net: ethtool: let the core choose RSS context IDs

Add a new API to create/modify/remove RSS contexts, that passes in the
 newly-chosen context ID (not as a pointer) rather than leaving the
 driver to choose it on create.  Also pass in the ctx, allowing drivers
 to easily use its private data area to store their hardware-specific
 state.
Keep the existing .set_rxfh API for now as a fallback, but deprecate it
 for custom contexts (rss_context != 0).
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/45f1fe61df2163c091ec394c9f52000c8b16cc3b.1719502240.git.ecree.xilinx@gmail.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/ethtool.h

@@ -723,6 +723,10 @@ struct ethtool_rxfh_param {
  *	RSS.
  * @rxfh_priv_size: size of the driver private data area the core should
  *	allocate for an RSS context (in &struct ethtool_rxfh_context).
+ * @rxfh_max_context_id: maximum (exclusive) supported RSS context ID.  If this
+ *	is zero then the core may choose any (nonzero) ID, otherwise the core
+ *	will only use IDs strictly less than this value, as the @rss_context
+ *	argument to @create_rxfh_context and friends.
  * @supported_coalesce_params: supported types of interrupt coalescing.
  * @supported_ring_params: supported ring params.
  * @get_drvinfo: Report driver/device information. Modern drivers no
@@ -819,6 +823,32 @@ struct ethtool_rxfh_param {
  *	will remain unchanged.
  *	Returns a negative error code or zero. An error code must be returned
  *	if at least one unsupported change was requested.
+ * @create_rxfh_context: Create a new RSS context with the specified RX flow
+ *	hash indirection table, hash key, and hash function.
+ *	The &struct ethtool_rxfh_context for this context is passed in @ctx;
+ *	note that the indir table, hkey and hfunc are not yet populated as
+ *	of this call.  The driver does not need to update these; the core
+ *	will do so if this op succeeds.
+ *	However, if @rxfh.indir is set to %NULL, the driver must update the
+ *	indir table in @ctx with the (default or inherited) table actually in
+ *	use; similarly, if @rxfh.key is %NULL, @rxfh.hfunc is
+ *	%ETH_RSS_HASH_NO_CHANGE, or @rxfh.input_xfrm is %RXH_XFRM_NO_CHANGE,
+ *	the driver should update the corresponding information in @ctx.
+ *	If the driver provides this method, it must also provide
+ *	@modify_rxfh_context and @remove_rxfh_context.
+ *	Returns a negative error code or zero.
+ * @modify_rxfh_context: Reconfigure the specified RSS context.  Allows setting
+ *	the contents of the RX flow hash indirection table, hash key, and/or
+ *	hash function associated with the given context.
+ *	Parameters which are set to %NULL or zero will remain unchanged.
+ *	The &struct ethtool_rxfh_context for this context is passed in @ctx;
+ *	note that it will still contain the *old* settings.  The driver does
+ *	not need to update these; the core will do so if this op succeeds.
+ *	Returns a negative error code or zero. An error code must be returned
+ *	if at least one unsupported change was requested.
+ * @remove_rxfh_context: Remove the specified RSS context.
+ *	The &struct ethtool_rxfh_context for this context is passed in @ctx.
+ *	Returns a negative error code or zero.
  * @get_channels: Get number of channels.
  * @set_channels: Set number of channels.  Returns a negative error code or
  *	zero.
@@ -909,6 +939,7 @@ struct ethtool_ops {
 	u32     cap_rss_ctx_supported:1;
 	u32	cap_rss_sym_xor_supported:1;
 	u16	rxfh_priv_size;
+	u32	rxfh_max_context_id;
 	u32	supported_coalesce_params;
 	u32	supported_ring_params;
 	void	(*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *);
@@ -971,6 +1002,15 @@ struct ethtool_ops {
 	int	(*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *);
 	int	(*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *,
 			    struct netlink_ext_ack *extack);
+	int	(*create_rxfh_context)(struct net_device *,
+				       struct ethtool_rxfh_context *ctx,
+				       const struct ethtool_rxfh_param *rxfh);
+	int	(*modify_rxfh_context)(struct net_device *,
+				       struct ethtool_rxfh_context *ctx,
+				       const struct ethtool_rxfh_param *rxfh);
+	int	(*remove_rxfh_context)(struct net_device *,
+				       struct ethtool_rxfh_context *ctx,
+				       u32 rss_context);
 	void	(*get_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*set_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*get_dump_flag)(struct net_device *, struct ethtool_dump *);

net/core/dev.c

@@ -11254,6 +11254,10 @@ static void netdev_rss_contexts_free(struct net_device *dev)
 		rxfh.rss_delete = true;
 
 		xa_erase(&dev->ethtool->rss_ctx, context);
+		if (dev->ethtool_ops->create_rxfh_context)
+			dev->ethtool_ops->remove_rxfh_context(dev, ctx,
+							      context);
+		else
 			dev->ethtool_ops->set_rxfh(dev, &rxfh, NULL);
 		kfree(ctx);
 	}

net/ethtool/ioctl.c

@@ -1395,9 +1395,24 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		}
 		ctx->indir_size = dev_indir_size;
 		ctx->key_size = dev_key_size;
-		ctx->hfunc = rxfh.hfunc;
-		ctx->input_xfrm = rxfh.input_xfrm;
 		ctx->priv_size = ops->rxfh_priv_size;
+		/* Initialise to an empty context */
+		ctx->hfunc = ETH_RSS_HASH_NO_CHANGE;
+		ctx->input_xfrm = RXH_XFRM_NO_CHANGE;
+		if (ops->create_rxfh_context) {
+			u32 limit = ops->rxfh_max_context_id ?: U32_MAX;
+			u32 ctx_id;
+
+			/* driver uses new API, core allocates ID */
+			ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx,
+				       XA_LIMIT(1, limit), GFP_KERNEL_ACCOUNT);
+			if (ret < 0) {
+				kfree(ctx);
+				goto out;
+			}
+			WARN_ON(!ctx_id); /* can't happen */
+			rxfh.rss_context = ctx_id;
+		}
 	} else if (rxfh.rss_context) {
 		ctx = xa_load(&dev->ethtool->rss_ctx, rxfh.rss_context);
 		if (!ctx) {
@@ -1409,11 +1424,24 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	rxfh_dev.rss_context = rxfh.rss_context;
 	rxfh_dev.input_xfrm = rxfh.input_xfrm;
 
+	if (rxfh.rss_context && ops->create_rxfh_context) {
+		if (create)
+			ret = ops->create_rxfh_context(dev, ctx, &rxfh_dev);
+		else if (rxfh_dev.rss_delete)
+			ret = ops->remove_rxfh_context(dev, ctx,
+						       rxfh.rss_context);
+		else
+			ret = ops->modify_rxfh_context(dev, ctx, &rxfh_dev);
+	} else {
 		ret = ops->set_rxfh(dev, &rxfh_dev, extack);
+	}
 	if (ret) {
-		if (create)
+		if (create) {
 			/* failed to create, free our new tracking entry */
+			if (ops->create_rxfh_context)
+				xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context);
 			kfree(ctx);
+		}
 		goto out;
 	}
 
@@ -1429,12 +1457,8 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 			dev->priv_flags |= IFF_RXFH_CONFIGURED;
 	}
 	/* Update rss_ctx tracking */
-	if (create) {
-		/* Ideally this should happen before calling the driver,
-		 * so that we can fail more cleanly; but we don't have the
-		 * context ID until the driver picks it, so we have to
-		 * wait until after.
-		 */
+	if (create && !ops->create_rxfh_context) {
+		/* driver uses old API, it chose context ID */
 		if (WARN_ON(xa_load(&dev->ethtool->rss_ctx, rxfh.rss_context))) {
 			/* context ID reused, our tracking is screwed */
 			kfree(ctx);
@@ -1446,8 +1470,6 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 			kfree(ctx);
 			goto out;
 		}
-		ctx->indir_configured = rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE;
-		ctx->key_configured = !!rxfh.key_size;
 	}
 	if (rxfh_dev.rss_delete) {
 		WARN_ON(xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context) != ctx);