u64 packets;
+};
+
+struct netdev_queue_stats_tx {
+	u64 bytes;
+	u64 packets;
+};
+
+/**
+ * struct netdev_stat_ops - netdev ops for fine grained stats
+ * @get_queue_stats_rx:	get stats for a given Rx queue
+ * @get_queue_stats_tx:	get stats for a given Tx queue
+ * @get_base_stats:	get base stats (not belonging to any live instance)
+ *
+ * Query stats for a given object. The values of the statistics are undefined
+ * on entry (specifically they are *not* zero-initialized). Drivers should
+ * assign values only to the statistics they collect. Statistics which are not
+ * collected must be left undefined.
+ *
+ * Queue objects are not necessarily persistent, and only currently active
+ * queues are queried by the per-queue callbacks. This means that per-queue
+ * statistics will not generally add up to the total number of events for
+ * the device. The @get_base_stats callback allows filling in the delta
+ * between events for currently live queues and overall device history.
+ * When the statistics for the entire device are queried, first @get_base_stats
+ * is issued to collect the delta, and then a series of per-queue callbacks.
+ * Only statistics which are set in @get_base_stats will be reported
+ * at the device level, meaning that unlike in queue callbacks, setting
+ * a statistic to zero in @get_base_stats is a legitimate thing to do.
+ * This is because @get_base_stats has a second function of designating which
+ * statistics are in fact correct for the entire device (e.g. when history
+ * for some of the events is not maintained, and reliable "total" cannot
+ * be provided).
+ *
+ * Device drivers can assume that when collecting total device stats,
+ * the @get_base_stats and subsequent per-queue calls are performed
+ * "atomically" (without releasing the rtnl_lock).
+ *
+ * Device drivers are encouraged to reset the per-queue statistics when
+ * number of queues change. This is because the primary use case for
+ * per-queue statistics is currently to detect traffic imbalance.
+ */
+struct netdev_stat_ops {
+	void (*get_queue_stats_rx)(struct net_device *dev, int idx,
+				   struct netdev_queue_stats_rx *stats);
+	void (*get_queue_stats_tx)(struct net_device *dev, int idx,
+				   struct netdev_queue_stats_tx *stats);
+	void (*get_base_stats)(struct net_device *dev,
+			       struct netdev_queue_stats_rx *rx,
+			       struct netdev_queue_stats_tx *tx);
+};
+
 /**
  * DOC: Lockless queue stopping / waking helpers.
  *
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 93cb411adf72..639ffa04c172 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -70,6 +70,10 @@ enum netdev_queue_type {
 	NETDEV_QUEUE_TYPE_TX,
 };
 
+enum netdev_qstats_scope {
+	NETDEV_QSTATS_SCOPE_QUEUE = 1,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
@@ -133,6 +137,20 @@ enum {
 };
 
 enum {
+	NETDEV_A_QSTATS_IFINDEX = 1,
+	NETDEV_A_QSTATS_QUEUE_TYPE,
+	NETDEV_A_QSTATS_QUEUE_ID,
+	NETDEV_A_QSTATS_SCOPE,
+	NETDEV_A_QSTATS_RX_PACKETS = 8,
+	NETDEV_A_QSTATS_RX_BYTES,
+	NETDEV_A_QSTATS_TX_PACKETS,
+	NETDEV_A_QSTATS_TX_BYTES,
+
+	__NETDEV_A_QSTATS_MAX,
+	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
+};
+
+enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
 	NETDEV_CMD_DEV_DEL_NTF,
@@ -144,6 +162,7 @@ enum {
 	NETDEV_CMD_PAGE_POOL_STATS_GET,
 	NETDEV_CMD_QUEUE_GET,
 	NETDEV_CMD_NAPI_GET,
+	NETDEV_CMD_QSTATS_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)