Merge branch 'ntuple-filters-with-RSS'

Edward Cree says:

====================
ntuple filters with RSS

This series introduces the ability to mark an ethtool steering filter to use
 RSS spreading, and the ability to create and configure multiple RSS contexts
 with different indirection tables, hash keys, and hash fields.
An implementation for the sfc driver (for 7000-series and later SFC NICs) is
 included in patch 2/2.

The anticipated use case of this feature is for steering traffic destined for
 a container (or virtual machine) to the subset of CPUs on which processes in
 the container (or the VM's vCPUs) are bound, while retaining the scalability
 of RSS spreading from the viewpoint inside the container.
The use of both a base queue number (ring_cookie) and indirection table is
 intended to allow re-use of a single RSS context to target multiple sets of
 CPUs.  For instance, if an 8-core system is hosting three containers on CPUs
 [1,2], [3,4] and [6,7], then a single RSS context with an equal-weight [0,1]
 indirection table could be used to target all three containers by setting
 ring_cookie to 1, 3 and 6 on the respective filters.

v2: Initialised ctx in efx_ef10_filter_insert() to avoid (false positive) gcc
 warning.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/sfc/efx.c

@@ -1353,12 +1353,13 @@ static void efx_fini_io(struct efx_nic *efx)
 		pci_disable_device(efx->pci_dev);
 }
 
-void efx_set_default_rx_indir_table(struct efx_nic *efx)
+void efx_set_default_rx_indir_table(struct efx_nic *efx,
+				    struct efx_rss_context *ctx)
 {
 	size_t i;
 
-	for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)
-		efx->rx_indir_table[i] =
+	for (i = 0; i < ARRAY_SIZE(ctx->rx_indir_table); i++)
+		ctx->rx_indir_table[i] =
 			ethtool_rxfh_indir_default(i, efx->rss_spread);
 }
 
@@ -1739,9 +1740,9 @@ static int efx_probe_nic(struct efx_nic *efx)
 	} while (rc == -EAGAIN);
 
 	if (efx->n_channels > 1)
-		netdev_rss_key_fill(&efx->rx_hash_key,
-				    sizeof(efx->rx_hash_key));
-	efx_set_default_rx_indir_table(efx);
+		netdev_rss_key_fill(efx->rss_context.rx_hash_key,
+				    sizeof(efx->rss_context.rx_hash_key));
+	efx_set_default_rx_indir_table(efx, &efx->rss_context);
 
 	netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
 	netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels);
@@ -2700,6 +2701,8 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 			   " VFs may not function\n", rc);
 #endif
 
+	if (efx->type->rx_restore_rss_contexts)
+		efx->type->rx_restore_rss_contexts(efx);
 	down_read(&efx->filter_sem);
 	efx_restore_filters(efx);
 	up_read(&efx->filter_sem);
@@ -3003,6 +3006,7 @@ static int efx_init_struct(struct efx_nic *efx,
 		efx->type->rx_hash_offset - efx->type->rx_prefix_size;
 	efx->rx_packet_ts_offset =
 		efx->type->rx_ts_offset - efx->type->rx_prefix_size;
+	INIT_LIST_HEAD(&efx->rss_context.list);
 	spin_lock_init(&efx->stats_lock);
 	efx->vi_stride = EFX_DEFAULT_VI_STRIDE;
 	efx->num_mac_stats = MC_CMD_MAC_NSTATS;
@@ -3072,6 +3076,55 @@ void efx_update_sw_stats(struct efx_nic *efx, u64 *stats)
 	stats[GENERIC_STAT_rx_noskb_drops] = atomic_read(&efx->n_rx_noskb_drops);
 }
 
+/* RSS contexts.  We're using linked lists and crappy O(n) algorithms, because
+ * (a) this is an infrequent control-plane operation and (b) n is small (max 64)
+ */
+struct efx_rss_context *efx_alloc_rss_context_entry(struct list_head *head)
+{
+	struct efx_rss_context *ctx, *new;
+	u32 id = 1; /* Don't use zero, that refers to the master RSS context */
+
+	/* Search for first gap in the numbering */
+	list_for_each_entry(ctx, head, list) {
+		if (ctx->user_id != id)
+			break;
+		id++;
+		/* Check for wrap.  If this happens, we have nearly 2^32
+		 * allocated RSS contexts, which seems unlikely.
+		 */
+		if (WARN_ON_ONCE(!id))
+			return NULL;
+	}
+
+	/* Create the new entry */
+	new = kmalloc(sizeof(struct efx_rss_context), GFP_KERNEL);
+	if (!new)
+		return NULL;
+	new->context_id = EFX_EF10_RSS_CONTEXT_INVALID;
+	new->rx_hash_udp_4tuple = false;
+
+	/* Insert the new entry into the gap */
+	new->user_id = id;
+	list_add_tail(&new->list, &ctx->list);
+	return new;
+}
+
+struct efx_rss_context *efx_find_rss_context_entry(u32 id, struct list_head *head)
+{
+	struct efx_rss_context *ctx;
+
+	list_for_each_entry(ctx, head, list)
+		if (ctx->user_id == id)
+			return ctx;
+	return NULL;
+}
+
+void efx_free_rss_context_entry(struct efx_rss_context *ctx)
+{
+	list_del(&ctx->list);
+	kfree(ctx);
+}
+
 /**************************************************************************
  *
  * PCI interface

drivers/net/ethernet/sfc/efx.h

@@ -34,7 +34,8 @@ extern unsigned int efx_piobuf_size;
 extern bool efx_separate_tx_channels;
 
 /* RX */
-void efx_set_default_rx_indir_table(struct efx_nic *efx);
+void efx_set_default_rx_indir_table(struct efx_nic *efx,
+				    struct efx_rss_context *ctx);
 void efx_rx_config_page_split(struct efx_nic *efx);
 int efx_probe_rx_queue(struct efx_rx_queue *rx_queue);
 void efx_remove_rx_queue(struct efx_rx_queue *rx_queue);
@@ -182,6 +183,15 @@ static inline void efx_filter_rfs_expire(struct efx_channel *channel) {}
 #endif
 bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec);
 
+/* RSS contexts */
+struct efx_rss_context *efx_alloc_rss_context_entry(struct list_head *list);
+struct efx_rss_context *efx_find_rss_context_entry(u32 id, struct list_head *list);
+void efx_free_rss_context_entry(struct efx_rss_context *ctx);
+static inline bool efx_rss_active(struct efx_rss_context *ctx)
+{
+	return ctx->context_id != EFX_EF10_RSS_CONTEXT_INVALID;
+}
+
 /* Channels */
 int efx_channel_dummy_op_int(struct efx_channel *channel);
 void efx_channel_dummy_op_void(struct efx_channel *channel);

drivers/net/ethernet/sfc/ethtool.c

@@ -808,7 +808,8 @@ static inline void ip6_fill_mask(__be32 *mask)
 }
 
 static int efx_ethtool_get_class_rule(struct efx_nic *efx,
-				      struct ethtool_rx_flow_spec *rule)
+				      struct ethtool_rx_flow_spec *rule,
+				      u32 *rss_context)
 {
 	struct ethtool_tcpip4_spec *ip_entry = &rule->h_u.tcp_ip4_spec;
 	struct ethtool_tcpip4_spec *ip_mask = &rule->m_u.tcp_ip4_spec;
@@ -964,6 +965,11 @@ static int efx_ethtool_get_class_rule(struct efx_nic *efx,
 		rule->m_ext.vlan_tci = htons(0xfff);
 	}
 
+	if (spec.flags & EFX_FILTER_FLAG_RX_RSS) {
+		rule->flow_type |= FLOW_RSS;
+		*rss_context = spec.rss_context;
+	}
+
 	return rc;
 }
 
@@ -972,6 +978,8 @@ efx_ethtool_get_rxnfc(struct net_device *net_dev,
 		      struct ethtool_rxnfc *info, u32 *rule_locs)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
+	u32 rss_context = 0;
+	s32 rc;
 
 	switch (info->cmd) {
 	case ETHTOOL_GRXRINGS:
@@ -979,12 +987,20 @@ efx_ethtool_get_rxnfc(struct net_device *net_dev,
 		return 0;
 
 	case ETHTOOL_GRXFH: {
+		struct efx_rss_context *ctx = &efx->rss_context;
+
+		if (info->flow_type & FLOW_RSS && info->rss_context) {
+			ctx = efx_find_rss_context_entry(info->rss_context,
+							 &efx->rss_context.list);
+			if (!ctx)
+				return -ENOENT;
+		}
 		info->data = 0;
-		if (!efx->rss_active) /* No RSS */
+		if (!efx_rss_active(ctx)) /* No RSS */
 			return 0;
-		switch (info->flow_type) {
+		switch (info->flow_type & ~FLOW_RSS) {
 		case UDP_V4_FLOW:
-			if (efx->rx_hash_udp_4tuple)
+			if (ctx->rx_hash_udp_4tuple)
 				/* fall through */
 		case TCP_V4_FLOW:
 				info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
@@ -995,7 +1011,7 @@ efx_ethtool_get_rxnfc(struct net_device *net_dev,
 			info->data |= RXH_IP_SRC | RXH_IP_DST;
 			break;
 		case UDP_V6_FLOW:
-			if (efx->rx_hash_udp_4tuple)
+			if (ctx->rx_hash_udp_4tuple)
 				/* fall through */
 		case TCP_V6_FLOW:
 				info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
@@ -1023,10 +1039,14 @@ efx_ethtool_get_rxnfc(struct net_device *net_dev,
 	case ETHTOOL_GRXCLSRULE:
 		if (efx_filter_get_rx_id_limit(efx) == 0)
 			return -EOPNOTSUPP;
-		return efx_ethtool_get_class_rule(efx, &info->fs);
+		rc = efx_ethtool_get_class_rule(efx, &info->fs, &rss_context);
+		if (rc < 0)
+			return rc;
+		if (info->fs.flow_type & FLOW_RSS)
+			info->rss_context = rss_context;
+		return 0;
 
-	case ETHTOOL_GRXCLSRLALL: {
-		s32 rc;
+	case ETHTOOL_GRXCLSRLALL:
 		info->data = efx_filter_get_rx_id_limit(efx);
 		if (info->data == 0)
 			return -EOPNOTSUPP;
@@ -1036,7 +1056,6 @@ efx_ethtool_get_rxnfc(struct net_device *net_dev,
 			return rc;
 		info->rule_cnt = rc;
 		return 0;
-	}
 
 	default:
 		return -EOPNOTSUPP;
@@ -1054,7 +1073,8 @@ static inline bool ip6_mask_is_empty(__be32 mask[4])
 }
 
 static int efx_ethtool_set_class_rule(struct efx_nic *efx,
-				      struct ethtool_rx_flow_spec *rule)
+				      struct ethtool_rx_flow_spec *rule,
+				      u32 rss_context)
 {
 	struct ethtool_tcpip4_spec *ip_entry = &rule->h_u.tcp_ip4_spec;
 	struct ethtool_tcpip4_spec *ip_mask = &rule->m_u.tcp_ip4_spec;
@@ -1066,6 +1086,7 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx,
 	struct ethtool_usrip6_spec *uip6_mask = &rule->m_u.usr_ip6_spec;
 	struct ethhdr *mac_entry = &rule->h_u.ether_spec;
 	struct ethhdr *mac_mask = &rule->m_u.ether_spec;
+	enum efx_filter_flags flags = 0;
 	struct efx_filter_spec spec;
 	int rc;
 
@@ -1084,12 +1105,19 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx,
 	     rule->m_ext.data[1]))
 		return -EINVAL;
 
-	efx_filter_init_rx(&spec, EFX_FILTER_PRI_MANUAL,
-			   efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0,
+	if (efx->rx_scatter)
+		flags |= EFX_FILTER_FLAG_RX_SCATTER;
+	if (rule->flow_type & FLOW_RSS)
+		flags |= EFX_FILTER_FLAG_RX_RSS;
+
+	efx_filter_init_rx(&spec, EFX_FILTER_PRI_MANUAL, flags,
 			   (rule->ring_cookie == RX_CLS_FLOW_DISC) ?
 			   EFX_FILTER_RX_DMAQ_ID_DROP : rule->ring_cookie);
 
-	switch (rule->flow_type & ~FLOW_EXT) {
+	if (rule->flow_type & FLOW_RSS)
+		spec.rss_context = rss_context;
+
+	switch (rule->flow_type & ~(FLOW_EXT | FLOW_RSS)) {
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
 		spec.match_flags = (EFX_FILTER_MATCH_ETHER_TYPE |
@@ -1265,7 +1293,8 @@ static int efx_ethtool_set_rxnfc(struct net_device *net_dev,
 
 	switch (info->cmd) {
 	case ETHTOOL_SRXCLSRLINS:
-		return efx_ethtool_set_class_rule(efx, &info->fs);
+		return efx_ethtool_set_class_rule(efx, &info->fs,
+						  info->rss_context);
 
 	case ETHTOOL_SRXCLSRLDEL:
 		return efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_MANUAL,
@@ -1280,7 +1309,9 @@ static u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
-	return (efx->n_rx_channels == 1) ? 0 : ARRAY_SIZE(efx->rx_indir_table);
+	if (efx->n_rx_channels == 1)
+		return 0;
+	return ARRAY_SIZE(efx->rss_context.rx_indir_table);
 }
 
 static u32 efx_ethtool_get_rxfh_key_size(struct net_device *net_dev)
@@ -1303,9 +1334,11 @@ static int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
 	if (hfunc)
 		*hfunc = ETH_RSS_HASH_TOP;
 	if (indir)
-		memcpy(indir, efx->rx_indir_table, sizeof(efx->rx_indir_table));
+		memcpy(indir, efx->rss_context.rx_indir_table,
+		       sizeof(efx->rss_context.rx_indir_table));
 	if (key)
-		memcpy(key, efx->rx_hash_key, efx->type->rx_hash_key_size);
+		memcpy(key, efx->rss_context.rx_hash_key,
+		       efx->type->rx_hash_key_size);
 	return 0;
 }
 
@@ -1321,13 +1354,93 @@ static int efx_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
 		return 0;
 
 	if (!key)
-		key = efx->rx_hash_key;
+		key = efx->rss_context.rx_hash_key;
 	if (!indir)
-		indir = efx->rx_indir_table;
+		indir = efx->rss_context.rx_indir_table;
 
 	return efx->type->rx_push_rss_config(efx, true, indir, key);
 }
 
+static int efx_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
+					u8 *key, u8 *hfunc, u32 rss_context)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+	struct efx_rss_context *ctx;
+	int rc;
+
+	if (!efx->type->rx_pull_rss_context_config)
+		return -EOPNOTSUPP;
+	ctx = efx_find_rss_context_entry(rss_context, &efx->rss_context.list);
+	if (!ctx)
+		return -ENOENT;
+	rc = efx->type->rx_pull_rss_context_config(efx, ctx);
+	if (rc)
+		return rc;
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (indir)
+		memcpy(indir, ctx->rx_indir_table, sizeof(ctx->rx_indir_table));
+	if (key)
+		memcpy(key, ctx->rx_hash_key, efx->type->rx_hash_key_size);
+	return 0;
+}
+
+static int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
+					const u32 *indir, const u8 *key,
+					const u8 hfunc, u32 *rss_context,
+					bool delete)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+	struct efx_rss_context *ctx;
+	bool allocated = false;
+	int rc;
+
+	if (!efx->type->rx_push_rss_context_config)
+		return -EOPNOTSUPP;
+	/* Hash function is Toeplitz, cannot be changed */
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
+		if (delete)
+			/* alloc + delete == Nothing to do */
+			return -EINVAL;
+		ctx = efx_alloc_rss_context_entry(&efx->rss_context.list);
+		if (!ctx)
+			return -ENOMEM;
+		ctx->context_id = EFX_EF10_RSS_CONTEXT_INVALID;
+		/* Initialise indir table and key to defaults */
+		efx_set_default_rx_indir_table(efx, ctx);
+		netdev_rss_key_fill(ctx->rx_hash_key, sizeof(ctx->rx_hash_key));
+		allocated = true;
+	} else {
+		ctx = efx_find_rss_context_entry(*rss_context,
+						 &efx->rss_context.list);
+		if (!ctx)
+			return -ENOENT;
+	}
+
+	if (delete) {
+		/* delete this context */
+		rc = efx->type->rx_push_rss_context_config(efx, ctx, NULL, NULL);
+		if (!rc)
+			efx_free_rss_context_entry(ctx);
+		return rc;
+	}
+
+	if (!key)
+		key = ctx->rx_hash_key;
+	if (!indir)
+		indir = ctx->rx_indir_table;
+
+	rc = efx->type->rx_push_rss_context_config(efx, ctx, indir, key);
+	if (rc && allocated)
+		efx_free_rss_context_entry(ctx);
+	else
+		*rss_context = ctx->user_id;
+	return rc;
+}
+
 static int efx_ethtool_get_ts_info(struct net_device *net_dev,
 				   struct ethtool_ts_info *ts_info)
 {
@@ -1403,6 +1516,8 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
 	.get_rxfh		= efx_ethtool_get_rxfh,
 	.set_rxfh		= efx_ethtool_set_rxfh,
+	.get_rxfh_context	= efx_ethtool_get_rxfh_context,
+	.set_rxfh_context	= efx_ethtool_set_rxfh_context,
 	.get_ts_info		= efx_ethtool_get_ts_info,
 	.get_module_info	= efx_ethtool_get_module_info,
 	.get_module_eeprom	= efx_ethtool_get_module_eeprom,

drivers/net/ethernet/sfc/farch.c

@@ -1630,12 +1630,12 @@ void efx_farch_rx_push_indir_table(struct efx_nic *efx)
 	size_t i = 0;
 	efx_dword_t dword;
 
-	BUILD_BUG_ON(ARRAY_SIZE(efx->rx_indir_table) !=
+	BUILD_BUG_ON(ARRAY_SIZE(efx->rss_context.rx_indir_table) !=
 		     FR_BZ_RX_INDIRECTION_TBL_ROWS);
 
 	for (i = 0; i < FR_BZ_RX_INDIRECTION_TBL_ROWS; i++) {
 		EFX_POPULATE_DWORD_1(dword, FRF_BZ_IT_QUEUE,
-				     efx->rx_indir_table[i]);
+				     efx->rss_context.rx_indir_table[i]);
 		efx_writed(efx, &dword,
 			   FR_BZ_RX_INDIRECTION_TBL +
 			   FR_BZ_RX_INDIRECTION_TBL_STEP * i);
@@ -1647,14 +1647,14 @@ void efx_farch_rx_pull_indir_table(struct efx_nic *efx)
 	size_t i = 0;
 	efx_dword_t dword;
 
-	BUILD_BUG_ON(ARRAY_SIZE(efx->rx_indir_table) !=
+	BUILD_BUG_ON(ARRAY_SIZE(efx->rss_context.rx_indir_table) !=
 		     FR_BZ_RX_INDIRECTION_TBL_ROWS);
 
 	for (i = 0; i < FR_BZ_RX_INDIRECTION_TBL_ROWS; i++) {
 		efx_readd(efx, &dword,
 			   FR_BZ_RX_INDIRECTION_TBL +
 			   FR_BZ_RX_INDIRECTION_TBL_STEP * i);
-		efx->rx_indir_table[i] = EFX_DWORD_FIELD(dword, FRF_BZ_IT_QUEUE);
+		efx->rss_context.rx_indir_table[i] = EFX_DWORD_FIELD(dword, FRF_BZ_IT_QUEUE);
 	}
 }
 
@@ -2032,8 +2032,7 @@ efx_farch_filter_from_gen_spec(struct efx_farch_filter_spec *spec,
 {
 	bool is_full = false;
 
-	if ((gen_spec->flags & EFX_FILTER_FLAG_RX_RSS) &&
-	    gen_spec->rss_context != EFX_FILTER_RSS_CONTEXT_DEFAULT)
+	if ((gen_spec->flags & EFX_FILTER_FLAG_RX_RSS) && gen_spec->rss_context)
 		return -EINVAL;
 
 	spec->priority = gen_spec->priority;

drivers/net/ethernet/sfc/filter.h

@@ -125,7 +125,9 @@ enum efx_encap_type {
  * @match_flags: Match type flags, from &enum efx_filter_match_flags
  * @priority: Priority of the filter, from &enum efx_filter_priority
  * @flags: Miscellaneous flags, from &enum efx_filter_flags
- * @rss_context: RSS context to use, if %EFX_FILTER_FLAG_RX_RSS is set
+ * @rss_context: RSS context to use, if %EFX_FILTER_FLAG_RX_RSS is set.  This
+ *	is a user_id (with 0 meaning the driver/default RSS context), not an
+ *	MCFW context_id.
  * @dmaq_id: Source/target queue index, or %EFX_FILTER_RX_DMAQ_ID_DROP for
  *	an RX drop filter
  * @outer_vid: Outer VLAN ID to match, if %EFX_FILTER_MATCH_OUTER_VID is set
@@ -173,7 +175,6 @@ struct efx_filter_spec {
 };
 
 enum {
-	EFX_FILTER_RSS_CONTEXT_DEFAULT = 0xffffffff,
 	EFX_FILTER_RX_DMAQ_ID_DROP = 0xfff
 };
 
@@ -185,7 +186,7 @@ static inline void efx_filter_init_rx(struct efx_filter_spec *spec,
 	memset(spec, 0, sizeof(*spec));
 	spec->priority = priority;
 	spec->flags = EFX_FILTER_FLAG_RX | flags;
-	spec->rss_context = EFX_FILTER_RSS_CONTEXT_DEFAULT;
+	spec->rss_context = 0;
 	spec->dmaq_id = rxq_id;
 }
 

drivers/net/ethernet/sfc/net_driver.h

@@ -704,6 +704,28 @@ union efx_multicast_hash {
 
 struct vfdi_status;
 
+/* The reserved RSS context value */
+#define EFX_EF10_RSS_CONTEXT_INVALID	0xffffffff
+/**
+ * struct efx_rss_context - A user-defined RSS context for filtering
+ * @list: node of linked list on which this struct is stored
+ * @context_id: the RSS_CONTEXT_ID returned by MC firmware, or
+ *	%EFX_EF10_RSS_CONTEXT_INVALID if this context is not present on the NIC.
+ *	For Siena, 0 if RSS is active, else %EFX_EF10_RSS_CONTEXT_INVALID.
+ * @user_id: the rss_context ID exposed to userspace over ethtool.
+ * @rx_hash_udp_4tuple: UDP 4-tuple hashing enabled
+ * @rx_hash_key: Toeplitz hash key for this RSS context
+ * @indir_table: Indirection table for this RSS context
+ */
+struct efx_rss_context {
+	struct list_head list;
+	u32 context_id;
+	u32 user_id;
+	bool rx_hash_udp_4tuple;
+	u8 rx_hash_key[40];
+	u32 rx_indir_table[128];
+};
+
 /**
  * struct efx_nic - an Efx NIC
  * @name: Device name (net device name or bus id before net device registered)
@@ -764,11 +786,9 @@ struct vfdi_status;
  *	(valid only for NICs that set %EFX_RX_PKT_PREFIX_LEN; always negative)
  * @rx_packet_ts_offset: Offset of timestamp from start of packet data
  *	(valid only if channel->sync_timestamps_enabled; always negative)
- * @rx_hash_key: Toeplitz hash key for RSS
- * @rx_indir_table: Indirection table for RSS
  * @rx_scatter: Scatter mode enabled for receives
- * @rss_active: RSS enabled on hardware
- * @rx_hash_udp_4tuple: UDP 4-tuple hashing enabled
+ * @rss_context: Main RSS context.  Its @list member is the head of the list of
+ *	RSS contexts created by user requests
  * @int_error_count: Number of internal errors seen recently
  * @int_error_expire: Time at which error count will be expired
  * @irq_soft_enabled: Are IRQs soft-enabled? If not, IRQ handler will
@@ -909,11 +929,8 @@ struct efx_nic {
 	int rx_packet_hash_offset;
 	int rx_packet_len_offset;
 	int rx_packet_ts_offset;
-	u8 rx_hash_key[40];
-	u32 rx_indir_table[128];
 	bool rx_scatter;
-	bool rss_active;
-	bool rx_hash_udp_4tuple;
+	struct efx_rss_context rss_context;
 
 	unsigned int_error_count;
 	unsigned long int_error_expire;
@@ -1099,6 +1116,10 @@ struct efx_udp_tunnel {
  * @tx_write: Write TX descriptors and doorbell
  * @rx_push_rss_config: Write RSS hash key and indirection table to the NIC
  * @rx_pull_rss_config: Read RSS hash key and indirection table back from the NIC
+ * @rx_push_rss_context_config: Write RSS hash key and indirection table for
+ *	user RSS context to the NIC
+ * @rx_pull_rss_context_config: Read RSS hash key and indirection table for user
+ *	RSS context back from the NIC
  * @rx_probe: Allocate resources for RX queue
  * @rx_init: Initialise RX queue on the NIC
  * @rx_remove: Free resources for RX queue
@@ -1237,6 +1258,13 @@ struct efx_nic_type {
 	int (*rx_push_rss_config)(struct efx_nic *efx, bool user,
 				  const u32 *rx_indir_table, const u8 *key);
 	int (*rx_pull_rss_config)(struct efx_nic *efx);
+	int (*rx_push_rss_context_config)(struct efx_nic *efx,
+					  struct efx_rss_context *ctx,
+					  const u32 *rx_indir_table,
+					  const u8 *key);
+	int (*rx_pull_rss_context_config)(struct efx_nic *efx,
+					  struct efx_rss_context *ctx);
+	void (*rx_restore_rss_contexts)(struct efx_nic *efx);
 	int (*rx_probe)(struct efx_rx_queue *rx_queue);
 	void (*rx_init)(struct efx_rx_queue *rx_queue);
 	void (*rx_remove)(struct efx_rx_queue *rx_queue);

drivers/net/ethernet/sfc/nic.h

@@ -374,7 +374,6 @@ enum {
  * @piobuf_size: size of a single PIO buffer
  * @must_restore_piobufs: Flag: PIO buffers have yet to be restored after MC
  *	reboot
- * @rx_rss_context: Firmware handle for our RSS context
  * @rx_rss_context_exclusive: Whether our RSS context is exclusive or shared
  * @stats: Hardware statistics
  * @workaround_35388: Flag: firmware supports workaround for bug 35388
@@ -415,7 +414,6 @@ struct efx_ef10_nic_data {
 	unsigned int piobuf_handle[EF10_TX_PIOBUF_COUNT];
 	u16 piobuf_size;
 	bool must_restore_piobufs;
-	u32 rx_rss_context;
 	bool rx_rss_context_exclusive;
 	u64 stats[EF10_STAT_COUNT];
 	bool workaround_35388;

drivers/net/ethernet/sfc/siena.c

@@ -350,11 +350,11 @@ static int siena_rx_pull_rss_config(struct efx_nic *efx)
 	 * siena_rx_push_rss_config, below)
 	 */
 	efx_reado(efx, &temp, FR_CZ_RX_RSS_IPV6_REG1);
-	memcpy(efx->rx_hash_key, &temp, sizeof(temp));
+	memcpy(efx->rss_context.rx_hash_key, &temp, sizeof(temp));
 	efx_reado(efx, &temp, FR_CZ_RX_RSS_IPV6_REG2);
-	memcpy(efx->rx_hash_key + sizeof(temp), &temp, sizeof(temp));
+	memcpy(efx->rss_context.rx_hash_key + sizeof(temp), &temp, sizeof(temp));
 	efx_reado(efx, &temp, FR_CZ_RX_RSS_IPV6_REG3);
-	memcpy(efx->rx_hash_key + 2 * sizeof(temp), &temp,
+	memcpy(efx->rss_context.rx_hash_key + 2 * sizeof(temp), &temp,
 	       FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8);
 	efx_farch_rx_pull_indir_table(efx);
 	return 0;
@@ -367,26 +367,26 @@ static int siena_rx_push_rss_config(struct efx_nic *efx, bool user,
 
 	/* Set hash key for IPv4 */
 	if (key)
-		memcpy(efx->rx_hash_key, key, sizeof(temp));
-	memcpy(&temp, efx->rx_hash_key, sizeof(temp));
+		memcpy(efx->rss_context.rx_hash_key, key, sizeof(temp));
+	memcpy(&temp, efx->rss_context.rx_hash_key, sizeof(temp));
 	efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY);
 
 	/* Enable IPv6 RSS */
-	BUILD_BUG_ON(sizeof(efx->rx_hash_key) <
+	BUILD_BUG_ON(sizeof(efx->rss_context.rx_hash_key) <
 		     2 * sizeof(temp) + FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8 ||
 		     FRF_CZ_RX_RSS_IPV6_TKEY_HI_LBN != 0);
-	memcpy(&temp, efx->rx_hash_key, sizeof(temp));
+	memcpy(&temp, efx->rss_context.rx_hash_key, sizeof(temp));
 	efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG1);
-	memcpy(&temp, efx->rx_hash_key + sizeof(temp), sizeof(temp));
+	memcpy(&temp, efx->rss_context.rx_hash_key + sizeof(temp), sizeof(temp));
 	efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG2);
 	EFX_POPULATE_OWORD_2(temp, FRF_CZ_RX_RSS_IPV6_THASH_ENABLE, 1,
 			     FRF_CZ_RX_RSS_IPV6_IP_THASH_ENABLE, 1);
-	memcpy(&temp, efx->rx_hash_key + 2 * sizeof(temp),
+	memcpy(&temp, efx->rss_context.rx_hash_key + 2 * sizeof(temp),
 	       FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8);
 	efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG3);
 
-	memcpy(efx->rx_indir_table, rx_indir_table,
-	       sizeof(efx->rx_indir_table));
+	memcpy(efx->rss_context.rx_indir_table, rx_indir_table,
+	       sizeof(efx->rss_context.rx_indir_table));
 	efx_farch_rx_push_indir_table(efx);
 
 	return 0;
@@ -432,8 +432,8 @@ static int siena_init_nic(struct efx_nic *efx)
 			    EFX_RX_USR_BUF_SIZE >> 5);
 	efx_writeo(efx, &temp, FR_AZ_RX_CFG);
 
-	siena_rx_push_rss_config(efx, false, efx->rx_indir_table, NULL);
-	efx->rss_active = true;
+	siena_rx_push_rss_config(efx, false, efx->rss_context.rx_indir_table, NULL);
+	efx->rss_context.context_id = 0; /* indicates RSS is active */
 
 	/* Enable event logging */
 	rc = efx_mcdi_log_ctrl(efx, true, false, 0);

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);