diff mbox series

[RFC,v2,4/5] vfio/type1: Add IOVA range capability support

Message ID 20180112164531.93712-5-shameerali.kolothum.thodi@huawei.com
State Superseded
Headers show
Series vfio/type1: Add support for valid iova list management | expand

Commit Message

Shameerali Kolothum Thodi Jan. 12, 2018, 4:45 p.m. UTC 
This  allows the user-space to retrieve the supported IOVA
range(s), excluding any reserved regions. The implementation
is based on capability chains, added to VFIO_IOMMU_GET_INFO ioctl.

Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>

---
 drivers/vfio/vfio_iommu_type1.c | 91 +++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/vfio.h       | 23 +++++++++++
 2 files changed, 114 insertions(+)

-- 
1.9.1

Comments

Eric Auger Jan. 23, 2018, 11:16 a.m. UTC | #1 
Hi Shameer,

On 12/01/18 17:45, Shameer Kolothum wrote:
> This  allows the user-space to retrieve the supported IOVA

> range(s), excluding any reserved regions. The implementation

> is based on capability chains, added to VFIO_IOMMU_GET_INFO ioctl.

> 

> Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>

> ---

>  drivers/vfio/vfio_iommu_type1.c | 91 +++++++++++++++++++++++++++++++++++++++++

>  include/uapi/linux/vfio.h       | 23 +++++++++++

>  2 files changed, 114 insertions(+)

> 

> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c

> index 47ea490..dc6ed85 100644

> --- a/drivers/vfio/vfio_iommu_type1.c

> +++ b/drivers/vfio/vfio_iommu_type1.c

> @@ -1893,6 +1893,67 @@ static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)

>  	return ret;

>  }

>  

> +static int vfio_add_iova_cap(struct vfio_info_cap *caps, void *cap_type,

can't you pass cap_type directly as a struct vfio_iommu_type1_info_cap_iova?

Also maybe using more explicit name for cap_type such as cap_iova_ranges?
> +			     size_t size)

> +{

> +	struct vfio_info_cap_header *header;

> +	struct vfio_iommu_type1_info_cap_iova *iova_cap, *iova = cap_type;

> +

> +	header = vfio_info_cap_add(caps, size,

> +				VFIO_IOMMU_TYPE1_INFO_CAP_IOVA, 1);

> +	if (IS_ERR(header))

> +		return PTR_ERR(header);

> +

> +	iova_cap = container_of(header,

> +			struct vfio_iommu_type1_info_cap_iova, header);

> +	iova_cap->nr_iovas = iova->nr_iovas;

> +	memcpy(iova_cap->iova_ranges, iova->iova_ranges,

> +			iova->nr_iovas * sizeof(*iova->iova_ranges));

> +	return 0;

> +}

> +

> +static int vfio_build_iommu_iova_caps(struct vfio_iommu *iommu,

> +				struct vfio_info_cap *caps)

> +{

> +	struct vfio_iommu_type1_info_cap_iova *iova_cap;

> +	struct vfio_iova *iova;

> +	size_t size;

> +	int iovas = 0, i = 0, ret;

> +

> +	mutex_lock(&iommu->lock);

> +

> +	list_for_each_entry(iova, &iommu->iova_list, list)

> +		iovas++;

> +

> +	if (!iovas) {

> +		ret = EINVAL;

> +		goto out_unlock;

> +	}

> +

> +	size = sizeof(*iova_cap) + (iovas * sizeof(*iova_cap->iova_ranges));

> +

> +	iova_cap = kzalloc(size, GFP_KERNEL);

> +	if (!iova_cap) {

> +		ret = -ENOMEM;

> +		goto out_unlock;

> +	}

> +

> +	iova_cap->nr_iovas = iovas;

> +

> +	list_for_each_entry(iova, &iommu->iova_list, list) {

> +		iova_cap->iova_ranges[i].start = iova->start;

> +		iova_cap->iova_ranges[i].end = iova->end;

> +		i++;

> +	}

> +

> +	ret = vfio_add_iova_cap(caps, iova_cap, size);

> +

> +	kfree(iova_cap);

> +out_unlock:

> +	mutex_unlock(&iommu->lock);

> +	return ret;

> +}

> +

>  static long vfio_iommu_type1_ioctl(void *iommu_data,

>  				   unsigned int cmd, unsigned long arg)

>  {

> @@ -1914,6 +1975,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,

>  		}

>  	} else if (cmd == VFIO_IOMMU_GET_INFO) {

>  		struct vfio_iommu_type1_info info;

> +		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };

> +		int ret;

>  

>  		minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes);

>  

> @@ -1927,6 +1990,34 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,

>  

>  		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);

>  

> +		if (info.argsz == minsz)

> +			goto done;

> +

> +		ret = vfio_build_iommu_iova_caps(iommu, &caps);

> +		if (ret)

> +			return ret;

> +

> +		if (caps.size) {

> +			info.flags |= VFIO_IOMMU_INFO_CAPS;

> +			minsz = offsetofend(struct vfio_iommu_type1_info,

> +							 cap_offset);

> +			if (info.argsz < sizeof(info) + caps.size) {

> +				info.argsz = sizeof(info) + caps.size;

> +				info.cap_offset = 0;

> +			} else {

> +				vfio_info_cap_shift(&caps, sizeof(info));

> +				if (copy_to_user((void __user *)arg +

> +						sizeof(info), caps.buf,

> +						caps.size)) {

> +					kfree(caps.buf);

> +					return -EFAULT;

> +				}

> +				info.cap_offset = sizeof(info);

> +			}

> +

> +			kfree(caps.buf);

> +		}

> +done:

>  		return copy_to_user((void __user *)arg, &info, minsz) ?

>  			-EFAULT : 0;

>  

> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h

> index e3301db..8671448 100644

> --- a/include/uapi/linux/vfio.h

> +++ b/include/uapi/linux/vfio.h

> @@ -517,7 +517,30 @@ struct vfio_iommu_type1_info {

>  	__u32	argsz;

>  	__u32	flags;

>  #define VFIO_IOMMU_INFO_PGSIZES (1 << 0)	/* supported page sizes info */

> +#define VFIO_IOMMU_INFO_CAPS	(1 << 1)	/* Info supports caps */

>  	__u64	iova_pgsizes;		/* Bitmap of supported page sizes */

> +	__u32   cap_offset;	/* Offset within info struct of first cap */

> +};

> +

> +/*

> + * The IOVA capability allows to report the valid IOVA range(s)

> + * excluding any reserved regions associated with dev group. Any dma

> + * map attempt outside the valid iova range will return error.

> + *

> + * The structures below define version 1 of this capability.

> + */

> +#define VFIO_IOMMU_TYPE1_INFO_CAP_IOVA  1

VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE ?
> +

> +struct vfio_iova_range {

> +	__u64	start;

> +	__u64	end;

> +};

> +

> +struct vfio_iommu_type1_info_cap_iova {

cap_iova_ranges?
> +	struct vfio_info_cap_header header;

> +	__u32	nr_iovas;

> +	__u32	reserved;

> +	struct vfio_iova_range iova_ranges[];

>  };

>  

>  #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)

> 

Otherwise looks good to me.

Thanks

Eric
Shameerali Kolothum Thodi Jan. 23, 2018, 12:51 p.m. UTC | #2 
> -----Original Message-----

> From: Auger Eric [mailto:eric.auger@redhat.com]

> Sent: Tuesday, January 23, 2018 11:17 AM

> To: Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>;

> alex.williamson@redhat.com; pmorel@linux.vnet.ibm.com

> Cc: kvm@vger.kernel.org; linux-kernel@vger.kernel.org; Linuxarm

> <linuxarm@huawei.com>; John Garry <john.garry@huawei.com>; xuwei (O)

> <xuwei5@huawei.com>

> Subject: Re: [RFC v2 4/5] vfio/type1: Add IOVA range capability support

> 

> Hi Shameer,

> 

> On 12/01/18 17:45, Shameer Kolothum wrote:

> > This  allows the user-space to retrieve the supported IOVA range(s),

> > excluding any reserved regions. The implementation is based on

> > capability chains, added to VFIO_IOMMU_GET_INFO ioctl.

> >

> > Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>

> > ---

> >  drivers/vfio/vfio_iommu_type1.c | 91

> +++++++++++++++++++++++++++++++++++++++++

> >  include/uapi/linux/vfio.h       | 23 +++++++++++

> >  2 files changed, 114 insertions(+)

> >

> > diff --git a/drivers/vfio/vfio_iommu_type1.c

> > b/drivers/vfio/vfio_iommu_type1.c index 47ea490..dc6ed85 100644

> > --- a/drivers/vfio/vfio_iommu_type1.c

> > +++ b/drivers/vfio/vfio_iommu_type1.c

> > @@ -1893,6 +1893,67 @@ static int

> vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)

> >  	return ret;

> >  }

> >

> > +static int vfio_add_iova_cap(struct vfio_info_cap *caps, void

> > +*cap_type,

> can't you pass cap_type directly as a struct vfio_iommu_type1_info_cap_iova?

> 

> Also maybe using more explicit name for cap_type such as cap_iova_ranges?

> > +			     size_t size)

> > +{

> > +	struct vfio_info_cap_header *header;

> > +	struct vfio_iommu_type1_info_cap_iova *iova_cap, *iova = cap_type;

> > +

> > +	header = vfio_info_cap_add(caps, size,

> > +				VFIO_IOMMU_TYPE1_INFO_CAP_IOVA, 1);

> > +	if (IS_ERR(header))

> > +		return PTR_ERR(header);

> > +

> > +	iova_cap = container_of(header,

> > +			struct vfio_iommu_type1_info_cap_iova, header);

> > +	iova_cap->nr_iovas = iova->nr_iovas;

> > +	memcpy(iova_cap->iova_ranges, iova->iova_ranges,

> > +			iova->nr_iovas * sizeof(*iova->iova_ranges));

> > +	return 0;

> > +}

> > +

> > +static int vfio_build_iommu_iova_caps(struct vfio_iommu *iommu,

> > +				struct vfio_info_cap *caps)

> > +{

> > +	struct vfio_iommu_type1_info_cap_iova *iova_cap;

> > +	struct vfio_iova *iova;

> > +	size_t size;

> > +	int iovas = 0, i = 0, ret;

> > +

> > +	mutex_lock(&iommu->lock);

> > +

> > +	list_for_each_entry(iova, &iommu->iova_list, list)

> > +		iovas++;

> > +

> > +	if (!iovas) {

> > +		ret = EINVAL;

> > +		goto out_unlock;

> > +	}

> > +

> > +	size = sizeof(*iova_cap) + (iovas * sizeof(*iova_cap->iova_ranges));

> > +

> > +	iova_cap = kzalloc(size, GFP_KERNEL);

> > +	if (!iova_cap) {

> > +		ret = -ENOMEM;

> > +		goto out_unlock;

> > +	}

> > +

> > +	iova_cap->nr_iovas = iovas;

> > +

> > +	list_for_each_entry(iova, &iommu->iova_list, list) {

> > +		iova_cap->iova_ranges[i].start = iova->start;

> > +		iova_cap->iova_ranges[i].end = iova->end;

> > +		i++;

> > +	}

> > +

> > +	ret = vfio_add_iova_cap(caps, iova_cap, size);

> > +

> > +	kfree(iova_cap);

> > +out_unlock:

> > +	mutex_unlock(&iommu->lock);

> > +	return ret;

> > +}

> > +

> >  static long vfio_iommu_type1_ioctl(void *iommu_data,

> >  				   unsigned int cmd, unsigned long arg)  { @@ -

> 1914,6 +1975,8 @@

> > static long vfio_iommu_type1_ioctl(void *iommu_data,

> >  		}

> >  	} else if (cmd == VFIO_IOMMU_GET_INFO) {

> >  		struct vfio_iommu_type1_info info;

> > +		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };

> > +		int ret;

> >

> >  		minsz = offsetofend(struct vfio_iommu_type1_info,

> iova_pgsizes);

> >

> > @@ -1927,6 +1990,34 @@ static long vfio_iommu_type1_ioctl(void

> > *iommu_data,

> >

> >  		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);

> >

> > +		if (info.argsz == minsz)

> > +			goto done;

> > +

> > +		ret = vfio_build_iommu_iova_caps(iommu, &caps);

> > +		if (ret)

> > +			return ret;

> > +

> > +		if (caps.size) {

> > +			info.flags |= VFIO_IOMMU_INFO_CAPS;

> > +			minsz = offsetofend(struct vfio_iommu_type1_info,

> > +							 cap_offset);

> > +			if (info.argsz < sizeof(info) + caps.size) {

> > +				info.argsz = sizeof(info) + caps.size;

> > +				info.cap_offset = 0;

> > +			} else {

> > +				vfio_info_cap_shift(&caps, sizeof(info));

> > +				if (copy_to_user((void __user *)arg +

> > +						sizeof(info), caps.buf,

> > +						caps.size)) {

> > +					kfree(caps.buf);

> > +					return -EFAULT;

> > +				}

> > +				info.cap_offset = sizeof(info);

> > +			}

> > +

> > +			kfree(caps.buf);

> > +		}

> > +done:

> >  		return copy_to_user((void __user *)arg, &info, minsz) ?

> >  			-EFAULT : 0;

> >

> > diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h

> > index e3301db..8671448 100644

> > --- a/include/uapi/linux/vfio.h

> > +++ b/include/uapi/linux/vfio.h

> > @@ -517,7 +517,30 @@ struct vfio_iommu_type1_info {

> >  	__u32	argsz;

> >  	__u32	flags;

> >  #define VFIO_IOMMU_INFO_PGSIZES (1 << 0)	/* supported page sizes info */

> > +#define VFIO_IOMMU_INFO_CAPS	(1 << 1)	/* Info supports caps */

> >  	__u64	iova_pgsizes;		/* Bitmap of supported page sizes */

> > +	__u32   cap_offset;	/* Offset within info struct of first cap */

> > +};

> > +

> > +/*

> > + * The IOVA capability allows to report the valid IOVA range(s)

> > + * excluding any reserved regions associated with dev group. Any dma

> > + * map attempt outside the valid iova range will return error.

> > + *

> > + * The structures below define version 1 of this capability.

> > + */

> > +#define VFIO_IOMMU_TYPE1_INFO_CAP_IOVA  1

> VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE ?

> > +

> > +struct vfio_iova_range {

> > +	__u64	start;

> > +	__u64	end;

> > +};

> > +

> > +struct vfio_iommu_type1_info_cap_iova {

> cap_iova_ranges?

> > +	struct vfio_info_cap_header header;

> > +	__u32	nr_iovas;

> > +	__u32	reserved;

> > +	struct vfio_iova_range iova_ranges[];

> >  };

> >

> >  #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)

> >

> Otherwise looks good to me.


Ok. I will take care of them.

Thanks,
Shameer

> Thanks

> 

> Eric
diff mbox series

Patch

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 47ea490..dc6ed85 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1893,6 +1893,67 @@  static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)
 	return ret;
 }
 
+static int vfio_add_iova_cap(struct vfio_info_cap *caps, void *cap_type,
+			     size_t size)
+{
+	struct vfio_info_cap_header *header;
+	struct vfio_iommu_type1_info_cap_iova *iova_cap, *iova = cap_type;
+
+	header = vfio_info_cap_add(caps, size,
+				VFIO_IOMMU_TYPE1_INFO_CAP_IOVA, 1);
+	if (IS_ERR(header))
+		return PTR_ERR(header);
+
+	iova_cap = container_of(header,
+			struct vfio_iommu_type1_info_cap_iova, header);
+	iova_cap->nr_iovas = iova->nr_iovas;
+	memcpy(iova_cap->iova_ranges, iova->iova_ranges,
+			iova->nr_iovas * sizeof(*iova->iova_ranges));
+	return 0;
+}
+
+static int vfio_build_iommu_iova_caps(struct vfio_iommu *iommu,
+				struct vfio_info_cap *caps)
+{
+	struct vfio_iommu_type1_info_cap_iova *iova_cap;
+	struct vfio_iova *iova;
+	size_t size;
+	int iovas = 0, i = 0, ret;
+
+	mutex_lock(&iommu->lock);
+
+	list_for_each_entry(iova, &iommu->iova_list, list)
+		iovas++;
+
+	if (!iovas) {
+		ret = EINVAL;
+		goto out_unlock;
+	}
+
+	size = sizeof(*iova_cap) + (iovas * sizeof(*iova_cap->iova_ranges));
+
+	iova_cap = kzalloc(size, GFP_KERNEL);
+	if (!iova_cap) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	iova_cap->nr_iovas = iovas;
+
+	list_for_each_entry(iova, &iommu->iova_list, list) {
+		iova_cap->iova_ranges[i].start = iova->start;
+		iova_cap->iova_ranges[i].end = iova->end;
+		i++;
+	}
+
+	ret = vfio_add_iova_cap(caps, iova_cap, size);
+
+	kfree(iova_cap);
+out_unlock:
+	mutex_unlock(&iommu->lock);
+	return ret;
+}
+
 static long vfio_iommu_type1_ioctl(void *iommu_data,
 				   unsigned int cmd, unsigned long arg)
 {
@@ -1914,6 +1975,8 @@  static long vfio_iommu_type1_ioctl(void *iommu_data,
 		}
 	} else if (cmd == VFIO_IOMMU_GET_INFO) {
 		struct vfio_iommu_type1_info info;
+		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
+		int ret;
 
 		minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes);
 
@@ -1927,6 +1990,34 @@  static long vfio_iommu_type1_ioctl(void *iommu_data,
 
 		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);
 
+		if (info.argsz == minsz)
+			goto done;
+
+		ret = vfio_build_iommu_iova_caps(iommu, &caps);
+		if (ret)
+			return ret;
+
+		if (caps.size) {
+			info.flags |= VFIO_IOMMU_INFO_CAPS;
+			minsz = offsetofend(struct vfio_iommu_type1_info,
+							 cap_offset);
+			if (info.argsz < sizeof(info) + caps.size) {
+				info.argsz = sizeof(info) + caps.size;
+				info.cap_offset = 0;
+			} else {
+				vfio_info_cap_shift(&caps, sizeof(info));
+				if (copy_to_user((void __user *)arg +
+						sizeof(info), caps.buf,
+						caps.size)) {
+					kfree(caps.buf);
+					return -EFAULT;
+				}
+				info.cap_offset = sizeof(info);
+			}
+
+			kfree(caps.buf);
+		}
+done:
 		return copy_to_user((void __user *)arg, &info, minsz) ?
 			-EFAULT : 0;
 
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index e3301db..8671448 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -517,7 +517,30 @@  struct vfio_iommu_type1_info {
 	__u32	argsz;
 	__u32	flags;
 #define VFIO_IOMMU_INFO_PGSIZES (1 << 0)	/* supported page sizes info */
+#define VFIO_IOMMU_INFO_CAPS	(1 << 1)	/* Info supports caps */
 	__u64	iova_pgsizes;		/* Bitmap of supported page sizes */
+	__u32   cap_offset;	/* Offset within info struct of first cap */
+};
+
+/*
+ * The IOVA capability allows to report the valid IOVA range(s)
+ * excluding any reserved regions associated with dev group. Any dma
+ * map attempt outside the valid iova range will return error.
+ *
+ * The structures below define version 1 of this capability.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_CAP_IOVA  1
+
+struct vfio_iova_range {
+	__u64	start;
+	__u64	end;
+};
+
+struct vfio_iommu_type1_info_cap_iova {
+	struct vfio_info_cap_header header;
+	__u32	nr_iovas;
+	__u32	reserved;
+	struct vfio_iova_range iova_ranges[];
 };
 
 #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)