[PATCH v6 00/11] virtio: s4 support

[PATCH v6 00/11] virtio: s4 support

[Amit Shah]

Hi,

These patches add support for S4 to virtio (pci) and all drivers.

For each driver, all vqs are removed before hibernation, and then
re-created after restore.  Some driver-specific uninit and init work
is also done in the freeze and restore functions.

All the drivers in testing work fine:

* virtio-blk is used for the only disk in the VM, IO works fine before
  and after.  'dd if=/dev/zero of=/tmp/bigfile bs=1024 count=200000'
  across S4 gives same sha1sum for the file in the guest as well as
  one that's created without invoking S4.

* virtio-console: port IO keeps working fine before and after.
  * If a port is waiting for data from the host (blocking read(2)
    call), this works fine in both the cases: host-side connection is
    available or unavailable after resume.  In case the host-side
    connection isn't available, the blocking call is terminated.  If
    it is available, the call continues to remain in blocked state
    till further data arrives.

* virtio-net: ping remains active across S4.

* virtio-balloon: Works fine before and after.  Forgets the ballooned
  value across S4 (see details in commit log). Maintains ballooned
  value on failed freeze.

All of these tests are run in parallel.

v6:
 - Based on top of block and net module remove race fix patches

v5:
 - Enable virtio device after the driver-specific restore/thaw
   callbacks are completed.
 - Balloon: Don't exit kthread on freeze.  It's already frozen by the
   PM API before invoking the freeze callback, so exiting is pointless.

v4:
 - Disable / enable napi across S4 (Michael S. Tsirkin)
 - Balloon: lots of improvements (I had neglected this driver thinking
   it was a simple one, but this one needed the most thought!  Check
   the commit log for patch 12 for details.)
 - Net, Blk: Reset device as the first operation on freeze

v3:
 - Reset vqs before deleting them (Sasha Levin)
 - Flush block queue before freeze (Rusty)
 - Detach netdev before freeze (Michael S. Tsirkin)

v2:
 - fix checkpatch errors/warnings

Amit Shah (11):
  virtio: pci: switch to new PM API
  virtio: pci: add PM notification handlers for restore, freeze, thaw,
    poweroff
  virtio: console: Move vq and vq buf removal into separate functions
  virtio: console: Add freeze and restore handlers to support S4
  virtio: blk: Move vq initialization to separate function
  virtio: blk: Add freeze, restore handlers to support S4
  virtio: net: Move vq initialization into separate function
  virtio: net: Move vq and vq buf removal into separate function
  virtio: net: Add freeze, restore handlers to support S4
  virtio: balloon: Move vq initialization into separate function
  virtio: balloon: Add freeze, restore handlers to support S4

 drivers/block/virtio_blk.c      |   63 ++++++++++++++++++--
 drivers/char/virtio_console.c   |  126 ++++++++++++++++++++++++++++++---------
 drivers/net/virtio_net.c        |  113 ++++++++++++++++++++++++++--------
 drivers/virtio/virtio_balloon.c |   95 ++++++++++++++++++++++++------
 drivers/virtio/virtio_pci.c     |  106 +++++++++++++++++++++++++++++++-
 include/linux/virtio.h          |    5 ++
 6 files changed, 426 insertions(+), 82 deletions(-)

-- 
1.7.7.4

[PATCH v6 01/11] virtio: pci: switch to new PM API

[Amit Shah]

The older PM API doesn't have a way to get notifications on hibernate
events.  Switch to the newer one that gives us those notifications.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/virtio/virtio_pci.c |   16 ++++++++++++----
 1 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 03d1984..23e1532 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -708,19 +708,28 @@ static void __devexit virtio_pci_remove(struct pci_dev *pci_dev)
 }
 
 #ifdef CONFIG_PM
-static int virtio_pci_suspend(struct pci_dev *pci_dev, pm_message_t state)
+static int virtio_pci_suspend(struct device *dev)
 {
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+
 	pci_save_state(pci_dev);
 	pci_set_power_state(pci_dev, PCI_D3hot);
 	return 0;
 }
 
-static int virtio_pci_resume(struct pci_dev *pci_dev)
+static int virtio_pci_resume(struct device *dev)
 {
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+
 	pci_restore_state(pci_dev);
 	pci_set_power_state(pci_dev, PCI_D0);
 	return 0;
 }
+
+static const struct dev_pm_ops virtio_pci_pm_ops = {
+	.suspend = virtio_pci_suspend,
+	.resume  = virtio_pci_resume,
+};
 #endif
 
 static struct pci_driver virtio_pci_driver = {
@@ -729,8 +738,7 @@ static struct pci_driver virtio_pci_driver = {
 	.probe		= virtio_pci_probe,
 	.remove		= __devexit_p(virtio_pci_remove),
 #ifdef CONFIG_PM
-	.suspend	= virtio_pci_suspend,
-	.resume		= virtio_pci_resume,
+	.driver.pm	= &virtio_pci_pm_ops,
 #endif
 };
 
-- 
1.7.7.4

[PATCH v6 02/11] virtio: pci: add PM notification handlers for restore, freeze, thaw, poweroff

[Amit Shah]

Handle thaw, restore and freeze notifications from the PM core.  Expose
these to individual virtio drivers that can quiesce and resume vq
operations.  For drivers not implementing the thaw() method, use the
restore method instead.

These functions also save device-specific data so that the device can be
put in pre-suspend state after resume, and disable and enable the PCI
device in the freeze and resume functions, respectively.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/virtio/virtio_pci.c |   94 ++++++++++++++++++++++++++++++++++++++++++-
 include/linux/virtio.h      |    5 ++
 2 files changed, 97 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 23e1532..63bf242 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -55,6 +55,10 @@ struct virtio_pci_device
 	unsigned msix_vectors;
 	/* Vectors allocated, excluding per-vq vectors if any */
 	unsigned msix_used_vectors;
+
+	/* Status saved during hibernate/restore */
+	u8 saved_status;
+
 	/* Whether we have vector per vq */
 	bool per_vq_vectors;
 };
@@ -726,9 +730,95 @@ static int virtio_pci_resume(struct device *dev)
 	return 0;
 }
 
+static int virtio_pci_freeze(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct virtio_driver *drv;
+	int ret;
+
+	drv = container_of(vp_dev->vdev.dev.driver,
+			   struct virtio_driver, driver);
+
+	ret = 0;
+	vp_dev->saved_status = vp_get_status(&vp_dev->vdev);
+	if (drv && drv->freeze)
+		ret = drv->freeze(&vp_dev->vdev);
+
+	if (!ret)
+		pci_disable_device(pci_dev);
+	return ret;
+}
+
+static int restore_common(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret;
+
+	ret = pci_enable_device(pci_dev);
+	if (ret)
+		return ret;
+	pci_set_master(pci_dev);
+	vp_finalize_features(&vp_dev->vdev);
+
+	return ret;
+}
+
+static int virtio_pci_thaw(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct virtio_driver *drv;
+	int ret;
+
+	ret = restore_common(dev);
+	if (ret)
+		return ret;
+
+	drv = container_of(vp_dev->vdev.dev.driver,
+			   struct virtio_driver, driver);
+
+	if (drv && drv->thaw)
+		ret = drv->thaw(&vp_dev->vdev);
+	else if (drv && drv->restore)
+		ret = drv->restore(&vp_dev->vdev);
+
+	/* Finally, tell the device we're all set */
+	if (!ret)
+		vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
+
+	return ret;
+}
+
+static int virtio_pci_restore(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct virtio_driver *drv;
+	int ret;
+
+	drv = container_of(vp_dev->vdev.dev.driver,
+			   struct virtio_driver, driver);
+
+	ret = restore_common(dev);
+	if (!ret && drv && drv->restore)
+		ret = drv->restore(&vp_dev->vdev);
+
+	/* Finally, tell the device we're all set */
+	if (!ret)
+		vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
+
+	return ret;
+}
+
 static const struct dev_pm_ops virtio_pci_pm_ops = {
-	.suspend = virtio_pci_suspend,
-	.resume  = virtio_pci_resume,
+	.suspend	= virtio_pci_suspend,
+	.resume		= virtio_pci_resume,
+	.freeze		= virtio_pci_freeze,
+	.thaw		= virtio_pci_thaw,
+	.restore	= virtio_pci_restore,
+	.poweroff	= virtio_pci_suspend,
 };
 #endif
 
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 4c069d8..92902ab 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -146,6 +146,11 @@ struct virtio_driver {
 	int (*probe)(struct virtio_device *dev);
 	void (*remove)(struct virtio_device *dev);
 	void (*config_changed)(struct virtio_device *dev);
+#ifdef CONFIG_PM
+	int (*freeze)(struct virtio_device *dev);
+	int (*thaw)(struct virtio_device *dev);
+	int (*restore)(struct virtio_device *dev);
+#endif
 };
 
 int register_virtio_driver(struct virtio_driver *drv);
-- 
1.7.7.4

[PATCH v6 03/11] virtio: console: Move vq and vq buf removal into separate functions

[Amit Shah]

This common code will be shared with the PM freeze function.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/char/virtio_console.c |   68 ++++++++++++++++++++++++-----------------
 1 files changed, 40 insertions(+), 28 deletions(-)

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 8e3c46d..e14f5aa 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1271,6 +1271,20 @@ static void remove_port(struct kref *kref)
 	kfree(port);
 }
 
+static void remove_port_data(struct port *port)
+{
+	struct port_buffer *buf;
+
+	/* Remove unused data this port might have received. */
+	discard_port_data(port);
+
+	reclaim_consumed_buffers(port);
+
+	/* Remove buffers we queued up for the Host to send us data in. */
+	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
+		free_buf(buf);
+}
+
 /*
  * Port got unplugged.  Remove port from portdev's list and drop the
  * kref reference.  If no userspace has this port opened, it will
@@ -1278,8 +1292,6 @@ static void remove_port(struct kref *kref)
  */
 static void unplug_port(struct port *port)
 {
-	struct port_buffer *buf;
-
 	spin_lock_irq(&port->portdev->ports_lock);
 	list_del(&port->list);
 	spin_unlock_irq(&port->portdev->ports_lock);
@@ -1300,14 +1312,7 @@ static void unplug_port(struct port *port)
 		hvc_remove(port->cons.hvc);
 	}
 
-	/* Remove unused data this port might have received. */
-	discard_port_data(port);
-
-	reclaim_consumed_buffers(port);
-
-	/* Remove buffers we queued up for the Host to send us data in. */
-	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf);
+	remove_port_data(port);
 
 	/*
 	 * We should just assume the device itself has gone off --
@@ -1659,6 +1664,28 @@ static const struct file_operations portdev_fops = {
 	.owner = THIS_MODULE,
 };
 
+static void remove_vqs(struct ports_device *portdev)
+{
+	portdev->vdev->config->del_vqs(portdev->vdev);
+	kfree(portdev->in_vqs);
+	kfree(portdev->out_vqs);
+}
+
+static void remove_controlq_data(struct ports_device *portdev)
+{
+	struct port_buffer *buf;
+	unsigned int len;
+
+	if (!use_multiport(portdev))
+		return;
+
+	while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
+		free_buf(buf);
+
+	while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
+		free_buf(buf);
+}
+
 /*
  * Once we're further in boot, we get probed like any other virtio
  * device.
@@ -1764,9 +1791,7 @@ free_vqs:
 	/* The host might want to notify mgmt sw about device add failure */
 	__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
 			   VIRTIO_CONSOLE_DEVICE_READY, 0);
-	vdev->config->del_vqs(vdev);
-	kfree(portdev->in_vqs);
-	kfree(portdev->out_vqs);
+	remove_vqs(portdev);
 free_chrdev:
 	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
 free:
@@ -1804,21 +1829,8 @@ static void virtcons_remove(struct virtio_device *vdev)
 	 * have to just stop using the port, as the vqs are going
 	 * away.
 	 */
-	if (use_multiport(portdev)) {
-		struct port_buffer *buf;
-		unsigned int len;
-
-		while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
-			free_buf(buf);
-
-		while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
-			free_buf(buf);
-	}
-
-	vdev->config->del_vqs(vdev);
-	kfree(portdev->in_vqs);
-	kfree(portdev->out_vqs);
-
+	remove_controlq_data(portdev);
+	remove_vqs(portdev);
 	kfree(portdev);
 }
 
-- 
1.7.7.4

[PATCH v6 04/11] virtio: console: Add freeze and restore handlers to support S4

[Amit Shah]

Remove all vqs and associated buffers in the freeze callback which
prepares us to go into hibernation state.  On restore, re-create all the
vqs and populate the input vqs with buffers to get to the pre-hibernate
state.

Note: Any outstanding unconsumed buffers are discarded; which means
there's a possibility of data loss in case the host or the guest didn't
consume any data already present in the vqs.  This can be addressed in a
later patch series, perhaps in virtio common code.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/char/virtio_console.c |   58 +++++++++++++++++++++++++++++++++++++++++
 1 files changed, 58 insertions(+), 0 deletions(-)

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index e14f5aa..fd2fd6f 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1844,6 +1844,60 @@ static unsigned int features[] = {
 	VIRTIO_CONSOLE_F_MULTIPORT,
 };
 
+#ifdef CONFIG_PM
+static int virtcons_freeze(struct virtio_device *vdev)
+{
+	struct ports_device *portdev;
+	struct port *port;
+
+	portdev = vdev->priv;
+
+	vdev->config->reset(vdev);
+
+	cancel_work_sync(&portdev->control_work);
+	remove_controlq_data(portdev);
+
+	list_for_each_entry(port, &portdev->ports, list) {
+		/*
+		 * We'll ask the host later if the new invocation has
+		 * the port opened or closed.
+		 */
+		port->host_connected = false;
+		remove_port_data(port);
+	}
+	remove_vqs(portdev);
+
+	return 0;
+}
+
+static int virtcons_restore(struct virtio_device *vdev)
+{
+	struct ports_device *portdev;
+	struct port *port;
+	int ret;
+
+	portdev = vdev->priv;
+
+	ret = init_vqs(portdev);
+	if (ret)
+		return ret;
+
+	if (use_multiport(portdev))
+		fill_queue(portdev->c_ivq, &portdev->cvq_lock);
+
+	list_for_each_entry(port, &portdev->ports, list) {
+		port->in_vq = portdev->in_vqs[port->id];
+		port->out_vq = portdev->out_vqs[port->id];
+
+		fill_queue(port->in_vq, &port->inbuf_lock);
+
+		/* Get port open/close status on the host */
+		send_control_msg(port, VIRTIO_CONSOLE_PORT_READY, 1);
+	}
+	return 0;
+}
+#endif
+
 static struct virtio_driver virtio_console = {
 	.feature_table = features,
 	.feature_table_size = ARRAY_SIZE(features),
@@ -1853,6 +1907,10 @@ static struct virtio_driver virtio_console = {
 	.probe =	virtcons_probe,
 	.remove =	virtcons_remove,
 	.config_changed = config_intr,
+#ifdef CONFIG_PM
+	.freeze =	virtcons_freeze,
+	.restore =	virtcons_restore,
+#endif
 };
 
 static int __init init(void)
-- 
1.7.7.4

[PATCH v6 05/11] virtio: blk: Move vq initialization to separate function

[Amit Shah]

The probe and PM restore functions will share this code.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/block/virtio_blk.c |   19 ++++++++++++++-----
 1 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 34633f3..86c9c5b 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -362,6 +362,18 @@ static void virtblk_config_changed(struct virtio_device *vdev)
 	queue_work(virtblk_wq, &vblk->config_work);
 }
 
+static int init_vq(struct virtio_blk *vblk)
+{
+	int err = 0;
+
+	/* We expect one virtqueue, for output. */
+	vblk->vq = virtio_find_single_vq(vblk->vdev, blk_done, "requests");
+	if (IS_ERR(vblk->vq))
+		err = PTR_ERR(vblk->vq);
+
+	return err;
+}
+
 static int __devinit virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
@@ -405,12 +417,9 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 	vblk->config_enable = true;
 
-	/* We expect one virtqueue, for output. */
-	vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests");
-	if (IS_ERR(vblk->vq)) {
-		err = PTR_ERR(vblk->vq);
+	err = init_vq(vblk);
+	if (err)
 		goto out_free_vblk;
-	}
 
 	vblk->pool = mempool_create_kmalloc_pool(1,sizeof(struct virtblk_req));
 	if (!vblk->pool) {
-- 
1.7.7.4

[PATCH v6 06/11] virtio: blk: Add freeze, restore handlers to support S4

[Amit Shah]

Delete the vq and flush any pending requests from the block queue on the
freeze callback to prepare for hibernation.

Re-create the vq in the restore callback to resume normal function.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/block/virtio_blk.c |   44 ++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 44 insertions(+), 0 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 86c9c5b..e3bd9dc 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -588,6 +588,46 @@ static void __devexit virtblk_remove(struct virtio_device *vdev)
 	ida_simple_remove(&vd_index_ida, index);
 }
 
+#ifdef CONFIG_PM
+static int virtblk_freeze(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk = vdev->priv;
+
+	/* Ensure we don't receive any more interrupts */
+	vdev->config->reset(vdev);
+
+	/* Prevent config work handler from accessing the device. */
+	mutex_lock(&vblk->config_lock);
+	vblk->config_enable = false;
+	mutex_unlock(&vblk->config_lock);
+
+	flush_work(&vblk->config_work);
+
+	spin_lock_irq(vblk->disk->queue->queue_lock);
+	blk_stop_queue(vblk->disk->queue);
+	spin_unlock_irq(vblk->disk->queue->queue_lock);
+	blk_sync_queue(vblk->disk->queue);
+
+	vdev->config->del_vqs(vdev);
+	return 0;
+}
+
+static int virtblk_restore(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk = vdev->priv;
+	int ret;
+
+	vblk->config_enable = true;
+	ret = init_vq(vdev->priv);
+	if (!ret) {
+		spin_lock_irq(vblk->disk->queue->queue_lock);
+		blk_start_queue(vblk->disk->queue);
+		spin_unlock_irq(vblk->disk->queue->queue_lock);
+	}
+	return ret;
+}
+#endif
+
 static const struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
 	{ 0 },
@@ -613,6 +653,10 @@ static struct virtio_driver __refdata virtio_blk = {
 	.probe			= virtblk_probe,
 	.remove			= __devexit_p(virtblk_remove),
 	.config_changed		= virtblk_config_changed,
+#ifdef CONFIG_PM
+	.freeze			= virtblk_freeze,
+	.restore		= virtblk_restore,
+#endif
 };
 
 static int __init init(void)
-- 
1.7.7.4

[PATCH v6 07/11] virtio: net: Move vq initialization into separate function

[Amit Shah]

The probe and PM restore functions will share this code.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/net/virtio_net.c |   47 +++++++++++++++++++++++++++------------------
 1 files changed, 28 insertions(+), 19 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 1b67e8a..ec8c400 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -966,15 +966,38 @@ static void virtnet_config_changed(struct virtio_device *vdev)
 	virtnet_update_status(vi);
 }
 
+static int init_vqs(struct virtnet_info *vi)
+{
+	struct virtqueue *vqs[3];
+	vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL};
+	const char *names[] = { "input", "output", "control" };
+	int nvqs, err;
+
+	/* We expect two virtqueues, receive then send,
+	 * and optionally control. */
+	nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2;
+
+	err = vi->vdev->config->find_vqs(vi->vdev, nvqs, vqs, callbacks, names);
+	if (err)
+		return err;
+
+	vi->rvq = vqs[0];
+	vi->svq = vqs[1];
+
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
+		vi->cvq = vqs[2];
+
+		if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
+			vi->dev->features |= NETIF_F_HW_VLAN_FILTER;
+	}
+	return 0;
+}
+
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int err;
 	struct net_device *dev;
 	struct virtnet_info *vi;
-	struct virtqueue *vqs[3];
-	vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL};
-	const char *names[] = { "input", "output", "control" };
-	int nvqs;
 
 	/* Allocate ourselves a network device with room for our info */
 	dev = alloc_etherdev(sizeof(struct virtnet_info));
@@ -1046,24 +1069,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
 		vi->mergeable_rx_bufs = true;
 
-	/* We expect two virtqueues, receive then send,
-	 * and optionally control. */
-	nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2;
-
-	err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
+	err = init_vqs(vi);
 	if (err)
 		goto free_stats;
 
-	vi->rvq = vqs[0];
-	vi->svq = vqs[1];
-
-	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
-		vi->cvq = vqs[2];
-
-		if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
-			dev->features |= NETIF_F_HW_VLAN_FILTER;
-	}
-
 	err = register_netdev(dev);
 	if (err) {
 		pr_debug("virtio_net: registering device failed\n");
-- 
1.7.7.4

[PATCH v6 08/11] virtio: net: Move vq and vq buf removal into separate function

[Amit Shah]

The remove and PM freeze functions will share this code.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/net/virtio_net.c |   20 ++++++++++++--------
 1 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ec8c400..7a2a5bf 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1134,22 +1134,26 @@ static void free_unused_bufs(struct virtnet_info *vi)
 	BUG_ON(vi->num != 0);
 }
 
-static void __devexit virtnet_remove(struct virtio_device *vdev)
+static void remove_vq_common(struct virtnet_info *vi)
 {
-	struct virtnet_info *vi = vdev->priv;
-
-	/* Stop all the virtqueues. */
-	vdev->config->reset(vdev);
-
-	unregister_netdev(vi->dev);
+	vi->vdev->config->reset(vi->vdev);
 
 	/* Free unused buffers in both send and recv, if any. */
 	free_unused_bufs(vi);
 
-	vdev->config->del_vqs(vi->vdev);
+	vi->vdev->config->del_vqs(vi->vdev);
 
 	while (vi->pages)
 		__free_pages(get_a_page(vi, GFP_KERNEL), 0);
+}
+
+static void __devexit virtnet_remove(struct virtio_device *vdev)
+{
+	struct virtnet_info *vi = vdev->priv;
+
+	unregister_netdev(vi->dev);
+
+	remove_vq_common(vi);
 
 	free_percpu(vi->stats);
 	free_netdev(vi->dev);
-- 
1.7.7.4

[PATCH v6 09/11] virtio: net: Add freeze, restore handlers to support S4

[Amit Shah]

Remove all the vqs, disable napi and detach from the netdev on
hibernation.

Re-create vqs after restoring from a hibernated image, re-enable napi
and re-attach the netdev.  This keeps networking working across
hibernation.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/net/virtio_net.c |   46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 46 insertions(+), 0 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7a2a5bf..b31670f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1159,6 +1159,48 @@ static void __devexit virtnet_remove(struct virtio_device *vdev)
 	free_netdev(vi->dev);
 }
 
+#ifdef CONFIG_PM
+static int virtnet_freeze(struct virtio_device *vdev)
+{
+	struct virtnet_info *vi = vdev->priv;
+
+	virtqueue_disable_cb(vi->rvq);
+	virtqueue_disable_cb(vi->svq);
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ))
+		virtqueue_disable_cb(vi->cvq);
+
+	netif_device_detach(vi->dev);
+	cancel_delayed_work_sync(&vi->refill);
+
+	if (netif_running(vi->dev))
+		napi_disable(&vi->napi);
+
+	remove_vq_common(vi);
+
+	return 0;
+}
+
+static int virtnet_restore(struct virtio_device *vdev)
+{
+	struct virtnet_info *vi = vdev->priv;
+	int err;
+
+	err = init_vqs(vi);
+	if (err)
+		return err;
+
+	if (netif_running(vi->dev))
+		virtnet_napi_enable(vi);
+
+	netif_device_attach(vi->dev);
+
+	if (!try_fill_recv(vi, GFP_KERNEL))
+		schedule_delayed_work(&vi->refill, 0);
+
+	return 0;
+}
+#endif
+
 static struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID },
 	{ 0 },
@@ -1183,6 +1225,10 @@ static struct virtio_driver virtio_net_driver = {
 	.probe =	virtnet_probe,
 	.remove =	__devexit_p(virtnet_remove),
 	.config_changed = virtnet_config_changed,
+#ifdef CONFIG_PM
+	.freeze =	virtnet_freeze,
+	.restore =	virtnet_restore,
+#endif
 };
 
 static int __init init(void)
-- 
1.7.7.4

Re: [PATCH v6 09/11] virtio: net: Add freeze, restore handlers to support S4

[Michael S. Tsirkin]

On Thu, Dec 22, 2011 at 04:58:33PM +0530, Amit Shah wrote:
> Remove all the vqs, disable napi and detach from the netdev on
> hibernation.
> 
> Re-create vqs after restoring from a hibernated image, re-enable napi
> and re-attach the netdev.  This keeps networking working across
> hibernation.
> 
> Signed-off-by: Amit Shah <amit.shah@redhat.com>
> ---
>  drivers/net/virtio_net.c |   46 ++++++++++++++++++++++++++++++++++++++++++++++
>  1 files changed, 46 insertions(+), 0 deletions(-)
> 
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 7a2a5bf..b31670f 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -1159,6 +1159,48 @@ static void __devexit virtnet_remove(struct virtio_device *vdev)
>  	free_netdev(vi->dev);
>  }
>  
> +#ifdef CONFIG_PM
> +static int virtnet_freeze(struct virtio_device *vdev)
> +{
> +	struct virtnet_info *vi = vdev->priv;
> +
> +	virtqueue_disable_cb(vi->rvq);
> +	virtqueue_disable_cb(vi->svq);
> +	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ))
> +		virtqueue_disable_cb(vi->cvq);
> +
> +	netif_device_detach(vi->dev);
> +	cancel_delayed_work_sync(&vi->refill);
> +
> +	if (netif_running(vi->dev))
> +		napi_disable(&vi->napi);
> +
> +	remove_vq_common(vi);
> +
> +	return 0;
> +}
> +
> +static int virtnet_restore(struct virtio_device *vdev)
> +{
> +	struct virtnet_info *vi = vdev->priv;
> +	int err;
> +
> +	err = init_vqs(vi);
> +	if (err)
> +		return err;
> +
> +	if (netif_running(vi->dev))

Can virtnet close run at this point?
If yes it's a bug.

> +		virtnet_napi_enable(vi);
> +
> +	netif_device_attach(vi->dev);
> +

Not that open/close start/stop refill,
I wonder whether this is a problem.
For example, can virtnet_close run at this point,
and cancel refill?

> +	if (!try_fill_recv(vi, GFP_KERNEL))
> +		schedule_delayed_work(&vi->refill, 0);

This needs to be switched to non reentrant wq too?

> +
> +	return 0;
> +}
> +#endif
> +
>  static struct virtio_device_id id_table[] = {
>  	{ VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID },
>  	{ 0 },
> @@ -1183,6 +1225,10 @@ static struct virtio_driver virtio_net_driver = {
>  	.probe =	virtnet_probe,
>  	.remove =	__devexit_p(virtnet_remove),
>  	.config_changed = virtnet_config_changed,
> +#ifdef CONFIG_PM
> +	.freeze =	virtnet_freeze,
> +	.restore =	virtnet_restore,
> +#endif
>  };
>  
>  static int __init init(void)
> -- 
> 1.7.7.4

Re: [PATCH v6 09/11] virtio: net: Add freeze, restore handlers to support S4

[Amit Shah]

On (Thu) 29 Dec 2011 [18:15:23], Michael S. Tsirkin wrote:
> On Thu, Dec 22, 2011 at 04:58:33PM +0530, Amit Shah wrote:
> > Remove all the vqs, disable napi and detach from the netdev on
> > hibernation.
> > 
> > Re-create vqs after restoring from a hibernated image, re-enable napi
> > and re-attach the netdev.  This keeps networking working across
> > hibernation.
> > 
> > Signed-off-by: Amit Shah <amit.shah@redhat.com>
> > ---
> >  drivers/net/virtio_net.c |   46 ++++++++++++++++++++++++++++++++++++++++++++++
> >  1 files changed, 46 insertions(+), 0 deletions(-)
> > 
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index 7a2a5bf..b31670f 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -1159,6 +1159,48 @@ static void __devexit virtnet_remove(struct virtio_device *vdev)
> >  	free_netdev(vi->dev);
> >  }
> >  
> > +#ifdef CONFIG_PM
> > +static int virtnet_freeze(struct virtio_device *vdev)
> > +{
> > +	struct virtnet_info *vi = vdev->priv;
> > +
> > +	virtqueue_disable_cb(vi->rvq);
> > +	virtqueue_disable_cb(vi->svq);
> > +	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ))
> > +		virtqueue_disable_cb(vi->cvq);
> > +
> > +	netif_device_detach(vi->dev);
> > +	cancel_delayed_work_sync(&vi->refill);
> > +
> > +	if (netif_running(vi->dev))
> > +		napi_disable(&vi->napi);
> > +
> > +	remove_vq_common(vi);
> > +
> > +	return 0;
> > +}
> > +
> > +static int virtnet_restore(struct virtio_device *vdev)
> > +{
> > +	struct virtnet_info *vi = vdev->priv;
> > +	int err;
> > +
> > +	err = init_vqs(vi);
> > +	if (err)
> > +		return err;
> > +
> > +	if (netif_running(vi->dev))
> 
> Can virtnet close run at this point?
> If yes it's a bug.

Userspace is suspended, and kthreads are frozen.  If virtnet_close was
called before suspend, it would have already succeeded in disabling
napi.

> > +		virtnet_napi_enable(vi);
> > +
> > +	netif_device_attach(vi->dev);
> > +
> 
> Not that open/close start/stop refill,
> I wonder whether this is a problem.
> For example, can virtnet_close run at this point,
> and cancel refill?

Same as above

> 
> > +	if (!try_fill_recv(vi, GFP_KERNEL))
> > +		schedule_delayed_work(&vi->refill, 0);
> 
> This needs to be switched to non reentrant wq too?

Subsequent invocations could create problems?  Note that this will be
the first item to be queued in the workqueue for the refill work.

		Amit

Re: [PATCH v6 09/11] virtio: net: Add freeze, restore handlers to support S4

[Michael S. Tsirkin]

On Fri, Dec 30, 2011 at 03:08:19PM +0530, Amit Shah wrote:
> > 
> > > +	if (!try_fill_recv(vi, GFP_KERNEL))
> > > +		schedule_delayed_work(&vi->refill, 0);
> > 
> > This needs to be switched to non reentrant wq too?
> 
> Subsequent invocations could create problems?  Note that this will be
> the first item to be queued in the workqueue for the refill work.
> 
> 		Amit

See recent patches on net-next.
We switched other calls to a non reentrant wq so I think same
reasoning applies there.

Re: [PATCH v6 09/11] virtio: net: Add freeze, restore handlers to support S4

[Amit Shah]

On (Sun) 01 Jan 2012 [13:47:27], Michael S. Tsirkin wrote:
> On Fri, Dec 30, 2011 at 03:08:19PM +0530, Amit Shah wrote:
> > > 
> > > > +	if (!try_fill_recv(vi, GFP_KERNEL))
> > > > +		schedule_delayed_work(&vi->refill, 0);
> > > 
> > > This needs to be switched to non reentrant wq too?
> > 
> > Subsequent invocations could create problems?  Note that this will be
> > the first item to be queued in the workqueue for the refill work.
> > 
> > 		Amit
> 
> See recent patches on net-next.
> We switched other calls to a non reentrant wq so I think same
> reasoning applies there.

There's a patch ordering issue; so this series should land after the
-net series is merged.

Rusty, do you want me to re-spin this patch on top of yours, or is
that something that you'll handle?

		Amit

Re: [PATCH v6 09/11] virtio: net: Add freeze, restore handlers to support S4

[Rusty Russell]

On Tue, 3 Jan 2012 22:37:48 +0530, Amit Shah <amit.shah@redhat.com> wrote:
> On (Sun) 01 Jan 2012 [13:47:27], Michael S. Tsirkin wrote:
> > On Fri, Dec 30, 2011 at 03:08:19PM +0530, Amit Shah wrote:
> > > > 
> > > > > +	if (!try_fill_recv(vi, GFP_KERNEL))
> > > > > +		schedule_delayed_work(&vi->refill, 0);
> > > > 
> > > > This needs to be switched to non reentrant wq too?
> > > 
> > > Subsequent invocations could create problems?  Note that this will be
> > > the first item to be queued in the workqueue for the refill work.
> > > 
> > > 		Amit
> > 
> > See recent patches on net-next.
> > We switched other calls to a non reentrant wq so I think same
> > reasoning applies there.
> 
> There's a patch ordering issue; so this series should land after the
> -net series is merged.
> 
> Rusty, do you want me to re-spin this patch on top of yours, or is
> that something that you'll handle?

Indeed, this can't go via -net, since it needs the virtio-pci patches
which change power management.

I've changed that one line, and will post those patches for DaveM's ack.

Thanks,
Rusty.

[PATCH v6 10/11] virtio: balloon: Move vq initialization into separate function

[Amit Shah]

The probe and PM restore functions will share this code.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/virtio/virtio_balloon.c |   48 ++++++++++++++++++++++++--------------
 1 files changed, 30 insertions(+), 18 deletions(-)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 94fd738..1ff3cf4 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -275,32 +275,21 @@ static int balloon(void *_vballoon)
 	return 0;
 }
 
-static int virtballoon_probe(struct virtio_device *vdev)
+static int init_vqs(struct virtio_balloon *vb)
 {
-	struct virtio_balloon *vb;
 	struct virtqueue *vqs[3];
 	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
 	const char *names[] = { "inflate", "deflate", "stats" };
 	int err, nvqs;
 
-	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
-	if (!vb) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	INIT_LIST_HEAD(&vb->pages);
-	vb->num_pages = 0;
-	init_waitqueue_head(&vb->config_change);
-	vb->vdev = vdev;
-	vb->need_stats_update = 0;
-
-	/* We expect two virtqueues: inflate and deflate,
-	 * and optionally stat. */
+	/*
+	 * We expect two virtqueues: inflate and deflate, and
+	 * optionally stat.
+	 */
 	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
-	err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
+	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names);
 	if (err)
-		goto out_free_vb;
+		return err;
 
 	vb->inflate_vq = vqs[0];
 	vb->deflate_vq = vqs[1];
@@ -317,6 +306,29 @@ static int virtballoon_probe(struct virtio_device *vdev)
 			BUG();
 		virtqueue_kick(vb->stats_vq);
 	}
+	return 0;
+}
+
+static int virtballoon_probe(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb;
+	int err;
+
+	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
+	if (!vb) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	INIT_LIST_HEAD(&vb->pages);
+	vb->num_pages = 0;
+	init_waitqueue_head(&vb->config_change);
+	vb->vdev = vdev;
+	vb->need_stats_update = 0;
+
+	err = init_vqs(vb);
+	if (err)
+		goto out_free_vb;
 
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
-- 
1.7.7.4

[PATCH v6 11/11] virtio: balloon: Add freeze, restore handlers to support S4

[Amit Shah]

Handling balloon hibernate / restore is tricky.  If the balloon was
inflated before going into the hibernation state, upon resume, the host
will not have any memory of that.  Any pages that were passed on to the
host earlier would most likely be invalid, and the host will have to
re-balloon to the previous value to get in the pre-hibernate state.

So the only sane thing for the guest to do here is to discard all the
pages that were put in the balloon.  When to discard the pages is the
next question.

One solution is to deflate the balloon just before writing the image to
the disk (in the freeze() PM callback).  However, asking for pages from
the host just to discard them immediately after seems wasteful of
resources.  Hence, it makes sense to do this by just fudging our
counters soon after wakeup.  This means we don't deflate the balloon
before sleep, and also don't put unnecessary pressure on the host.

This also helps in the thaw case: if the freeze fails for whatever
reason, the balloon should continue to remain in the inflated state.
This was tested by issuing 'swapoff -a' and trying to go into the S4
state.  That fails, and the balloon stays inflated, as expected.  Both
the host and the guest are happy.

Finally, in the restore() callback, we empty the list of pages that were
previously given off to the host, add the appropriate number of pages to
the totalram_pages counter, reset the num_pages counter to 0, and
all is fine.

As a last step, delete the vqs on the freeze callback to prepare for
hibernation, and re-create them in the restore and thaw callbacks to
resume normal operation.

The kthread doesn't race with any operations here, since it's frozen
before the freeze() call and is thawed after the thaw() and restore()
callbacks, so we're safe with that.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
---
 drivers/virtio/virtio_balloon.c |   47 +++++++++++++++++++++++++++++++++++++++
 1 files changed, 47 insertions(+), 0 deletions(-)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 1ff3cf4..4c327c7 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -363,6 +363,48 @@ static void __devexit virtballoon_remove(struct virtio_device *vdev)
 	kfree(vb);
 }
 
+#ifdef CONFIG_PM
+static int virtballoon_freeze(struct virtio_device *vdev)
+{
+	/*
+	 * The kthread is already frozen by the PM core before this
+	 * function is called.
+	 */
+
+	/* Ensure we don't get any more requests from the host */
+	vdev->config->reset(vdev);
+	vdev->config->del_vqs(vdev);
+	return 0;
+}
+
+static int virtballoon_thaw(struct virtio_device *vdev)
+{
+	return init_vqs(vdev->priv);
+}
+
+static int virtballoon_restore(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+	struct page *page, *page2;
+
+	/* We're starting from a clean slate */
+	vb->num_pages = 0;
+
+	/*
+	 * If a request wasn't complete at the time of freezing, this
+	 * could have been set.
+	 */
+	vb->need_stats_update = 0;
+
+	/* We don't have these pages in the balloon anymore! */
+	list_for_each_entry_safe(page, page2, &vb->pages, lru) {
+		list_del(&page->lru);
+		totalram_pages++;
+	}
+	return init_vqs(vdev->priv);
+}
+#endif
+
 static unsigned int features[] = {
 	VIRTIO_BALLOON_F_MUST_TELL_HOST,
 	VIRTIO_BALLOON_F_STATS_VQ,
@@ -377,6 +419,11 @@ static struct virtio_driver virtio_balloon_driver = {
 	.probe =	virtballoon_probe,
 	.remove =	__devexit_p(virtballoon_remove),
 	.config_changed = virtballoon_changed,
+#ifdef CONFIG_PM
+	.freeze	=	virtballoon_freeze,
+	.restore =	virtballoon_restore,
+	.thaw =		virtballoon_thaw,
+#endif
 };
 
 static int __init init(void)
-- 
1.7.7.4

Re: [PATCH v6 00/11] virtio: s4 support

[Rusty Russell]

On Thu, 22 Dec 2011 16:58:24 +0530, Amit Shah <amit.shah@redhat.com> wrote:
> Hi,
> 
> These patches add support for S4 to virtio (pci) and all drivers.

Thanks, they're neatly divided, and all seem sane.

Applied,
Rusty.