[net-next, v4 05/10] bnge: add ethtool support to manage RSS contexts

@@ -1009,6 +1009,166 @@ static u32 bnge_get_rx_ring_count(struct net_device *dev)
 	return bd->rx_nr_rings;
 }
 
+static int bnge_rxfh_context_check(struct bnge_net *bn,
+				   const struct ethtool_rxfh_param *rxfh,
+				   struct netlink_ext_ack *extack)
+{
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) {
+		NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!(bn->priv_flags & BNGE_NET_EN_NTUPLE)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Enable ntuple filtering before adding RSS contexts");
+		return -EOPNOTSUPP;
+	}
+
+	if (!netif_running(bn->netdev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to set RSS contexts when interface is down");
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+static int bnge_create_rxfh_context(struct net_device *dev,
+				    struct ethtool_rxfh_context *ctx,
+				    const struct ethtool_rxfh_param *rxfh,
+				    struct netlink_ext_ack *extack)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_rss_ctx *rss_ctx;
+	struct bnge_vnic_info *vnic;
+	int rc;
+
+	rc = bnge_rxfh_context_check(bn, rxfh, extack);
+	if (rc)
+		return rc;
+
+	if (bn->num_rss_ctx >= BNGE_MAX_ETH_RSS_CTX) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Out of RSS contexts, maximum %u",
+				       BNGE_MAX_ETH_RSS_CTX);
+		return -EINVAL;
+	}
+
+	if (!bnge_arfs_capable(bn->bd, true)) {
+		NL_SET_ERR_MSG_MOD(extack, "Out of hardware resources");
+		return -ENOMEM;
+	}
+
+	rss_ctx = ethtool_rxfh_context_priv(ctx);
+
+	bn->num_rss_ctx++;
+
+	vnic = &rss_ctx->vnic;
+
+	bnge_init_vnic_mem(vnic);
+
+	vnic->rss_ctx = ctx;
+	vnic->flags |= BNGE_VNIC_RSSCTX_FLAG;
+	rc = bnge_alloc_vnic_rss_table(bn, vnic);
+	if (rc)
+		goto err_del_rss_ctx;
+
+	/* Populate defaults in the context */
+	bnge_set_dflt_rss_indir_tbl(bn->bd, ctx);
+	ctx->hfunc = ETH_RSS_HASH_TOP;
+	memcpy(vnic->rss_hash_key, bn->rss_hash_key, HW_HASH_KEY_SIZE);
+	memcpy(ethtool_rxfh_context_key(ctx),
+	       bn->rss_hash_key, HW_HASH_KEY_SIZE);
+
+	rc = bnge_hwrm_vnic_alloc(bn->bd, vnic, bn->bd->rx_nr_rings);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to allocate VNIC");
+		goto err_del_rss_ctx;
+	}
+
+	rc = bnge_hwrm_vnic_set_tpa(bn->bd, vnic,
+				    bn->priv_flags & BNGE_NET_EN_TPA);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Unable to set TPA settings to vnic");
+		goto err_del_rss_ctx;
+	}
+	bnge_modify_rss(bn, ctx, rss_ctx, rxfh);
+
+	rc = bnge_setup_vnic(bn, vnic);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to setup vnic");
+		goto err_del_rss_ctx;
+	}
+
+	rss_ctx->index = rxfh->rss_context;
+	return 0;
+
+err_del_rss_ctx:
+	bnge_del_one_rss_ctx(bn, rss_ctx, true);
+	return rc;
+}
+
+static int bnge_modify_rxfh_context(struct net_device *dev,
+				    struct ethtool_rxfh_context *ctx,
+				    const struct ethtool_rxfh_param *rxfh,
+				    struct netlink_ext_ack *extack)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	u8 old_key[HW_HASH_KEY_SIZE];
+	struct bnge_rss_ctx *rss_ctx;
+	u32 *old_indir = NULL;
+	u32 tbl_size;
+	int rc;
+
+	rc = bnge_rxfh_context_check(bn, rxfh, extack);
+	if (rc)
+		return rc;
+
+	rss_ctx = ethtool_rxfh_context_priv(ctx);
+	tbl_size = bnge_get_rxfh_indir_size(bn->bd);
+
+	/* Snapshot the software state so it can be restored if the hardware
+	 * update fails, keeping the reported config consistent with the
+	 * hardware.
+	 */
+	if (rxfh->key)
+		memcpy(old_key, rss_ctx->vnic.rss_hash_key, HW_HASH_KEY_SIZE);
+	if (rxfh->indir) {
+		old_indir = kmemdup(ethtool_rxfh_context_indir(ctx),
+				    tbl_size * sizeof(*old_indir), GFP_KERNEL);
+		if (!old_indir)
+			return -ENOMEM;
+	}
+
+	bnge_modify_rss(bn, ctx, rss_ctx, rxfh);
+
+	rc = bnge_hwrm_vnic_rss_cfg(bn, &rss_ctx->vnic);
+	if (rc) {
+		if (rxfh->key)
+			memcpy(rss_ctx->vnic.rss_hash_key, old_key,
+			       HW_HASH_KEY_SIZE);
+		if (rxfh->indir)
+			memcpy(ethtool_rxfh_context_indir(ctx), old_indir,
+			       tbl_size * sizeof(*old_indir));
+	}
+
+	kfree(old_indir);
+	return rc;
+}
+
+static int bnge_remove_rxfh_context(struct net_device *dev,
+				    struct ethtool_rxfh_context *ctx,
+				    u32 rss_context,
+				    struct netlink_ext_ack *extack)
+{
+	struct bnge_net *bn = netdev_priv(dev);
+	struct bnge_rss_ctx *rss_ctx;
+
+	rss_ctx = ethtool_rxfh_context_priv(ctx);
+
+	bnge_del_one_rss_ctx(bn, rss_ctx, true);
+	return 0;
+}
+
 static const struct ethtool_ops bnge_ethtool_ops = {
 	.cap_link_lanes_supported	= 1,
 	.get_link_ksettings	= bnge_get_link_ksettings,

@@ -1038,6 +1198,9 @@ static const struct ethtool_ops bnge_ethtool_ops = {
 	.set_rxfh		= bnge_set_rxfh,
 	.get_rxfh_fields	= bnge_get_rxfh_fields,
 	.set_rxfh_fields	= bnge_set_rxfh_fields,
+	.create_rxfh_context	= bnge_create_rxfh_context,
+	.modify_rxfh_context	= bnge_modify_rxfh_context,
+	.remove_rxfh_context	= bnge_remove_rxfh_context,
 };
 
 void bnge_set_ethtool_ops(struct net_device *dev)

@@ -2784,6 +2784,8 @@ static int bnge_open_core(struct bnge_net *bn)
 	/* Poll link status and check for SFP+ module status */
 	bnge_get_port_module_status(bn);
 
+	bnge_hwrm_realloc_rss_ctx_vnic(bn);
+
 	return 0;
 
 err_free_irq:

@@ -3001,7 +3003,10 @@ static void bnge_close_core(struct bnge_net *bn)
 	clear_bit(BNGE_STATE_OPEN, &bd->state);
 
 	timer_delete_sync(&bn->timer);
+
+	bnge_clear_rss_ctxs(bn);
 	bnge_shutdown_nic(bn);
+
 	bnge_disable_napi(bn);
 
 	/* Save ring stats before shutdown */

@@ -3139,6 +3144,10 @@ static int bnge_set_features(struct net_device *dev, netdev_features_t features)
 	if (flags == bn->priv_flags)
 		return 0;
 
+	if ((bn->priv_flags & BNGE_NET_EN_NTUPLE) &&
+	    !(flags & BNGE_NET_EN_NTUPLE) && bn->num_rss_ctx)
+		return -EBUSY;
+
 	bn->priv_flags = flags;
 
 	return 0;

@@ -229,6 +229,19 @@ u32 bnge_get_rxfh_indir_size(struct bnge_dev *bd)
 	       BNGE_RSS_TABLE_ENTRIES;
 }
 
+static u16 bnge_get_max_rss_ring(struct bnge_dev *bd)
+{
+	u32 i, tbl_size, max_ring = 0;
+
+	if (!bd->rss_indir_tbl)
+		return 0;
+
+	tbl_size = bnge_get_rxfh_indir_size(bd);
+	for (i = 0; i < tbl_size; i++)
+		max_ring = max_t(u32, max_ring, bd->rss_indir_tbl[i]);
+	return max_ring;
+}
+
 static void bnge_copy_reserved_rings(struct bnge_dev *bd,
 				     struct bnge_hw_rings *hwr)
 {

@@ -344,9 +357,15 @@ int bnge_reserve_rings(struct bnge_dev *bd)
 	hwr.nq = sh ? max_t(u16, tx_cp, rx_rings) : tx_cp + rx_rings;
 	bd->tx_nr_rings = hwr.tx;
 
-	if (rx_rings != bd->rx_nr_rings)
+	if (rx_rings != bd->rx_nr_rings) {
 		dev_warn(bd->dev, "RX rings resv reduced to %d than earlier %d requested\n",
 			 rx_rings, bd->rx_nr_rings);
+		if (bd->netdev && netif_is_rxfh_configured(bd->netdev) &&
+		    (bnge_cal_nr_rss_ctxs(bd->rx_nr_rings) !=
+		     bnge_cal_nr_rss_ctxs(rx_rings) ||
+		     bnge_get_max_rss_ring(bd) >= rx_rings))
+			ethtool_rxfh_indir_lost(bd->netdev);
+	}
 
 	bd->rx_nr_rings = rx_rings;
 	bd->nq_nr_rings = hwr.nq;

@@ -354,8 +373,9 @@ int bnge_reserve_rings(struct bnge_dev *bd)
 	if (!bnge_rings_ok(&hwr))
 		return -ENOMEM;
 
-	if (old_rx_rings != bd->hw_resc.resv_rx_rings)
-		bnge_set_dflt_rss_indir_tbl(bd);
+	if (old_rx_rings != bd->hw_resc.resv_rx_rings &&
+	    (!bd->netdev || !netif_is_rxfh_configured(bd->netdev)))
+		bnge_set_dflt_rss_indir_tbl(bd, NULL);
 
 	if (!bnge_aux_registered(bd)) {
 		u16 resv_msix, resv_ctx, aux_ctxs;

@@ -12,21 +12,26 @@
 #include "bnge_filter.h"
 #include "bnge_resc.h"
 
-void bnge_set_dflt_rss_indir_tbl(struct bnge_dev *bd)
+void bnge_set_dflt_rss_indir_tbl(struct bnge_dev *bd,
+				 struct ethtool_rxfh_context *rss_ctx)
 {
 	u16 max_entries, pad;
 	u32 *rss_indir_tbl;
 	u16 i;
 
 	max_entries = bnge_get_rxfh_indir_size(bd);
-	rss_indir_tbl = &bd->rss_indir_tbl[0];
+
+	if (rss_ctx)
+		rss_indir_tbl = ethtool_rxfh_context_indir(rss_ctx);
+	else
+		rss_indir_tbl = &bd->rss_indir_tbl[0];
 
 	for (i = 0; i < max_entries; i++)
 		rss_indir_tbl[i] = ethtool_rxfh_indir_default(i,
 							      bd->rx_nr_rings);
 
 	pad = bd->rss_indir_tbl_entries - max_entries;
-	if (pad)
+	if (pad && !rss_ctx)
 		memset(&rss_indir_tbl[i], 0, pad * sizeof(*rss_indir_tbl));
 }
 

@@ -44,9 +49,14 @@ void bnge_fill_hw_rss_tbl(struct bnge_net *bn, struct bnge_vnic_info *vnic)
 
 		if (vnic->flags & BNGE_VNIC_NTUPLE_FLAG)
 			j = ethtool_rxfh_indir_default(i, bd->rx_nr_rings);
+		else if (vnic->flags & BNGE_VNIC_RSSCTX_FLAG)
+			j = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
 		else
 			j = bd->rss_indir_tbl[i];
 
+		if (j >= bd->rx_nr_rings)
+			j = ethtool_rxfh_indir_default(i, bd->rx_nr_rings);
+
 		rxr = &bn->rx_ring[j];
 
 		ring_id = rxr->rx_ring_struct.fw_ring_id;

@@ -155,7 +165,7 @@ void bnge_modify_rss(struct bnge_net *bn, struct ethtool_rxfh_context *ctx,
 		for (i = 0; i < tbl_size; i++)
 			indir_tbl[i] = rxfh->indir[i];
 		pad = bd->rss_indir_tbl_entries - tbl_size;
-		if (pad)
+		if (pad && !rss_ctx)
 			memset(&indir_tbl[i], 0, pad * sizeof(*indir_tbl));
 	}
 }

@@ -168,8 +178,11 @@ void bnge_del_one_rss_ctx(struct bnge_net *bn, struct bnge_rss_ctx *rss_ctx,
 
 	bnge_hwrm_vnic_free_one(bn->bd, &rss_ctx->vnic);
 	for (i = 0; i < BNGE_MAX_CTX_PER_VNIC; i++) {
-		if (vnic->fw_rss_cos_lb_ctx[i] != INVALID_HW_RING_ID)
+		if (vnic->fw_rss_cos_lb_ctx[i] != INVALID_HW_RING_ID) {
 			bnge_hwrm_vnic_ctx_free_one(bn->bd, vnic, i);
+			vnic->fw_rss_cos_lb_ctx[i] = INVALID_HW_RING_ID;
+			bn->rsscos_nr_ctxs--;
+		}
 	}
 
 	if (!all)

@@ -188,6 +201,10 @@ void bnge_hwrm_realloc_rss_ctx_vnic(struct bnge_net *bn)
 	struct ethtool_rxfh_context *ctx;
 	unsigned long context;
 
+	/* Erasing lost contexts touches netdev->ethtool->rss_ctx and calls
+	 * ethtool_rxfh_context_lost(), which requires the ethtool rss_lock.
+	 */
+	mutex_lock(&bn->netdev->ethtool->rss_lock);
 	xa_for_each(&bn->netdev->ethtool->rss_ctx, context, ctx) {
 		struct bnge_rss_ctx *rss_ctx = ethtool_rxfh_context_priv(ctx);
 		struct bnge_vnic_info *vnic = &rss_ctx->vnic;

@@ -201,6 +218,7 @@ void bnge_hwrm_realloc_rss_ctx_vnic(struct bnge_net *bn)
 			ethtool_rxfh_context_lost(bn->netdev, rss_ctx->index);
 		}
 	}
+	mutex_unlock(&bn->netdev->ethtool->rss_lock);
 }
 
 void bnge_clear_rss_ctxs(struct bnge_net *bn)

@@ -242,3 +260,14 @@ int bnge_alloc_vnic_rss_table(struct bnge_net *bn,
 	vnic->rss_hash_key_dma_addr = vnic->rss_table_dma_addr + size;
 	return 0;
 }
+
+void bnge_init_vnic_mem(struct bnge_vnic_info *vnic)
+{
+	int i;
+
+	vnic->fw_vnic_id = INVALID_HW_RING_ID;
+	vnic->vnic_id = BNGE_VNIC_ID_INVALID;
+
+	for (i = 0; i < BNGE_MAX_CTX_PER_VNIC; i++)
+		vnic->fw_rss_cos_lb_ctx[i] = INVALID_HW_RING_ID;
+}

@@ -22,6 +22,11 @@ struct bnge_l2_filter;
 #define BNGE_MAX_MC_ADDRS	16
 #define BNGE_MAX_UC_ADDRS	4
 
+#define BNGE_VNIC_ID_INVALID	0xffffffff
+
+struct ethtool_rxfh_context;
+struct ethtool_rxfh_param;
+
 enum {
 	BNGE_VNIC_DEFAULT	= 0,
 	BNGE_VNIC_NTUPLE	= 1

@@ -31,7 +36,8 @@ enum {
 	BNGE_VNIC_RSS_FLAG	= BIT(0),
 	BNGE_VNIC_MCAST_FLAG	= BIT(1),
 	BNGE_VNIC_UCAST_FLAG	= BIT(2),
-	BNGE_VNIC_NTUPLE_FLAG	= BIT(3)
+	BNGE_VNIC_NTUPLE_FLAG	= BIT(3),
+	BNGE_VNIC_RSSCTX_FLAG	= BIT(4)
 };
 
 struct bnge_vnic_info {

@@ -56,6 +62,8 @@ struct bnge_vnic_info {
 
 	u32		flags;
 	u32		vnic_id;
+
+	struct ethtool_rxfh_context	*rss_ctx;
 };
 
 struct bnge_rss_ctx {

@@ -67,7 +75,8 @@ void bnge_fill_hw_rss_tbl(struct bnge_net *bn, struct bnge_vnic_info *vnic);
 int bnge_hwrm_vnic_rss_cfg(struct bnge_net *bn,
 			   struct bnge_vnic_info *vnic);
 int bnge_setup_vnic(struct bnge_net *bn, struct bnge_vnic_info *vnic);
-void bnge_set_dflt_rss_indir_tbl(struct bnge_dev *bd);
+void bnge_set_dflt_rss_indir_tbl(struct bnge_dev *bd,
+				 struct ethtool_rxfh_context *ctx);
 int bnge_alloc_rfs_vnic(struct bnge_net *bn);
 int bnge_alloc_vnic_rss_table(struct bnge_net *bn,
 			      struct bnge_vnic_info *vnic);

@@ -79,4 +88,5 @@ void bnge_del_one_rss_ctx(struct bnge_net *bn, struct bnge_rss_ctx *rss_ctx,
 			  bool all);
 void bnge_hwrm_realloc_rss_ctx_vnic(struct bnge_net *bn);
 void bnge_clear_rss_ctxs(struct bnge_net *bn);
+void bnge_init_vnic_mem(struct bnge_vnic_info *vnic);
 #endif /* _BNGE_VNIC_H_ */