nfp: add control vNIC datapath

Since control vNICs don't have a netdev, they can't use napi and
queuing stack provides.  Add simple tasklet-based data receive
and send of control messages with queuing on a skb_list.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 345 insertions, 9 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index 13efdefffa1a..f6091ad0a9a9 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -38,6 +38,7 @@ struct bpf_prog;
 struct net_device;
 struct pci_dev;
 struct tc_to_netdev;
+struct sk_buff;
 struct nfp_app;
 struct nfp_cpp;
 struct nfp_pf;
@@ -55,6 +56,7 @@ extern const struct nfp_app_type app_bpf;
  * struct nfp_app_type - application definition
  * @id:		application ID
  * @name:	application name
+ * @ctrl_has_meta:  control messages have prepend of type:5/port:CTRL
  *
  * Callbacks
  * @init:	perform basic app checks
@@ -69,6 +71,8 @@ struct nfp_app_type {
 	enum nfp_app_id id;
 	const char *name;
 
+	bool ctrl_has_meta;
+
 	int (*init)(struct nfp_app *app);
 
 	const char *(*extra_cap)(struct nfp_app *app, struct nfp_net *nn);
@@ -99,6 +103,8 @@ struct nfp_app {
 	const struct nfp_app_type *type;
 };
 
+bool nfp_ctrl_tx(struct nfp_net *nn, struct sk_buff *skb);
+
 static inline int nfp_app_init(struct nfp_app *app)
 {
 	if (!app->type->init)
@@ -125,6 +131,11 @@ static inline const char *nfp_app_name(struct nfp_app *app)
 	return app->type->name;
 }
 
+static inline bool nfp_app_ctrl_has_meta(struct nfp_app *app)
+{
+	return app->type->ctrl_has_meta;
+}
+
 static inline const char *nfp_app_extra_cap(struct nfp_app *app,
 					    struct nfp_net *nn)
 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 6b21c4d0ccfa..eb849d26f4dd 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -405,7 +405,14 @@ struct nfp_net_rx_ring {
  */
 struct nfp_net_r_vector {
 	struct nfp_net *nfp_net;
-	struct napi_struct napi;
+	union {
+		struct napi_struct napi;
+		struct {
+			struct tasklet_struct tasklet;
+			struct sk_buff_head queue;
+			struct spinlock lock;
+		};
+	};
 
 	struct nfp_net_tx_ring *tx_ring;
 	struct nfp_net_rx_ring *rx_ring;
@@ -816,6 +823,11 @@ static inline bool nfp_net_running(struct nfp_net *nn)
 	return nn->dp.ctrl & NFP_NET_CFG_CTRL_ENABLE;
 }
 
+static inline const char *nfp_net_name(struct nfp_net *nn)
+{
+	return nn->dp.netdev ? nn->dp.netdev->name : "ctrl";
+}
+
 /* Globals */
 extern const char nfp_driver_version[];
 
@@ -838,6 +850,9 @@ void nfp_net_free(struct nfp_net *nn);
 int nfp_net_init(struct nfp_net *nn);
 void nfp_net_clean(struct nfp_net *nn);
 
+int nfp_ctrl_open(struct nfp_net *nn);
+void nfp_ctrl_close(struct nfp_net *nn);
+
 void nfp_net_set_ethtool_ops(struct net_device *netdev);
 void nfp_net_info(struct nfp_net *nn);
 int nfp_net_reconfig(struct nfp_net *nn, u32 update);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index c47705861a81..59f1764242a0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -392,6 +392,15 @@ static irqreturn_t nfp_net_irq_rxtx(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t nfp_ctrl_irq_rxtx(int irq, void *data)
+{
+	struct nfp_net_r_vector *r_vec = data;
+
+	tasklet_schedule(&r_vec->tasklet);
+
+	return IRQ_HANDLED;
+}
+
 /**
  * nfp_net_read_link_status() - Reread link status from control BAR
  * @nn:       NFP Network structure
@@ -523,7 +532,7 @@ nfp_net_aux_irq_request(struct nfp_net *nn, u32 ctrl_offset,
 
 	entry = &nn->irq_entries[vector_idx];
 
-	snprintf(name, name_sz, format, netdev_name(nn->dp.netdev));
+	snprintf(name, name_sz, format, nfp_net_name(nn));
 	err = request_irq(entry->vector, handler, 0, name, nn);
 	if (err) {
 		nn_err(nn, "Failed to request IRQ %d (err=%d).\n",
@@ -943,6 +952,9 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 	r_vec->tx_pkts += done_pkts;
 	u64_stats_update_end(&r_vec->tx_sync);
 
+	if (!dp->netdev)
+		return;
+
 	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
 	netdev_tx_completed_queue(nd_q, done_pkts, done_bytes);
 	if (nfp_net_tx_ring_should_wake(tx_ring)) {
@@ -1052,7 +1064,7 @@ nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 	tx_ring->qcp_rd_p = 0;
 	tx_ring->wr_ptr_add = 0;
 
-	if (tx_ring->is_xdp)
+	if (tx_ring->is_xdp || !dp->netdev)
 		return;
 
 	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
@@ -1742,6 +1754,231 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
 	return pkts_polled;
 }
 
+/* Control device data path
+ */
+
+static bool
+nfp_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+		struct sk_buff *skb, bool old)
+{
+	unsigned int real_len = skb->len, meta_len = 0;
+	struct nfp_net_tx_ring *tx_ring;
+	struct nfp_net_tx_buf *txbuf;
+	struct nfp_net_tx_desc *txd;
+	struct nfp_net_dp *dp;
+	dma_addr_t dma_addr;
+	int wr_idx;
+
+	dp = &r_vec->nfp_net->dp;
+	tx_ring = r_vec->tx_ring;
+
+	if (WARN_ON_ONCE(skb_shinfo(skb)->nr_frags)) {
+		nn_dp_warn(dp, "Driver's CTRL TX does not implement gather\n");
+		goto err_free;
+	}
+
+	if (unlikely(nfp_net_tx_full(tx_ring, 1))) {
+		u64_stats_update_begin(&r_vec->tx_sync);
+		r_vec->tx_busy++;
+		u64_stats_update_end(&r_vec->tx_sync);
+		if (!old)
+			__skb_queue_tail(&r_vec->queue, skb);
+		else
+			__skb_queue_head(&r_vec->queue, skb);
+		return true;
+	}
+
+	if (nfp_app_ctrl_has_meta(nn->app)) {
+		if (unlikely(skb_headroom(skb) < 8)) {
+			nn_dp_warn(dp, "CTRL TX on skb without headroom\n");
+			goto err_free;
+		}
+		meta_len = 8;
+		put_unaligned_be32(NFP_META_PORT_ID_CTRL, skb_push(skb, 4));
+		put_unaligned_be32(NFP_NET_META_PORTID, skb_push(skb, 4));
+	}
+
+	/* Start with the head skbuf */
+	dma_addr = dma_map_single(dp->dev, skb->data, skb_headlen(skb),
+				  DMA_TO_DEVICE);
+	if (dma_mapping_error(dp->dev, dma_addr))
+		goto err_dma_warn;
+
+	wr_idx = D_IDX(tx_ring, tx_ring->wr_p);
+
+	/* Stash the soft descriptor of the head then initialize it */
+	txbuf = &tx_ring->txbufs[wr_idx];
+	txbuf->skb = skb;
+	txbuf->dma_addr = dma_addr;
+	txbuf->fidx = -1;
+	txbuf->pkt_cnt = 1;
+	txbuf->real_len = real_len;
+
+	/* Build TX descriptor */
+	txd = &tx_ring->txds[wr_idx];
+	txd->offset_eop = meta_len | PCIE_DESC_TX_EOP;
+	txd->dma_len = cpu_to_le16(skb_headlen(skb));
+	nfp_desc_set_dma_addr(txd, dma_addr);
+	txd->data_len = cpu_to_le16(skb->len);
+
+	txd->flags = 0;
+	txd->mss = 0;
+	txd->lso_hdrlen = 0;
+
+	tx_ring->wr_p++;
+	tx_ring->wr_ptr_add++;
+	nfp_net_tx_xmit_more_flush(tx_ring);
+
+	return false;
+
+err_dma_warn:
+	nn_dp_warn(dp, "Failed to DMA map TX CTRL buffer\n");
+err_free:
+	u64_stats_update_begin(&r_vec->tx_sync);
+	r_vec->tx_errors++;
+	u64_stats_update_end(&r_vec->tx_sync);
+	dev_kfree_skb_any(skb);
+	return false;
+}
+
+bool nfp_ctrl_tx(struct nfp_net *nn, struct sk_buff *skb)
+{
+	struct nfp_net_r_vector *r_vec = &nn->r_vecs[0];
+	bool ret;
+
+	spin_lock_bh(&r_vec->lock);
+	ret = nfp_ctrl_tx_one(nn, r_vec, skb, false);
+	spin_unlock_bh(&r_vec->lock);
+
+	return ret;
+}
+
+static void __nfp_ctrl_tx_queued(struct nfp_net_r_vector *r_vec)
+{
+	struct sk_buff *skb;
+
+	while ((skb = __skb_dequeue(&r_vec->queue)))
+		if (nfp_ctrl_tx_one(r_vec->nfp_net, r_vec, skb, true))
+			return;
+}
+
+static bool
+nfp_ctrl_meta_ok(struct nfp_net *nn, void *data, unsigned int meta_len)
+{
+	u32 meta_type, meta_tag;
+
+	if (!nfp_app_ctrl_has_meta(nn->app))
+		return !meta_len;
+
+	if (meta_len != 8)
+		return false;
+
+	meta_type = get_unaligned_be32(data);
+	meta_tag = get_unaligned_be32(data + 4);
+
+	return (meta_type == NFP_NET_META_PORTID &&
+		meta_tag == NFP_META_PORT_ID_CTRL);
+}
+
+static bool
+nfp_ctrl_rx_one(struct nfp_net *nn, struct nfp_net_dp *dp,
+		struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring)
+{
+	unsigned int meta_len, data_len, meta_off, pkt_len, pkt_off;
+	struct nfp_net_rx_buf *rxbuf;
+	struct nfp_net_rx_desc *rxd;
+	dma_addr_t new_dma_addr;
+	struct sk_buff *skb;
+	void *new_frag;
+	int idx;
+
+	idx = D_IDX(rx_ring, rx_ring->rd_p);
+
+	rxd = &rx_ring->rxds[idx];
+	if (!(rxd->rxd.meta_len_dd & PCIE_DESC_RX_DD))
+		return false;
+
+	/* Memory barrier to ensure that we won't do other reads
+	 * before the DD bit.
+	 */
+	dma_rmb();
+
+	rx_ring->rd_p++;
+
+	rxbuf =	&rx_ring->rxbufs[idx];
+	meta_len = rxd->rxd.meta_len_dd & PCIE_DESC_RX_META_LEN_MASK;
+	data_len = le16_to_cpu(rxd->rxd.data_len);
+	pkt_len = data_len - meta_len;
+
+	pkt_off = NFP_NET_RX_BUF_HEADROOM + dp->rx_dma_off;
+	if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
+		pkt_off += meta_len;
+	else
+		pkt_off += dp->rx_offset;
+	meta_off = pkt_off - meta_len;
+
+	/* Stats update */
+	u64_stats_update_begin(&r_vec->rx_sync);
+	r_vec->rx_pkts++;
+	r_vec->rx_bytes += pkt_len;
+	u64_stats_update_end(&r_vec->rx_sync);
+
+	nfp_net_dma_sync_cpu_rx(dp, rxbuf->dma_addr + meta_off,	data_len);
+
+	if (unlikely(!nfp_ctrl_meta_ok(nn, rxbuf->frag + meta_off, meta_len))) {
+		nn_dp_warn(dp, "incorrect metadata for ctrl packet (%d)\n",
+			   meta_len);
+		nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
+		return true;
+	}
+
+	skb = build_skb(rxbuf->frag, dp->fl_bufsz);
+	if (unlikely(!skb)) {
+		nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
+		return true;
+	}
+	new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr);
+	if (unlikely(!new_frag)) {
+		nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, skb);
+		return true;
+	}
+
+	nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr);
+
+	nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr);
+
+	skb_reserve(skb, pkt_off);
+	skb_put(skb, pkt_len);
+
+	dev_kfree_skb_any(skb);
+
+	return true;
+}
+
+static void nfp_ctrl_rx(struct nfp_net_r_vector *r_vec)
+{
+	struct nfp_net_rx_ring *rx_ring = r_vec->rx_ring;
+	struct nfp_net *nn = r_vec->nfp_net;
+	struct nfp_net_dp *dp = &nn->dp;
+
+	while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring))
+		continue;
+}
+
+static void nfp_ctrl_poll(unsigned long arg)
+{
+	struct nfp_net_r_vector *r_vec = (void *)arg;
+
+	spin_lock_bh(&r_vec->lock);
+	nfp_net_tx_complete(r_vec->tx_ring);
+	__nfp_ctrl_tx_queued(r_vec);
+	spin_unlock_bh(&r_vec->lock);
+
+	nfp_ctrl_rx(r_vec);
+
+	nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
+}
+
 /* Setup and Configuration
  */
 
@@ -1764,10 +2001,21 @@ static void nfp_net_vecs_init(struct nfp_net *nn)
 
 		r_vec = &nn->r_vecs[r];
 		r_vec->nfp_net = nn;
-		r_vec->handler = nfp_net_irq_rxtx;
 		r_vec->irq_entry = entry->entry;
 		r_vec->irq_vector = entry->vector;
 
+		if (nn->dp.netdev) {
+			r_vec->handler = nfp_net_irq_rxtx;
+		} else {
+			r_vec->handler = nfp_ctrl_irq_rxtx;
+
+			__skb_queue_head_init(&r_vec->queue);
+			spin_lock_init(&r_vec->lock);
+			tasklet_init(&r_vec->tasklet, nfp_ctrl_poll,
+				     (unsigned long)r_vec);
+			tasklet_disable(&r_vec->tasklet);
+		}
+
 		cpumask_set_cpu(r, &r_vec->affinity_mask);
 	}
 }
@@ -2034,15 +2282,22 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	int err;
 
 	/* Setup NAPI */
-	netif_napi_add(nn->dp.netdev, &r_vec->napi,
-		       nfp_net_poll, NAPI_POLL_WEIGHT);
+	if (nn->dp.netdev)
+		netif_napi_add(nn->dp.netdev, &r_vec->napi,
+			       nfp_net_poll, NAPI_POLL_WEIGHT);
+	else
+		tasklet_enable(&r_vec->tasklet);
 
 	snprintf(r_vec->name, sizeof(r_vec->name),
-		 "%s-rxtx-%d", nn->dp.netdev->name, idx);
+		 "%s-rxtx-%d", nfp_net_name(nn), idx);
 	err = request_irq(r_vec->irq_vector, r_vec->handler, 0, r_vec->name,
 			  r_vec);
 	if (err) {
-		netif_napi_del(&r_vec->napi);
+		if (nn->dp.netdev)
+			netif_napi_del(&r_vec->napi);
+		else
+			tasklet_disable(&r_vec->tasklet);
+
 		nn_err(nn, "Error requesting IRQ %d\n", r_vec->irq_vector);
 		return err;
 	}
@@ -2060,7 +2315,11 @@ static void
 nfp_net_cleanup_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec)
 {
 	irq_set_affinity_hint(r_vec->irq_vector, NULL);
-	netif_napi_del(&r_vec->napi);
+	if (nn->dp.netdev)
+		netif_napi_del(&r_vec->napi);
+	else
+		tasklet_disable(&r_vec->tasklet);
+
 	free_irq(r_vec->irq_vector, r_vec);
 }
 
@@ -2338,6 +2597,24 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 	return 0;
 }
 
+void nfp_ctrl_close(struct nfp_net *nn)
+{
+	int r;
+
+	rtnl_lock();
+
+	for (r = 0; r < nn->dp.num_r_vecs; r++) {
+		disable_irq(nn->r_vecs[r].irq_vector);
+		tasklet_disable(&nn->r_vecs[r].tasklet);
+	}
+
+	nfp_net_clear_config_and_disable(nn);
+
+	nfp_net_close_free_all(nn);
+
+	rtnl_unlock();
+}
+
 /**
  * nfp_net_open_stack() - Start the device from stack's perspective
  * @nn:      NFP Net device to reconfigure
@@ -2453,6 +2730,35 @@ err_free_all:
 	return err;
 }
 
+int nfp_ctrl_open(struct nfp_net *nn)
+{
+	int err, r;
+
+	/* ring dumping depends on vNICs being opened/closed under rtnl */
+	rtnl_lock();
+
+	err = nfp_net_open_alloc_all(nn);
+	if (err)
+		goto err_unlock;
+
+	err = nfp_net_set_config_and_enable(nn);
+	if (err)
+		goto err_free_all;
+
+	for (r = 0; r < nn->dp.num_r_vecs; r++)
+		enable_irq(nn->r_vecs[r].irq_vector);
+
+	rtnl_unlock();
+
+	return 0;
+
+err_free_all:
+	nfp_net_close_free_all(nn);
+err_unlock:
+	rtnl_unlock();
+	return err;
+}
+
 static void nfp_net_set_rx_mode(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
@@ -3278,6 +3584,7 @@ int nfp_net_init(struct nfp_net *nn)
 
 	/* Chained metadata is signalled by capabilities except in version 4 */
 	nn->dp.chained_metadata_format = nn->fw_ver.major == 4 ||
+					 !nn->dp.netdev ||
 					 nn->cap & NFP_NET_CFG_CTRL_CHAIN_META;
 	if (nn->dp.chained_metadata_format && nn->fw_ver.major != 4)
 		nn->cap &= ~NFP_NET_CFG_CTRL_RSS;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index c8208bf370e0..48a8bf97645e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -71,8 +71,11 @@
 #define NFP_NET_META_FIELD_SIZE		4
 #define NFP_NET_META_HASH		1 /* next field carries hash type */
 #define NFP_NET_META_MARK		2
+#define NFP_NET_META_PORTID		5
 #define NFP_NET_META_CSUM		6 /* checksum complete type */
 
+#define	NFP_META_PORT_ID_CTRL		~0U
+
 /**
  * Hash type pre-pended when a RSS hash was computed
  */