1 files changed, 173 insertions, 30 deletions

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 9259a74eca40..6120f2b6684f 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -12,7 +12,20 @@
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
 
-#include "mana.h"
+#include <net/mana/mana.h>
+#include <net/mana/mana_auxiliary.h>
+
+static DEFINE_IDA(mana_adev_ida);
+
+static int mana_adev_idx_alloc(void)
+{
+	return ida_alloc(&mana_adev_ida, GFP_KERNEL);
+}
+
+static void mana_adev_idx_free(int idx)
+{
+	ida_free(&mana_adev_ida, idx);
+}
 
 /* Microsoft Azure Network Adapter (MANA) functions */
 
@@ -128,7 +141,7 @@ frag_err:
 	return -ENOMEM;
 }
 
-int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	enum mana_tx_pkt_format pkt_fmt = MANA_SHORT_PKT_FMT;
 	struct mana_port_context *apc = netdev_priv(ndev);
@@ -176,7 +189,7 @@ int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	pkg.wqe_req.client_data_unit = 0;
 
 	pkg.wqe_req.num_sge = 1 + skb_shinfo(skb)->nr_frags;
-	WARN_ON_ONCE(pkg.wqe_req.num_sge > 30);
+	WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES);
 
 	if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) {
 		pkg.wqe_req.sgl = pkg.sgl_array;
@@ -315,10 +328,10 @@ static void mana_get_stats64(struct net_device *ndev,
 		rx_stats = &apc->rxqs[q]->stats;
 
 		do {
-			start = u64_stats_fetch_begin_irq(&rx_stats->syncp);
+			start = u64_stats_fetch_begin(&rx_stats->syncp);
 			packets = rx_stats->packets;
 			bytes = rx_stats->bytes;
-		} while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start));
+		} while (u64_stats_fetch_retry(&rx_stats->syncp, start));
 
 		st->rx_packets += packets;
 		st->rx_bytes += bytes;
@@ -328,10 +341,10 @@ static void mana_get_stats64(struct net_device *ndev,
 		tx_stats = &apc->tx_qp[q].txq.stats;
 
 		do {
-			start = u64_stats_fetch_begin_irq(&tx_stats->syncp);
+			start = u64_stats_fetch_begin(&tx_stats->syncp);
 			packets = tx_stats->packets;
 			bytes = tx_stats->bytes;
-		} while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start));
+		} while (u64_stats_fetch_retry(&tx_stats->syncp, start));
 
 		st->tx_packets += packets;
 		st->tx_bytes += bytes;
@@ -633,13 +646,48 @@ static int mana_query_vport_cfg(struct mana_port_context *apc, u32 vport_index,
 	return 0;
 }
 
-static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
-			  u32 doorbell_pg_id)
+void mana_uncfg_vport(struct mana_port_context *apc)
+{
+	mutex_lock(&apc->vport_mutex);
+	apc->vport_use_count--;
+	WARN_ON(apc->vport_use_count < 0);
+	mutex_unlock(&apc->vport_mutex);
+}
+EXPORT_SYMBOL_NS(mana_uncfg_vport, NET_MANA);
+
+int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
+		   u32 doorbell_pg_id)
 {
 	struct mana_config_vport_resp resp = {};
 	struct mana_config_vport_req req = {};
 	int err;
 
+	/* This function is used to program the Ethernet port in the hardware
+	 * table. It can be called from the Ethernet driver or the RDMA driver.
+	 *
+	 * For Ethernet usage, the hardware supports only one active user on a
+	 * physical port. The driver checks on the port usage before programming
+	 * the hardware when creating the RAW QP (RDMA driver) or exposing the
+	 * device to kernel NET layer (Ethernet driver).
+	 *
+	 * Because the RDMA driver doesn't know in advance which QP type the
+	 * user will create, it exposes the device with all its ports. The user
+	 * may not be able to create RAW QP on a port if this port is already
+	 * in used by the Ethernet driver from the kernel.
+	 *
+	 * This physical port limitation only applies to the RAW QP. For RC QP,
+	 * the hardware doesn't have this limitation. The user can create RC
+	 * QPs on a physical port up to the hardware limits independent of the
+	 * Ethernet usage on the same port.
+	 */
+	mutex_lock(&apc->vport_mutex);
+	if (apc->vport_use_count > 0) {
+		mutex_unlock(&apc->vport_mutex);
+		return -EBUSY;
+	}
+	apc->vport_use_count++;
+	mutex_unlock(&apc->vport_mutex);
+
 	mana_gd_init_req_hdr(&req.hdr, MANA_CONFIG_VPORT_TX,
 			     sizeof(req), sizeof(resp));
 	req.vport = apc->port_handle;
@@ -666,9 +714,16 @@ static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
 
 	apc->tx_shortform_allowed = resp.short_form_allowed;
 	apc->tx_vp_offset = resp.tx_vport_offset;
+
+	netdev_info(apc->ndev, "Configured vPort %llu PD %u DB %u\n",
+		    apc->port_handle, protection_dom_id, doorbell_pg_id);
 out:
+	if (err)
+		mana_uncfg_vport(apc);
+
 	return err;
 }
+EXPORT_SYMBOL_NS(mana_cfg_vport, NET_MANA);
 
 static int mana_cfg_vport_steering(struct mana_port_context *apc,
 				   enum TRI_STATE rx,
@@ -729,16 +784,19 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 			   resp.hdr.status);
 		err = -EPROTO;
 	}
+
+	netdev_info(ndev, "Configured steering vPort %llu entries %u\n",
+		    apc->port_handle, num_entries);
 out:
 	kfree(req);
 	return err;
 }
 
-static int mana_create_wq_obj(struct mana_port_context *apc,
-			      mana_handle_t vport,
-			      u32 wq_type, struct mana_obj_spec *wq_spec,
-			      struct mana_obj_spec *cq_spec,
-			      mana_handle_t *wq_obj)
+int mana_create_wq_obj(struct mana_port_context *apc,
+		       mana_handle_t vport,
+		       u32 wq_type, struct mana_obj_spec *wq_spec,
+		       struct mana_obj_spec *cq_spec,
+		       mana_handle_t *wq_obj)
 {
 	struct mana_create_wqobj_resp resp = {};
 	struct mana_create_wqobj_req req = {};
@@ -787,9 +845,10 @@ static int mana_create_wq_obj(struct mana_port_context *apc,
 out:
 	return err;
 }
+EXPORT_SYMBOL_NS(mana_create_wq_obj, NET_MANA);
 
-static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
-				mana_handle_t wq_obj)
+void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
+			 mana_handle_t wq_obj)
 {
 	struct mana_destroy_wqobj_resp resp = {};
 	struct mana_destroy_wqobj_req req = {};
@@ -814,6 +873,7 @@ static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
 		netdev_err(ndev, "Failed to destroy WQ object: %d, 0x%x\n", err,
 			   resp.hdr.status);
 }
+EXPORT_SYMBOL_NS(mana_destroy_wq_obj, NET_MANA);
 
 static void mana_destroy_eq(struct mana_context *ac)
 {
@@ -1303,10 +1363,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
 		xdp_do_flush();
 }
 
-static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
+static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
 {
 	struct mana_cq *cq = context;
 	u8 arm_bit;
+	int w;
 
 	WARN_ON_ONCE(cq->gdma_cq != gdma_queue);
 
@@ -1315,26 +1376,31 @@ static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
 	else
 		mana_poll_tx_cq(cq);
 
-	if (cq->work_done < cq->budget &&
-	    napi_complete_done(&cq->napi, cq->work_done)) {
+	w = cq->work_done;
+
+	if (w < cq->budget &&
+	    napi_complete_done(&cq->napi, w)) {
 		arm_bit = SET_ARM_BIT;
 	} else {
 		arm_bit = 0;
 	}
 
 	mana_gd_ring_cq(gdma_queue, arm_bit);
+
+	return w;
 }
 
 static int mana_poll(struct napi_struct *napi, int budget)
 {
 	struct mana_cq *cq = container_of(napi, struct mana_cq, napi);
+	int w;
 
 	cq->work_done = 0;
 	cq->budget = budget;
 
-	mana_cq_handler(cq, cq->gdma_cq);
+	w = mana_cq_handler(cq, cq->gdma_cq);
 
-	return min(cq->work_done, budget);
+	return min(w, budget);
 }
 
 static void mana_schedule_napi(void *context, struct gdma_queue *gdma_queue)
@@ -1463,10 +1529,10 @@ static int mana_create_txq(struct mana_port_context *apc,
 		memset(&wq_spec, 0, sizeof(wq_spec));
 		memset(&cq_spec, 0, sizeof(cq_spec));
 
-		wq_spec.gdma_region = txq->gdma_sq->mem_info.gdma_region;
+		wq_spec.gdma_region = txq->gdma_sq->mem_info.dma_region_handle;
 		wq_spec.queue_size = txq->gdma_sq->queue_size;
 
-		cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region;
+		cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle;
 		cq_spec.queue_size = cq->gdma_cq->queue_size;
 		cq_spec.modr_ctx_id = 0;
 		cq_spec.attached_eq = cq->gdma_cq->cq.parent->id;
@@ -1481,8 +1547,10 @@ static int mana_create_txq(struct mana_port_context *apc,
 		txq->gdma_sq->id = wq_spec.queue_index;
 		cq->gdma_cq->id = cq_spec.queue_index;
 
-		txq->gdma_sq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION;
-		cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION;
+		txq->gdma_sq->mem_info.dma_region_handle =
+			GDMA_INVALID_DMA_REGION;
+		cq->gdma_cq->mem_info.dma_region_handle =
+			GDMA_INVALID_DMA_REGION;
 
 		txq->gdma_txq_id = txq->gdma_sq->id;
 
@@ -1693,10 +1761,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	memset(&wq_spec, 0, sizeof(wq_spec));
 	memset(&cq_spec, 0, sizeof(cq_spec));
-	wq_spec.gdma_region = rxq->gdma_rq->mem_info.gdma_region;
+	wq_spec.gdma_region = rxq->gdma_rq->mem_info.dma_region_handle;
 	wq_spec.queue_size = rxq->gdma_rq->queue_size;
 
-	cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region;
+	cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle;
 	cq_spec.queue_size = cq->gdma_cq->queue_size;
 	cq_spec.modr_ctx_id = 0;
 	cq_spec.attached_eq = cq->gdma_cq->cq.parent->id;
@@ -1709,8 +1777,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 	rxq->gdma_rq->id = wq_spec.queue_index;
 	cq->gdma_cq->id = cq_spec.queue_index;
 
-	rxq->gdma_rq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION;
-	cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION;
+	rxq->gdma_rq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION;
+	cq->gdma_cq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION;
 
 	rxq->gdma_id = rxq->gdma_rq->id;
 	cq->gdma_id = cq->gdma_cq->id;
@@ -1791,6 +1859,7 @@ static void mana_destroy_vport(struct mana_port_context *apc)
 	}
 
 	mana_destroy_txq(apc);
+	mana_uncfg_vport(apc);
 
 	if (gd->gdma_context->is_pf)
 		mana_pf_deregister_hw_vport(apc);
@@ -2063,12 +2132,16 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	apc->pf_filter_handle = INVALID_MANA_HANDLE;
 	apc->port_idx = port_idx;
 
+	mutex_init(&apc->vport_mutex);
+	apc->vport_use_count = 0;
+
 	ndev->netdev_ops = &mana_devops;
 	ndev->ethtool_ops = &mana_ethtool_ops;
 	ndev->mtu = ETH_DATA_LEN;
 	ndev->max_mtu = ndev->mtu;
 	ndev->min_mtu = ndev->mtu;
 	ndev->needed_headroom = MANA_HEADROOM;
+	ndev->dev_port = port_idx;
 	SET_NETDEV_DEV(ndev, gc->dev);
 
 	netif_carrier_off(ndev);
@@ -2087,6 +2160,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	ndev->hw_features |= NETIF_F_RXHASH;
 	ndev->features = ndev->hw_features;
 	ndev->vlan_features = 0;
+	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			     NETDEV_XDP_ACT_NDO_XMIT;
 
 	err = register_netdev(ndev);
 	if (err) {
@@ -2106,6 +2181,69 @@ free_net:
 	return err;
 }
 
+static void adev_release(struct device *dev)
+{
+	struct mana_adev *madev = container_of(dev, struct mana_adev, adev.dev);
+
+	kfree(madev);
+}
+
+static void remove_adev(struct gdma_dev *gd)
+{
+	struct auxiliary_device *adev = gd->adev;
+	int id = adev->id;
+
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
+
+	mana_adev_idx_free(id);
+	gd->adev = NULL;
+}
+
+static int add_adev(struct gdma_dev *gd)
+{
+	struct auxiliary_device *adev;
+	struct mana_adev *madev;
+	int ret;
+
+	madev = kzalloc(sizeof(*madev), GFP_KERNEL);
+	if (!madev)
+		return -ENOMEM;
+
+	adev = &madev->adev;
+	ret = mana_adev_idx_alloc();
+	if (ret < 0)
+		goto idx_fail;
+	adev->id = ret;
+
+	adev->name = "rdma";
+	adev->dev.parent = gd->gdma_context->dev;
+	adev->dev.release = adev_release;
+	madev->mdev = gd;
+
+	ret = auxiliary_device_init(adev);
+	if (ret)
+		goto init_fail;
+
+	ret = auxiliary_device_add(adev);
+	if (ret)
+		goto add_fail;
+
+	gd->adev = adev;
+	return 0;
+
+add_fail:
+	auxiliary_device_uninit(adev);
+
+init_fail:
+	mana_adev_idx_free(adev->id);
+
+idx_fail:
+	kfree(madev);
+
+	return ret;
+}
+
 int mana_probe(struct gdma_dev *gd, bool resuming)
 {
 	struct gdma_context *gc = gd->gdma_context;
@@ -2173,6 +2311,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 				break;
 		}
 	}
+
+	err = add_adev(gd);
 out:
 	if (err)
 		mana_remove(gd, false);
@@ -2189,6 +2329,10 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
 	int err;
 	int i;
 
+	/* adev currently doesn't support suspending, always remove it */
+	if (gd->adev)
+		remove_adev(gd);
+
 	for (i = 0; i < ac->num_ports; i++) {
 		ndev = ac->ports[i];
 		if (!ndev) {
@@ -2221,7 +2365,6 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
 	}
 
 	mana_destroy_eq(ac);
-
 out:
 	mana_gd_deregister_device(gd);