Merge branch 'net-ethtool-add-dedicated-grxrings-driver-callbacks'

Breno Leitao says:

====================
net: ethtool: add dedicated GRXRINGS driver callbacks

This patchset introduces a new dedicated ethtool_ops callback,
.get_rx_ring_count, which enables drivers to provide the number of RX
rings directly, improving efficiency and clarity in RX ring queries and
RSS configuration.

Number of drivers implements .get_rxnfc callback just to report the ring
count, so, having a proper callback makes sense and simplify .get_rxnfc
(in some cases remove it completely).

This has been suggested by Jakub, and follow the same idea as RXFH
driver callbacks [1].

This also port virtio_net to this new callback. Once there is consensus
on this approach, I can start moving the drivers to this new callback.

Link: https://lore.kernel.org/all/[e-mail]/ [1]

v3: https://lore.kernel.org/[e-mail]
v2: https://lore.kernel.org/[e-mail]
v1: https://lore.kernel.org/[e-mail]
RFC: https://lore.kernel.org/[e-mail]
====================

Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

drivers/net/virtio_net.c

···
 	return 0;
 }
 
-static int virtnet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs)
+static u32 virtnet_get_rx_ring_count(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
-	int rc = 0;
 
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data = vi->curr_queue_pairs;
-		break;
-	default:
-		rc = -EOPNOTSUPP;
-	}
-
-	return rc;
+	return vi->curr_queue_pairs;
 }
 
 static const struct ethtool_ops virtnet_ethtool_ops = {
···
 	.set_rxfh = virtnet_set_rxfh,
 	.get_rxfh_fields = virtnet_get_hashflow,
 	.set_rxfh_fields = virtnet_set_hashflow,
-	.get_rxnfc = virtnet_get_rxnfc,
+	.get_rx_ring_count = virtnet_get_rx_ring_count,
 };
 
 static void virtnet_get_queue_stats_rx(struct net_device *dev, int i,

include/linux/ethtool.h

···
  * @reset: Reset (part of) the device, as specified by a bitmask of
  *	flags from &enum ethtool_reset_flags.  Returns a negative
  *	error code or zero.
+ * @get_rx_ring_count: Return the number of RX rings
  * @get_rxfh_key_size: Get the size of the RX flow hash key.
  *	Returns zero if not supported for this specific device.
  * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table.
···
 	int	(*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *);
 	int	(*flash_device)(struct net_device *, struct ethtool_flash *);
 	int	(*reset)(struct net_device *, u32 *);
+	u32	(*get_rx_ring_count)(struct net_device *dev);
 	u32	(*get_rxfh_key_size)(struct net_device *);
 	u32	(*get_rxfh_indir_size)(struct net_device *);
 	int	(*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *);

net/ethtool/common.c

···
 	return netif_running(dev) && dev->ethtool_ops->get_link(dev);
 }
 
+int ethtool_get_rx_ring_count(struct net_device *dev)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxnfc rx_rings = {};
+	int ret;
+
+	if (ops->get_rx_ring_count)
+		return ops->get_rx_ring_count(dev);
+
+	if (!ops->get_rxnfc)
+		return -EOPNOTSUPP;
+
+	rx_rings.cmd = ETHTOOL_GRXRINGS;
+	ret = ops->get_rxnfc(dev, &rx_rings, NULL);
+	if (ret < 0)
+		return ret;
+
+	return rx_rings.data;
+}
+
 static int ethtool_get_rxnfc_rule_count(struct net_device *dev)
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;

net/ethtool/common.h

···
 			       struct kernel_ethtool_ringparam *kparam,
 			       struct netlink_ext_ack *extack);
 
+int ethtool_get_rx_ring_count(struct net_device *dev);
+
 int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info);
 int ethtool_get_ts_info_by_phc(struct net_device *dev,
 			       struct kernel_ethtool_ts_info *info,

net/ethtool/ioctl.c

···
 	return 0;
 }
 
+static noinline_for_stack int ethtool_get_rxrings(struct net_device *dev,
+						  u32 cmd,
+						  void __user *useraddr)
+{
+	struct ethtool_rxnfc info;
+	size_t info_size;
+	int ret;
+
+	info_size = sizeof(info);
+	ret = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr);
+	if (ret)
+		return ret;
+
+	ret = ethtool_get_rx_ring_count(dev);
+	if (ret < 0)
+		return ret;
+
+	info.data = ret;
+
+	return ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, NULL);
+}
+
 static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
 						u32 cmd, void __user *useraddr)
 {
-	struct ethtool_rxnfc info;
-	size_t info_size = sizeof(info);
 	const struct ethtool_ops *ops = dev->ethtool_ops;
-	int ret;
+	struct ethtool_rxnfc info;
 	void *rule_buf = NULL;
+	size_t info_size;
+	int ret;
 
 	if (!ops->get_rxnfc)
 		return -EOPNOTSUPP;
 
+	info_size = sizeof(info);
 	ret = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr);
 	if (ret)
 		return ret;
···
 }
 
 static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr,
-					struct ethtool_rxnfc *rx_rings,
-					u32 size)
+				       int num_rx_rings,
+				       u32 size)
 {
 	int i;
 
···
 
 	/* Validate ring indices */
 	for (i = 0; i < size; i++)
-		if (indir[i] >= rx_rings->data)
+		if (indir[i] >= num_rx_rings)
 			return -EINVAL;
 
 	return 0;
···
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct ethtool_rxfh_param rxfh_dev = {};
 	struct netlink_ext_ack *extack = NULL;
-	struct ethtool_rxnfc rx_rings;
+	int num_rx_rings;
 	u32 user_size, i;
 	int ret;
 	u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]);
 
-	if (!ops->get_rxfh_indir_size || !ops->set_rxfh ||
-	    !ops->get_rxnfc)
+	if (!ops->get_rxfh_indir_size || !ops->set_rxfh)
 		return -EOPNOTSUPP;
 
 	rxfh_dev.indir_size = ops->get_rxfh_indir_size(dev);
···
 	if (!rxfh_dev.indir)
 		return -ENOMEM;
 
-	rx_rings.cmd = ETHTOOL_GRXRINGS;
-	ret = ops->get_rxnfc(dev, &rx_rings, NULL);
-	if (ret)
+	num_rx_rings = ethtool_get_rx_ring_count(dev);
+	if (num_rx_rings < 0) {
+		ret = num_rx_rings;
 		goto out;
+	}
 
 	if (user_size == 0) {
 		u32 *indir = rxfh_dev.indir;
 
 		for (i = 0; i < rxfh_dev.indir_size; i++)
-			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
+			indir[i] = ethtool_rxfh_indir_default(i, num_rx_rings);
 	} else {
 		ret = ethtool_copy_validate_indir(rxfh_dev.indir,
 						  useraddr + ringidx_offset,
-						  &rx_rings,
+						  num_rx_rings,
 						  rxfh_dev.indir_size);
 		if (ret)
 			goto out;
···
 	struct ethtool_rxfh_param rxfh_dev = {};
 	struct ethtool_rxfh_context *ctx = NULL;
 	struct netlink_ext_ack *extack = NULL;
-	struct ethtool_rxnfc rx_rings;
 	struct ethtool_rxfh rxfh;
 	bool create = false;
+	int num_rx_rings;
 	u8 *rss_config;
 	int ntf = 0;
 	int ret;
 
-	if (!ops->get_rxnfc || !ops->set_rxfh)
+	if (!ops->set_rxfh)
 		return -EOPNOTSUPP;
 
 	if (ops->get_rxfh_indir_size)
···
 	if (!rss_config)
 		return -ENOMEM;
 
-	rx_rings.cmd = ETHTOOL_GRXRINGS;
-	ret = ops->get_rxnfc(dev, &rx_rings, NULL);
-	if (ret)
+	num_rx_rings = ethtool_get_rx_ring_count(dev);
+	if (num_rx_rings < 0) {
+		ret = num_rx_rings;
 		goto out_free;
+	}
 
 	/* rxfh.indir_size == 0 means reset the indir table to default (master
 	 * context) or delete the context (other RSS contexts).
···
 		rxfh_dev.indir_size = dev_indir_size;
 		ret = ethtool_copy_validate_indir(rxfh_dev.indir,
 						  useraddr + rss_cfg_offset,
-						  &rx_rings,
+						  num_rx_rings,
 						  rxfh.indir_size);
 		if (ret)
 			goto out_free;
···
 			rxfh_dev.indir_size = dev_indir_size;
 			indir = rxfh_dev.indir;
 			for (i = 0; i < dev_indir_size; i++)
-				indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
+				indir[i] =
+					ethtool_rxfh_indir_default(i, num_rx_rings);
 		} else {
 			rxfh_dev.rss_delete = true;
 		}
···
 		rc = ethtool_set_rxfh_fields(dev, ethcmd, useraddr);
 		break;
 	case ETHTOOL_GRXRINGS:
+		rc = ethtool_get_rxrings(dev, ethcmd, useraddr);
+		break;
 	case ETHTOOL_GRXCLSRLCNT:
 	case ETHTOOL_GRXCLSRULE:
 	case ETHTOOL_GRXCLSRLALL:

net/ethtool/rss.c

···
 		   struct rss_reply_data *data, struct ethtool_rxfh_param *rxfh,
 		   bool *reset, bool *mod)
 {
-	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct netlink_ext_ack *extack = info->extack;
 	struct nlattr **tb = info->attrs;
-	struct ethtool_rxnfc rx_rings;
 	size_t alloc_size;
+	int num_rx_rings;
 	u32 user_size;
 	int i, err;
 
 	if (!tb[ETHTOOL_A_RSS_INDIR])
 		return 0;
-	if (!data->indir_size || !ops->get_rxnfc)
+	if (!data->indir_size)
 		return -EOPNOTSUPP;
 
-	rx_rings.cmd = ETHTOOL_GRXRINGS;
-	err = ops->get_rxnfc(dev, &rx_rings, NULL);
-	if (err)
+	err = ethtool_get_rx_ring_count(dev);
+	if (err < 0)
 		return err;
+	num_rx_rings = err;
 
 	if (nla_len(tb[ETHTOOL_A_RSS_INDIR]) % 4) {
 		NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_INDIR]);
···
 
 	nla_memcpy(rxfh->indir, tb[ETHTOOL_A_RSS_INDIR], alloc_size);
 	for (i = 0; i < user_size; i++) {
-		if (rxfh->indir[i] < rx_rings.data)
+		if (rxfh->indir[i] < num_rx_rings)
 			continue;
 
 		NL_SET_ERR_MSG_ATTR_FMT(extack, tb[ETHTOOL_A_RSS_INDIR],
···
 	} else {
 		for (i = 0; i < data->indir_size; i++)
 			rxfh->indir[i] =
-				ethtool_rxfh_indir_default(i, rx_rings.data);
+				ethtool_rxfh_indir_default(i, num_rx_rings);
 	}
 
 	*mod |= memcmp(rxfh->indir, data->indir_table, data->indir_size);