[dpdk-dev] [PATCH v4 42/58] net/txgbe: add RSS support

[Jiawen Wu <jiawenwu@trustnetic.com>]

Add RSS configure, support to RSS hash and reta operations for PF.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
---
 doc/guides/nics/features/txgbe.ini |   3 +
 doc/guides/nics/txgbe.rst          |   1 +
 drivers/net/txgbe/meson.build      |   2 +
 drivers/net/txgbe/txgbe_ethdev.c   | 102 ++++++++++++++
 drivers/net/txgbe/txgbe_ethdev.h   |  16 +++
 drivers/net/txgbe/txgbe_rxtx.c     | 216 ++++++++++++++++++++++++++++-
 6 files changed, 339 insertions(+), 1 deletion(-)

diff --git a/doc/guides/nics/features/txgbe.ini b/doc/guides/nics/features/txgbe.ini
index 578ec05b0..fd9c5850d 100644
--- a/doc/guides/nics/features/txgbe.ini
+++ b/doc/guides/nics/features/txgbe.ini
@@ -15,6 +15,9 @@ LRO                  = Y
 TSO                  = Y
 Unicast MAC filter   = Y
 Multicast MAC filter = Y
+RSS hash             = Y
+RSS key update       = Y
+RSS reta update      = Y
 VMDq                 = Y
 SR-IOV               = Y
 VLAN filter          = Y
diff --git a/doc/guides/nics/txgbe.rst b/doc/guides/nics/txgbe.rst
index 212167d22..c07fef99b 100644
--- a/doc/guides/nics/txgbe.rst
+++ b/doc/guides/nics/txgbe.rst
@@ -11,6 +11,7 @@ Features
 --------
 
 - Multiple queues for TX and RX
+- Receiver Side Scaling (RSS)
 - MAC/VLAN filtering
 - Packet type information
 - Checksum offload
diff --git a/drivers/net/txgbe/meson.build b/drivers/net/txgbe/meson.build
index 7b6c1731b..345dffaf6 100644
--- a/drivers/net/txgbe/meson.build
+++ b/drivers/net/txgbe/meson.build
@@ -11,6 +11,8 @@ sources = files(
 	'txgbe_rxtx.c',
 )
 
+deps += ['hash']
+
 includes += include_directories('base')
 
 install_headers('rte_pmd_txgbe.h')
diff --git a/drivers/net/txgbe/txgbe_ethdev.c b/drivers/net/txgbe/txgbe_ethdev.c
index e14980a2e..96f8720e9 100644
--- a/drivers/net/txgbe/txgbe_ethdev.c
+++ b/drivers/net/txgbe/txgbe_ethdev.c
@@ -1476,6 +1476,7 @@ static void
 txgbe_dev_stop(struct rte_eth_dev *dev)
 {
 	struct rte_eth_link link;
+	struct txgbe_adapter *adapter = TXGBE_DEV_ADAPTER(dev);
 	struct txgbe_hw *hw = TXGBE_DEV_HW(dev);
 	struct txgbe_vf_info *vfinfo = *TXGBE_DEV_VFDATA(dev);
 	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
@@ -1533,6 +1534,7 @@ txgbe_dev_stop(struct rte_eth_dev *dev)
 		intr_handle->intr_vec = NULL;
 	}
 
+	adapter->rss_reta_updated = 0;
 	wr32m(hw, TXGBE_LEDCTL, 0xFFFFFFFF, TXGBE_LEDCTL_SEL_MASK);
 
 	hw->adapter_stopped = true;
@@ -2633,6 +2635,91 @@ txgbe_dev_interrupt_handler(void *param)
 	txgbe_dev_interrupt_action(dev, dev->intr_handle);
 }
 
+int
+txgbe_dev_rss_reta_update(struct rte_eth_dev *dev,
+			  struct rte_eth_rss_reta_entry64 *reta_conf,
+			  uint16_t reta_size)
+{
+	uint8_t i, j, mask;
+	uint32_t reta;
+	uint16_t idx, shift;
+	struct txgbe_adapter *adapter = TXGBE_DEV_ADAPTER(dev);
+	struct txgbe_hw *hw = TXGBE_DEV_HW(dev);
+
+	PMD_INIT_FUNC_TRACE();
+
+	if (!txgbe_rss_update_sp(hw->mac.type)) {
+		PMD_DRV_LOG(ERR, "RSS reta update is not supported on this "
+			"NIC.");
+		return -ENOTSUP;
+	}
+
+	if (reta_size != ETH_RSS_RETA_SIZE_128) {
+		PMD_DRV_LOG(ERR, "The size of hash lookup table configured "
+			"(%d) doesn't match the number hardware can supported "
+			"(%d)", reta_size, ETH_RSS_RETA_SIZE_128);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < reta_size; i += 4) {
+		idx = i / RTE_RETA_GROUP_SIZE;
+		shift = i % RTE_RETA_GROUP_SIZE;
+		mask = (uint8_t)RS64(reta_conf[idx].mask, shift, 0xF);
+		if (!mask)
+			continue;
+
+		reta = rd32a(hw, TXGBE_REG_RSSTBL, i >> 2);
+		for (j = 0; j < 4; j++) {
+			if (RS8(mask, j, 0x1)) {
+				reta  &= ~(MS32(8 * j, 0xFF));
+				reta |= LS32(reta_conf[idx].reta[shift + j],
+						8 * j, 0xFF);
+			}
+		}
+		wr32a(hw, TXGBE_REG_RSSTBL, i >> 2, reta);
+	}
+	adapter->rss_reta_updated = 1;
+
+	return 0;
+}
+
+int
+txgbe_dev_rss_reta_query(struct rte_eth_dev *dev,
+			 struct rte_eth_rss_reta_entry64 *reta_conf,
+			 uint16_t reta_size)
+{
+	struct txgbe_hw *hw = TXGBE_DEV_HW(dev);
+	uint8_t i, j, mask;
+	uint32_t reta;
+	uint16_t idx, shift;
+
+	PMD_INIT_FUNC_TRACE();
+
+	if (reta_size != ETH_RSS_RETA_SIZE_128) {
+		PMD_DRV_LOG(ERR, "The size of hash lookup table configured "
+			"(%d) doesn't match the number hardware can supported "
+			"(%d)", reta_size, ETH_RSS_RETA_SIZE_128);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < reta_size; i += 4) {
+		idx = i / RTE_RETA_GROUP_SIZE;
+		shift = i % RTE_RETA_GROUP_SIZE;
+		mask = (uint8_t)RS64(reta_conf[idx].mask, shift, 0xF);
+		if (!mask)
+			continue;
+
+		reta = rd32a(hw, TXGBE_REG_RSSTBL, i >> 2);
+		for (j = 0; j < 4; j++) {
+			if (RS8(mask, j, 0x1))
+				reta_conf[idx].reta[shift + j] =
+					(uint16_t)RS32(reta, 8 * j, 0xFF);
+		}
+	}
+
+	return 0;
+}
+
 static int
 txgbe_add_rar(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr,
 				uint32_t index, uint32_t pool)
@@ -2989,6 +3076,17 @@ txgbe_dev_set_mc_addr_list(struct rte_eth_dev *dev,
 					 txgbe_dev_addr_list_itr, TRUE);
 }
 
+bool
+txgbe_rss_update_sp(enum txgbe_mac_type mac_type)
+{
+	switch (mac_type) {
+	case txgbe_mac_raptor:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
 static const struct eth_dev_ops txgbe_eth_dev_ops = {
 	.dev_configure              = txgbe_dev_configure,
 	.dev_infos_get              = txgbe_dev_info_get,
@@ -3028,6 +3126,10 @@ static const struct eth_dev_ops txgbe_eth_dev_ops = {
 	.uc_hash_table_set          = txgbe_uc_hash_table_set,
 	.uc_all_hash_table_set      = txgbe_uc_all_hash_table_set,
 	.set_queue_rate_limit       = txgbe_set_queue_rate_limit,
+	.reta_update                = txgbe_dev_rss_reta_update,
+	.reta_query                 = txgbe_dev_rss_reta_query,
+	.rss_hash_update            = txgbe_dev_rss_hash_update,
+	.rss_hash_conf_get          = txgbe_dev_rss_hash_conf_get,
 	.set_mc_addr_list           = txgbe_dev_set_mc_addr_list,
 	.rxq_info_get               = txgbe_rxq_info_get,
 	.txq_info_get               = txgbe_txq_info_get,
diff --git a/drivers/net/txgbe/txgbe_ethdev.h b/drivers/net/txgbe/txgbe_ethdev.h
index bf13e0378..e264bcc5e 100644
--- a/drivers/net/txgbe/txgbe_ethdev.h
+++ b/drivers/net/txgbe/txgbe_ethdev.h
@@ -142,6 +142,8 @@ struct txgbe_adapter {
 	struct txgbe_uta_info       uta_info;
 	struct txgbe_filter_info    filter;
 	bool rx_bulk_alloc_allowed;
+	/* For RSS reta table update */
+	uint8_t rss_reta_updated;
 };
 
 #define TXGBE_DEV_ADAPTER(dev) \
@@ -242,6 +244,14 @@ uint16_t txgbe_xmit_pkts_simple(void *tx_queue, struct rte_mbuf **tx_pkts,
 uint16_t txgbe_prep_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 		uint16_t nb_pkts);
 
+int txgbe_dev_rss_hash_update(struct rte_eth_dev *dev,
+			      struct rte_eth_rss_conf *rss_conf);
+
+int txgbe_dev_rss_hash_conf_get(struct rte_eth_dev *dev,
+				struct rte_eth_rss_conf *rss_conf);
+
+bool txgbe_rss_update_sp(enum txgbe_mac_type mac_type);
+
 void txgbe_set_ivar_map(struct txgbe_hw *hw, int8_t direction,
 			       uint8_t queue, uint8_t msix_vector);
 
@@ -328,6 +338,12 @@ const uint32_t *txgbe_dev_supported_ptypes_get(struct rte_eth_dev *dev);
 int txgbe_dev_set_mc_addr_list(struct rte_eth_dev *dev,
 				      struct rte_ether_addr *mc_addr_set,
 				      uint32_t nb_mc_addr);
+int txgbe_dev_rss_reta_update(struct rte_eth_dev *dev,
+			struct rte_eth_rss_reta_entry64 *reta_conf,
+			uint16_t reta_size);
+int txgbe_dev_rss_reta_query(struct rte_eth_dev *dev,
+			struct rte_eth_rss_reta_entry64 *reta_conf,
+			uint16_t reta_size);
 void txgbe_dev_setup_link_alarm_handler(void *param);
 void txgbe_read_stats_registers(struct txgbe_hw *hw,
 			   struct txgbe_hw_stats *hw_stats);
diff --git a/drivers/net/txgbe/txgbe_rxtx.c b/drivers/net/txgbe/txgbe_rxtx.c
index c8ca9e2d0..00724270b 100644
--- a/drivers/net/txgbe/txgbe_rxtx.c
+++ b/drivers/net/txgbe/txgbe_rxtx.c
@@ -2555,6 +2555,33 @@ txgbe_dev_free_queues(struct rte_eth_dev *dev)
 	dev->data->nb_tx_queues = 0;
 }
 
+/**
+ * Receive Side Scaling (RSS)
+ *
+ * Principles:
+ * The source and destination IP addresses of the IP header and the source
+ * and destination ports of TCP/UDP headers, if any, of received packets are
+ * hashed against a configurable random key to compute a 32-bit RSS hash result.
+ * The seven (7) LSBs of the 32-bit hash result are used as an index into a
+ * 128-entry redirection table (RETA).  Each entry of the RETA provides a 3-bit
+ * RSS output index which is used as the RX queue index where to store the
+ * received packets.
+ * The following output is supplied in the RX write-back descriptor:
+ *     - 32-bit result of the Microsoft RSS hash function,
+ *     - 4-bit RSS type field.
+ */
+
+/*
+ * Used as the default key.
+ */
+static uint8_t rss_intel_key[40] = {
+	0x6D, 0x5A, 0x56, 0xDA, 0x25, 0x5B, 0x0E, 0xC2,
+	0x41, 0x67, 0x25, 0x3D, 0x43, 0xA3, 0x8F, 0xB0,
+	0xD0, 0xCA, 0x2B, 0xCB, 0xAE, 0x7B, 0x30, 0xB4,
+	0x77, 0xCB, 0x2D, 0xA3, 0x80, 0x30, 0xF2, 0x0C,
+	0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA,
+};
+
 static void
 txgbe_rss_disable(struct rte_eth_dev *dev)
 {
@@ -2565,6 +2592,151 @@ txgbe_rss_disable(struct rte_eth_dev *dev)
 	wr32m(hw, TXGBE_RACTL, TXGBE_RACTL_RSSENA, 0);
 }
 
+int
+txgbe_dev_rss_hash_update(struct rte_eth_dev *dev,
+			  struct rte_eth_rss_conf *rss_conf)
+{
+	struct txgbe_hw *hw = TXGBE_DEV_HW(dev);
+	uint8_t  *hash_key;
+	uint32_t mrqc;
+	uint32_t rss_key;
+	uint64_t rss_hf;
+	uint16_t i;
+
+	if (!txgbe_rss_update_sp(hw->mac.type)) {
+		PMD_DRV_LOG(ERR, "RSS hash update is not supported on this "
+			"NIC.");
+		return -ENOTSUP;
+	}
+
+	hash_key = rss_conf->rss_key;
+	if (hash_key) {
+		/* Fill in RSS hash key */
+		for (i = 0; i < 10; i++) {
+			rss_key  = LS32(hash_key[(i * 4) + 0], 0, 0xFF);
+			rss_key |= LS32(hash_key[(i * 4) + 1], 8, 0xFF);
+			rss_key |= LS32(hash_key[(i * 4) + 2], 16, 0xFF);
+			rss_key |= LS32(hash_key[(i * 4) + 3], 24, 0xFF);
+			wr32a(hw, TXGBE_REG_RSSKEY, i, rss_key);
+		}
+	}
+
+	/* Set configured hashing protocols */
+	rss_hf = rss_conf->rss_hf & TXGBE_RSS_OFFLOAD_ALL;
+	mrqc = rd32(hw, TXGBE_RACTL);
+	mrqc &= ~TXGBE_RACTL_RSSMASK;
+	if (rss_hf & ETH_RSS_IPV4)
+		mrqc |= TXGBE_RACTL_RSSIPV4;
+	if (rss_hf & ETH_RSS_NONFRAG_IPV4_TCP)
+		mrqc |= TXGBE_RACTL_RSSIPV4TCP;
+	if (rss_hf & ETH_RSS_IPV6 ||
+	    rss_hf & ETH_RSS_IPV6_EX)
+		mrqc |= TXGBE_RACTL_RSSIPV6;
+	if (rss_hf & ETH_RSS_NONFRAG_IPV6_TCP ||
+	    rss_hf & ETH_RSS_IPV6_TCP_EX)
+		mrqc |= TXGBE_RACTL_RSSIPV6TCP;
+	if (rss_hf & ETH_RSS_NONFRAG_IPV4_UDP)
+		mrqc |= TXGBE_RACTL_RSSIPV4UDP;
+	if (rss_hf & ETH_RSS_NONFRAG_IPV6_UDP ||
+	    rss_hf & ETH_RSS_IPV6_UDP_EX)
+		mrqc |= TXGBE_RACTL_RSSIPV6UDP;
+
+	if (rss_hf)
+		mrqc |= TXGBE_RACTL_RSSENA;
+	else
+		mrqc &= ~TXGBE_RACTL_RSSENA;
+
+	wr32(hw, TXGBE_RACTL, mrqc);
+
+	return 0;
+}
+
+int
+txgbe_dev_rss_hash_conf_get(struct rte_eth_dev *dev,
+			    struct rte_eth_rss_conf *rss_conf)
+{
+	struct txgbe_hw *hw = TXGBE_DEV_HW(dev);
+	uint8_t *hash_key;
+	uint32_t mrqc;
+	uint32_t rss_key;
+	uint64_t rss_hf;
+	uint16_t i;
+
+	hash_key = rss_conf->rss_key;
+	if (hash_key) {
+		/* Return RSS hash key */
+		for (i = 0; i < 10; i++) {
+			rss_key = rd32a(hw, TXGBE_REG_RSSKEY, i);
+			hash_key[(i * 4) + 0] = RS32(rss_key, 0, 0xFF);
+			hash_key[(i * 4) + 1] = RS32(rss_key, 8, 0xFF);
+			hash_key[(i * 4) + 2] = RS32(rss_key, 16, 0xFF);
+			hash_key[(i * 4) + 3] = RS32(rss_key, 24, 0xFF);
+		}
+	}
+
+	rss_hf = 0;
+	mrqc = rd32(hw, TXGBE_RACTL);
+	if (mrqc & TXGBE_RACTL_RSSIPV4)
+		rss_hf |= ETH_RSS_IPV4;
+	if (mrqc & TXGBE_RACTL_RSSIPV4TCP)
+		rss_hf |= ETH_RSS_NONFRAG_IPV4_TCP;
+	if (mrqc & TXGBE_RACTL_RSSIPV6)
+		rss_hf |= ETH_RSS_IPV6 |
+			  ETH_RSS_IPV6_EX;
+	if (mrqc & TXGBE_RACTL_RSSIPV6TCP)
+		rss_hf |= ETH_RSS_NONFRAG_IPV6_TCP |
+			  ETH_RSS_IPV6_TCP_EX;
+	if (mrqc & TXGBE_RACTL_RSSIPV4UDP)
+		rss_hf |= ETH_RSS_NONFRAG_IPV4_UDP;
+	if (mrqc & TXGBE_RACTL_RSSIPV6UDP)
+		rss_hf |= ETH_RSS_NONFRAG_IPV6_UDP |
+			  ETH_RSS_IPV6_UDP_EX;
+	if (!(mrqc & TXGBE_RACTL_RSSENA))
+		rss_hf = 0;
+
+	rss_hf &= TXGBE_RSS_OFFLOAD_ALL;
+
+	rss_conf->rss_hf = rss_hf;
+	return 0;
+}
+
+static void
+txgbe_rss_configure(struct rte_eth_dev *dev)
+{
+	struct rte_eth_rss_conf rss_conf;
+	struct txgbe_adapter *adapter = TXGBE_DEV_ADAPTER(dev);
+	struct txgbe_hw *hw = TXGBE_DEV_HW(dev);
+	uint32_t reta;
+	uint16_t i;
+	uint16_t j;
+
+	PMD_INIT_FUNC_TRACE();
+
+	/*
+	 * Fill in redirection table
+	 * The byte-swap is needed because NIC registers are in
+	 * little-endian order.
+	 */
+	if (adapter->rss_reta_updated == 0) {
+		reta = 0;
+		for (i = 0, j = 0; i < ETH_RSS_RETA_SIZE_128; i++, j++) {
+			if (j == dev->data->nb_rx_queues)
+				j = 0;
+			reta = (reta >> 8) | LS32(j, 24, 0xFF);
+			if ((i & 3) == 3)
+				wr32a(hw, TXGBE_REG_RSSTBL, i >> 2, reta);
+		}
+	}
+	/*
+	 * Configure the RSS key and the RSS protocols used to compute
+	 * the RSS hash of input packets.
+	 */
+	rss_conf = dev->data->dev_conf.rx_adv_conf.rss_conf;
+	if (rss_conf.rss_key == NULL)
+		rss_conf.rss_key = rss_intel_key; /* Default hash key */
+	txgbe_dev_rss_hash_update(dev, &rss_conf);
+}
+
 #define NUM_VFTA_REGISTERS 128
 
 /*
@@ -2726,6 +2898,38 @@ txgbe_alloc_rx_queue_mbufs(struct txgbe_rx_queue *rxq)
 	return 0;
 }
 
+static int
+txgbe_config_vf_rss(struct rte_eth_dev *dev)
+{
+	struct txgbe_hw *hw;
+	uint32_t mrqc;
+
+	txgbe_rss_configure(dev);
+
+	hw = TXGBE_DEV_HW(dev);
+
+	/* enable VF RSS */
+	mrqc = rd32(hw, TXGBE_PORTCTL);
+	mrqc &= ~(TXGBE_PORTCTL_NUMTC_MASK | TXGBE_PORTCTL_NUMVT_MASK);
+	switch (RTE_ETH_DEV_SRIOV(dev).active) {
+	case ETH_64_POOLS:
+		mrqc |= TXGBE_PORTCTL_NUMVT_64;
+		break;
+
+	case ETH_32_POOLS:
+		mrqc |= TXGBE_PORTCTL_NUMVT_32;
+		break;
+
+	default:
+		PMD_INIT_LOG(ERR, "Invalid pool number in IOV mode with VMDQ RSS");
+		return -EINVAL;
+	}
+
+	wr32(hw, TXGBE_PORTCTL, mrqc);
+
+	return 0;
+}
+
 static int
 txgbe_config_vf_default(struct rte_eth_dev *dev)
 {
@@ -2763,9 +2967,14 @@ txgbe_dev_mq_rx_configure(struct rte_eth_dev *dev)
 	if (RTE_ETH_DEV_SRIOV(dev).active == 0) {
 		/*
 		 * SRIOV inactive scheme
-		 * VMDq multi-queue setting
+		 * any RSS w/o VMDq multi-queue setting
 		 */
 		switch (dev->data->dev_conf.rxmode.mq_mode) {
+		case ETH_MQ_RX_RSS:
+		case ETH_MQ_RX_VMDQ_RSS:
+			txgbe_rss_configure(dev);
+			break;
+
 		case ETH_MQ_RX_VMDQ_ONLY:
 			txgbe_vmdq_rx_hw_configure(dev);
 			break;
@@ -2778,8 +2987,13 @@ txgbe_dev_mq_rx_configure(struct rte_eth_dev *dev)
 		}
 	} else {
 		/* SRIOV active scheme
+		 * Support RSS together with SRIOV.
 		 */
 		switch (dev->data->dev_conf.rxmode.mq_mode) {
+		case ETH_MQ_RX_RSS:
+		case ETH_MQ_RX_VMDQ_RSS:
+			txgbe_config_vf_rss(dev);
+			break;
 		default:
 			txgbe_config_vf_default(dev);
 			break;
-- 
2.18.4