net: ethtool: extend RXNFC API to support RSS spreading of filter matches

We use a two-step process to configure a filter with RSS spreading.  First,
 the RSS context is allocated and configured using ETHTOOL_SRSSH; this
 returns an identifier (rss_context) which can then be passed to subsequent
 invocations of ETHTOOL_SRXCLSRLINS to specify that the offset from the RSS
 indirection table lookup should be added to the queue number (ring_cookie)
 when delivering the packet.  Drivers for devices which can only use the
 indirection table entry directly (not add it to a base queue number)
 should reject rule insertions combining RSS with a nonzero ring_cookie.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/ethtool.h

@@ -371,6 +371,11 @@ struct ethtool_ops {
 			    u8 *hfunc);
 	int	(*set_rxfh)(struct net_device *, const u32 *indir,
 			    const u8 *key, const u8 hfunc);
+	int	(*get_rxfh_context)(struct net_device *, u32 *indir, u8 *key,
+				    u8 *hfunc, u32 rss_context);
+	int	(*set_rxfh_context)(struct net_device *, const u32 *indir,
+				    const u8 *key, const u8 hfunc,
+				    u32 *rss_context, bool delete);
 	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 *);

include/uapi/linux/ethtool.h

@@ -914,12 +914,15 @@ static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie)
  * @flow_type: Type of flow to be affected, e.g. %TCP_V4_FLOW
  * @data: Command-dependent value
  * @fs: Flow classification rule
+ * @rss_context: RSS context to be affected
  * @rule_cnt: Number of rules to be affected
  * @rule_locs: Array of used rule locations
  *
  * For %ETHTOOL_GRXFH and %ETHTOOL_SRXFH, @data is a bitmask indicating
  * the fields included in the flow hash, e.g. %RXH_IP_SRC.  The following
- * structure fields must not be used.
+ * structure fields must not be used, except that if @flow_type includes
+ * the %FLOW_RSS flag, then @rss_context determines which RSS context to
+ * act on.
  *
  * For %ETHTOOL_GRXRINGS, @data is set to the number of RX rings/queues
  * on return.
@@ -931,7 +934,9 @@ static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie)
  * set in @data then special location values should not be used.
  *
  * For %ETHTOOL_GRXCLSRULE, @fs.@location specifies the location of an
- * existing rule on entry and @fs contains the rule on return.
+ * existing rule on entry and @fs contains the rule on return; if
+ * @fs.@flow_type includes the %FLOW_RSS flag, then @rss_context is
+ * filled with the RSS context ID associated with the rule.
  *
  * For %ETHTOOL_GRXCLSRLALL, @rule_cnt specifies the array size of the
  * user buffer for @rule_locs on entry.  On return, @data is the size
@@ -942,7 +947,11 @@ static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie)
  * For %ETHTOOL_SRXCLSRLINS, @fs specifies the rule to add or update.
  * @fs.@location either specifies the location to use or is a special
  * location value with %RX_CLS_LOC_SPECIAL flag set.  On return,
- * @fs.@location is the actual rule location.
+ * @fs.@location is the actual rule location.  If @fs.@flow_type
+ * includes the %FLOW_RSS flag, @rss_context is the RSS context ID to
+ * use for flow spreading traffic which matches this rule.  The value
+ * from the rxfh indirection table will be added to @fs.@ring_cookie
+ * to choose which ring to deliver to.
  *
  * For %ETHTOOL_SRXCLSRLDEL, @fs.@location specifies the location of an
  * existing rule on entry.
@@ -963,7 +972,10 @@ struct ethtool_rxnfc {
 	__u32				flow_type;
 	__u64				data;
 	struct ethtool_rx_flow_spec	fs;
-	__u32				rule_cnt;
+	union {
+		__u32			rule_cnt;
+		__u32			rss_context;
+	};
 	__u32				rule_locs[0];
 };
 
@@ -990,7 +1002,11 @@ struct ethtool_rxfh_indir {
 /**
  * struct ethtool_rxfh - command to get/set RX flow hash indir or/and hash key.
  * @cmd: Specific command number - %ETHTOOL_GRSSH or %ETHTOOL_SRSSH
- * @rss_context: RSS context identifier.
+ * @rss_context: RSS context identifier.  Context 0 is the default for normal
+ *	traffic; other contexts can be referenced as the destination for RX flow
+ *	classification rules.  %ETH_RXFH_CONTEXT_ALLOC is used with command
+ *	%ETHTOOL_SRSSH to allocate a new RSS context; on return this field will
+ *	contain the ID of the newly allocated context.
  * @indir_size: On entry, the array size of the user buffer for the
  *	indirection table, which may be zero, or (for %ETHTOOL_SRSSH),
  *	%ETH_RXFH_INDIR_NO_CHANGE.  On return from %ETHTOOL_GRSSH,
@@ -1009,7 +1025,8 @@ struct ethtool_rxfh_indir {
  * size should be returned.  For %ETHTOOL_SRSSH, an @indir_size of
  * %ETH_RXFH_INDIR_NO_CHANGE means that indir table setting is not requested
  * and a @indir_size of zero means the indir table should be reset to default
- * values. An hfunc of zero means that hash function setting is not requested.
+ * values (if @rss_context == 0) or that the RSS context should be deleted.
+ * An hfunc of zero means that hash function setting is not requested.
  */
 struct ethtool_rxfh {
 	__u32   cmd;
@@ -1021,6 +1038,7 @@ struct ethtool_rxfh {
 	__u32	rsvd32;
 	__u32   rss_config[0];
 };
+#define ETH_RXFH_CONTEXT_ALLOC		0xffffffff
 #define ETH_RXFH_INDIR_NO_CHANGE	0xffffffff
 
 /**
@@ -1635,6 +1653,8 @@ static inline int ethtool_validate_duplex(__u8 duplex)
 /* Flag to enable additional fields in struct ethtool_rx_flow_spec */
 #define	FLOW_EXT	0x80000000
 #define	FLOW_MAC_EXT	0x40000000
+/* Flag to enable RSS spreading of traffic matching rule (nfc only) */
+#define	FLOW_RSS	0x20000000
 
 /* L3-L4 network traffic flow hash options */
 #define	RXH_L2DA	(1 << 1)

net/core/ethtool.c

@@ -1022,6 +1022,15 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
 	if (copy_from_user(&info, useraddr, info_size))
 		return -EFAULT;
 
+	/* If FLOW_RSS was requested then user-space must be using the
+	 * new definition, as FLOW_RSS is newer.
+	 */
+	if (cmd == ETHTOOL_GRXFH && info.flow_type & FLOW_RSS) {
+		info_size = sizeof(info);
+		if (copy_from_user(&info, useraddr, info_size))
+			return -EFAULT;
+	}
+
 	if (info.cmd == ETHTOOL_GRXCLSRLALL) {
 		if (info.rule_cnt > 0) {
 			if (info.rule_cnt <= KMALLOC_MAX_SIZE / sizeof(u32))
@@ -1251,9 +1260,11 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	user_key_size = rxfh.key_size;
 
 	/* Check that reserved fields are 0 for now */
-	if (rxfh.rss_context || rxfh.rsvd8[0] || rxfh.rsvd8[1] ||
-	    rxfh.rsvd8[2] || rxfh.rsvd32)
+	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
 		return -EINVAL;
+	/* Most drivers don't handle rss_context, check it's 0 as well */
+	if (rxfh.rss_context && !ops->get_rxfh_context)
+		return -EOPNOTSUPP;
 
 	rxfh.indir_size = dev_indir_size;
 	rxfh.key_size = dev_key_size;
@@ -1276,7 +1287,12 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	if (user_key_size)
 		hkey = rss_config + indir_bytes;
 
-	ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc);
+	if (rxfh.rss_context)
+		ret = dev->ethtool_ops->get_rxfh_context(dev, indir, hkey,
+							 &dev_hfunc,
+							 rxfh.rss_context);
+	else
+		ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc);
 	if (ret)
 		goto out;
 
@@ -1306,6 +1322,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	u8 *hkey = NULL;
 	u8 *rss_config;
 	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
+	bool delete = false;
 
 	if (!ops->get_rxnfc || !ops->set_rxfh)
 		return -EOPNOTSUPP;
@@ -1319,9 +1336,11 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		return -EFAULT;
 
 	/* Check that reserved fields are 0 for now */
-	if (rxfh.rss_context || rxfh.rsvd8[0] || rxfh.rsvd8[1] ||
-	    rxfh.rsvd8[2] || rxfh.rsvd32)
+	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
 		return -EINVAL;
+	/* Most drivers don't handle rss_context, check it's 0 as well */
+	if (rxfh.rss_context && !ops->set_rxfh_context)
+		return -EOPNOTSUPP;
 
 	/* If either indir, hash key or function is valid, proceed further.
 	 * Must request at least one change: indir size, hash key or function.
@@ -1346,7 +1365,8 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	if (ret)
 		goto out;
 
-	/* rxfh.indir_size == 0 means reset the indir table to default.
+	/* rxfh.indir_size == 0 means reset the indir table to default (master
+	 * context) or delete the context (other RSS contexts).
 	 * rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE means leave it unchanged.
 	 */
 	if (rxfh.indir_size &&
@@ -1359,9 +1379,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		if (ret)
 			goto out;
 	} else if (rxfh.indir_size == 0) {
-		indir = (u32 *)rss_config;
-		for (i = 0; i < dev_indir_size; i++)
-			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
+		if (rxfh.rss_context == 0) {
+			indir = (u32 *)rss_config;
+			for (i = 0; i < dev_indir_size; i++)
+				indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
+		} else {
+			delete = true;
+		}
 	}
 
 	if (rxfh.key_size) {
@@ -1374,15 +1398,25 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		}
 	}
 
-	ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc);
+	if (rxfh.rss_context)
+		ret = ops->set_rxfh_context(dev, indir, hkey, rxfh.hfunc,
+					    &rxfh.rss_context, delete);
+	else
+		ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc);
 	if (ret)
 		goto out;
 
-	/* indicate whether rxfh was set to default */
-	if (rxfh.indir_size == 0)
-		dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
-	else if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
-		dev->priv_flags |= IFF_RXFH_CONFIGURED;
+	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_context),
+			 &rxfh.rss_context, sizeof(rxfh.rss_context)))
+		ret = -EFAULT;
+
+	if (!rxfh.rss_context) {
+		/* indicate whether rxfh was set to default */
+		if (rxfh.indir_size == 0)
+			dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
+		else if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
+			dev->priv_flags |= IFF_RXFH_CONFIGURED;
+	}
 
 out:
 	kfree(rss_config);