Merge branch 'ethtool-provide-the-dim-profile-fine-tuning-channel'

Heng Qi says:

====================
ethtool: provide the dim profile fine-tuning channel

The NetDIM library provides excellent acceleration for many modern
network cards. However, the default profiles of DIM limits its maximum
capabilities for different NICs, so providing a way which the NIC can
be custom configured is necessary.

Currently, the way is based on the commonly used "ethtool -C".

For example,
on the server side, the virtio-net NIC with rx dim enabled has 8
queues and runs nginx.
The client uses the following command to send traffic to the server:
  ./wrk http://server_ip:80 -c 64 -t 5 -d 30

Then adjust the default rx-profile for server dim to

  {.usec =   1, .pkts = 256, .comps = n/a,},
  {.usec =   8, .pkts = 256, .comps = n/a,},
  {.usec =  30, .pkts = 256, .comps = n/a,},
  {.usec =  64, .pkts = 256, .comps = n/a,},
  {.usec = 128, .pkts = 256, .comps = n/a,}

The server PPS is improved by 20%+.
====================

Link: https://patch.msgid.link/20240621101353.107425-1-hengqi@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 141 insertions, 1 deletions

diff --git a/include/linux/dim.h b/include/linux/dim.h
index f343bc9aa2ec..1b581ff25a15 100644
--- a/include/linux/dim.h
+++ b/include/linux/dim.h
@@ -10,6 +10,15 @@
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
+struct net_device;
+
+/* Number of DIM profiles and period mode. */
+#define NET_DIM_PARAMS_NUM_PROFILES 5
+#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256
+#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128
+#define NET_DIM_DEF_PROFILE_CQE 1
+#define NET_DIM_DEF_PROFILE_EQE 1
+
 /*
  * Number of events between DIM iterations.
  * Causes a moderation of the algorithm run.
@@ -38,12 +47,45 @@
  * @pkts: CQ packet counter suggestion (by DIM)
  * @comps: Completion counter
  * @cq_period_mode: CQ period count mode (from CQE/EQE)
+ * @rcu: for asynchronous kfree_rcu
  */
 struct dim_cq_moder {
 	u16 usec;
 	u16 pkts;
 	u16 comps;
 	u8 cq_period_mode;
+	struct rcu_head rcu;
+};
+
+#define DIM_PROFILE_RX		BIT(0)	/* support rx profile modification */
+#define DIM_PROFILE_TX		BIT(1)	/* support tx profile modification */
+
+#define DIM_COALESCE_USEC	BIT(0)	/* support usec field modification */
+#define DIM_COALESCE_PKTS	BIT(1)	/* support pkts field modification */
+#define DIM_COALESCE_COMPS	BIT(2)	/* support comps field modification */
+
+/**
+ * struct dim_irq_moder - Structure for irq moderation information.
+ * Used to collect irq moderation related information.
+ *
+ * @profile_flags: DIM_PROFILE_*
+ * @coal_flags: DIM_COALESCE_* for Rx and Tx
+ * @dim_rx_mode: Rx DIM period count mode: CQE or EQE
+ * @dim_tx_mode: Tx DIM period count mode: CQE or EQE
+ * @rx_profile: DIM profile list for Rx
+ * @tx_profile: DIM profile list for Tx
+ * @rx_dim_work: Rx DIM worker scheduled by net_dim()
+ * @tx_dim_work: Tx DIM worker scheduled by net_dim()
+ */
+struct dim_irq_moder {
+	u8 profile_flags;
+	u8 coal_flags;
+	u8 dim_rx_mode;
+	u8 dim_tx_mode;
+	struct dim_cq_moder __rcu *rx_profile;
+	struct dim_cq_moder __rcu *tx_profile;
+	void (*rx_dim_work)(struct work_struct *work);
+	void (*tx_dim_work)(struct work_struct *work);
 };
 
 /**
@@ -192,6 +234,77 @@ enum dim_step_result {
 };
 
 /**
+ * net_dim_init_irq_moder - collect information to initialize irq moderation
+ * @dev: target network device
+ * @profile_flags: Rx or Tx profile modification capability
+ * @coal_flags: irq moderation params flags
+ * @rx_mode: CQ period mode for Rx
+ * @tx_mode: CQ period mode for Tx
+ * @rx_dim_work: Rx worker called after dim decision
+ * @tx_dim_work: Tx worker called after dim decision
+ *
+ * Return: 0 on success or a negative error code.
+ */
+int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags,
+			   u8 coal_flags, u8 rx_mode, u8 tx_mode,
+			   void (*rx_dim_work)(struct work_struct *work),
+			   void (*tx_dim_work)(struct work_struct *work));
+
+/**
+ * net_dim_free_irq_moder - free fields for irq moderation
+ * @dev: target network device
+ */
+void net_dim_free_irq_moder(struct net_device *dev);
+
+/**
+ * net_dim_setting - initialize DIM's cq mode and schedule worker
+ * @dev: target network device
+ * @dim: DIM context
+ * @is_tx: true indicates the tx direction, false indicates the rx direction
+ */
+void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx);
+
+/**
+ * net_dim_work_cancel - synchronously cancel dim's worker
+ * @dim: DIM context
+ */
+void net_dim_work_cancel(struct dim *dim);
+
+/**
+ * net_dim_get_rx_irq_moder - get DIM rx results based on profile_ix
+ * @dev: target network device
+ * @dim: DIM context
+ *
+ * Return: DIM irq moderation
+ */
+struct dim_cq_moder
+net_dim_get_rx_irq_moder(struct net_device *dev, struct dim *dim);
+
+/**
+ * net_dim_get_tx_irq_moder - get DIM tx results based on profile_ix
+ * @dev: target network device
+ * @dim: DIM context
+ *
+ * Return: DIM irq moderation
+ */
+struct dim_cq_moder
+net_dim_get_tx_irq_moder(struct net_device *dev, struct dim *dim);
+
+/**
+ * net_dim_set_rx_mode - set DIM rx cq mode
+ * @dev: target network device
+ * @rx_mode: target rx cq mode
+ */
+void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode);
+
+/**
+ * net_dim_set_tx_mode - set DIM tx cq mode
+ * @dev: target network device
+ * @tx_mode: target tx cq mode
+ */
+void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode);
+
+/**
  *	dim_on_top - check if current state is a good place to stop (top location)
  *	@dim: DIM context
  *
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 6fd9107d3cc0..959196af7f5a 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -284,7 +284,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
 #define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES	BIT(24)
 #define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES	BIT(25)
 #define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS	BIT(26)
-#define ETHTOOL_COALESCE_ALL_PARAMS		GENMASK(26, 0)
+#define ETHTOOL_COALESCE_RX_PROFILE		BIT(27)
+#define ETHTOOL_COALESCE_TX_PROFILE		BIT(28)
+#define ETHTOOL_COALESCE_ALL_PARAMS		GENMASK(28, 0)
 
 #define ETHTOOL_COALESCE_USECS						\
 	(ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4e81660b4462..cc18acd3c58b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2402,6 +2402,9 @@ struct net_device {
 	/** @page_pools: page pools created for this netdevice */
 	struct hlist_head	page_pools;
 #endif
+
+	/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
+	struct dim_irq_moder	*irq_moder;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index b49b804b9495..d15856c7e001 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -415,12 +415,34 @@ enum {
 	ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES,		/* u32 */
 	ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES,		/* u32 */
 	ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS,		/* u32 */
+	/* nest - _A_PROFILE_IRQ_MODERATION */
+	ETHTOOL_A_COALESCE_RX_PROFILE,
+	/* nest - _A_PROFILE_IRQ_MODERATION */
+	ETHTOOL_A_COALESCE_TX_PROFILE,
 
 	/* add new constants above here */
 	__ETHTOOL_A_COALESCE_CNT,
 	ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1)
 };
 
+enum {
+	ETHTOOL_A_PROFILE_UNSPEC,
+	/* nest, _A_IRQ_MODERATION_* */
+	ETHTOOL_A_PROFILE_IRQ_MODERATION,
+	__ETHTOOL_A_PROFILE_CNT,
+	ETHTOOL_A_PROFILE_MAX = (__ETHTOOL_A_PROFILE_CNT - 1)
+};
+
+enum {
+	ETHTOOL_A_IRQ_MODERATION_UNSPEC,
+	ETHTOOL_A_IRQ_MODERATION_USEC,			/* u32 */
+	ETHTOOL_A_IRQ_MODERATION_PKTS,			/* u32 */
+	ETHTOOL_A_IRQ_MODERATION_COMPS,			/* u32 */
+
+	__ETHTOOL_A_IRQ_MODERATION_CNT,
+	ETHTOOL_A_IRQ_MODERATION_MAX = (__ETHTOOL_A_IRQ_MODERATION_CNT - 1)
+};
+
 /* PAUSE */
 
 enum {