[SIG-CLOUD-9] LE-3893 LE-3903 LE-3907

drivers/infiniband/hw/mana/device.c

@@ -52,6 +52,38 @@ static const struct ib_device_ops mana_ib_dev_ops = {
 			   ib_ind_table),
 };
 
+static int mana_ib_netdev_event(struct notifier_block *this,
+				unsigned long event, void *ptr)
+{
+	struct mana_ib_dev *dev = container_of(this, struct mana_ib_dev, nb);
+	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+	struct gdma_context *gc = dev->gdma_dev->gdma_context;
+	struct mana_context *mc = gc->mana.driver_data;
+	struct net_device *ndev;
+
+	/* Only process events from our parent device */
+	if (event_dev != mc->ports[0])
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_CHANGEUPPER:
+		ndev = mana_get_primary_netdev(mc, 0, &dev->dev_tracker);
+		/*
+		 * RDMA core will setup GID based on updated netdev.
+		 * It's not possible to race with the core as rtnl lock is being
+		 * held.
+		 */
+		ib_device_set_netdev(&dev->ib_dev, ndev, 1);
+
+		/* mana_get_primary_netdev() returns ndev with refcount held */
+		netdev_put(ndev, &dev->dev_tracker);
+
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
 static int mana_ib_probe(struct auxiliary_device *adev,
 			 const struct auxiliary_device_id *id)
 {
@@ -85,18 +117,17 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 	dev->ib_dev.num_comp_vectors = mdev->gdma_context->max_num_queues;
 	dev->ib_dev.dev.parent = mdev->gdma_context->dev;
 
-	rcu_read_lock(); /* required to get primary netdev */
-	ndev = mana_get_primary_netdev_rcu(mc, 0);
+	ndev = mana_get_primary_netdev(mc, 0, &dev->dev_tracker);
 	if (!ndev) {
-		rcu_read_unlock();
 		ret = -ENODEV;
 		ibdev_err(&dev->ib_dev, "Failed to get netdev for IB port 1");
 		goto free_ib_device;
 	}
 	ether_addr_copy(mac_addr, ndev->dev_addr);
 	addrconf_addr_eui48((u8 *)&dev->ib_dev.node_guid, ndev->dev_addr);
 	ret = ib_device_set_netdev(&dev->ib_dev, ndev, 1);
-	rcu_read_unlock();
+	/* mana_get_primary_netdev() returns ndev with refcount held */
+	netdev_put(ndev, &dev->dev_tracker);
 	if (ret) {
 		ibdev_err(&dev->ib_dev, "Failed to set ib netdev, ret %d", ret);
 		goto free_ib_device;
@@ -110,17 +141,25 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 	}
 	dev->gdma_dev = &mdev->gdma_context->mana_ib;
 
+	dev->nb.notifier_call = mana_ib_netdev_event;
+	ret = register_netdevice_notifier(&dev->nb);
+	if (ret) {
+		ibdev_err(&dev->ib_dev, "Failed to register net notifier, %d",
+			  ret);
+		goto deregister_device;
+	}
+
 	ret = mana_ib_gd_query_adapter_caps(dev);
 	if (ret) {
 		ibdev_err(&dev->ib_dev, "Failed to query device caps, ret %d",
 			  ret);
-		goto deregister_device;
+		goto deregister_net_notifier;
 	}
 
 	ret = mana_ib_create_eqs(dev);
 	if (ret) {
 		ibdev_err(&dev->ib_dev, "Failed to create EQs, ret %d", ret);
-		goto deregister_device;
+		goto deregister_net_notifier;
 	}
 
 	ret = mana_ib_gd_create_rnic_adapter(dev);
@@ -149,6 +188,8 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 	mana_ib_gd_destroy_rnic_adapter(dev);
 destroy_eqs:
 	mana_ib_destroy_eqs(dev);
+deregister_net_notifier:
+	unregister_netdevice_notifier(&dev->nb);
 deregister_device:
 	mana_gd_deregister_device(dev->gdma_dev);
 free_ib_device:
@@ -164,6 +205,7 @@ static void mana_ib_remove(struct auxiliary_device *adev)
 	xa_destroy(&dev->qp_table_wq);
 	mana_ib_gd_destroy_rnic_adapter(dev);
 	mana_ib_destroy_eqs(dev);
+	unregister_netdevice_notifier(&dev->nb);
 	mana_gd_deregister_device(dev->gdma_dev);
 	ib_dealloc_device(&dev->ib_dev);
 }

drivers/infiniband/hw/mana/mana_ib.h

@@ -64,6 +64,8 @@ struct mana_ib_dev {
 	struct gdma_queue **eqs;
 	struct xarray qp_table_wq;
 	struct mana_ib_adapter_caps adapter_caps;
+	netdevice_tracker dev_tracker;
+	struct notifier_block nb;
 };
 
 struct mana_ib_wq {

drivers/net/ethernet/microsoft/mana/gdma_main.c

@@ -135,9 +135,10 @@ static int mana_gd_detect_devices(struct pci_dev *pdev)
 	struct gdma_list_devices_resp resp = {};
 	struct gdma_general_req req = {};
 	struct gdma_dev_id dev;
-	u32 i, max_num_devs;
+	int found_dev = 0;
 	u16 dev_type;
 	int err;
+	u32 i;
 
 	mana_gd_init_req_hdr(&req.hdr, GDMA_LIST_DEVICES, sizeof(req),
 			     sizeof(resp));
@@ -149,12 +150,17 @@ static int mana_gd_detect_devices(struct pci_dev *pdev)
 		return err ? err : -EPROTO;
 	}
 
-	max_num_devs = min_t(u32, MAX_NUM_GDMA_DEVICES, resp.num_of_devs);
-
-	for (i = 0; i < max_num_devs; i++) {
+	for (i = 0; i < GDMA_DEV_LIST_SIZE &&
+	     found_dev < resp.num_of_devs; i++) {
 		dev = resp.devs[i];
 		dev_type = dev.type;
 
+		/* Skip empty devices */
+		if (dev.as_uint32 == 0)
+			continue;
+
+		found_dev++;
+
 		/* HWC is already detected in mana_hwc_create_channel(). */
 		if (dev_type == GDMA_DEVICE_HWC)
 			continue;

drivers/net/ethernet/microsoft/mana/mana_en.c

@@ -655,30 +655,16 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu
 	mpc->rxbpre_total = 0;
 
 	for (i = 0; i < num_rxb; i++) {
-		if (mpc->rxbpre_alloc_size > PAGE_SIZE) {
-			va = netdev_alloc_frag(mpc->rxbpre_alloc_size);
-			if (!va)
-				goto error;
-
-			page = virt_to_head_page(va);
-			/* Check if the frag falls back to single page */
-			if (compound_order(page) <
-			    get_order(mpc->rxbpre_alloc_size)) {
-				put_page(page);
-				goto error;
-			}
-		} else {
-			page = dev_alloc_page();
-			if (!page)
-				goto error;
+		page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size));
+		if (!page)
+			goto error;
 
-			va = page_to_virt(page);
-		}
+		va = page_to_virt(page);
 
 		da = dma_map_single(dev, va + mpc->rxbpre_headroom,
 				    mpc->rxbpre_datasize, DMA_FROM_DEVICE);
 		if (dma_mapping_error(dev, da)) {
-			put_page(virt_to_head_page(va));
+			put_page(page);
 			goto error;
 		}
 
@@ -1671,7 +1657,7 @@ static void mana_rx_skb(void *buf_va, bool from_pool,
 }
 
 static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
-			     dma_addr_t *da, bool *from_pool, bool is_napi)
+			     dma_addr_t *da, bool *from_pool)
 {
 	struct page *page;
 	void *va;
@@ -1682,21 +1668,6 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
 	if (rxq->xdp_save_va) {
 		va = rxq->xdp_save_va;
 		rxq->xdp_save_va = NULL;
-	} else if (rxq->alloc_size > PAGE_SIZE) {
-		if (is_napi)
-			va = napi_alloc_frag(rxq->alloc_size);
-		else
-			va = netdev_alloc_frag(rxq->alloc_size);
-
-		if (!va)
-			return NULL;
-
-		page = virt_to_head_page(va);
-		/* Check if the frag falls back to single page */
-		if (compound_order(page) < get_order(rxq->alloc_size)) {
-			put_page(page);
-			return NULL;
-		}
 	} else {
 		page = page_pool_dev_alloc_pages(rxq->page_pool);
 		if (!page)
@@ -1729,7 +1700,7 @@ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq,
 	dma_addr_t da;
 	void *va;
 
-	va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true);
+	va = mana_get_rxfrag(rxq, dev, &da, &from_pool);
 	if (!va)
 		return;
 
@@ -2165,7 +2136,7 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key,
 	if (mpc->rxbufs_pre)
 		va = mana_get_rxbuf_pre(rxq, &da);
 	else
-		va = mana_get_rxfrag(rxq, dev, &da, &from_pool, false);
+		va = mana_get_rxfrag(rxq, dev, &da, &from_pool);
 
 	if (!va)
 		return -ENOMEM;
@@ -2251,6 +2222,7 @@ static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
 	pprm.nid = gc->numa_node;
 	pprm.napi = &rxq->rx_cq.napi;
 	pprm.netdev = rxq->ndev;
+	pprm.order = get_order(rxq->alloc_size);
 
 	rxq->page_pool = page_pool_create(&pprm);
 
@@ -3171,21 +3143,27 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
 	dev_dbg(dev, "%s succeeded\n", __func__);
 }
 
-struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index)
+struct net_device *mana_get_primary_netdev(struct mana_context *ac,
+					   u32 port_index,
+					   netdevice_tracker *tracker)
 {
 	struct net_device *ndev;
 
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
-			 "Taking primary netdev without holding the RCU read lock");
 	if (port_index >= ac->num_ports)
 		return NULL;
 
-	/* When mana is used in netvsc, the upper netdevice should be returned. */
-	if (ac->ports[port_index]->flags & IFF_SLAVE)
-		ndev = netdev_master_upper_dev_get_rcu(ac->ports[port_index]);
-	else
+	rcu_read_lock();
+
+	/* If mana is used in netvsc, the upper netdevice should be returned. */
+	ndev = netdev_master_upper_dev_get_rcu(ac->ports[port_index]);
+
+	/* If there is no upper device, use the parent Ethernet device */
+	if (!ndev)
 		ndev = ac->ports[port_index];
 
+	netdev_hold(ndev, tracker, GFP_ATOMIC);
+	rcu_read_unlock();
+
 	return ndev;
 }
-EXPORT_SYMBOL_NS(mana_get_primary_netdev_rcu, NET_MANA);
+EXPORT_SYMBOL_NS(mana_get_primary_netdev, NET_MANA);

include/net/mana/gdma.h

@@ -408,8 +408,6 @@ struct gdma_context {
 	struct gdma_dev		mana_ib;
 };
 
-#define MAX_NUM_GDMA_DEVICES	4
-
 static inline bool mana_gd_is_mana(struct gdma_dev *gd)
 {
 	return gd->dev_id.type == GDMA_DEVICE_MANA;
@@ -556,11 +554,15 @@ enum {
 #define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3)
 #define GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT BIT(5)
 
+/* Driver can handle holes (zeros) in the device list */
+#define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11)
+
 #define GDMA_DRV_CAP_FLAGS1 \
 	(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
 	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \
 	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \
-	 GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT)
+	 GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \
+	 GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP)
 
 #define GDMA_DRV_CAP_FLAGS2 0
 
@@ -621,11 +623,12 @@ struct gdma_query_max_resources_resp {
 }; /* HW DATA */
 
 /* GDMA_LIST_DEVICES */
+#define GDMA_DEV_LIST_SIZE 64
 struct gdma_list_devices_resp {
 	struct gdma_resp_hdr hdr;
 	u32 num_of_devs;
 	u32 reserved;
-	struct gdma_dev_id devs[64];
+	struct gdma_dev_id devs[GDMA_DEV_LIST_SIZE];
 }; /* HW DATA */
 
 /* GDMA_REGISTER_DEVICE */

include/net/mana/mana.h

@@ -826,5 +826,7 @@ 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);
 
-struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index);
+struct net_device *mana_get_primary_netdev(struct mana_context *ac,
+					   u32 port_index,
+					   netdevice_tracker *tracker);
 #endif /* _MANA_H */