[v4,2/5] virtio-pmem: Add virtio pmem driver
diff mbox series

Message ID 20190403104018.23947-3-pagupta@redhat.com
State Superseded
Headers show
Series
  • virtio pmem driver
Related show

Commit Message

Pankaj Gupta April 3, 2019, 10:40 a.m. UTC
This patch adds virtio-pmem driver for KVM guest.

Guest reads the persistent memory range information from
Qemu over VIRTIO and registers it on nvdimm_bus. It also
creates a nd_region object with the persistent memory
range information so that existing 'nvdimm/pmem' driver
can reserve this into system memory map. This way
'virtio-pmem' driver uses existing functionality of pmem
driver to register persistent memory compatible for DAX
capable filesystems.

This also provides function to perform guest flush over
VIRTIO from 'pmem' driver when userspace performs flush
on DAX memory range.

Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
---
 drivers/nvdimm/virtio_pmem.c     |  84 +++++++++++++++++++++
 drivers/virtio/Kconfig           |  10 +++
 drivers/virtio/Makefile          |   1 +
 drivers/virtio/pmem.c            | 125 +++++++++++++++++++++++++++++++
 include/linux/virtio_pmem.h      |  60 +++++++++++++++
 include/uapi/linux/virtio_ids.h  |   1 +
 include/uapi/linux/virtio_pmem.h |  10 +++
 7 files changed, 291 insertions(+)
 create mode 100644 drivers/nvdimm/virtio_pmem.c
 create mode 100644 drivers/virtio/pmem.c
 create mode 100644 include/linux/virtio_pmem.h
 create mode 100644 include/uapi/linux/virtio_pmem.h

Comments

Yuval Shaia April 3, 2019, 11:43 a.m. UTC | #1
On Wed, Apr 03, 2019 at 04:10:15PM +0530, Pankaj Gupta wrote:
> This patch adds virtio-pmem driver for KVM guest.
> 
> Guest reads the persistent memory range information from
> Qemu over VIRTIO and registers it on nvdimm_bus. It also
> creates a nd_region object with the persistent memory
> range information so that existing 'nvdimm/pmem' driver
> can reserve this into system memory map. This way
> 'virtio-pmem' driver uses existing functionality of pmem
> driver to register persistent memory compatible for DAX
> capable filesystems.
> 
> This also provides function to perform guest flush over
> VIRTIO from 'pmem' driver when userspace performs flush
> on DAX memory range.
> 
> Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
> ---
>  drivers/nvdimm/virtio_pmem.c     |  84 +++++++++++++++++++++
>  drivers/virtio/Kconfig           |  10 +++
>  drivers/virtio/Makefile          |   1 +
>  drivers/virtio/pmem.c            | 125 +++++++++++++++++++++++++++++++
>  include/linux/virtio_pmem.h      |  60 +++++++++++++++
>  include/uapi/linux/virtio_ids.h  |   1 +
>  include/uapi/linux/virtio_pmem.h |  10 +++
>  7 files changed, 291 insertions(+)
>  create mode 100644 drivers/nvdimm/virtio_pmem.c
>  create mode 100644 drivers/virtio/pmem.c
>  create mode 100644 include/linux/virtio_pmem.h
>  create mode 100644 include/uapi/linux/virtio_pmem.h
> 
> diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
> new file mode 100644
> index 000000000000..2a1b1ba2c1ff
> --- /dev/null
> +++ b/drivers/nvdimm/virtio_pmem.c
> @@ -0,0 +1,84 @@
> +// SPDX-License-Identifier: GPL-2.0

Is this comment stile (//) acceptable?

> +/*
> + * virtio_pmem.c: Virtio pmem Driver
> + *
> + * Discovers persistent memory range information
> + * from host and provides a virtio based flushing
> + * interface.
> + */
> +#include <linux/virtio_pmem.h>
> +#include "nd.h"
> +
> + /* The interrupt handler */
> +void host_ack(struct virtqueue *vq)
> +{
> +	unsigned int len;
> +	unsigned long flags;
> +	struct virtio_pmem_request *req, *req_buf;
> +	struct virtio_pmem *vpmem = vq->vdev->priv;
> +
> +	spin_lock_irqsave(&vpmem->pmem_lock, flags);
> +	while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
> +		req->done = true;
> +		wake_up(&req->host_acked);
> +
> +		if (!list_empty(&vpmem->req_list)) {
> +			req_buf = list_first_entry(&vpmem->req_list,
> +					struct virtio_pmem_request, list);
> +			list_del(&vpmem->req_list);
> +			req_buf->wq_buf_avail = true;
> +			wake_up(&req_buf->wq_buf);
> +		}
> +	}
> +	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> +}
> +EXPORT_SYMBOL_GPL(host_ack);
> +
> + /* The request submission function */
> +int virtio_pmem_flush(struct nd_region *nd_region)
> +{
> +	int err;
> +	unsigned long flags;
> +	struct scatterlist *sgs[2], sg, ret;
> +	struct virtio_device *vdev = nd_region->provider_data;
> +	struct virtio_pmem *vpmem = vdev->priv;
> +	struct virtio_pmem_request *req;
> +
> +	might_sleep();

[1]

> +	req = kmalloc(sizeof(*req), GFP_KERNEL);
> +	if (!req)
> +		return -ENOMEM;
> +
> +	req->done = req->wq_buf_avail = false;
> +	strcpy(req->name, "FLUSH");
> +	init_waitqueue_head(&req->host_acked);
> +	init_waitqueue_head(&req->wq_buf);
> +	sg_init_one(&sg, req->name, strlen(req->name));
> +	sgs[0] = &sg;
> +	sg_init_one(&ret, &req->ret, sizeof(req->ret));
> +	sgs[1] = &ret;
> +
> +	spin_lock_irqsave(&vpmem->pmem_lock, flags);
> +	err = virtqueue_add_sgs(vpmem->req_vq, sgs, 1, 1, req, GFP_ATOMIC);

Is it okay to use GFP_ATOMIC in a might-sleep ([1]) function?

> +	if (err) {
> +		dev_err(&vdev->dev, "failed to send command to virtio pmem device\n");
> +
> +		list_add_tail(&vpmem->req_list, &req->list);
> +		spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> +
> +		/* When host has read buffer, this completes via host_ack */
> +		wait_event(req->wq_buf, req->wq_buf_avail);
> +		spin_lock_irqsave(&vpmem->pmem_lock, flags);
> +	}
> +	virtqueue_kick(vpmem->req_vq);

You probably want to check return value here.

> +	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> +
> +	/* When host has read buffer, this completes via host_ack */
> +	wait_event(req->host_acked, req->done);
> +	err = req->ret;
> +	kfree(req);
> +
> +	return err;
> +};
> +EXPORT_SYMBOL_GPL(virtio_pmem_flush);
> +MODULE_LICENSE("GPL");
> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> index 35897649c24f..9f634a2ed638 100644
> --- a/drivers/virtio/Kconfig
> +++ b/drivers/virtio/Kconfig
> @@ -42,6 +42,16 @@ config VIRTIO_PCI_LEGACY
>  
>  	  If unsure, say Y.
>  
> +config VIRTIO_PMEM
> +	tristate "Support for virtio pmem driver"
> +	depends on VIRTIO
> +	depends on LIBNVDIMM
> +	help
> +	This driver provides support for virtio based flushing interface
> +	for persistent memory range.
> +
> +	If unsure, say M.
> +
>  config VIRTIO_BALLOON
>  	tristate "Virtio balloon driver"
>  	depends on VIRTIO
> diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
> index 3a2b5c5dcf46..143ce91eabe9 100644
> --- a/drivers/virtio/Makefile
> +++ b/drivers/virtio/Makefile
> @@ -6,3 +6,4 @@ virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
>  virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
>  obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
>  obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
> +obj-$(CONFIG_VIRTIO_PMEM) += pmem.o ../nvdimm/virtio_pmem.o
> diff --git a/drivers/virtio/pmem.c b/drivers/virtio/pmem.c
> new file mode 100644
> index 000000000000..52f74064f67e
> --- /dev/null
> +++ b/drivers/virtio/pmem.c
> @@ -0,0 +1,125 @@
> +// SPDX-License-Identifier: GPL-2.0

Ditto

> +/*
> + * virtio_pmem.c: Virtio pmem Driver
> + *
> + * Discovers persistent memory range information
> + * from host and registers the virtual pmem device
> + * with libnvdimm core.
> + */
> +#include <linux/virtio_pmem.h>
> +#include <../../drivers/nvdimm/nd.h>

Should this file be moved to include/ directory?

> +
> +static struct virtio_device_id id_table[] = {
> +	{ VIRTIO_ID_PMEM, VIRTIO_DEV_ANY_ID },
> +	{ 0 },
> +};
> +
> + /* Initialize virt queue */
> +static int init_vq(struct virtio_pmem *vpmem)
> +{
> +	struct virtqueue *vq;
> +
> +	/* single vq */
> +	vpmem->req_vq = vq = virtio_find_single_vq(vpmem->vdev,
> +				host_ack, "flush_queue");
> +	if (IS_ERR(vq))
> +		return PTR_ERR(vq);
> +
> +	spin_lock_init(&vpmem->pmem_lock);
> +	INIT_LIST_HEAD(&vpmem->req_list);
> +
> +	return 0;
> +};
> +
> +static int virtio_pmem_probe(struct virtio_device *vdev)
> +{
> +	int err = 0;
> +	struct resource res;
> +	struct virtio_pmem *vpmem;
> +	struct nvdimm_bus *nvdimm_bus;
> +	struct nd_region_desc ndr_desc;
> +	int nid = dev_to_node(&vdev->dev);
> +	struct nd_region *nd_region;
> +
> +	if (!vdev->config->get) {
> +		dev_err(&vdev->dev, "%s failure: config disabled\n",
> +			__func__);
> +		return -EINVAL;
> +	}
> +
> +	vdev->priv = vpmem = devm_kzalloc(&vdev->dev, sizeof(*vpmem),
> +			GFP_KERNEL);

Suggesting to indent it right so it will be under &vdev

> +	if (!vpmem) {
> +		err = -ENOMEM;
> +		goto out_err;
> +	}
> +
> +	vpmem->vdev = vdev;
> +	err = init_vq(vpmem);
> +	if (err)
> +		goto out_err;

No need to free vpmem here?

> +
> +	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
> +			start, &vpmem->start);
> +	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
> +			size, &vpmem->size);
> +
> +	res.start = vpmem->start;
> +	res.end   = vpmem->start + vpmem->size-1;
> +	vpmem->nd_desc.provider_name = "virtio-pmem";
> +	vpmem->nd_desc.module = THIS_MODULE;
> +
> +	vpmem->nvdimm_bus = nvdimm_bus = nvdimm_bus_register(&vdev->dev,
> +						&vpmem->nd_desc);
> +	if (!nvdimm_bus)
> +		goto out_vq;

Ditto (i'm probably missing something here)

> +
> +	dev_set_drvdata(&vdev->dev, nvdimm_bus);
> +	memset(&ndr_desc, 0, sizeof(ndr_desc));

Any reason not to use compiler initialization?
i.e.
	struct nd_region_desc ndr_desc = {};

> +
> +	ndr_desc.res = &res;
> +	ndr_desc.numa_node = nid;
> +	ndr_desc.flush = virtio_pmem_flush;
> +	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
> +	set_bit(ND_REGION_ASYNC, &ndr_desc.flags);
> +	nd_region = nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc);
> +	nd_region->provider_data =  dev_to_virtio
> +					(nd_region->dev.parent->parent);
> +
> +	if (!nd_region)
> +		goto out_nd;
> +
> +	//virtio_device_ready(vdev);

Left over

> +	return 0;
> +out_nd:
> +	err = -ENXIO;
> +	nvdimm_bus_unregister(nvdimm_bus);
> +out_vq:
> +	vdev->config->del_vqs(vdev);
> +out_err:
> +	dev_err(&vdev->dev, "failed to register virtio pmem memory\n");
> +	return err;
> +}
> +
> +static void virtio_pmem_remove(struct virtio_device *vdev)
> +{
> +	struct virtio_pmem *vpmem = vdev->priv;
> +	struct nvdimm_bus *nvdimm_bus = dev_get_drvdata(&vdev->dev);
> +
> +	nvdimm_bus_unregister(nvdimm_bus);
> +	vdev->config->del_vqs(vdev);

I think you should also call vdev->config->reset

> +	kfree(vpmem);
> +}
> +
> +static struct virtio_driver virtio_pmem_driver = {
> +	.driver.name		= KBUILD_MODNAME,
> +	.driver.owner		= THIS_MODULE,
> +	.id_table		= id_table,
> +	.probe			= virtio_pmem_probe,
> +	.remove			= virtio_pmem_remove,
> +};
> +
> +module_virtio_driver(virtio_pmem_driver);
> +MODULE_DEVICE_TABLE(virtio, id_table);
> +MODULE_DESCRIPTION("Virtio pmem driver");
> +MODULE_LICENSE("GPL");
> diff --git a/include/linux/virtio_pmem.h b/include/linux/virtio_pmem.h
> new file mode 100644
> index 000000000000..224f9d934be6
> --- /dev/null
> +++ b/include/linux/virtio_pmem.h
> @@ -0,0 +1,60 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * virtio_pmem.h: virtio pmem Driver
> + *
> + * Discovers persistent memory range information
> + * from host and provides a virtio based flushing
> + * interface.
> + **/
> +
> +#ifndef _LINUX_VIRTIO_PMEM_H
> +#define _LINUX_VIRTIO_PMEM_H
> +
> +#include <linux/virtio_ids.h>
> +#include <linux/module.h>
> +#include <linux/virtio_config.h>
> +#include <uapi/linux/virtio_pmem.h>
> +#include <linux/libnvdimm.h>
> +#include <linux/spinlock.h>
> +
> +struct virtio_pmem_request {
> +	/* Host return status corresponding to flush request */
> +	int ret;
> +
> +	/* command name*/
> +	char name[16];
> +
> +	/* Wait queue to process deferred work after ack from host */
> +	wait_queue_head_t host_acked;
> +	bool done;
> +
> +	/* Wait queue to process deferred work after virt queue buffer avail */
> +	wait_queue_head_t wq_buf;
> +	bool wq_buf_avail;
> +	struct list_head list;
> +};
> +
> +struct virtio_pmem {
> +	struct virtio_device *vdev;
> +
> +	/* Virtio pmem request queue */
> +	struct virtqueue *req_vq;
> +
> +	/* nvdimm bus registers virtio pmem device */
> +	struct nvdimm_bus *nvdimm_bus;
> +	struct nvdimm_bus_descriptor nd_desc;
> +
> +	/* List to store deferred work if virtqueue is full */
> +	struct list_head req_list;
> +
> +	/* Synchronize virtqueue data */
> +	spinlock_t pmem_lock;
> +
> +	/* Memory region information */
> +	uint64_t start;
> +	uint64_t size;
> +};
> +
> +void host_ack(struct virtqueue *vq);
> +int virtio_pmem_flush(struct nd_region *nd_region);
> +#endif
> diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
> index 6d5c3b2d4f4d..346389565ac1 100644
> --- a/include/uapi/linux/virtio_ids.h
> +++ b/include/uapi/linux/virtio_ids.h
> @@ -43,5 +43,6 @@
>  #define VIRTIO_ID_INPUT        18 /* virtio input */
>  #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
>  #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
> +#define VIRTIO_ID_PMEM         25 /* virtio pmem */

Any reason for the jump here? are 21 to 24 already taken or you just
want to be on the safe side?

>  
>  #endif /* _LINUX_VIRTIO_IDS_H */
> diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h
> new file mode 100644
> index 000000000000..fa3f7d52717a
> --- /dev/null
> +++ b/include/uapi/linux/virtio_pmem.h
> @@ -0,0 +1,10 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +
> +#ifndef _UAPI_LINUX_VIRTIO_PMEM_H
> +#define _UAPI_LINUX_VIRTIO_PMEM_H
> +
> +struct virtio_pmem_config {
> +	__le64 start;
> +	__le64 size;
> +};
> +#endif
> -- 
> 2.20.1
> 
>
Pankaj Gupta April 3, 2019, 12:40 p.m. UTC | #2
> Subject: Re: [Qemu-devel] [PATCH v4 2/5] virtio-pmem: Add virtio pmem driver
> 
> On Wed, Apr 03, 2019 at 04:10:15PM +0530, Pankaj Gupta wrote:
> > This patch adds virtio-pmem driver for KVM guest.
> > 
> > Guest reads the persistent memory range information from
> > Qemu over VIRTIO and registers it on nvdimm_bus. It also
> > creates a nd_region object with the persistent memory
> > range information so that existing 'nvdimm/pmem' driver
> > can reserve this into system memory map. This way
> > 'virtio-pmem' driver uses existing functionality of pmem
> > driver to register persistent memory compatible for DAX
> > capable filesystems.
> > 
> > This also provides function to perform guest flush over
> > VIRTIO from 'pmem' driver when userspace performs flush
> > on DAX memory range.
> > 
> > Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
> > ---
> >  drivers/nvdimm/virtio_pmem.c     |  84 +++++++++++++++++++++
> >  drivers/virtio/Kconfig           |  10 +++
> >  drivers/virtio/Makefile          |   1 +
> >  drivers/virtio/pmem.c            | 125 +++++++++++++++++++++++++++++++
> >  include/linux/virtio_pmem.h      |  60 +++++++++++++++
> >  include/uapi/linux/virtio_ids.h  |   1 +
> >  include/uapi/linux/virtio_pmem.h |  10 +++
> >  7 files changed, 291 insertions(+)
> >  create mode 100644 drivers/nvdimm/virtio_pmem.c
> >  create mode 100644 drivers/virtio/pmem.c
> >  create mode 100644 include/linux/virtio_pmem.h
> >  create mode 100644 include/uapi/linux/virtio_pmem.h
> > 
> > diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
> > new file mode 100644
> > index 000000000000..2a1b1ba2c1ff
> > --- /dev/null
> > +++ b/drivers/nvdimm/virtio_pmem.c
> > @@ -0,0 +1,84 @@
> > +// SPDX-License-Identifier: GPL-2.0
> 
> Is this comment stile (//) acceptable?

In existing code, i can see same comment
pattern for license at some places.

> 
> > +/*
> > + * virtio_pmem.c: Virtio pmem Driver
> > + *
> > + * Discovers persistent memory range information
> > + * from host and provides a virtio based flushing
> > + * interface.
> > + */
> > +#include <linux/virtio_pmem.h>
> > +#include "nd.h"
> > +
> > + /* The interrupt handler */
> > +void host_ack(struct virtqueue *vq)
> > +{
> > +	unsigned int len;
> > +	unsigned long flags;
> > +	struct virtio_pmem_request *req, *req_buf;
> > +	struct virtio_pmem *vpmem = vq->vdev->priv;
> > +
> > +	spin_lock_irqsave(&vpmem->pmem_lock, flags);
> > +	while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
> > +		req->done = true;
> > +		wake_up(&req->host_acked);
> > +
> > +		if (!list_empty(&vpmem->req_list)) {
> > +			req_buf = list_first_entry(&vpmem->req_list,
> > +					struct virtio_pmem_request, list);
> > +			list_del(&vpmem->req_list);
> > +			req_buf->wq_buf_avail = true;
> > +			wake_up(&req_buf->wq_buf);
> > +		}
> > +	}
> > +	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> > +}
> > +EXPORT_SYMBOL_GPL(host_ack);
> > +
> > + /* The request submission function */
> > +int virtio_pmem_flush(struct nd_region *nd_region)
> > +{
> > +	int err;
> > +	unsigned long flags;
> > +	struct scatterlist *sgs[2], sg, ret;
> > +	struct virtio_device *vdev = nd_region->provider_data;
> > +	struct virtio_pmem *vpmem = vdev->priv;
> > +	struct virtio_pmem_request *req;
> > +
> > +	might_sleep();
> 
> [1]
> 
> > +	req = kmalloc(sizeof(*req), GFP_KERNEL);
> > +	if (!req)
> > +		return -ENOMEM;
> > +
> > +	req->done = req->wq_buf_avail = false;
> > +	strcpy(req->name, "FLUSH");
> > +	init_waitqueue_head(&req->host_acked);
> > +	init_waitqueue_head(&req->wq_buf);
> > +	sg_init_one(&sg, req->name, strlen(req->name));
> > +	sgs[0] = &sg;
> > +	sg_init_one(&ret, &req->ret, sizeof(req->ret));
> > +	sgs[1] = &ret;
> > +
> > +	spin_lock_irqsave(&vpmem->pmem_lock, flags);
> > +	err = virtqueue_add_sgs(vpmem->req_vq, sgs, 1, 1, req, GFP_ATOMIC);
> 
> Is it okay to use GFP_ATOMIC in a might-sleep ([1]) function?

might sleep will give us a warning if we try to sleep from non-sleepable
context. 

We are doing it other way, i.e might_sleep is not inside GFP_ATOMIC. 

> 
> > +	if (err) {
> > +		dev_err(&vdev->dev, "failed to send command to virtio pmem device\n");
> > +
> > +		list_add_tail(&vpmem->req_list, &req->list);
> > +		spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> > +
> > +		/* When host has read buffer, this completes via host_ack */
> > +		wait_event(req->wq_buf, req->wq_buf_avail);
> > +		spin_lock_irqsave(&vpmem->pmem_lock, flags);
> > +	}
> > +	virtqueue_kick(vpmem->req_vq);
> 
> You probably want to check return value here.

Don't think it will matter in this case?

> 
> > +	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> > +
> > +	/* When host has read buffer, this completes via host_ack */
> > +	wait_event(req->host_acked, req->done);
> > +	err = req->ret;
> > +	kfree(req);
> > +
> > +	return err;
> > +};
> > +EXPORT_SYMBOL_GPL(virtio_pmem_flush);
> > +MODULE_LICENSE("GPL");
> > diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> > index 35897649c24f..9f634a2ed638 100644
> > --- a/drivers/virtio/Kconfig
> > +++ b/drivers/virtio/Kconfig
> > @@ -42,6 +42,16 @@ config VIRTIO_PCI_LEGACY
> >  
> >  	  If unsure, say Y.
> >  
> > +config VIRTIO_PMEM
> > +	tristate "Support for virtio pmem driver"
> > +	depends on VIRTIO
> > +	depends on LIBNVDIMM
> > +	help
> > +	This driver provides support for virtio based flushing interface
> > +	for persistent memory range.
> > +
> > +	If unsure, say M.
> > +
> >  config VIRTIO_BALLOON
> >  	tristate "Virtio balloon driver"
> >  	depends on VIRTIO
> > diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
> > index 3a2b5c5dcf46..143ce91eabe9 100644
> > --- a/drivers/virtio/Makefile
> > +++ b/drivers/virtio/Makefile
> > @@ -6,3 +6,4 @@ virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
> >  virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
> >  obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
> >  obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
> > +obj-$(CONFIG_VIRTIO_PMEM) += pmem.o ../nvdimm/virtio_pmem.o
> > diff --git a/drivers/virtio/pmem.c b/drivers/virtio/pmem.c
> > new file mode 100644
> > index 000000000000..52f74064f67e
> > --- /dev/null
> > +++ b/drivers/virtio/pmem.c
> > @@ -0,0 +1,125 @@
> > +// SPDX-License-Identifier: GPL-2.0
> 
> Ditto
> 
> > +/*
> > + * virtio_pmem.c: Virtio pmem Driver
> > + *
> > + * Discovers persistent memory range information
> > + * from host and registers the virtual pmem device
> > + * with libnvdimm core.
> > + */
> > +#include <linux/virtio_pmem.h>
> > +#include <../../drivers/nvdimm/nd.h>
> 
> Should this file be moved to include/ directory?

We are not touching the directory structure of nd & nd_pmem
kernel driver.

> 
> > +
> > +static struct virtio_device_id id_table[] = {
> > +	{ VIRTIO_ID_PMEM, VIRTIO_DEV_ANY_ID },
> > +	{ 0 },
> > +};
> > +
> > + /* Initialize virt queue */
> > +static int init_vq(struct virtio_pmem *vpmem)
> > +{
> > +	struct virtqueue *vq;
> > +
> > +	/* single vq */
> > +	vpmem->req_vq = vq = virtio_find_single_vq(vpmem->vdev,
> > +				host_ack, "flush_queue");
> > +	if (IS_ERR(vq))
> > +		return PTR_ERR(vq);
> > +
> > +	spin_lock_init(&vpmem->pmem_lock);
> > +	INIT_LIST_HEAD(&vpmem->req_list);
> > +
> > +	return 0;
> > +};
> > +
> > +static int virtio_pmem_probe(struct virtio_device *vdev)
> > +{
> > +	int err = 0;
> > +	struct resource res;
> > +	struct virtio_pmem *vpmem;
> > +	struct nvdimm_bus *nvdimm_bus;
> > +	struct nd_region_desc ndr_desc;
> > +	int nid = dev_to_node(&vdev->dev);
> > +	struct nd_region *nd_region;
> > +
> > +	if (!vdev->config->get) {
> > +		dev_err(&vdev->dev, "%s failure: config disabled\n",
> > +			__func__);
> > +		return -EINVAL;
> > +	}
> > +
> > +	vdev->priv = vpmem = devm_kzalloc(&vdev->dev, sizeof(*vpmem),
> > +			GFP_KERNEL);
> 
> Suggesting to indent it right so it will be under &vdev

o.k

> 
> > +	if (!vpmem) {
> > +		err = -ENOMEM;
> > +		goto out_err;
> > +	}
> > +
> > +	vpmem->vdev = vdev;
> > +	err = init_vq(vpmem);
> > +	if (err)
> > +		goto out_err;
> 
> No need to free vpmem here?

No. devm_kzalloc will take care of it.

> 
> > +
> > +	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
> > +			start, &vpmem->start);
> > +	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
> > +			size, &vpmem->size);
> > +
> > +	res.start = vpmem->start;
> > +	res.end   = vpmem->start + vpmem->size-1;
> > +	vpmem->nd_desc.provider_name = "virtio-pmem";
> > +	vpmem->nd_desc.module = THIS_MODULE;
> > +
> > +	vpmem->nvdimm_bus = nvdimm_bus = nvdimm_bus_register(&vdev->dev,
> > +						&vpmem->nd_desc);
> > +	if (!nvdimm_bus)
> > +		goto out_vq;
> 
> Ditto (i'm probably missing something here)
> 
> > +
> > +	dev_set_drvdata(&vdev->dev, nvdimm_bus);
> > +	memset(&ndr_desc, 0, sizeof(ndr_desc));
> 
> Any reason not to use compiler initialization?
> i.e.
> 	struct nd_region_desc ndr_desc = {};

will change.

> 
> > +
> > +	ndr_desc.res = &res;
> > +	ndr_desc.numa_node = nid;
> > +	ndr_desc.flush = virtio_pmem_flush;
> > +	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
> > +	set_bit(ND_REGION_ASYNC, &ndr_desc.flags);
> > +	nd_region = nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc);
> > +	nd_region->provider_data =  dev_to_virtio
> > +					(nd_region->dev.parent->parent);
> > +
> > +	if (!nd_region)
> > +		goto out_nd;
> > +
> > +	//virtio_device_ready(vdev);
> 
> Left over

o.k

> 
> > +	return 0;
> > +out_nd:
> > +	err = -ENXIO;
> > +	nvdimm_bus_unregister(nvdimm_bus);
> > +out_vq:
> > +	vdev->config->del_vqs(vdev);
> > +out_err:
> > +	dev_err(&vdev->dev, "failed to register virtio pmem memory\n");
> > +	return err;
> > +}
> > +
> > +static void virtio_pmem_remove(struct virtio_device *vdev)
> > +{
> > +	struct virtio_pmem *vpmem = vdev->priv;
> > +	struct nvdimm_bus *nvdimm_bus = dev_get_drvdata(&vdev->dev);
> > +
> > +	nvdimm_bus_unregister(nvdimm_bus);
> > +	vdev->config->del_vqs(vdev);
> 
> I think you should also call vdev->config->reset

o.k. Here device will be removed completely, still its required?

> 
> > +	kfree(vpmem);
> > +}
> > +
> > +static struct virtio_driver virtio_pmem_driver = {
> > +	.driver.name		= KBUILD_MODNAME,
> > +	.driver.owner		= THIS_MODULE,
> > +	.id_table		= id_table,
> > +	.probe			= virtio_pmem_probe,
> > +	.remove			= virtio_pmem_remove,
> > +};
> > +
> > +module_virtio_driver(virtio_pmem_driver);
> > +MODULE_DEVICE_TABLE(virtio, id_table);
> > +MODULE_DESCRIPTION("Virtio pmem driver");
> > +MODULE_LICENSE("GPL");
> > diff --git a/include/linux/virtio_pmem.h b/include/linux/virtio_pmem.h
> > new file mode 100644
> > index 000000000000..224f9d934be6
> > --- /dev/null
> > +++ b/include/linux/virtio_pmem.h
> > @@ -0,0 +1,60 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +/*
> > + * virtio_pmem.h: virtio pmem Driver
> > + *
> > + * Discovers persistent memory range information
> > + * from host and provides a virtio based flushing
> > + * interface.
> > + **/
> > +
> > +#ifndef _LINUX_VIRTIO_PMEM_H
> > +#define _LINUX_VIRTIO_PMEM_H
> > +
> > +#include <linux/virtio_ids.h>
> > +#include <linux/module.h>
> > +#include <linux/virtio_config.h>
> > +#include <uapi/linux/virtio_pmem.h>
> > +#include <linux/libnvdimm.h>
> > +#include <linux/spinlock.h>
> > +
> > +struct virtio_pmem_request {
> > +	/* Host return status corresponding to flush request */
> > +	int ret;
> > +
> > +	/* command name*/
> > +	char name[16];
> > +
> > +	/* Wait queue to process deferred work after ack from host */
> > +	wait_queue_head_t host_acked;
> > +	bool done;
> > +
> > +	/* Wait queue to process deferred work after virt queue buffer avail */
> > +	wait_queue_head_t wq_buf;
> > +	bool wq_buf_avail;
> > +	struct list_head list;
> > +};
> > +
> > +struct virtio_pmem {
> > +	struct virtio_device *vdev;
> > +
> > +	/* Virtio pmem request queue */
> > +	struct virtqueue *req_vq;
> > +
> > +	/* nvdimm bus registers virtio pmem device */
> > +	struct nvdimm_bus *nvdimm_bus;
> > +	struct nvdimm_bus_descriptor nd_desc;
> > +
> > +	/* List to store deferred work if virtqueue is full */
> > +	struct list_head req_list;
> > +
> > +	/* Synchronize virtqueue data */
> > +	spinlock_t pmem_lock;
> > +
> > +	/* Memory region information */
> > +	uint64_t start;
> > +	uint64_t size;
> > +};
> > +
> > +void host_ack(struct virtqueue *vq);
> > +int virtio_pmem_flush(struct nd_region *nd_region);
> > +#endif
> > diff --git a/include/uapi/linux/virtio_ids.h
> > b/include/uapi/linux/virtio_ids.h
> > index 6d5c3b2d4f4d..346389565ac1 100644
> > --- a/include/uapi/linux/virtio_ids.h
> > +++ b/include/uapi/linux/virtio_ids.h
> > @@ -43,5 +43,6 @@
> >  #define VIRTIO_ID_INPUT        18 /* virtio input */
> >  #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
> >  #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
> > +#define VIRTIO_ID_PMEM         25 /* virtio pmem */
> 
> Any reason for the jump here? are 21 to 24 already taken or you just
> want to be on the safe side?

They are already reserved.

Thanks,
Pankaj

> 
> >  
> >  #endif /* _LINUX_VIRTIO_IDS_H */
> > diff --git a/include/uapi/linux/virtio_pmem.h
> > b/include/uapi/linux/virtio_pmem.h
> > new file mode 100644
> > index 000000000000..fa3f7d52717a
> > --- /dev/null
> > +++ b/include/uapi/linux/virtio_pmem.h
> > @@ -0,0 +1,10 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +
> > +#ifndef _UAPI_LINUX_VIRTIO_PMEM_H
> > +#define _UAPI_LINUX_VIRTIO_PMEM_H
> > +
> > +struct virtio_pmem_config {
> > +	__le64 start;
> > +	__le64 size;
> > +};
> > +#endif
> > --
> > 2.20.1
> > 
> > 
> 
>
Yuval Shaia April 4, 2019, 6:40 a.m. UTC | #3
On Wed, Apr 03, 2019 at 08:40:13AM -0400, Pankaj Gupta wrote:
> 
> > Subject: Re: [Qemu-devel] [PATCH v4 2/5] virtio-pmem: Add virtio pmem driver
> > 
> > On Wed, Apr 03, 2019 at 04:10:15PM +0530, Pankaj Gupta wrote:
> > > This patch adds virtio-pmem driver for KVM guest.
> > > 
> > > Guest reads the persistent memory range information from
> > > Qemu over VIRTIO and registers it on nvdimm_bus. It also
> > > creates a nd_region object with the persistent memory
> > > range information so that existing 'nvdimm/pmem' driver
> > > can reserve this into system memory map. This way
> > > 'virtio-pmem' driver uses existing functionality of pmem
> > > driver to register persistent memory compatible for DAX
> > > capable filesystems.
> > > 
> > > This also provides function to perform guest flush over
> > > VIRTIO from 'pmem' driver when userspace performs flush
> > > on DAX memory range.
> > > 
> > > Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
> > > ---
> > >  drivers/nvdimm/virtio_pmem.c     |  84 +++++++++++++++++++++
> > >  drivers/virtio/Kconfig           |  10 +++
> > >  drivers/virtio/Makefile          |   1 +
> > >  drivers/virtio/pmem.c            | 125 +++++++++++++++++++++++++++++++
> > >  include/linux/virtio_pmem.h      |  60 +++++++++++++++
> > >  include/uapi/linux/virtio_ids.h  |   1 +
> > >  include/uapi/linux/virtio_pmem.h |  10 +++
> > >  7 files changed, 291 insertions(+)
> > >  create mode 100644 drivers/nvdimm/virtio_pmem.c
> > >  create mode 100644 drivers/virtio/pmem.c
> > >  create mode 100644 include/linux/virtio_pmem.h
> > >  create mode 100644 include/uapi/linux/virtio_pmem.h
> > > 
> > > diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
> > > new file mode 100644
> > > index 000000000000..2a1b1ba2c1ff
> > > --- /dev/null
> > > +++ b/drivers/nvdimm/virtio_pmem.c
> > > @@ -0,0 +1,84 @@
> > > +// SPDX-License-Identifier: GPL-2.0
> > 
> > Is this comment stile (//) acceptable?
> 
> In existing code, i can see same comment
> pattern for license at some places.

Is it preferred for new code?

> 
> > 
> > > +/*
> > > + * virtio_pmem.c: Virtio pmem Driver
> > > + *
> > > + * Discovers persistent memory range information
> > > + * from host and provides a virtio based flushing
> > > + * interface.
> > > + */
> > > +#include <linux/virtio_pmem.h>
> > > +#include "nd.h"
> > > +
> > > + /* The interrupt handler */
> > > +void host_ack(struct virtqueue *vq)
> > > +{
> > > +	unsigned int len;
> > > +	unsigned long flags;
> > > +	struct virtio_pmem_request *req, *req_buf;
> > > +	struct virtio_pmem *vpmem = vq->vdev->priv;
> > > +
> > > +	spin_lock_irqsave(&vpmem->pmem_lock, flags);
> > > +	while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
> > > +		req->done = true;
> > > +		wake_up(&req->host_acked);
> > > +
> > > +		if (!list_empty(&vpmem->req_list)) {
> > > +			req_buf = list_first_entry(&vpmem->req_list,
> > > +					struct virtio_pmem_request, list);
> > > +			list_del(&vpmem->req_list);
> > > +			req_buf->wq_buf_avail = true;
> > > +			wake_up(&req_buf->wq_buf);
> > > +		}
> > > +	}
> > > +	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> > > +}
> > > +EXPORT_SYMBOL_GPL(host_ack);
> > > +
> > > + /* The request submission function */
> > > +int virtio_pmem_flush(struct nd_region *nd_region)
> > > +{
> > > +	int err;
> > > +	unsigned long flags;
> > > +	struct scatterlist *sgs[2], sg, ret;
> > > +	struct virtio_device *vdev = nd_region->provider_data;
> > > +	struct virtio_pmem *vpmem = vdev->priv;
> > > +	struct virtio_pmem_request *req;
> > > +
> > > +	might_sleep();
> > 
> > [1]
> > 
> > > +	req = kmalloc(sizeof(*req), GFP_KERNEL);
> > > +	if (!req)
> > > +		return -ENOMEM;
> > > +
> > > +	req->done = req->wq_buf_avail = false;
> > > +	strcpy(req->name, "FLUSH");
> > > +	init_waitqueue_head(&req->host_acked);
> > > +	init_waitqueue_head(&req->wq_buf);
> > > +	sg_init_one(&sg, req->name, strlen(req->name));
> > > +	sgs[0] = &sg;
> > > +	sg_init_one(&ret, &req->ret, sizeof(req->ret));
> > > +	sgs[1] = &ret;
> > > +
> > > +	spin_lock_irqsave(&vpmem->pmem_lock, flags);
> > > +	err = virtqueue_add_sgs(vpmem->req_vq, sgs, 1, 1, req, GFP_ATOMIC);
> > 
> > Is it okay to use GFP_ATOMIC in a might-sleep ([1]) function?
> 
> might sleep will give us a warning if we try to sleep from non-sleepable
> context. 
> 
> We are doing it other way, i.e might_sleep is not inside GFP_ATOMIC. 
> 
> > 
> > > +	if (err) {
> > > +		dev_err(&vdev->dev, "failed to send command to virtio pmem device\n");
> > > +
> > > +		list_add_tail(&vpmem->req_list, &req->list);
> > > +		spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> > > +
> > > +		/* When host has read buffer, this completes via host_ack */
> > > +		wait_event(req->wq_buf, req->wq_buf_avail);
> > > +		spin_lock_irqsave(&vpmem->pmem_lock, flags);
> > > +	}
> > > +	virtqueue_kick(vpmem->req_vq);
> > 
> > You probably want to check return value here.
> 
> Don't think it will matter in this case?

Have no idea, if it fails maybe you will never get to host_acked.

> 
> > 
> > > +	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> > > +
> > > +	/* When host has read buffer, this completes via host_ack */
> > > +	wait_event(req->host_acked, req->done);
> > > +	err = req->ret;
> > > +	kfree(req);
> > > +
> > > +	return err;
> > > +};
> > > +EXPORT_SYMBOL_GPL(virtio_pmem_flush);
> > > +MODULE_LICENSE("GPL");
> > > diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> > > index 35897649c24f..9f634a2ed638 100644
> > > --- a/drivers/virtio/Kconfig
> > > +++ b/drivers/virtio/Kconfig
> > > @@ -42,6 +42,16 @@ config VIRTIO_PCI_LEGACY
> > >  
> > >  	  If unsure, say Y.
> > >  
> > > +config VIRTIO_PMEM
> > > +	tristate "Support for virtio pmem driver"
> > > +	depends on VIRTIO
> > > +	depends on LIBNVDIMM
> > > +	help
> > > +	This driver provides support for virtio based flushing interface
> > > +	for persistent memory range.
> > > +
> > > +	If unsure, say M.
> > > +
> > >  config VIRTIO_BALLOON
> > >  	tristate "Virtio balloon driver"
> > >  	depends on VIRTIO
> > > diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
> > > index 3a2b5c5dcf46..143ce91eabe9 100644
> > > --- a/drivers/virtio/Makefile
> > > +++ b/drivers/virtio/Makefile
> > > @@ -6,3 +6,4 @@ virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
> > >  virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
> > >  obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
> > >  obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
> > > +obj-$(CONFIG_VIRTIO_PMEM) += pmem.o ../nvdimm/virtio_pmem.o
> > > diff --git a/drivers/virtio/pmem.c b/drivers/virtio/pmem.c
> > > new file mode 100644
> > > index 000000000000..52f74064f67e
> > > --- /dev/null
> > > +++ b/drivers/virtio/pmem.c
> > > @@ -0,0 +1,125 @@
> > > +// SPDX-License-Identifier: GPL-2.0
> > 
> > Ditto
> > 
> > > +/*
> > > + * virtio_pmem.c: Virtio pmem Driver
> > > + *
> > > + * Discovers persistent memory range information
> > > + * from host and registers the virtual pmem device
> > > + * with libnvdimm core.
> > > + */
> > > +#include <linux/virtio_pmem.h>
> > > +#include <../../drivers/nvdimm/nd.h>
> > 
> > Should this file be moved to include/ directory?
> 
> We are not touching the directory structure of nd & nd_pmem
> kernel driver.

But since this file becomes public it should be considered, right?

> 
> > 
> > > +
> > > +static struct virtio_device_id id_table[] = {
> > > +	{ VIRTIO_ID_PMEM, VIRTIO_DEV_ANY_ID },
> > > +	{ 0 },
> > > +};
> > > +
> > > + /* Initialize virt queue */
> > > +static int init_vq(struct virtio_pmem *vpmem)
> > > +{
> > > +	struct virtqueue *vq;
> > > +
> > > +	/* single vq */
> > > +	vpmem->req_vq = vq = virtio_find_single_vq(vpmem->vdev,
> > > +				host_ack, "flush_queue");
> > > +	if (IS_ERR(vq))
> > > +		return PTR_ERR(vq);
> > > +
> > > +	spin_lock_init(&vpmem->pmem_lock);
> > > +	INIT_LIST_HEAD(&vpmem->req_list);
> > > +
> > > +	return 0;
> > > +};
> > > +
> > > +static int virtio_pmem_probe(struct virtio_device *vdev)
> > > +{
> > > +	int err = 0;
> > > +	struct resource res;
> > > +	struct virtio_pmem *vpmem;
> > > +	struct nvdimm_bus *nvdimm_bus;
> > > +	struct nd_region_desc ndr_desc;
> > > +	int nid = dev_to_node(&vdev->dev);
> > > +	struct nd_region *nd_region;
> > > +
> > > +	if (!vdev->config->get) {
> > > +		dev_err(&vdev->dev, "%s failure: config disabled\n",
> > > +			__func__);
> > > +		return -EINVAL;
> > > +	}
> > > +
> > > +	vdev->priv = vpmem = devm_kzalloc(&vdev->dev, sizeof(*vpmem),
> > > +			GFP_KERNEL);
> > 
> > Suggesting to indent it right so it will be under &vdev
> 
> o.k
> 
> > 
> > > +	if (!vpmem) {
> > > +		err = -ENOMEM;
> > > +		goto out_err;
> > > +	}
> > > +
> > > +	vpmem->vdev = vdev;
> > > +	err = init_vq(vpmem);
> > > +	if (err)
> > > +		goto out_err;
> > 
> > No need to free vpmem here?
> 
> No. devm_kzalloc will take care of it.

Nice.

> 
> > 
> > > +
> > > +	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
> > > +			start, &vpmem->start);
> > > +	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
> > > +			size, &vpmem->size);
> > > +
> > > +	res.start = vpmem->start;
> > > +	res.end   = vpmem->start + vpmem->size-1;
> > > +	vpmem->nd_desc.provider_name = "virtio-pmem";
> > > +	vpmem->nd_desc.module = THIS_MODULE;
> > > +
> > > +	vpmem->nvdimm_bus = nvdimm_bus = nvdimm_bus_register(&vdev->dev,
> > > +						&vpmem->nd_desc);
> > > +	if (!nvdimm_bus)
> > > +		goto out_vq;
> > 
> > Ditto (i'm probably missing something here)
> > 
> > > +
> > > +	dev_set_drvdata(&vdev->dev, nvdimm_bus);
> > > +	memset(&ndr_desc, 0, sizeof(ndr_desc));
> > 
> > Any reason not to use compiler initialization?
> > i.e.
> > 	struct nd_region_desc ndr_desc = {};
> 
> will change.
> 
> > 
> > > +
> > > +	ndr_desc.res = &res;
> > > +	ndr_desc.numa_node = nid;
> > > +	ndr_desc.flush = virtio_pmem_flush;
> > > +	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
> > > +	set_bit(ND_REGION_ASYNC, &ndr_desc.flags);
> > > +	nd_region = nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc);
> > > +	nd_region->provider_data =  dev_to_virtio
> > > +					(nd_region->dev.parent->parent);
> > > +
> > > +	if (!nd_region)
> > > +		goto out_nd;
> > > +
> > > +	//virtio_device_ready(vdev);
> > 
> > Left over
> 
> o.k
> 
> > 
> > > +	return 0;
> > > +out_nd:
> > > +	err = -ENXIO;
> > > +	nvdimm_bus_unregister(nvdimm_bus);
> > > +out_vq:
> > > +	vdev->config->del_vqs(vdev);
> > > +out_err:
> > > +	dev_err(&vdev->dev, "failed to register virtio pmem memory\n");
> > > +	return err;
> > > +}
> > > +
> > > +static void virtio_pmem_remove(struct virtio_device *vdev)
> > > +{
> > > +	struct virtio_pmem *vpmem = vdev->priv;
> > > +	struct nvdimm_bus *nvdimm_bus = dev_get_drvdata(&vdev->dev);
> > > +
> > > +	nvdimm_bus_unregister(nvdimm_bus);
> > > +	vdev->config->del_vqs(vdev);
> > 
> > I think you should also call vdev->config->reset
> 
> o.k. Here device will be removed completely, still its required?

I had a bad experience with unloading virtio PCI driver and it gone after i
added call to 'reset'.
See the warning in function virtio_dev_remove.

> 
> > 
> > > +	kfree(vpmem);
> > > +}
> > > +
> > > +static struct virtio_driver virtio_pmem_driver = {
> > > +	.driver.name		= KBUILD_MODNAME,
> > > +	.driver.owner		= THIS_MODULE,
> > > +	.id_table		= id_table,
> > > +	.probe			= virtio_pmem_probe,
> > > +	.remove			= virtio_pmem_remove,
> > > +};
> > > +
> > > +module_virtio_driver(virtio_pmem_driver);
> > > +MODULE_DEVICE_TABLE(virtio, id_table);
> > > +MODULE_DESCRIPTION("Virtio pmem driver");
> > > +MODULE_LICENSE("GPL");
> > > diff --git a/include/linux/virtio_pmem.h b/include/linux/virtio_pmem.h
> > > new file mode 100644
> > > index 000000000000..224f9d934be6
> > > --- /dev/null
> > > +++ b/include/linux/virtio_pmem.h
> > > @@ -0,0 +1,60 @@
> > > +/* SPDX-License-Identifier: GPL-2.0 */
> > > +/*
> > > + * virtio_pmem.h: virtio pmem Driver
> > > + *
> > > + * Discovers persistent memory range information
> > > + * from host and provides a virtio based flushing
> > > + * interface.
> > > + **/
> > > +
> > > +#ifndef _LINUX_VIRTIO_PMEM_H
> > > +#define _LINUX_VIRTIO_PMEM_H
> > > +
> > > +#include <linux/virtio_ids.h>
> > > +#include <linux/module.h>
> > > +#include <linux/virtio_config.h>
> > > +#include <uapi/linux/virtio_pmem.h>
> > > +#include <linux/libnvdimm.h>
> > > +#include <linux/spinlock.h>
> > > +
> > > +struct virtio_pmem_request {
> > > +	/* Host return status corresponding to flush request */
> > > +	int ret;
> > > +
> > > +	/* command name*/
> > > +	char name[16];
> > > +
> > > +	/* Wait queue to process deferred work after ack from host */
> > > +	wait_queue_head_t host_acked;
> > > +	bool done;
> > > +
> > > +	/* Wait queue to process deferred work after virt queue buffer avail */
> > > +	wait_queue_head_t wq_buf;
> > > +	bool wq_buf_avail;
> > > +	struct list_head list;
> > > +};
> > > +
> > > +struct virtio_pmem {
> > > +	struct virtio_device *vdev;
> > > +
> > > +	/* Virtio pmem request queue */
> > > +	struct virtqueue *req_vq;
> > > +
> > > +	/* nvdimm bus registers virtio pmem device */
> > > +	struct nvdimm_bus *nvdimm_bus;
> > > +	struct nvdimm_bus_descriptor nd_desc;
> > > +
> > > +	/* List to store deferred work if virtqueue is full */
> > > +	struct list_head req_list;
> > > +
> > > +	/* Synchronize virtqueue data */
> > > +	spinlock_t pmem_lock;
> > > +
> > > +	/* Memory region information */
> > > +	uint64_t start;
> > > +	uint64_t size;
> > > +};
> > > +
> > > +void host_ack(struct virtqueue *vq);
> > > +int virtio_pmem_flush(struct nd_region *nd_region);
> > > +#endif
> > > diff --git a/include/uapi/linux/virtio_ids.h
> > > b/include/uapi/linux/virtio_ids.h
> > > index 6d5c3b2d4f4d..346389565ac1 100644
> > > --- a/include/uapi/linux/virtio_ids.h
> > > +++ b/include/uapi/linux/virtio_ids.h
> > > @@ -43,5 +43,6 @@
> > >  #define VIRTIO_ID_INPUT        18 /* virtio input */
> > >  #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
> > >  #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
> > > +#define VIRTIO_ID_PMEM         25 /* virtio pmem */
> > 
> > Any reason for the jump here? are 21 to 24 already taken or you just
> > want to be on the safe side?
> 
> They are already reserved.

Can you direct me to how to find a free ID?

> 
> Thanks,
> Pankaj
> 
> > 
> > >  
> > >  #endif /* _LINUX_VIRTIO_IDS_H */
> > > diff --git a/include/uapi/linux/virtio_pmem.h
> > > b/include/uapi/linux/virtio_pmem.h
> > > new file mode 100644
> > > index 000000000000..fa3f7d52717a
> > > --- /dev/null
> > > +++ b/include/uapi/linux/virtio_pmem.h
> > > @@ -0,0 +1,10 @@
> > > +/* SPDX-License-Identifier: GPL-2.0 */
> > > +
> > > +#ifndef _UAPI_LINUX_VIRTIO_PMEM_H
> > > +#define _UAPI_LINUX_VIRTIO_PMEM_H
> > > +
> > > +struct virtio_pmem_config {
> > > +	__le64 start;
> > > +	__le64 size;
> > > +};
> > > +#endif
> > > --
> > > 2.20.1
> > > 
> > > 
> > 
> >
Pankaj Gupta April 4, 2019, 7:14 a.m. UTC | #4
> > 
> > > Subject: Re: [Qemu-devel] [PATCH v4 2/5] virtio-pmem: Add virtio pmem
> > > driver
> > > 
> > > On Wed, Apr 03, 2019 at 04:10:15PM +0530, Pankaj Gupta wrote:
> > > > This patch adds virtio-pmem driver for KVM guest.
> > > > 
> > > > Guest reads the persistent memory range information from
> > > > Qemu over VIRTIO and registers it on nvdimm_bus. It also
> > > > creates a nd_region object with the persistent memory
> > > > range information so that existing 'nvdimm/pmem' driver
> > > > can reserve this into system memory map. This way
> > > > 'virtio-pmem' driver uses existing functionality of pmem
> > > > driver to register persistent memory compatible for DAX
> > > > capable filesystems.
> > > > 
> > > > This also provides function to perform guest flush over
> > > > VIRTIO from 'pmem' driver when userspace performs flush
> > > > on DAX memory range.
> > > > 
> > > > Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
> > > > ---
> > > >  drivers/nvdimm/virtio_pmem.c     |  84 +++++++++++++++++++++
> > > >  drivers/virtio/Kconfig           |  10 +++
> > > >  drivers/virtio/Makefile          |   1 +
> > > >  drivers/virtio/pmem.c            | 125 +++++++++++++++++++++++++++++++
> > > >  include/linux/virtio_pmem.h      |  60 +++++++++++++++
> > > >  include/uapi/linux/virtio_ids.h  |   1 +
> > > >  include/uapi/linux/virtio_pmem.h |  10 +++
> > > >  7 files changed, 291 insertions(+)
> > > >  create mode 100644 drivers/nvdimm/virtio_pmem.c
> > > >  create mode 100644 drivers/virtio/pmem.c
> > > >  create mode 100644 include/linux/virtio_pmem.h
> > > >  create mode 100644 include/uapi/linux/virtio_pmem.h
> > > > 
> > > > diff --git a/drivers/nvdimm/virtio_pmem.c
> > > > b/drivers/nvdimm/virtio_pmem.c
> > > > new file mode 100644
> > > > index 000000000000..2a1b1ba2c1ff
> > > > --- /dev/null
> > > > +++ b/drivers/nvdimm/virtio_pmem.c
> > > > @@ -0,0 +1,84 @@
> > > > +// SPDX-License-Identifier: GPL-2.0
> > > 
> > > Is this comment stile (//) acceptable?
> > 
> > In existing code, i can see same comment
> > pattern for license at some places.
> 
> Is it preferred for new code?

will change.

> 
> > 
> > > 
> > > > +/*
> > > > + * virtio_pmem.c: Virtio pmem Driver
> > > > + *
> > > > + * Discovers persistent memory range information
> > > > + * from host and provides a virtio based flushing
> > > > + * interface.
> > > > + */
> > > > +#include <linux/virtio_pmem.h>
> > > > +#include "nd.h"
> > > > +
> > > > + /* The interrupt handler */
> > > > +void host_ack(struct virtqueue *vq)
> > > > +{
> > > > +	unsigned int len;
> > > > +	unsigned long flags;
> > > > +	struct virtio_pmem_request *req, *req_buf;
> > > > +	struct virtio_pmem *vpmem = vq->vdev->priv;
> > > > +
> > > > +	spin_lock_irqsave(&vpmem->pmem_lock, flags);
> > > > +	while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
> > > > +		req->done = true;
> > > > +		wake_up(&req->host_acked);
> > > > +
> > > > +		if (!list_empty(&vpmem->req_list)) {
> > > > +			req_buf = list_first_entry(&vpmem->req_list,
> > > > +					struct virtio_pmem_request, list);
> > > > +			list_del(&vpmem->req_list);
> > > > +			req_buf->wq_buf_avail = true;
> > > > +			wake_up(&req_buf->wq_buf);
> > > > +		}
> > > > +	}
> > > > +	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> > > > +}
> > > > +EXPORT_SYMBOL_GPL(host_ack);
> > > > +
> > > > + /* The request submission function */
> > > > +int virtio_pmem_flush(struct nd_region *nd_region)
> > > > +{
> > > > +	int err;
> > > > +	unsigned long flags;
> > > > +	struct scatterlist *sgs[2], sg, ret;
> > > > +	struct virtio_device *vdev = nd_region->provider_data;
> > > > +	struct virtio_pmem *vpmem = vdev->priv;
> > > > +	struct virtio_pmem_request *req;
> > > > +
> > > > +	might_sleep();
> > > 
> > > [1]
> > > 
> > > > +	req = kmalloc(sizeof(*req), GFP_KERNEL);
> > > > +	if (!req)
> > > > +		return -ENOMEM;
> > > > +
> > > > +	req->done = req->wq_buf_avail = false;
> > > > +	strcpy(req->name, "FLUSH");
> > > > +	init_waitqueue_head(&req->host_acked);
> > > > +	init_waitqueue_head(&req->wq_buf);
> > > > +	sg_init_one(&sg, req->name, strlen(req->name));
> > > > +	sgs[0] = &sg;
> > > > +	sg_init_one(&ret, &req->ret, sizeof(req->ret));
> > > > +	sgs[1] = &ret;
> > > > +
> > > > +	spin_lock_irqsave(&vpmem->pmem_lock, flags);
> > > > +	err = virtqueue_add_sgs(vpmem->req_vq, sgs, 1, 1, req, GFP_ATOMIC);
> > > 
> > > Is it okay to use GFP_ATOMIC in a might-sleep ([1]) function?
> > 
> > might sleep will give us a warning if we try to sleep from non-sleepable
> > context.
> > 
> > We are doing it other way, i.e might_sleep is not inside GFP_ATOMIC.
> > 
> > > 
> > > > +	if (err) {
> > > > +		dev_err(&vdev->dev, "failed to send command to virtio pmem
> > > > device\n");
> > > > +
> > > > +		list_add_tail(&vpmem->req_list, &req->list);
> > > > +		spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> > > > +
> > > > +		/* When host has read buffer, this completes via host_ack */
> > > > +		wait_event(req->wq_buf, req->wq_buf_avail);
> > > > +		spin_lock_irqsave(&vpmem->pmem_lock, flags);
> > > > +	}
> > > > +	virtqueue_kick(vpmem->req_vq);
> > > 
> > > You probably want to check return value here.
> > 
> > Don't think it will matter in this case?
> 
> Have no idea, if it fails maybe you will never get to host_acked.

I am not sure about this. Surely will check.

> 
> > 
> > > 
> > > > +	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
> > > > +
> > > > +	/* When host has read buffer, this completes via host_ack */
> > > > +	wait_event(req->host_acked, req->done);
> > > > +	err = req->ret;
> > > > +	kfree(req);
> > > > +
> > > > +	return err;
> > > > +};
> > > > +EXPORT_SYMBOL_GPL(virtio_pmem_flush);
> > > > +MODULE_LICENSE("GPL");
> > > > diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> > > > index 35897649c24f..9f634a2ed638 100644
> > > > --- a/drivers/virtio/Kconfig
> > > > +++ b/drivers/virtio/Kconfig
> > > > @@ -42,6 +42,16 @@ config VIRTIO_PCI_LEGACY
> > > >  
> > > >  	  If unsure, say Y.
> > > >  
> > > > +config VIRTIO_PMEM
> > > > +	tristate "Support for virtio pmem driver"
> > > > +	depends on VIRTIO
> > > > +	depends on LIBNVDIMM
> > > > +	help
> > > > +	This driver provides support for virtio based flushing interface
> > > > +	for persistent memory range.
> > > > +
> > > > +	If unsure, say M.
> > > > +
> > > >  config VIRTIO_BALLOON
> > > >  	tristate "Virtio balloon driver"
> > > >  	depends on VIRTIO
> > > > diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
> > > > index 3a2b5c5dcf46..143ce91eabe9 100644
> > > > --- a/drivers/virtio/Makefile
> > > > +++ b/drivers/virtio/Makefile
> > > > @@ -6,3 +6,4 @@ virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
> > > >  virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
> > > >  obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
> > > >  obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
> > > > +obj-$(CONFIG_VIRTIO_PMEM) += pmem.o ../nvdimm/virtio_pmem.o
> > > > diff --git a/drivers/virtio/pmem.c b/drivers/virtio/pmem.c
> > > > new file mode 100644
> > > > index 000000000000..52f74064f67e
> > > > --- /dev/null
> > > > +++ b/drivers/virtio/pmem.c
> > > > @@ -0,0 +1,125 @@
> > > > +// SPDX-License-Identifier: GPL-2.0
> > > 
> > > Ditto
> > > 
> > > > +/*
> > > > + * virtio_pmem.c: Virtio pmem Driver
> > > > + *
> > > > + * Discovers persistent memory range information
> > > > + * from host and registers the virtual pmem device
> > > > + * with libnvdimm core.
> > > > + */
> > > > +#include <linux/virtio_pmem.h>
> > > > +#include <../../drivers/nvdimm/nd.h>
> > > 
> > > Should this file be moved to include/ directory?
> > 
> > We are not touching the directory structure of nd & nd_pmem
> > kernel driver.
> 
> But since this file becomes public it should be considered, right?

IIRC I tried to do it but that required changes in existing pmem code 
directory structure for conflict resolution. I would suggest to keep
the directory structure as it is currently and submit a followup 
patch to do this after current code is merged upstream.   

> 
> > 
> > > 
> > > > +
> > > > +static struct virtio_device_id id_table[] = {
> > > > +	{ VIRTIO_ID_PMEM, VIRTIO_DEV_ANY_ID },
> > > > +	{ 0 },
> > > > +};
> > > > +
> > > > + /* Initialize virt queue */
> > > > +static int init_vq(struct virtio_pmem *vpmem)
> > > > +{
> > > > +	struct virtqueue *vq;
> > > > +
> > > > +	/* single vq */
> > > > +	vpmem->req_vq = vq = virtio_find_single_vq(vpmem->vdev,
> > > > +				host_ack, "flush_queue");
> > > > +	if (IS_ERR(vq))
> > > > +		return PTR_ERR(vq);
> > > > +
> > > > +	spin_lock_init(&vpmem->pmem_lock);
> > > > +	INIT_LIST_HEAD(&vpmem->req_list);
> > > > +
> > > > +	return 0;
> > > > +};
> > > > +
> > > > +static int virtio_pmem_probe(struct virtio_device *vdev)
> > > > +{
> > > > +	int err = 0;
> > > > +	struct resource res;
> > > > +	struct virtio_pmem *vpmem;
> > > > +	struct nvdimm_bus *nvdimm_bus;
> > > > +	struct nd_region_desc ndr_desc;
> > > > +	int nid = dev_to_node(&vdev->dev);
> > > > +	struct nd_region *nd_region;
> > > > +
> > > > +	if (!vdev->config->get) {
> > > > +		dev_err(&vdev->dev, "%s failure: config disabled\n",
> > > > +			__func__);
> > > > +		return -EINVAL;
> > > > +	}
> > > > +
> > > > +	vdev->priv = vpmem = devm_kzalloc(&vdev->dev, sizeof(*vpmem),
> > > > +			GFP_KERNEL);
> > > 
> > > Suggesting to indent it right so it will be under &vdev
> > 
> > o.k
> > 
> > > 
> > > > +	if (!vpmem) {
> > > > +		err = -ENOMEM;
> > > > +		goto out_err;
> > > > +	}
> > > > +
> > > > +	vpmem->vdev = vdev;
> > > > +	err = init_vq(vpmem);
> > > > +	if (err)
> > > > +		goto out_err;
> > > 
> > > No need to free vpmem here?
> > 
> > No. devm_kzalloc will take care of it.
> 
> Nice.
> 
> > 
> > > 
> > > > +
> > > > +	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
> > > > +			start, &vpmem->start);
> > > > +	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
> > > > +			size, &vpmem->size);
> > > > +
> > > > +	res.start = vpmem->start;
> > > > +	res.end   = vpmem->start + vpmem->size-1;
> > > > +	vpmem->nd_desc.provider_name = "virtio-pmem";
> > > > +	vpmem->nd_desc.module = THIS_MODULE;
> > > > +
> > > > +	vpmem->nvdimm_bus = nvdimm_bus = nvdimm_bus_register(&vdev->dev,
> > > > +						&vpmem->nd_desc);
> > > > +	if (!nvdimm_bus)
> > > > +		goto out_vq;
> > > 
> > > Ditto (i'm probably missing something here)
> > > 
> > > > +
> > > > +	dev_set_drvdata(&vdev->dev, nvdimm_bus);
> > > > +	memset(&ndr_desc, 0, sizeof(ndr_desc));
> > > 
> > > Any reason not to use compiler initialization?
> > > i.e.
> > > 	struct nd_region_desc ndr_desc = {};
> > 
> > will change.
> > 
> > > 
> > > > +
> > > > +	ndr_desc.res = &res;
> > > > +	ndr_desc.numa_node = nid;
> > > > +	ndr_desc.flush = virtio_pmem_flush;
> > > > +	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
> > > > +	set_bit(ND_REGION_ASYNC, &ndr_desc.flags);
> > > > +	nd_region = nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc);
> > > > +	nd_region->provider_data =  dev_to_virtio
> > > > +					(nd_region->dev.parent->parent);
> > > > +
> > > > +	if (!nd_region)
> > > > +		goto out_nd;
> > > > +
> > > > +	//virtio_device_ready(vdev);
> > > 
> > > Left over
> > 
> > o.k
> > 
> > > 
> > > > +	return 0;
> > > > +out_nd:
> > > > +	err = -ENXIO;
> > > > +	nvdimm_bus_unregister(nvdimm_bus);
> > > > +out_vq:
> > > > +	vdev->config->del_vqs(vdev);
> > > > +out_err:
> > > > +	dev_err(&vdev->dev, "failed to register virtio pmem memory\n");
> > > > +	return err;
> > > > +}
> > > > +
> > > > +static void virtio_pmem_remove(struct virtio_device *vdev)
> > > > +{
> > > > +	struct virtio_pmem *vpmem = vdev->priv;
> > > > +	struct nvdimm_bus *nvdimm_bus = dev_get_drvdata(&vdev->dev);
> > > > +
> > > > +	nvdimm_bus_unregister(nvdimm_bus);
> > > > +	vdev->config->del_vqs(vdev);
> > > 
> > > I think you should also call vdev->config->reset
> > 
> > o.k. Here device will be removed completely, still its required?
> 
> I had a bad experience with unloading virtio PCI driver and it gone after i
> added call to 'reset'.
> See the warning in function virtio_dev_remove.

Fair point. I will add call to vdev->config->reset.

> 
> > 
> > > 
> > > > +	kfree(vpmem);
> > > > +}
> > > > +
> > > > +static struct virtio_driver virtio_pmem_driver = {
> > > > +	.driver.name		= KBUILD_MODNAME,
> > > > +	.driver.owner		= THIS_MODULE,
> > > > +	.id_table		= id_table,
> > > > +	.probe			= virtio_pmem_probe,
> > > > +	.remove			= virtio_pmem_remove,
> > > > +};
> > > > +
> > > > +module_virtio_driver(virtio_pmem_driver);
> > > > +MODULE_DEVICE_TABLE(virtio, id_table);
> > > > +MODULE_DESCRIPTION("Virtio pmem driver");
> > > > +MODULE_LICENSE("GPL");
> > > > diff --git a/include/linux/virtio_pmem.h b/include/linux/virtio_pmem.h
> > > > new file mode 100644
> > > > index 000000000000..224f9d934be6
> > > > --- /dev/null
> > > > +++ b/include/linux/virtio_pmem.h
> > > > @@ -0,0 +1,60 @@
> > > > +/* SPDX-License-Identifier: GPL-2.0 */
> > > > +/*
> > > > + * virtio_pmem.h: virtio pmem Driver
> > > > + *
> > > > + * Discovers persistent memory range information
> > > > + * from host and provides a virtio based flushing
> > > > + * interface.
> > > > + **/
> > > > +
> > > > +#ifndef _LINUX_VIRTIO_PMEM_H
> > > > +#define _LINUX_VIRTIO_PMEM_H
> > > > +
> > > > +#include <linux/virtio_ids.h>
> > > > +#include <linux/module.h>
> > > > +#include <linux/virtio_config.h>
> > > > +#include <uapi/linux/virtio_pmem.h>
> > > > +#include <linux/libnvdimm.h>
> > > > +#include <linux/spinlock.h>
> > > > +
> > > > +struct virtio_pmem_request {
> > > > +	/* Host return status corresponding to flush request */
> > > > +	int ret;
> > > > +
> > > > +	/* command name*/
> > > > +	char name[16];
> > > > +
> > > > +	/* Wait queue to process deferred work after ack from host */
> > > > +	wait_queue_head_t host_acked;
> > > > +	bool done;
> > > > +
> > > > +	/* Wait queue to process deferred work after virt queue buffer avail
> > > > */
> > > > +	wait_queue_head_t wq_buf;
> > > > +	bool wq_buf_avail;
> > > > +	struct list_head list;
> > > > +};
> > > > +
> > > > +struct virtio_pmem {
> > > > +	struct virtio_device *vdev;
> > > > +
> > > > +	/* Virtio pmem request queue */
> > > > +	struct virtqueue *req_vq;
> > > > +
> > > > +	/* nvdimm bus registers virtio pmem device */
> > > > +	struct nvdimm_bus *nvdimm_bus;
> > > > +	struct nvdimm_bus_descriptor nd_desc;
> > > > +
> > > > +	/* List to store deferred work if virtqueue is full */
> > > > +	struct list_head req_list;
> > > > +
> > > > +	/* Synchronize virtqueue data */
> > > > +	spinlock_t pmem_lock;
> > > > +
> > > > +	/* Memory region information */
> > > > +	uint64_t start;
> > > > +	uint64_t size;
> > > > +};
> > > > +
> > > > +void host_ack(struct virtqueue *vq);
> > > > +int virtio_pmem_flush(struct nd_region *nd_region);
> > > > +#endif
> > > > diff --git a/include/uapi/linux/virtio_ids.h
> > > > b/include/uapi/linux/virtio_ids.h
> > > > index 6d5c3b2d4f4d..346389565ac1 100644
> > > > --- a/include/uapi/linux/virtio_ids.h
> > > > +++ b/include/uapi/linux/virtio_ids.h
> > > > @@ -43,5 +43,6 @@
> > > >  #define VIRTIO_ID_INPUT        18 /* virtio input */
> > > >  #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
> > > >  #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
> > > > +#define VIRTIO_ID_PMEM         25 /* virtio pmem */
> > > 
> > > Any reason for the jump here? are 21 to 24 already taken or you just
> > > want to be on the safe side?
> > 
> > They are already reserved.
> 
> Can you direct me to how to find a free ID?

I referred 'content.tex' in virtio-spec.

I have also posted a draft spec document[1] for virtio-pmem.
[1] https://lists.oasis-open.org/archives/virtio-dev/201903/msg00083.html

Thanks for the suggestions.

Best regards,
Pankaj

> 
> > 
> > Thanks,
> > Pankaj
> > 
> > > 
> > > >  
> > > >  #endif /* _LINUX_VIRTIO_IDS_H */
> > > > diff --git a/include/uapi/linux/virtio_pmem.h
> > > > b/include/uapi/linux/virtio_pmem.h
> > > > new file mode 100644
> > > > index 000000000000..fa3f7d52717a
> > > > --- /dev/null
> > > > +++ b/include/uapi/linux/virtio_pmem.h
> > > > @@ -0,0 +1,10 @@
> > > > +/* SPDX-License-Identifier: GPL-2.0 */
> > > > +
> > > > +#ifndef _UAPI_LINUX_VIRTIO_PMEM_H
> > > > +#define _UAPI_LINUX_VIRTIO_PMEM_H
> > > > +
> > > > +struct virtio_pmem_config {
> > > > +	__le64 start;
> > > > +	__le64 size;
> > > > +};
> > > > +#endif
> > > > --
> > > > 2.20.1
> > > > 
> > > > 
> > > 
> > > 
>

Patch
diff mbox series

diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
new file mode 100644
index 000000000000..2a1b1ba2c1ff
--- /dev/null
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -0,0 +1,84 @@ 
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * virtio_pmem.c: Virtio pmem Driver
+ *
+ * Discovers persistent memory range information
+ * from host and provides a virtio based flushing
+ * interface.
+ */
+#include <linux/virtio_pmem.h>
+#include "nd.h"
+
+ /* The interrupt handler */
+void host_ack(struct virtqueue *vq)
+{
+	unsigned int len;
+	unsigned long flags;
+	struct virtio_pmem_request *req, *req_buf;
+	struct virtio_pmem *vpmem = vq->vdev->priv;
+
+	spin_lock_irqsave(&vpmem->pmem_lock, flags);
+	while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
+		req->done = true;
+		wake_up(&req->host_acked);
+
+		if (!list_empty(&vpmem->req_list)) {
+			req_buf = list_first_entry(&vpmem->req_list,
+					struct virtio_pmem_request, list);
+			list_del(&vpmem->req_list);
+			req_buf->wq_buf_avail = true;
+			wake_up(&req_buf->wq_buf);
+		}
+	}
+	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
+}
+EXPORT_SYMBOL_GPL(host_ack);
+
+ /* The request submission function */
+int virtio_pmem_flush(struct nd_region *nd_region)
+{
+	int err;
+	unsigned long flags;
+	struct scatterlist *sgs[2], sg, ret;
+	struct virtio_device *vdev = nd_region->provider_data;
+	struct virtio_pmem *vpmem = vdev->priv;
+	struct virtio_pmem_request *req;
+
+	might_sleep();
+	req = kmalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	req->done = req->wq_buf_avail = false;
+	strcpy(req->name, "FLUSH");
+	init_waitqueue_head(&req->host_acked);
+	init_waitqueue_head(&req->wq_buf);
+	sg_init_one(&sg, req->name, strlen(req->name));
+	sgs[0] = &sg;
+	sg_init_one(&ret, &req->ret, sizeof(req->ret));
+	sgs[1] = &ret;
+
+	spin_lock_irqsave(&vpmem->pmem_lock, flags);
+	err = virtqueue_add_sgs(vpmem->req_vq, sgs, 1, 1, req, GFP_ATOMIC);
+	if (err) {
+		dev_err(&vdev->dev, "failed to send command to virtio pmem device\n");
+
+		list_add_tail(&vpmem->req_list, &req->list);
+		spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
+
+		/* When host has read buffer, this completes via host_ack */
+		wait_event(req->wq_buf, req->wq_buf_avail);
+		spin_lock_irqsave(&vpmem->pmem_lock, flags);
+	}
+	virtqueue_kick(vpmem->req_vq);
+	spin_unlock_irqrestore(&vpmem->pmem_lock, flags);
+
+	/* When host has read buffer, this completes via host_ack */
+	wait_event(req->host_acked, req->done);
+	err = req->ret;
+	kfree(req);
+
+	return err;
+};
+EXPORT_SYMBOL_GPL(virtio_pmem_flush);
+MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 35897649c24f..9f634a2ed638 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -42,6 +42,16 @@  config VIRTIO_PCI_LEGACY
 
 	  If unsure, say Y.
 
+config VIRTIO_PMEM
+	tristate "Support for virtio pmem driver"
+	depends on VIRTIO
+	depends on LIBNVDIMM
+	help
+	This driver provides support for virtio based flushing interface
+	for persistent memory range.
+
+	If unsure, say M.
+
 config VIRTIO_BALLOON
 	tristate "Virtio balloon driver"
 	depends on VIRTIO
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 3a2b5c5dcf46..143ce91eabe9 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -6,3 +6,4 @@  virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
 virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
 obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
+obj-$(CONFIG_VIRTIO_PMEM) += pmem.o ../nvdimm/virtio_pmem.o
diff --git a/drivers/virtio/pmem.c b/drivers/virtio/pmem.c
new file mode 100644
index 000000000000..52f74064f67e
--- /dev/null
+++ b/drivers/virtio/pmem.c
@@ -0,0 +1,125 @@ 
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * virtio_pmem.c: Virtio pmem Driver
+ *
+ * Discovers persistent memory range information
+ * from host and registers the virtual pmem device
+ * with libnvdimm core.
+ */
+#include <linux/virtio_pmem.h>
+#include <../../drivers/nvdimm/nd.h>
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_PMEM, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+ /* Initialize virt queue */
+static int init_vq(struct virtio_pmem *vpmem)
+{
+	struct virtqueue *vq;
+
+	/* single vq */
+	vpmem->req_vq = vq = virtio_find_single_vq(vpmem->vdev,
+				host_ack, "flush_queue");
+	if (IS_ERR(vq))
+		return PTR_ERR(vq);
+
+	spin_lock_init(&vpmem->pmem_lock);
+	INIT_LIST_HEAD(&vpmem->req_list);
+
+	return 0;
+};
+
+static int virtio_pmem_probe(struct virtio_device *vdev)
+{
+	int err = 0;
+	struct resource res;
+	struct virtio_pmem *vpmem;
+	struct nvdimm_bus *nvdimm_bus;
+	struct nd_region_desc ndr_desc;
+	int nid = dev_to_node(&vdev->dev);
+	struct nd_region *nd_region;
+
+	if (!vdev->config->get) {
+		dev_err(&vdev->dev, "%s failure: config disabled\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	vdev->priv = vpmem = devm_kzalloc(&vdev->dev, sizeof(*vpmem),
+			GFP_KERNEL);
+	if (!vpmem) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	vpmem->vdev = vdev;
+	err = init_vq(vpmem);
+	if (err)
+		goto out_err;
+
+	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
+			start, &vpmem->start);
+	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
+			size, &vpmem->size);
+
+	res.start = vpmem->start;
+	res.end   = vpmem->start + vpmem->size-1;
+	vpmem->nd_desc.provider_name = "virtio-pmem";
+	vpmem->nd_desc.module = THIS_MODULE;
+
+	vpmem->nvdimm_bus = nvdimm_bus = nvdimm_bus_register(&vdev->dev,
+						&vpmem->nd_desc);
+	if (!nvdimm_bus)
+		goto out_vq;
+
+	dev_set_drvdata(&vdev->dev, nvdimm_bus);
+	memset(&ndr_desc, 0, sizeof(ndr_desc));
+
+	ndr_desc.res = &res;
+	ndr_desc.numa_node = nid;
+	ndr_desc.flush = virtio_pmem_flush;
+	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
+	set_bit(ND_REGION_ASYNC, &ndr_desc.flags);
+	nd_region = nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc);
+	nd_region->provider_data =  dev_to_virtio
+					(nd_region->dev.parent->parent);
+
+	if (!nd_region)
+		goto out_nd;
+
+	//virtio_device_ready(vdev);
+	return 0;
+out_nd:
+	err = -ENXIO;
+	nvdimm_bus_unregister(nvdimm_bus);
+out_vq:
+	vdev->config->del_vqs(vdev);
+out_err:
+	dev_err(&vdev->dev, "failed to register virtio pmem memory\n");
+	return err;
+}
+
+static void virtio_pmem_remove(struct virtio_device *vdev)
+{
+	struct virtio_pmem *vpmem = vdev->priv;
+	struct nvdimm_bus *nvdimm_bus = dev_get_drvdata(&vdev->dev);
+
+	nvdimm_bus_unregister(nvdimm_bus);
+	vdev->config->del_vqs(vdev);
+	kfree(vpmem);
+}
+
+static struct virtio_driver virtio_pmem_driver = {
+	.driver.name		= KBUILD_MODNAME,
+	.driver.owner		= THIS_MODULE,
+	.id_table		= id_table,
+	.probe			= virtio_pmem_probe,
+	.remove			= virtio_pmem_remove,
+};
+
+module_virtio_driver(virtio_pmem_driver);
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_DESCRIPTION("Virtio pmem driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/virtio_pmem.h b/include/linux/virtio_pmem.h
new file mode 100644
index 000000000000..224f9d934be6
--- /dev/null
+++ b/include/linux/virtio_pmem.h
@@ -0,0 +1,60 @@ 
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * virtio_pmem.h: virtio pmem Driver
+ *
+ * Discovers persistent memory range information
+ * from host and provides a virtio based flushing
+ * interface.
+ **/
+
+#ifndef _LINUX_VIRTIO_PMEM_H
+#define _LINUX_VIRTIO_PMEM_H
+
+#include <linux/virtio_ids.h>
+#include <linux/module.h>
+#include <linux/virtio_config.h>
+#include <uapi/linux/virtio_pmem.h>
+#include <linux/libnvdimm.h>
+#include <linux/spinlock.h>
+
+struct virtio_pmem_request {
+	/* Host return status corresponding to flush request */
+	int ret;
+
+	/* command name*/
+	char name[16];
+
+	/* Wait queue to process deferred work after ack from host */
+	wait_queue_head_t host_acked;
+	bool done;
+
+	/* Wait queue to process deferred work after virt queue buffer avail */
+	wait_queue_head_t wq_buf;
+	bool wq_buf_avail;
+	struct list_head list;
+};
+
+struct virtio_pmem {
+	struct virtio_device *vdev;
+
+	/* Virtio pmem request queue */
+	struct virtqueue *req_vq;
+
+	/* nvdimm bus registers virtio pmem device */
+	struct nvdimm_bus *nvdimm_bus;
+	struct nvdimm_bus_descriptor nd_desc;
+
+	/* List to store deferred work if virtqueue is full */
+	struct list_head req_list;
+
+	/* Synchronize virtqueue data */
+	spinlock_t pmem_lock;
+
+	/* Memory region information */
+	uint64_t start;
+	uint64_t size;
+};
+
+void host_ack(struct virtqueue *vq);
+int virtio_pmem_flush(struct nd_region *nd_region);
+#endif
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index 6d5c3b2d4f4d..346389565ac1 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -43,5 +43,6 @@ 
 #define VIRTIO_ID_INPUT        18 /* virtio input */
 #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
 #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
+#define VIRTIO_ID_PMEM         25 /* virtio pmem */
 
 #endif /* _LINUX_VIRTIO_IDS_H */
diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h
new file mode 100644
index 000000000000..fa3f7d52717a
--- /dev/null
+++ b/include/uapi/linux/virtio_pmem.h
@@ -0,0 +1,10 @@ 
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _UAPI_LINUX_VIRTIO_PMEM_H
+#define _UAPI_LINUX_VIRTIO_PMEM_H
+
+struct virtio_pmem_config {
+	__le64 start;
+	__le64 size;
+};
+#endif