ethtool: provide customized dim profile management

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 rx profile setting
(with DIM_PROFILE_RX flag set in profile_flags) and supports modification
of usec and pkt fields.

1. Query the currently customized list of the device

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

2. Tune
$ ethtool -C ethx rx-profile 1,1,n_2,n,n_3,3,n_4,4,n_n,5,n
"n" means do not modify this field.
$ ethtool -c ethx
...
rx-profile:
{.usec =   1, .pkts =   1, .comps = n/a,},
{.usec =   2, .pkts = 256, .comps = n/a,},
{.usec =   3, .pkts =   3, .comps = n/a,},
{.usec =   4, .pkts =   4, .comps = n/a,},
{.usec = 256, .pkts =   5, .comps = n/a,}
tx-profile:   n/a

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

If the "n/a" field is being modified, -EOPNOTSUPP will be reported.

Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240621101353.107425-4-hengqi@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 271 insertions, 2 deletions

diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c
index 83112c1a71ae..759b16e3d134 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"
 
@@ -82,6 +83,14 @@ 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) + /* _PROFILE_IRQ_MODERATION, nest */
+		      nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_USEC */
+		      nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_PKTS */
+		      nla_total_size(sizeof(u32));  /* _IRQ_MODERATION_COMPS */
+
+	int total_modersz = nla_total_size(0) +  /* _{R,T}X_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 +117,8 @@ 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 * 2;		/* _{R,T}X_PROFILE */
 }
 
 static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val,
@@ -127,14 +137,84 @@ static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val,
 	return nla_put_u8(skb, attr_type, !!val);
 }
 
+/**
+ * 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_PROFILE
+ * @profile: data passed to userspace
+ * @coal_flags: modifiable parameters supported by the driver
+ *
+ * Put a dim profile nest attribute. Refer to ETHTOOL_A_PROFILE_IRQ_MODERATION.
+ *
+ * Return: 0 on success or a negative error code.
+ */
+static int coalesce_put_profile(struct sk_buff *skb, u16 attr_type,
+				const struct dim_cq_moder *profile,
+				u8 coal_flags)
+{
+	struct nlattr *profile_attr, *moder_attr;
+	int i, ret;
+
+	if (!profile || !coal_flags)
+		return 0;
+
+	profile_attr = nla_nest_start(skb, attr_type);
+	if (!profile_attr)
+		return -EMSGSIZE;
+
+	for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) {
+		moder_attr = nla_nest_start(skb,
+					    ETHTOOL_A_PROFILE_IRQ_MODERATION);
+		if (!moder_attr) {
+			ret = -EMSGSIZE;
+			goto cancel_profile;
+		}
+
+		if (coal_flags & DIM_COALESCE_USEC) {
+			ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_USEC,
+					  profile[i].usec);
+			if (ret)
+				goto cancel_moder;
+		}
+
+		if (coal_flags & DIM_COALESCE_PKTS) {
+			ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_PKTS,
+					  profile[i].pkts);
+			if (ret)
+				goto cancel_moder;
+		}
+
+		if (coal_flags & DIM_COALESCE_COMPS) {
+			ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_COMPS,
+					  profile[i].comps);
+			if (ret)
+				goto cancel_moder;
+		}
+
+		nla_nest_end(skb, moder_attr);
+	}
+
+	nla_nest_end(skb, profile_attr);
+
+	return 0;
+
+cancel_moder:
+	nla_nest_cancel(skb, moder_attr);
+cancel_profile:
+	nla_nest_cancel(skb, profile_attr);
+	return ret;
+}
+
 static int coalesce_fill_reply(struct sk_buff *skb,
 			       const struct ethnl_req_info *req_base,
 			       const struct ethnl_reply_data *reply_base)
 {
 	const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base);
 	const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce;
+	struct dim_irq_moder *moder = req_base->dev->irq_moder;
 	const struct ethtool_coalesce *coal = &data->coalesce;
 	u32 supported = data->supported_params;
+	int ret = 0;
 
 	if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS,
 			     coal->rx_coalesce_usecs, supported) ||
@@ -192,11 +272,41 @@ static int coalesce_fill_reply(struct sk_buff *skb,
 			     kcoal->tx_aggr_time_usecs, supported))
 		return -EMSGSIZE;
 
-	return 0;
+	if (!moder)
+		return 0;
+
+	rcu_read_lock();
+	if (moder->profile_flags & DIM_PROFILE_RX) {
+		ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_PROFILE,
+					   rcu_dereference(moder->rx_profile),
+					   moder->coal_flags);
+		if (ret)
+			goto out;
+	}
+
+	if (moder->profile_flags & DIM_PROFILE_TX)
+		ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_PROFILE,
+					   rcu_dereference(moder->tx_profile),
+					   moder->coal_flags);
+
+out:
+	rcu_read_unlock();
+	return ret;
 }
 
 /* COALESCE_SET */
 
+static const struct nla_policy coalesce_irq_moderation_policy[] = {
+	[ETHTOOL_A_IRQ_MODERATION_USEC]	= { .type = NLA_U32 },
+	[ETHTOOL_A_IRQ_MODERATION_PKTS]	= { .type = NLA_U32 },
+	[ETHTOOL_A_IRQ_MODERATION_COMPS] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy coalesce_profile_policy[] = {
+	[ETHTOOL_A_PROFILE_IRQ_MODERATION] =
+		NLA_POLICY_NESTED(coalesce_irq_moderation_policy),
+};
+
 const struct nla_policy ethnl_coalesce_set_policy[] = {
 	[ETHTOOL_A_COALESCE_HEADER]		=
 		NLA_POLICY_NESTED(ethnl_header_policy),
@@ -227,6 +337,10 @@ 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_PROFILE] =
+		NLA_POLICY_NESTED(coalesce_profile_policy),
+	[ETHTOOL_A_COALESCE_TX_PROFILE] =
+		NLA_POLICY_NESTED(coalesce_profile_policy),
 };
 
 static int
@@ -234,6 +348,7 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info,
 			    struct genl_info *info)
 {
 	const struct ethtool_ops *ops = req_info->dev->ethtool_ops;
+	struct dim_irq_moder *irq_moder = req_info->dev->irq_moder;
 	struct nlattr **tb = info->attrs;
 	u32 supported_params;
 	u16 a;
@@ -243,6 +358,12 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info,
 
 	/* make sure that only supported parameters are present */
 	supported_params = ops->supported_coalesce_params;
+	if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_RX)
+		supported_params |= ETHTOOL_COALESCE_RX_PROFILE;
+
+	if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_TX)
+		supported_params |= ETHTOOL_COALESCE_TX_PROFILE;
+
 	for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++)
 		if (tb[a] && !(supported_params & attr_to_mask(a))) {
 			NL_SET_ERR_MSG_ATTR(info->extack, tb[a],
@@ -253,6 +374,138 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info,
 	return 1;
 }
 
+/**
+ * ethnl_update_irq_moder - update a specific field in the given profile
+ * @irq_moder: place that collects dim related information
+ * @irq_field: field in profile to modify
+ * @attr_type: attr type ETHTOOL_A_IRQ_MODERATION_*
+ * @tb: netlink attribute with new values or null
+ * @coal_bit: DIM_COALESCE_* bit from coal_flags
+ * @mod: pointer to bool for modification tracking
+ * @extack: netlink extended ack
+ *
+ * Return: 0 on success or a negative error code.
+ */
+static int ethnl_update_irq_moder(struct dim_irq_moder *irq_moder,
+				  u16 *irq_field, u16 attr_type,
+				  struct nlattr **tb,
+				  u8 coal_bit, bool *mod,
+				  struct netlink_ext_ack *extack)
+{
+	int ret = 0;
+	u32 val;
+
+	if (!tb[attr_type])
+		return 0;
+
+	if (irq_moder->coal_flags & coal_bit) {
+		val = nla_get_u32(tb[attr_type]);
+		if (*irq_field == val)
+			return 0;
+
+		*irq_field = val;
+		*mod = true;
+	} else {
+		NL_SET_BAD_ATTR(extack, tb[attr_type]);
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+/**
+ * ethnl_update_profile - get a profile nest with child nests from userspace.
+ * @dev: netdevice to update the profile
+ * @dst: profile get from the driver and modified by ethnl_update_profile.
+ * @nests: nest attr ETHTOOL_A_COALESCE_*X_PROFILE to set profile.
+ * @mod: pointer to bool for modification tracking
+ * @extack: Netlink extended ack
+ *
+ * Layout of nests:
+ *   Nested ETHTOOL_A_COALESCE_*X_PROFILE attr
+ *     Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr
+ *       ETHTOOL_A_IRQ_MODERATION_USEC attr
+ *       ETHTOOL_A_IRQ_MODERATION_PKTS attr
+ *       ETHTOOL_A_IRQ_MODERATION_COMPS attr
+ *     ...
+ *     Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr
+ *       ETHTOOL_A_IRQ_MODERATION_USEC attr
+ *       ETHTOOL_A_IRQ_MODERATION_PKTS attr
+ *       ETHTOOL_A_IRQ_MODERATION_COMPS attr
+ *
+ * Return: 0 on success or a negative error code.
+ */
+static int ethnl_update_profile(struct net_device *dev,
+				struct dim_cq_moder __rcu **dst,
+				const struct nlattr *nests,
+				bool *mod,
+				struct netlink_ext_ack *extack)
+{
+	int len_irq_moder = ARRAY_SIZE(coalesce_irq_moderation_policy);
+	struct nlattr *tb[ARRAY_SIZE(coalesce_irq_moderation_policy)];
+	struct dim_irq_moder *irq_moder = dev->irq_moder;
+	struct dim_cq_moder *new_profile, *old_profile;
+	int ret, rem, i = 0, len;
+	struct nlattr *nest;
+
+	if (!nests)
+		return 0;
+
+	if (!*dst)
+		return -EOPNOTSUPP;
+
+	old_profile = rtnl_dereference(*dst);
+	len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*old_profile);
+	new_profile = kmemdup(old_profile, len, GFP_KERNEL);
+	if (!new_profile)
+		return -ENOMEM;
+
+	nla_for_each_nested_type(nest, ETHTOOL_A_PROFILE_IRQ_MODERATION,
+				 nests, rem) {
+		ret = nla_parse_nested(tb, len_irq_moder - 1, nest,
+				       coalesce_irq_moderation_policy,
+				       extack);
+		if (ret)
+			goto err_out;
+
+		ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].usec,
+					     ETHTOOL_A_IRQ_MODERATION_USEC,
+					     tb, DIM_COALESCE_USEC,
+					     mod, extack);
+		if (ret)
+			goto err_out;
+
+		ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].pkts,
+					     ETHTOOL_A_IRQ_MODERATION_PKTS,
+					     tb, DIM_COALESCE_PKTS,
+					     mod, extack);
+		if (ret)
+			goto err_out;
+
+		ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].comps,
+					     ETHTOOL_A_IRQ_MODERATION_COMPS,
+					     tb, DIM_COALESCE_COMPS,
+					     mod, extack);
+		if (ret)
+			goto err_out;
+
+		i++;
+	}
+
+	/* After the profile is modified, dim itself is a dynamic
+	 * mechanism and will quickly fit to the appropriate
+	 * coalescing parameters according to the new profile.
+	 */
+	rcu_assign_pointer(*dst, new_profile);
+	kfree_rcu(old_profile, rcu);
+
+	return 0;
+
+err_out:
+	kfree(new_profile);
+	return ret;
+}
+
 static int
 __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info,
 		     bool *dual_change)
@@ -317,6 +570,22 @@ __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 (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_RX) {
+		ret = ethnl_update_profile(dev, &dev->irq_moder->rx_profile,
+					   tb[ETHTOOL_A_COALESCE_RX_PROFILE],
+					   &mod, info->extack);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_TX) {
+		ret = ethnl_update_profile(dev, &dev->irq_moder->tx_profile,
+					   tb[ETHTOOL_A_COALESCE_TX_PROFILE],
+					   &mod, info->extack);
+		if (ret < 0)
+			return ret;
+	}
+
 	/* Update operation modes */
 	ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce,
 			    tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod_mode);