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.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/netlink/specs/ethtool.yaml

@@ -414,6 +414,26 @@ attribute-sets:
         name: combined-count
         type: u32
 
+  -
+    name: irq-moderation
+    attributes:
+      -
+        name: usec
+        type: u32
+      -
+        name: pkts
+        type: u32
+      -
+        name: comps
+        type: u32
+  -
+    name: profile
+    attributes:
+      -
+        name: irq-moderation
+        type: nest
+        multi-attr: true
+        nested-attributes: irq-moderation
   -
     name: coalesce
     attributes:
@@ -502,6 +522,15 @@ attribute-sets:
       -
         name: tx-aggr-time-usecs
         type: u32
+      -
+        name: rx-profile
+        type: nest
+        nested-attributes: profile
+      -
+        name: tx-profile
+        type: nest
+        nested-attributes: profile
+
   -
     name: pause-stat
     attributes:
@@ -1325,6 +1354,8 @@ operations:
             - tx-aggr-max-bytes
             - tx-aggr-max-frames
             - tx-aggr-time-usecs
+            - rx-profile
+            - tx-profile
       dump: *coalesce-get-op
     -
       name: coalesce-set

Documentation/networking/ethtool-netlink.rst

@@ -1033,6 +1033,8 @@ Kernel response contents:
   ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES``     u32     max aggr size, Tx
   ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES``    u32     max aggr packets, Tx
   ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS``    u32     time (us), aggr, Tx
+  ``ETHTOOL_A_COALESCE_RX_PROFILE``            nested  profile of DIM, Rx
+  ``ETHTOOL_A_COALESCE_TX_PROFILE``            nested  profile of DIM, Tx
   ===========================================  ======  =======================
 
 Attributes are only included in reply if their value is not zero or the
@@ -1062,6 +1064,10 @@ block should be sent.
 This feature is mainly of interest for specific USB devices which does not cope
 well with frequent small-sized URBs transmissions.
 
+``ETHTOOL_A_COALESCE_RX_PROFILE`` and ``ETHTOOL_A_COALESCE_TX_PROFILE`` refer
+to DIM parameters, see `Generic Network Dynamic Interrupt Moderation (Net DIM)
+<https://www.kernel.org/doc/Documentation/networking/net_dim.rst>`_.
+
 COALESCE_SET
 ============
 
@@ -1098,6 +1104,8 @@ Request contents:
   ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES``     u32     max aggr size, Tx
   ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES``    u32     max aggr packets, Tx
   ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS``    u32     time (us), aggr, Tx
+  ``ETHTOOL_A_COALESCE_RX_PROFILE``            nested  profile of DIM, Rx
+  ``ETHTOOL_A_COALESCE_TX_PROFILE``            nested  profile of DIM, Tx
   ===========================================  ======  =======================
 
 Request is rejected if it attributes declared as unsupported by driver (i.e.

Documentation/networking/net_dim.rst

@@ -169,6 +169,48 @@ usage is not complete but it should make the outline of the usage clear.
 	...
   }
 
+
+Tuning DIM
+==========
+
+Net DIM serves a range of network devices and delivers excellent acceleration
+benefits. Yet, it has been observed that some preset configurations of DIM may
+not align seamlessly with the varying specifications of network devices, and
+this discrepancy has been identified as a factor to the suboptimal performance
+outcomes of DIM-enabled network devices, related to a mismatch in profiles.
+
+To address this issue, Net DIM introduces a per-device control to modify and
+access a device's ``rx-profile`` and ``tx-profile`` parameters:
+Assume that the target network device is named ethx, and ethx only declares
+support for RX profile setting and supports modification of ``usec`` field
+and ``pkts`` field (See the data structure:
+:c:type:`struct dim_cq_moder <dim_cq_moder>`).
+
+You can use ethtool to modify the current RX DIM profile where all
+values are 64::
+
+    $ ethtool -C ethx rx-profile 1,1,n_2,2,n_3,n,n_n,4,n_n,n,n
+
+``n`` means do not modify this field, and ``_`` separates structure
+elements of the profile array.
+
+Querying the current profiles using::
+
+    $ ethtool -c ethx
+    ...
+    rx-profile:
+    {.usec =   1, .pkts =   1, .comps = n/a,},
+    {.usec =   2, .pkts =   2, .comps = n/a,},
+    {.usec =   3, .pkts =  64, .comps = n/a,},
+    {.usec =  64, .pkts =   4, .comps = n/a,},
+    {.usec =  64, .pkts =  64, .comps = n/a,}
+    tx-profile:   n/a
+
+If the network device does not support specific fields of DIM profiles,
+the corresponding ``n/a`` will display. If the ``n/a`` field is being
+modified, error messages will be reported.
+
+
 Dynamic Interrupt Moderation (DIM) library API
 ==============================================
 

drivers/net/virtio_net.c

@@ -2469,6 +2469,13 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 	return err;
 }
 
+static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim)
+{
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		return;
+	net_dim_work_cancel(dim);
+}
+
 static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -2495,7 +2502,7 @@ static int virtnet_open(struct net_device *dev)
 
 	for (i--; i >= 0; i--) {
 		virtnet_disable_queue_pair(vi, i);
-		cancel_work_sync(&vi->rq[i].dim.work);
+		virtnet_cancel_dim(vi, &vi->rq[i].dim);
 	}
 
 	return err;
@@ -2671,7 +2678,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
 
 	if (running) {
 		napi_disable(&rq->napi);
-		cancel_work_sync(&rq->dim.work);
+		virtnet_cancel_dim(vi, &rq->dim);
 	}
 
 	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf);
@@ -2932,7 +2939,7 @@ static int virtnet_close(struct net_device *dev)
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		virtnet_disable_queue_pair(vi, i);
-		cancel_work_sync(&vi->rq[i].dim.work);
+		virtnet_cancel_dim(vi, &vi->rq[i].dim);
 	}
 
 	return 0;
@@ -4458,7 +4465,7 @@ static void virtnet_rx_dim_work(struct work_struct *work)
 	if (!rq->dim_enabled)
 		goto out;
 
-	update_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+	update_moder = net_dim_get_rx_irq_moder(dev, dim);
 	if (update_moder.usec != rq->intr_coal.max_usecs ||
 	    update_moder.pkts != rq->intr_coal.max_packets) {
 		err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum,
@@ -5158,6 +5165,36 @@ static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue)
 		   jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start)));
 }
 
+static int virtnet_init_irq_moder(struct virtnet_info *vi)
+{
+	u8 profile_flags = 0, coal_flags = 0;
+	int ret, i;
+
+	profile_flags |= DIM_PROFILE_RX;
+	coal_flags |= DIM_COALESCE_USEC | DIM_COALESCE_PKTS;
+	ret = net_dim_init_irq_moder(vi->dev, profile_flags, coal_flags,
+				     DIM_CQ_PERIOD_MODE_START_FROM_EQE,
+				     0, virtnet_rx_dim_work, NULL);
+
+	if (ret)
+		return ret;
+
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		net_dim_setting(vi->dev, &vi->rq[i].dim, false);
+
+	return 0;
+}
+
+static void virtnet_free_irq_moder(struct virtnet_info *vi)
+{
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		return;
+
+	rtnl_lock();
+	net_dim_free_irq_moder(vi->dev);
+	rtnl_unlock();
+}
+
 static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
@@ -5437,9 +5474,6 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 					 virtnet_poll_tx,
 					 napi_tx ? napi_weight : 0);
 
-		INIT_WORK(&vi->rq[i].dim.work, virtnet_rx_dim_work);
-		vi->rq[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
-
 		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
 		ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len);
 		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
@@ -5868,6 +5902,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 		for (i = 0; i < vi->max_queue_pairs; i++)
 			if (vi->sq[i].napi.weight)
 				vi->sq[i].intr_coal.max_packets = 1;
+
+		err = virtnet_init_irq_moder(vi);
+		if (err)
+			goto free;
 	}
 
 #ifdef CONFIG_SYSFS
@@ -6019,6 +6057,8 @@ static void virtnet_remove(struct virtio_device *vdev)
 	disable_rx_mode_work(vi);
 	flush_work(&vi->rx_mode_work);
 
+	virtnet_free_irq_moder(vi);
+
 	unregister_netdev(vi->dev);
 
 	net_failover_destroy(vi->failover);

drivers/soc/fsl/Kconfig

@@ -22,7 +22,7 @@ config FSL_GUTS
 
 config FSL_MC_DPIO
         tristate "QorIQ DPAA2 DPIO driver"
-        depends on FSL_MC_BUS
+        depends on FSL_MC_BUS && NET
         select SOC_BUS
         select FSL_GUTS
         select DIMLIB

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);
 };
 
 /**
@@ -191,6 +233,77 @@ enum dim_step_result {
 	DIM_ON_EDGE,
 };
 
+/**
+ * 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

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)

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)
 

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 {

lib/Kconfig

@@ -623,6 +623,7 @@ config SIGNATURE
 
 config DIMLIB
 	tristate
+	depends on NET
 	help
 	  Dynamic Interrupt Moderation library.
 	  Implements an algorithm for dynamically changing CQ moderation values

lib/dim/net_dim.c

@@ -4,6 +4,7 @@
  */
 
 #include <linux/dim.h>
+#include <linux/rtnetlink.h>
 
 /*
  * Net DIM profiles:
@@ -11,12 +12,6 @@
  *        There are different set of profiles for RX/TX CQs.
  *        Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES
  */
-#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
-
 #define NET_DIM_RX_EQE_PROFILES { \
 	{.usec = 1,   .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \
 	{.usec = 8,   .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \
@@ -101,6 +96,143 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode)
 }
 EXPORT_SYMBOL(net_dim_get_def_tx_moderation);
 
+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))
+{
+	struct dim_cq_moder *rxp = NULL, *txp;
+	struct dim_irq_moder *moder;
+	int len;
+
+	dev->irq_moder = kzalloc(sizeof(*dev->irq_moder), GFP_KERNEL);
+	if (!dev->irq_moder)
+		return -ENOMEM;
+
+	moder = dev->irq_moder;
+	len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_profile);
+
+	moder->coal_flags = coal_flags;
+	moder->profile_flags = profile_flags;
+
+	if (profile_flags & DIM_PROFILE_RX) {
+		moder->rx_dim_work = rx_dim_work;
+		moder->dim_rx_mode = rx_mode;
+		rxp = kmemdup(rx_profile[rx_mode], len, GFP_KERNEL);
+		if (!rxp)
+			goto free_moder;
+
+		rcu_assign_pointer(moder->rx_profile, rxp);
+	}
+
+	if (profile_flags & DIM_PROFILE_TX) {
+		moder->tx_dim_work = tx_dim_work;
+		moder->dim_tx_mode = tx_mode;
+		txp = kmemdup(tx_profile[tx_mode], len, GFP_KERNEL);
+		if (!txp)
+			goto free_rxp;
+
+		rcu_assign_pointer(moder->tx_profile, txp);
+	}
+
+	return 0;
+
+free_rxp:
+	kfree(rxp);
+free_moder:
+	kfree(moder);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(net_dim_init_irq_moder);
+
+/* RTNL lock is held. */
+void net_dim_free_irq_moder(struct net_device *dev)
+{
+	struct dim_cq_moder *rxp, *txp;
+
+	if (!dev->irq_moder)
+		return;
+
+	rxp = rtnl_dereference(dev->irq_moder->rx_profile);
+	txp = rtnl_dereference(dev->irq_moder->tx_profile);
+
+	rcu_assign_pointer(dev->irq_moder->rx_profile, NULL);
+	rcu_assign_pointer(dev->irq_moder->tx_profile, NULL);
+
+	kfree_rcu(rxp, rcu);
+	kfree_rcu(txp, rcu);
+	kfree(dev->irq_moder);
+}
+EXPORT_SYMBOL(net_dim_free_irq_moder);
+
+void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx)
+{
+	struct dim_irq_moder *irq_moder = dev->irq_moder;
+
+	if (!irq_moder)
+		return;
+
+	if (is_tx) {
+		INIT_WORK(&dim->work, irq_moder->tx_dim_work);
+		dim->mode = READ_ONCE(irq_moder->dim_tx_mode);
+		return;
+	}
+
+	INIT_WORK(&dim->work, irq_moder->rx_dim_work);
+	dim->mode = READ_ONCE(irq_moder->dim_rx_mode);
+}
+EXPORT_SYMBOL(net_dim_setting);
+
+void net_dim_work_cancel(struct dim *dim)
+{
+	cancel_work_sync(&dim->work);
+}
+EXPORT_SYMBOL(net_dim_work_cancel);
+
+struct dim_cq_moder net_dim_get_rx_irq_moder(struct net_device *dev,
+					     struct dim *dim)
+{
+	struct dim_cq_moder res, *profile;
+
+	rcu_read_lock();
+	profile = rcu_dereference(dev->irq_moder->rx_profile);
+	res = profile[dim->profile_ix];
+	rcu_read_unlock();
+
+	res.cq_period_mode = dim->mode;
+
+	return res;
+}
+EXPORT_SYMBOL(net_dim_get_rx_irq_moder);
+
+struct dim_cq_moder net_dim_get_tx_irq_moder(struct net_device *dev,
+					     struct dim *dim)
+{
+	struct dim_cq_moder res, *profile;
+
+	rcu_read_lock();
+	profile = rcu_dereference(dev->irq_moder->tx_profile);
+	res = profile[dim->profile_ix];
+	rcu_read_unlock();
+
+	res.cq_period_mode = dim->mode;
+
+	return res;
+}
+EXPORT_SYMBOL(net_dim_get_tx_irq_moder);
+
+void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode)
+{
+	WRITE_ONCE(dev->irq_moder->dim_rx_mode, rx_mode);
+}
+EXPORT_SYMBOL(net_dim_set_rx_mode);
+
+void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode)
+{
+	WRITE_ONCE(dev->irq_moder->dim_tx_mode, tx_mode);
+}
+EXPORT_SYMBOL(net_dim_set_tx_mode);
+
 static int net_dim_step(struct dim *dim)
 {
 	if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2))

net/Kconfig

@@ -508,6 +508,7 @@ config FAILOVER
 
 config ETHTOOL_NETLINK
 	bool "Netlink interface for ethtool"
+	select DIMLIB
 	default y
 	help
 	  An alternative userspace interface for ethtool based on generic