uio_hv_generic: defer opening vmbus until first use

This fixes two design flaws in hv_uio_generic.

Since hv_uio_probe is called from vmbus_probe with lock held
it potentially can cause sleep in an atomic section because
vmbus_open will wait for response from host.

The hv_uio_generic driver could not handle applications
exiting and restarting because the vmbus channel was
persistent.  Change the semantics so that the buffers are
allocated on probe, but not attached to host until
device is opened.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/uio/uio_hv_generic.c

@@ -55,6 +55,7 @@ enum hv_uio_map {
 struct hv_uio_private_data {
 	struct uio_info info;
 	struct hv_device *device;
+	atomic_t refcnt;
 
 	void	*recv_buf;
 	u32	recv_gpadl;
@@ -128,12 +129,10 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
 {
 	struct vmbus_channel *channel
 		= container_of(kobj, struct vmbus_channel, kobj);
-	struct hv_device *dev = channel->primary_channel->device_obj;
-	u16 q_idx = channel->offermsg.offer.sub_channel_index;
 	void *ring_buffer = page_address(channel->ringbuffer_page);
 
-	dev_dbg(&dev->device, "mmap channel %u pages %#lx at %#lx\n",
-		q_idx, vma_pages(vma), vma->vm_pgoff);
+	if (channel->state != CHANNEL_OPENED_STATE)
+		return -ENODEV;
 
 	return vm_iomap_memory(vma, virt_to_phys(ring_buffer),
 			       channel->ringbuffer_pagecount << PAGE_SHIFT);
@@ -176,57 +175,103 @@ hv_uio_new_channel(struct vmbus_channel *new_sc)
 	}
 }
 
+/* free the reserved buffers for send and receive */
 static void
 hv_uio_cleanup(struct hv_device *dev, struct hv_uio_private_data *pdata)
 {
-	if (pdata->send_gpadl)
+	if (pdata->send_gpadl) {
 		vmbus_teardown_gpadl(dev->channel, pdata->send_gpadl);
-	vfree(pdata->send_buf);
+		pdata->send_gpadl = 0;
+		vfree(pdata->send_buf);
+	}
 
-	if (pdata->recv_gpadl)
+	if (pdata->recv_gpadl) {
 		vmbus_teardown_gpadl(dev->channel, pdata->recv_gpadl);
-	vfree(pdata->recv_buf);
+		pdata->recv_gpadl = 0;
+		vfree(pdata->recv_buf);
+	}
+}
+
+/* VMBus primary channel is opened on first use */
+static int
+hv_uio_open(struct uio_info *info, struct inode *inode)
+{
+	struct hv_uio_private_data *pdata
+		= container_of(info, struct hv_uio_private_data, info);
+	struct hv_device *dev = pdata->device;
+	int ret;
+
+	if (atomic_inc_return(&pdata->refcnt) != 1)
+		return 0;
+
+	ret = vmbus_connect_ring(dev->channel,
+				 hv_uio_channel_cb, dev->channel);
+
+	if (ret == 0)
+		dev->channel->inbound.ring_buffer->interrupt_mask = 1;
+	else
+		atomic_dec(&pdata->refcnt);
+
+	return ret;
+}
+
+/* VMBus primary channel is closed on last close */
+static int
+hv_uio_release(struct uio_info *info, struct inode *inode)
+{
+	struct hv_uio_private_data *pdata
+		= container_of(info, struct hv_uio_private_data, info);
+	struct hv_device *dev = pdata->device;
+	int ret = 0;
+
+	if (atomic_dec_and_test(&pdata->refcnt))
+		ret = vmbus_disconnect_ring(dev->channel);
+
+	return ret;
 }
 
 static int
 hv_uio_probe(struct hv_device *dev,
 	     const struct hv_vmbus_device_id *dev_id)
 {
+	struct vmbus_channel *channel = dev->channel;
 	struct hv_uio_private_data *pdata;
+	void *ring_buffer;
 	int ret;
 
+	/* Communicating with host has to be via shared memory not hypercall */
+	if (!channel->offermsg.monitor_allocated) {
+		dev_err(&dev->device, "vmbus channel requires hypercall\n");
+		return -ENOTSUPP;
+	}
+
 	pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return -ENOMEM;
 
-	ret = vmbus_open(dev->channel, HV_RING_SIZE * PAGE_SIZE,
-			 HV_RING_SIZE * PAGE_SIZE, NULL, 0,
-			 hv_uio_channel_cb, dev->channel);
+	ret = vmbus_alloc_ring(channel, HV_RING_SIZE * PAGE_SIZE,
+			       HV_RING_SIZE * PAGE_SIZE);
 	if (ret)
 		goto fail;
 
-	/* Communicating with host has to be via shared memory not hypercall */
-	if (!dev->channel->offermsg.monitor_allocated) {
-		dev_err(&dev->device, "vmbus channel requires hypercall\n");
-		ret = -ENOTSUPP;
-		goto fail_close;
-	}
-
-	dev->channel->inbound.ring_buffer->interrupt_mask = 1;
-	set_channel_read_mode(dev->channel, HV_CALL_ISR);
+	set_channel_read_mode(channel, HV_CALL_ISR);
 
 	/* Fill general uio info */
 	pdata->info.name = "uio_hv_generic";
 	pdata->info.version = DRIVER_VERSION;
 	pdata->info.irqcontrol = hv_uio_irqcontrol;
+	pdata->info.open = hv_uio_open;
+	pdata->info.release = hv_uio_release;
 	pdata->info.irq = UIO_IRQ_CUSTOM;
+	atomic_set(&pdata->refcnt, 0);
 
 	/* mem resources */
 	pdata->info.mem[TXRX_RING_MAP].name = "txrx_rings";
+	ring_buffer = page_address(channel->ringbuffer_page);
 	pdata->info.mem[TXRX_RING_MAP].addr
-		= (uintptr_t)virt_to_phys(page_address(dev->channel->ringbuffer_page));
+		= (uintptr_t)virt_to_phys(ring_buffer);
 	pdata->info.mem[TXRX_RING_MAP].size
-		= dev->channel->ringbuffer_pagecount << PAGE_SHIFT;
+		= channel->ringbuffer_pagecount << PAGE_SHIFT;
 	pdata->info.mem[TXRX_RING_MAP].memtype = UIO_MEM_IOVA;
 
 	pdata->info.mem[INT_PAGE_MAP].name = "int_page";
@@ -247,7 +292,7 @@ hv_uio_probe(struct hv_device *dev,
 		goto fail_close;
 	}
 
-	ret = vmbus_establish_gpadl(dev->channel, pdata->recv_buf,
+	ret = vmbus_establish_gpadl(channel, pdata->recv_buf,
 				    RECV_BUFFER_SIZE, &pdata->recv_gpadl);
 	if (ret)
 		goto fail_close;
@@ -261,14 +306,13 @@ hv_uio_probe(struct hv_device *dev,
 	pdata->info.mem[RECV_BUF_MAP].size = RECV_BUFFER_SIZE;
 	pdata->info.mem[RECV_BUF_MAP].memtype = UIO_MEM_VIRTUAL;
 
-
 	pdata->send_buf = vzalloc(SEND_BUFFER_SIZE);
 	if (pdata->send_buf == NULL) {
 		ret = -ENOMEM;
 		goto fail_close;
 	}
 
-	ret = vmbus_establish_gpadl(dev->channel, pdata->send_buf,
+	ret = vmbus_establish_gpadl(channel, pdata->send_buf,
 				    SEND_BUFFER_SIZE, &pdata->send_gpadl);
 	if (ret)
 		goto fail_close;
@@ -290,10 +334,10 @@ hv_uio_probe(struct hv_device *dev,
 		goto fail_close;
 	}
 
-	vmbus_set_chn_rescind_callback(dev->channel, hv_uio_rescind);
-	vmbus_set_sc_create_callback(dev->channel, hv_uio_new_channel);
+	vmbus_set_chn_rescind_callback(channel, hv_uio_rescind);
+	vmbus_set_sc_create_callback(channel, hv_uio_new_channel);
 
-	ret = sysfs_create_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr);
+	ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr);
 	if (ret)
 		dev_notice(&dev->device,
 			   "sysfs create ring bin file failed; %d\n", ret);
@@ -304,7 +348,6 @@ hv_uio_probe(struct hv_device *dev,
 
 fail_close:
 	hv_uio_cleanup(dev, pdata);
-	vmbus_close(dev->channel);
 fail:
 	kfree(pdata);
 
@@ -322,7 +365,8 @@ hv_uio_remove(struct hv_device *dev)
 	uio_unregister_device(&pdata->info);
 	hv_uio_cleanup(dev, pdata);
 	hv_set_drvdata(dev, NULL);
-	vmbus_close(dev->channel);
+
+	vmbus_free_ring(dev->channel);
 	kfree(pdata);
 	return 0;
 }