This patch allows user space to request PASID allocation/free, e.g. when
serving the request from the guest.
PASIDs that are not freed by userspace are automatically freed when the
IOASID set is destroyed when process exits.
Cc: Kevin Tian <[email protected]>
CC: Jacob Pan <[email protected]>
Cc: Alex Williamson <[email protected]>
Cc: Eric Auger <[email protected]>
Cc: Jean-Philippe Brucker <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Lu Baolu <[email protected]>
Signed-off-by: Liu Yi L <[email protected]>
Signed-off-by: Yi Sun <[email protected]>
Signed-off-by: Jacob Pan <[email protected]>
---
v3 -> v4:
*) address comments from v3, except the below comment against the range
of PASID_FREE request. needs more help on it.
"> +if (req.range.min > req.range.max)
Is it exploitable that a user can spin the kernel for a long time in
the case of a free by calling this with [0, MAX_UINT] regardless of
their actual allocations?"
v1 -> v2:
*) move the vfio_mm related code to be a seprate module
*) use a single structure for alloc/free, could support a range of PASIDs
*) fetch vfio_mm at group_attach time instead of at iommu driver open time
---
drivers/vfio/Kconfig | 1 +
drivers/vfio/vfio_iommu_type1.c | 84 +++++++++++++++++++++++++++++++++++++++++
drivers/vfio/vfio_pasid.c | 10 +++++
include/linux/vfio.h | 6 +++
include/uapi/linux/vfio.h | 36 ++++++++++++++++++
5 files changed, 137 insertions(+)
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 3d8a108..95d90c6 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -2,6 +2,7 @@
config VFIO_IOMMU_TYPE1
tristate
depends on VFIO
+ select VFIO_PASID if (X86)
default n
config VFIO_IOMMU_SPAPR_TCE
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 80623b8..29726ca 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -76,6 +76,7 @@ struct vfio_iommu {
bool dirty_page_tracking;
bool pinned_page_dirty_scope;
struct iommu_nesting_info *nesting_info;
+ struct vfio_mm *vmm;
};
struct vfio_domain {
@@ -1937,6 +1938,11 @@ static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu,
static void vfio_iommu_release_nesting_info(struct vfio_iommu *iommu)
{
+ if (iommu->vmm) {
+ vfio_mm_put(iommu->vmm);
+ iommu->vmm = NULL;
+ }
+
kfree(iommu->nesting_info);
iommu->nesting_info = NULL;
}
@@ -2075,6 +2081,25 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
goto out_detach;
}
iommu->nesting_info = info;
+
+ if (info->features & IOMMU_NESTING_FEAT_SYSWIDE_PASID) {
+ struct vfio_mm *vmm;
+ int sid;
+
+ vmm = vfio_mm_get_from_task(current);
+ if (IS_ERR(vmm)) {
+ ret = PTR_ERR(vmm);
+ goto out_detach;
+ }
+ iommu->vmm = vmm;
+
+ sid = vfio_mm_ioasid_sid(vmm);
+ ret = iommu_domain_set_attr(domain->domain,
+ DOMAIN_ATTR_IOASID_SID,
+ &sid);
+ if (ret)
+ goto out_detach;
+ }
}
/* Get aperture info */
@@ -2860,6 +2885,63 @@ static int vfio_iommu_type1_dirty_pages(struct vfio_iommu *iommu,
return -EINVAL;
}
+static int vfio_iommu_type1_pasid_alloc(struct vfio_iommu *iommu,
+ unsigned int min,
+ unsigned int max)
+{
+ int ret = -EOPNOTSUPP;
+
+ mutex_lock(&iommu->lock);
+ if (iommu->vmm)
+ ret = vfio_pasid_alloc(iommu->vmm, min, max);
+ mutex_unlock(&iommu->lock);
+ return ret;
+}
+
+static int vfio_iommu_type1_pasid_free(struct vfio_iommu *iommu,
+ unsigned int min,
+ unsigned int max)
+{
+ int ret = -EOPNOTSUPP;
+
+ mutex_lock(&iommu->lock);
+ if (iommu->vmm) {
+ vfio_pasid_free_range(iommu->vmm, min, max);
+ ret = 0;
+ }
+ mutex_unlock(&iommu->lock);
+ return ret;
+}
+
+static int vfio_iommu_type1_pasid_request(struct vfio_iommu *iommu,
+ unsigned long arg)
+{
+ struct vfio_iommu_type1_pasid_request req;
+ unsigned long minsz;
+
+ minsz = offsetofend(struct vfio_iommu_type1_pasid_request, range);
+
+ if (copy_from_user(&req, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ if (req.argsz < minsz || (req.flags & ~VFIO_PASID_REQUEST_MASK))
+ return -EINVAL;
+
+ if (req.range.min > req.range.max)
+ return -EINVAL;
+
+ switch (req.flags & VFIO_PASID_REQUEST_MASK) {
+ case VFIO_IOMMU_FLAG_ALLOC_PASID:
+ return vfio_iommu_type1_pasid_alloc(iommu,
+ req.range.min, req.range.max);
+ case VFIO_IOMMU_FLAG_FREE_PASID:
+ return vfio_iommu_type1_pasid_free(iommu,
+ req.range.min, req.range.max);
+ default:
+ return -EINVAL;
+ }
+}
+
static long vfio_iommu_type1_ioctl(void *iommu_data,
unsigned int cmd, unsigned long arg)
{
@@ -2876,6 +2958,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
return vfio_iommu_type1_unmap_dma(iommu, arg);
case VFIO_IOMMU_DIRTY_PAGES:
return vfio_iommu_type1_dirty_pages(iommu, arg);
+ case VFIO_IOMMU_PASID_REQUEST:
+ return vfio_iommu_type1_pasid_request(iommu, arg);
}
return -ENOTTY;
diff --git a/drivers/vfio/vfio_pasid.c b/drivers/vfio/vfio_pasid.c
index c46b870..6f907db 100644
--- a/drivers/vfio/vfio_pasid.c
+++ b/drivers/vfio/vfio_pasid.c
@@ -53,6 +53,7 @@ void vfio_mm_put(struct vfio_mm *vmm)
{
kref_put_mutex(&vmm->kref, vfio_mm_release, &vfio_pasid.vfio_mm_lock);
}
+EXPORT_SYMBOL_GPL(vfio_mm_put);
static void vfio_mm_get(struct vfio_mm *vmm)
{
@@ -104,6 +105,13 @@ struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task)
mmput(mm);
return vmm;
}
+EXPORT_SYMBOL_GPL(vfio_mm_get_from_task);
+
+int vfio_mm_ioasid_sid(struct vfio_mm *vmm)
+{
+ return vmm->ioasid_sid;
+}
+EXPORT_SYMBOL_GPL(vfio_mm_ioasid_sid);
int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
{
@@ -113,6 +121,7 @@ int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
return (pasid == INVALID_IOASID) ? -ENOSPC : pasid;
}
+EXPORT_SYMBOL_GPL(vfio_pasid_alloc);
void vfio_pasid_free_range(struct vfio_mm *vmm,
ioasid_t min, ioasid_t max)
@@ -130,6 +139,7 @@ void vfio_pasid_free_range(struct vfio_mm *vmm,
for (; pasid <= max; pasid++)
ioasid_free(pasid);
}
+EXPORT_SYMBOL_GPL(vfio_pasid_free_range);
static int __init vfio_pasid_init(void)
{
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 9da6468..35c922a 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -101,6 +101,7 @@ struct vfio_mm;
#if IS_ENABLED(CONFIG_VFIO_PASID)
extern struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task);
extern void vfio_mm_put(struct vfio_mm *vmm);
+int vfio_mm_ioasid_sid(struct vfio_mm *vmm);
extern int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max);
extern void vfio_pasid_free_range(struct vfio_mm *vmm,
ioasid_t min, ioasid_t max);
@@ -114,6 +115,11 @@ static inline void vfio_mm_put(struct vfio_mm *vmm)
{
}
+static inline int vfio_mm_ioasid_sid(struct vfio_mm *vmm)
+{
+ return -ENOTTY;
+}
+
static inline int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
{
return -ENOTTY;
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 3e3de9c..fe267b8e 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1169,6 +1169,42 @@ struct vfio_iommu_type1_dirty_bitmap_get {
#define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17)
+/**
+ * VFIO_IOMMU_PASID_REQUEST - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
+ * struct vfio_iommu_type1_pasid_request)
+ *
+ * PASID (Processor Address Space ID) is a PCIe concept for tagging
+ * address spaces in DMA requests. When system-wide PASID allocation
+ * is required by underlying iommu driver (e.g. Intel VT-d), this
+ * provides an interface for userspace to request pasid alloc/free
+ * for its assigned devices. Userspace should check the availability
+ * of this API through VFIO_IOMMU_GET_INFO.
+ *
+ * @flags=VFIO_IOMMU_FLAG_ALLOC_PASID, allocate a single PASID within @range.
+ * @flags=VFIO_IOMMU_FLAG_FREE_PASID, free the PASIDs within @range.
+ * @range is [min, max], which means both @min and @max are inclusive.
+ * ALLOC_PASID and FREE_PASID are mutually exclusive.
+ *
+ * returns: allocated PASID value on success, -errno on failure for
+ * ALLOC_PASID;
+ * 0 for FREE_PASID operation;
+ */
+struct vfio_iommu_type1_pasid_request {
+ __u32 argsz;
+#define VFIO_IOMMU_FLAG_ALLOC_PASID (1 << 0)
+#define VFIO_IOMMU_FLAG_FREE_PASID (1 << 1)
+ __u32 flags;
+ struct {
+ __u32 min;
+ __u32 max;
+ } range;
+};
+
+#define VFIO_PASID_REQUEST_MASK (VFIO_IOMMU_FLAG_ALLOC_PASID | \
+ VFIO_IOMMU_FLAG_FREE_PASID)
+
+#define VFIO_IOMMU_PASID_REQUEST _IO(VFIO_TYPE, VFIO_BASE + 18)
+
/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
/*
--
2.7.4
Hi Yi,
On 7/4/20 1:26 PM, Liu Yi L wrote:
> This patch allows user space to request PASID allocation/free, e.g. when
> serving the request from the guest.
>
> PASIDs that are not freed by userspace are automatically freed when the
> IOASID set is destroyed when process exits.
>
> Cc: Kevin Tian <[email protected]>
> CC: Jacob Pan <[email protected]>
> Cc: Alex Williamson <[email protected]>
> Cc: Eric Auger <[email protected]>
> Cc: Jean-Philippe Brucker <[email protected]>
> Cc: Joerg Roedel <[email protected]>
> Cc: Lu Baolu <[email protected]>
> Signed-off-by: Liu Yi L <[email protected]>
> Signed-off-by: Yi Sun <[email protected]>
> Signed-off-by: Jacob Pan <[email protected]>
> ---
> v3 -> v4:
> *) address comments from v3, except the below comment against the range
> of PASID_FREE request. needs more help on it.
> "> +if (req.range.min > req.range.max)
>
> Is it exploitable that a user can spin the kernel for a long time in
> the case of a free by calling this with [0, MAX_UINT] regardless of
> their actual allocations?"
>
> v1 -> v2:
> *) move the vfio_mm related code to be a seprate module
> *) use a single structure for alloc/free, could support a range of PASIDs
> *) fetch vfio_mm at group_attach time instead of at iommu driver open time
> ---
> drivers/vfio/Kconfig | 1 +
> drivers/vfio/vfio_iommu_type1.c | 84 +++++++++++++++++++++++++++++++++++++++++
> drivers/vfio/vfio_pasid.c | 10 +++++
> include/linux/vfio.h | 6 +++
> include/uapi/linux/vfio.h | 36 ++++++++++++++++++
> 5 files changed, 137 insertions(+)
>
> diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
> index 3d8a108..95d90c6 100644
> --- a/drivers/vfio/Kconfig
> +++ b/drivers/vfio/Kconfig
> @@ -2,6 +2,7 @@
> config VFIO_IOMMU_TYPE1
> tristate
> depends on VFIO
> + select VFIO_PASID if (X86)
> default n
>
> config VFIO_IOMMU_SPAPR_TCE
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 80623b8..29726ca 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -76,6 +76,7 @@ struct vfio_iommu {
> bool dirty_page_tracking;
> bool pinned_page_dirty_scope;
> struct iommu_nesting_info *nesting_info;
> + struct vfio_mm *vmm;
> };
>
> struct vfio_domain {
> @@ -1937,6 +1938,11 @@ static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu,
>
> static void vfio_iommu_release_nesting_info(struct vfio_iommu *iommu)
> {
> + if (iommu->vmm) {
> + vfio_mm_put(iommu->vmm);
> + iommu->vmm = NULL;
> + }
> +
> kfree(iommu->nesting_info);
> iommu->nesting_info = NULL;
> }
> @@ -2075,6 +2081,25 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
> goto out_detach;
> }
> iommu->nesting_info = info;
> +
> + if (info->features & IOMMU_NESTING_FEAT_SYSWIDE_PASID) {
> + struct vfio_mm *vmm;
> + int sid;
> +
> + vmm = vfio_mm_get_from_task(current);
> + if (IS_ERR(vmm)) {
> + ret = PTR_ERR(vmm);
> + goto out_detach;
> + }
> + iommu->vmm = vmm;
> +
> + sid = vfio_mm_ioasid_sid(vmm);
> + ret = iommu_domain_set_attr(domain->domain,
> + DOMAIN_ATTR_IOASID_SID,
> + &sid);
> + if (ret)
> + goto out_detach;
> + }
> }
>
> /* Get aperture info */
> @@ -2860,6 +2885,63 @@ static int vfio_iommu_type1_dirty_pages(struct vfio_iommu *iommu,
> return -EINVAL;
> }
>
> +static int vfio_iommu_type1_pasid_alloc(struct vfio_iommu *iommu,
> + unsigned int min,
> + unsigned int max)
> +{
> + int ret = -EOPNOTSUPP;
> +
> + mutex_lock(&iommu->lock);
> + if (iommu->vmm)
> + ret = vfio_pasid_alloc(iommu->vmm, min, max);
> + mutex_unlock(&iommu->lock);
> + return ret;
> +}
> +
> +static int vfio_iommu_type1_pasid_free(struct vfio_iommu *iommu,
> + unsigned int min,
> + unsigned int max)
> +{
> + int ret = -EOPNOTSUPP;
> +
> + mutex_lock(&iommu->lock);
> + if (iommu->vmm) {
> + vfio_pasid_free_range(iommu->vmm, min, max);
> + ret = 0;
> + }
> + mutex_unlock(&iommu->lock);
> + return ret;
> +}
> +
> +static int vfio_iommu_type1_pasid_request(struct vfio_iommu *iommu,
> + unsigned long arg)
> +{
> + struct vfio_iommu_type1_pasid_request req;
> + unsigned long minsz;
> +
> + minsz = offsetofend(struct vfio_iommu_type1_pasid_request, range);
> +
> + if (copy_from_user(&req, (void __user *)arg, minsz))
> + return -EFAULT;
> +
> + if (req.argsz < minsz || (req.flags & ~VFIO_PASID_REQUEST_MASK))
> + return -EINVAL;
> +
> + if (req.range.min > req.range.max)
> + return -EINVAL;
> +
> + switch (req.flags & VFIO_PASID_REQUEST_MASK) {
> + case VFIO_IOMMU_FLAG_ALLOC_PASID:
> + return vfio_iommu_type1_pasid_alloc(iommu,
> + req.range.min, req.range.max);
> + case VFIO_IOMMU_FLAG_FREE_PASID:
> + return vfio_iommu_type1_pasid_free(iommu,
> + req.range.min, req.range.max);
> + default:
> + return -EINVAL;
> + }
> +}
> +
> static long vfio_iommu_type1_ioctl(void *iommu_data,
> unsigned int cmd, unsigned long arg)
> {
> @@ -2876,6 +2958,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
> return vfio_iommu_type1_unmap_dma(iommu, arg);
> case VFIO_IOMMU_DIRTY_PAGES:
> return vfio_iommu_type1_dirty_pages(iommu, arg);
> + case VFIO_IOMMU_PASID_REQUEST:
> + return vfio_iommu_type1_pasid_request(iommu, arg);
> }
>
> return -ENOTTY;
> diff --git a/drivers/vfio/vfio_pasid.c b/drivers/vfio/vfio_pasid.c
> index c46b870..6f907db 100644
> --- a/drivers/vfio/vfio_pasid.c
> +++ b/drivers/vfio/vfio_pasid.c
> @@ -53,6 +53,7 @@ void vfio_mm_put(struct vfio_mm *vmm)
> {
> kref_put_mutex(&vmm->kref, vfio_mm_release, &vfio_pasid.vfio_mm_lock);
> }
> +EXPORT_SYMBOL_GPL(vfio_mm_put);
I think this should be belong to [5/15]
>
> static void vfio_mm_get(struct vfio_mm *vmm)
> {
> @@ -104,6 +105,13 @@ struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task)
> mmput(mm);
> return vmm;
> }
> +EXPORT_SYMBOL_GPL(vfio_mm_get_from_task);
same
> +
> +int vfio_mm_ioasid_sid(struct vfio_mm *vmm)
extern?
same
> +{
> + return vmm->ioasid_sid;
> +}
> +EXPORT_SYMBOL_GPL(vfio_mm_ioasid_sid);
>
> int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
> {
> @@ -113,6 +121,7 @@ int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
>
> return (pasid == INVALID_IOASID) ? -ENOSPC : pasid;
> }
> +EXPORT_SYMBOL_GPL(vfio_pasid_alloc);
same
>
> void vfio_pasid_free_range(struct vfio_mm *vmm,
> ioasid_t min, ioasid_t max)
> @@ -130,6 +139,7 @@ void vfio_pasid_free_range(struct vfio_mm *vmm,
> for (; pasid <= max; pasid++)
> ioasid_free(pasid);
> }
> +EXPORT_SYMBOL_GPL(vfio_pasid_free_range);
same
>
> static int __init vfio_pasid_init(void)
> {
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 9da6468..35c922a 100644
> --- a/include/linux/vfio.h
> +++ b/include/linux/vfio.h
> @@ -101,6 +101,7 @@ struct vfio_mm;
> #if IS_ENABLED(CONFIG_VFIO_PASID)
> extern struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task);
> extern void vfio_mm_put(struct vfio_mm *vmm);
> +int vfio_mm_ioasid_sid(struct vfio_mm *vmm);
> extern int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max);
> extern void vfio_pasid_free_range(struct vfio_mm *vmm,
> ioasid_t min, ioasid_t max);
> @@ -114,6 +115,11 @@ static inline void vfio_mm_put(struct vfio_mm *vmm)
> {
> }
>
> +static inline int vfio_mm_ioasid_sid(struct vfio_mm *vmm)
> +{
> + return -ENOTTY;
> +}
> +
> static inline int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
> {
> return -ENOTTY;
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 3e3de9c..fe267b8e 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -1169,6 +1169,42 @@ struct vfio_iommu_type1_dirty_bitmap_get {
>
> #define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17)
>
> +/**
> + * VFIO_IOMMU_PASID_REQUEST - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
> + * struct vfio_iommu_type1_pasid_request)
> + *
> + * PASID (Processor Address Space ID) is a PCIe concept for tagging
> + * address spaces in DMA requests. When system-wide PASID allocation
> + * is required by underlying iommu driver (e.g. Intel VT-d), this
> + * provides an interface for userspace to request pasid alloc/free
> + * for its assigned devices. Userspace should check the availability
> + * of this API through VFIO_IOMMU_GET_INFO.
name the capability?
> + *
> + * @flags=VFIO_IOMMU_FLAG_ALLOC_PASID, allocate a single PASID within @range.
> + * @flags=VFIO_IOMMU_FLAG_FREE_PASID, free the PASIDs within @range.
> + * @range is [min, max], which means both @min and @max are inclusive.
> + * ALLOC_PASID and FREE_PASID are mutually exclusive.
> + *
> + * returns: allocated PASID value on success, -errno on failure for
> + * ALLOC_PASID;
> + * 0 for FREE_PASID operation;
> + */
> +struct vfio_iommu_type1_pasid_request {
> + __u32 argsz;
> +#define VFIO_IOMMU_FLAG_ALLOC_PASID (1 << 0)
> +#define VFIO_IOMMU_FLAG_FREE_PASID (1 << 1)
> + __u32 flags;> + struct {
> + __u32 min;
> + __u32 max;
> + } range;
> +};
> +
> +#define VFIO_PASID_REQUEST_MASK (VFIO_IOMMU_FLAG_ALLOC_PASID | \
> + VFIO_IOMMU_FLAG_FREE_PASID)
> +
> +#define VFIO_IOMMU_PASID_REQUEST _IO(VFIO_TYPE, VFIO_BASE + 18)
> +
> /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
>
> /*
>
Thanks
Eric
Hi Eric,
> From: Auger Eric <[email protected]>
> Sent: Monday, July 6, 2020 11:18 PM
>
> Hi Yi,
>
> On 7/4/20 1:26 PM, Liu Yi L wrote:
> > This patch allows user space to request PASID allocation/free, e.g. when
> > serving the request from the guest.
> >
> > PASIDs that are not freed by userspace are automatically freed when the
> > IOASID set is destroyed when process exits.
> >
> > Cc: Kevin Tian <[email protected]>
> > CC: Jacob Pan <[email protected]>
> > Cc: Alex Williamson <[email protected]>
> > Cc: Eric Auger <[email protected]>
> > Cc: Jean-Philippe Brucker <[email protected]>
> > Cc: Joerg Roedel <[email protected]>
> > Cc: Lu Baolu <[email protected]>
> > Signed-off-by: Liu Yi L <[email protected]>
> > Signed-off-by: Yi Sun <[email protected]>
> > Signed-off-by: Jacob Pan <[email protected]>
> > ---
> > v3 -> v4:
> > *) address comments from v3, except the below comment against the range
> > of PASID_FREE request. needs more help on it.
> > "> +if (req.range.min > req.range.max)
> >
> > Is it exploitable that a user can spin the kernel for a long time in
> > the case of a free by calling this with [0, MAX_UINT] regardless of
> > their actual allocations?"
> >
> > v1 -> v2:
> > *) move the vfio_mm related code to be a seprate module
> > *) use a single structure for alloc/free, could support a range of PASIDs
> > *) fetch vfio_mm at group_attach time instead of at iommu driver open time
> > ---
> > drivers/vfio/Kconfig | 1 +
> > drivers/vfio/vfio_iommu_type1.c | 84
> +++++++++++++++++++++++++++++++++++++++++
> > drivers/vfio/vfio_pasid.c | 10 +++++
> > include/linux/vfio.h | 6 +++
> > include/uapi/linux/vfio.h | 36 ++++++++++++++++++
> > 5 files changed, 137 insertions(+)
> >
> > diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
> > index 3d8a108..95d90c6 100644
> > --- a/drivers/vfio/Kconfig
> > +++ b/drivers/vfio/Kconfig
> > @@ -2,6 +2,7 @@
> > config VFIO_IOMMU_TYPE1
> > tristate
> > depends on VFIO
> > + select VFIO_PASID if (X86)
> > default n
> >
> > config VFIO_IOMMU_SPAPR_TCE
> > diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> > index 80623b8..29726ca 100644
> > --- a/drivers/vfio/vfio_iommu_type1.c
> > +++ b/drivers/vfio/vfio_iommu_type1.c
> > @@ -76,6 +76,7 @@ struct vfio_iommu {
> > bool dirty_page_tracking;
> > bool pinned_page_dirty_scope;
> > struct iommu_nesting_info *nesting_info;
> > + struct vfio_mm *vmm;
> > };
> >
> > struct vfio_domain {
> > @@ -1937,6 +1938,11 @@ static void vfio_iommu_iova_insert_copy(struct
> vfio_iommu *iommu,
> >
> > static void vfio_iommu_release_nesting_info(struct vfio_iommu *iommu)
> > {
> > + if (iommu->vmm) {
> > + vfio_mm_put(iommu->vmm);
> > + iommu->vmm = NULL;
> > + }
> > +
> > kfree(iommu->nesting_info);
> > iommu->nesting_info = NULL;
> > }
> > @@ -2075,6 +2081,25 @@ static int vfio_iommu_type1_attach_group(void
> *iommu_data,
> > goto out_detach;
> > }
> > iommu->nesting_info = info;
> > +
> > + if (info->features & IOMMU_NESTING_FEAT_SYSWIDE_PASID) {
> > + struct vfio_mm *vmm;
> > + int sid;
> > +
> > + vmm = vfio_mm_get_from_task(current);
> > + if (IS_ERR(vmm)) {
> > + ret = PTR_ERR(vmm);
> > + goto out_detach;
> > + }
> > + iommu->vmm = vmm;
> > +
> > + sid = vfio_mm_ioasid_sid(vmm);
> > + ret = iommu_domain_set_attr(domain->domain,
> > + DOMAIN_ATTR_IOASID_SID,
> > + &sid);
> > + if (ret)
> > + goto out_detach;
> > + }
> > }
> >
> > /* Get aperture info */
> > @@ -2860,6 +2885,63 @@ static int vfio_iommu_type1_dirty_pages(struct
> vfio_iommu *iommu,
> > return -EINVAL;
> > }
> >
> > +static int vfio_iommu_type1_pasid_alloc(struct vfio_iommu *iommu,
> > + unsigned int min,
> > + unsigned int max)
> > +{
> > + int ret = -EOPNOTSUPP;
> > +
> > + mutex_lock(&iommu->lock);
> > + if (iommu->vmm)
> > + ret = vfio_pasid_alloc(iommu->vmm, min, max);
> > + mutex_unlock(&iommu->lock);
> > + return ret;
> > +}
> > +
> > +static int vfio_iommu_type1_pasid_free(struct vfio_iommu *iommu,
> > + unsigned int min,
> > + unsigned int max)
> > +{
> > + int ret = -EOPNOTSUPP;
> > +
> > + mutex_lock(&iommu->lock);
> > + if (iommu->vmm) {
> > + vfio_pasid_free_range(iommu->vmm, min, max);
> > + ret = 0;
> > + }
> > + mutex_unlock(&iommu->lock);
> > + return ret;
> > +}
> > +
> > +static int vfio_iommu_type1_pasid_request(struct vfio_iommu *iommu,
> > + unsigned long arg)
> > +{
> > + struct vfio_iommu_type1_pasid_request req;
> > + unsigned long minsz;
> > +
> > + minsz = offsetofend(struct vfio_iommu_type1_pasid_request, range);
> > +
> > + if (copy_from_user(&req, (void __user *)arg, minsz))
> > + return -EFAULT;
> > +
> > + if (req.argsz < minsz || (req.flags & ~VFIO_PASID_REQUEST_MASK))
> > + return -EINVAL;
> > +
> > + if (req.range.min > req.range.max)
> > + return -EINVAL;
> > +
> > + switch (req.flags & VFIO_PASID_REQUEST_MASK) {
> > + case VFIO_IOMMU_FLAG_ALLOC_PASID:
> > + return vfio_iommu_type1_pasid_alloc(iommu,
> > + req.range.min, req.range.max);
> > + case VFIO_IOMMU_FLAG_FREE_PASID:
> > + return vfio_iommu_type1_pasid_free(iommu,
> > + req.range.min, req.range.max);
> > + default:
> > + return -EINVAL;
> > + }
> > +}
> > +
> > static long vfio_iommu_type1_ioctl(void *iommu_data,
> > unsigned int cmd, unsigned long arg)
> > {
> > @@ -2876,6 +2958,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
> > return vfio_iommu_type1_unmap_dma(iommu, arg);
> > case VFIO_IOMMU_DIRTY_PAGES:
> > return vfio_iommu_type1_dirty_pages(iommu, arg);
> > + case VFIO_IOMMU_PASID_REQUEST:
> > + return vfio_iommu_type1_pasid_request(iommu, arg);
> > }
> >
> > return -ENOTTY;
> > diff --git a/drivers/vfio/vfio_pasid.c b/drivers/vfio/vfio_pasid.c
> > index c46b870..6f907db 100644
> > --- a/drivers/vfio/vfio_pasid.c
> > +++ b/drivers/vfio/vfio_pasid.c
> > @@ -53,6 +53,7 @@ void vfio_mm_put(struct vfio_mm *vmm)
> > {
> > kref_put_mutex(&vmm->kref, vfio_mm_release,
> &vfio_pasid.vfio_mm_lock);
> > }
> > +EXPORT_SYMBOL_GPL(vfio_mm_put);
> I think this should be belong to [5/15]
yeah, the implementation is in [5/15], but the user is in this patch, so export
it in this patch.
> >
> > static void vfio_mm_get(struct vfio_mm *vmm)
> > {
> > @@ -104,6 +105,13 @@ struct vfio_mm *vfio_mm_get_from_task(struct
> task_struct *task)
> > mmput(mm);
> > return vmm;
> > }
> > +EXPORT_SYMBOL_GPL(vfio_mm_get_from_task);
> same
the same with above.
> > +
> > +int vfio_mm_ioasid_sid(struct vfio_mm *vmm)
> extern?
> same
why need extern? as it's used in this patch, so add it in this patch.
> > +{
> > + return vmm->ioasid_sid;
> > +}
> > +EXPORT_SYMBOL_GPL(vfio_mm_ioasid_sid);
> >
> > int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
> > {
> > @@ -113,6 +121,7 @@ int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
> >
> > return (pasid == INVALID_IOASID) ? -ENOSPC : pasid;
> > }
> > +EXPORT_SYMBOL_GPL(vfio_pasid_alloc);
> same
same as above reason. :-)
> >
> > void vfio_pasid_free_range(struct vfio_mm *vmm,
> > ioasid_t min, ioasid_t max)
> > @@ -130,6 +139,7 @@ void vfio_pasid_free_range(struct vfio_mm *vmm,
> > for (; pasid <= max; pasid++)
> > ioasid_free(pasid);
> > }
> > +EXPORT_SYMBOL_GPL(vfio_pasid_free_range);
> same
same as above.
> >
> > static int __init vfio_pasid_init(void)
> > {
> > diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> > index 9da6468..35c922a 100644
> > --- a/include/linux/vfio.h
> > +++ b/include/linux/vfio.h
> > @@ -101,6 +101,7 @@ struct vfio_mm;
> > #if IS_ENABLED(CONFIG_VFIO_PASID)
> > extern struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task);
> > extern void vfio_mm_put(struct vfio_mm *vmm);
> > +int vfio_mm_ioasid_sid(struct vfio_mm *vmm);
> > extern int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max);
> > extern void vfio_pasid_free_range(struct vfio_mm *vmm,
> > ioasid_t min, ioasid_t max);
> > @@ -114,6 +115,11 @@ static inline void vfio_mm_put(struct vfio_mm *vmm)
> > {
> > }
> >
> > +static inline int vfio_mm_ioasid_sid(struct vfio_mm *vmm)
> > +{
> > + return -ENOTTY;
> > +}
> > +
> > static inline int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
> > {
> > return -ENOTTY;
> > diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> > index 3e3de9c..fe267b8e 100644
> > --- a/include/uapi/linux/vfio.h
> > +++ b/include/uapi/linux/vfio.h
> > @@ -1169,6 +1169,42 @@ struct vfio_iommu_type1_dirty_bitmap_get {
> >
> > #define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17)
> >
> > +/**
> > + * VFIO_IOMMU_PASID_REQUEST - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
> > + * struct vfio_iommu_type1_pasid_request)
> > + *
> > + * PASID (Processor Address Space ID) is a PCIe concept for tagging
> > + * address spaces in DMA requests. When system-wide PASID allocation
> > + * is required by underlying iommu driver (e.g. Intel VT-d), this
> > + * provides an interface for userspace to request pasid alloc/free
> > + * for its assigned devices. Userspace should check the availability
> > + * of this API through VFIO_IOMMU_GET_INFO.
> name the capability?
yep. will add it.
Regards,
Yi Liu
> > + *
> > + * @flags=VFIO_IOMMU_FLAG_ALLOC_PASID, allocate a single PASID within
> @range.
> > + * @flags=VFIO_IOMMU_FLAG_FREE_PASID, free the PASIDs within @range.
> > + * @range is [min, max], which means both @min and @max are inclusive.
> > + * ALLOC_PASID and FREE_PASID are mutually exclusive.
> > + *
> > + * returns: allocated PASID value on success, -errno on failure for
> > + * ALLOC_PASID;
> > + * 0 for FREE_PASID operation;
> > + */
> > +struct vfio_iommu_type1_pasid_request {
> > + __u32 argsz;
> > +#define VFIO_IOMMU_FLAG_ALLOC_PASID (1 << 0)
> > +#define VFIO_IOMMU_FLAG_FREE_PASID (1 << 1)
> > + __u32 flags;> + struct {
> > + __u32 min;
> > + __u32 max;
> > + } range;
> > +};
> > +
> > +#define VFIO_PASID_REQUEST_MASK (VFIO_IOMMU_FLAG_ALLOC_PASID | \
> > + VFIO_IOMMU_FLAG_FREE_PASID)
> > +
> > +#define VFIO_IOMMU_PASID_REQUEST _IO(VFIO_TYPE, VFIO_BASE + 18)
> > +
> > /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
> >
> > /*
> >
>
> Thanks
>
> Eric