[PATCH net-next v7 0/4] ethtool: provide the dim profile fine-tuning channel

[PATCH net-next v7 0/4] ethtool: provide the dim profile fine-tuning channel

[Heng Qi]

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, interaction with the driver is still based on the commonly
used "ethtool -C".

Since the profile now exists in netdevice, adding a function similar
to net_dim_get_rx_moderation_dev() with netdevice as argument is
nice, but this would be better along with cleaning up the rest of
the drivers, which we can get to very soon after this set.

Please review, thank you very much!

Changelog
=====
v6->v7:
  - A new wrapper struct pointer is used in struct net_device.
  - Add IS_ENABLED(CONFIG_DIMLIB) to avoid compiler warnings.
  - Profile fields changed from u16 to u32.

v5->v6:
  - Place the profile in netdevice to bypass the driver.
    The interaction code of ethtool <-> kernel has not changed at all,
    only the interaction part of kernel <-> driver has changed.

v4->v5:
  - Update some snippets from Kuba, Thanks.

v3->v4:
  - Some tiny updates and patch 1 only add a new comment.

v2->v3:
  - Break up the attributes to avoid the use of raw c structs.
  - Use per-device profile instead of global profile in the driver.

v1->v2:
  - Use ethtool tool instead of net-sysfs

Heng Qi (4):
  linux/dim: move useful macros to .h file
  ethtool: provide customized dim profile management
  virtio-net: refactor dim initialization/destruction
  virtio-net: support dim profile fine-tuning

 Documentation/netlink/specs/ethtool.yaml     |  33 +++
 Documentation/networking/ethtool-netlink.rst |   8 +
 drivers/net/virtio_net.c                     |  46 +++--
 include/linux/dim.h                          |  13 ++
 include/linux/ethtool.h                      |  11 +-
 include/linux/netdevice.h                    |  24 +++
 include/uapi/linux/ethtool_netlink.h         |  24 +++
 lib/dim/net_dim.c                            |  10 +-
 net/core/dev.c                               |  83 ++++++++
 net/ethtool/coalesce.c                       | 199 ++++++++++++++++++-
 10 files changed, 428 insertions(+), 23 deletions(-)

-- 
2.32.0.3.g01195cf9f

[PATCH net-next v7 1/4] linux/dim: move useful macros to .h file

[Heng Qi]

These will be used in subsequent patches, including
newly declared profile arrays.

Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
---
 include/linux/dim.h | 13 +++++++++++++
 lib/dim/net_dim.c   | 10 ++--------
 2 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/include/linux/dim.h b/include/linux/dim.h
index f343bc9aa2ec..8149d2d6589c 100644
--- a/include/linux/dim.h
+++ b/include/linux/dim.h
@@ -10,6 +10,13 @@
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
+/* 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.
@@ -127,6 +134,12 @@ enum dim_cq_period_mode {
 	DIM_CQ_PERIOD_NUM_MODES
 };
 
+extern const struct dim_cq_moder
+rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES];
+
+extern const struct dim_cq_moder
+tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES];
+
 /**
  * enum dim_state - DIM algorithm states
  *
diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c
index 4e32f7aaac86..a649d9069c06 100644
--- a/lib/dim/net_dim.c
+++ b/lib/dim/net_dim.c
@@ -11,12 +11,6 @@
  *        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,}, \
@@ -49,13 +43,13 @@
 	{.usec = 64, .pkts = 32,}   \
 }
 
-static const struct dim_cq_moder
+const struct dim_cq_moder
 rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
 	NET_DIM_RX_EQE_PROFILES,
 	NET_DIM_RX_CQE_PROFILES,
 };
 
-static const struct dim_cq_moder
+const struct dim_cq_moder
 tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
 	NET_DIM_TX_EQE_PROFILES,
 	NET_DIM_TX_CQE_PROFILES,
-- 
2.32.0.3.g01195cf9f

[PATCH net-next v7 2/4] ethtool: provide customized dim profile management

[Heng Qi]

The NetDIM library, currently leveraged by an array of NICs, delivers
excellent acceleration benefits. Nevertheless, NICs vary significantly
in their dim profile list prerequisites.

Specifically, virtio-net backends may present diverse sw or hw device
implementation, making a one-size-fits-all parameter list impractical.
On Alibaba Cloud, the virtio DPU's performance under the default DIM
profile falls short of expectations, partly due to a mismatch in
parameter configuration.

I also noticed that ice/idpf/ena and other NICs have customized
profilelist or placed some restrictions on dim capabilities.

Motivated by this, I tried adding new params for "ethtool -C" that provides
a per-device control to modify and access a device's interrupt parameters.

Usage
========
The target NIC is named ethx.

Assume that ethx only declares support for ETHTOOL_COALESCE_RX_EQE_PROFILE
in ethtool_ops->supported_coalesce_params.

1. Query the currently customized list of the device

$ ethtool -c ethx
...
rx-eqe-profile:
{.usec =   1, .pkts = 256, .comps =   0,},
{.usec =   8, .pkts = 256, .comps =   0,},
{.usec =  64, .pkts = 256, .comps =   0,},
{.usec = 128, .pkts = 256, .comps =   0,},
{.usec = 256, .pkts = 256, .comps =   0,}
rx-cqe-profile:   n/a
tx-eqe-profile:   n/a
tx-cqe-profile:   n/a

2. Tune
$ ethtool -C ethx rx-eqe-profile 1,1,0_2,2,0_3,3,0_4,4,0_5,5,0
$ ethtool -c ethx
...
rx-eqe-profile:
{.usec =   1, .pkts =   1, .comps =   0,},
{.usec =   2, .pkts =   2, .comps =   0,},
{.usec =   3, .pkts =   3, .comps =   0,},
{.usec =   4, .pkts =   4, .comps =   0,},
{.usec =   5, .pkts =   5, .comps =   0,}
rx-cqe-profile:   n/a
tx-eqe-profile:   n/a
tx-cqe-profile:   n/a

3. Hint
If the device does not support some type of customized dim
profiles, the corresponding "n/a" will display.

Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
---
 Documentation/netlink/specs/ethtool.yaml     |  33 +++
 Documentation/networking/ethtool-netlink.rst |   8 +
 include/linux/ethtool.h                      |  11 +-
 include/linux/netdevice.h                    |  24 +++
 include/uapi/linux/ethtool_netlink.h         |  24 +++
 net/core/dev.c                               |  83 ++++++++
 net/ethtool/coalesce.c                       | 199 ++++++++++++++++++-
 7 files changed, 380 insertions(+), 2 deletions(-)

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 87ae7b397984..8165b598dab7 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -413,6 +413,18 @@ attribute-sets:
       -
         name: combined-count
         type: u32
+  -
+    name: moderation
+    attributes:
+      -
+        name: usec
+        type: u32
+      -
+        name: pkts
+        type: u32
+      -
+        name: comps
+        type: u32
 
   -
     name: coalesce
@@ -502,6 +514,23 @@ attribute-sets:
       -
         name: tx-aggr-time-usecs
         type: u32
+      -
+        name: rx-eqe-profile
+        type: nest
+        nested-attributes: moderation
+      -
+        name: rx-cqe-profile
+        type: nest
+        nested-attributes: moderation
+      -
+        name: tx-eqe-profile
+        type: nest
+        nested-attributes: moderation
+      -
+        name: tx-cqe-profile
+        type: nest
+        nested-attributes: moderation
+
   -
     name: pause-stat
     attributes:
@@ -1313,6 +1342,10 @@ operations:
             - tx-aggr-max-bytes
             - tx-aggr-max-frames
             - tx-aggr-time-usecs
+            - rx-eqe-profile
+            - rx-cqe-profile
+            - tx-eqe-profile
+            - tx-cqe-profile
       dump: *coalesce-get-op
     -
       name: coalesce-set
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 5dc42f7ce429..4d9eecf7d9d6 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1040,6 +1040,10 @@ 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_EQE_PROFILE``        nested  profile of DIM EQE, Rx
+  ``ETHTOOL_A_COALESCE_RX_CQE_PROFILE``        nested  profile of DIM CQE, Rx
+  ``ETHTOOL_A_COALESCE_TX_EQE_PROFILE``        nested  profile of DIM EQE, Tx
+  ``ETHTOOL_A_COALESCE_TX_CQE_PROFILE``        nested  profile of DIM CQE, Tx
   ===========================================  ======  =======================
 
 Attributes are only included in reply if their value is not zero or the
@@ -1105,6 +1109,10 @@ 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_EQE_PROFILE``        nested  profile of DIM EQE, Rx
+  ``ETHTOOL_A_COALESCE_RX_CQE_PROFILE``        nested  profile of DIM CQE, Rx
+  ``ETHTOOL_A_COALESCE_TX_EQE_PROFILE``        nested  profile of DIM EQE, Tx
+  ``ETHTOOL_A_COALESCE_TX_CQE_PROFILE``        nested  profile of DIM CQE, Tx
   ===========================================  ======  =======================
 
 Request is rejected if it attributes declared as unsupported by driver (i.e.
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 6fd9107d3cc0..614a113eda29 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -284,7 +284,11 @@ 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_EQE_PROFILE         BIT(27)
+#define ETHTOOL_COALESCE_RX_CQE_PROFILE         BIT(28)
+#define ETHTOOL_COALESCE_TX_EQE_PROFILE         BIT(29)
+#define ETHTOOL_COALESCE_TX_CQE_PROFILE         BIT(30)
+#define ETHTOOL_COALESCE_ALL_PARAMS		GENMASK(30, 0)
 
 #define ETHTOOL_COALESCE_USECS						\
 	(ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS)
@@ -316,6 +320,11 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
 	(ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES |	\
 	 ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES |	\
 	 ETHTOOL_COALESCE_TX_AGGR_TIME_USECS)
+#define ETHTOOL_COALESCE_PROFILE		\
+	(ETHTOOL_COALESCE_RX_EQE_PROFILE |	\
+	 ETHTOOL_COALESCE_RX_CQE_PROFILE |	\
+	 ETHTOOL_COALESCE_TX_EQE_PROFILE |	\
+	 ETHTOOL_COALESCE_TX_CQE_PROFILE)
 
 #define ETHTOOL_STAT_NOT_SET	(~0ULL)
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d45f330d083d..a1c7e9c2be86 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -80,6 +80,25 @@ struct xdp_frame;
 struct xdp_metadata_ops;
 struct xdp_md;
 
+#if IS_ENABLED(CONFIG_DIMLIB)
+struct dim_cq_moder;
+
+#define NETDEV_PROFILE_USEC	BIT(0)	/* device supports usec field modification */
+#define NETDEV_PROFILE_PKTS	BIT(1)	/* device supports pkts field modification */
+#define NETDEV_PROFILE_COMPS	BIT(2)	/* device supports comps field modification */
+
+struct netdev_profile_moder {
+	/* See NETDEV_PROFILE_* */
+	unsigned int flags;
+
+	/* DIM profile lists for different dim cq modes */
+	struct dim_cq_moder *rx_eqe_profile;
+	struct dim_cq_moder *rx_cqe_profile;
+	struct dim_cq_moder *tx_eqe_profile;
+	struct dim_cq_moder *tx_cqe_profile;
+};
+#endif
+
 typedef u32 xdp_features_t;
 
 void synchronize_net(void);
@@ -2400,6 +2419,11 @@ struct net_device {
 	/** @page_pools: page pools created for this netdevice */
 	struct hlist_head	page_pools;
 #endif
+
+#if IS_ENABLED(CONFIG_DIMLIB)
+	/** @moderation: dim tunable parameters for this netdevice */
+	struct netdev_profile_moder	*moderation;
+#endif
 };
 #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 23e225f00fb0..d884d76a1b98 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -416,12 +416,36 @@ 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 */
+	ETHTOOL_A_COALESCE_RX_EQE_PROFILE,              /* nest - _A_MODERATIONS_MODERATION */
+	ETHTOOL_A_COALESCE_RX_CQE_PROFILE,              /* nest - _A_MODERATIONS_MODERATION */
+	ETHTOOL_A_COALESCE_TX_EQE_PROFILE,              /* nest - _A_MODERATIONS_MODERATION */
+	ETHTOOL_A_COALESCE_TX_CQE_PROFILE,              /* nest - _A_MODERATIONS_MODERATION */
 
 	/* add new constants above here */
 	__ETHTOOL_A_COALESCE_CNT,
 	ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1)
 };
 
+enum {
+	ETHTOOL_A_MODERATIONS_UNSPEC,
+	ETHTOOL_A_MODERATIONS_MODERATION,		/* nest, _A_MODERATION_* */
+
+	/* add new constants above here */
+	__ETHTOOL_A_MODERATIONS_CNT,
+	ETHTOOL_A_MODERATIONS_MAX = (__ETHTOOL_A_MODERATIONS_CNT - 1)
+};
+
+enum {
+	ETHTOOL_A_MODERATION_UNSPEC,
+	ETHTOOL_A_MODERATION_USEC,			/* u32 */
+	ETHTOOL_A_MODERATION_PKTS,			/* u32 */
+	ETHTOOL_A_MODERATION_COMPS,			/* u32 */
+
+	/* add new constants above here */
+	__ETHTOOL_A_MODERATION_CNT,
+	ETHTOOL_A_MODERATION_MAX = (__ETHTOOL_A_MODERATION_CNT - 1)
+};
+
 /* PAUSE */
 
 enum {
diff --git a/net/core/dev.c b/net/core/dev.c
index 854a3a28a8d8..dba27150f035 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -96,6 +96,7 @@
 #include <linux/kthread.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
+#include <linux/dim.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/busy_poll.h>
@@ -10229,6 +10230,61 @@ static void netdev_do_free_pcpu_stats(struct net_device *dev)
 	}
 }
 
+static int dev_dim_profile_init(struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_DIMLIB)
+	u32 supported = dev->ethtool_ops->supported_coalesce_params;
+	struct netdev_profile_moder *moder;
+	int length;
+
+	dev->moderation = kzalloc(sizeof(*dev->moderation), GFP_KERNEL);
+	if (!dev->moderation)
+		goto err_moder;
+
+	moder = dev->moderation;
+	length = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_eqe_profile);
+
+	if (supported & ETHTOOL_COALESCE_RX_EQE_PROFILE) {
+		moder->rx_eqe_profile = kzalloc(length, GFP_KERNEL);
+		if (!moder->rx_eqe_profile)
+			goto err_rx_eqe;
+		memcpy(moder->rx_eqe_profile, rx_profile[0], length);
+	}
+	if (supported & ETHTOOL_COALESCE_RX_CQE_PROFILE) {
+		moder->rx_cqe_profile = kzalloc(length, GFP_KERNEL);
+		if (!moder->rx_cqe_profile)
+			goto err_rx_cqe;
+		memcpy(moder->rx_cqe_profile, rx_profile[1], length);
+	}
+	if (supported & ETHTOOL_COALESCE_TX_EQE_PROFILE) {
+		moder->tx_eqe_profile = kzalloc(length, GFP_KERNEL);
+		if (!moder->tx_eqe_profile)
+			goto err_tx_eqe;
+		memcpy(moder->tx_eqe_profile, tx_profile[0], length);
+	}
+	if (supported & ETHTOOL_COALESCE_TX_CQE_PROFILE) {
+		moder->tx_cqe_profile = kzalloc(length, GFP_KERNEL);
+		if (!moder->tx_cqe_profile)
+			goto err_tx_cqe;
+		memcpy(moder->tx_cqe_profile, tx_profile[1], length);
+	}
+#endif
+	return 0;
+
+#if IS_ENABLED(CONFIG_DIMLIB)
+err_tx_cqe:
+	kfree(moder->tx_eqe_profile);
+err_tx_eqe:
+	kfree(moder->rx_cqe_profile);
+err_rx_cqe:
+	kfree(moder->rx_eqe_profile);
+err_rx_eqe:
+	kfree(moder);
+err_moder:
+	return -ENOMEM;
+#endif
+}
+
 /**
  * register_netdevice() - register a network device
  * @dev: device to register
@@ -10258,6 +10314,10 @@ int register_netdevice(struct net_device *dev)
 	if (ret)
 		return ret;
 
+	ret = dev_dim_profile_init(dev);
+	if (ret)
+		return ret;
+
 	spin_lock_init(&dev->addr_list_lock);
 	netdev_set_addr_lockdep_class(dev);
 
@@ -11011,6 +11071,27 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 }
 EXPORT_SYMBOL(alloc_netdev_mqs);
 
+static void netif_free_profile(struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_DIMLIB)
+	u32 supported = dev->ethtool_ops->supported_coalesce_params;
+
+	if (supported & ETHTOOL_COALESCE_RX_EQE_PROFILE)
+		kfree(dev->moderation->rx_eqe_profile);
+
+	if (supported & ETHTOOL_COALESCE_RX_CQE_PROFILE)
+		kfree(dev->moderation->rx_cqe_profile);
+
+	if (supported & ETHTOOL_COALESCE_TX_EQE_PROFILE)
+		kfree(dev->moderation->tx_eqe_profile);
+
+	if (supported & ETHTOOL_COALESCE_TX_CQE_PROFILE)
+		kfree(dev->moderation->tx_cqe_profile);
+
+	kfree(dev->moderation);
+#endif
+}
+
 /**
  * free_netdev - free network device
  * @dev: device
@@ -11036,6 +11117,8 @@ void free_netdev(struct net_device *dev)
 		return;
 	}
 
+	netif_free_profile(dev);
+
 	netif_free_tx_queues(dev);
 	netif_free_rx_queues(dev);
 
diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c
index 83112c1a71ae..2c290048db15 100644
--- a/net/ethtool/coalesce.c
+++ b/net/ethtool/coalesce.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <linux/dim.h>
 #include "netlink.h"
 #include "common.h"
 
@@ -51,6 +52,10 @@ __CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_HIGH);
 __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_HIGH);
 __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_HIGH);
 __CHECK_SUPPORTED_OFFSET(COALESCE_RATE_SAMPLE_INTERVAL);
+__CHECK_SUPPORTED_OFFSET(COALESCE_RX_EQE_PROFILE);
+__CHECK_SUPPORTED_OFFSET(COALESCE_RX_CQE_PROFILE);
+__CHECK_SUPPORTED_OFFSET(COALESCE_TX_EQE_PROFILE);
+__CHECK_SUPPORTED_OFFSET(COALESCE_TX_CQE_PROFILE);
 
 const struct nla_policy ethnl_coalesce_get_policy[] = {
 	[ETHTOOL_A_COALESCE_HEADER]		=
@@ -82,6 +87,14 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base,
 static int coalesce_reply_size(const struct ethnl_req_info *req_base,
 			       const struct ethnl_reply_data *reply_base)
 {
+	int modersz = nla_total_size(0) + /* _MODERATIONS_MODERATION, nest */
+		      nla_total_size(sizeof(u32)) + /* _MODERATION_USEC */
+		      nla_total_size(sizeof(u32)) + /* _MODERATION_PKTS */
+		      nla_total_size(sizeof(u32));  /* _MODERATION_COMPS */
+
+	int total_modersz = nla_total_size(0) +  /* _{R,T}X_{E,C}QE_PROFILE, nest */
+			modersz * NET_DIM_PARAMS_NUM_PROFILES;
+
 	return nla_total_size(sizeof(u32)) +	/* _RX_USECS */
 	       nla_total_size(sizeof(u32)) +	/* _RX_MAX_FRAMES */
 	       nla_total_size(sizeof(u32)) +	/* _RX_USECS_IRQ */
@@ -108,7 +121,8 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base,
 	       nla_total_size(sizeof(u8)) +	/* _USE_CQE_MODE_RX */
 	       nla_total_size(sizeof(u32)) +	/* _TX_AGGR_MAX_BYTES */
 	       nla_total_size(sizeof(u32)) +	/* _TX_AGGR_MAX_FRAMES */
-	       nla_total_size(sizeof(u32));	/* _TX_AGGR_TIME_USECS */
+	       nla_total_size(sizeof(u32)) +	/* _TX_AGGR_TIME_USECS */
+	       total_modersz * 4;		/* _{R,T}X_{E,C}QE_PROFILE */
 }
 
 static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val,
@@ -127,6 +141,62 @@ static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val,
 	return nla_put_u8(skb, attr_type, !!val);
 }
 
+#if IS_ENABLED(CONFIG_DIMLIB)
+/**
+ * coalesce_put_profile - fill reply with a nla nest with four child nla nests.
+ * @skb: socket buffer the message is stored in
+ * @attr_type: nest attr type ETHTOOL_A_COALESCE_*X_*QE_PROFILE
+ * @profile: data passed to userspace
+ * @supported_params: modifiable parameters supported by the driver
+ *
+ * Put a dim profile nest attribute. Refer to ETHTOOL_A_MODERATIONS_MODERATION.
+ *
+ * Returns false to indicate successful placement or no placement, and
+ * returns true to pass the -EMSGSIZE error to the wrapper.
+ */
+static bool coalesce_put_profile(struct sk_buff *skb, u16 attr_type,
+				 const struct dim_cq_moder *profile,
+				 u32 supported_params)
+{
+	struct nlattr *profile_attr, *moder_attr;
+	bool emsg = !!-EMSGSIZE;
+	int i;
+
+	if (!profile)
+		return false;
+
+	if (!(supported_params & attr_to_mask(attr_type)))
+		return false;
+
+	profile_attr = nla_nest_start(skb, attr_type);
+	if (!profile_attr)
+		return emsg;
+
+	for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) {
+		moder_attr = nla_nest_start(skb, ETHTOOL_A_MODERATIONS_MODERATION);
+		if (!moder_attr)
+			goto nla_cancel_profile;
+
+		if (nla_put_u32(skb, ETHTOOL_A_MODERATION_USEC, profile[i].usec) ||
+		    nla_put_u32(skb, ETHTOOL_A_MODERATION_PKTS, profile[i].pkts) ||
+		    nla_put_u32(skb, ETHTOOL_A_MODERATION_COMPS, profile[i].comps))
+			goto nla_cancel_moder;
+
+		nla_nest_end(skb, moder_attr);
+	}
+
+	nla_nest_end(skb, profile_attr);
+
+	return 0;
+
+nla_cancel_moder:
+	nla_nest_cancel(skb, moder_attr);
+nla_cancel_profile:
+	nla_nest_cancel(skb, profile_attr);
+	return emsg;
+}
+#endif
+
 static int coalesce_fill_reply(struct sk_buff *skb,
 			       const struct ethnl_req_info *req_base,
 			       const struct ethnl_reply_data *reply_base)
@@ -134,6 +204,9 @@ static int coalesce_fill_reply(struct sk_buff *skb,
 	const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base);
 	const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce;
 	const struct ethtool_coalesce *coal = &data->coalesce;
+#if IS_ENABLED(CONFIG_DIMLIB)
+	struct net_device *dev = req_base->dev;
+#endif
 	u32 supported = data->supported_params;
 
 	if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS,
@@ -192,6 +265,21 @@ static int coalesce_fill_reply(struct sk_buff *skb,
 			     kcoal->tx_aggr_time_usecs, supported))
 		return -EMSGSIZE;
 
+#if IS_ENABLED(CONFIG_DIMLIB)
+	if (!(dev->moderation->flags & (NETDEV_PROFILE_USEC | NETDEV_PROFILE_PKTS |
+					NETDEV_PROFILE_COMPS)))
+		return 0;
+
+	if (coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_EQE_PROFILE,
+				 dev->moderation->rx_eqe_profile, supported) ||
+	    coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_CQE_PROFILE,
+				 dev->moderation->rx_cqe_profile, supported) ||
+	    coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_EQE_PROFILE,
+				 dev->moderation->tx_eqe_profile, supported) ||
+	    coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_CQE_PROFILE,
+				 dev->moderation->tx_cqe_profile, supported))
+		return -EMSGSIZE;
+#endif
 	return 0;
 }
 
@@ -227,6 +315,16 @@ const struct nla_policy ethnl_coalesce_set_policy[] = {
 	[ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 },
 	[ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 },
 	[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 },
+	[ETHTOOL_A_COALESCE_RX_EQE_PROFILE]     = { .type = NLA_NESTED },
+	[ETHTOOL_A_COALESCE_RX_CQE_PROFILE]     = { .type = NLA_NESTED },
+	[ETHTOOL_A_COALESCE_TX_EQE_PROFILE]     = { .type = NLA_NESTED },
+	[ETHTOOL_A_COALESCE_TX_CQE_PROFILE]     = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy coalesce_set_profile_policy[] = {
+	[ETHTOOL_A_MODERATION_USEC]	= {.type = NLA_U32},
+	[ETHTOOL_A_MODERATION_PKTS]	= {.type = NLA_U32},
+	[ETHTOOL_A_MODERATION_COMPS]	= {.type = NLA_U32},
 };
 
 static int
@@ -253,6 +351,76 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info,
 	return 1;
 }
 
+#if IS_ENABLED(CONFIG_DIMLIB)
+/**
+ * ethnl_update_profile - get a nla nest with four child nla nests from userspace.
+ * @dev: netdevice to update the profile
+ * @dst: data get from the driver and modified by ethnl_update_profile.
+ * @nests: nest attr ETHTOOL_A_COALESCE_*X_*QE_PROFILE to set driver's profile.
+ * @extack: Netlink extended ack
+ *
+ * Layout of nests:
+ *   Nested ETHTOOL_A_COALESCE_*X_*QE_PROFILE attr
+ *     Nested ETHTOOL_A_MODERATIONS_MODERATION attr
+ *       ETHTOOL_A_MODERATION_USEC attr
+ *       ETHTOOL_A_MODERATION_PKTS attr
+ *       ETHTOOL_A_MODERATION_COMPS attr
+ *     ...
+ *     Nested ETHTOOL_A_MODERATIONS_MODERATION attr
+ *       ETHTOOL_A_MODERATION_USEC attr
+ *       ETHTOOL_A_MODERATION_PKTS attr
+ *       ETHTOOL_A_MODERATION_COMPS attr
+ *
+ * Returns 0 on success or a negative error code.
+ */
+static inline int ethnl_update_profile(struct net_device *dev,
+				       struct dim_cq_moder *dst,
+				       const struct nlattr *nests,
+				       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb_moder[ARRAY_SIZE(coalesce_set_profile_policy)];
+	struct dim_cq_moder profile[NET_DIM_PARAMS_NUM_PROFILES];
+	struct netdev_profile_moder *moder = dev->moderation;
+	struct nlattr *nest;
+	int ret, rem, i = 0;
+
+	if (!nests)
+		return 0;
+
+	if (!dst)
+		return -EOPNOTSUPP;
+
+	nla_for_each_nested_type(nest, ETHTOOL_A_MODERATIONS_MODERATION, nests, rem) {
+		ret = nla_parse_nested(tb_moder,
+				       ARRAY_SIZE(coalesce_set_profile_policy) - 1,
+				       nest, coalesce_set_profile_policy,
+				       extack);
+		if (ret)
+			return ret;
+
+		if (NL_REQ_ATTR_CHECK(extack, nest, tb_moder, ETHTOOL_A_MODERATION_USEC) ||
+		    NL_REQ_ATTR_CHECK(extack, nest, tb_moder, ETHTOOL_A_MODERATION_PKTS) ||
+		    NL_REQ_ATTR_CHECK(extack, nest, tb_moder, ETHTOOL_A_MODERATION_COMPS))
+			return -EINVAL;
+
+		profile[i].usec = nla_get_u32(tb_moder[ETHTOOL_A_MODERATION_USEC]);
+		profile[i].pkts = nla_get_u32(tb_moder[ETHTOOL_A_MODERATION_PKTS]);
+		profile[i].comps = nla_get_u32(tb_moder[ETHTOOL_A_MODERATION_COMPS]);
+
+		if ((dst[i].usec != profile[i].usec && !(moder->flags & NETDEV_PROFILE_USEC)) ||
+		    (dst[i].pkts != profile[i].pkts && !(moder->flags & NETDEV_PROFILE_PKTS)) ||
+		    (dst[i].comps != profile[i].comps && !(moder->flags & NETDEV_PROFILE_COMPS)))
+			return -EOPNOTSUPP;
+
+		i++;
+	}
+
+	memcpy(dst, profile, sizeof(profile));
+
+	return 0;
+}
+#endif
+
 static int
 __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info,
 		     bool *dual_change)
@@ -317,6 +485,35 @@ __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info,
 	ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs,
 			 tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod);
 
+#if IS_ENABLED(CONFIG_DIMLIB)
+	ret = ethnl_update_profile(dev, dev->moderation->rx_eqe_profile,
+				   tb[ETHTOOL_A_COALESCE_RX_EQE_PROFILE],
+				   info->extack);
+	if (ret < 0)
+		return ret;
+	ret = ethnl_update_profile(dev, dev->moderation->rx_cqe_profile,
+				   tb[ETHTOOL_A_COALESCE_RX_CQE_PROFILE],
+				   info->extack);
+	if (ret < 0)
+		return ret;
+	ret = ethnl_update_profile(dev, dev->moderation->tx_eqe_profile,
+				   tb[ETHTOOL_A_COALESCE_TX_EQE_PROFILE],
+				   info->extack);
+	if (ret < 0)
+		return ret;
+	ret = ethnl_update_profile(dev, dev->moderation->tx_cqe_profile,
+				   tb[ETHTOOL_A_COALESCE_TX_CQE_PROFILE],
+				   info->extack);
+	if (ret < 0)
+		return ret;
+#else
+	if (tb[ETHTOOL_A_COALESCE_RX_EQE_PROFILE] ||
+	    tb[ETHTOOL_A_COALESCE_RX_CQE_PROFILE] ||
+	    tb[ETHTOOL_A_COALESCE_TX_EQE_PROFILE] ||
+	    tb[ETHTOOL_A_COALESCE_TX_CQE_PROFILE])
+		return -EOPNOTSUPP;
+
+#endif
 	/* Update operation modes */
 	ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce,
 			    tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod_mode);
-- 
2.32.0.3.g01195cf9f

[PATCH net-next v7 3/4] virtio-net: refactor dim initialization/destruction

[Heng Qi]

Extract the initialization and destruction actions
of dim for use in the next patch.

Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
---
 drivers/net/virtio_net.c | 38 +++++++++++++++++++++++++++-----------
 1 file changed, 27 insertions(+), 11 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c22d1118a133..e8fbee204bf0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2274,6 +2274,13 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 	return err;
 }
 
+static void virtnet_dim_clean(struct virtnet_info *vi,
+			      int start_qnum, int end_qnum)
+{
+	for (; start_qnum <= end_qnum; start_qnum++)
+		cancel_work_sync(&vi->rq[start_qnum].dim.work);
+}
+
 static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -2297,11 +2304,9 @@ static int virtnet_open(struct net_device *dev)
 err_enable_qp:
 	disable_delayed_refill(vi);
 	cancel_delayed_work_sync(&vi->refill);
-
-	for (i--; i >= 0; i--) {
+	virtnet_dim_clean(vi, 0, i - 1);
+	for (i--; i >= 0; i--)
 		virtnet_disable_queue_pair(vi, i);
-		cancel_work_sync(&vi->rq[i].dim.work);
-	}
 
 	return err;
 }
@@ -2466,7 +2471,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
 
 	if (running) {
 		napi_disable(&rq->napi);
-		cancel_work_sync(&rq->dim.work);
+		virtnet_dim_clean(vi, qindex, qindex);
 	}
 
 	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf);
@@ -2716,10 +2721,9 @@ static int virtnet_close(struct net_device *dev)
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
 
-	for (i = 0; i < vi->max_queue_pairs; i++) {
+	virtnet_dim_clean(vi, 0, vi->max_queue_pairs - 1);
+	for (i = 0; i < vi->max_queue_pairs; i++)
 		virtnet_disable_queue_pair(vi, i);
-		cancel_work_sync(&vi->rq[i].dim.work);
-	}
 
 	return 0;
 }
@@ -4418,6 +4422,19 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	return ret;
 }
 
+static void virtnet_dim_init(struct virtnet_info *vi)
+{
+	int i;
+
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		return;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		INIT_WORK(&vi->rq[i].dim.work, virtnet_rx_dim_work);
+		vi->rq[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+	}
+}
+
 static int virtnet_alloc_queues(struct virtnet_info *vi)
 {
 	int i;
@@ -4445,9 +4462,6 @@ 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));
@@ -4855,6 +4869,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
+	virtnet_dim_init(vi);
+
 	_virtnet_set_queues(vi, vi->curr_queue_pairs);
 
 	/* a random MAC address has been assigned, notify the device.
-- 
2.32.0.3.g01195cf9f

[PATCH net-next v7 4/4] virtio-net: support dim profile fine-tuning

[Heng Qi]

Virtio-net has different types of back-end device implementations.
In order to effectively optimize the dim library's gains for
different device implementations, let's use the new interface
params to fine-tune the profile list.

Since the profile now exists in netdevice, adding a function similar
to net_dim_get_rx_moderation_dev() with netdevice as argument is
nice, but this would be better along with cleaning up the rest of
the drivers, which we can get to very soon after this set.

Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
---
 drivers/net/virtio_net.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index e8fbee204bf0..f31c27ad3f85 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3584,7 +3584,7 @@ static void virtnet_rx_dim_work(struct work_struct *work)
 		if (!rq->dim_enabled)
 			continue;
 
-		update_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+		update_moder = dev->moderation->rx_eqe_profile[dim->profile_ix];
 		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,
@@ -3868,7 +3868,8 @@ static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
 
 static const struct ethtool_ops virtnet_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES |
-		ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
+		ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX |
+		ETHTOOL_COALESCE_RX_EQE_PROFILE,
 	.get_drvinfo = virtnet_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = virtnet_get_ringparam,
@@ -4424,6 +4425,7 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 
 static void virtnet_dim_init(struct virtnet_info *vi)
 {
+	struct netdev_profile_moder *moder = vi->dev->moderation;
 	int i;
 
 	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
@@ -4433,6 +4435,8 @@ static void virtnet_dim_init(struct virtnet_info *vi)
 		INIT_WORK(&vi->rq[i].dim.work, virtnet_rx_dim_work);
 		vi->rq[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 	}
+
+	moder->flags |= NETDEV_PROFILE_USEC | NETDEV_PROFILE_PKTS;
 }
 
 static int virtnet_alloc_queues(struct virtnet_info *vi)
-- 
2.32.0.3.g01195cf9f

Re: [PATCH net-next v7 2/4] ethtool: provide customized dim profile management

[kernel test robot]

Hi Heng,

kernel test robot noticed the following build warnings:

[auto build test WARNING on net-next/main]

url:    https://github.com/intel-lab-lkp/linux/commits/Heng-Qi/linux-dim-move-useful-macros-to-h-file/20240415-173921
base:   net-next/main
patch link:    https://lore.kernel.org/r/20240415093638.123962-3-hengqi%40linux.alibaba.com
patch subject: [PATCH net-next v7 2/4] ethtool: provide customized dim profile management
config: openrisc-defconfig (https://download.01.org/0day-ci/archive/20240415/202404152018.KkOQ39NY-lkp@intel.com/config)
compiler: or1k-linux-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240415/202404152018.KkOQ39NY-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202404152018.KkOQ39NY-lkp@intel.com/

All warnings (new ones prefixed by >>):

>> net/ethtool/coalesce.c:324:32: warning: 'coalesce_set_profile_policy' defined but not used [-Wunused-const-variable=]
     324 | static const struct nla_policy coalesce_set_profile_policy[] = {
         |                                ^~~~~~~~~~~~~~~~~~~~~~~~~~~


vim +/coalesce_set_profile_policy +324 net/ethtool/coalesce.c

   323	
 > 324	static const struct nla_policy coalesce_set_profile_policy[] = {
   325		[ETHTOOL_A_MODERATION_USEC]	= {.type = NLA_U32},
   326		[ETHTOOL_A_MODERATION_PKTS]	= {.type = NLA_U32},
   327		[ETHTOOL_A_MODERATION_COMPS]	= {.type = NLA_U32},
   328	};
   329	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH net-next v7 2/4] ethtool: provide customized dim profile management

[kernel test robot]

Hi Heng,

kernel test robot noticed the following build warnings:

[auto build test WARNING on net-next/main]

url:    https://github.com/intel-lab-lkp/linux/commits/Heng-Qi/linux-dim-move-useful-macros-to-h-file/20240415-173921
base:   net-next/main
patch link:    https://lore.kernel.org/r/20240415093638.123962-3-hengqi%40linux.alibaba.com
patch subject: [PATCH net-next v7 2/4] ethtool: provide customized dim profile management
config: um-allnoconfig (https://download.01.org/0day-ci/archive/20240415/202404152005.vHS17jjP-lkp@intel.com/config)
compiler: clang version 17.0.6 (https://github.com/llvm/llvm-project 6009708b4367171ccdbf4b5905cb6a803753fe18)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240415/202404152005.vHS17jjP-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202404152005.vHS17jjP-lkp@intel.com/

All warnings (new ones prefixed by >>):

   In file included from net/ethtool/coalesce.c:4:
   In file included from net/ethtool/netlink.h:6:
   In file included from include/linux/ethtool_netlink.h:6:
   In file included from include/uapi/linux/ethtool_netlink.h:12:
   In file included from include/linux/ethtool.h:18:
   In file included from include/linux/if_ether.h:19:
   In file included from include/linux/skbuff.h:17:
   In file included from include/linux/bvec.h:10:
   In file included from include/linux/highmem.h:12:
   In file included from include/linux/hardirq.h:11:
   In file included from arch/um/include/asm/hardirq.h:5:
   In file included from include/asm-generic/hardirq.h:17:
   In file included from include/linux/irq.h:20:
   In file included from include/linux/io.h:13:
   In file included from arch/um/include/asm/io.h:24:
   include/asm-generic/io.h:547:31: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     547 |         val = __raw_readb(PCI_IOBASE + addr);
         |                           ~~~~~~~~~~ ^
   include/asm-generic/io.h:560:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     560 |         val = __le16_to_cpu((__le16 __force)__raw_readw(PCI_IOBASE + addr));
         |                                                         ~~~~~~~~~~ ^
   include/uapi/linux/byteorder/little_endian.h:37:51: note: expanded from macro '__le16_to_cpu'
      37 | #define __le16_to_cpu(x) ((__force __u16)(__le16)(x))
         |                                                   ^
   In file included from net/ethtool/coalesce.c:4:
   In file included from net/ethtool/netlink.h:6:
   In file included from include/linux/ethtool_netlink.h:6:
   In file included from include/uapi/linux/ethtool_netlink.h:12:
   In file included from include/linux/ethtool.h:18:
   In file included from include/linux/if_ether.h:19:
   In file included from include/linux/skbuff.h:17:
   In file included from include/linux/bvec.h:10:
   In file included from include/linux/highmem.h:12:
   In file included from include/linux/hardirq.h:11:
   In file included from arch/um/include/asm/hardirq.h:5:
   In file included from include/asm-generic/hardirq.h:17:
   In file included from include/linux/irq.h:20:
   In file included from include/linux/io.h:13:
   In file included from arch/um/include/asm/io.h:24:
   include/asm-generic/io.h:573:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     573 |         val = __le32_to_cpu((__le32 __force)__raw_readl(PCI_IOBASE + addr));
         |                                                         ~~~~~~~~~~ ^
   include/uapi/linux/byteorder/little_endian.h:35:51: note: expanded from macro '__le32_to_cpu'
      35 | #define __le32_to_cpu(x) ((__force __u32)(__le32)(x))
         |                                                   ^
   In file included from net/ethtool/coalesce.c:4:
   In file included from net/ethtool/netlink.h:6:
   In file included from include/linux/ethtool_netlink.h:6:
   In file included from include/uapi/linux/ethtool_netlink.h:12:
   In file included from include/linux/ethtool.h:18:
   In file included from include/linux/if_ether.h:19:
   In file included from include/linux/skbuff.h:17:
   In file included from include/linux/bvec.h:10:
   In file included from include/linux/highmem.h:12:
   In file included from include/linux/hardirq.h:11:
   In file included from arch/um/include/asm/hardirq.h:5:
   In file included from include/asm-generic/hardirq.h:17:
   In file included from include/linux/irq.h:20:
   In file included from include/linux/io.h:13:
   In file included from arch/um/include/asm/io.h:24:
   include/asm-generic/io.h:584:33: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     584 |         __raw_writeb(value, PCI_IOBASE + addr);
         |                             ~~~~~~~~~~ ^
   include/asm-generic/io.h:594:59: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     594 |         __raw_writew((u16 __force)cpu_to_le16(value), PCI_IOBASE + addr);
         |                                                       ~~~~~~~~~~ ^
   include/asm-generic/io.h:604:59: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     604 |         __raw_writel((u32 __force)cpu_to_le32(value), PCI_IOBASE + addr);
         |                                                       ~~~~~~~~~~ ^
   include/asm-generic/io.h:692:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     692 |         readsb(PCI_IOBASE + addr, buffer, count);
         |                ~~~~~~~~~~ ^
   include/asm-generic/io.h:700:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     700 |         readsw(PCI_IOBASE + addr, buffer, count);
         |                ~~~~~~~~~~ ^
   include/asm-generic/io.h:708:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     708 |         readsl(PCI_IOBASE + addr, buffer, count);
         |                ~~~~~~~~~~ ^
   include/asm-generic/io.h:717:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     717 |         writesb(PCI_IOBASE + addr, buffer, count);
         |                 ~~~~~~~~~~ ^
   include/asm-generic/io.h:726:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     726 |         writesw(PCI_IOBASE + addr, buffer, count);
         |                 ~~~~~~~~~~ ^
   include/asm-generic/io.h:735:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     735 |         writesl(PCI_IOBASE + addr, buffer, count);
         |                 ~~~~~~~~~~ ^
>> net/ethtool/coalesce.c:324:32: warning: unused variable 'coalesce_set_profile_policy' [-Wunused-const-variable]
     324 | static const struct nla_policy coalesce_set_profile_policy[] = {
         |                                ^~~~~~~~~~~~~~~~~~~~~~~~~~~
   13 warnings generated.


vim +/coalesce_set_profile_policy +324 net/ethtool/coalesce.c

   323	
 > 324	static const struct nla_policy coalesce_set_profile_policy[] = {
   325		[ETHTOOL_A_MODERATION_USEC]	= {.type = NLA_U32},
   326		[ETHTOOL_A_MODERATION_PKTS]	= {.type = NLA_U32},
   327		[ETHTOOL_A_MODERATION_COMPS]	= {.type = NLA_U32},
   328	};
   329	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH net-next v7 0/4] ethtool: provide the dim profile fine-tuning channel

[Heng Qi]

Please ignore this set, "RESEND v7" will be used instead.

在 2024/4/15 下午5:36, Heng Qi 写道:
> 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, interaction with the driver is still based on the commonly
> used "ethtool -C".
>
> Since the profile now exists in netdevice, adding a function similar
> to net_dim_get_rx_moderation_dev() with netdevice as argument is
> nice, but this would be better along with cleaning up the rest of
> the drivers, which we can get to very soon after this set.
>
> Please review, thank you very much!
>
> Changelog
> =====
> v6->v7:
>    - A new wrapper struct pointer is used in struct net_device.
>    - Add IS_ENABLED(CONFIG_DIMLIB) to avoid compiler warnings.
>    - Profile fields changed from u16 to u32.
>
> v5->v6:
>    - Place the profile in netdevice to bypass the driver.
>      The interaction code of ethtool <-> kernel has not changed at all,
>      only the interaction part of kernel <-> driver has changed.
>
> v4->v5:
>    - Update some snippets from Kuba, Thanks.
>
> v3->v4:
>    - Some tiny updates and patch 1 only add a new comment.
>
> v2->v3:
>    - Break up the attributes to avoid the use of raw c structs.
>    - Use per-device profile instead of global profile in the driver.
>
> v1->v2:
>    - Use ethtool tool instead of net-sysfs
>
> Heng Qi (4):
>    linux/dim: move useful macros to .h file
>    ethtool: provide customized dim profile management
>    virtio-net: refactor dim initialization/destruction
>    virtio-net: support dim profile fine-tuning
>
>   Documentation/netlink/specs/ethtool.yaml     |  33 +++
>   Documentation/networking/ethtool-netlink.rst |   8 +
>   drivers/net/virtio_net.c                     |  46 +++--
>   include/linux/dim.h                          |  13 ++
>   include/linux/ethtool.h                      |  11 +-
>   include/linux/netdevice.h                    |  24 +++
>   include/uapi/linux/ethtool_netlink.h         |  24 +++
>   lib/dim/net_dim.c                            |  10 +-
>   net/core/dev.c                               |  83 ++++++++
>   net/ethtool/coalesce.c                       | 199 ++++++++++++++++++-
>   10 files changed, 428 insertions(+), 23 deletions(-)
>

Re: [PATCH net-next v7 2/4] ethtool: provide customized dim profile management

[Simon Horman]

On Mon, Apr 15, 2024 at 05:36:36PM +0800, Heng Qi wrote:

...

> @@ -10229,6 +10230,61 @@ static void netdev_do_free_pcpu_stats(struct net_device *dev)
>  	}
>  }
>  
> +static int dev_dim_profile_init(struct net_device *dev)
> +{
> +#if IS_ENABLED(CONFIG_DIMLIB)
> +	u32 supported = dev->ethtool_ops->supported_coalesce_params;
> +	struct netdev_profile_moder *moder;
> +	int length;
> +
> +	dev->moderation = kzalloc(sizeof(*dev->moderation), GFP_KERNEL);
> +	if (!dev->moderation)
> +		goto err_moder;
> +
> +	moder = dev->moderation;
> +	length = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_eqe_profile);
> +
> +	if (supported & ETHTOOL_COALESCE_RX_EQE_PROFILE) {
> +		moder->rx_eqe_profile = kzalloc(length, GFP_KERNEL);
> +		if (!moder->rx_eqe_profile)
> +			goto err_rx_eqe;
> +		memcpy(moder->rx_eqe_profile, rx_profile[0], length);
> +	}
> +	if (supported & ETHTOOL_COALESCE_RX_CQE_PROFILE) {
> +		moder->rx_cqe_profile = kzalloc(length, GFP_KERNEL);
> +		if (!moder->rx_cqe_profile)
> +			goto err_rx_cqe;
> +		memcpy(moder->rx_cqe_profile, rx_profile[1], length);
> +	}
> +	if (supported & ETHTOOL_COALESCE_TX_EQE_PROFILE) {
> +		moder->tx_eqe_profile = kzalloc(length, GFP_KERNEL);
> +		if (!moder->tx_eqe_profile)
> +			goto err_tx_eqe;
> +		memcpy(moder->tx_eqe_profile, tx_profile[0], length);
> +	}
> +	if (supported & ETHTOOL_COALESCE_TX_CQE_PROFILE) {
> +		moder->tx_cqe_profile = kzalloc(length, GFP_KERNEL);
> +		if (!moder->tx_cqe_profile)
> +			goto err_tx_cqe;
> +		memcpy(moder->tx_cqe_profile, tx_profile[1], length);
> +	}

nit: Coccinelle suggests that the kzalloc()/memcpy() pattern above
     could be replaced with calls to kmemdup()

> +#endif
> +	return 0;
> +
> +#if IS_ENABLED(CONFIG_DIMLIB)
> +err_tx_cqe:
> +	kfree(moder->tx_eqe_profile);
> +err_tx_eqe:
> +	kfree(moder->rx_cqe_profile);
> +err_rx_cqe:
> +	kfree(moder->rx_eqe_profile);
> +err_rx_eqe:
> +	kfree(moder);
> +err_moder:
> +	return -ENOMEM;
> +#endif
> +}
> +
>  /**
>   * register_netdevice() - register a network device
>   * @dev: device to register

...

Re: [PATCH net-next v7 2/4] ethtool: provide customized dim profile management

[Heng Qi]

在 2024/4/16 上午4:03, Simon Horman 写道:
> On Mon, Apr 15, 2024 at 05:36:36PM +0800, Heng Qi wrote:
>
> ...
>
>> @@ -10229,6 +10230,61 @@ static void netdev_do_free_pcpu_stats(struct net_device *dev)
>>   	}
>>   }
>>   
>> +static int dev_dim_profile_init(struct net_device *dev)
>> +{
>> +#if IS_ENABLED(CONFIG_DIMLIB)
>> +	u32 supported = dev->ethtool_ops->supported_coalesce_params;
>> +	struct netdev_profile_moder *moder;
>> +	int length;
>> +
>> +	dev->moderation = kzalloc(sizeof(*dev->moderation), GFP_KERNEL);
>> +	if (!dev->moderation)
>> +		goto err_moder;
>> +
>> +	moder = dev->moderation;
>> +	length = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_eqe_profile);
>> +
>> +	if (supported & ETHTOOL_COALESCE_RX_EQE_PROFILE) {
>> +		moder->rx_eqe_profile = kzalloc(length, GFP_KERNEL);
>> +		if (!moder->rx_eqe_profile)
>> +			goto err_rx_eqe;
>> +		memcpy(moder->rx_eqe_profile, rx_profile[0], length);
>> +	}
>> +	if (supported & ETHTOOL_COALESCE_RX_CQE_PROFILE) {
>> +		moder->rx_cqe_profile = kzalloc(length, GFP_KERNEL);
>> +		if (!moder->rx_cqe_profile)
>> +			goto err_rx_cqe;
>> +		memcpy(moder->rx_cqe_profile, rx_profile[1], length);
>> +	}
>> +	if (supported & ETHTOOL_COALESCE_TX_EQE_PROFILE) {
>> +		moder->tx_eqe_profile = kzalloc(length, GFP_KERNEL);
>> +		if (!moder->tx_eqe_profile)
>> +			goto err_tx_eqe;
>> +		memcpy(moder->tx_eqe_profile, tx_profile[0], length);
>> +	}
>> +	if (supported & ETHTOOL_COALESCE_TX_CQE_PROFILE) {
>> +		moder->tx_cqe_profile = kzalloc(length, GFP_KERNEL);
>> +		if (!moder->tx_cqe_profile)
>> +			goto err_tx_cqe;
>> +		memcpy(moder->tx_cqe_profile, tx_profile[1], length);
>> +	}
> nit: Coccinelle suggests that the kzalloc()/memcpy() pattern above
>       could be replaced with calls to kmemdup()

Good idea.

Thanks.

>> +#endif
>> +	return 0;
>> +
>> +#if IS_ENABLED(CONFIG_DIMLIB)
>> +err_tx_cqe:
>> +	kfree(moder->tx_eqe_profile);
>> +err_tx_eqe:
>> +	kfree(moder->rx_cqe_profile);
>> +err_rx_cqe:
>> +	kfree(moder->rx_eqe_profile);
>> +err_rx_eqe:
>> +	kfree(moder);
>> +err_moder:
>> +	return -ENOMEM;
>> +#endif
>> +}
>> +
>>   /**
>>    * register_netdevice() - register a network device
>>    * @dev: device to register
> ...