[SIG-CLOUD-9] rebase custom changes to kernel-5.14.0-570.49.1.el9_6

drivers/hv/channel.c

@@ -1077,68 +1077,10 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
 EXPORT_SYMBOL(vmbus_sendpacket);
 
 /*
- * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer
- * packets using a GPADL Direct packet type. This interface allows you
- * to control notifying the host. This will be useful for sending
- * batched data. Also the sender can control the send flags
- * explicitly.
- */
-int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
-				struct hv_page_buffer pagebuffers[],
-				u32 pagecount, void *buffer, u32 bufferlen,
-				u64 requestid)
-{
-	int i;
-	struct vmbus_channel_packet_page_buffer desc;
-	u32 descsize;
-	u32 packetlen;
-	u32 packetlen_aligned;
-	struct kvec bufferlist[3];
-	u64 aligned_data = 0;
-
-	if (pagecount > MAX_PAGE_BUFFER_COUNT)
-		return -EINVAL;
-
-	/*
-	 * Adjust the size down since vmbus_channel_packet_page_buffer is the
-	 * largest size we support
-	 */
-	descsize = sizeof(struct vmbus_channel_packet_page_buffer) -
-			  ((MAX_PAGE_BUFFER_COUNT - pagecount) *
-			  sizeof(struct hv_page_buffer));
-	packetlen = descsize + bufferlen;
-	packetlen_aligned = ALIGN(packetlen, sizeof(u64));
-
-	/* Setup the descriptor */
-	desc.type = VM_PKT_DATA_USING_GPA_DIRECT;
-	desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
-	desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */
-	desc.length8 = (u16)(packetlen_aligned >> 3);
-	desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
-	desc.reserved = 0;
-	desc.rangecount = pagecount;
-
-	for (i = 0; i < pagecount; i++) {
-		desc.range[i].len = pagebuffers[i].len;
-		desc.range[i].offset = pagebuffers[i].offset;
-		desc.range[i].pfn	 = pagebuffers[i].pfn;
-	}
-
-	bufferlist[0].iov_base = &desc;
-	bufferlist[0].iov_len = descsize;
-	bufferlist[1].iov_base = buffer;
-	bufferlist[1].iov_len = bufferlen;
-	bufferlist[2].iov_base = &aligned_data;
-	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
-
-	return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL);
-}
-EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);
-
-/*
- * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet
+ * vmbus_sendpacket_mpb_desc - Send one or more multi-page buffer packets
  * using a GPADL Direct packet type.
- * The buffer includes the vmbus descriptor.
+ * The desc argument must include space for the VMBus descriptor. The
+ * rangecount field must already be set.
  */
 int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 			      struct vmbus_packet_mpb_array *desc,
@@ -1160,7 +1102,6 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	desc->length8 = (u16)(packetlen_aligned >> 3);
 	desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
 	desc->reserved = 0;
-	desc->rangecount = 1;
 
 	bufferlist[0].iov_base = desc;
 	bufferlist[0].iov_len = desc_size;

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/main.c

@@ -383,7 +383,7 @@ static int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem
 
 	create_req->length = umem->length;
 	create_req->offset_in_page = ib_umem_dma_offset(umem, page_sz);
-	create_req->gdma_page_type = order_base_2(page_sz) - PAGE_SHIFT;
+	create_req->gdma_page_type = order_base_2(page_sz) - MANA_PAGE_SHIFT;
 	create_req->page_count = num_pages_total;
 
 	ibdev_dbg(&dev->ib_dev, "size_dma_region %lu num_pages_total %lu\n",
@@ -511,13 +511,13 @@ int mana_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma)
 	      PAGE_SHIFT;
 	prot = pgprot_writecombine(vma->vm_page_prot);
 
-	ret = rdma_user_mmap_io(ibcontext, vma, pfn, gc->db_page_size, prot,
+	ret = rdma_user_mmap_io(ibcontext, vma, pfn, PAGE_SIZE, prot,
 				NULL);
 	if (ret)
 		ibdev_dbg(ibdev, "can't rdma_user_mmap_io ret %d\n", ret);
 	else
-		ibdev_dbg(ibdev, "mapped I/O pfn 0x%llx page_size %u, ret %d\n",
-			  pfn, gc->db_page_size, ret);
+		ibdev_dbg(ibdev, "mapped I/O pfn 0x%llx page_size %lu, ret %d\n",
+			  pfn, PAGE_SIZE, ret);
 
 	return ret;
 }

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 {