[net-next, v3 05/11] bnge: add RXFH ethtool support

[Vikas Gupta <vikas.gupta@broadcom.com>]

Introduce ethtool RXFH operations including get/set_rxfh for
reading and programming the RSS hash key and indirection table.

Currently set_rxfh and set_rxfh_fields are supported only while the
device is down. A future patch series will rework
bnge_close_core()/bnge_open_core() so they can be driven safely
from the ethtool path, adding full functionality by applying the
configuration on a live device.

Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Reviewed-by: Bhargava Chenna Marreddy <bhargava.marreddy@broadcom.com>
Reviewed-by: Dharmender Garg <dharmender.garg@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnge/bnge.h     |   1 +
 .../net/ethernet/broadcom/bnge/bnge_ethtool.c | 276 ++++++++++++++++++
 .../ethernet/broadcom/bnge/bnge_hwrm_lib.c    |   2 +
 .../net/ethernet/broadcom/bnge/bnge_netdev.c  |  17 +-
 .../net/ethernet/broadcom/bnge/bnge_netdev.h  |   2 +
 .../net/ethernet/broadcom/bnge/bnge_vnic.h    |   1 +
 6 files changed, 297 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnge/bnge.h b/drivers/net/ethernet/broadcom/bnge/bnge.h
index fc2f45fa7712..f0b152e6a43a 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge.h
+++ b/drivers/net/ethernet/broadcom/bnge/bnge.h
@@ -87,6 +87,7 @@ enum {
 	BNGE_RSS_CAP_AH_V6_RSS_CAP			= BIT(5),
 	BNGE_RSS_CAP_ESP_V4_RSS_CAP			= BIT(6),
 	BNGE_RSS_CAP_ESP_V6_RSS_CAP			= BIT(7),
+	BNGE_RSS_CAP_IPV6_FLOW_LABEL_RSS_CAP		= BIT(8),
 };
 
 #define BNGE_MAX_QUEUE		8
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c
index 2467e44de291..f1969de08534 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c
@@ -10,6 +10,9 @@
 #include <linux/ethtool_netlink.h>
 
 #include "bnge.h"
+#include "bnge_netdev.h"
+#include "bnge_vnic.h"
+#include "bnge_resc.h"
 #include "bnge_ethtool.h"
 #include "bnge_hwrm_lib.h"
 
@@ -740,6 +743,267 @@ static int bnge_set_pauseparam(struct net_device *dev,
 	return rc;
 }
 
+static u64 bnge_get_ethtool_ipv4_rss(struct bnge_dev *bd)
+{
+	if (bd->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4)
+		return RXH_IP_SRC | RXH_IP_DST;
+	return 0;
+}
+
+static u64 bnge_get_ethtool_ipv6_rss(struct bnge_dev *bd)
+{
+	if (bd->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6)
+		return RXH_IP_SRC | RXH_IP_DST;
+	if (bd->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL)
+		return RXH_IP_SRC | RXH_IP_DST | RXH_IP6_FL;
+	return 0;
+}
+
+static int bnge_get_rxfh_fields(struct net_device *dev,
+				struct ethtool_rxfh_fields *cmd)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_dev *bd = bn->bd;
+
+	cmd->data = 0;
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+		if (bd->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4)
+			cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+				     RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		cmd->data |= bnge_get_ethtool_ipv4_rss(bd);
+		break;
+	case UDP_V4_FLOW:
+		if (bd->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4)
+			cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+				     RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		cmd->data |= bnge_get_ethtool_ipv4_rss(bd);
+		break;
+	case AH_ESP_V4_FLOW:
+		if (bd->rss_hash_cfg &
+		    (VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV4 |
+		     VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV4))
+			cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+				     RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		cmd->data |= bnge_get_ethtool_ipv4_rss(bd);
+		break;
+	case SCTP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case IPV4_FLOW:
+		cmd->data |= bnge_get_ethtool_ipv4_rss(bd);
+		break;
+	case TCP_V6_FLOW:
+		if (bd->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6)
+			cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+				     RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		cmd->data |= bnge_get_ethtool_ipv6_rss(bd);
+		break;
+	case UDP_V6_FLOW:
+		if (bd->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6)
+			cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+				     RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		cmd->data |= bnge_get_ethtool_ipv6_rss(bd);
+		break;
+	case AH_ESP_V6_FLOW:
+		if (bd->rss_hash_cfg &
+		    (VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV6 |
+		     VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV6))
+			cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+				     RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		cmd->data |= bnge_get_ethtool_ipv6_rss(bd);
+		break;
+	case SCTP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case IPV6_FLOW:
+		cmd->data |= bnge_get_ethtool_ipv6_rss(bd);
+		break;
+	}
+	return 0;
+}
+
+#define RXH_4TUPLE (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)
+#define RXH_2TUPLE (RXH_IP_SRC | RXH_IP_DST)
+
+static int bnge_set_rxfh_fields(struct net_device *dev,
+				const struct ethtool_rxfh_fields *cmd,
+				struct netlink_ext_ack *extack)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_dev *bd = bn->bd;
+	u32 rss_hash_cfg;
+	int tuple;
+
+	rss_hash_cfg = bd->rss_hash_cfg;
+
+	if (cmd->data == RXH_4TUPLE ||
+	    cmd->data == (RXH_4TUPLE | RXH_IP6_FL))
+		tuple = 4;
+	else if (cmd->data == RXH_2TUPLE ||
+		 cmd->data == (RXH_2TUPLE | RXH_IP6_FL))
+		tuple = 2;
+	else if (!cmd->data)
+		tuple = 0;
+	else
+		return -EINVAL;
+
+	if (cmd->data & RXH_IP6_FL &&
+	    !(bd->rss_cap & BNGE_RSS_CAP_IPV6_FLOW_LABEL_RSS_CAP))
+		return -EINVAL;
+
+	if (cmd->flow_type == TCP_V4_FLOW) {
+		rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4;
+		if (tuple == 4)
+			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4;
+	} else if (cmd->flow_type == UDP_V4_FLOW) {
+		rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4;
+		if (tuple == 4)
+			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4;
+	} else if (cmd->flow_type == TCP_V6_FLOW) {
+		rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
+		if (tuple == 4)
+			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
+	} else if (cmd->flow_type == UDP_V6_FLOW) {
+		rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
+		if (tuple == 4)
+			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
+	} else if (cmd->flow_type == AH_ESP_V4_FLOW) {
+		if (tuple == 4 &&
+		    (!(bd->rss_cap & BNGE_RSS_CAP_AH_V4_RSS_CAP) ||
+		     !(bd->rss_cap & BNGE_RSS_CAP_ESP_V4_RSS_CAP)))
+			return -EINVAL;
+		rss_hash_cfg &= ~(VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV4 |
+				  VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV4);
+		if (tuple == 4)
+			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV4 |
+					VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV4;
+	} else if (cmd->flow_type == AH_ESP_V6_FLOW) {
+		if (tuple == 4 &&
+		    (!(bd->rss_cap & BNGE_RSS_CAP_AH_V6_RSS_CAP) ||
+		     !(bd->rss_cap & BNGE_RSS_CAP_ESP_V6_RSS_CAP)))
+			return -EINVAL;
+		rss_hash_cfg &= ~(VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV6 |
+				  VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV6);
+		if (tuple == 4)
+			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV6 |
+					VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV6;
+	} else if (tuple == 4) {
+		return -EINVAL;
+	}
+
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case IPV4_FLOW:
+		if (tuple == 2)
+			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4;
+		else if (!tuple)
+			rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4;
+		break;
+
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case IPV6_FLOW:
+		if (cmd->data & RXH_IP6_FL) {
+			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL;
+			rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6;
+		} else if (tuple == 2) {
+			rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6;
+			rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL;
+		} else if (!tuple) {
+			rss_hash_cfg &= ~(VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
+					  VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL);
+		}
+		break;
+	}
+
+	if (bd->rss_hash_cfg == rss_hash_cfg)
+		return 0;
+
+	if (netif_running(dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "RSS configuration can only be changed while the interface is down");
+		return -EBUSY;
+	}
+
+	bd->rss_hash_cfg = rss_hash_cfg;
+
+	return 0;
+}
+
+static u32 bnge_get_rxfh_indir_size_eth(struct net_device *dev)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_dev *bd = bn->bd;
+
+	return bnge_get_rxfh_indir_size(bd);
+}
+
+static u32 bnge_get_rxfh_key_size(struct net_device *dev)
+{
+	return HW_HASH_KEY_SIZE;
+}
+
+static int bnge_get_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_dev *bd = bn->bd;
+	u32 i, tbl_size;
+	u32 *indir_tbl;
+
+	indir_tbl = bd->rss_indir_tbl;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+
+	if (rxfh->indir && indir_tbl) {
+		tbl_size = bnge_get_rxfh_indir_size(bd);
+		for (i = 0; i < tbl_size; i++)
+			rxfh->indir[i] = indir_tbl[i];
+	}
+
+	if (rxfh->key)
+		memcpy(rxfh->key, bn->rss_hash_key, HW_HASH_KEY_SIZE);
+
+	return 0;
+}
+
+static int bnge_set_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (netif_running(dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "RSS configuration can only be changed while the interface is down");
+		return -EBUSY;
+	}
+
+	bnge_modify_rss(bn, NULL, NULL, rxfh);
+
+	return 0;
+}
+
+static u32 bnge_get_rx_ring_count(struct net_device *dev)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_dev *bd = bn->bd;
+
+	return bd->rx_nr_rings;
+}
+
 static const struct ethtool_ops bnge_ethtool_ops = {
 	.cap_link_lanes_supported	= 1,
 	.get_link_ksettings	= bnge_get_link_ksettings,
@@ -757,6 +1021,18 @@ static const struct ethtool_ops bnge_ethtool_ops = {
 	.get_eth_ctrl_stats	= bnge_get_eth_ctrl_stats,
 	.get_pause_stats	= bnge_get_pause_stats,
 	.get_rmon_stats		= bnge_get_rmon_stats,
+	/* RXFH */
+	.rxfh_per_ctx_key	= 1,
+	.rxfh_max_num_contexts	= BNGE_MAX_ETH_RSS_CTX + 1,
+	.rxfh_indir_space	= BNGE_MAX_RSS_TABLE_ENTRIES,
+	.rxfh_priv_size		= sizeof(struct bnge_rss_ctx),
+	.get_rx_ring_count	= bnge_get_rx_ring_count,
+	.get_rxfh_indir_size	= bnge_get_rxfh_indir_size_eth,
+	.get_rxfh_key_size	= bnge_get_rxfh_key_size,
+	.get_rxfh		= bnge_get_rxfh,
+	.set_rxfh		= bnge_set_rxfh,
+	.get_rxfh_fields	= bnge_get_rxfh_fields,
+	.set_rxfh_fields	= bnge_set_rxfh_fields,
 };
 
 void bnge_set_ethtool_ops(struct net_device *dev)
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
index 91d246c8dcf2..86edb70d323e 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
@@ -676,6 +676,8 @@ int bnge_hwrm_vnic_qcaps(struct bnge_dev *bd)
 			bd->rss_cap |= BNGE_RSS_CAP_ESP_V4_RSS_CAP;
 		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP)
 			bd->rss_cap |= BNGE_RSS_CAP_ESP_V6_RSS_CAP;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPV6_FLOW_LABEL_CAP)
+			bd->rss_cap |= BNGE_RSS_CAP_IPV6_FLOW_LABEL_RSS_CAP;
 	}
 	bnge_hwrm_req_drop(bd, req);
 
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
index bab706cb969f..c75c0a7f5c80 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
@@ -772,6 +772,9 @@ static void bnge_free_tx_skbs(struct bnge_net *bn)
 	u16 max_idx;
 	int i;
 
+	if (!bn->tx_ring)
+		return;
+
 	max_idx = bn->tx_nr_pages * TX_DESC_CNT;
 	for (i = 0; i < bd->tx_nr_rings; i++) {
 		struct bnge_tx_ring_info *txr = &bn->tx_ring[i];
@@ -883,6 +886,9 @@ static void bnge_free_rx_rings(struct bnge_net *bn)
 	struct bnge_dev *bd = bn->bd;
 	int i;
 
+	if (!bn->rx_ring)
+		return;
+
 	bnge_free_tpa_info(bn);
 	for (i = 0; i < bd->rx_nr_rings; i++) {
 		struct bnge_rx_ring_info *rxr = &bn->rx_ring[i];
@@ -1026,6 +1032,9 @@ static void bnge_free_tx_rings(struct bnge_net *bn)
 	struct bnge_dev *bd = bn->bd;
 	int i;
 
+	if (!bn->tx_ring)
+		return;
+
 	for (i = 0; i < bd->tx_nr_rings; i++) {
 		struct bnge_tx_ring_info *txr = &bn->tx_ring[i];
 		struct bnge_ring_struct *ring;
@@ -2723,7 +2732,7 @@ static int bnge_hwrm_if_change(struct bnge_dev *bd, bool up)
 	return bnge_hwrm_req_send(bd, req);
 }
 
-static int bnge_open_core(struct bnge_net *bn)
+int bnge_open_core(struct bnge_net *bn)
 {
 	struct bnge_dev *bd = bn->bd;
 	int rc;
@@ -2993,10 +3002,14 @@ static void bnge_save_ring_stats(struct bnge_net *bn)
 	}
 }
 
-static void bnge_close_core(struct bnge_net *bn)
+void bnge_close_core(struct bnge_net *bn)
 {
 	struct bnge_dev *bd = bn->bd;
 
+	/* Already torn down (e.g. after a failed open/reconfiguration) */
+	if (!bn->bnapi)
+		return;
+
 	bnge_tx_disable(bn);
 
 	clear_bit(BNGE_STATE_OPEN, &bd->state);
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
index 3c0fea0a7608..d68eaa78d4e0 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
@@ -579,4 +579,6 @@ int bnge_alloc_rx_netmem(struct bnge_net *bn, struct bnge_rx_ring_info *rxr,
 			 u16 prod, gfp_t gfp);
 void __bnge_queue_sp_work(struct bnge_net *bn);
 void bnge_copy_hw_masks(u64 *mask_arr, __le64 *hw_mask_arr, int count);
+int bnge_open_core(struct bnge_net *bn);
+void bnge_close_core(struct bnge_net *bn);
 #endif /* _BNGE_NETDEV_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_vnic.h b/drivers/net/ethernet/broadcom/bnge/bnge_vnic.h
index af066d8ff156..b2a1d8332a5f 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_vnic.h
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_vnic.h
@@ -15,6 +15,7 @@ struct bnge_l2_filter;
 #define BNGE_MAX_RSS_TABLE_ENTRIES				\
 	(BNGE_RSS_TABLE_ENTRIES * BNGE_RSS_TABLE_MAX_TBL)
 
+#define BNGE_MAX_ETH_RSS_CTX	32
 #define BNGE_MAX_CTX_PER_VNIC	8
 
 #define BNGE_MAX_MC_ADDRS	16
-- 
2.52.0